[
  {
    "path": ".gitignore",
    "content": "__pycache__\n*.pyc\n*.swp\n*.swo\n.DS_Store\n\nvpg/outputs/*/*/a.diff\n\nbc/data/*\nbc/expert_data/*\n"
  },
  {
    "path": "LICENSE",
    "content": "MIT License\n\nCopyright (c) 2017 Daniel Seita\n\nPermission is hereby granted, free of charge, to any person obtaining a copy\nof this software and associated documentation files (the \"Software\"), to deal\nin the Software without restriction, including without limitation the rights\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\ncopies of the Software, and to permit persons to whom the Software is\nfurnished to do so, subject to the following conditions:\n\nThe above copyright notice and this permission notice shall be included in all\ncopies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\nSOFTWARE.\n"
  },
  {
    "path": "README.md",
    "content": "Note: this repository has not been updated in years and I don't have plans to do so. I recommend using rlpyt for future RL research.\n\n# Reinforcement Learning Algorithms\n\nI will use this repository to implement various reinforcement learning\nalgorithms (also imitation learning), because I'm sick of reading about them but\nnot really understanding them.  Hence, hopefully this repository will help me\nunderstand them better. I will also implement various supporting code as needed,\nsuch as for simple custom scenarios like GridWorld. Or I can use OpenAI gym.\nClick on the links to get to the appropriate algorithms. Each sub-directory will\nhave its own READMEs with results there, along with usage instructions.\n\nHere are the algorithms currently implemented or in progress:\n\n- [Q-Learning, tabular version](https://github.com/DanielTakeshi/rl_algorithms/tree/master/q_learning) (should be correct)\n- [G-Learning](https://github.com/DanielTakeshi/rl_algorithms/tree/master/g_learning) (in progress ...)\n- [Behavioral Cloning](https://github.com/DanielTakeshi/rl_algorithms/tree/master/bc) (should be correct)\n- [Natural Evolution Strategies](https://github.com/DanielTakeshi/rl_algorithms/tree/master/es) (should be correct)\n- [Deep-Q Networks](https://github.com/DanielTakeshi/rl_algorithms/tree/master/dqn) (should be correct)\n- [Vanilla Policy Gradients](https://github.com/DanielTakeshi/rl_algorithms/tree/master/vpg) (should be correct)\n- [Deep Deterministic Policy Gradients](https://github.com/DanielTakeshi/rl_algorithms/tree/master/ddpg) (in progress ...)\n- [Trust Region Policy Optimization](https://github.com/DanielTakeshi/rl_algorithms/tree/master/trpo) (in progress ...)\n\nNote: \"Vanilla Policy Gradients\" refers to the REINFORCE algorithm, also known\nas Monte Carlo Policy Gradient. Sometimes it's called an actor-critic method\nand other times it's not. Even if it's considered an actor-critic method, the\nusual way we think of actor-critic involves a TD update rather than waiting\nuntil the end of an episode to get returns.\n\n\n# Requirements\n\nRight now the code is designed for Python 2.7, but it *should* be compatible\nwith Python 3.5+, with the possible exception of if the bash scripts can't tell\nthe difference between which Python versions I'm using.\n\nIn short:\n\n- Python 2.7.x\n- Tensorflow 1.2.0\n\n\n# GPU and TensorFlow \n\n(Update 06/16/17, these are out of date ... just install with pip and preferably\nvirtualenv. It's so much easier.)\n\nI installed TensorFlow 1.0.1 from source.  For the configuration script, I used\nCUDA 8.0, cuDNN 5.1.5, and compute capability 6.1.\n\nCompiling from source means I can get faster CPU instructions. This requires\n`bazel` plus extra compiler options. I used:\n\n```\nbazel build -c opt --copt=-mavx --copt=-mavx2 --copt=-mfma --copt=-mfpmath=both --copt=-msse4.2 --config=opt --config=cuda //tensorflow/tools/pip_package:build_pip_package\n```\n\nThis resulted in ton of warning messages but I ended up with:\n\n```\nTarget //tensorflow/tools/pip_package:build_pip_package up-to-date:\n  bazel-bin/tensorflow/tools/pip_package/build_pip_package\nINFO: Elapsed time: 884.276s, Critical Path: 672.19s\n```\n\nand things seem to be working. Then run the command:\n\n```\nbazel-bin/tensorflow/tools/pip_package/build_pip_package /tmp/tensorflow_pkg\n```\n\nTo get a wheel, which we then do a pip install. But be careful due to pip on\nanaconda vs pip with default python. I use anaconda. And make sure you're not in\neither the `tensorflow` or the `bazel` directories!\n\nTrack the GPU usage with `nvidia-smi`. Unfortunately, that's only for one\ntime-step, but we can instead run:\n\n```\nwhile true; do nvidia-smi --query-gpu=utilization.gpu --format=csv >> gpu_utilization.log; sleep 10; done;\n```\n\nOr something like that. It will record the output every 10 seconds and dump it\ninto the log file. Ideally, GPU usage should be as high as possible (100% or\nclose to it).\n\n# References\n\nI have read a number of reinforcement learning paper references to help me out.\nA list of papers and summaries (for a few of them) are [in my paper notes\nrepository](https://github.com/DanielTakeshi/Paper_Notes).\n"
  },
  {
    "path": "bc/README.md",
    "content": "# Behavioral Cloning\n\n## Main Idea\n\nThis runs Behavioral Cloning (BC) on MuJoCo environments, with settings inspired\nby the NIPS 2016 [GAIL paper][1]. Specifically:\n\n- The expert is TRPO and provided from Jonathan Ho (see below).\n\n- Dataset consists of inputs (states=s) to labels (actions=a). They're\n  continuous, so minimize mean L2 loss across minibatches. It is split into 70%\n  training, 30% validation.\n\n- Expert data size is measured in terms of the number of expert rollouts we\n  collected. Note that, like the GAIL paper, I *subsample*, so the actual amount\n  of (s,a) pairs available for BC is much smaller.\n\n- The neural network (from TensorFlow) is fully connected and has two hidden\n  layers of 100 units each with hyperbolic tangent non-linearities. It's trained\n  with Adam, with a step size of 1e-3, and has a batch size of 128.\n\n- For now, I plot validation set performance (i.e. loss) without really using\n  it. If I needed to be formal and had to pick a given iteration for which to\n  choose my BC expert (because different iterations mean different weights) I'd\n  choose the one with best validation set performance. I also plot training set\n  performance just for kicks.\n\n\n## Running the Code\n\nTo run BC, there are several steps:\n\n- (If needed) generate expert data. Run\n\n  ```\n  ./bash_scripts/gen_exp_data.sh\n  ```\n\n  which will run and save expert trajectories in numpy arrays. They're not saved\n  in the repository (ask if you want my version). By default, the number of\n  trajectories is saved into the file name by default and matches the values in\n  the GAIL paper (see Table 1). No subsampling is done at this stage.\n  \n- See the bash scripts for examples of running BC. For these, I used one script\n  to run everything.\n\n- To plot the code, it's simple: `python plot_bc.py`. No command line arguments!\n\n\nIf you're interested:\n\n- The expert performance that I'm seeing is roughly similar to what's reported\n  in the GAIL paper, with the exception of the Walker environment, but I may be\n  running a newer version from Jonathan Ho. See the output in\n  `logs/gen_exp_data.text` for details.\n\n- The `bash_scripts` directory also contains a file called `demo.bash`, which\n  you can use to visualize expert trajectories, just for fun.\n\n\n# Results\n\nMany subplots have three curves, each with one standard deviation error regions.\nThe reason is that for a given BC run, each \"evaluation point\" (e.g. every 50\ntraining minibatches) I will run some \"test-time\" rollouts to see performance,\nbut I also wanted to test with different initializations, hence the different\nrandom seeds.\n\nAnt-v1, HalfCheetah-v1, Hopper-v1, and Walker2d-v1 use 4, 11, 18, and 25 expert\nrollouts since that follows the GAIL paper. Humanoid-v1 uses 80, 160, and 240\nexpert trajectories.\n\nObservations:\n\n- BC does well in Ant-v1 and HalfCheetah-v1. \n\n- Hopper-v1 seems to be difficult, surprisingly. It has a relatively small state\n  space compared to Ant (11 vs 111).\n\n- Walker2d-v1 seems to be in between, BC doesn't get going until 25 rollouts.\n\n- How am I doing so poorly on Humanoid-v1?\n\n## Ant-v1\n\n![ant](figures/Ant-v1.png?raw=true)\n\n## HalfCheetah-v1\n\n![halfcheetah](figures/HalfCheetah-v1.png?raw=true)\n\n## Hopper-v1\n\n![hopper](figures/Hopper-v1.png?raw=true)\n\n## Walker2d-v1\n\n![walker2d](figures/Walker2d-v1.png?raw=true)\n\n## Reacher-v1\n\n![reacher](figures/Reacher-v1.png?raw=true)\n\n## Humanoid-v1\n\n![humanoid](figures/Humanoid-v1.png?raw=true)\n\n\n# Original Notes from Berkeley\n\nThis started from UC Berkeley's Deep Reinforcement Learning class. Here's their\ninformation:\n\n> Dependencies: TensorFlow, MuJoCo version 1.31, OpenAI Gym\n> \n> The only file that you need to look at is `run_expert.py`, which is code to\n> load up an expert policy, run a specified number of roll-outs, and save out\n> data.\n> \n> In `experts/`, the provided expert policies are:\n> * Ant-v1.pkl\n> * HalfCheetah-v1.pkl\n> * Hopper-v1.pkl\n> * Humanoid-v1.pkl\n> * Reacher-v1.pkl\n> * Walker2d-v1.pkl\n> \n> The name of the pickle file corresponds to the name of the gym environment.\n\n[1]:https://arxiv.org/abs/1606.03476\n"
  },
  {
    "path": "bc/bash_scripts/demo.bash",
    "content": "#!/bin/bash\nset -eux\nfor e in Hopper-v1 Ant-v1 HalfCheetah-v1 Humanoid-v1 Reacher-v1 Walker2d-v1\ndo\n    python run_expert.py experts/$e.pkl $e --render --num_rollouts=1\ndone\n"
  },
  {
    "path": "bc/bash_scripts/gen_exp_data.sh",
    "content": "python run_expert.py experts/Reacher-v1.pkl Reacher-v1 --save --num_rollouts 4\npython run_expert.py experts/Reacher-v1.pkl Reacher-v1 --save --num_rollouts 11\npython run_expert.py experts/Reacher-v1.pkl Reacher-v1 --save --num_rollouts 18\n\npython run_expert.py experts/HalfCheetah-v1.pkl HalfCheetah-v1 --save --num_rollouts 4\npython run_expert.py experts/HalfCheetah-v1.pkl HalfCheetah-v1 --save --num_rollouts 11\npython run_expert.py experts/HalfCheetah-v1.pkl HalfCheetah-v1 --save --num_rollouts 18\npython run_expert.py experts/HalfCheetah-v1.pkl HalfCheetah-v1 --save --num_rollouts 25\n\npython run_expert.py experts/Hopper-v1.pkl Hopper-v1 --save --num_rollouts 4\npython run_expert.py experts/Hopper-v1.pkl Hopper-v1 --save --num_rollouts 11\npython run_expert.py experts/Hopper-v1.pkl Hopper-v1 --save --num_rollouts 18\npython run_expert.py experts/Hopper-v1.pkl Hopper-v1 --save --num_rollouts 25\n\npython run_expert.py experts/Walker2d-v1.pkl Walker2d-v1 --save --num_rollouts 4\npython run_expert.py experts/Walker2d-v1.pkl Walker2d-v1 --save --num_rollouts 11\npython run_expert.py experts/Walker2d-v1.pkl Walker2d-v1 --save --num_rollouts 18\npython run_expert.py experts/Walker2d-v1.pkl Walker2d-v1 --save --num_rollouts 25\n\npython run_expert.py experts/Ant-v1.pkl Ant-v1 --save --num_rollouts 4\npython run_expert.py experts/Ant-v1.pkl Ant-v1 --save --num_rollouts 11\npython run_expert.py experts/Ant-v1.pkl Ant-v1 --save --num_rollouts 18\npython run_expert.py experts/Ant-v1.pkl Ant-v1 --save --num_rollouts 25\n\npython run_expert.py experts/Humanoid-v1.pkl Humanoid-v1 --save --num_rollouts 80\npython run_expert.py experts/Humanoid-v1.pkl Humanoid-v1 --save --num_rollouts 160\npython run_expert.py experts/Humanoid-v1.pkl Humanoid-v1 --save --num_rollouts 240\n"
  },
  {
    "path": "bc/bash_scripts/runbc_allmujoco.sh",
    "content": "#!/bin/bash\nset -eux\nfor e in 4 11 18 25; do\n    for s in 0 1 2; do\n        python bc.py Ant-v1         $e --test_rollouts 50 --eval_freq 100 --train_iters 20001 --seed $s --subsamp_freq 20\n        python bc.py HalfCheetah-v1 $e --test_rollouts 50 --eval_freq 100 --train_iters 20001 --seed $s --subsamp_freq 20\n        python bc.py Hopper-v1      $e --test_rollouts 50 --eval_freq 100 --train_iters 20001 --seed $s --subsamp_freq 20\n        python bc.py Walker2d-v1    $e --test_rollouts 50 --eval_freq 100 --train_iters 20001 --seed $s --subsamp_freq 20 \n    done\ndone\nfor e in 4 11 18; do\n    for s in 0 1 2; do\n        python bc.py Reacher-v1     $e --test_rollouts 50 --eval_freq 100 --train_iters 20001 --seed $s --subsamp_freq 1\n    done\ndone\nfor e in 80 160 240; do\n    for s in 0 1 2; do\n        python bc.py Humanoid-v1    $e --test_rollouts 50 --eval_freq 100 --train_iters 20001 --seed $s --subsamp_freq 20\n    done\ndone\n"
  },
  {
    "path": "bc/bc.py",
    "content": "\"\"\"\n(c) June 2017 by Daniel Seita\n\nBehavioral cloning (continuous actions only).  For results, see the README(s)\nnearby.\n\n    TODO right now we assume we'll get our minibatches of data with `get_batch`\n    but this is inefficient if we decide to scale up and avoid subsampling the\n    data, where it would be better to have a list which supplies fixed,\n    pre-computed minibatches. I should fix this later.\n\n    TODO handle l2 regualrization? Though I have found that this doesn't have as\n    good an effect as I thought it would ...\n\n    TODO maybe save the weights with best validation set performance, along with\n    weights every 500 iterations or so? Then we can visualize it.\n\"\"\"\n\nimport argparse\nimport gym\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport os\nimport pickle\nimport sys\nimport tensorflow as tf\nimport tensorflow.contrib.layers as layers\nimport tf_util\nplt.style.use('seaborn-darkgrid')\nnp.set_printoptions(edgeitems=100, linewidth=100, suppress=True)\n\n\ndef get_tf_session():\n    \"\"\" Returning a session. Set options here if desired. \"\"\"\n    tf.reset_default_graph()\n    tf_config = tf.ConfigProto(inter_op_parallelism_threads=1,\n                               intra_op_parallelism_threads=1)\n    gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.5)\n    session = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))\n\n    def get_available_gpus():\n        from tensorflow.python.client import device_lib\n        local_device_protos = device_lib.list_local_devices()\n        return [x.physical_device_desc for x in local_device_protos if x.device_type == 'GPU']\n\n    print(\"AVAILABLE GPUS: \", get_available_gpus())\n    return session\n\n\ndef load_dataset(args):\n    \"\"\" Loads the dataset for BC and return training and validation splits,\n    separating the observations and actions, along with observation and action\n    shapes.\n\n    This is also where we should handle the case of varying-length expert\n    trajectories, even though these should be rare. (I kept those there so that\n    the leading dimension is the number of trajectories, in case we want to use\n    that information somehow, but right now we just mix among trajectories.) In\n    addition, it might be useful to subsample the data.\n    \"\"\"\n    # Load the numpy file and parse it.\n    str_roll = str(args.num_rollouts).zfill(3)\n    expert_data = np.load('expert_data/'+args.envname+'_'+str_roll+'.npy')\n    expert_obs = expert_data[()]['observations']\n    expert_act = expert_data[()]['actions']\n    expert_ret = expert_data[()]['returns']\n    expert_stp = expert_data[()]['steps']\n    N = expert_obs.shape[0]\n    assert N == expert_act.shape[0] == len(expert_ret) == len(expert_stp)\n    obs_shape = expert_obs.shape[2]\n    act_shape = expert_act.shape[2]\n    print(\"\\nobs_shape = {}\\nact_shape = {}\".format(obs_shape, act_shape))\n    print(\"subsampling freq = {}\".format(args.subsamp_freq))\n    print(\"expert_steps = {}\".format(expert_stp))\n    print(\"expert_returns = {}\".format(expert_ret))\n    print(\"mean(expert_returns) = {}\".format(np.mean(expert_ret))) # remember!\n    print(\"(raw) expert_obs.shape = {}\".format(expert_obs.shape))\n    print(\"(raw) expert_act.shape = {}\".format(expert_act.shape))\n\n    # Choose a different starting point to subsample for each trajectory.\n    start_indices = np.random.randint(0, args.subsamp_freq, N)\n    \n    # Subsample expert data, remove actions which were only for padding.\n    expert_obs_l = []\n    expert_act_l = []\n    for i in range(N):\n        expert_obs_l.append(\n            expert_obs[i, start_indices[i]:expert_stp[i]:args.subsamp_freq, :]\n        )\n        expert_act_l.append(\n            expert_act[i, start_indices[i]:expert_stp[i]:args.subsamp_freq, :]\n        )\n\n    # Concatenate everything together.\n    expert_obs = np.concatenate(expert_obs_l, axis=0)\n    expert_act = np.concatenate(expert_act_l, axis=0)\n    print(\"(subsampled/reshaped) expert_obs.shape = {}\".format(expert_obs.shape))\n    print(\"(subsampled/reshaped) expert_act.shape = {}\".format(expert_act.shape))\n    assert expert_obs.shape[0] == expert_act.shape[0]\n\n    # Finally, form training and validation splits.\n    num_examples = expert_obs.shape[0]\n    num_train = int(args.train_frac * num_examples)\n    shuffled_inds = np.random.permutation(num_examples)\n    train_inds, valid_inds = shuffled_inds[:num_train], shuffled_inds[num_train:]\n    expert_obs_tr  = expert_obs[train_inds]\n    expert_act_tr  = expert_act[train_inds]\n    expert_obs_val = expert_obs[valid_inds]\n    expert_act_val = expert_act[valid_inds]\n    print(\"\\n(train) expert_obs.shape = {}\".format(expert_obs_tr.shape))\n    print(\"(train) expert_act.shape = {}\".format(expert_act_tr.shape))\n    print(\"(valid) expert_obs.shape = {}\".format(expert_obs_val.shape))\n    print(\"(valid) expert_act.shape = {}\\n\".format(expert_act_val.shape))\n\n    return (expert_obs_tr, expert_act_tr, expert_obs_val, expert_act_val, \\\n            obs_shape, act_shape)\n\n\ndef policy_model(data_in, action_dim):\n    \"\"\" Create a neural network representing the BC policy. It will be trained\n    using standard supervised learning techniques.\n    \n    Parameters\n    ----------\n    data_in: [Tensor]\n        The input (a placeholder) to the network, with leading dimension\n        representing the batch size.\n    action_dim: [int]\n        Number of actions, each of which (at least for MuJoCo) is\n        continuous-valued.\n\n    Returns\n    ------- \n    out [Tensor]\n        The output tensor which represents the predicted (or desired, if\n        testing) action to take for the agent.\n    \"\"\"\n    with tf.variable_scope(\"BCNetwork\", reuse=False):\n        out = data_in\n        out = layers.fully_connected(out, num_outputs=100,\n                weights_initializer=layers.xavier_initializer(uniform=True),\n                activation_fn=tf.nn.tanh)\n        out = layers.fully_connected(out, num_outputs=100,\n                weights_initializer=layers.xavier_initializer(uniform=True),\n                activation_fn=tf.nn.tanh)\n        out = layers.fully_connected(out, num_outputs=action_dim,\n                weights_initializer=layers.xavier_initializer(uniform=True),\n                activation_fn=None)\n        return out\n\n\ndef get_batch(expert_obs, expert_act, batch_size):\n    \"\"\" \n    Obtain a minibatch of samples. Note that this is relatively inefficient, and\n    if dealing with very large datasets without subsampling, use a list of\n    samples instead. \n    \"\"\"\n    indices = np.arange(expert_obs.shape[0])\n    np.random.shuffle(indices)\n    xs = expert_obs[indices[:batch_size]]\n    ys = expert_act[indices[:batch_size]]\n    return xs, ys\n\n\ndef run_bc(session, args, log_dir):\n    \"\"\" Runs behavioral cloning on some stored data.\n\n    It roughly mirrors the experimental setup of [Ho & Ermon, NIPS 2016]. They\n    trained using ADAM (batch size 128) on 70% of the data and trained until\n    validation error on the held-out set of 30% no longer decreases. They also\n    substantially subsampled their data.\n\n    Parameters\n    ----------\n    session: [TF Session]\n        The TensorFlow session we're using.\n    args: [Arguments Namespace]\n        Namedspace representing convenient arguments from the user.\n    log_dir: [string]\n        Where we save files to. FYI, it doesn't include the ending slash.\n    \"\"\"\n    env = gym.make(args.envname)\n    (expert_obs_tr, expert_act_tr, expert_obs_val, expert_act_val, obs_shape, \\\n            act_shape) = load_dataset(args)\n\n    # Build the data and network. For now, no casting (see DQN code).\n    x = tf.placeholder(tf.float32, shape=[None,obs_shape])\n    y = tf.placeholder(tf.float32, shape=[None,act_shape])\n    policy_fn = policy_model(data_in=x, action_dim=act_shape)\n\n    # Save weights as a single vector to make saving/loading easy.\n    weights_bc = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='BCNetwork')\n    weight_vector = tf.concat([tf.reshape(w, [-1]) for w in weights_bc], axis=0)\n\n    # Construct the loss function and training information.\n    l2_loss = tf.reduce_mean(\n        tf.reduce_sum((policy_fn-y)*(policy_fn-y), axis=[1])\n    )\n    train_step = tf.train.AdamOptimizer(args.lrate).minimize(l2_loss)\n\n    all_tr_loss = []\n    all_val_loss = []\n    all_iters = [] # Makes plotting easier since these are the x-coords.\n    all_returns = [] # Will turn into an array of arrays later.\n    session.run(tf.global_variables_initializer())\n\n    for i in range(args.train_iters):\n        b_xs, b_ys = get_batch(expert_obs_tr, expert_act_tr, args.batch_size)\n        _,tr_loss = session.run([train_step, l2_loss], feed_dict={x:b_xs, y:b_ys})\n\n        if (i % args.eval_freq == 0):\n            # Only save/evaluate stuff every `args.eval_freq` iterations.\n            val_loss = session.run(l2_loss, feed_dict={x:expert_obs_val, y:expert_act_val})\n            returns = run_bc_test(args, session, policy_fn, x, env)\n            print(\"iter={}   tr_loss={:.5f}   val_loss={:.5f}\".format(\n                str(i).zfill(4), tr_loss, val_loss))\n            print(\"mean(returns): {}\\nstd(returns): {}\\n\".format(\n                    np.mean(returns), np.std(returns)))\n            all_iters.append(i)\n            all_tr_loss.append(tr_loss)\n            all_val_loss.append(val_loss)\n            all_returns.append(returns)\n\n            # Save snapshot of the current weights. We can pick out the best one\n            # by seeing the minimizing index in `all_val_loss`.\n            itr = str(i).zfill(len(str(abs(args.train_iters))))\n            weights_numpy = session.run(weight_vector) \n            np.save(log_dir+'/snapshots/weights_'+itr, weights_numpy)\n\n    # Store the results as numpy arrays so we can easily plot later.\n    np.save(log_dir +\"/iters\", np.array(all_iters))\n    np.save(log_dir +\"/tr_loss\", np.array(all_tr_loss))\n    np.save(log_dir +\"/val_loss\", np.array(all_val_loss))\n    np.save(log_dir +\"/returns\", np.array(all_returns))\n\n\ndef run_bc_test(args, session, policy_fn, x, env):\n    \"\"\" Run the agent in the world! \n    \n    Returns\n    -------\n    returns [list]\n        A list of returns, one for each of the `args.test_rollouts` rollouts.\n    \"\"\"\n    actions = []\n    observations = []\n    returns = []\n    max_steps = env.spec.timestep_limit\n\n    for rr in range(args.test_rollouts):\n        obs = env.reset()\n        done = False\n        totalr = 0\n        steps = 0\n        while not done:\n            # Take steps by expanding observation (to get shapes to match).\n            exp_obs = np.expand_dims(obs, axis=0)\n            action = np.squeeze(session.run(policy_fn, feed_dict={x:exp_obs}))\n            obs, r, done, _ = env.step(action)\n            totalr += r\n            steps += 1\n            if args.render: env.render()\n            if steps >= max_steps: break\n        returns.append(totalr)\n\n    return returns\n\n\nif __name__ == \"__main__\":\n    parser = argparse.ArgumentParser()\n    parser.add_argument('envname', type=str)\n    parser.add_argument('num_rollouts', type=str)\n    parser.add_argument('--batch_size', type=int, default=128)\n    parser.add_argument('--eval_freq', type=int, default=100)\n    parser.add_argument('--lrate', type=float, default=0.001)\n    parser.add_argument('--regu', type=float, default=0.0) # don't use now\n    parser.add_argument('--seed', type=int, default=0)\n    parser.add_argument('--subsamp_freq', type=int, default=20)\n    parser.add_argument('--test_rollouts', type=int, default=50) # GAIL paper used 50\n    parser.add_argument('--train_frac', type=float, default=0.7)\n    parser.add_argument('--train_iters', type=int, default=5001) # GAIL paper used 20001\n    parser.add_argument('--render', action='store_true') # don't use now\n    args = parser.parse_args()\n    print(\"\\nUsing the following arguments: {}\".format(args))\n\n    # Handle some logic with the log file and save the args there.\n    log_dir = \"logs/\"+args.envname+\"/numroll_\"+args.num_rollouts+\"_seed_\"+str(args.seed)\n    print(\"log_dir: {}\\n\".format(log_dir))\n    assert not os.path.exists(log_dir), \"Error: log_dir already exists!\"\n    os.makedirs(log_dir)\n    os.makedirs(log_dir+'/snapshots/')\n    with open(log_dir+'/args.pkl','w') as f:\n        pickle.dump(args, f)\n\n    # Create a session, handle random seeds (well, partly...) and run.\n    session = get_tf_session()\n    np.random.seed(args.seed)\n    tf.set_random_seed(args.seed)\n    run_bc(session, args, log_dir)\n"
  },
  {
    "path": "bc/load_policy.py",
    "content": "import pickle, tensorflow as tf, tf_util, numpy as np\n\ndef load_policy(filename):\n    with open(filename, 'rb') as f:\n        data = pickle.loads(f.read())\n\n    # assert len(data.keys()) == 2\n    nonlin_type = data['nonlin_type']\n    policy_type = [k for k in data.keys() if k != 'nonlin_type'][0]\n\n    assert policy_type == 'GaussianPolicy', 'Policy type {} not supported'.format(policy_type)\n    policy_params = data[policy_type]\n\n    assert set(policy_params.keys()) == {'logstdevs_1_Da', 'hidden', 'obsnorm', 'out'}\n\n    # Keep track of input and output dims (i.e. observation and action dims) for the user\n\n    def build_policy(obs_bo):\n        def read_layer(l):\n            assert list(l.keys()) == ['AffineLayer']\n            assert sorted(l['AffineLayer'].keys()) == ['W', 'b']\n            return l['AffineLayer']['W'].astype(np.float32), l['AffineLayer']['b'].astype(np.float32)\n\n        def apply_nonlin(x):\n            if nonlin_type == 'lrelu':\n                return tf_util.lrelu(x, leak=.01) # openai/imitation nn.py:233\n            elif nonlin_type == 'tanh':\n                return tf.tanh(x)\n            else:\n                raise NotImplementedError(nonlin_type)\n\n        # Build the policy. First, observation normalization.\n        assert list(policy_params['obsnorm'].keys()) == ['Standardizer']\n        obsnorm_mean = policy_params['obsnorm']['Standardizer']['mean_1_D']\n        obsnorm_meansq = policy_params['obsnorm']['Standardizer']['meansq_1_D']\n        obsnorm_stdev = np.sqrt(np.maximum(0, obsnorm_meansq - np.square(obsnorm_mean)))\n        print('obs', obsnorm_mean.shape, obsnorm_stdev.shape)\n        normedobs_bo = (obs_bo - obsnorm_mean) / (obsnorm_stdev + 1e-6) # 1e-6 constant from Standardizer class in nn.py:409 in openai/imitation\n\n        curr_activations_bd = normedobs_bo\n\n        # Hidden layers next\n        assert list(policy_params['hidden'].keys()) == ['FeedforwardNet']\n        layer_params = policy_params['hidden']['FeedforwardNet']\n        for layer_name in sorted(layer_params.keys()):\n            l = layer_params[layer_name]\n            W, b = read_layer(l)\n            curr_activations_bd = apply_nonlin(tf.matmul(curr_activations_bd, W) + b)\n\n        # Output layer\n        W, b = read_layer(policy_params['out'])\n        output_bo = tf.matmul(curr_activations_bd, W) + b\n        return output_bo\n\n    obs_bo = tf.placeholder(tf.float32, [None, None])\n    a_ba = build_policy(obs_bo)\n    policy_fn = tf_util.function([obs_bo], a_ba)\n    return policy_fn"
  },
  {
    "path": "bc/plot_bc.py",
    "content": "\"\"\"\n(c) April 2017 by Daniel Seita\n\nCode for plotting behavioral cloning. No need to use command line arguments,\njust run `python plot_bc.py`. Easy! Right now it generates two figures per\nenvironment, one with validation set losses and the other with returns. The\nlatter is probably more interesting.\n\"\"\"\n\nimport argparse\nimport gym\nimport matplotlib\nmatplotlib.use('Agg')\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport os\nimport pickle\nimport sys\nnp.set_printoptions(edgeitems=100, linewidth=100, suppress=True)\n\n# Some matplotlib settings.\nplt.style.use('seaborn-darkgrid')\nerror_region_alpha = 0.25\nLOGDIR = 'logs/'\nFIGDIR = 'figures/'\ntitle_size = 22\ntick_size = 17\nlegend_size = 17\nysize = 18\nxsize = 18\nlw = 3\nms = 8\ncolors = ['red', 'blue', 'yellow', 'black']\n\n\ndef plot_bc_modern(edir):\n    \"\"\" Plot the results for this particular environment. \"\"\"\n    subdirs = os.listdir(LOGDIR+edir)\n    print(\"plotting subdirs {}\".format(subdirs))\n\n    # Make it easy to count how many of each numrollouts we have.\n    R_TO_COUNT = {'4':0, '11':0, '18':0, '25':0}\n    R_TO_IJ = {'4':(0,2), '11':(1,0), '18':(1,1), '25':(1,2)}\n\n    fig,axarr = plt.subplots(2, 3, figsize=(24,15))\n    axarr[0,2].set_title(edir+\", Returns, 4 Rollouts\", fontsize=title_size)\n    axarr[1,0].set_title(edir+\", Returns, 11 Rollouts\", fontsize=title_size)\n    axarr[1,1].set_title(edir+\", Returns, 18 Rollouts\", fontsize=title_size)\n    axarr[1,2].set_title(edir+\", Returns, 25 Rollouts\", fontsize=title_size)\n\n    # Don't forget to plot the expert performance!\n    exp04 = np.mean(np.load(\"expert_data/\"+edir+\"_004.npy\")[()]['returns'])\n    exp11 = np.mean(np.load(\"expert_data/\"+edir+\"_011.npy\")[()]['returns'])\n    exp18 = np.mean(np.load(\"expert_data/\"+edir+\"_018.npy\")[()]['returns'])\n    axarr[0,2].axhline(y=exp04, color='brown', lw=lw, linestyle='--', label='expert')\n    axarr[1,0].axhline(y=exp11, color='brown', lw=lw, linestyle='--', label='expert')\n    axarr[1,1].axhline(y=exp18, color='brown', lw=lw, linestyle='--', label='expert')\n    if 'Reacher' not in edir:\n        exp25 = np.mean(np.load(\"expert_data/\"+edir+\"_025.npy\")[()]['returns'])\n        axarr[1,2].axhline(y=exp25, color='brown', lw=lw, linestyle='--', label='expert')\n\n    for dd in subdirs:\n        ddsplit = dd.split(\"_\") # `dd` is of the form `numroll_X_seed_Y`\n        numroll, seed = ddsplit[1], ddsplit[3]\n        xcoord   = np.load(LOGDIR+edir+\"/\"+dd+\"/iters.npy\")\n        tr_loss  = np.load(LOGDIR+edir+\"/\"+dd+\"/tr_loss.npy\")\n        val_loss = np.load(LOGDIR+edir+\"/\"+dd+\"/val_loss.npy\")\n        returns  = np.load(LOGDIR+edir+\"/\"+dd+\"/returns.npy\")\n        mean_ret = np.mean(returns, axis=1)\n        std_ret  = np.std(returns, axis=1)\n\n        # Playing with dictionaries\n        ijcoord = R_TO_IJ[numroll]\n        cc = colors[ R_TO_COUNT[numroll] ]\n        R_TO_COUNT[numroll] += 1\n\n        axarr[ijcoord].plot(xcoord, mean_ret, lw=lw, color=cc, label=dd)\n        axarr[ijcoord].fill_between(xcoord, \n                mean_ret-std_ret,\n                mean_ret+std_ret,\n                alpha=error_region_alpha,\n                facecolor=cc)\n\n        # Cram the training and validation losses on these subplots.\n        axarr[0,0].plot(xcoord, tr_loss, lw=lw, label=dd)\n        axarr[0,1].plot(xcoord, val_loss, lw=lw, label=dd)\n\n    boring_stuff(axarr, edir)\n    plt.tight_layout()\n    plt.savefig(FIGDIR+edir+\".png\")\n\n\ndef plot_bc_humanoid(edir):\n    \"\"\" Plots humanoid. The argument here is kind of redundant... also, I guess\n    we'll have to ignore one of the plots here since Humanoid will have 5\n    subplots. Yeah, it's a bit awkward.\n    \"\"\" \n    assert edir == \"Humanoid-v1\"\n    subdirs = os.listdir(LOGDIR+edir)\n    print(\"plotting subdirs {}\".format(subdirs))\n\n    # Make it easy to count how many of each numrollouts we have.\n    R_TO_COUNT = {'80':0, '160':0, '240':0}\n    R_TO_IJ = {'80':(1,0), '160':(1,1), '240':(1,2)}\n\n    fig,axarr = plt.subplots(2, 3, figsize=(24,15))\n    axarr[0,2].set_title(\"Empty Plot\", fontsize=title_size)\n    axarr[1,0].set_title(edir+\", Returns, 80 Rollouts\", fontsize=title_size)\n    axarr[1,1].set_title(edir+\", Returns, 160 Rollouts\", fontsize=title_size)\n    axarr[1,2].set_title(edir+\", Returns, 240 Rollouts\", fontsize=title_size)\n\n    # Plot expert performance (um, this takes a while...).\n    exp080 = np.mean(np.load(\"expert_data/\"+edir+\"_080.npy\")[()]['returns'])\n    exp160 = np.mean(np.load(\"expert_data/\"+edir+\"_160.npy\")[()]['returns'])\n    exp240 = np.mean(np.load(\"expert_data/\"+edir+\"_240.npy\")[()]['returns'])\n    axarr[1,0].axhline(y=exp080, color='brown', lw=lw, linestyle='--', label='expert')\n    axarr[1,1].axhline(y=exp160, color='brown', lw=lw, linestyle='--', label='expert')\n    axarr[1,2].axhline(y=exp240, color='brown', lw=lw, linestyle='--', label='expert')\n\n    for dd in subdirs:\n        ddsplit = dd.split(\"_\") # `dd` is of the form `numroll_X_seed_Y`\n        numroll, seed = ddsplit[1], ddsplit[3]\n        xcoord   = np.load(LOGDIR+edir+\"/\"+dd+\"/iters.npy\")\n        tr_loss  = np.load(LOGDIR+edir+\"/\"+dd+\"/tr_loss.npy\")\n        val_loss = np.load(LOGDIR+edir+\"/\"+dd+\"/val_loss.npy\")\n        returns  = np.load(LOGDIR+edir+\"/\"+dd+\"/returns.npy\")\n        mean_ret = np.mean(returns, axis=1)\n        std_ret  = np.std(returns, axis=1)\n\n        # Playing with dictionaries\n        ijcoord = R_TO_IJ[numroll]\n        cc = colors[ R_TO_COUNT[numroll] ]\n        R_TO_COUNT[numroll] += 1\n\n        axarr[ijcoord].plot(xcoord, mean_ret, lw=lw, color=cc, label=dd)\n        axarr[ijcoord].fill_between(xcoord, \n                mean_ret-std_ret,\n                mean_ret+std_ret,\n                alpha=error_region_alpha,\n                facecolor=cc)\n\n        # Cram the training and validation losses on these subplots.\n        axarr[0,0].plot(xcoord, tr_loss, lw=lw, label=dd)\n        axarr[0,1].plot(xcoord, val_loss, lw=lw, label=dd)\n\n    boring_stuff(axarr, edir)\n    plt.tight_layout()\n    plt.savefig(FIGDIR+edir+\".png\")\n\n\ndef boring_stuff(axarr, edir):\n    \"\"\" Axes, titles, legends, etc. Yeah yeah ... \"\"\"\n    for i in range(2):\n        for j in range(3):\n            if i == 0 and j == 0:\n                axarr[i,j].set_ylabel(\"Loss Training MBs\", fontsize=ysize)\n            if i == 0 and j == 1:\n                axarr[i,j].set_ylabel(\"Loss Validation Set\", fontsize=ysize)\n            else:\n                axarr[i,j].set_ylabel(\"Average Return\", fontsize=ysize)\n            axarr[i,j].set_xlabel(\"Training Minibatches\", fontsize=xsize)\n            axarr[i,j].tick_params(axis='x', labelsize=tick_size)\n            axarr[i,j].tick_params(axis='y', labelsize=tick_size)\n            axarr[i,j].legend(loc=\"best\", prop={'size':legend_size})\n            axarr[i,j].legend(loc=\"best\", prop={'size':legend_size})\n    axarr[0,0].set_title(edir+\", Training Losses\", fontsize=title_size)\n    axarr[0,1].set_title(edir+\", Validation Losses\", fontsize=title_size)\n    axarr[0,0].set_yscale('log')\n    axarr[0,1].set_yscale('log')\n\n\ndef plot_bc(e):\n    \"\"\" Split into cases. It makes things easier for me. \"\"\"\n    env_to_method = {'Ant-v1': plot_bc_modern, \n                     'HalfCheetah-v1': plot_bc_modern, \n                     'Hopper-v1': plot_bc_modern,\n                     'Walker2d-v1': plot_bc_modern,\n                     'Reacher-v1': plot_bc_modern,\n                     'Humanoid-v1': plot_bc_humanoid}\n    env_to_method[e](e)\n\n\nif __name__ == \"__main__\":\n    env_dirs = [e for e in os.listdir(LOGDIR) if \"text\" not in e]\n    print(\"Plotting with one figure per env_dirs = {}\".format(env_dirs))\n    for e in env_dirs:\n        plot_bc(e)\n"
  },
  {
    "path": "bc/random_logs/gen_exp_data.text",
    "content": "loading and building expert policy\n('obs', (1, 11), (1, 11))\nloaded and built\n('roll/traj', 0)\n('roll/traj', 1)\n('roll/traj', 2)\n('roll/traj', 3)\n('steps', [50, 50, 50, 50])\n('returns', [-5.0986563080722789, -2.3470820413705882, -3.4806488084021563, -5.3923959304937243])\n('mean return', -4.0796957720846869)\n('std of return', 1.2371610530104316)\nobs.shape = (4, 50, 11)\nact.shape = (4, 50, 2)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 11), (1, 11))\nloaded and built\n('roll/traj', 0)\n('roll/traj', 1)\n('roll/traj', 2)\n('roll/traj', 3)\n('roll/traj', 4)\n('roll/traj', 5)\n('roll/traj', 6)\n('roll/traj', 7)\n('roll/traj', 8)\n('roll/traj', 9)\n('roll/traj', 10)\n('steps', [50, 50, 50, 50, 50, 50, 50, 50, 50, 50, 50])\n('returns', [-6.0676632781974975, -4.8437408266431676, -2.7646205850154639, -4.8883500259847468, -5.5523827036728743, -3.5066640100964652, -2.8579657682413164, -3.5256961737336221, -1.9851548296485364, -5.7610544616077641, -4.4387894971172894])\n('mean return', -4.1992801963598856)\n('std of return', 1.2933939982797207)\nobs.shape = (11, 50, 11)\nact.shape = (11, 50, 2)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 11), (1, 11))\nloaded and built\n('roll/traj', 0)\n('roll/traj', 1)\n('roll/traj', 2)\n('roll/traj', 3)\n('roll/traj', 4)\n('roll/traj', 5)\n('roll/traj', 6)\n('roll/traj', 7)\n('roll/traj', 8)\n('roll/traj', 9)\n('roll/traj', 10)\n('roll/traj', 11)\n('roll/traj', 12)\n('roll/traj', 13)\n('roll/traj', 14)\n('roll/traj', 15)\n('roll/traj', 16)\n('roll/traj', 17)\n('steps', [50, 50, 50, 50, 50, 50, 50, 50, 50, 50, 50, 50, 50, 50, 50, 50, 50, 50])\n('returns', [-7.0167051921724175, -2.2971802003578921, -3.0596530187565367, -4.6337475094076872, -4.3389105427312291, -2.0122997124407345, -6.936080880634159, -3.8789676786284204, -3.0374973076118006, -5.8012000292179202, -5.282670215008328, -1.4478122702743865, -1.6729209302580386, -2.0049694364017943, -3.4791679686749157, -4.537885362741525, -6.7110718543266392, -2.6161470377728997])\n('mean return', -3.9313826193009627)\n('std of return', 1.7865687858709369)\nobs.shape = (18, 50, 11)\nact.shape = (18, 50, 2)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 17), (1, 17))\nloaded and built\n('roll/traj', 0)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 1)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 2)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 3)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('steps', [1000, 1000, 1000, 1000])\n('returns', [4142.2707122049451, 4073.2926100930354, 4160.2641919997595, 4137.3904574971248])\n('mean return', 4128.304492948716)\n('std of return', 32.8836572283574)\nobs.shape = (4, 1000, 17)\nact.shape = (4, 1000, 6)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 17), (1, 17))\nloaded and built\n('roll/traj', 0)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 1)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 2)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 3)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 4)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 5)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 6)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 7)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 8)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 9)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 10)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('steps', [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000])\n('returns', [4163.926640414601, 4082.5260763172073, 4088.7890907004175, 4261.2822528361958, 4258.7193259277701, 4003.5642815073606, 4014.550963767033, 4236.2386061269835, 4110.2043680589713, 3979.6921007858841, 4082.8862028719918])\n('mean return', 4116.5799917558552)\n('std of return', 96.639402441900685)\nobs.shape = (11, 1000, 17)\nact.shape = (11, 1000, 6)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 17), (1, 17))\nloaded and built\n('roll/traj', 0)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 1)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 2)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 3)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 4)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 5)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 6)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 7)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 8)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 9)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 10)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 11)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 12)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 13)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 14)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 15)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 16)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 17)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('steps', [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000])\n('returns', [4086.4099200096416, 4131.2709022133558, 4093.6069841238532, 4224.1550004107994, 4040.8835600400148, 4205.8018352881491, 4121.3078008257926, 4059.7018278076703, 4068.9727601843761, 4158.2791893541871, 4133.9336557521283, 4248.6852156813147, 4117.3499451442194, 4105.1856269166738, 4118.7413080467604, 3999.8364477747714, 4070.2510751567406, 3998.4489992439239])\n('mean return', 4110.156780776354)\n('std of return', 67.104887652297236)\nobs.shape = (18, 1000, 17)\nact.shape = (18, 1000, 6)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 17), (1, 17))\nloaded and built\n('roll/traj', 0)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 1)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 2)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 3)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 4)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 5)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 6)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 7)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 8)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 9)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 10)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 11)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 12)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 13)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 14)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 15)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 16)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 17)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 18)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 19)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 20)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 21)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 22)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 23)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 24)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('steps', [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000])\n('returns', [4277.0649177373989, 4134.9545756917705, 4137.2293138303303, 4303.8329029398674, 4129.3451831595994, 4141.294405302373, 4113.7214986254858, 4160.1223028192289, 4097.0754966253426, 4027.5727894938377, 4076.0161230017616, 4066.6420436003768, 4110.8062524027519, 3910.0827144736527, 4301.7383387989348, 4050.0758406333521, 4244.5068451702218, 4211.9442440870207, 4198.5772637205318, 4113.6755909929007, 4058.1256463993295, 4174.9359832628352, 4110.7459681292185, 4143.0735610903803, 4032.5424608180847])\n('mean return', 4133.0280905122636)\n('std of return', 89.024141578474556)\nobs.shape = (25, 1000, 17)\nact.shape = (25, 1000, 6)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 11), (1, 11))\nloaded and built\n('roll/traj', 0)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 1)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 2)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 3)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('steps', [1000, 1000, 1000, 1000])\n('returns', [3768.6945100631256, 3780.2323839436513, 3783.3528713417622, 3776.522165486092])\n('mean return', 3777.200482708658)\n('std of return', 5.4739381594168464)\nobs.shape = (4, 1000, 11)\nact.shape = (4, 1000, 3)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 11), (1, 11))\nloaded and built\n('roll/traj', 0)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 1)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 2)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 3)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 4)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 5)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 6)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 7)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 8)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 9)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 10)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('steps', [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000])\n('returns', [3776.8642751689367, 3781.2504298398662, 3780.2410426724359, 3775.3710552957577, 3779.3902980707512, 3773.8634184348703, 3770.8866723075585, 3780.4207844762936, 3781.523831445847, 3774.5681184694013, 3779.319841231219])\n('mean return', 3777.6090697648124)\n('std of return', 3.3513734023594219)\nobs.shape = (11, 1000, 11)\nact.shape = (11, 1000, 3)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 11), (1, 11))\nloaded and built\n('roll/traj', 0)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 1)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 2)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 3)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 4)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 5)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 6)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 7)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 8)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 9)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 10)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 11)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 12)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 13)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 14)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 15)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 16)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 17)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('steps', [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000])\n('returns', [3779.7050891800823, 3781.8261053421129, 3777.0348874624683, 3780.7564369429952, 3783.8023742794289, 3778.8540765735338, 3778.2838509060907, 3772.0179836318312, 3776.0436511846556, 3777.2671771759328, 3769.7932782467242, 3778.1612858500016, 3774.5197732402466, 3777.4526753302625, 3782.1303038320079, 3774.1603254054885, 3775.4472428566828, 3780.9678196906061])\n('mean return', 3777.6791298406192)\n('std of return', 3.5415301661767842)\nobs.shape = (18, 1000, 11)\nact.shape = (18, 1000, 3)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 11), (1, 11))\nloaded and built\n('roll/traj', 0)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 1)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 2)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 3)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 4)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 5)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 6)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 7)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 8)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 9)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 10)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 11)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 12)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 13)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 14)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 15)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 16)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 17)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 18)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 19)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 20)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 21)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 22)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 23)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 24)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('steps', [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000])\n('returns', [3778.8392263167784, 3779.5006762211756, 3775.2079612199959, 3775.2461797134188, 3786.7071619918361, 3774.4111189507835, 3781.201699112346, 3775.7413417770244, 3784.7917817859939, 3775.7521896648682, 3782.0005480505479, 3774.0474578427702, 3777.5763692084424, 3778.0439539881991, 3779.5541702189857, 3778.9263420042721, 3770.50841808619, 3770.0953559770523, 3776.9041194485176, 3778.243240343334, 3775.3263028992428, 3779.0318634723531, 3775.5486034283458, 3777.3872833124879, 3773.873717042653])\n('mean return', 3777.3786832831042)\n('std of return', 3.7442553033205863)\nobs.shape = (25, 1000, 11)\nact.shape = (25, 1000, 3)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 17), (1, 17))\nloaded and built\n('roll/traj', 0)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 1)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 2)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 3)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('steps', [1000, 1000, 1000, 1000])\n('returns', [5547.48969243587, 5540.1468480510594, 5564.1321310009662, 5581.989894252667])\n('mean return', 5558.4396414351404)\n('std of return', 16.136499915608695)\nobs.shape = (4, 1000, 17)\nact.shape = (4, 1000, 6)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 17), (1, 17))\nloaded and built\n('roll/traj', 0)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 1)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 2)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 3)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 4)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 5)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 6)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 7)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 8)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 9)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 10)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('steps', [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000])\n('returns', [5502.1118374247135, 5578.4542887283278, 5512.2398724981667, 5480.4346126756691, 5449.5133369384566, 5502.7943665881003, 5480.9276296636272, 5569.665719912703, 5327.7553945147201, 5572.5422903562821, 5457.7194853879455])\n('mean return', 5494.0144395171556)\n('std of return', 67.950561745997945)\nobs.shape = (11, 1000, 17)\nact.shape = (11, 1000, 6)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 17), (1, 17))\nloaded and built\n('roll/traj', 0)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 1)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 2)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 3)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 4)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 5)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 6)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 7)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 8)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 9)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 10)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 11)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 12)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 13)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 14)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 15)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 16)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 17)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('steps', [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000])\n('returns', [5585.8651523527433, 5545.8725858595817, 5593.3858841511465, 5541.4536733079985, 5536.8433392198067, 5548.443185949196, 5498.6548050012489, 5475.8332938827907, 5549.4836474238609, 5459.2497362763906, 5459.0740379511835, 5528.9377877374009, 5556.5587139897398, 5604.7437566384324, 5514.978407911135, 5558.1672712935715, 5537.4998013342065, 5471.741539720425])\n('mean return', 5531.4881455556042)\n('std of return', 42.793853572241282)\nobs.shape = (18, 1000, 17)\nact.shape = (18, 1000, 6)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 17), (1, 17))\nloaded and built\n('roll/traj', 0)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 1)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 2)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 3)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 4)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 5)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 6)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 7)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 8)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 9)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 10)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 11)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 12)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 13)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 14)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 15)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 16)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 17)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 18)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 19)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 20)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 21)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 22)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 23)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 24)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('steps', [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000])\n('returns', [5578.8211167348663, 5426.9564890547936, 5495.0790952607813, 5543.7290426113759, 5592.7433886393574, 5575.0766246791163, 5600.9145321887609, 5453.7858257194703, 5537.535331383041, 5528.1267955137027, 5535.8466728732074, 5583.1063825847186, 5560.6501884998252, 5544.3170077259037, 5485.541927125917, 5485.1008470458091, 5497.1258420310323, 5569.4957143113088, 5564.0545535147003, 5531.2521617385428, 5543.0294088290084, 5527.3037651829809, 5541.4369527234321, 5575.584682356186, 5532.5198507543264])\n('mean return', 5536.3653679632871)\n('std of return', 42.16551288781001)\nobs.shape = (25, 1000, 17)\nact.shape = (25, 1000, 6)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 111), (1, 111))\nloaded and built\n('roll/traj', 0)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 1)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 2)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 3)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('steps', [1000, 1000, 1000, 1000])\n('returns', [4681.2816282568092, 4787.1411375950993, 4962.6022230934659, 4718.8344067219441])\n('mean return', 4787.4648489168294)\n('std of return', 108.00256775663604)\nobs.shape = (4, 1000, 111)\nact.shape = (4, 1000, 8)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 111), (1, 111))\nloaded and built\n('roll/traj', 0)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 1)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 2)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 3)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 4)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 5)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 6)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 7)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 8)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 9)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 10)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('steps', [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000])\n('returns', [4970.2446233142127, 4791.8262870918743, 4990.8731983221924, 4874.367844853743, 4782.723353789389, 4945.6210534642532, 4865.8945243349517, 4671.9618293821068, 4867.5339908714595, 4704.239325228632, 4938.5563507509096])\n('mean return', 4854.8947619457931)\n('std of return', 101.36973550237347)\nobs.shape = (11, 1000, 111)\nact.shape = (11, 1000, 8)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 111), (1, 111))\nloaded and built\n('roll/traj', 0)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 1)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 2)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 3)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 4)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 5)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 6)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 7)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 8)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 9)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 10)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 11)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 12)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 13)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 14)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 15)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 16)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 17)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('steps', [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000])\n('returns', [4848.5062792733324, 4807.5472169657733, 5071.3916076107216, 4772.4505171213505, 4783.1801074056393, 4963.8292362281081, 4852.7933288258428, 4622.0828740587067, 4818.8940558568593, 4794.9563490573546, 4886.5164229950242, 4845.0225230289898, 4921.775360975862, 4793.3807631300815, 4778.7836096652518, 4896.3028634806333, 4806.808013490021, 4604.2827672429912])\n('mean return', 4826.0279942451407)\n('std of return', 105.15493988748189)\nobs.shape = (18, 1000, 111)\nact.shape = (18, 1000, 8)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 111), (1, 111))\nloaded and built\n('roll/traj', 0)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 1)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 2)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 3)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 4)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n('roll/traj', 5)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 6)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 7)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 8)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 9)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 10)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 11)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 12)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 13)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 14)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 15)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 16)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 17)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 18)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 19)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 20)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 21)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 22)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 23)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 24)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('steps', [1000, 1000, 1000, 1000, 848, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000])\n('returns', [4754.9337197919212, 4670.2130539203708, 4819.8898310669547, 4791.8539952710335, 4064.1610110578895, 4846.4238471685767, 4628.0066176373239, 4950.5587981938552, 4689.3336871789252, 4954.1424188340579, 4885.0033215638896, 4884.1785356975643, 4956.1598758246191, 4878.141685788979, 4668.1071285208754, 5037.0403488927232, 4775.9386244523239, 4720.482841645392, 4917.8331223202549, 4637.6262947721079, 4864.5559085830791, 4765.1690928682719, 4984.9211936248039, 4695.7990112358748, 4797.3908402291418])\n('mean return', 4785.5145922456322)\n('std of return', 185.68178387438161)\nobs.shape = (25, 1000, 111)\nact.shape = (25, 1000, 8)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 376), (1, 376))\nloaded and built\n('roll/traj', 0)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 1)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 2)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 3)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 4)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 5)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 6)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 7)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 8)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 9)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 10)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 11)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 12)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 13)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 14)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 15)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 16)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 17)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 18)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 19)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 20)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 21)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 22)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 23)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 24)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 25)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 26)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 27)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 28)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 29)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 30)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 31)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 32)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 33)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 34)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 35)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 36)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 37)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 38)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 39)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 40)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 41)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 42)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 43)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 44)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 45)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 46)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 47)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 48)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 49)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 50)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 51)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 52)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 53)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 54)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 55)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 56)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 57)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 58)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 59)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 60)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 61)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 62)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 63)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 64)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 65)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 66)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 67)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 68)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 69)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 70)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 71)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 72)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 73)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 74)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 75)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 76)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 77)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 78)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 79)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('steps', [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000])\n('returns', [10329.628439115793, 10398.40769333656, 10363.937395680477, 10427.772885501496, 10397.027566319715, 10480.217506670058, 10479.585647890968, 10424.793655049612, 10373.86341372582, 10451.954902520636, 10305.228173137471, 10387.087426785178, 10453.408417209403, 10459.609235675824, 10356.678362034181, 10398.510234478614, 10515.361236604076, 10436.751276740513, 10498.396235392102, 10370.772157990363, 10430.672213922286, 10426.891222992064, 10394.551522552107, 10445.06614354315, 10435.721466817618, 10386.238617037665, 10471.072341941242, 10402.245401001908, 10418.328439772547, 10379.46465504614, 10419.762363070555, 10392.181917234415, 10413.336573901424, 10402.971022743775, 10425.173517290992, 10397.79028895028, 10452.611322512847, 10386.092300526794, 10419.523884184186, 10301.980675007637, 10410.288969989273, 10385.581664314219, 10435.416096147484, 10429.411956568458, 10469.366651914606, 10498.987284536122, 10335.452597636722, 10361.801676501475, 10415.437900649116, 10359.093623262546, 10434.897488733488, 10489.523672114101, 10490.177397527659, 10388.55547638126, 10401.568538908834, 10439.716990475352, 10456.447774649503, 10436.715874399713, 10445.687900447212, 10459.767461022309, 10450.912812774666, 10400.022412165528, 10380.876547571568, 10404.604527280735, 10427.798994291225, 10465.62206122202, 10410.584622564747, 10379.356959054881, 10378.237741675022, 10351.699958008387, 10430.091076781926, 10447.880494902356, 10420.966302199247, 10376.269492971323, 10415.708895867358, 10387.617975152678, 10429.483388870894, 10468.32437980919, 10370.386539478415, 10366.425967282034])\n('mean return', 10415.217948725152)\n('std of return', 43.377480472278329)\nobs.shape = (80, 1000, 376)\nact.shape = (80, 1000, 17)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 376), (1, 376))\nloaded and built\n('roll/traj', 0)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 1)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 2)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 3)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 4)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 5)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 6)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 7)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 8)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 9)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 10)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 11)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 12)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 13)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 14)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 15)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 16)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 17)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 18)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 19)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 20)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 21)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 22)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 23)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 24)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 25)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 26)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 27)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 28)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 29)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 30)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 31)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 32)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 33)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 34)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 35)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 36)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 37)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 38)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 39)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 40)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 41)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 42)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 43)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 44)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 45)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 46)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 47)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 48)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 49)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 50)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 51)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 52)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 53)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 54)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 55)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 56)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 57)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 58)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 59)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 60)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 61)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 62)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 63)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 64)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 65)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 66)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 67)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 68)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 69)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 70)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 71)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 72)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 73)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 74)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 75)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 76)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 77)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 78)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 79)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 80)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 81)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 82)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 83)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 84)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 85)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 86)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 87)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 88)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 89)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 90)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 91)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 92)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 93)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 94)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 95)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 96)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 97)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 98)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 99)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 100)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 101)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 102)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 103)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 104)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 105)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 106)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 107)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 108)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 109)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 110)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 111)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 112)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 113)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 114)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 115)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 116)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 117)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 118)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 119)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 120)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 121)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 122)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 123)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 124)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 125)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 126)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 127)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 128)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 129)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 130)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 131)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 132)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 133)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 134)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 135)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 136)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 137)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 138)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 139)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 140)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 141)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 142)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 143)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 144)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 145)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 146)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 147)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 148)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 149)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 150)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 151)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 152)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 153)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 154)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 155)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 156)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 157)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 158)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 159)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('steps', [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000])\n('returns', [10348.039897018045, 10412.120600025346, 10414.600220855498, 10400.288598306544, 10425.754906339394, 10421.076194429483, 10400.632701710943, 10416.669621179697, 10276.638537743353, 10451.765342424274, 10325.61237757394, 10403.698634306571, 10440.485902785687, 10396.395646652431, 10381.090569354996, 10383.448626388783, 10409.214568325104, 10456.129785239242, 10396.076454384205, 10446.146525160382, 10444.714613069202, 10481.364722831169, 10482.614076759115, 10359.848966341915, 10448.104631147276, 10429.533199705202, 10349.853354558692, 10380.280019446729, 10423.117348283296, 10413.211546436249, 10346.124737317437, 10510.825034017083, 10486.313543964088, 10396.845288704506, 10401.494402286997, 10445.340512404808, 10434.403029474815, 10388.302267239604, 10412.754505634748, 10376.949443825182, 10393.018126891815, 10433.213791286351, 10421.152012774721, 10186.344624600346, 10344.49120008269, 10343.996541394808, 10413.359454476365, 10447.690701808311, 10328.198282106212, 10444.002274656699, 10379.84969917434, 10321.388161571269, 10433.82289639493, 10412.841410261621, 10371.889775892891, 10427.675977073088, 10390.497618321489, 10498.835163041722, 10394.654046401409, 10495.03278044463, 10427.264469624544, 10516.451735081086, 10440.677304396846, 10451.095179872322, 10339.01297731753, 10416.064377272531, 10385.277856504987, 10446.098255812693, 10477.363623988707, 10337.205649890591, 10433.560924742498, 10398.504043972673, 10444.008071255814, 10457.594456360755, 10486.141167680124, 10380.752306783172, 10341.330094617224, 10367.67561648005, 10440.95883467388, 10306.306715833394, 10445.656606537519, 10454.775640870996, 10290.568617039909, 10389.119039196186, 10325.744217813219, 10237.367014540105, 10261.826908243245, 10360.634578658341, 10471.424822712983, 10381.783356597498, 10433.17492549642, 10485.087354167277, 10354.714589113271, 10421.06611572363, 10424.774213241597, 10467.833384009717, 10371.979916305236, 10466.426261599292, 10409.449391913096, 10380.835049441102, 10410.073548892695, 10367.193723856519, 10379.088885072279, 10467.696826160809, 10464.128752202789, 10386.74244888222, 10293.183884741829, 10483.476608244462, 10458.08024040571, 10460.411334963712, 10433.210048462861, 10441.604706421725, 10389.483742197081, 10431.16297873758, 10440.07447219877, 10396.946535618768, 10418.482020834617, 10322.581761528521, 10414.728150806106, 10460.013436823698, 10415.143800597814, 10470.79940001007, 10548.32062854944, 10470.238487157361, 10366.476299413807, 10344.317240008371, 10305.634106269641, 10389.172160090457, 10354.519992588741, 10428.600682833614, 10319.42771561299, 10435.137602835264, 10421.888519098182, 10299.99848375721, 10415.667749808155, 10398.732209077052, 10469.894975191943, 10410.759600796177, 10453.668437671595, 10341.595393798012, 10393.504827407303, 10425.195590290434, 10428.973097295844, 10400.902230025302, 10405.970511773929, 10291.347476732706, 10356.527889358571, 10450.119402821079, 10455.911873713219, 10407.519825571921, 10390.519102863, 10331.557411498277, 10315.628237308545, 10360.292187022018, 10448.939786697532, 10376.699852817559, 10449.694663498973, 10326.637755602909, 10388.850561283136, 10425.00257666954])\n('mean return', 10403.972335063499)\n('std of return', 56.536074597213009)\nobs.shape = (160, 1000, 376)\nact.shape = (160, 1000, 17)\nexpert data has been saved.\nloading and building expert policy\n('obs', (1, 376), (1, 376))\nloaded and built\n('roll/traj', 0)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 1)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 2)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 3)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 4)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 5)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 6)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 7)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 8)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 9)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 10)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 11)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 12)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 13)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 14)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 15)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 16)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 17)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 18)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 19)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 20)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 21)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 22)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 23)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 24)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 25)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 26)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 27)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 28)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 29)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 30)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 31)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 32)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 33)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 34)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 35)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 36)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 37)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 38)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 39)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 40)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 41)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 42)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 43)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 44)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 45)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 46)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 47)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 48)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 49)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 50)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 51)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 52)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 53)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 54)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 55)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 56)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 57)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 58)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 59)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 60)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 61)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 62)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 63)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 64)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 65)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 66)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 67)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 68)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 69)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 70)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 71)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 72)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 73)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 74)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 75)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 76)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 77)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 78)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 79)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 80)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 81)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 82)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 83)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 84)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 85)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 86)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 87)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 88)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 89)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 90)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 91)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 92)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 93)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 94)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 95)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 96)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 97)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 98)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 99)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 100)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 101)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 102)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 103)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 104)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 105)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 106)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 107)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 108)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 109)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 110)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 111)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 112)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 113)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 114)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 115)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 116)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 117)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 118)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 119)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 120)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 121)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 122)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 123)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 124)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 125)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 126)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 127)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 128)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 129)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 130)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 131)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 132)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 133)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 134)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 135)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 136)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 137)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 138)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 139)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 140)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 141)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 142)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 143)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 144)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 145)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 146)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 147)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 148)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 149)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 150)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 151)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 152)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 153)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 154)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 155)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 156)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 157)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 158)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 159)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 160)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 161)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 162)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 163)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 164)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 165)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 166)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 167)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 168)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 169)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 170)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 171)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 172)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 173)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 174)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 175)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 176)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 177)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 178)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 179)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 180)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 181)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 182)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 183)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 184)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 185)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 186)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 187)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 188)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 189)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 190)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 191)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 192)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 193)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 194)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 195)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 196)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 197)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 198)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 199)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 200)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 201)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 202)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 203)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 204)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 205)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 206)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 207)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 208)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 209)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 210)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 211)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 212)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 213)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 214)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 215)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 216)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 217)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 218)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 219)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 220)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 221)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 222)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 223)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 224)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 225)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 226)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 227)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 228)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 229)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 230)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 231)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 232)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 233)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 234)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 235)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 236)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 237)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 238)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('roll/traj', 239)\n100/1000\n200/1000\n300/1000\n400/1000\n500/1000\n600/1000\n700/1000\n800/1000\n900/1000\n1000/1000\n('steps', [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000])\n('returns', [10373.442886251316, 10504.355777991737, 10432.946322763684, 10375.656078906675, 10388.623410275639, 10462.871400254879, 10447.049903637855, 10468.962907885809, 10386.398832025012, 10413.565351255793, 10414.86442966, 10387.104676430643, 10291.832182996131, 10371.844971701123, 10313.509324820825, 10389.558033043339, 10462.230554781279, 10397.30590295671, 10369.880983921739, 10340.822300346397, 10353.539620925292, 10389.980886577376, 10395.351222058045, 10329.003792956428, 10396.362315753431, 10510.120904021258, 10430.37977017577, 10393.3237347747, 10405.577042784973, 10437.507940315096, 10389.40984919135, 10441.886814922711, 10354.146524368323, 10420.851929535253, 10409.924515427872, 10374.921911984509, 10444.903227638719, 10352.652058183083, 10356.484338998533, 10342.600534301917, 10432.670817777791, 10492.151961155751, 10402.912114518849, 10419.429942828756, 10317.839698843383, 10382.492006727474, 10446.530503288828, 10374.570492862162, 10397.208863404074, 10266.706805183734, 10416.179858245298, 10434.742134793834, 10373.126922936233, 10406.674622503893, 10418.229651572323, 10402.270458181169, 10368.692180294076, 10409.498573028788, 10363.260951873779, 10353.812669988863, 10430.942618772633, 10398.42252303828, 10416.788493524968, 10472.738858972663, 10349.481925487231, 10399.001205951523, 10344.758339293989, 10217.136648804568, 10295.514656104158, 10490.128550579466, 10374.027586273838, 10399.312488312025, 10430.910978172271, 10377.93738789266, 10374.857693934313, 10402.432197219552, 10450.470080731284, 10454.213608206494, 10441.299822640272, 10413.161081259577, 10273.410406100049, 10371.828428763667, 10437.77529662195, 10488.507151865075, 10345.316789336943, 10306.638089431763, 10420.653871506474, 10469.759091979537, 10329.174792354786, 10456.360935675255, 10447.272201189575, 10490.20181057477, 10450.01344325538, 10501.668125669008, 10274.301563853547, 10387.431930814124, 10353.122390058918, 10386.159658583991, 10311.433527062274, 10356.19524367908, 10439.575750982758, 10349.103374986189, 10430.670137365511, 10353.721451433979, 10379.745945867631, 10425.619261666705, 10376.787489417442, 10392.128358818254, 10290.753092985407, 10357.052935577196, 10380.63342076658, 10383.900730398709, 10321.091692639871, 10440.031320293632, 10277.768010621834, 10409.57389326697, 10209.579904225844, 10350.043036005216, 10453.173106207145, 10464.746220207116, 10358.489480404436, 10459.021927889535, 10425.247778259683, 10449.055511809527, 10396.232434623043, 10306.409812089978, 10423.704723896422, 10415.832776541676, 10466.721677830237, 10447.8303467038, 10393.301272103035, 10421.294879923726, 10411.417974321503, 10458.618584668042, 10419.387716003352, 10543.295254667795, 10384.609154498008, 10427.159882637794, 10360.761322763399, 10424.460520418381, 10435.096285852271, 10330.872645338357, 10347.01047740803, 10384.485490797815, 10455.289491820226, 10428.051036607136, 10437.291819751952, 10406.218134566681, 10410.740110757266, 10427.780958498059, 10377.37595987856, 10386.781010159781, 10405.597813276039, 10444.473158066465, 10357.521564866434, 10398.087978429083, 10449.471814554323, 10491.411052286205, 10394.943343575726, 10442.424813246422, 10351.247272789924, 10392.472367642747, 10459.498986757979, 10405.078737359368, 10431.369573219452, 10409.384507045541, 10429.920399449567, 10430.139483486206, 10400.166309104887, 10385.279828352872, 10323.38182495301, 10402.594885043121, 10395.234063557686, 10401.663069061864, 10354.731792675035, 10416.939236951337, 10390.76726513448, 10365.781944224063, 10399.47368367667, 10406.028495274742, 10303.548008764921, 10381.858554844968, 10391.171115721796, 10434.057022919505, 10526.400373624814, 10351.899858578001, 10331.53404736148, 10344.478510266285, 10360.782187448216, 10523.333948085099, 10391.527307762213, 10427.908910140995, 10427.087703234074, 10377.211022652822, 10422.78745307182, 10494.775008519529, 10441.8424524811, 10251.49765472824, 10445.902117181255, 10410.218595788947, 10459.329571664388, 10414.940464319339, 10430.810372776283, 10381.978232198366, 10456.979742591213, 10418.619527943896, 10452.278191124849, 10262.092508010348, 10374.296966847185, 10421.733506427247, 10398.138584384178, 10414.298366028546, 10478.326591074978, 10448.339810533314, 10421.75194610956, 10391.227528206966, 10420.032987012893, 10353.462399375221, 10294.670999946606, 10362.879212005173, 10476.953305078934, 10251.161544427283, 10350.515514970182, 10406.155922769996, 10380.15566584465, 10408.873197396146, 10465.964412718173, 10399.430126710264, 10378.477651181529, 10510.420584358521, 10351.237789878212, 10357.110547450866, 10410.980673340327, 10363.275786019311, 10393.692737450561, 10416.361115548065, 10450.104331704217, 10430.483607858447, 10482.403526232087, 10461.183494042869])\n('mean return', 10399.47124849325)\n('std of return', 54.868826640962055)\nobs.shape = (240, 1000, 376)\nact.shape = (240, 1000, 17)\nexpert data has been saved.\n"
  },
  {
    "path": "bc/run_expert.py",
    "content": "\"\"\"\nCode to load an expert policy and generate roll-out data for behavioral cloning.\nExample usage:\n\n    python run_expert.py experts/Humanoid-v1.pkl Humanoid-v1 --render \\\n            --num_rollouts 20\n\nAuthor of this script and included expert policies: Jonathan Ho (hoj@openai.com)\n\n(Daniel) I save an array of trajectories of shape \n\n    (numtrajs, numtimes, obs_dim)  // observations\n    (numtrajs, numtimes, act_dim)  // actions, squeezed as needed\n    // and also a list of returns and steps, each of length `numtrajs`.\n\nHowever this requires padding some zeros at the end for trajectories that didn't\nmanage to finish (should be rare with experts, but it can still happen). Thus, I\nalso save a trajectory *lengths* array which can tell us when to stop dealing\nwith a trajectory.\n\"\"\"\n\nimport pickle\nimport tensorflow as tf\nimport numpy as np\nimport tf_util\nimport gym\nimport load_policy\n\n\ndef main():\n    import argparse\n    parser = argparse.ArgumentParser()\n    parser.add_argument('expert_policy_file', type=str)\n    parser.add_argument('envname', type=str)\n    parser.add_argument('--render', action='store_true')\n    parser.add_argument('--save', action='store_true')\n    parser.add_argument('--max_timesteps', type=int)\n    parser.add_argument('--num_rollouts', type=int, default=20,\n                        help='Number of expert roll outs')\n    args = parser.parse_args()\n\n    print('loading and building expert policy')\n    policy_fn = load_policy.load_policy(args.expert_policy_file)\n    print('loaded and built')\n\n    with tf.Session():\n        tf_util.initialize()\n\n        import gym\n        env = gym.make(args.envname)\n        max_steps = args.max_timesteps or env.spec.timestep_limit\n\n        all_observations = []\n        all_actions = []\n        all_steps = []\n        all_returns = []\n\n        for i in range(args.num_rollouts):\n            print('roll/traj', i)\n            obs = env.reset()\n            done = False\n            totalr = 0.\n            steps = 0\n            observations = []\n            actions = []\n            while not done:\n                action = policy_fn(obs[None,:])\n                observations.append(obs)\n                actions.append(action)\n                obs, r, done, _ = env.step(action)\n                totalr += r\n                steps += 1\n                if args.render:\n                    env.render()\n                if steps % 100 == 0: print(\"%i/%i\"%(steps, max_steps))\n                if steps >= max_steps:\n                    break\n            all_returns.append(totalr)\n            all_steps.append(steps)\n\n            # Ensure that observations and actions lengths are at max_steps.\n            # To make it easy, just append the last obs/action since they are\n            # automatically the correct dimension, reduces headaches.\n            while steps < max_steps:\n                observations.append(obs)\n                actions.append(action)\n                steps += 1\n            assert len(observations) == max_steps, \"{}\".format(len(observations))\n            assert len(actions) == max_steps, \"{}\".format(len(actions))\n            all_observations.append(observations)\n            all_actions.append(actions)\n\n        # Squeezing since we know MuJoCo does some (1,D)-dim actions.\n        expert_data = {'observations': np.array(all_observations),\n                       'actions': np.squeeze(np.array(all_actions)),\n                       'returns': all_returns,\n                       'steps': all_steps}\n\n        print('steps', all_steps)\n        print('returns', all_returns)\n        print('mean return', np.mean(all_returns))\n        print('std of return', np.std(all_returns))\n        print(\"obs.shape = {}\".format(expert_data['observations'].shape))\n        print(\"act.shape = {}\".format(expert_data['actions'].shape))\n\n        if args.save:\n            str_roll = str(args.num_rollouts).zfill(3)\n            np.save(\"expert_data/\" +args.envname+ \"_\" +str_roll, expert_data)\n            print(\"expert data has been saved.\")\n\n\nif __name__ == '__main__':\n    main()\n"
  },
  {
    "path": "bc/tf_util.py",
    "content": "import numpy as np\nimport tensorflow as tf # pylint: ignore-module\n#import builtins\nimport functools\nimport copy\nimport os\nimport collections\n\n# ================================================================\n# Import all names into common namespace\n# ================================================================\n\nclip = tf.clip_by_value\n\n# Make consistent with numpy\n# ----------------------------------------\n\ndef sum(x, axis=None, keepdims=False):\n    return tf.reduce_sum(x, reduction_indices=None if axis is None else [axis], keep_dims = keepdims)\ndef mean(x, axis=None, keepdims=False):\n    return tf.reduce_mean(x, reduction_indices=None if axis is None else [axis], keep_dims = keepdims)\ndef var(x, axis=None, keepdims=False):\n    meanx = mean(x, axis=axis, keepdims=keepdims)\n    return mean(tf.square(x - meanx), axis=axis, keepdims=keepdims)\ndef std(x, axis=None, keepdims=False):\n    return tf.sqrt(var(x, axis=axis, keepdims=keepdims))\ndef max(x, axis=None, keepdims=False):\n    return tf.reduce_max(x, reduction_indices=None if axis is None else [axis], keep_dims = keepdims)\ndef min(x, axis=None, keepdims=False):\n    return tf.reduce_min(x, reduction_indices=None if axis is None else [axis], keep_dims = keepdims)\ndef concatenate(arrs, axis=0):\n    return tf.concat(axis, arrs)\ndef argmax(x, axis=None):\n    return tf.argmax(x, dimension=axis)\n\ndef switch(condition, then_expression, else_expression):\n    '''Switches between two operations depending on a scalar value (int or bool).\n    Note that both `then_expression` and `else_expression`\n    should be symbolic tensors of the *same shape*.\n\n    # Arguments\n        condition: scalar tensor.\n        then_expression: TensorFlow operation.\n        else_expression: TensorFlow operation.\n    '''\n    x_shape = copy.copy(then_expression.get_shape())\n    x = tf.cond(tf.cast(condition, 'bool'),\n                lambda: then_expression,\n                lambda: else_expression)\n    x.set_shape(x_shape)\n    return x\n\n# Extras\n# ----------------------------------------\ndef l2loss(params):\n    if len(params) == 0:\n        return tf.constant(0.0)\n    else:\n        return tf.add_n([sum(tf.square(p)) for p in params])\ndef lrelu(x, leak=0.2):\n    f1 = 0.5 * (1 + leak)\n    f2 = 0.5 * (1 - leak)\n    return f1 * x + f2 * abs(x)\ndef categorical_sample_logits(X):\n    # https://github.com/tensorflow/tensorflow/issues/456\n    U = tf.random_uniform(tf.shape(X))\n    return argmax(X - tf.log(-tf.log(U)), axis=1)\n\n# ================================================================\n# Global session\n# ================================================================\n\ndef get_session():\n    return tf.get_default_session()\n\ndef single_threaded_session():\n    tf_config = tf.ConfigProto(\n        inter_op_parallelism_threads=1,\n        intra_op_parallelism_threads=1)\n    return tf.Session(config=tf_config)\n\ndef make_session(num_cpu):\n    tf_config = tf.ConfigProto(\n        inter_op_parallelism_threads=num_cpu,\n        intra_op_parallelism_threads=num_cpu)\n    return tf.Session(config=tf_config)\n\n\nALREADY_INITIALIZED = set()\ndef initialize():\n    new_variables = set(tf.global_variables()) - ALREADY_INITIALIZED\n    get_session().run(tf.variables_initializer(new_variables))\n    ALREADY_INITIALIZED.update(new_variables)\n\n\ndef eval(expr, feed_dict=None):\n    if feed_dict is None: feed_dict = {}\n    return get_session().run(expr, feed_dict=feed_dict)\n\ndef set_value(v, val):\n    get_session().run(v.assign(val))\n\ndef load_state(fname):\n    saver = tf.train.Saver()\n    saver.restore(get_session(), fname)\n\ndef save_state(fname):\n    os.makedirs(os.path.dirname(fname), exist_ok=True)\n    saver = tf.train.Saver()\n    saver.save(get_session(), fname)\n\n# ================================================================\n# Model components\n# ================================================================\n\n\ndef normc_initializer(std=1.0):\n    def _initializer(shape, dtype=None, partition_info=None): #pylint: disable=W0613\n        out = np.random.randn(*shape).astype(np.float32)\n        out *= std / np.sqrt(np.square(out).sum(axis=0, keepdims=True))\n        return tf.constant(out)\n    return _initializer\n\n\ndef conv2d(x, num_filters, name, filter_size=(3, 3), stride=(1, 1), pad=\"SAME\", dtype=tf.float32, collections=None,\n           summary_tag=None):\n    with tf.variable_scope(name):\n        stride_shape = [1, stride[0], stride[1], 1]\n        filter_shape = [filter_size[0], filter_size[1], int(x.get_shape()[3]), num_filters]\n\n        # there are \"num input feature maps * filter height * filter width\"\n        # inputs to each hidden unit\n        fan_in = intprod(filter_shape[:3])\n        # each unit in the lower layer receives a gradient from:\n        # \"num output feature maps * filter height * filter width\" /\n        #   pooling size\n        fan_out = intprod(filter_shape[:2]) * num_filters\n        # initialize weights with random weights\n        w_bound = np.sqrt(6. / (fan_in + fan_out))\n\n        w = tf.get_variable(\"W\", filter_shape, dtype, tf.random_uniform_initializer(-w_bound, w_bound),\n                            collections=collections)\n        b = tf.get_variable(\"b\", [1, 1, 1, num_filters], initializer=tf.zeros_initializer,\n                            collections=collections)\n\n        if summary_tag is not None:\n            tf.image_summary(summary_tag,\n                             tf.transpose(tf.reshape(w, [filter_size[0], filter_size[1], -1, 1]),\n                                          [2, 0, 1, 3]),\n                             max_images=10)\n\n        return tf.nn.conv2d(x, w, stride_shape, pad) + b\n\n\ndef dense(x, size, name, weight_init=None, bias=True):\n    w = tf.get_variable(name + \"/w\", [x.get_shape()[1], size], initializer=weight_init)\n    ret = tf.matmul(x, w)\n    if bias:\n        b = tf.get_variable(name + \"/b\", [size], initializer=tf.zeros_initializer)\n        return ret + b\n    else:\n        return ret\n\ndef wndense(x, size, name, init_scale=1.0):\n    v = tf.get_variable(name + \"/V\", [int(x.get_shape()[1]), size],\n                        initializer=tf.random_normal_initializer(0, 0.05))\n    g = tf.get_variable(name + \"/g\", [size], initializer=tf.constant_initializer(init_scale))\n    b = tf.get_variable(name + \"/b\", [size], initializer=tf.constant_initializer(0.0))\n\n    # use weight normalization (Salimans & Kingma, 2016)\n    x = tf.matmul(x, v)\n    scaler = g / tf.sqrt(sum(tf.square(v), axis=0, keepdims=True))\n    return tf.reshape(scaler, [1, size]) * x + tf.reshape(b, [1, size])\n\ndef densenobias(x, size, name, weight_init=None):\n    return dense(x, size, name, weight_init=weight_init, bias=False)\n\ndef dropout(x, pkeep, phase=None, mask=None):\n    mask = tf.floor(pkeep + tf.random_uniform(tf.shape(x))) if mask is None else mask\n    if phase is None:\n        return mask * x\n    else:\n        return switch(phase, mask*x, pkeep*x)\n\ndef batchnorm(x, name, phase, updates, gamma=0.96):\n    k = x.get_shape()[1]\n    runningmean = tf.get_variable(name+\"/mean\", shape=[1, k], initializer=tf.constant_initializer(0.0), trainable=False)\n    runningvar = tf.get_variable(name+\"/var\", shape=[1, k], initializer=tf.constant_initializer(1e-4), trainable=False)\n    testy = (x - runningmean) / tf.sqrt(runningvar)\n\n    mean_ = mean(x, axis=0, keepdims=True)\n    var_ = mean(tf.square(x), axis=0, keepdims=True)\n    std = tf.sqrt(var_)\n    trainy = (x - mean_) / std\n\n    updates.extend([\n        tf.assign(runningmean, runningmean * gamma + mean_ * (1 - gamma)),\n        tf.assign(runningvar, runningvar * gamma + var_ * (1 - gamma))\n    ])\n\n    y = switch(phase, trainy, testy)\n\n    out = y * tf.get_variable(name+\"/scaling\", shape=[1, k], initializer=tf.constant_initializer(1.0), trainable=True)\\\n            + tf.get_variable(name+\"/translation\", shape=[1,k], initializer=tf.constant_initializer(0.0), trainable=True)\n    return out\n\n\n\n# ================================================================\n# Basic Stuff\n# ================================================================\n\ndef function(inputs, outputs, updates=None, givens=None):\n    if isinstance(outputs, list):\n        return _Function(inputs, outputs, updates, givens=givens)\n    elif isinstance(outputs, (dict, collections.OrderedDict)):\n        f = _Function(inputs, outputs.values(), updates, givens=givens)\n        return lambda *inputs : type(outputs)(zip(outputs.keys(), f(*inputs)))\n    else:\n        f = _Function(inputs, [outputs], updates, givens=givens)\n        return lambda *inputs : f(*inputs)[0]\n\nclass _Function(object):\n    def __init__(self, inputs, outputs, updates, givens, check_nan=False):\n        assert all(len(i.op.inputs)==0 for i in inputs), \"inputs should all be placeholders\"\n        self.inputs = inputs\n        updates = updates or []\n        self.update_group = tf.group(*updates)\n        self.outputs_update = list(outputs) + [self.update_group]\n        self.givens = {} if givens is None else givens\n        self.check_nan = check_nan\n    def __call__(self, *inputvals):\n        assert len(inputvals) == len(self.inputs)\n        feed_dict = dict(zip(self.inputs, inputvals))\n        feed_dict.update(self.givens)\n        results = get_session().run(self.outputs_update, feed_dict=feed_dict)[:-1]\n        if self.check_nan:\n            if any(np.isnan(r).any() for r in results):\n                raise RuntimeError(\"Nan detected\")\n        return results\n\ndef mem_friendly_function(nondata_inputs, data_inputs, outputs, batch_size):\n    if isinstance(outputs, list):\n        return _MemFriendlyFunction(nondata_inputs, data_inputs, outputs, batch_size)\n    else:\n        f = _MemFriendlyFunction(nondata_inputs, data_inputs, [outputs], batch_size)\n        return lambda *inputs : f(*inputs)[0]\n\nclass _MemFriendlyFunction(object):\n    def __init__(self, nondata_inputs, data_inputs, outputs, batch_size):\n        self.nondata_inputs = nondata_inputs\n        self.data_inputs = data_inputs\n        self.outputs = list(outputs)\n        self.batch_size = batch_size\n    def __call__(self, *inputvals):\n        assert len(inputvals) == len(self.nondata_inputs) + len(self.data_inputs)\n        nondata_vals = inputvals[0:len(self.nondata_inputs)]\n        data_vals = inputvals[len(self.nondata_inputs):]\n        feed_dict = dict(zip(self.nondata_inputs, nondata_vals))\n        n = data_vals[0].shape[0]\n        for v in data_vals[1:]:\n            assert v.shape[0] == n\n        for i_start in range(0, n, self.batch_size):\n            slice_vals = [v[i_start:min(i_start+self.batch_size, n)] for v in data_vals]\n            for (var,val) in zip(self.data_inputs, slice_vals):\n                feed_dict[var]=val\n            results = tf.get_default_session().run(self.outputs, feed_dict=feed_dict)\n            if i_start==0:\n                sum_results = results\n            else:\n                for i in range(len(results)):\n                    sum_results[i] = sum_results[i] + results[i]\n        for i in range(len(results)):\n            sum_results[i] = sum_results[i] / n\n        return sum_results\n\n# ================================================================\n# Modules\n# ================================================================\n\nclass Module(object):\n    def __init__(self, name):\n        self.name = name\n        self.first_time = True\n        self.scope = None\n        self.cache = {}\n    def __call__(self, *args):\n        if args in self.cache:\n            print(\"(%s) retrieving value from cache\"%self.name)\n            return self.cache[args]\n        with tf.variable_scope(self.name, reuse=not self.first_time):\n            scope = tf.get_variable_scope().name\n            if self.first_time:\n                self.scope = scope\n                print(\"(%s) running function for the first time\"%self.name)\n            else:\n                assert self.scope == scope, \"Tried calling function with a different scope\"\n                print(\"(%s) running function on new inputs\"%self.name)\n            self.first_time = False\n            out = self._call(*args)\n        self.cache[args] = out\n        return out\n    def _call(self, *args):\n        raise NotImplementedError\n\n    @property\n    def trainable_variables(self):\n        assert self.scope is not None, \"need to call module once before getting variables\"\n        return tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, self.scope)\n\n    @property\n    def variables(self):\n        assert self.scope is not None, \"need to call module once before getting variables\"\n        return tf.get_collection(tf.GraphKeys.VARIABLES, self.scope)\n\n\ndef module(name):\n    @functools.wraps\n    def wrapper(f):\n        class WrapperModule(Module):\n            def _call(self, *args):\n                return f(*args)\n        return WrapperModule(name)\n    return wrapper\n\n# ================================================================\n# Graph traversal\n# ================================================================\n\nVARIABLES = {}\n\n\ndef get_parents(node):\n    return node.op.inputs\n\ndef topsorted(outputs):\n    \"\"\"\n    Topological sort via non-recursive depth-first search\n    \"\"\"\n    assert isinstance(outputs, (list,tuple))\n    marks = {}\n    out = []\n    stack = [] #pylint: disable=W0621\n    # i: node\n    # jidx = number of children visited so far from that node\n    # marks: state of each node, which is one of\n    #   0: haven't visited\n    #   1: have visited, but not done visiting children\n    #   2: done visiting children\n    for x in outputs:\n        stack.append((x,0))\n        while stack:\n            (i,jidx) = stack.pop()\n            if jidx == 0:\n                m = marks.get(i,0)\n                if m == 0:\n                    marks[i] = 1\n                elif m == 1:\n                    raise ValueError(\"not a dag\")\n                else:\n                    continue\n            ps = get_parents(i)\n            if jidx == len(ps):\n                marks[i] = 2\n                out.append(i)\n            else:\n                stack.append((i,jidx+1))\n                j = ps[jidx]\n                stack.append((j,0))\n    return out\n\n\n# ================================================================\n# Flat vectors\n# ================================================================\n\ndef var_shape(x):\n    out = [k.value for k in x.get_shape()]\n    assert all(isinstance(a, int) for a in out), \\\n        \"shape function assumes that shape is fully known\"\n    return out\n\ndef numel(x):\n    return intprod(var_shape(x))\n\ndef intprod(x):\n    return int(np.prod(x))\n\ndef flatgrad(loss, var_list):\n    grads = tf.gradients(loss, var_list)\n    return tf.concat(0, [tf.reshape(grad, [numel(v)])\n        for (v, grad) in zip(var_list, grads)])\n\nclass SetFromFlat(object):\n    def __init__(self, var_list, dtype=tf.float32):\n        assigns = []\n        shapes = list(map(var_shape, var_list))\n        total_size = np.sum([intprod(shape) for shape in shapes])\n\n        self.theta = theta = tf.placeholder(dtype,[total_size])\n        start=0\n        assigns = []\n        for (shape,v) in zip(shapes,var_list):\n            size = intprod(shape)\n            assigns.append(tf.assign(v, tf.reshape(theta[start:start+size],shape)))\n            start+=size\n        self.op = tf.group(*assigns)\n    def __call__(self, theta):\n        get_session().run(self.op, feed_dict={self.theta:theta})\n\nclass GetFlat(object):\n    def __init__(self, var_list):\n        self.op = tf.concat(0, [tf.reshape(v, [numel(v)]) for v in var_list])\n    def __call__(self):\n        return get_session().run(self.op)\n\n# ================================================================\n# Misc\n# ================================================================\n\n\ndef fancy_slice_2d(X, inds0, inds1):\n    \"\"\"\n    like numpy X[inds0, inds1]\n    XXX this implementation is bad\n    \"\"\"\n    inds0 = tf.cast(inds0, tf.int64)\n    inds1 = tf.cast(inds1, tf.int64)\n    shape = tf.cast(tf.shape(X), tf.int64)\n    ncols = shape[1]\n    Xflat = tf.reshape(X, [-1])\n    return tf.gather(Xflat, inds0 * ncols + inds1)\n\n\ndef scope_vars(scope, trainable_only):\n    \"\"\"\n    Get variables inside a scope\n    The scope can be specified as a string\n    \"\"\"\n    return tf.get_collection(\n        tf.GraphKeys.TRAINABLE_VARIABLES if trainable_only else tf.GraphKeys.VARIABLES,\n        scope=scope if isinstance(scope, str) else scope.name\n    )\n\ndef lengths_to_mask(lengths_b, max_length):\n    \"\"\"\n    Turns a vector of lengths into a boolean mask\n\n    Args:\n        lengths_b: an integer vector of lengths\n        max_length: maximum length to fill the mask\n\n    Returns:\n        a boolean array of shape (batch_size, max_length)\n        row[i] consists of True repeated lengths_b[i] times, followed by False\n    \"\"\"\n    lengths_b = tf.convert_to_tensor(lengths_b)\n    assert lengths_b.get_shape().ndims == 1\n    mask_bt = tf.expand_dims(tf.range(max_length), 0) < tf.expand_dims(lengths_b, 1)\n    return mask_bt\n\n\ndef in_session(f):\n    @functools.wraps(f)\n    def newfunc(*args, **kwargs):\n        with tf.Session():\n            f(*args, **kwargs)\n    return newfunc\n\n\n_PLACEHOLDER_CACHE = {} # name -> (placeholder, dtype, shape)\ndef get_placeholder(name, dtype, shape):\n    print(\"calling get_placeholder\", name)\n    if name in _PLACEHOLDER_CACHE:\n        out, dtype1, shape1 = _PLACEHOLDER_CACHE[name]\n        assert dtype1==dtype and shape1==shape\n        return out\n    else:\n        out = tf.placeholder(dtype=dtype, shape=shape, name=name)\n        _PLACEHOLDER_CACHE[name] = (out,dtype,shape)\n        return out\ndef get_placeholder_cached(name):\n    return _PLACEHOLDER_CACHE[name][0]\n\ndef flattenallbut0(x):\n    return tf.reshape(x, [-1, intprod(x.get_shape().as_list()[1:])])\n\ndef reset():\n    global _PLACEHOLDER_CACHE\n    global VARIABLES\n    _PLACEHOLDER_CACHE = {}\n    VARIABLES = {}\n    tf.reset_default_graph()\n"
  },
  {
    "path": "ddpg/README.md",
    "content": "# Deep Deterministic Policy Gradients\n\n- Python 3.5\n- Tensorflow 1.2\n\nI'm following the original DDPG paper as much as possible, and using their\n\"low-dimensional\" representation, not the pixels-based one.\n\n## Pendulum-v0\n\nAction space: -2 to 2.\n\n```\npython main.py Pendulum-v0\n```\n\nStatus: not yet working. I think it's done but alas there is some bug somewhere.\nUgh.\n\n\n## References\n\n(These might be useful to supplement the original paper.)\n\n- http://pemami4911.github.io/blog/2016/08/21/ddpg-rl.html\n- https://github.com/rmst/ddpg\n- https://github.com/openai/rllab\n- https://github.com/yukezhu/tensorflow-reinforce\n- https://github.com/stevenpjg/ddpg-aigym\n"
  },
  {
    "path": "ddpg/ddpg.py",
    "content": "\"\"\"\nDeep Deterministic Policy Gradients\n\nMake Actor and Critic subclasses of a NNet class? Not sure ...  for now, I'll\nput everything here but that might take a lot.\n\"\"\"\n\nimport gym\nimport numpy as np\nimport sys\nimport tensorflow as tf\nimport tensorflow.contrib.layers as layers\nimport time\nfrom replay_buffer import ReplayBuffer\nfrom collections import defaultdict\nsys.path.append(\"../\")\nfrom utils import logz\n\n\nclass DDPGAgent(object):\n\n    def __init__(self, sess, env, test_env, args):\n        self.sess = sess\n        self.args = args\n        self.env = env\n        self.test_env = test_env\n        self.ob_dim = env.observation_space.shape[0]\n        self.ac_dim = env.action_space.shape[0]\n\n        # Construct the networks and the experience replay buffer.\n        self.actor   = Actor(sess, env, args)\n        self.critic  = Critic(sess, env, args)\n        self.rbuffer = ReplayBuffer(args.replay_size, self.ob_dim, self.ac_dim)\n\n        # Initialize then run, also setting current=target to start.\n        self._debug_print()\n        self.sess.run(tf.global_variables_initializer())\n        self.actor.update_target_net(smooth=False)\n        self.critic.update_target_net(smooth=False)\n\n\n    def train(self):\n        \"\"\" \n        Algorithm 1 in the DDPG paper. \n        \"\"\"\n        num_episodes = 0\n        t_start = time.time()\n        obs = self.env.reset()\n\n        for t in range(self.args.n_iter):\n            if (t % self.args.log_every_t_iter == 0) and (t > self.args.wait_until_rbuffer):\n                print(\"\\n*** DDPG Iteration {} ***\".format(t))\n\n            # Sample actions with noise injection and manage buffer.\n            act = self.actor.sample_action(obs, train=True)\n            new_obs, rew, done, info = self.env.step(act)\n            self.rbuffer.add_sample(s=obs, a=act, r=rew, done=done)\n            if done:\n                obs = self.env.reset()\n                num_episodes += 1\n            else:\n                obs = new_obs\n\n            if (t > self.args.wait_until_rbuffer) and (t % self.args.learning_freq == 0):\n                # Sample from the replay buffer.\n                states_t_BO, actions_t_BA, rewards_t_B, states_tp1_BO, done_mask_B = \\\n                        self.rbuffer.sample(num=self.args.batch_size)\n\n                feed = {'obs_t_BO':    states_t_BO, \n                        'act_t_BA':    actions_t_BA, \n                        'rew_t_B':     rewards_t_B, \n                        'obs_tp1_BO':  states_tp1_BO, \n                        'done_mask_B': done_mask_B}\n\n                # Update the critic, get sampled policy gradients, update actor.\n                a_grads_BA, l2_error = self.critic.update_weights(feed)\n                actor_gradients = self.actor.update_weights(feed, a_grads_BA)\n\n                # Update both target networks.\n                self.critic.update_target_net()\n                self.actor.update_target_net()\n\n            if (t % self.args.log_every_t_iter == 0) and (t > self.args.wait_until_rbuffer):\n                # Do some rollouts here and then record statistics.  Note that\n                # some of these stats rely on stuff computed from sampling the\n                # replay buffer, so be careful interpreting these. The code\n                # probably needs to guard against this case as well.\n                stats = self._do_rollouts()\n                hours = (time.time()-t_start) / (60*60.)\n                logz.log_tabular(\"MeanReward\",     np.mean(stats['reward']))\n                logz.log_tabular(\"MaxReward\",      np.max(stats['reward']))\n                logz.log_tabular(\"MinReward\",      np.min(stats['reward']))\n                logz.log_tabular(\"StdReward\",      np.std(stats['reward']))\n                logz.log_tabular(\"MeanLength\",     np.mean(stats['length']))\n                logz.log_tabular(\"NumTrainingEps\", num_episodes)\n                logz.log_tabular(\"L2ErrorCritic\",  l2_error)\n                logz.log_tabular(\"QaGradL2Norm\",   np.linalg.norm(a_grads_BA))\n                logz.log_tabular(\"TimeHours\",      hours)\n                logz.log_tabular(\"Iterations\",     t)\n                logz.dump_tabular()\n\n\n    def _do_rollouts(self):\n        \"\"\" \n        Some rollouts to evaluate the agent's progress.  Returns a dictionary\n        containing relevant statistics. Later, I should parallelize this using\n        an array of environments.\n        \"\"\"\n        num_episodes = 50\n        stats = defaultdict(list)\n\n        for i in range(num_episodes):\n            obs = self.test_env.reset()\n            ep_time = 0\n            ep_reward = 0\n\n            # Run one episode ...\n            while True:\n                act = self.actor.sample_action(obs, train=False)\n                new_obs, rew, done, info = self.test_env.step(act)\n                ep_time += 1\n                ep_reward += rew\n                if done:\n                    break\n\n            # ... and collect its information here.\n            stats['length'].append(ep_time)\n            stats['reward'].append(ep_reward)\n\n        return stats\n\n\n    def _debug_print(self):\n        print(\"\\n\\t(A bunch of debug prints)\\n\")\n\n        print(\"\\nActor weights\")\n        for v in self.actor.weights:\n            shp = v.get_shape().as_list()\n            print(\"- {} shape:{} size:{}\".format(v.name, shp, np.prod(shp)))\n        print(\"Total # of weights: {}.\".format(self.actor.num_weights))\n\n        print(\"\\nCritic weights\")\n        for v in self.critic.weights:\n            shp = v.get_shape().as_list()\n            print(\"- {} shape:{} size:{}\".format(v.name, shp, np.prod(shp)))\n        print(\"Total # of weights: {}.\".format(self.critic.num_weights))\n\n\n\nclass Network(object):\n    \"\"\" \n    Just so the Actor and Critic nets don't have more duplicate code. This way\n    they can refer to the similar sets of placeholders (but not the exact same\n    ones in memory, just a copy) and I can change it easily here.\n    \"\"\"\n\n    def __init__(self, sess, env, args):\n        self.sess = sess\n        self.args = args\n\n        # Some random stuff.\n        assert len(env.observation_space.shape) == 1\n        assert len(env.action_space.shape) == 1\n        self.ob_dim = env.observation_space.shape[0]\n        self.ac_dim = env.action_space.shape[0]\n        self.ac_high = env.action_space.high\n        self.ac_low = env.action_space.low\n\n        # Placeholders for minibatches of data. End of episode = 1 for mask.\n        self.obs_t_BO    = tf.placeholder(tf.float32, [None,self.ob_dim])\n        self.act_t_BA    = tf.placeholder(tf.float32, [None,self.ac_dim])\n        self.rew_t_B     = tf.placeholder(tf.float32, [None])\n        self.obs_tp1_BO  = tf.placeholder(tf.float32, [None,self.ob_dim])\n        self.done_mask_B = tf.placeholder(tf.float32, [None])\n\n\n\nclass Actor(Network):\n    \"\"\" Given input as a batch of states, the actor deterministically provides\n    us with actions, indicated as \"mu\" in the paper. \n    \n    Since DDPG is off-policy, we can treat the problem of exploration\n    independently from the learning algorithm. External to this class, I add\n    Gaussian noise for this purpose.\n    \"\"\"\n\n    def __init__(self, sess, env, args):\n        super().__init__(sess, env, args)\n\n        # The action network and its corresponding taget.\n        self.actions_BA      = self._build_net(self.obs_t_BO, scope='ActorNet')\n        self.actions_targ_BA = self._build_net(self.obs_t_BO, scope='TargActorNet')\n\n        # Collect weights since it's generally convenient to do so.\n        self.weights      = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='ActorNet')\n        self.weights_targ = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='TargActorNet')\n        self.weights_v      = tf.concat([tf.reshape(w, [-1]) for w in self.weights], axis=0)\n        self.weights_v_targ = tf.concat([tf.reshape(w, [-1]) for w in self.weights_targ], axis=0)\n\n        # These should be the same among both nets.\n        self.w_shapes = [w.get_shape().as_list() for w in self.weights]\n        self.num_weights = np.sum([np.prod(sh) for sh in self.w_shapes])\n\n        # Update the target action network. Provide hard and smooth updates.\n        target_smooth = []\n        target_hard = []\n        for var, var_target in zip(sorted(self.weights,      key=lambda v: v.name),\n                                   sorted(self.weights_targ, key=lambda v: v.name)):\n            update_sm = self.args.tau * var + (1 - self.args.tau) * var_target\n            target_smooth.append(var_target.assign(update_sm))\n            target_hard.append(var_target.assign(var))\n        self.update_target_smooth = tf.group(*target_smooth)\n        self.update_target_hard   = tf.group(*target_hard)\n\n        # The Actor _update_, with one gradient provided by the critic which\n        # serves as initialization (I think) since we need to multiply. Negate\n        # it (I think) since we we want to minimize a loss function.\n        self.a_grads_BA = tf.placeholder(tf.float32, [None,self.ac_dim])\n        self.actor_gradients = tf.gradients(self.actions_BA, self.weights, -self.a_grads_BA)\n        self.optimize_a = tf.train.AdamOptimizer(self.args.step_size_actor).\\\n                    apply_gradients(zip(self.actor_gradients, self.weights))\n\n\n    def _build_net(self, input_BO, scope):\n        \"\"\" The Actor network.\n        \n        Uses ReLUs for all hidden layers, but a tanh to the output to bound the\n        action. This follows their 'low-dimensional networks' using 400 and 300\n        units for the hidden layers. Set `reuse=False`. I don't use batch\n        normalization or their precise weight initialization.\n        \"\"\"\n        with tf.variable_scope(scope, reuse=False):\n            hidden1 = layers.fully_connected(input_BO,\n                    num_outputs=400,\n                    weights_initializer=layers.xavier_initializer(),\n                    activation_fn=tf.nn.relu)\n            hidden2 = layers.fully_connected(hidden1, \n                    num_outputs=300,\n                    weights_initializer=layers.xavier_initializer(),\n                    activation_fn=tf.nn.relu)\n            actions_BA = layers.fully_connected(hidden2,\n                    num_outputs=self.ac_dim,\n                    weights_initializer=layers.xavier_initializer(),\n                    activation_fn=tf.nn.tanh) # Note the tanh!\n            # This should broadcast, but haven't tested with ac_dim > 1.\n            actions_BA = tf.multiply(actions_BA, self.ac_high)\n            return actions_BA\n\n\n    def sample_action(self, obs, train=True):\n        \"\"\" Samples an action.\n        \n        TODO we don't have their exact Gaussian noise injection process because\n        I can't figure out how to implement it. :-(\n\n        Parameters\n        ----------\n        obs: [np.array]\n            Represents current states. We assume we need to expand it.\n        train: [boolean]\n            True means we need to inject noise. False is for test evaluation.\n        \"\"\"\n        act = self.sess.run(self.actions_BA, {self.obs_t_BO: obs[None]})\n        act = act[0]\n        assert self.ac_low < act < self.ac_high\n        if train:\n            return act + np.random.normal(loc=self.args.ou_noise_theta,\n                    scale=self.args.ou_noise_sigma, size=act.shape)\n        else:\n            return act\n\n    \n    def update_target_net(self, smooth=True):\n        \"\"\" \n        Update the target network based on the current weights. Normally we do\n        this with smooth=True except for the first step, or unless we want to\n        see how poorly hard updates perform generally.\n        \"\"\"\n        if smooth:\n            self.sess.run(self.update_target_smooth)\n        else:\n            self.sess.run(self.update_target_hard)\n\n\n    def update_weights(self, f, a_grads_BA):\n        \"\"\" Gradient-based update of current actor parameters. \"\"\"\n        feed = {self.obs_t_BO: f['obs_t_BO'], self.a_grads_BA: a_grads_BA}\n        _, actor_gradients = self.sess.run([self.optimize_a, \\\n                self.actor_gradients], feed)\n        return actor_gradients\n\n\n\nclass Critic(Network):\n    \"\"\" Computes Q(s,a) values to encourage the Actor to learn better policies.\n\n    This is colloquially referred to as 'Q' in the paper.\n    \"\"\"\n\n    def __init__(self, sess, env, args):\n        super().__init__(sess, env, args)\n\n        # The critic network (i.e. Q-values) and its corresponding target.\n        self.qvals_B      = self._build_net(self.obs_t_BO, self.act_t_BA, scope='CriticNet')\n        self.qvals_targ_B = self._build_net(self.obs_t_BO, self.act_t_BA, scope='TargCriticNet')\n\n        # Collect weights since it's generally convenient to do so.\n        self.weights      = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='CriticNet')\n        self.weights_targ = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='TargCriticNet')\n        self.weights_v      = tf.concat([tf.reshape(w, [-1]) for w in self.weights], axis=0)\n        self.weights_v_targ = tf.concat([tf.reshape(w, [-1]) for w in self.weights_targ], axis=0)\n\n        # These should be the same among both nets.\n        self.w_shapes = [w.get_shape().as_list() for w in self.weights]\n        self.num_weights = np.sum([np.prod(sh) for sh in self.w_shapes])\n\n        # Update the target action network. Provide hard and smooth updates.\n        target_smooth = []\n        target_hard = []\n        for var, var_target in zip(sorted(self.weights,      key=lambda v: v.name),\n                                   sorted(self.weights_targ, key=lambda v: v.name)):\n            update_sm = self.args.tau * var + (1 - self.args.tau) * var_target\n            target_smooth.append(var_target.assign(update_sm))\n            target_hard.append(var_target.assign(var))\n        self.update_target_smooth = tf.group(*target_smooth)\n        self.update_target_hard   = tf.group(*target_hard)\n\n        # The _critic_ uses y_i, the target for its loss. Depends on `done` mask! \n        self.target_val_B = self.rew_t_B + (self.args.Q_gamma * self.qvals_targ_B) * (1 - self.done_mask_B)\n        self.l2_error = tf.reduce_mean(tf.square(self.target_val_B - self.qvals_B))\n        # TODO l2 weight decay?\n\n        # Use the built-in Adam optimizer, but might want to try gradient clipping?\n        self.optimize_c = tf.train.AdamOptimizer(self.args.step_size_critic).minimize(self.l2_error) \n\n        # Then return this in the gradient step to provide to the Actor.\n        # TODO should check this, it _should_ deal with gradients row-wise, and\n        # then the gradient can be summed over B. Where is the summing over B?\n        # Is this also equivalent if I did targ = tf.reduce_sum(self.qvals_B)? I\n        # think so because it doesn't matter if we sum, action in b-th minibatch\n        # only (directly) affects the b-th Q-value and has a gradient, right?\n        self.act_grads_BA = tf.gradients(self.qvals_B, self.act_t_BA)\n\n\n    def _build_net(self, input_BO, acts_BO, scope):\n        \"\"\" The critic network.\n        \n        Use ReLUs for all hidden layers. The output consists of one Q-value for\n        each batch. Set `reuse=False`. I don't use batch normalization or their\n        precise weight initialization.\n\n        Unlike the critic, it uses actions here but they are NOT included in the\n        first hidden layer. In addition, we do a tf.reshape to get an output of\n        shape (B,), not (B,1). Seems like tf.squeeze doesn't work with `?`.\n        \"\"\"\n        with tf.variable_scope(scope, reuse=False):\n            hidden1 = layers.fully_connected(input_BO,\n                    num_outputs=400,\n                    weights_initializer=layers.xavier_initializer(),\n                    activation_fn=tf.nn.relu)\n            # Insert the concatenation here. This should be fine, I think.\n            state_action = tf.concat(axis=1, values=[hidden1, acts_BO])\n            hidden2 = layers.fully_connected(state_action,\n                    num_outputs=300,\n                    weights_initializer=layers.xavier_initializer(),\n                    activation_fn=tf.nn.relu)\n            qvals_B = layers.fully_connected(hidden2,\n                    num_outputs=1,\n                    weights_initializer=layers.xavier_initializer(),\n                    activation_fn=None)\n            return tf.reshape(qvals_B, shape=[-1])\n\n\n    def update_target_net(self, smooth=True):\n        \"\"\" \n        Update the target network based on the current weights. Normally we do\n        this with smooth=True except for the first step, or unless we want to\n        see how poorly hard updates perform generally.\n        \"\"\"\n        if smooth:\n            self.sess.run(self.update_target_smooth)\n        else:\n            self.sess.run(self.update_target_hard)\n\n\n    def update_weights(self, f):\n        \"\"\" \n        Gradient-based update of current Critic parameters.  Also return the\n        action gradients for the Actor update later. This is the dQ/da in the\n        paper, and Q is the current Q network, not the target Q network.\n        \"\"\"\n        feed = {\n            self.obs_t_BO:    f['obs_t_BO'],\n            self.act_t_BA:    f['act_t_BA'],\n            self.rew_t_B:     f['rew_t_B'],\n            self.obs_tp1_BO:  f['obs_tp1_BO'],\n            self.done_mask_B: f['done_mask_B']\n        }\n        action_grads_BA, _, l2_error = self.sess.run([self.act_grads_BA, \\\n                self.optimize_c, self.l2_error], feed)\n\n        # We assume that the only item in the list has what we want.\n        assert len(action_grads_BA) == 1\n        return action_grads_BA[0], l2_error\n"
  },
  {
    "path": "ddpg/main.py",
    "content": "\"\"\"\nMain script for DDPG code, for CONTINUOUS control environments.\n\n(c) 2017 by Daniel Seita, though mostly building upon other code as usual, with\ncredit attrbuted to in the DDPG's README.\n\"\"\"\n\nfrom ddpg import DDPGAgent\nimport argparse\nimport gym\nimport numpy as np\nnp.set_printoptions(suppress=True, precision=5, edgeitems=10)\nimport pickle\nimport sys\nimport tensorflow as tf\nif \"../\" not in sys.path:\n    sys.path.append(\"../\")\nfrom utils import utils_pg as utils\nfrom utils import value_functions as vfuncs\nfrom utils import logz\nfrom utils import policies\n\n\nif __name__ == \"__main__\":\n    p = argparse.ArgumentParser()\n    p.add_argument('envname', type=str)\n\n    # DDPG stuff, all directly from the paper.\n    p.add_argument('--batch_size', type=int, default=64) # Used 16 on pixels.\n    p.add_argument('--ou_noise_theta', type=float, default=0.15)\n    p.add_argument('--ou_noise_sigma', type=float, default=0.2)\n    p.add_argument('--Q_gamma', type=float, default=0.99)\n    p.add_argument('--Q_l2_weight_decay', type=float, default=1e-2)\n    p.add_argument('--replay_size', type=int, default=1000000)\n    p.add_argument('--step_size_actor', type=float, default=1e-4)\n    p.add_argument('--step_size_critic', type=float, default=1e-3)\n    p.add_argument('--tau', type=float, default=0.001)\n\n    # Other stuff that I use for my own or based on other code.\n    p.add_argument('--do_not_save', action='store_true')\n    p.add_argument('--learning_freq', type=int, default=50)\n    p.add_argument('--log_every_t_iter', type=int, default=50)\n    p.add_argument('--max_gradient', type=float, default=10.0)\n    p.add_argument('--n_iter', type=int, default=10000)\n    p.add_argument('--seed', type=int, default=0)\n    p.add_argument('--wait_until_rbuffer', type=int, default=1000)\n    args = p.parse_args()\n\n    # Handle the log directory and save the arguments.\n    logdir = 'out/' +args.envname+ '/seed' +str(args.seed).zfill(2)\n    if args.do_not_save:\n        logdir = None\n    logz.configure_output_dir(logdir)\n    if logdir is not None:\n        with open(logdir+'/args.pkl', 'wb') as f:\n            pickle.dump(args, f)\n    print(\"Saving in logdir: {}\".format(logdir))\n\n    # Other stuff for seeding and getting things set up.\n    tf.set_random_seed(args.seed)\n    np.random.seed(args.seed)\n    env = gym.make(args.envname)\n    test_env = gym.make(args.envname)\n    tf_config = tf.ConfigProto(inter_op_parallelism_threads=1, \n                               intra_op_parallelism_threads=1) \n    sess = tf.Session(config=tf_config)\n\n    ddpg = DDPGAgent(sess, env, test_env, args)\n    ddpg.train()\n"
  },
  {
    "path": "ddpg/replay_buffer.py",
    "content": "import numpy as np\nimport sys\n\n\nclass ReplayBuffer(object):\n\n    def __init__(self, size, ob_dim, ac_dim):\n        \"\"\" A replay buffer to store transitions (s,a,r,s') for DDPG.\n\n        - We save with numpy arrays, because there doesn't seem to be a better\n          alternative. (I'm not sure if deques are memory efficient.) Create a\n          *fixed* numpy array to start. \n\n        - Use `self.end_idx` to identify the index of the most recent transition. It\n          starts at 0, increases towards the buffer limit, then wraps around 0 as\n          needed. Instead of \"throwing transitions away\" we simply override them.\n\n        - It can be tricky to think about successor states. Since a full\n          observation sequence is {s0,a0,r0,s1,a1,r1,s2,...} we should always\n          have an equal amount of states, actions, and reward stored, but the\n          successor state will be \"known\" before the action and the reward at\n          its correponding index. I think the easiest way to resolve this is to\n          limit the API of `add_sample` so that it doesn't have to worry about\n          successor states. Then here, we have a \"done\" mask which can tell us\n          when to ignore the successor. In general, there will still _be_ a\n          state stored at the next time index, but the \"done\" mask informs us\n          about if it's actually a successor, or simply the beginning state of\n          the next episode.\n        \n        - Values are 1 in the \"done mask\" if the next state corresponds to the\n          end of an episode when doing env.step(), which is equivalent to saying\n          that the next state stored in this buffer is a start state.\n\n        Parameters\n        ----------\n        size: [int]\n            Maximum number of transitions to store in the buffer. When the\n            buffer overflows the old memories are over-written.\n        ob_dim: [int]\n            State dimension, assumes an integer and not a list or tuple.\n        ac_dim: [int]\n            Action dimension, assumes an integer and not a list or tuple.\n        \"\"\"\n        self.next_idx = 0\n        self.num_in_buffer = 0\n        self.size = size\n        self.states_NO  = np.zeros((size, ob_dim), dtype=np.float32)\n        self.actions_NA = np.zeros((size, ac_dim), dtype=np.float32)\n        self.rewards_N  = np.zeros((size,), dtype=np.float32)\n        self.done_N     = np.zeros((size,), dtype=np.uint8)\n\n\n    def add_sample(self, s, a, r, done):\n        \"\"\" Stores transition (s,a,r) along with the `done` boolean.\n        \n        States (`ob`) that exist as a result of `ob = env.reset()` should be\n        added like usual states. The action and reward as a result of\n\n            `obsucc, rew, done, _ = env.step(act)` \n            \n        should be added to the same index as `ob`. Successor states (`obsucc`\n        here) are stored in the _next_ index, which in rare cases wraps around\n        the buffer size to be zero. However, we add the successor state in the\n        next set of calls outside the code.\n\n        Use `self.next_idx` to store the index, NOT `self.num_in_buffer`. The\n        former will automatically override old samples.\n        \"\"\"\n        self.states_NO[self.next_idx] = s \n        self.actions_NA[self.next_idx] = a\n        self.rewards_N[self.next_idx] = r\n        self.done_N[self.next_idx] = int(done)\n        self.num_in_buffer += 1\n        self.next_idx = (self.next_idx + 1) % self.size\n\n\n    def sample(self, num):\n        \"\"\" Sample `num` transitions (s,a,r,s') for a minibatch. \n        \n        We can use the minimum of the number we've added so far and the max\n        buffer size to determine the range of indices to consider when sampling\n        (_without_ replacement). When taking the successor states, we increment\n        the indices by one and wrap to zero as needed.\n\n        Don't forget the `done` mask! This means we ignore the state at time t\n        plus one (\"tp1\", i.e. the successor state) since it is ignored with the\n        loss function. And the successor at that point would actually be the\n        start of the _next_ episode.\n\n        The `-1` in the `max_index` computation handles annoying corner case of\n        having buffer partially filled and avoiding an un-touched index.\n        \"\"\"\n        assert num < self.num_in_buffer\n        max_index = min(self.num_in_buffer-1, self.size)\n        indices = np.random.choice(max_index, num, replace=False)\n\n        # Make next indices (+1) equal to index `self.size` back to zero.\n        below_thresh = ((indices+1) < self.size).astype(int)\n        indices_next = (indices+1) * below_thresh \n\n        # Get the minibatches for training purposes.\n        states_t_BO   = self.states_NO[indices]\n        actions_t_BA  = self.actions_NA[indices]\n        rewards_t_B   = self.rewards_N[indices]\n        states_tp1_BO = self.states_NO[indices_next]\n        done_mask_B   = self.done_N[indices]\n        return (states_t_BO, actions_t_BA, rewards_t_B, states_tp1_BO, done_mask_B)\n"
  },
  {
    "path": "dqn/README.md",
    "content": "# Deep Q-Networks\n\nThe starter code is from UC Berkeley's Deep Reinforcement Learning class.  These\nare their comments:\n\n> See http://rll.berkeley.edu/deeprlcourse/docs/hw3.pdf for instructions\n> \n> The starter code was based on an implementation of Q-learning for Atari\n> generously provided by Szymon Sidor from OpenAI\n\nThe rest of this README contains my comments and results. \n\n# Usage, Games, etc.\n\nFirst, here is example usage (slashes are only for readability here):\n\n```\npython run_dqn_atari.py --game Pong --seed 1 --num_timesteps 30000000 | tee logs_text/Pong_s001.text\n```\n\nWith these settings, the statistics for plotting data will be stored in the\n`log_pkls/Pong_s001.pkl` file.\n\nHere are some of the `task` stuff in the code, ordered by index (i.e. 0, 1,\netc.).\n\n```\nTask<env_id=BeamRiderNoFrameskip-v3 trials=2 max_timesteps=40000000 max_seconds=None reward_floor=363.9 reward_ceiling=60000.0>\nTask<env_id=BreakoutNoFrameskip-v3 trials=2 max_timesteps=40000000 max_seconds=None reward_floor=1.7 reward_ceiling=800.0>\nTask<env_id=EnduroNoFrameskip-v3 trials=2 max_timesteps=40000000 max_seconds=None reward_floor=0.0 reward_ceiling=5000.0>\nTask<env_id=PongNoFrameskip-v3 trials=2 max_timesteps=40000000 max_seconds=None reward_floor=-20.7 reward_ceiling=21.0>\nTask<env_id=QbertNoFrameskip-v3 trials=2 max_timesteps=40000000 max_seconds=None reward_floor=163.9 reward_ceiling=40000.0>\n```\n\nThe default for these is 40 million episodes, but that's not always needed for\nthe easier games.\n\nThe `num_timesteps` parameter corresponds to the number of steps in the\n\"underlying\" environment, *not* the \"wrapped\" environment. See the stopping\ncriterion:\n\n```\ndef stopping_criterion(env, t):\n    # notice that here t is the number of steps of the wrapped env,\n    # which is different from the number of steps in the underlying env\n    return get_wrapper_by_name(env, \"Monitor\").get_total_steps() >= num_timesteps\n```\n\nThe `t` here is what I think of as \"the number of steps.\" It's confusing, I\nknow. There might be a better way to handle this. From now on, when I say\n\"steps\", it refers to the `t`-like number, and *not* the `num_timesteps`\nparameter.\n\n# Results\n\nNotes:\n\n- Timing results are based on running with an NVIDIA Titan X with Pascal GPU.\n- Scores per Episode indicate scores for every episode.\n- Scores per Timestep indicate the score of the current episode at a given\n  timestep; each episode requires some number of timesteps for the agent to\n  complete it. Theres' a lot of them, so I take every 10,000.\n- Blocks mean taking an interval of some size (100) and taking the mean.\n\n## Pong\n\nCommands:\n\n```\npython run_dqn_atari.py --game Pong --seed 1 --num_timesteps 30000000 | tee logs_text/Pong_s001.text\npython run_dqn_atari.py --game Pong --seed 2 --num_timesteps 30000000 | tee logs_text/Pong_s002.text\n```\n\n- `num_timesteps`: 30 million\n- Training steps: about 7.5 million\n- Episodes: about 4200\n- Time: about 9.0 hours\n\n![pong](figures/Pong.png?raw=true)\n\n## Breakout\n\nCommand:\n\n```\npython run_dqn_atari.py --game Breakout --seed 1 --num_timesteps 40000000 | tee logs_text/Breakout_s001.text\npython run_dqn_atari.py --game Breakout --seed 2 --num_timesteps 40000000 | tee logs_text/Breakout_s002.text\n```\n\n- `num_timesteps`: 40 million\n- Training steps: about 9.7 million\n- Episodes: about 10,200\n- Time: about 11.8 hours\n\nI have no idea why the performance plummeted after 4500 episodes. I may need to\ninvestigate. Note that a few times we get the absolute perfect highest score\n(two full boards cleared); I think the \"800\" value as the maximum score is wrong\n...\n\n![breakout](figures/Breakout.png?raw=true)\n\n\n## BeamRider\n\nCommand:\n\n```\npython run_dqn_atari.py --game BeamRider --seed 1 --num_timesteps 40000000 | tee logs_text/BeamRider_s001.text\npython run_dqn_atari.py --game BeamRider --seed 2 --num_timesteps 40000000 | tee logs_text/BeamRider_s002.text\n```\n\n- `num_timesteps`: 40 million\n- Training steps: about 10.0 million\n- Episodes: about 2,500 to 4,000\n- Time: about 12.5 hours\n\nThe results look different among the seeds since seed 2 apparently had better\npeformance earlier, thus meaning its episodes became longer sooner than the seed\n1 version. At least they look reasonably good. A3C got roughly 13k on this game.\n\n![beamrider](figures/BeamRider.png?raw=true)\n\n\n## Enduro\n\nCommand:\n\n```\npython run_dqn_atari.py --game Enduro --seed 1 --num_timesteps 40000000 | tee logs_text/Enduro_s001.text\npython run_dqn_atari.py --game Enduro --seed 2 --num_timesteps 40000000 | tee logs_text/Enduro_s002.text\n```\n\n- `num_timesteps`: 40 million\n- Training steps: about 10.0 million\n- Episodes: about 2,500 to 3,000\n- Time: about 12.5 hours\n\nAck, what happened to seed 2?!? The first seed matches the DQN result (475.6)\nfrom the Nature script, yet I don't know why the second one failed to learn\nmuch. It's worth noting, though, that the A3C paper actually reported -82.2 on\nthis game (really?!?). Oh well ...\n\n![enduro](figures/Enduro.png?raw=true)\n"
  },
  {
    "path": "dqn/atari_wrappers.py",
    "content": "import cv2\nimport numpy as np\nfrom collections import deque\nimport gym\nfrom gym import spaces\n\n\nclass NoopResetEnv(gym.Wrapper):\n    def __init__(self, env=None, noop_max=30):\n        \"\"\"Sample initial states by taking random number of no-ops on reset.\n        No-op is assumed to be action 0.\n        \"\"\"\n        super(NoopResetEnv, self).__init__(env)\n        self.noop_max = noop_max\n        assert env.unwrapped.get_action_meanings()[0] == 'NOOP'\n\n    def _reset(self):\n        \"\"\" Do no-op action for a number of steps in [1, noop_max].\"\"\"\n        self.env.reset()\n        noops = np.random.randint(1, self.noop_max + 1)\n        for _ in range(noops):\n            obs, _, _, _ = self.env.step(0)\n        return obs\n\nclass FireResetEnv(gym.Wrapper):\n    def __init__(self, env=None):\n        \"\"\"Take action on reset for environments that are fixed until firing.\"\"\"\n        super(FireResetEnv, self).__init__(env)\n        assert env.unwrapped.get_action_meanings()[1] == 'FIRE'\n        assert len(env.unwrapped.get_action_meanings()) >= 3\n\n    def _reset(self):\n        self.env.reset()\n        obs, _, _, _ = self.env.step(1)\n        obs, _, _, _ = self.env.step(2)\n        return obs\n\nclass EpisodicLifeEnv(gym.Wrapper):\n    def __init__(self, env=None):\n        \"\"\"Make end-of-life == end-of-episode, but only reset on true game over.\n        Done by DeepMind for the DQN and co. since it helps value estimation.\n        \"\"\"\n        super(EpisodicLifeEnv, self).__init__(env)\n        self.lives = 0\n        self.was_real_done  = True\n        self.was_real_reset = False\n\n    def _step(self, action):\n        obs, reward, done, info = self.env.step(action)\n        self.was_real_done = done\n        # check current lives, make loss of life terminal,\n        # then update lives to handle bonus lives\n        lives = self.env.unwrapped.ale.lives()\n        if lives < self.lives and lives > 0:\n            # for Qbert somtimes we stay in lives == 0 condtion for a few frames\n            # so its important to keep lives > 0, so that we only reset once\n            # the environment advertises done.\n            done = True\n        self.lives = lives\n        return obs, reward, done, info\n\n    def _reset(self):\n        \"\"\"Reset only when lives are exhausted.\n        This way all states are still reachable even though lives are episodic,\n        and the learner need not know about any of this behind-the-scenes.\n        \"\"\"\n        if self.was_real_done:\n            obs = self.env.reset()\n            self.was_real_reset = True\n        else:\n            # no-op step to advance from terminal/lost life state\n            obs, _, _, _ = self.env.step(0)\n            self.was_real_reset = False\n        self.lives = self.env.unwrapped.ale.lives()\n        return obs\n\nclass MaxAndSkipEnv(gym.Wrapper):\n    def __init__(self, env=None, skip=4):\n        \"\"\"Return only every `skip`-th frame\"\"\"\n        super(MaxAndSkipEnv, self).__init__(env)\n        # most recent raw observations (for max pooling across time steps)\n        self._obs_buffer = deque(maxlen=2)\n        self._skip       = skip\n\n    def _step(self, action):\n        total_reward = 0.0\n        done = None\n        for _ in range(self._skip):\n            obs, reward, done, info = self.env.step(action)\n            self._obs_buffer.append(obs)\n            total_reward += reward\n            if done:\n                break\n\n        max_frame = np.max(np.stack(self._obs_buffer), axis=0)\n\n        return max_frame, total_reward, done, info\n\n    def _reset(self):\n        \"\"\"Clear past frame buffer and init. to first obs. from inner env.\"\"\"\n        self._obs_buffer.clear()\n        obs = self.env.reset()\n        self._obs_buffer.append(obs)\n        return obs\n\ndef _process_frame84(frame):\n    img = np.reshape(frame, [210, 160, 3]).astype(np.float32)\n    img = img[:, :, 0] * 0.299 + img[:, :, 1] * 0.587 + img[:, :, 2] * 0.114\n    resized_screen = cv2.resize(img, (84, 110),  interpolation=cv2.INTER_LINEAR)\n    x_t = resized_screen[18:102, :]\n    x_t = np.reshape(x_t, [84, 84, 1])\n    return x_t.astype(np.uint8)\n\nclass ProcessFrame84(gym.Wrapper):\n    def __init__(self, env=None):\n        super(ProcessFrame84, self).__init__(env)\n        self.observation_space = spaces.Box(low=0, high=255, shape=(84, 84, 1))\n\n    def _step(self, action):\n        obs, reward, done, info = self.env.step(action)\n        return _process_frame84(obs), reward, done, info\n\n    def _reset(self):\n        return _process_frame84(self.env.reset())\n\nclass ClippedRewardsWrapper(gym.Wrapper):\n    def _step(self, action):\n        obs, reward, done, info = self.env.step(action)\n        return obs, np.sign(reward), done, info\n\ndef wrap_deepmind_ram(env):\n    env = EpisodicLifeEnv(env)\n    env = NoopResetEnv(env, noop_max=30)\n    env = MaxAndSkipEnv(env, skip=4)\n    if 'FIRE' in env.unwrapped.get_action_meanings():\n        env = FireResetEnv(env)\n    env = ClippedRewardsWrapper(env)\n    return env\n\ndef wrap_deepmind(env):\n    assert 'NoFrameskip' in env.spec.id\n    env = EpisodicLifeEnv(env)\n    env = NoopResetEnv(env, noop_max=30)\n    env = MaxAndSkipEnv(env, skip=4)\n    if 'FIRE' in env.unwrapped.get_action_meanings():\n        env = FireResetEnv(env)\n    env = ProcessFrame84(env)\n    env = ClippedRewardsWrapper(env)\n    return env\n"
  },
  {
    "path": "dqn/dqn.py",
    "content": "import sys\nimport time\nimport pickle\nimport gym.spaces\nimport itertools\nimport numpy as np\nimport random\nimport tensorflow                as tf\nimport tensorflow.contrib.layers as layers\nfrom collections import namedtuple\nfrom dqn_utils import *\n\nOptimizerSpec = namedtuple(\"OptimizerSpec\", [\"constructor\", \"kwargs\", \"lr_schedule\"])\n\ndef learn(env,\n          q_func,\n          optimizer_spec,\n          session,\n          exploration=LinearSchedule(1000000, 0.1),\n          stopping_criterion=None,\n          replay_buffer_size=1000000,\n          batch_size=32,\n          gamma=0.99,\n          learning_starts=50000,\n          learning_freq=4,\n          frame_history_len=4,\n          target_update_freq=10000,\n          grad_norm_clipping=10,\n          log_file='./logs_pkls/rewards.pkl'):\n    \"\"\"Run Deep Q-learning algorithm.\n\n    You can specify your own convnet using q_func.\n\n    All schedules are w.r.t. total number of steps taken in the environment.\n\n    Parameters\n    ----------\n    env: gym.Env\n        gym environment to train on.\n    q_func: function\n        Model to use for computing the q function. It should accept the\n        following named arguments:\n            img_in: tf.Tensor\n                tensorflow tensor representing the input image\n            num_actions: int\n                number of actions\n            scope: str\n                scope in which all the model related variables\n                should be created\n            reuse: bool\n                whether previously created variables should be reused.\n    optimizer_spec: OptimizerSpec\n        Specifying the constructor and kwargs, as well as learning rate schedule\n        for the optimizer\n    session: tf.Session\n        tensorflow session to use.\n    exploration: rl_algs.deepq.utils.schedules.Schedule\n        schedule for probability of chosing random action.\n    stopping_criterion: (env, t) -> bool\n        should return true when it's ok for the RL algorithm to stop.\n        takes in env and the number of steps executed so far.\n    replay_buffer_size: int\n        How many memories to store in the replay buffer.\n    batch_size: int\n        How many transitions to sample each time experience is replayed.\n    gamma: float\n        Discount Factor\n    learning_starts: int\n        After how many environment steps to start replaying experiences\n    learning_freq: int\n        How many steps of environment to take between every experience replay\n    frame_history_len: int\n        How many past frames to include as input to the model.\n    target_update_freq: int\n        How many experience replay rounds (not steps!) to perform between\n        each update to the target Q network\n    grad_norm_clipping: float or None\n        If not None gradients' norms are clipped to this value.\n    log_file: string\n        Indicates where to save the resulting scores, for plotting later.\n    \"\"\"\n    assert type(env.observation_space) == gym.spaces.Box\n    assert type(env.action_space)      == gym.spaces.Discrete\n\n    ###############\n    # BUILD MODEL #\n    ###############\n\n    if len(env.observation_space.shape) == 1:\n        # This means we are running on low-dimensional observations (e.g. RAM)\n        input_shape = env.observation_space.shape\n    else:\n        img_h, img_w, img_c = env.observation_space.shape\n        input_shape = (img_h, img_w, frame_history_len * img_c)\n    num_actions = env.action_space.n\n\n    # set up placeholders\n    # placeholder for current observation (or state)\n    obs_t_ph              = tf.placeholder(tf.uint8, [None] + list(input_shape))\n    # placeholder for current action\n    act_t_ph              = tf.placeholder(tf.int32,   [None])\n    # placeholder for current reward\n    rew_t_ph              = tf.placeholder(tf.float32, [None])\n    # placeholder for next observation (or state)\n    obs_tp1_ph            = tf.placeholder(tf.uint8, [None] + list(input_shape))\n    # placeholder for end of episode mask\n    # this value is 1 if the next state corresponds to the end of an episode,\n    # in which case there is no Q-value at the next state; at the end of an\n    # episode, only the current state reward contributes to the target, not the\n    # next state Q-value (i.e. target is just rew_t_ph, not rew_t_ph + gamma * q_tp1)\n    done_mask_ph          = tf.placeholder(tf.float32, [None])\n\n    # casting to float on GPU ensures lower data transfer times.\n    obs_t_float   = tf.cast(obs_t_ph,   tf.float32) / 255.0\n    obs_tp1_float = tf.cast(obs_tp1_ph, tf.float32) / 255.0\n\n    # Here, you should fill in your own code to compute the Bellman error. This requires\n    # evaluating the current and next Q-values and constructing the corresponding error.\n    # TensorFlow will differentiate this error for you, you just need to pass it to the\n    # optimizer. See assignment text for details.\n    # Your code should produce one scalar-valued tensor: total_error\n    # This will be passed to the optimizer in the provided code below.\n    # Your code should also produce two collections of variables:\n    # q_func_vars\n    # target_q_func_vars\n    # These should hold all of the variables of the Q-function network and target network,\n    # respectively. A convenient way to get these is to make use of TF's \"scope\" feature.\n    # For example, you can create your Q-function network with the scope \"q_func\" like this:\n    # <something> = q_func(obs_t_float, num_actions, scope=\"q_func\", reuse=False)\n    # And then you can obtain the variables like this:\n    # q_func_vars = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='q_func')\n    # Older versions of TensorFlow may require using \"VARIABLES\" instead of \"GLOBAL_VARIABLES\"\n    ######\n\n    # Building the networks. Have current_net so I can also call Q-values.\n    act_one_hot = tf.one_hot(act_t_ph, num_actions, on_value=1.0, off_value=0.0)\n    current_net = q_func(obs_t_float, num_actions, scope=\"q_func\")\n    current_q = tf.reduce_sum(current_net * act_one_hot, axis=1)\n    target_q = tf.reduce_max(q_func(obs_tp1_float, num_actions, scope=\"target_q_func\"), axis=1)\n\n    # Now form the loss function and collect variables.\n    target_val = rew_t_ph + (gamma * target_q) * (1 - done_mask_ph)\n    total_error = tf.nn.l2_loss(target_val-current_q) / batch_size\n    q_func_vars = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='q_func')\n    target_q_func_vars = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='target_q_func')\n    ######\n\n    # construct optimization op (with gradient clipping)\n    learning_rate = tf.placeholder(tf.float32, (), name=\"learning_rate\")\n    optimizer = optimizer_spec.constructor(learning_rate=learning_rate, **optimizer_spec.kwargs)\n    train_fn = minimize_and_clip(optimizer, total_error,\n                 var_list=q_func_vars, clip_val=grad_norm_clipping)\n\n    # update_target_fn will be called periodically to copy Q network to target Q network\n    update_target_fn = []\n    for var, var_target in zip(sorted(q_func_vars,        key=lambda v: v.name),\n                               sorted(target_q_func_vars, key=lambda v: v.name)):\n        update_target_fn.append(var_target.assign(var))\n    update_target_fn = tf.group(*update_target_fn)\n\n    # construct the replay buffer\n    replay_buffer = ReplayBuffer(replay_buffer_size, frame_history_len)\n\n    ###############\n    # RUN ENV     #\n    ###############\n    scores_for_log = []\n    model_initialized = False\n    num_param_updates = 0\n    mean_episode_reward      = -float('nan')\n    best_mean_episode_reward = -float('inf')\n    last_obs = env.reset() # A numpy structure with shape (height, width, 1).\n    LOG_EVERY_N_STEPS = 10000\n    t_start = time.time()\n\n    for t in itertools.count():\n        ### 1. Check stopping criterion\n        if stopping_criterion is not None and stopping_criterion(env, t):\n            break\n\n        ### 2. Step the env and store the transition\n        # At this point, \"last_obs\" contains the latest observation that was\n        # recorded from the simulator. Here, your code needs to store this\n        # observation and its outcome (reward, next observation, etc.) into\n        # the replay buffer while stepping the simulator forward one step.\n        # At the end of this block of code, the simulator should have been\n        # advanced one step, and the replay buffer should contain one more\n        # transition.\n        # Specifically, last_obs must point to the new latest observation.\n        # Useful functions you'll need to call:\n        # obs, reward, done, info = env.step(action)\n        # this steps the environment forward one step\n        # obs = env.reset()\n        # this resets the environment if you reached an episode boundary.\n        # Don't forget to call env.reset() to get a new observation if done\n        # is true!!\n        # Note that you cannot use \"last_obs\" directly as input\n        # into your network, since it needs to be processed to include context\n        # from previous frames. You should check out the replay buffer\n        # implementation in dqn_utils.py to see what functionality the replay\n        # buffer exposes. The replay buffer has a function called\n        # encode_recent_observation that will take the latest observation\n        # that you pushed into the buffer and compute the corresponding\n        # input that should be given to a Q network by appending some\n        # previous frames.\n        # Don't forget to include epsilon greedy exploration!\n        # And remember that the first time you enter this loop, the model\n        # may not yet have been initialized (but of course, the first step\n        # might as well be random, since you haven't trained your net...)\n        #####\n\n        # This section is for one trial. Don't worry about batch sizes here.\n        rb_index = replay_buffer.store_frame(last_obs)\n\n        if (np.random.rand() < exploration.value(t) or not model_initialized):\n            action = np.random.randint(num_actions)    \n        else:\n            current_phi = replay_buffer.encode_recent_observation()\n            current_phi = np.expand_dims(current_phi, axis=0)\n            action = np.argmax(np.squeeze( \n                session.run(current_net, feed_dict={obs_t_ph: current_phi}) \n            ))\n\n        obs, reward, done, info = env.step(action)\n        replay_buffer.store_effect(rb_index, action, reward, done)\n        if done:\n            obs = env.reset()\n        last_obs = obs\n        #####\n\n        # at this point, the environment should have been advanced one step (and\n        # reset if done was true), and last_obs should point to the new latest\n        # observation\n\n        ### 3. Perform experience replay and train the network.\n        # note that this is only done if the replay buffer contains enough samples\n        # for us to learn something useful -- until then, the model will not be\n        # initialized and random actions should be taken\n        if (t > learning_starts and\n                t % learning_freq == 0 and\n                replay_buffer.can_sample(batch_size)):\n            # Here, you should perform training. Training consists of four steps:\n            # 3.a: use the replay buffer to sample a batch of transitions (see the\n            # replay buffer code for function definition, each batch that you sample\n            # should consist of current observations, current actions, rewards,\n            # next observations, and done indicator).\n            # 3.b: initialize the model if it has not been initialized yet; to do\n            # that, call\n            #    initialize_interdependent_variables(session, tf.global_variables(), {\n            #        obs_t_ph: obs_t_batch,\n            #        obs_tp1_ph: obs_tp1_batch,\n            #    })\n            # where obs_t_batch and obs_tp1_batch are the batches of observations at\n            # the current and next time step. The boolean variable model_initialized\n            # indicates whether or not the model has been initialized.\n            # Remember that you have to update the target network too (see 3.d)!\n            # 3.c: train the model. To do this, you'll need to use the train_fn and\n            # total_error ops that were created earlier: total_error is what you\n            # created to compute the total Bellman error in a batch, and train_fn\n            # will actually perform a gradient step and update the network parameters\n            # to reduce total_error. When calling session.run on these you'll need to\n            # populate the following placeholders:\n            # obs_t_ph\n            # act_t_ph\n            # rew_t_ph\n            # obs_tp1_ph\n            # done_mask_ph\n            # (this is needed for computing total_error)\n            # learning_rate -- you can get this from optimizer_spec.lr_schedule.value(t)\n            # (this is needed by the optimizer to choose the learning rate)\n            # 3.d: periodically update the target network by calling\n            # session.run(update_target_fn)\n            # you should update every target_update_freq steps, and you may find the\n            # variable num_param_updates useful for this (it was initialized to 0)\n            #####\n            obs_t_batch, act_batch, rew_batch, obs_tp1_batch, done_mask = \\\n                    replay_buffer.sample(batch_size)\n\n            if (not model_initialized):\n                initialize_interdependent_variables(session, tf.global_variables(), {\n                    obs_t_ph: obs_t_batch,\n                    obs_tp1_ph: obs_tp1_batch,\n                })\n                model_initialized = True\n\n            session.run(train_fn, \n                        feed_dict = {\n                            obs_t_ph: obs_t_batch,\n                            act_t_ph: act_batch,\n                            rew_t_ph: rew_batch,\n                            obs_tp1_ph: obs_tp1_batch,\n                            done_mask_ph: done_mask,\n                            learning_rate: optimizer_spec.lr_schedule.value(t)\n                        }\n            )\n\n            # After some number of xp-replay updates, update the target network.\n            if (num_param_updates % target_update_freq):\n                session.run(update_target_fn)\n            num_param_updates += 1\n            #####\n\n        ### 4. Log progress. \n        episode_rewards = get_wrapper_by_name(env, \"Monitor\").get_episode_rewards()\n        if len(episode_rewards) > 0:\n            mean_episode_reward = np.mean(episode_rewards[-100:])\n        if len(episode_rewards) > 100:\n            best_mean_episode_reward = max(best_mean_episode_reward, mean_episode_reward)\n\n        # Report results, write to file. If case handles very last iteration.\n        if ((t % LOG_EVERY_N_STEPS == 0 and model_initialized) or\n            (stopping_criterion is not None and stopping_criterion(env,t+1))):\n\n            current_episode_reward = episode_rewards[-1]\n            print(\"\\nTimestep: {}\".format(t))\n            print(\"mean reward (100 episodes): {:.4f}\".format(mean_episode_reward))\n            print(\"best mean reward: {:.4f}\".format(best_mean_episode_reward))\n            print(\"current episode reward: {:.4f}\".format(current_episode_reward))\n            print(\"episodes: {}\".format(len(episode_rewards)))\n            print(\"exploration: {:.5f}\".format(exploration.value(t)))\n            print(\"learning_rate: {:.5f}\".format(optimizer_spec.lr_schedule.value(t)))\n            seconds = (time.time()-t_start)\n            hours = (time.time()-t_start) / (60*60)\n            print(\"elapsed time: {:.1f} seconds ({:.2f} hours)\".format(seconds,hours))\n            sys.stdout.flush()\n            scores_for_log.append((t, \n                                   mean_episode_reward, \n                                   best_mean_episode_reward,\n                                   current_episode_reward))\n            with open('./logs_pkls/'+log_file,'wb') as f:\n                pickle.dump(scores_for_log, f)\n                pickle.dump(episode_rewards, f)\n"
  },
  {
    "path": "dqn/dqn_utils.py",
    "content": "\"\"\"This file includes a collection of utility functions that are useful for\nimplementing DQN.\"\"\"\nimport gym\nimport tensorflow as tf\nimport numpy as np\nimport random\n\ndef huber_loss(x, delta=1.0):\n    # https://en.wikipedia.org/wiki/Huber_loss\n    return tf.select(\n        tf.abs(x) < delta,\n        tf.square(x) * 0.5,\n        delta * (tf.abs(x) - 0.5 * delta)\n    )\n\ndef sample_n_unique(sampling_f, n):\n    \"\"\"Helper function. Given a function `sampling_f` that returns\n    comparable objects, sample n such unique objects.\n    \"\"\"\n    res = []\n    while len(res) < n:\n        candidate = sampling_f()\n        if candidate not in res:\n            res.append(candidate)\n    return res\n\nclass Schedule(object):\n    def value(self, t):\n        \"\"\"Value of the schedule at time t\"\"\"\n        raise NotImplementedError()\n\nclass ConstantSchedule(object):\n    def __init__(self, value):\n        \"\"\"Value remains constant over time.\n        Parameters\n        ----------\n        value: float\n            Constant value of the schedule\n        \"\"\"\n        self._v = value\n\n    def value(self, t):\n        \"\"\"See Schedule.value\"\"\"\n        return self._v\n\ndef linear_interpolation(l, r, alpha):\n    return l + alpha * (r - l)\n\nclass PiecewiseSchedule(object):\n    def __init__(self, endpoints, interpolation=linear_interpolation, outside_value=None):\n        \"\"\"Piecewise schedule.\n        endpoints: [(int, int)]\n            list of pairs `(time, value)` meanining that schedule should output\n            `value` when `t==time`. All the values for time must be sorted in\n            an increasing order. When t is between two times, e.g. `(time_a, value_a)`\n            and `(time_b, value_b)`, such that `time_a <= t < time_b` then value outputs\n            `interpolation(value_a, value_b, alpha)` where alpha is a fraction of\n            time passed between `time_a` and `time_b` for time `t`.\n        interpolation: lambda float, float, float: float\n            a function that takes value to the left and to the right of t according\n            to the `endpoints`. Alpha is the fraction of distance from left endpoint to\n            right endpoint that t has covered. See linear_interpolation for example.\n        outside_value: float\n            if the value is requested outside of all the intervals sepecified in\n            `endpoints` this value is returned. If None then AssertionError is\n            raised when outside value is requested.\n        \"\"\"\n        idxes = [e[0] for e in endpoints]\n        assert idxes == sorted(idxes)\n        self._interpolation = interpolation\n        self._outside_value = outside_value\n        self._endpoints      = endpoints\n\n    def value(self, t):\n        \"\"\"See Schedule.value\"\"\"\n        for (l_t, l), (r_t, r) in zip(self._endpoints[:-1], self._endpoints[1:]):\n            if l_t <= t and t < r_t:\n                alpha = float(t - l_t) / (r_t - l_t)\n                return self._interpolation(l, r, alpha)\n\n        # t does not belong to any of the pieces, so doom.\n        assert self._outside_value is not None\n        return self._outside_value\n\nclass LinearSchedule(object):\n    def __init__(self, schedule_timesteps, final_p, initial_p=1.0):\n        \"\"\"Linear interpolation between initial_p and final_p over\n        schedule_timesteps. After this many timesteps pass final_p is\n        returned.\n        Parameters\n        ----------\n        schedule_timesteps: int\n            Number of timesteps for which to linearly anneal initial_p\n            to final_p\n        initial_p: float\n            initial output value\n        final_p: float\n            final output value\n        \"\"\"\n        self.schedule_timesteps = schedule_timesteps\n        self.final_p            = final_p\n        self.initial_p          = initial_p\n\n    def value(self, t):\n        \"\"\"See Schedule.value\"\"\"\n        fraction  = min(float(t) / self.schedule_timesteps, 1.0)\n        return self.initial_p + fraction * (self.final_p - self.initial_p)\n\ndef compute_exponential_averages(variables, decay):\n    \"\"\"Given a list of tensorflow scalar variables\n    create ops corresponding to their exponential\n    averages\n    Parameters\n    ----------\n    variables: [tf.Tensor]\n        List of scalar tensors.\n    Returns\n    -------\n    averages: [tf.Tensor]\n        List of scalar tensors corresponding to averages\n        of al the `variables` (in order)\n    apply_op: tf.runnable\n        Op to be run to update the averages with current value\n        of variables.\n    \"\"\"\n    averager = tf.train.ExponentialMovingAverage(decay=decay)\n    apply_op = averager.apply(variables)\n    return [averager.average(v) for v in variables], apply_op\n\ndef minimize_and_clip(optimizer, objective, var_list, clip_val=10):\n    \"\"\"Minimized `objective` using `optimizer` w.r.t. variables in\n    `var_list` while ensure the norm of the gradients for each\n    variable is clipped to `clip_val`\n    \"\"\"\n    gradients = optimizer.compute_gradients(objective, var_list=var_list)\n    for i, (grad, var) in enumerate(gradients):\n        if grad is not None:\n            gradients[i] = (tf.clip_by_norm(grad, clip_val), var)\n    return optimizer.apply_gradients(gradients)\n\ndef initialize_interdependent_variables(session, vars_list, feed_dict):\n    \"\"\"Initialize a list of variables one at a time, which is useful if\n    initialization of some variables depends on initialization of the others.\n    \"\"\"\n    vars_left = vars_list\n    while len(vars_left) > 0:\n        new_vars_left = []\n        for v in vars_left:\n            try:\n                # If using an older version of TensorFlow, uncomment the line\n                # below and comment out the line after it.\n\t\t#session.run(tf.initialize_variables([v]), feed_dict)\n                session.run(tf.variables_initializer([v]), feed_dict)\n            except tf.errors.FailedPreconditionError:\n                new_vars_left.append(v)\n        if len(new_vars_left) >= len(vars_left):\n            # This can happend if the variables all depend on each other, or more likely if there's\n            # another variable outside of the list, that still needs to be initialized. This could be\n            # detected here, but life's finite.\n            raise Exception(\"Cycle in variable dependencies, or extenrnal precondition unsatisfied.\")\n        else:\n            vars_left = new_vars_left\n\ndef get_wrapper_by_name(env, classname):\n    currentenv = env\n    while True:\n        if classname in currentenv.__class__.__name__:\n            return currentenv\n        elif isinstance(env, gym.Wrapper):\n            currentenv = currentenv.env\n        else:\n            raise ValueError(\"Couldn't find wrapper named %s\"%classname)\n\nclass ReplayBuffer(object):\n    def __init__(self, size, frame_history_len):\n        \"\"\"This is a memory efficient implementation of the replay buffer.\n\n        The sepecific memory optimizations use here are:\n            - only store each frame once rather than k times\n              even if every observation normally consists of k last frames\n            - store frames as np.uint8 (actually it is most time-performance\n              to cast them back to float32 on GPU to minimize memory transfer\n              time)\n            - store frame_t and frame_(t+1) in the same buffer.\n\n        For the typical use case in Atari Deep RL buffer with 1M frames the total\n        memory footprint of this buffer is 10^6 * 84 * 84 bytes ~= 7 gigabytes\n\n        Warning! Assumes that returning frame of zeros at the beginning\n        of the episode, when there is less frames than `frame_history_len`,\n        is acceptable.\n\n        Parameters\n        ----------\n        size: int\n            Max number of transitions to store in the buffer. When the buffer\n            overflows the old memories are dropped.\n        frame_history_len: int\n            Number of memories to be retried for each observation.\n        \"\"\"\n        self.size = size\n        self.frame_history_len = frame_history_len\n\n        self.next_idx      = 0\n        self.num_in_buffer = 0\n\n        self.obs      = None\n        self.action   = None\n        self.reward   = None\n        self.done     = None\n\n    def can_sample(self, batch_size):\n        \"\"\"Returns true if `batch_size` different transitions can be sampled from the buffer.\"\"\"\n        return batch_size + 1 <= self.num_in_buffer\n\n    def _encode_sample(self, idxes):\n        obs_batch      = np.concatenate([self._encode_observation(idx)[None] for idx in idxes], 0)\n        act_batch      = self.action[idxes]\n        rew_batch      = self.reward[idxes]\n        next_obs_batch = np.concatenate([self._encode_observation(idx + 1)[None] for idx in idxes], 0)\n        done_mask      = np.array([1.0 if self.done[idx] else 0.0 for idx in idxes], dtype=np.float32)\n\n        return obs_batch, act_batch, rew_batch, next_obs_batch, done_mask\n\n\n    def sample(self, batch_size):\n        \"\"\"Sample `batch_size` different transitions.\n\n        i-th sample transition is the following:\n\n        when observing `obs_batch[i]`, action `act_batch[i]` was taken,\n        after which reward `rew_batch[i]` was received and subsequent\n        observation  next_obs_batch[i] was observed, unless the epsiode\n        was done which is represented by `done_mask[i]` which is equal\n        to 1 if episode has ended as a result of that action.\n\n        Parameters\n        ----------\n        batch_size: int\n            How many transitions to sample.\n\n        Returns\n        -------\n        obs_batch: np.array\n            Array of shape\n            (batch_size, img_h, img_w, img_c * frame_history_len)\n            and dtype np.uint8\n        act_batch: np.array\n            Array of shape (batch_size,) and dtype np.int32\n        rew_batch: np.array\n            Array of shape (batch_size,) and dtype np.float32\n        next_obs_batch: np.array\n            Array of shape\n            (batch_size, img_h, img_w, img_c * frame_history_len)\n            and dtype np.uint8\n        done_mask: np.array\n            Array of shape (batch_size,) and dtype np.float32\n        \"\"\"\n        assert self.can_sample(batch_size)\n        idxes = sample_n_unique(lambda: random.randint(0, self.num_in_buffer - 2), batch_size)\n        return self._encode_sample(idxes)\n\n    def encode_recent_observation(self):\n        \"\"\"Return the most recent `frame_history_len` frames.\n\n        Returns\n        -------\n        observation: np.array\n            Array of shape (img_h, img_w, img_c * frame_history_len)\n            and dtype np.uint8, where observation[:, :, i*img_c:(i+1)*img_c]\n            encodes frame at time `t - frame_history_len + i`\n        \"\"\"\n        assert self.num_in_buffer > 0\n        return self._encode_observation((self.next_idx - 1) % self.size)\n\n    def _encode_observation(self, idx):\n        end_idx   = idx + 1 # make noninclusive\n        start_idx = end_idx - self.frame_history_len\n        # this checks if we are using low-dimensional observations, such as RAM\n        # state, in which case we just directly return the latest RAM.\n        if len(self.obs.shape) == 2:\n            return self.obs[end_idx-1]\n        # if there weren't enough frames ever in the buffer for context\n        if start_idx < 0 and self.num_in_buffer != self.size:\n            start_idx = 0\n        for idx in range(start_idx, end_idx - 1):\n            if self.done[idx % self.size]:\n                start_idx = idx + 1\n        missing_context = self.frame_history_len - (end_idx - start_idx)\n        # if zero padding is needed for missing context\n        # or we are on the boundry of the buffer\n        if start_idx < 0 or missing_context > 0:\n            frames = [np.zeros_like(self.obs[0]) for _ in range(missing_context)]\n            for idx in range(start_idx, end_idx):\n                frames.append(self.obs[idx % self.size])\n            return np.concatenate(frames, 2)\n        else:\n            # this optimization has potential to saves about 30% compute time \\o/\n            img_h, img_w = self.obs.shape[1], self.obs.shape[2]\n            return self.obs[start_idx:end_idx].transpose(1, 2, 0, 3).reshape(img_h, img_w, -1)\n\n    def store_frame(self, frame):\n        \"\"\"Store a single frame in the buffer at the next available index, overwriting\n        old frames if necessary.\n\n        Parameters\n        ----------\n        frame: np.array\n            Array of shape (img_h, img_w, img_c) and dtype np.uint8\n            the frame to be stored\n\n        Returns\n        -------\n        idx: int\n            Index at which the frame is stored. To be used for `store_effect` later.\n        \"\"\"\n        if self.obs is None:\n            self.obs      = np.empty([self.size] + list(frame.shape), dtype=np.uint8)\n            self.action   = np.empty([self.size],                     dtype=np.int32)\n            self.reward   = np.empty([self.size],                     dtype=np.float32)\n            self.done     = np.empty([self.size],                     dtype=np.bool)\n        self.obs[self.next_idx] = frame\n\n        ret = self.next_idx\n        self.next_idx = (self.next_idx + 1) % self.size\n        self.num_in_buffer = min(self.size, self.num_in_buffer + 1)\n\n        return ret\n\n    def store_effect(self, idx, action, reward, done):\n        \"\"\"Store effects of action taken after observing frame stored at index\n        idx. The reason `store_frame` and `store_effect` is broken up into two\n        functions is so that once can call `encode_recent_observation` in\n        between.\n\n        Paramters\n        ---------\n        idx: int\n            Index in buffer of recently observed frame (returned by `store_frame`).\n        action: int\n            Action that was performed upon observing this frame.\n        reward: float\n            Reward that was received when the actions was performed.\n        done: bool\n            True if episode was finished after performing that action.\n        \"\"\"\n        self.action[idx] = action\n        self.reward[idx] = reward\n        self.done[idx]   = done\n\n"
  },
  {
    "path": "dqn/logs_pkls/BeamRider_s001.pkl",
    "content": "(lp0\n(I60000\ncnumpy.core.multiarray\nscalar\np1\n(cnumpy\ndtype\np2\n(S'f8'\np3\nI0\nI1\ntp4\nRp5\n(I3\nS'<'\np6\nNNNI-1\nI-1\nI0\ntp7\nbS'8\\xbd\\xe9Mo\\x1au@'\np8\ntp9\nRp10\nF-inf\nF352.0\ntp11\na(I70000\ng1\n(g5\nS'\"5\\xc1x+;u@'\np12\ntp13\nRp14\nF-inf\nF396.0\ntp15\na(I80000\ng1\n(g5\nS'\\xef\\xee\\xee\\xee\\xee.u@'\np16\ntp17\nRp18\nF-inf\nF308.0\ntp19\na(I90000\ng1\n(g5\nS'\\xb5\\xb4\\xb4\\xb4\\xb4\\xa4u@'\np20\ntp21\nRp22\nF-inf\nF352.0\ntp23\na(I100000\ng1\n(g5\nS'\\xfdb\\xc9/\\x96\\xfcu@'\np24\ntp25\nRp26\nF-inf\nF900.0\ntp27\na(I110000\ng1\n(g5\nS'\\xa9]\\x89\\xda\\x95(v@'\np28\ntp29\nRp30\nF-inf\nF308.0\ntp31\na(I120000\ng1\n(g5\nS'\\xde\\xdd\\xdd\\xdd\\xdd\\xfdu@'\np32\ntp33\nRp34\nF-inf\nF264.0\ntp35\na(I130000\ng1\n(g5\nS'\\x99\\x86\\xedfy\\xd2u@'\np36\ntp37\nRp38\nF-inf\nF308.0\ntp39\na(I140000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb0u@'\np40\ntp41\nRp42\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xccu@'\np43\ntp44\nRp45\nF264.0\ntp46\na(I150000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x7fu@'\np47\ntp48\nRp49\ng45\nF352.0\ntp50\na(I160000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xcdu@'\np51\ntp52\nRp53\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf0u@'\np54\ntp55\nRp56\nF352.0\ntp57\na(I170000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQhv@'\np58\ntp59\nRp60\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQhv@'\np61\ntp62\nRp63\nF352.0\ntp64\na(I180000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xa7v@'\np65\ntp66\nRp67\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xbcv@'\np68\ntp69\nRp70\nF440.0\ntp71\na(I190000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQhv@'\np72\ntp73\nRp74\ng70\nF396.0\ntp75\na(I200000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8av@'\np76\ntp77\nRp78\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xd8v@'\np79\ntp80\nRp81\nF264.0\ntp82\na(I210000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1Jv@'\np83\ntp84\nRp85\ng81\nF176.0\ntp86\na(I220000\ng1\n(g5\nS'q=\\n\\xd7\\xa3 v@'\np87\ntp88\nRp89\ng81\nF176.0\ntp90\na(I230000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGav@'\np91\ntp92\nRp93\ng81\nF264.0\ntp94\na(I240000\ng1\n(g5\nS\"\\xd7\\xa3p=\\n'v@\"\np95\ntp96\nRp97\ng81\nF440.0\ntp98\na(I250000\ng1\n(g5\nS'33333Cv@'\np99\ntp100\nRp101\ng81\nF308.0\ntp102\na(I260000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xb3v@'\np103\ntp104\nRp105\ng81\nF440.0\ntp106\na(I270000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xb3v@'\np107\ntp108\nRp109\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xecv@'\np110\ntp111\nRp112\nF352.0\ntp113\na(I280000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x1dw@'\np114\ntp115\nRp116\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x1dw@'\np117\ntp118\nRp119\nF176.0\ntp120\na(I290000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x90v@'\np121\ntp122\nRp123\ng119\nF440.0\ntp124\na(I300000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xd8u@'\np125\ntp126\nRp127\ng119\nF132.0\ntp128\na(I310000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xeeu@'\np129\ntp130\nRp131\ng119\nF484.0\ntp132\na(I320000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^v@'\np133\ntp134\nRp135\ng119\nF176.0\ntp136\na(I330000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xf5u@'\np137\ntp138\nRp139\ng119\nF176.0\ntp140\na(I340000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z4v@'\np141\ntp142\nRp143\ng119\nF484.0\ntp144\na(I350000\ng1\n(g5\nS'fffff\\xd6v@'\np145\ntp146\nRp147\ng119\nF220.0\ntp148\na(I360000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcfv@'\np149\ntp150\nRp151\ng119\nF484.0\ntp152\na(I370000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x95v@'\np153\ntp154\nRp155\ng119\nF264.0\ntp156\na(I380000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8cv@'\np157\ntp158\nRp159\ng119\nF396.0\ntp160\na(I390000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xb7v@'\np161\ntp162\nRp163\ng119\nF352.0\ntp164\na(I400000\ng1\n(g5\nS'q=\\n\\xd7\\xa3pv@'\np165\ntp166\nRp167\ng119\nF440.0\ntp168\na(I410000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fbv@'\np169\ntp170\nRp171\ng119\nF572.0\ntp172\na(I420000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xe8v@'\np173\ntp174\nRp175\ng119\nF352.0\ntp176\na(I430000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1euw@'\np177\ntp178\nRp179\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1euw@'\np180\ntp181\nRp182\nF440.0\ntp183\na(I440000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xc3w@'\np184\ntp185\nRp186\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xc3w@'\np187\ntp188\nRp189\nF756.0\ntp190\na(I450000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Ix@'\np191\ntp192\nRp193\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2ex@'\np194\ntp195\nRp196\nF264.0\ntp197\na(I460000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14Nw@'\np198\ntp199\nRp200\ng196\nF88.0\ntp201\na(I470000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x9bw@'\np202\ntp203\nRp204\ng196\nF660.0\ntp205\na(I480000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xccw@'\np206\ntp207\nRp208\ng196\nF352.0\ntp209\na(I490000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQxw@'\np210\ntp211\nRp212\ng196\nF528.0\ntp213\na(I500000\ng1\n(g5\nS'33333cw@'\np214\ntp215\nRp216\ng196\nF308.0\ntp217\na(I510000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQxw@'\np218\ntp219\nRp220\ng196\nF220.0\ntp221\na(I520000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQxw@'\np222\ntp223\nRp224\ng196\nF352.0\ntp225\na(I530000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xa9w@'\np226\ntp227\nRp228\ng196\nF396.0\ntp229\na(I540000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x1bx@'\np230\ntp231\nRp232\ng196\nF308.0\ntp233\na(I550000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xb1w@'\np234\ntp235\nRp236\ng196\nF176.0\ntp237\na(I560000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x95w@'\np238\ntp239\nRp240\ng196\nF484.0\ntp241\na(I570000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e%w@'\np242\ntp243\nRp244\ng196\nF264.0\ntp245\na(I580000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z4v@'\np246\ntp247\nRp248\ng196\nF220.0\ntp249\na(I590000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=v@'\np250\ntp251\nRp252\ng196\nF528.0\ntp253\na(I600000\ng1\n(g5\nS'q=\\n\\xd7\\xa3Pv@'\np254\ntp255\nRp256\ng196\nF88.0\ntp257\na(I610000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^v@'\np258\ntp259\nRp260\ng196\nF264.0\ntp261\na(I620000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^v@'\np262\ntp263\nRp264\ng196\nF308.0\ntp265\na(I630000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2ev@'\np266\ntp267\nRp268\ng196\nF396.0\ntp269\na(I640000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xe7u@'\np270\ntp271\nRp272\ng196\nF308.0\ntp273\na(I650000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x84u@'\np274\ntp275\nRp276\ng196\nF264.0\ntp277\na(I660000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99iu@'\np278\ntp279\nRp280\ng196\nF440.0\ntp281\na(I670000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xcdt@'\np282\ntp283\nRp284\ng196\nF132.0\ntp285\na(I680000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xe2t@'\np286\ntp287\nRp288\ng196\nF44.0\ntp289\na(I690000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xf7t@'\np290\ntp291\nRp292\ng196\nF352.0\ntp293\na(I700000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0cu@'\np294\ntp295\nRp296\ng196\nF220.0\ntp297\na(I710000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb!u@'\np298\ntp299\nRp300\ng196\nF88.0\ntp301\na(I720000\ng1\n(g5\nS'H\\xe1z\\x14\\xaewu@'\np302\ntp303\nRp304\ng196\nF220.0\ntp305\na(I730000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8nu@'\np306\ntp307\nRp308\ng196\nF308.0\ntp309\na(I740000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x8au@'\np310\ntp311\nRp312\ng196\nF352.0\ntp313\na(I750000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fRu@'\np314\ntp315\nRp316\ng196\nF484.0\ntp317\na(I760000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Yu@'\np318\ntp319\nRp320\ng196\nF264.0\ntp321\na(I770000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xa0u@'\np322\ntp323\nRp324\ng196\nF440.0\ntp325\na(I780000\ng1\n(g5\nS'\\xa4p=\\n\\xd73v@'\np326\ntp327\nRp328\ng196\nF264.0\ntp329\na(I790000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eev@'\np330\ntp331\nRp332\ng196\nF660.0\ntp333\na(I800000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2Uv@'\np334\ntp335\nRp336\ng196\nF264.0\ntp337\na(I810000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8Nv@'\np338\ntp339\nRp340\ng196\nF220.0\ntp341\na(I820000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7u@'\np342\ntp343\nRp344\ng196\nF220.0\ntp345\na(I830000\ng1\n(g5\nS'=\\n\\xd7\\xa3p]v@'\np346\ntp347\nRp348\ng196\nF308.0\ntp349\na(I840000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xb8v@'\np350\ntp351\nRp352\ng196\nF616.0\ntp353\na(I850000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdcv@'\np354\ntp355\nRp356\ng196\nF220.0\ntp357\na(I860000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb0v@'\np358\ntp359\nRp360\ng196\nF176.0\ntp361\na(I870000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x7fv@'\np362\ntp363\nRp364\ng196\nF220.0\ntp365\na(I880000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x0ev@'\np366\ntp367\nRp368\ng196\nF352.0\ntp369\na(I890000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x97u@'\np370\ntp371\nRp372\ng196\nF264.0\ntp373\na(I900000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85Ku@'\np374\ntp375\nRp376\ng196\nF804.0\ntp377\na(I910000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xd8u@'\np378\ntp379\nRp380\ng196\nF660.0\ntp381\na(I920000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xd1u@'\np382\ntp383\nRp384\ng196\nF88.0\ntp385\na(I930000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fRu@'\np386\ntp387\nRp388\ng196\nF176.0\ntp389\na(I940000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xd1u@'\np390\ntp391\nRp392\ng196\nF616.0\ntp393\na(I950000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fRu@'\np394\ntp395\nRp396\ng196\nF484.0\ntp397\na(I960000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x1au@'\np398\ntp399\nRp400\ng196\nF484.0\ntp401\na(I970000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xbcu@'\np402\ntp403\nRp404\ng196\nF660.0\ntp405\na(I980000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xabv@'\np406\ntp407\nRp408\ng196\nF572.0\ntp409\na(I990000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\Ov@'\np410\ntp411\nRp412\ng196\nF220.0\ntp413\na(I1000000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xe5u@'\np414\ntp415\nRp416\ng196\nF440.0\ntp417\na(I1010000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQu@'\np418\ntp419\nRp420\ng196\nF264.0\ntp421\na(I1020000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQu@'\np422\ntp423\nRp424\ng196\nF440.0\ntp425\na(I1030000\ng1\n(g5\nS'\\xa4p=\\n\\xd7Cu@'\np426\ntp427\nRp428\ng196\nF616.0\ntp429\na(I1040000\ng1\n(g5\nS'33333\\x03v@'\np430\ntp431\nRp432\ng196\nF220.0\ntp433\na(I1050000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85;v@'\np434\ntp435\nRp436\ng196\nF528.0\ntp437\na(I1060000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^v@'\np438\ntp439\nRp440\ng196\nF44.0\ntp441\na(I1070000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.u@'\np442\ntp443\nRp444\ng196\nF176.0\ntp445\na(I1080000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5t@'\np446\ntp447\nRp448\ng196\nF572.0\ntp449\na(I1090000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xeet@'\np450\ntp451\nRp452\ng196\nF440.0\ntp453\na(I1100000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xaft@'\np454\ntp455\nRp456\ng196\nF352.0\ntp457\na(I1110000\ng1\n(g5\nS\"\\xd7\\xa3p=\\n'u@\"\np458\ntp459\nRp460\ng196\nF88.0\ntp461\na(I1120000\ng1\n(g5\nS'\\xd7\\xa3p=\\nwt@'\np462\ntp463\nRp464\ng196\nF352.0\ntp465\na(I1130000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccLt@'\np466\ntp467\nRp468\ng196\nF440.0\ntp469\na(I1140000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xaft@'\np470\ntp471\nRp472\ng196\nF308.0\ntp473\na(I1150000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQXu@'\np474\ntp475\nRp476\ng196\nF528.0\ntp477\na(I1160000\ng1\n(g5\nS'=\\n\\xd7\\xa3pmu@'\np478\ntp479\nRp480\ng196\nF352.0\ntp481\na(I1170000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x97u@'\np482\ntp483\nRp484\ng196\nF220.0\ntp485\na(I1180000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xecu@'\np486\ntp487\nRp488\ng196\nF176.0\ntp489\na(I1190000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1eu@'\np490\ntp491\nRp492\ng196\nF220.0\ntp493\na(I1200000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xf4t@'\np494\ntp495\nRp496\ng196\nF484.0\ntp497\na(I1210000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xa0t@'\np498\ntp499\nRp500\ng196\nF220.0\ntp501\na(I1220000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xb5t@'\np502\ntp503\nRp504\ng196\nF440.0\ntp505\na(I1230000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00Pu@'\np506\ntp507\nRp508\ng196\nF264.0\ntp509\na(I1240000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14^u@'\np510\ntp511\nRp512\ng196\nF660.0\ntp513\na(I1250000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1eu@'\np514\ntp515\nRp516\ng196\nF660.0\ntp517\na(I1260000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5Hu@'\np518\ntp519\nRp520\ng196\nF308.0\ntp521\na(I1270000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(lu@'\np522\ntp523\nRp524\ng196\nF396.0\ntp525\na(I1280000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x98t@'\np526\ntp527\nRp528\ng196\nF132.0\ntp529\na(I1290000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x8bt@'\np530\ntp531\nRp532\ng196\nF708.0\ntp533\na(I1300000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x000t@'\np534\ntp535\nRp536\ng196\nF88.0\ntp537\na(I1310000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xb1s@'\np538\ntp539\nRp540\ng196\nF352.0\ntp541\na(I1320000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x1at@'\np542\ntp543\nRp544\ng196\nF176.0\ntp545\na(I1330000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eEt@'\np546\ntp547\nRp548\ng196\nF396.0\ntp549\na(I1340000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xcat@'\np550\ntp551\nRp552\ng196\nF484.0\ntp553\na(I1350000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xfct@'\np554\ntp555\nRp556\ng196\nF352.0\ntp557\na(I1360000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^u@'\np558\ntp559\nRp560\ng196\nF440.0\ntp561\na(I1370000\ng1\n(g5\nS'fffff&u@'\np562\ntp563\nRp564\ng196\nF440.0\ntp565\na(I1380000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xcat@'\np566\ntp567\nRp568\ng196\nF132.0\ntp569\na(I1390000\ng1\n(g5\nS'\\n\\xd7\\xa3p=Zt@'\np570\ntp571\nRp572\ng196\nF308.0\ntp573\na(I1400000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGat@'\np574\ntp575\nRp576\ng196\nF396.0\ntp577\na(I1410000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x84t@'\np578\ntp579\nRp580\ng196\nF132.0\ntp581\na(I1420000\ng1\n(g5\nS'33333St@'\np582\ntp583\nRp584\ng196\nF308.0\ntp585\na(I1430000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\ot@'\np586\ntp587\nRp588\ng196\nF308.0\ntp589\na(I1440000\ng1\n(g5\nS'33333\\xc3t@'\np590\ntp591\nRp592\ng196\nF616.0\ntp593\na(I1450000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xa4u@'\np594\ntp595\nRp596\ng196\nF660.0\ntp597\na(I1460000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xceu@'\np598\ntp599\nRp600\ng196\nF132.0\ntp601\na(I1470000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:u@'\np602\ntp603\nRp604\ng196\nF132.0\ntp605\na(I1480000\ng1\n(g5\nS'33333su@'\np606\ntp607\nRp608\ng196\nF528.0\ntp609\na(I1490000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2%u@'\np610\ntp611\nRp612\ng196\nF352.0\ntp613\na(I1500000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(lu@'\np614\ntp615\nRp616\ng196\nF220.0\ntp617\na(I1510000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x88u@'\np618\ntp619\nRp620\ng196\nF176.0\ntp621\na(I1520000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc7u@'\np622\ntp623\nRp624\ng196\nF352.0\ntp625\na(I1530000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:u@'\np626\ntp627\nRp628\ng196\nF220.0\ntp629\na(I1540000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xceu@'\np630\ntp631\nRp632\ng196\nF176.0\ntp633\na(I1550000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xdcu@'\np634\ntp635\nRp636\ng196\nF264.0\ntp637\na(I1560000\ng1\n(g5\nS'\\xd7\\xa3p=\\nWu@'\np638\ntp639\nRp640\ng196\nF308.0\ntp641\na(I1570000\ng1\n(g5\nS'fffff\\x96u@'\np642\ntp643\nRp644\ng196\nF308.0\ntp645\na(I1580000\ng1\n(g5\nS'33333su@'\np646\ntp647\nRp648\ng196\nF528.0\ntp649\na(I1590000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xf4t@'\np650\ntp651\nRp652\ng196\nF264.0\ntp653\na(I1600000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xbes@'\np654\ntp655\nRp656\ng196\nF264.0\ntp657\na(I1610000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xf0s@'\np658\ntp659\nRp660\ng196\nF440.0\ntp661\na(I1620000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ(t@'\np662\ntp663\nRp664\ng196\nF396.0\ntp665\na(I1630000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Yt@'\np666\ntp667\nRp668\ng196\nF396.0\ntp669\na(I1640000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x1at@'\np670\ntp671\nRp672\ng196\nF220.0\ntp673\na(I1650000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xb7s@'\np674\ntp675\nRp676\ng196\nF220.0\ntp677\na(I1660000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x7fs@'\np678\ntp679\nRp680\ng196\nF308.0\ntp681\na(I1670000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb1s@'\np682\ntp683\nRp684\ng196\nF176.0\ntp685\na(I1680000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQxs@'\np686\ntp687\nRp688\ng196\nF176.0\ntp689\na(I1690000\ng1\n(g5\nS'fffff\\x86s@'\np690\ntp691\nRp692\ng196\nF352.0\ntp693\na(I1700000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x8ds@'\np694\ntp695\nRp696\ng196\nF352.0\ntp697\na(I1710000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQxs@'\np698\ntp699\nRp700\ng196\nF220.0\ntp701\na(I1720000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xb7s@'\np702\ntp703\nRp704\ng196\nF176.0\ntp705\na(I1730000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGqs@'\np706\ntp707\nRp708\ng196\nF220.0\ntp709\na(I1740000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xa9s@'\np710\ntp711\nRp712\ng196\nF616.0\ntp713\na(I1750000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#s@'\np714\ntp715\nRp716\ng196\nF440.0\ntp717\na(I1760000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x00s@'\np718\ntp719\nRp720\ng196\nF484.0\ntp721\na(I1770000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xc1r@'\np722\ntp723\nRp724\ng196\nF220.0\ntp725\na(I1780000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xf9r@'\np726\ntp727\nRp728\ng196\nF88.0\ntp729\na(I1790000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xddr@'\np730\ntp731\nRp732\ng196\nF132.0\ntp733\na(I1800000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14Ns@'\np734\ntp735\nRp736\ng196\nF572.0\ntp737\na(I1810000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xbar@'\np738\ntp739\nRp740\ng196\nF220.0\ntp741\na(I1820000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^r@'\np742\ntp743\nRp744\ng196\nF176.0\ntp745\na(I1830000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Ir@'\np746\ntp747\nRp748\ng196\nF572.0\ntp749\na(I1840000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xfcq@'\np750\ntp751\nRp752\ng196\nF484.0\ntp753\na(I1850000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\nr@'\np754\ntp755\nRp756\ng196\nF396.0\ntp757\na(I1860000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xc3q@'\np758\ntp759\nRp760\ng196\nF88.0\ntp761\na(I1870000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x18r@'\np762\ntp763\nRp764\ng196\nF308.0\ntp765\na(I1880000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x11r@'\np766\ntp767\nRp768\ng196\nF352.0\ntp769\na(I1890000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fBr@'\np770\ntp771\nRp772\ng196\nF132.0\ntp773\na(I1900000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x97r@'\np774\ntp775\nRp776\ng196\nF660.0\ntp777\na(I1910000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2er@'\np778\ntp779\nRp780\ng196\nF176.0\ntp781\na(I1920000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85;r@'\np782\ntp783\nRp784\ng196\nF308.0\ntp785\na(I1930000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z4r@'\np786\ntp787\nRp788\ng196\nF484.0\ntp789\na(I1940000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xacr@'\np790\ntp791\nRp792\ng196\nF396.0\ntp793\na(I1950000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85;r@'\np794\ntp795\nRp796\ng196\nF264.0\ntp797\na(I1960000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb1s@'\np798\ntp799\nRp800\ng196\nF484.0\ntp801\na(I1970000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xa2s@'\np802\ntp803\nRp804\ng196\nF528.0\ntp805\na(I1980000\ng1\n(g5\nS'\\n\\xd7\\xa3p=js@'\np806\ntp807\nRp808\ng196\nF396.0\ntp809\na(I1990000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x1cs@'\np810\ntp811\nRp812\ng196\nF176.0\ntp813\na(I2000000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xa5r@'\np814\ntp815\nRp816\ng196\nF308.0\ntp817\na(I2010000\ng1\n(g5\nS'\\xa4p=\\n\\xd7sr@'\np818\ntp819\nRp820\ng196\nF308.0\ntp821\na(I2020000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Ir@'\np822\ntp823\nRp824\ng196\nF176.0\ntp825\na(I2030000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xe0q@'\np826\ntp827\nRp828\ng196\nF440.0\ntp829\na(I2040000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xa0q@'\np830\ntp831\nRp832\ng196\nF352.0\ntp833\na(I2050000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xcaq@'\np834\ntp835\nRp836\ng196\nF352.0\ntp837\na(I2060000\ng1\n(g5\nS'=\\n\\xd7\\xa3p-r@'\np838\ntp839\nRp840\ng196\nF264.0\ntp841\na(I2070000\ng1\n(g5\nS'=\\n\\xd7\\xa3p-r@'\np842\ntp843\nRp844\ng196\nF220.0\ntp845\na(I2080000\ng1\n(g5\nS'fffff&r@'\np846\ntp847\nRp848\ng196\nF308.0\ntp849\na(I2090000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z4r@'\np850\ntp851\nRp852\ng196\nF220.0\ntp853\na(I2100000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99q@'\np854\ntp855\nRp856\ng196\nF132.0\ntp857\na(I2110000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xfep@'\np858\ntp859\nRp860\ng196\nF352.0\ntp861\na(I2120000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eEq@'\np862\ntp863\nRp864\ng196\nF528.0\ntp865\na(I2130000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x18r@'\np866\ntp867\nRp868\ng196\nF484.0\ntp869\na(I2140000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xe0q@'\np870\ntp871\nRp872\ng196\nF88.0\ntp873\na(I2150000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\nr@'\np874\ntp875\nRp876\ng196\nF176.0\ntp877\na(I2160000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x1fr@'\np878\ntp879\nRp880\ng196\nF176.0\ntp881\na(I2170000\ng1\n(g5\nS'fffff&r@'\np882\ntp883\nRp884\ng196\nF308.0\ntp885\na(I2180000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xd8q@'\np886\ntp887\nRp888\ng196\nF88.0\ntp889\na(I2190000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xd8q@'\np890\ntp891\nRp892\ng196\nF264.0\ntp893\na(I2200000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0cq@'\np894\ntp895\nRp896\ng196\nF88.0\ntp897\na(I2210000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xcdp@'\np898\ntp899\nRp900\ng196\nF220.0\ntp901\na(I2220000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd4p@'\np902\ntp903\nRp904\ng196\nF88.0\ntp905\na(I2230000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x95p@'\np906\ntp907\nRp908\ng196\nF396.0\ntp909\na(I2240000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xe2p@'\np910\ntp911\nRp912\ng196\nF176.0\ntp913\na(I2250000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(Lq@'\np914\ntp915\nRp916\ng196\nF396.0\ntp917\na(I2260000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb!q@'\np918\ntp919\nRp920\ng196\nF132.0\ntp921\na(I2270000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xaap@'\np922\ntp923\nRp924\ng196\nF132.0\ntp925\na(I2280000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x000q@'\np926\ntp927\nRp928\ng196\nF308.0\ntp929\na(I2290000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14>q@'\np930\ntp931\nRp932\ng196\nF308.0\ntp933\na(I2300000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x84q@'\np934\ntp935\nRp936\ng196\nF132.0\ntp937\na(I2310000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99q@'\np938\ntp939\nRp940\ng196\nF264.0\ntp941\na(I2320000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\oq@'\np942\ntp943\nRp944\ng196\nF44.0\ntp945\na(I2330000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x13q@'\np946\ntp947\nRp948\ng196\nF0.0\ntp949\na(I2340000\ng1\n(g5\nS'\\xa4p=\\n\\xd7cp@'\np950\ntp951\nRp952\ng196\nF220.0\ntp953\na(I2350000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8Np@'\np954\ntp955\nRp956\ng196\nF88.0\ntp957\na(I2360000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x87p@'\np958\ntp959\nRp960\ng196\nF132.0\ntp961\na(I2370000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14>q@'\np962\ntp963\nRp964\ng196\nF308.0\ntp965\na(I2380000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(Lq@'\np966\ntp967\nRp968\ng196\nF484.0\ntp969\na(I2390000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xe9p@'\np970\ntp971\nRp972\ng196\nF264.0\ntp973\na(I2400000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0cq@'\np974\ntp975\nRp976\ng196\nF484.0\ntp977\na(I2410000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb!q@'\np978\ntp979\nRp980\ng196\nF264.0\ntp981\na(I2420000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xe9p@'\np982\ntp983\nRp984\ng196\nF88.0\ntp985\na(I2430000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd4p@'\np986\ntp987\nRp988\ng196\nF132.0\ntp989\na(I2440000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5xp@'\np990\ntp991\nRp992\ng196\nF220.0\ntp993\na(I2450000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9cp@'\np994\ntp995\nRp996\ng196\nF220.0\ntp997\na(I2460000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x000q@'\np998\ntp999\nRp1000\ng196\nF528.0\ntp1001\na(I2470000\ng1\n(g5\nS'fffffvq@'\np1002\ntp1003\nRp1004\ng196\nF220.0\ntp1005\na(I2480000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85;r@'\np1006\ntp1007\nRp1008\ng196\nF176.0\ntp1009\na(I2490000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xddr@'\np1010\ntp1011\nRp1012\ng196\nF308.0\ntp1013\na(I2500000\ng1\n(g5\nS'\\n\\xd7\\xa3p=js@'\np1014\ntp1015\nRp1016\ng196\nF660.0\ntp1017\na(I2510000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xf9r@'\np1018\ntp1019\nRp1020\ng196\nF572.0\ntp1021\na(I2520000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xc1r@'\np1022\ntp1023\nRp1024\ng196\nF220.0\ntp1025\na(I2530000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\s@'\np1026\ntp1027\nRp1028\ng196\nF616.0\ntp1029\na(I2540000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xa2s@'\np1030\ntp1031\nRp1032\ng196\nF396.0\ntp1033\na(I2550000\ng1\n(g5\nS'fffff6t@'\np1034\ntp1035\nRp1036\ng196\nF528.0\ntp1037\na(I2560000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xe1t@'\np1038\ntp1039\nRp1040\ng196\nF352.0\ntp1041\na(I2570000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Yu@'\np1042\ntp1043\nRp1044\ng196\nF308.0\ntp1045\na(I2580000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xd8u@'\np1046\ntp1047\nRp1048\ng196\nF308.0\ntp1049\na(I2590000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xcau@'\np1050\ntp1051\nRp1052\ng196\nF264.0\ntp1053\na(I2600000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\tv@'\np1054\ntp1055\nRp1056\ng196\nF396.0\ntp1057\na(I2610000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x81v@'\np1058\ntp1059\nRp1060\ng196\nF308.0\ntp1061\na(I2620000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:v@'\np1062\ntp1063\nRp1064\ng196\nF264.0\ntp1065\na(I2630000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x15w@'\np1066\ntp1067\nRp1068\ng196\nF616.0\ntp1069\na(I2640000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf58w@'\np1070\ntp1071\nRp1072\ng196\nF440.0\ntp1073\na(I2650000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:x@'\np1074\ntp1075\nRp1076\ng196\nF572.0\ntp1077\na(I2660000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Ix@'\np1078\ntp1079\nRp1080\ng196\nF132.0\ntp1081\na(I2670000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9ex@'\np1082\ntp1083\nRp1084\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xe5x@'\np1085\ntp1086\nRp1087\nF616.0\ntp1088\na(I2680000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85+y@'\np1089\ntp1090\nRp1091\ng1\n(g5\nS'H\\xe1z\\x14\\xaeGy@'\np1092\ntp1093\nRp1094\nF308.0\ntp1095\na(I2690000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xc1x@'\np1096\ntp1097\nRp1098\ng1094\nF132.0\ntp1099\na(I2700000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x11y@'\np1100\ntp1101\nRp1102\ng1094\nF308.0\ntp1103\na(I2710000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xc3x@'\np1104\ntp1105\nRp1106\ng1094\nF352.0\ntp1107\na(I2720000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xe4x@'\np1108\ntp1109\nRp1110\ng1094\nF660.0\ntp1111\na(I2730000\ng1\n(g5\nS'fffff\\xd6x@'\np1112\ntp1113\nRp1114\ng1094\nF396.0\ntp1115\na(I2740000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xf2x@'\np1116\ntp1117\nRp1118\ng1094\nF572.0\ntp1119\na(I2750000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb1y@'\np1120\ntp1121\nRp1122\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\y@'\np1123\ntp1124\nRp1125\nF484.0\ntp1126\na(I2760000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7y@'\np1127\ntp1128\nRp1129\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xe5y@'\np1130\ntp1131\nRp1132\nF308.0\ntp1133\na(I2770000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xe5y@'\np1134\ntp1135\nRp1136\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0fz@'\np1137\ntp1138\nRp1139\nF220.0\ntp1140\na(I2780000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8Nz@'\np1141\ntp1142\nRp1143\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\\\z@'\np1144\ntp1145\nRp1146\nF264.0\ntp1147\na(I2790000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xb1z@'\np1148\ntp1149\nRp1150\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xdbz@'\np1151\ntp1152\nRp1153\nF396.0\ntp1154\na(I2800000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQxz@'\np1155\ntp1156\nRp1157\ng1153\nF484.0\ntp1158\na(I2810000\ng1\n(g5\nS'\\xa4p=\\n\\xd7cz@'\np1159\ntp1160\nRp1161\ng1153\nF572.0\ntp1162\na(I2820000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x18z@'\np1163\ntp1164\nRp1165\ng1153\nF396.0\ntp1166\na(I2830000\ng1\n(g5\nS'=\\n\\xd7\\xa3p-z@'\np1167\ntp1168\nRp1169\ng1153\nF660.0\ntp1170\na(I2840000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeWz@'\np1171\ntp1172\nRp1173\ng1153\nF660.0\ntp1174\na(I2850000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(|z@'\np1175\ntp1176\nRp1177\ng1153\nF88.0\ntp1178\na(I2860000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc|y@'\np1179\ntp1180\nRp1181\ng1153\nF132.0\ntp1182\na(I2870000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xa9x@'\np1183\ntp1184\nRp1185\ng1153\nF88.0\ntp1186\na(I2880000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#x@'\np1187\ntp1188\nRp1189\ng1153\nF264.0\ntp1190\na(I2890000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x97w@'\np1191\ntp1192\nRp1193\ng1153\nF308.0\ntp1194\na(I2900000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x88w@'\np1195\ntp1196\nRp1197\ng1153\nF264.0\ntp1198\na(I2910000\ng1\n(g5\nS'\\xd7\\xa3p=\\nGx@'\np1199\ntp1200\nRp1201\ng1153\nF308.0\ntp1202\na(I2920000\ng1\n(g5\nS'33333\\xd3w@'\np1203\ntp1204\nRp1205\ng1153\nF352.0\ntp1206\na(I2930000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xa1w@'\np1207\ntp1208\nRp1209\ng1153\nF660.0\ntp1210\na(I2940000\ng1\n(g5\nS'33333#w@'\np1211\ntp1212\nRp1213\ng1153\nF352.0\ntp1214\na(I2950000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x15w@'\np1215\ntp1216\nRp1217\ng1153\nF352.0\ntp1218\na(I2960000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x9aw@'\np1219\ntp1220\nRp1221\ng1153\nF308.0\ntp1222\na(I2970000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccLw@'\np1223\ntp1224\nRp1225\ng1153\nF528.0\ntp1226\na(I2980000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdcv@'\np1227\ntp1228\nRp1229\ng1153\nF440.0\ntp1230\na(I2990000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xcev@'\np1231\ntp1232\nRp1233\ng1153\nF572.0\ntp1234\na(I3000000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2Uv@'\np1235\ntp1236\nRp1237\ng1153\nF264.0\ntp1238\na(I3010000\ng1\n(g5\nS'fffffvw@'\np1239\ntp1240\nRp1241\ng1153\nF440.0\ntp1242\na(I3020000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x1fx@'\np1243\ntp1244\nRp1245\ng1153\nF264.0\ntp1246\na(I3030000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x00y@'\np1247\ntp1248\nRp1249\ng1153\nF528.0\ntp1250\na(I3040000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5xy@'\np1251\ntp1252\nRp1253\ng1153\nF352.0\ntp1254\na(I3050000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGaz@'\np1255\ntp1256\nRp1257\ng1153\nF660.0\ntp1258\na(I3060000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xeez@'\np1259\ntp1260\nRp1261\ng1\n(g5\nS'33333\\x03{@'\np1262\ntp1263\nRp1264\nF264.0\ntp1265\na(I3070000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x18{@'\np1266\ntp1267\nRp1268\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99I{@'\np1269\ntp1270\nRp1271\nF484.0\ntp1272\na(I3080000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}z@'\np1273\ntp1274\nRp1275\ng1271\nF396.0\ntp1276\na(I3090000\ng1\n(g5\nS'q=\\n\\xd7\\xa3P{@'\np1277\ntp1278\nRp1279\ng1\n(g5\nS'q=\\n\\xd7\\xa3P{@'\np1280\ntp1281\nRp1282\nF660.0\ntp1283\na(I3100000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xfb{@'\np1284\ntp1285\nRp1286\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x17|@'\np1287\ntp1288\nRp1289\nF396.0\ntp1290\na(I3110000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xac|@'\np1291\ntp1292\nRp1293\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xac|@'\np1294\ntp1295\nRp1296\nF352.0\ntp1297\na(I3120000\ng1\n(g5\nS'33333c}@'\np1298\ntp1299\nRp1300\ng1\n(g5\nS'33333c}@'\np1301\ntp1302\nRp1303\nF616.0\ntp1304\na(I3130000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xec|@'\np1305\ntp1306\nRp1307\ng1303\nF756.0\ntp1308\na(I3140000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x97}@'\np1309\ntp1310\nRp1311\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x97}@'\np1312\ntp1313\nRp1314\nF804.0\ntp1315\na(I3150000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE~@'\np1316\ntp1317\nRp1318\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE~@'\np1319\ntp1320\nRp1321\nF616.0\ntp1322\na(I3160000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xcc~@'\np1323\ntp1324\nRp1325\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xcc~@'\np1326\ntp1327\nRp1328\nF528.0\ntp1329\na(I3170000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5~@'\np1330\ntp1331\nRp1332\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfd~@'\np1333\ntp1334\nRp1335\nF708.0\ntp1336\na(I3180000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xee~@'\np1337\ntp1338\nRp1339\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e5\\x7f@'\np1340\ntp1341\nRp1342\nF308.0\ntp1343\na(I3190000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.\\x7f@'\np1344\ntp1345\nRp1346\ng1\n(g5\nS'\\xe1z\\x14\\xaeGQ\\x7f@'\np1347\ntp1348\nRp1349\nF308.0\ntp1350\na(I3200000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00 \\x7f@'\np1351\ntp1352\nRp1353\ng1349\nF484.0\ntp1354\na(I3210000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.\\x7f@'\np1355\ntp1356\nRp1357\ng1349\nF616.0\ntp1358\na(I3220000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xac\\x7f@'\np1359\ntp1360\nRp1361\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xc8\\x7f@'\np1362\ntp1363\nRp1364\nF440.0\ntp1365\na(I3230000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1Z~@'\np1366\ntp1367\nRp1368\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7\\x7f@'\np1369\ntp1370\nRp1371\nF176.0\ntp1372\na(I3240000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xf1}@'\np1373\ntp1374\nRp1375\ng1371\nF352.0\ntp1376\na(I3250000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xc7}@'\np1377\ntp1378\nRp1379\ng1371\nF264.0\ntp1380\na(I3260000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99y}@'\np1381\ntp1382\nRp1383\ng1371\nF528.0\ntp1384\na(I3270000\ng1\n(g5\nS'33333#}@'\np1385\ntp1386\nRp1387\ng1371\nF396.0\ntp1388\na(I3280000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x10|@'\np1389\ntp1390\nRp1391\ng1371\nF264.0\ntp1392\na(I3290000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde{@'\np1393\ntp1394\nRp1395\ng1371\nF484.0\ntp1396\na(I3300000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xac{@'\np1397\ntp1398\nRp1399\ng1371\nF220.0\ntp1400\na(I3310000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa1z@'\np1401\ntp1402\nRp1403\ng1371\nF352.0\ntp1404\na(I3320000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fRz@'\np1405\ntp1406\nRp1407\ng1371\nF264.0\ntp1408\na(I3330000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(Lz@'\np1409\ntp1410\nRp1411\ng1371\nF440.0\ntp1412\na(I3340000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x91z@'\np1413\ntp1414\nRp1415\ng1371\nF572.0\ntp1416\na(I3350000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x1f{@'\np1417\ntp1418\nRp1419\ng1371\nF528.0\ntp1420\na(I3360000\ng1\n(g5\nS'\\xa4p=\\n\\xd7s{@'\np1421\ntp1422\nRp1423\ng1371\nF660.0\ntp1424\na(I3370000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x7f{@'\np1425\ntp1426\nRp1427\ng1371\nF264.0\ntp1428\na(I3380000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x87{@'\np1429\ntp1430\nRp1431\ng1371\nF396.0\ntp1432\na(I3390000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xb3{@'\np1433\ntp1434\nRp1435\ng1371\nF484.0\ntp1436\na(I3400000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xad|@'\np1437\ntp1438\nRp1439\ng1371\nF176.0\ntp1440\na(I3410000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xe5|@'\np1441\ntp1442\nRp1443\ng1371\nF528.0\ntp1444\na(I3420000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x95}@'\np1445\ntp1446\nRp1447\ng1371\nF308.0\ntp1448\na(I3430000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xe5}@'\np1449\ntp1450\nRp1451\ng1371\nF264.0\ntp1452\na(I3440000\ng1\n(g5\nS'q=\\n\\xd7\\xa3@~@'\np1453\ntp1454\nRp1455\ng1371\nF264.0\ntp1456\na(I3450000\ng1\n(g5\nS'fffff\\xd6~@'\np1457\ntp1458\nRp1459\ng1371\nF660.0\ntp1460\na(I3460000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xb7\\x7f@'\np1461\ntp1462\nRp1463\ng1371\nF660.0\ntp1464\na(I3470000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xce\\x7f@'\np1465\ntp1466\nRp1467\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xff\\x7f@'\np1468\ntp1469\nRp1470\nF264.0\ntp1471\na(I3480000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xad\\x7f@'\np1472\ntp1473\nRp1474\ng1470\nF852.0\ntp1475\na(I3490000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc|\\x80@'\np1476\ntp1477\nRp1478\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc|\\x80@'\np1479\ntp1480\nRp1481\nF660.0\ntp1482\na(I3500000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xcd\\x80@'\np1483\ntp1484\nRp1485\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xcd\\x80@'\np1486\ntp1487\nRp1488\nF396.0\ntp1489\na(I3510000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xf4\\x80@'\np1490\ntp1491\nRp1492\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xf4\\x80@'\np1493\ntp1494\nRp1495\nF660.0\ntp1496\na(I3520000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1c\\x81@'\np1497\ntp1498\nRp1499\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1c\\x81@'\np1500\ntp1501\nRp1502\nF756.0\ntp1503\na(I3530000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x14\\x81@'\np1504\ntp1505\nRp1506\ng1502\nF660.0\ntp1507\na(I3540000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zt\\x81@'\np1508\ntp1509\nRp1510\ng1\n(g5\nS'\\x14\\xaeG\\xe1zt\\x81@'\np1511\ntp1512\nRp1513\nF616.0\ntp1514\na(I3550000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa0\\x81@'\np1515\ntp1516\nRp1517\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb0\\x81@'\np1518\ntp1519\nRp1520\nF804.0\ntp1521\na(I3560000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xb6\\x81@'\np1522\ntp1523\nRp1524\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xb9\\x81@'\np1525\ntp1526\nRp1527\nF756.0\ntp1528\na(I3570000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xa3\\x81@'\np1529\ntp1530\nRp1531\ng1527\nF616.0\ntp1532\na(I3580000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\x81@'\np1533\ntp1534\nRp1535\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\x81@'\np1536\ntp1537\nRp1538\nF756.0\ntp1539\na(I3590000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14F\\x82@'\np1540\ntp1541\nRp1542\ng1\n(g5\nS'H\\xe1z\\x14\\xaeW\\x82@'\np1543\ntp1544\nRp1545\nF440.0\ntp1546\na(I3600000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x008\\x82@'\np1547\ntp1548\nRp1549\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2e\\x82@'\np1550\ntp1551\nRp1552\nF528.0\ntp1553\na(I3610000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGY\\x82@'\np1554\ntp1555\nRp1556\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebq\\x82@'\np1557\ntp1558\nRp1559\nF264.0\ntp1560\na(I3620000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e]\\x82@'\np1561\ntp1562\nRp1563\ng1559\nF660.0\ntp1564\na(I3630000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xac\\x82@'\np1565\ntp1566\nRp1567\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xb4\\x82@'\np1568\ntp1569\nRp1570\nF660.0\ntp1571\na(I3640000\ng1\n(g5\nS'33333\\xc3\\x82@'\np1572\ntp1573\nRp1574\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xc6\\x82@'\np1575\ntp1576\nRp1577\nF616.0\ntp1578\na(I3650000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x07\\x83@'\np1579\ntp1580\nRp1581\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x07\\x83@'\np1582\ntp1583\nRp1584\nF616.0\ntp1585\na(I3660000\ng1\n(g5\nS'=\\n\\xd7\\xa3p5\\x83@'\np1586\ntp1587\nRp1588\ng1\n(g5\nS'=\\n\\xd7\\xa3p5\\x83@'\np1589\ntp1590\nRp1591\nF572.0\ntp1592\na(I3670000\ng1\n(g5\nS'\\xa4p=\\n\\xd7S\\x83@'\np1593\ntp1594\nRp1595\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2m\\x83@'\np1596\ntp1597\nRp1598\nF1284.0\ntp1599\na(I3680000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8>\\x83@'\np1600\ntp1601\nRp1602\ng1598\nF396.0\ntp1603\na(I3690000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fR\\x83@'\np1604\ntp1605\nRp1606\ng1598\nF528.0\ntp1607\na(I3700000\ng1\n(g5\nS'33333c\\x83@'\np1608\ntp1609\nRp1610\ng1598\nF1140.0\ntp1611\na(I3710000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8v\\x83@'\np1612\ntp1613\nRp1614\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x7f\\x83@'\np1615\ntp1616\nRp1617\nF948.0\ntp1618\na(I3720000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQX\\x83@'\np1619\ntp1620\nRp1621\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x8d\\x83@'\np1622\ntp1623\nRp1624\nF528.0\ntp1625\na(I3730000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85;\\x83@'\np1626\ntp1627\nRp1628\ng1624\nF484.0\ntp1629\na(I3740000\ng1\n(g5\nS'\\xd7\\xa3p=\\nw\\x83@'\np1630\ntp1631\nRp1632\ng1624\nF708.0\ntp1633\na(I3750000\ng1\n(g5\nS'\\n\\xd7\\xa3p=J\\x83@'\np1634\ntp1635\nRp1636\ng1624\nF660.0\ntp1637\na(I3760000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x7f\\x83@'\np1638\ntp1639\nRp1640\ng1624\nF528.0\ntp1641\na(I3770000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xb4\\x83@'\np1642\ntp1643\nRp1644\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xc1\\x83@'\np1645\ntp1646\nRp1647\nF756.0\ntp1648\na(I3780000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xc2\\x83@'\np1649\ntp1650\nRp1651\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xd5\\x83@'\np1652\ntp1653\nRp1654\nF616.0\ntp1655\na(I3790000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebI\\x84@'\np1656\ntp1657\nRp1658\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebI\\x84@'\np1659\ntp1660\nRp1661\nF660.0\ntp1662\na(I3800000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2m\\x84@'\np1663\ntp1664\nRp1665\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2m\\x84@'\np1666\ntp1667\nRp1668\nF572.0\ntp1669\na(I3810000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd1\\x84@'\np1670\ntp1671\nRp1672\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd1\\x84@'\np1673\ntp1674\nRp1675\nF616.0\ntp1676\na(I3820000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xa0\\x84@'\np1677\ntp1678\nRp1679\ng1675\nF708.0\ntp1680\na(I3830000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe0\\x84@'\np1681\ntp1682\nRp1683\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe0\\x84@'\np1684\ntp1685\nRp1686\nF1092.0\ntp1687\na(I3840000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xd0\\x84@'\np1688\ntp1689\nRp1690\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xfe\\x84@'\np1691\ntp1692\nRp1693\nF708.0\ntp1694\na(I3850000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x0e\\x85@'\np1695\ntp1696\nRp1697\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x0e\\x85@'\np1698\ntp1699\nRp1700\nF756.0\ntp1701\na(I3860000\ng1\n(g5\nS'\\xd7\\xa3p=\\nO\\x85@'\np1702\ntp1703\nRp1704\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00P\\x85@'\np1705\ntp1706\nRp1707\nF948.0\ntp1708\na(I3870000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x88\\x85@'\np1709\ntp1710\nRp1711\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x97\\x85@'\np1712\ntp1713\nRp1714\nF948.0\ntp1715\na(I3880000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xd8\\x85@'\np1716\ntp1717\nRp1718\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xd8\\x85@'\np1719\ntp1720\nRp1721\nF852.0\ntp1722\na(I3890000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xda\\x85@'\np1723\ntp1724\nRp1725\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xda\\x85@'\np1726\ntp1727\nRp1728\nF1432.0\ntp1729\na(I3900000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xfd\\x85@'\np1730\ntp1731\nRp1732\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x12\\x86@'\np1733\ntp1734\nRp1735\nF660.0\ntp1736\na(I3910000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGA\\x86@'\np1737\ntp1738\nRp1739\ng1\n(g5\nS'\\xe1z\\x14\\xaeGA\\x86@'\np1740\ntp1741\nRp1742\nF804.0\ntp1743\na(I3920000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccT\\x86@'\np1744\ntp1745\nRp1746\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x86@'\np1747\ntp1748\nRp1749\nF708.0\ntp1750\na(I3930000\ng1\n(g5\nS'33333\\x0b\\x86@'\np1751\ntp1752\nRp1753\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebi\\x86@'\np1754\ntp1755\nRp1756\nF616.0\ntp1757\na(I3940000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h\\x86@'\np1758\ntp1759\nRp1760\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n\\x86@'\np1761\ntp1762\nRp1763\nF660.0\ntp1764\na(I3950000\ng1\n(g5\nS'fffff\\xae\\x86@'\np1765\ntp1766\nRp1767\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xb1\\x86@'\np1768\ntp1769\nRp1770\nF616.0\ntp1771\na(I3960000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x81\\x86@'\np1772\ntp1773\nRp1774\ng1770\nF660.0\ntp1775\na(I3970000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa0\\x86@'\np1776\ntp1777\nRp1778\ng1770\nF1044.0\ntp1779\na(I3980000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xf4\\x86@'\np1780\ntp1781\nRp1782\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xfc\\x86@'\np1783\ntp1784\nRp1785\nF660.0\ntp1786\na(I3990000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe8\\x86@'\np1787\ntp1788\nRp1789\ng1785\nF660.0\ntp1790\na(I4000000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x11\\x87@'\np1791\ntp1792\nRp1793\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x1b\\x87@'\np1794\ntp1795\nRp1796\nF484.0\ntp1797\na(I4010000\ng1\n(g5\nS'fffff\\xf6\\x86@'\np1798\ntp1799\nRp1800\ng1796\nF852.0\ntp1801\na(I4020000\ng1\n(g5\nS'fffff\\xf6\\x86@'\np1802\ntp1803\nRp1804\ng1796\nF396.0\ntp1805\na(I4030000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xba\\x86@'\np1806\ntp1807\nRp1808\ng1796\nF660.0\ntp1809\na(I4040000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\r\\x87@'\np1810\ntp1811\nRp1812\ng1796\nF1140.0\ntp1813\na(I4050000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x06\\x87@'\np1814\ntp1815\nRp1816\ng1796\nF948.0\ntp1817\na(I4060000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebq\\x87@'\np1818\ntp1819\nRp1820\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebq\\x87@'\np1821\ntp1822\nRp1823\nF900.0\ntp1824\na(I4070000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\G\\x87@'\np1825\ntp1826\nRp1827\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x94\\x87@'\np1828\ntp1829\nRp1830\nF660.0\ntp1831\na(I4080000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x87@'\np1832\ntp1833\nRp1834\ng1830\nF804.0\ntp1835\na(I4090000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc|\\x88@'\np1836\ntp1837\nRp1838\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc|\\x88@'\np1839\ntp1840\nRp1841\nF1284.0\ntp1842\na(I4100000\ng1\n(g5\nS'fffff\\x16\\x89@'\np1843\ntp1844\nRp1845\ng1\n(g5\nS'fffff\\x16\\x89@'\np1846\ntp1847\nRp1848\nF1692.0\ntp1849\na(I4110000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xb2\\x89@'\np1850\ntp1851\nRp1852\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xb2\\x89@'\np1853\ntp1854\nRp1855\nF948.0\ntp1856\na(I4120000\ng1\n(g5\nS'\\xa4p=\\n\\xd7;\\x8a@'\np1857\ntp1858\nRp1859\ng1\n(g5\nS'\\xa4p=\\n\\xd7;\\x8a@'\np1860\ntp1861\nRp1862\nF2160.0\ntp1863\na(I4130000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc8\\x8a@'\np1864\ntp1865\nRp1866\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc8\\x8a@'\np1867\ntp1868\nRp1869\nF660.0\ntp1870\na(I4140000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5p\\x8b@'\np1871\ntp1872\nRp1873\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5p\\x8b@'\np1874\ntp1875\nRp1876\nF1140.0\ntp1877\na(I4150000\ng1\n(g5\nS'q=\\n\\xd7\\xa38\\x8c@'\np1878\ntp1879\nRp1880\ng1\n(g5\nS'q=\\n\\xd7\\xa38\\x8c@'\np1881\ntp1882\nRp1883\nF1380.0\ntp1884\na(I4160000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x12\\x8d@'\np1885\ntp1886\nRp1887\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x12\\x8d@'\np1888\ntp1889\nRp1890\nF2004.0\ntp1891\na(I4170000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(T\\x8e@'\np1892\ntp1893\nRp1894\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(T\\x8e@'\np1895\ntp1896\nRp1897\nF1284.0\ntp1898\na(I4180000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x8d\\x8e@'\np1899\ntp1900\nRp1901\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x8d\\x8e@'\np1902\ntp1903\nRp1904\nF2004.0\ntp1905\na(I4190000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x00\\x8f@'\np1906\ntp1907\nRp1908\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x00\\x8f@'\np1909\ntp1910\nRp1911\nF708.0\ntp1912\na(I4200000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zl\\x8f@'\np1913\ntp1914\nRp1915\ng1\n(g5\nS'\\x14\\xaeG\\xe1zl\\x8f@'\np1916\ntp1917\nRp1918\nF1484.0\ntp1919\na(I4210000\ng1\n(g5\nS'=\\n\\xd7\\xa3p-\\x90@'\np1920\ntp1921\nRp1922\ng1\n(g5\nS'=\\n\\xd7\\xa3p-\\x90@'\np1923\ntp1924\nRp1925\nF1332.0\ntp1926\na(I4220000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xd8\\x90@'\np1927\ntp1928\nRp1929\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xdc\\x90@'\np1930\ntp1931\nRp1932\nF708.0\ntp1933\na(I4230000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99I\\x91@'\np1934\ntp1935\nRp1936\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99I\\x91@'\np1937\ntp1938\nRp1939\nF1236.0\ntp1940\na(I4240000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xc3\\x91@'\np1941\ntp1942\nRp1943\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xc3\\x91@'\np1944\ntp1945\nRp1946\nF2004.0\ntp1947\na(I4250000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x08\\x92@'\np1948\ntp1949\nRp1950\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x08\\x92@'\np1951\ntp1952\nRp1953\nF660.0\ntp1954\na(I4260000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zp\\x92@'\np1955\ntp1956\nRp1957\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x85\\x92@'\np1958\ntp1959\nRp1960\nF660.0\ntp1961\na(I4270000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xaf\\x92@'\np1962\ntp1963\nRp1964\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xaf\\x92@'\np1965\ntp1966\nRp1967\nF1380.0\ntp1968\na(I4280000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\r\\x93@'\np1969\ntp1970\nRp1971\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\r\\x93@'\np1972\ntp1973\nRp1974\nF1432.0\ntp1975\na(I4290000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc@\\x93@'\np1976\ntp1977\nRp1978\ng1\n(g5\nS'\\x14\\xaeG\\xe1zH\\x93@'\np1979\ntp1980\nRp1981\nF804.0\ntp1982\na(I4300000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xc0\\x93@'\np1983\ntp1984\nRp1985\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xc0\\x93@'\np1986\ntp1987\nRp1988\nF1332.0\ntp1989\na(I4310000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z<\\x94@'\np1990\ntp1991\nRp1992\ng1\n(g5\nS'\\x14\\xaeG\\xe1z<\\x94@'\np1993\ntp1994\nRp1995\nF2636.0\ntp1996\na(I4320000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xdb\\x94@'\np1997\ntp1998\nRp1999\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xdb\\x94@'\np2000\ntp2001\nRp2002\nF1900.0\ntp2003\na(I4330000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\\x95@'\np2004\ntp2005\nRp2006\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\\x95@'\np2007\ntp2008\nRp2009\nF2384.0\ntp2010\na(I4340000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x7f\\x95@'\np2011\ntp2012\nRp2013\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x7f\\x95@'\np2014\ntp2015\nRp2016\nF2328.0\ntp2017\na(I4350000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xdb\\x95@'\np2018\ntp2019\nRp2020\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xdb\\x95@'\np2021\ntp2022\nRp2023\nF2004.0\ntp2024\na(I4360000\ng1\n(g5\nS'=\\n\\xd7\\xa3p5\\x96@'\np2025\ntp2026\nRp2027\ng1\n(g5\nS'=\\n\\xd7\\xa3p5\\x96@'\np2028\ntp2029\nRp2030\nF1380.0\ntp2031\na(I4370000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xa4\\x96@'\np2032\ntp2033\nRp2034\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xa4\\x96@'\np2035\ntp2036\nRp2037\nF1140.0\ntp2038\na(I4380000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xbd\\x96@'\np2039\ntp2040\nRp2041\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xbd\\x96@'\np2042\ntp2043\nRp2044\nF948.0\ntp2045\na(I4390000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x06\\x97@'\np2046\ntp2047\nRp2048\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x06\\x97@'\np2049\ntp2050\nRp2051\nF3000.0\ntp2052\na(I4400000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x84\\x97@'\np2053\ntp2054\nRp2055\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x84\\x97@'\np2056\ntp2057\nRp2058\nF3084.0\ntp2059\na(I4410000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x04\\x98@'\np2060\ntp2061\nRp2062\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x04\\x98@'\np2063\ntp2064\nRp2065\nF1380.0\ntp2066\na(I4420000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(P\\x98@'\np2067\ntp2068\nRp2069\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(P\\x98@'\np2070\ntp2071\nRp2072\nF1332.0\ntp2073\na(I4430000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc8\\x98@'\np2074\ntp2075\nRp2076\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc8\\x98@'\np2077\ntp2078\nRp2079\nF4156.0\ntp2080\na(I4440000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb82\\x99@'\np2081\ntp2082\nRp2083\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb82\\x99@'\np2084\ntp2085\nRp2086\nF1432.0\ntp2087\na(I4450000\ng1\n(g5\nS'33333\\x9b\\x99@'\np2088\ntp2089\nRp2090\ng1\n(g5\nS'33333\\x9b\\x99@'\np2091\ntp2092\nRp2093\nF2832.0\ntp2094\na(I4460000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xdf\\x99@'\np2095\ntp2096\nRp2097\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xdf\\x99@'\np2098\ntp2099\nRp2100\nF4028.0\ntp2101\na(I4470000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xf9\\x99@'\np2102\ntp2103\nRp2104\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\n\\x9a@'\np2105\ntp2106\nRp2107\nF852.0\ntp2108\na(I4480000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x84\\x9a@'\np2109\ntp2110\nRp2111\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x84\\x9a@'\np2112\ntp2113\nRp2114\nF3840.0\ntp2115\na(I4490000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xdb\\x9a@'\np2116\ntp2117\nRp2118\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xdb\\x9a@'\np2119\ntp2120\nRp2121\nF1332.0\ntp2122\na(I4500000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99y\\x9b@'\np2123\ntp2124\nRp2125\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99y\\x9b@'\np2126\ntp2127\nRp2128\nF3360.0\ntp2129\na(I4510000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc(\\x9c@'\np2130\ntp2131\nRp2132\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc(\\x9c@'\np2133\ntp2134\nRp2135\nF1744.0\ntp2136\na(I4520000\ng1\n(g5\nS'33333\\xab\\x9c@'\np2137\ntp2138\nRp2139\ng1\n(g5\nS'33333\\xab\\x9c@'\np2140\ntp2141\nRp2142\nF4992.0\ntp2143\na(I4530000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQH\\x9d@'\np2144\ntp2145\nRp2146\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQH\\x9d@'\np2147\ntp2148\nRp2149\nF2832.0\ntp2150\na(I4540000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xbf\\x9d@'\np2151\ntp2152\nRp2153\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xbf\\x9d@'\np2154\ntp2155\nRp2156\nF3780.0\ntp2157\na(I4550000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xf4\\x9d@'\np2158\ntp2159\nRp2160\ng1\n(g5\nS'fffff\\n\\x9e@'\np2161\ntp2162\nRp2163\nF1900.0\ntp2164\na(I4560000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xc9\\x9e@'\np2165\ntp2166\nRp2167\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xc9\\x9e@'\np2168\ntp2169\nRp2170\nF3600.0\ntp2171\na(I4570000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\\\\\x9f@'\np2172\ntp2173\nRp2174\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\\\\\x9f@'\np2175\ntp2176\nRp2177\nF1588.0\ntp2178\na(I4580000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xb2\\x9f@'\np2179\ntp2180\nRp2181\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xb2\\x9f@'\np2182\ntp2183\nRp2184\nF2440.0\ntp2185\na(I4590000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x0c\\xa0@'\np2186\ntp2187\nRp2188\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x0c\\xa0@'\np2189\ntp2190\nRp2191\nF3084.0\ntp2192\na(I4600000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb^\\xa0@'\np2193\ntp2194\nRp2195\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb^\\xa0@'\np2196\ntp2197\nRp2198\nF4470.0\ntp2199\na(I4610000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8b\\xa0@'\np2200\ntp2201\nRp2202\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8b\\xa0@'\np2203\ntp2204\nRp2205\nF3810.0\ntp2206\na(I4620000\ng1\n(g5\nS'33333)\\xa1@'\np2207\ntp2208\nRp2209\ng1\n(g5\nS'33333)\\xa1@'\np2210\ntp2211\nRp2212\nF3840.0\ntp2213\na(I4630000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x88\\xa1@'\np2214\ntp2215\nRp2216\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x88\\xa1@'\np2217\ntp2218\nRp2219\nF3600.0\ntp2220\na(I4640000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xdd\\xa1@'\np2221\ntp2222\nRp2223\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xdd\\xa1@'\np2224\ntp2225\nRp2226\nF3784.0\ntp2227\na(I4650000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x0e\\xa2@'\np2228\ntp2229\nRp2230\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x0e\\xa2@'\np2231\ntp2232\nRp2233\nF3480.0\ntp2234\na(I4660000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xe3\\xa2@'\np2235\ntp2236\nRp2237\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xe3\\xa2@'\np2238\ntp2239\nRp2240\nF5246.0\ntp2241\na(I4670000\ng1\n(g5\nS'\\xa4p=\\n\\xd7(\\xa3@'\np2242\ntp2243\nRp2244\ng1\n(g5\nS'\\xa4p=\\n\\xd7(\\xa3@'\np2245\ntp2246\nRp2247\nF4892.0\ntp2248\na(I4680000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xa5\\xa3@'\np2249\ntp2250\nRp2251\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xa5\\xa3@'\np2252\ntp2253\nRp2254\nF5070.0\ntp2255\na(I4690000\ng1\n(g5\nS'fffff!\\xa4@'\np2256\ntp2257\nRp2258\ng1\n(g5\nS'fffff!\\xa4@'\np2259\ntp2260\nRp2261\nF4560.0\ntp2262\na(I4700000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5_\\xa4@'\np2263\ntp2264\nRp2265\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5_\\xa4@'\np2266\ntp2267\nRp2268\nF4412.0\ntp2269\na(I4710000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xc4\\xa4@'\np2270\ntp2271\nRp2272\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xc4\\xa4@'\np2273\ntp2274\nRp2275\nF3600.0\ntp2276\na(I4720000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xec\\xa4@'\np2277\ntp2278\nRp2279\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xec\\xa4@'\np2280\ntp2281\nRp2282\nF2944.0\ntp2283\na(I4730000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5t\\xa5@'\np2284\ntp2285\nRp2286\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5t\\xa5@'\np2287\ntp2288\nRp2289\nF2944.0\ntp2290\na(I4740000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xb4\\xa5@'\np2291\ntp2292\nRp2293\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xb4\\xa5@'\np2294\ntp2295\nRp2296\nF4892.0\ntp2297\na(I4750000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xf2\\xa5@'\np2298\ntp2299\nRp2300\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xf2\\xa5@'\np2301\ntp2302\nRp2303\nF1640.0\ntp2304\na(I4760000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccB\\xa6@'\np2305\ntp2306\nRp2307\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccB\\xa6@'\np2308\ntp2309\nRp2310\nF3840.0\ntp2311\na(I4770000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe7\\xa6@'\np2312\ntp2313\nRp2314\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe7\\xa6@'\np2315\ntp2316\nRp2317\nF5340.0\ntp2318\na(I4780000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x08\\xa7@'\np2319\ntp2320\nRp2321\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x08\\xa7@'\np2322\ntp2323\nRp2324\nF5212.0\ntp2325\na(I4790000\ng1\n(g5\nS'\\xd7\\xa3p=\\n?\\xa7@'\np2326\ntp2327\nRp2328\ng1\n(g5\nS'\\xd7\\xa3p=\\n?\\xa7@'\np2329\ntp2330\nRp2331\nF4734.0\ntp2332\na(I4800000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x88\\xa7@'\np2333\ntp2334\nRp2335\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x88\\xa7@'\np2336\ntp2337\nRp2338\nF2160.0\ntp2339\na(I4810000\ng1\n(g5\nS'fffff\\xf4\\xa7@'\np2340\ntp2341\nRp2342\ng1\n(g5\nS'fffff\\xf4\\xa7@'\np2343\ntp2344\nRp2345\nF3252.0\ntp2346\na(I4820000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xe4\\xa7@'\np2347\ntp2348\nRp2349\ng2345\nF1744.0\ntp2350\na(I4830000\ng1\n(g5\nS'q=\\n\\xd7\\xa3z\\xa8@'\np2351\ntp2352\nRp2353\ng1\n(g5\nS'q=\\n\\xd7\\xa3z\\xa8@'\np2354\ntp2355\nRp2356\nF1848.0\ntp2357\na(I4840000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xaa\\xa8@'\np2358\ntp2359\nRp2360\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xaa\\xa8@'\np2361\ntp2362\nRp2363\nF1952.0\ntp2364\na(I4850000\ng1\n(g5\nS'\\xd7\\xa3p=\\n3\\xa9@'\np2365\ntp2366\nRp2367\ng1\n(g5\nS'\\xd7\\xa3p=\\n3\\xa9@'\np2368\ntp2369\nRp2370\nF4606.0\ntp2371\na(I4860000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb1\\xa9@'\np2372\ntp2373\nRp2374\ng2370\nF3028.0\ntp2375\na(I4870000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14R\\xa9@'\np2376\ntp2377\nRp2378\ng1\n(g5\nS'\\xaeG\\xe1z\\x14R\\xa9@'\np2379\ntp2380\nRp2381\nF4384.0\ntp2382\na(I4880000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xe0\\xa9@'\np2383\ntp2384\nRp2385\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xe0\\xa9@'\np2386\ntp2387\nRp2388\nF4412.0\ntp2389\na(I4890000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(-\\xaa@'\np2390\ntp2391\nRp2392\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(-\\xaa@'\np2393\ntp2394\nRp2395\nF4734.0\ntp2396\na(I4900000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8e\\xaa@'\np2397\ntp2398\nRp2399\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8e\\xaa@'\np2400\ntp2401\nRp2402\nF4290.0\ntp2403\na(I4910000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x8d\\xaa@'\np2404\ntp2405\nRp2406\ng2402\nF2160.0\ntp2407\na(I4920000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xde\\xaa@'\np2408\ntp2409\nRp2410\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xde\\xaa@'\np2411\ntp2412\nRp2413\nF4892.0\ntp2414\na(I4930000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb1\\xab@'\np2415\ntp2416\nRp2417\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb1\\xab@'\np2418\ntp2419\nRp2420\nF6312.0\ntp2421\na(I4940000\ng1\n(g5\nS'\\n\\xd7\\xa3p=R\\xab@'\np2422\ntp2423\nRp2424\ng1\n(g5\nS'H\\xe1z\\x14\\xaeU\\xab@'\np2425\ntp2426\nRp2427\nF4512.0\ntp2428\na(I4950000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x9c\\xab@'\np2429\ntp2430\nRp2431\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x9c\\xab@'\np2432\ntp2433\nRp2434\nF5340.0\ntp2435\na(I4960000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5E\\xac@'\np2436\ntp2437\nRp2438\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5E\\xac@'\np2439\ntp2440\nRp2441\nF5632.0\ntp2442\na(I4970000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x7f\\xac@'\np2443\ntp2444\nRp2445\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x7f\\xac@'\np2446\ntp2447\nRp2448\nF5340.0\ntp2449\na(I4980000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xe1\\xac@'\np2450\ntp2451\nRp2452\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xe1\\xac@'\np2453\ntp2454\nRp2455\nF4500.0\ntp2456\na(I4990000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00(\\xad@'\np2457\ntp2458\nRp2459\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00(\\xad@'\np2460\ntp2461\nRp2462\nF5276.0\ntp2463\na(I5000000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1ey\\xad@'\np2464\ntp2465\nRp2466\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1ey\\xad@'\np2467\ntp2468\nRp2469\nF7416.0\ntp2470\na(I5010000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xbc\\xad@'\np2471\ntp2472\nRp2473\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xbc\\xad@'\np2474\ntp2475\nRp2476\nF2160.0\ntp2477\na(I5020000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8 \\xae@'\np2478\ntp2479\nRp2480\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8 \\xae@'\np2481\ntp2482\nRp2483\nF3964.0\ntp2484\na(I5030000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x1f\\xae@'\np2485\ntp2486\nRp2487\ng1\n(g5\nS'\\xa4p=\\n\\xd7/\\xae@'\np2488\ntp2489\nRp2490\nF2108.0\ntp2491\na(I5040000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebc\\xae@'\np2492\ntp2493\nRp2494\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebc\\xae@'\np2495\ntp2496\nRp2497\nF3840.0\ntp2498\na(I5050000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xc8\\xae@'\np2499\ntp2500\nRp2501\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xc8\\xae@'\np2502\ntp2503\nRp2504\nF5504.0\ntp2505\na(I5060000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xe4\\xae@'\np2506\ntp2507\nRp2508\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x06\\xaf@'\np2509\ntp2510\nRp2511\nF2608.0\ntp2512\na(I5070000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe3\\xae@'\np2513\ntp2514\nRp2515\ng2511\nF3000.0\ntp2516\na(I5080000\ng1\n(g5\nS'\\xa4p=\\n\\xd7$\\xaf@'\np2517\ntp2518\nRp2519\ng1\n(g5\nS'\\xa4p=\\n\\xd7$\\xaf@'\np2520\ntp2521\nRp2522\nF2160.0\ntp2523\na(I5090000\ng1\n(g5\nS'=\\n\\xd7\\xa3p^\\xaf@'\np2524\ntp2525\nRp2526\ng1\n(g5\nS'=\\n\\xd7\\xa3p^\\xaf@'\np2527\ntp2528\nRp2529\nF3300.0\ntp2530\na(I5100000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xf2\\xaf@'\np2531\ntp2532\nRp2533\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xf2\\xaf@'\np2534\ntp2535\nRp2536\nF6262.0\ntp2537\na(I5110000\ng1\n(g5\nS'{\\x14\\xaeGa\\x14\\xb0@'\np2538\ntp2539\nRp2540\ng1\n(g5\nS'{\\x14\\xaeGa\\x14\\xb0@'\np2541\ntp2542\nRp2543\nF5798.0\ntp2544\na(I5120000\ng1\n(g5\nS'33333%\\xb0@'\np2545\ntp2546\nRp2547\ng1\n(g5\nS'ffff\\xe6*\\xb0@'\np2548\ntp2549\nRp2550\nF3900.0\ntp2551\na(I5130000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00c\\xb0@'\np2552\ntp2553\nRp2554\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00c\\xb0@'\np2555\ntp2556\nRp2557\nF8132.0\ntp2558\na(I5140000\ng1\n(g5\nS'H\\xe1z\\x14.N\\xb0@'\np2559\ntp2560\nRp2561\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdcy\\xb0@'\np2562\ntp2563\nRp2564\nF2384.0\ntp2565\na(I5150000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94Y\\xb0@'\np2566\ntp2567\nRp2568\ng2564\nF3420.0\ntp2569\na(I5160000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xbdc\\xb0@'\np2570\ntp2571\nRp2572\ng2564\nF3420.0\ntp2573\na(I5170000\ng1\n(g5\nS'H\\xe1z\\x14.2\\xb0@'\np2574\ntp2575\nRp2576\ng2564\nF2608.0\ntp2577\na(I5180000\ng1\n(g5\nS'=\\n\\xd7\\xa3p(\\xb0@'\np2578\ntp2579\nRp2580\ng2564\nF5504.0\ntp2581\na(I5190000\ng1\n(g5\nS'\\xa4p=\\n\\xd7D\\xb0@'\np2582\ntp2583\nRp2584\ng2564\nF4860.0\ntp2585\na(I5200000\ng1\n(g5\nS'33333I\\xb0@'\np2586\ntp2587\nRp2588\ng2564\nF2944.0\ntp2589\na(I5210000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccLd\\xb0@'\np2590\ntp2591\nRp2592\ng2564\nF3660.0\ntp2593\na(I5220000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9el\\xb0@'\np2594\ntp2595\nRp2596\ng2564\nF5246.0\ntp2597\na(I5230000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x19\\x98\\xb0@'\np2598\ntp2599\nRp2600\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x19\\x98\\xb0@'\np2601\ntp2602\nRp2603\nF5964.0\ntp2604\na(I5240000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x8c\\xb0@'\np2605\ntp2606\nRp2607\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f\\xa8\\xb0@'\np2608\ntp2609\nRp2610\nF3990.0\ntp2611\na(I5250000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x88\\xb0@'\np2612\ntp2613\nRp2614\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xab\\xb0@'\np2615\ntp2616\nRp2617\nF1380.0\ntp2618\na(I5260000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00z\\xb0@'\np2619\ntp2620\nRp2621\ng2617\nF1744.0\ntp2622\na(I5270000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x85\\xb0@'\np2623\ntp2624\nRp2625\ng2617\nF5024.0\ntp2626\na(I5280000\ng1\n(g5\nS'\\n\\xd7\\xa3p=p\\xb0@'\np2627\ntp2628\nRp2629\ng2617\nF1952.0\ntp2630\na(I5290000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5k\\xb0@'\np2631\ntp2632\nRp2633\ng2617\nF3720.0\ntp2634\na(I5300000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05\\x82\\xb0@'\np2635\ntp2636\nRp2637\ng2617\nF3196.0\ntp2638\na(I5310000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xbd\\x83\\xb0@'\np2639\ntp2640\nRp2641\ng2617\nF3000.0\ntp2642\na(I5320000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xa7\\xb0@'\np2643\ntp2644\nRp2645\ng2617\nF4050.0\ntp2646\na(I5330000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x9e\\xb0@'\np2647\ntp2648\nRp2649\ng2617\nF3964.0\ntp2650\na(I5340000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xa2\\xb0@'\np2651\ntp2652\nRp2653\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xb9\\xb0@'\np2654\ntp2655\nRp2656\nF1536.0\ntp2657\na(I5350000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xc1\\xb0@'\np2658\ntp2659\nRp2660\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xc1\\xb0@'\np2661\ntp2662\nRp2663\nF6508.0\ntp2664\na(I5360000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xbb\\xb0@'\np2665\ntp2666\nRp2667\ng2663\nF2748.0\ntp2668\na(I5370000\ng1\n(g5\nS'fffff\\xf4\\xb0@'\np2669\ntp2670\nRp2671\ng1\n(g5\nS'fffff\\xf4\\xb0@'\np2672\ntp2673\nRp2674\nF6096.0\ntp2675\na(I5380000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xed\\xb0@'\np2676\ntp2677\nRp2678\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xf7\\xb0@'\np2679\ntp2680\nRp2681\nF5412.0\ntp2682\na(I5390000\ng1\n(g5\nS'q=\\n\\xd7#\\xde\\xb0@'\np2683\ntp2684\nRp2685\ng2681\nF3900.0\ntp2686\na(I5400000\ng1\n(g5\nS'{\\x14\\xaeGa\\x06\\xb1@'\np2687\ntp2688\nRp2689\ng1\n(g5\nS'{\\x14\\xaeGa\\x06\\xb1@'\np2690\ntp2691\nRp2692\nF6146.0\ntp2693\na(I5410000\ng1\n(g5\nS'ffff\\xe6&\\xb1@'\np2694\ntp2695\nRp2696\ng1\n(g5\nS'ffff\\xe6&\\xb1@'\np2697\ntp2698\nRp2699\nF5952.0\ntp2700\na(I5420000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1A\\xb1@'\np2701\ntp2702\nRp2703\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1A\\xb1@'\np2704\ntp2705\nRp2706\nF6804.0\ntp2707\na(I5430000\ng1\n(g5\nS'{\\x14\\xaeGa \\xb1@'\np2708\ntp2709\nRp2710\ng2706\nF3240.0\ntp2711\na(I5440000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccLJ\\xb1@'\np2712\ntp2713\nRp2714\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccLJ\\xb1@'\np2715\ntp2716\nRp2717\nF5602.0\ntp2718\na(I5450000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQA\\xb1@'\np2719\ntp2720\nRp2721\ng1\n(g5\nS'{\\x14\\xaeG\\xe1L\\xb1@'\np2722\ntp2723\nRp2724\nF4606.0\ntp2725\na(I5460000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdcV\\xb1@'\np2726\ntp2727\nRp2728\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdcV\\xb1@'\np2729\ntp2730\nRp2731\nF5812.0\ntp2732\na(I5470000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcck\\xb1@'\np2733\ntp2734\nRp2735\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8m\\xb1@'\np2736\ntp2737\nRp2738\nF5154.0\ntp2739\na(I5480000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1G\\xb1@'\np2740\ntp2741\nRp2742\ng2738\nF4156.0\ntp2743\na(I5490000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0s\\xb1@'\np2744\ntp2745\nRp2746\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0s\\xb1@'\np2747\ntp2748\nRp2749\nF5748.0\ntp2750\na(I5500000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(Z\\xb1@'\np2751\ntp2752\nRp2753\ng2749\nF7242.0\ntp2754\na(I5510000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x82\\xb1@'\np2755\ntp2756\nRp2757\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x82\\xb1@'\np2758\ntp2759\nRp2760\nF4704.0\ntp2761\na(I5520000\ng1\n(g5\nS'q=\\n\\xd7#\\x99\\xb1@'\np2762\ntp2763\nRp2764\ng1\n(g5\nS'q=\\n\\xd7#\\x9d\\xb1@'\np2765\ntp2766\nRp2767\nF5348.0\ntp2768\na(I5530000\ng1\n(g5\nS'R\\xb8\\x1e\\x85k\\xe7\\xb1@'\np2769\ntp2770\nRp2771\ng1\n(g5\nS'R\\xb8\\x1e\\x85k\\xe7\\xb1@'\np2772\ntp2773\nRp2774\nF9680.0\ntp2775\na(I5540000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94\\x13\\xb2@'\np2776\ntp2777\nRp2778\ng1\n(g5\nS'\\xaeG\\xe1z\\x94\\x13\\xb2@'\np2779\ntp2780\nRp2781\nF8256.0\ntp2782\na(I5550000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xca\\xb1@'\np2783\ntp2784\nRp2785\ng2781\nF3990.0\ntp2786\na(I5560000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xcd\\xb1@'\np2787\ntp2788\nRp2789\ng2781\nF2944.0\ntp2790\na(I5570000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x1f\\xb2@'\np2791\ntp2792\nRp2793\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x1f\\xb2@'\np2794\ntp2795\nRp2796\nF7182.0\ntp2797\na(I5580000\ng1\n(g5\nS'\\xf6(\\\\\\x8fB-\\xb2@'\np2798\ntp2799\nRp2800\ng1\n(g5\nS'\\xf6(\\\\\\x8fB-\\xb2@'\np2801\ntp2802\nRp2803\nF6876.0\ntp2804\na(I5590000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb,\\xb2@'\np2805\ntp2806\nRp2807\ng1\n(g5\nS'\\xa4p=\\n\\xd7G\\xb2@'\np2808\ntp2809\nRp2810\nF2944.0\ntp2811\na(I5600000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x02\\xb2@'\np2812\ntp2813\nRp2814\ng2810\nF3000.0\ntp2815\na(I5610000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x19\\xfd\\xb1@'\np2816\ntp2817\nRp2818\ng2810\nF2832.0\ntp2819\na(I5620000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccL\\xf0\\xb1@'\np2820\ntp2821\nRp2822\ng2810\nF3672.0\ntp2823\na(I5630000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x18\\xb2@'\np2824\ntp2825\nRp2826\ng2810\nF3000.0\ntp2827\na(I5640000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\,\\xb2@'\np2828\ntp2829\nRp2830\ng2810\nF4028.0\ntp2831\na(I5650000\ng1\n(g5\nS'3333\\xb39\\xb2@'\np2832\ntp2833\nRp2834\ng2810\nF3540.0\ntp2835\na(I5660000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8[\\xb2@'\np2836\ntp2837\nRp2838\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8[\\xb2@'\np2839\ntp2840\nRp2841\nF4284.0\ntp2842\na(I5670000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccL\\x1a\\xb2@'\np2843\ntp2844\nRp2845\ng2841\nF3000.0\ntp2846\na(I5680000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05\\x17\\xb2@'\np2847\ntp2848\nRp2849\ng2841\nF5880.0\ntp2850\na(I5690000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x1e\\xb2@'\np2851\ntp2852\nRp2853\ng2841\nF6240.0\ntp2854\na(I5700000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xbd+\\xb2@'\np2855\ntp2856\nRp2857\ng2841\nF4348.0\ntp2858\na(I5710000\ng1\n(g5\nS'R\\xb8\\x1e\\x85k4\\xb2@'\np2859\ntp2860\nRp2861\ng2841\nF7920.0\ntp2862\na(I5720000\ng1\n(g5\nS'\\xd7\\xa3p=\\nd\\xb2@'\np2863\ntp2864\nRp2865\ng1\n(g5\nS'\\xd7\\xa3p=\\nd\\xb2@'\np2866\ntp2867\nRp2868\nF7494.0\ntp2869\na(I5730000\ng1\n(g5\nS')\\\\\\x8f\\xc2u\\x81\\xb2@'\np2870\ntp2871\nRp2872\ng1\n(g5\nS')\\\\\\x8f\\xc2u\\x81\\xb2@'\np2873\ntp2874\nRp2875\nF8970.0\ntp2876\na(I5740000\ng1\n(g5\nS'33333\\xb9\\xb2@'\np2877\ntp2878\nRp2879\ng1\n(g5\nS'33333\\xb9\\xb2@'\np2880\ntp2881\nRp2882\nF5216.0\ntp2883\na(I5750000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xb5\\xb2@'\np2884\ntp2885\nRp2886\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xd6\\xb2@'\np2887\ntp2888\nRp2889\nF1796.0\ntp2890\na(I5760000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xc7\\xb2@'\np2891\ntp2892\nRp2893\ng2889\nF3840.0\ntp2894\na(I5770000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x9f\\xb2@'\np2895\ntp2896\nRp2897\ng2889\nF1588.0\ntp2898\na(I5780000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xd5\\xb2@'\np2899\ntp2900\nRp2901\ng2889\nF4414.0\ntp2902\na(I5790000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xfb\\xb2@'\np2903\ntp2904\nRp2905\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xfb\\xb2@'\np2906\ntp2907\nRp2908\nF7260.0\ntp2909\na(I5800000\ng1\n(g5\nS'fffff\\x11\\xb3@'\np2910\ntp2911\nRp2912\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x17\\xb3@'\np2913\ntp2914\nRp2915\nF3308.0\ntp2916\na(I5810000\ng1\n(g5\nS'H\\xe1z\\x14\\xae/\\xb3@'\np2917\ntp2918\nRp2919\ng1\n(g5\nS'H\\xe1z\\x14\\xae/\\xb3@'\np2920\ntp2921\nRp2922\nF5282.0\ntp2923\na(I5820000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2B\\xb3@'\np2924\ntp2925\nRp2926\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2B\\xb3@'\np2927\ntp2928\nRp2929\nF6384.0\ntp2930\na(I5830000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8h\\xb3@'\np2931\ntp2932\nRp2933\ng1\n(g5\nS'\\x1f\\x85\\xebQ8h\\xb3@'\np2934\ntp2935\nRp2936\nF4796.0\ntp2937\na(I5840000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94Z\\xb3@'\np2938\ntp2939\nRp2940\ng2936\nF5088.0\ntp2941\na(I5850000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00{\\xb3@'\np2942\ntp2943\nRp2944\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00{\\xb3@'\np2945\ntp2946\nRp2947\nF5182.0\ntp2948\na(I5860000\ng1\n(g5\nS'H\\xe1z\\x14.\\x98\\xb3@'\np2949\ntp2950\nRp2951\ng1\n(g5\nS'H\\xe1z\\x14.\\x98\\xb3@'\np2952\ntp2953\nRp2954\nF9014.0\ntp2955\na(I5870000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG|\\xb3@'\np2956\ntp2957\nRp2958\ng2954\nF3000.0\ntp2959\na(I5880000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x19\\xb8\\xb3@'\np2960\ntp2961\nRp2962\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x19\\xb8\\xb3@'\np2963\ntp2964\nRp2965\nF4640.0\ntp2966\na(I5890000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xe3\\xb3@'\np2967\ntp2968\nRp2969\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xe3\\xb3@'\np2970\ntp2971\nRp2972\nF9000.0\ntp2973\na(I5900000\ng1\n(g5\nS'\\xd7\\xa3p=\\x8a\\xe2\\xb3@'\np2974\ntp2975\nRp2976\ng2972\nF6096.0\ntp2977\na(I5910000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8\\x12\\xb4@'\np2978\ntp2979\nRp2980\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8\\x12\\xb4@'\np2981\ntp2982\nRp2983\nF7140.0\ntp2984\na(I5920000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\r\\xb4@'\np2985\ntp2986\nRp2987\ng1\n(g5\nS'\\xf6(\\\\\\x8fB\"\\xb4@'\np2988\ntp2989\nRp2990\nF4764.0\ntp2991\na(I5930000\ng1\n(g5\nS'33333%\\xb4@'\np2992\ntp2993\nRp2994\ng1\n(g5\nS'33333%\\xb4@'\np2995\ntp2996\nRp2997\nF5602.0\ntp2998\na(I5940000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG3\\xb4@'\np2999\ntp3000\nRp3001\ng1\n(g5\nS'\\xe1z\\x14\\xaeG3\\xb4@'\np3002\ntp3003\nRp3004\nF6462.0\ntp3005\na(I5950000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb4\\xb4@'\np3006\ntp3007\nRp3008\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0<\\xb4@'\np3009\ntp3010\nRp3011\nF4796.0\ntp3012\na(I5960000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x002\\xb4@'\np3013\ntp3014\nRp3015\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfaN\\xb4@'\np3016\ntp3017\nRp3018\nF4412.0\ntp3019\na(I5970000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc7\\x0e\\xb4@'\np3020\ntp3021\nRp3022\ng3018\nF2496.0\ntp3023\na(I5980000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9eH\\xb4@'\np3024\ntp3025\nRp3026\ng3018\nF7684.0\ntp3027\na(I5990000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0i\\xb4@'\np3028\ntp3029\nRp3030\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8q\\xb4@'\np3031\ntp3032\nRp3033\nF4860.0\ntp3034\na(I6000000\ng1\n(g5\nS'fffffb\\xb4@'\np3035\ntp3036\nRp3037\ng3033\nF6734.0\ntp3038\na(I6010000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99A\\xb4@'\np3039\ntp3040\nRp3041\ng3033\nF5182.0\ntp3042\na(I6020000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8,\\xb4@'\np3043\ntp3044\nRp3045\ng3033\nF4542.0\ntp3046\na(I6030000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94\\x15\\xb4@'\np3047\ntp3048\nRp3049\ng3033\nF3900.0\ntp3050\na(I6040000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xa9\\xb3@'\np3051\ntp3052\nRp3053\ng3033\nF1380.0\ntp3054\na(I6050000\ng1\n(g5\nS'\\xd7\\xa3p=\\x8a\\xb7\\xb3@'\np3055\ntp3056\nRp3057\ng3033\nF6600.0\ntp3058\na(I6060000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xb6\\xb3@'\np3059\ntp3060\nRp3061\ng3033\nF5130.0\ntp3062\na(I6070000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8\\xbd\\xb3@'\np3063\ntp3064\nRp3065\ng3033\nF5310.0\ntp3066\na(I6080000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xab\\xb3@'\np3067\ntp3068\nRp3069\ng3033\nF5310.0\ntp3070\na(I6090000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xef\\xb3@'\np3071\ntp3072\nRp3073\ng3033\nF9820.0\ntp3074\na(I6100000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e-\\xb4@'\np3075\ntp3076\nRp3077\ng3033\nF7950.0\ntp3078\na(I6110000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fI\\xb4@'\np3079\ntp3080\nRp3081\ng3033\nF7692.0\ntp3082\na(I6120000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f@\\xb4@'\np3083\ntp3084\nRp3085\ng3033\nF6682.0\ntp3086\na(I6130000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x19J\\xb4@'\np3087\ntp3088\nRp3089\ng3033\nF4350.0\ntp3090\na(I6140000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xbd_\\xb4@'\np3091\ntp3092\nRp3093\ng3033\nF8552.0\ntp3094\na(I6150000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05\\x86\\xb4@'\np3095\ntp3096\nRp3097\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05\\x86\\xb4@'\np3098\ntp3099\nRp3100\nF8064.0\ntp3101\na(I6160000\ng1\n(g5\nS'\\xa4p=\\nW\\x8d\\xb4@'\np3102\ntp3103\nRp3104\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8\\x91\\xb4@'\np3105\ntp3106\nRp3107\nF5268.0\ntp3108\na(I6170000\ng1\n(g5\nS')\\\\\\x8f\\xc2u\\x8b\\xb4@'\np3109\ntp3110\nRp3111\ng3107\nF4260.0\ntp3112\na(I6180000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1\\xbb\\xb4@'\np3113\ntp3114\nRp3115\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1\\xbb\\xb4@'\np3116\ntp3117\nRp3118\nF6504.0\ntp3119\na(I6190000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8\\xbf\\xb4@'\np3120\ntp3121\nRp3122\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8\\xbf\\xb4@'\np3123\ntp3124\nRp3125\nF4284.0\ntp3126\na(I6200000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xd4\\xb4@'\np3127\ntp3128\nRp3129\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xd4\\xb4@'\np3130\ntp3131\nRp3132\nF4512.0\ntp3133\na(I6210000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xbd\\xb4@'\np3134\ntp3135\nRp3136\ng3132\nF4220.0\ntp3137\na(I6220000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0\\xf2\\xb4@'\np3138\ntp3139\nRp3140\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0\\xf2\\xb4@'\np3141\ntp3142\nRp3143\nF7020.0\ntp3144\na(I6230000\ng1\n(g5\nS'3333\\xb3\\xd7\\xb4@'\np3145\ntp3146\nRp3147\ng3143\nF6198.0\ntp3148\na(I6240000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xae\\xb4@'\np3149\ntp3150\nRp3151\ng3143\nF5632.0\ntp3152\na(I6250000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xbd\\xca\\xb4@'\np3153\ntp3154\nRp3155\ng3143\nF5536.0\ntp3156\na(I6260000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xb3\\xb4@'\np3157\ntp3158\nRp3159\ng3143\nF6146.0\ntp3160\na(I6270000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x0f\\xb5@'\np3161\ntp3162\nRp3163\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x0f\\xb5@'\np3164\ntp3165\nRp3166\nF5926.0\ntp3167\na(I6280000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ)\\xb5@'\np3168\ntp3169\nRp3170\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ)\\xb5@'\np3171\ntp3172\nRp3173\nF5376.0\ntp3174\na(I6290000\ng1\n(g5\nS'\\n\\xd7\\xa3p=L\\xb5@'\np3175\ntp3176\nRp3177\ng1\n(g5\nS'\\n\\xd7\\xa3p=L\\xb5@'\np3178\ntp3179\nRp3180\nF7392.0\ntp3181\na(I6300000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05[\\xb5@'\np3182\ntp3183\nRp3184\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xbd}\\xb5@'\np3185\ntp3186\nRp3187\nF3900.0\ntp3188\na(I6310000\ng1\n(g5\nS'fffff\\x86\\xb5@'\np3189\ntp3190\nRp3191\ng1\n(g5\nS'fffff\\x86\\xb5@'\np3192\ntp3193\nRp3194\nF9674.0\ntp3195\na(I6320000\ng1\n(g5\nS'33333\\x89\\xb5@'\np3196\ntp3197\nRp3198\ng1\n(g5\nS'33333\\x89\\xb5@'\np3199\ntp3200\nRp3201\nF7760.0\ntp3202\na(I6330000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xa3\\xb5@'\np3203\ntp3204\nRp3205\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xa3\\xb5@'\np3206\ntp3207\nRp3208\nF6562.0\ntp3209\na(I6340000\ng1\n(g5\nS'{\\x14\\xaeGa\\xb3\\xb5@'\np3210\ntp3211\nRp3212\ng1\n(g5\nS'{\\x14\\xaeGa\\xb3\\xb5@'\np3213\ntp3214\nRp3215\nF6024.0\ntp3216\na(I6350000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xc9\\xb5@'\np3217\ntp3218\nRp3219\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xc9\\xb5@'\np3220\ntp3221\nRp3222\nF7046.0\ntp3223\na(I6360000\ng1\n(g5\nS'fffff\\xe7\\xb5@'\np3224\ntp3225\nRp3226\ng1\n(g5\nS'fffff\\xe7\\xb5@'\np3227\ntp3228\nRp3229\nF5132.0\ntp3230\na(I6370000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\n\\xb6@'\np3231\ntp3232\nRp3233\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\n\\xb6@'\np3234\ntp3235\nRp3236\nF8604.0\ntp3237\na(I6380000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa\\x03\\xb6@'\np3238\ntp3239\nRp3240\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x0c\\xb6@'\np3241\ntp3242\nRp3243\nF4320.0\ntp3244\na(I6390000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xbd\\xf0\\xb5@'\np3245\ntp3246\nRp3247\ng3243\nF4734.0\ntp3248\na(I6400000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xd9\\xb5@'\np3249\ntp3250\nRp3251\ng3243\nF5700.0\ntp3252\na(I6410000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xec\\xb5@'\np3253\ntp3254\nRp3255\ng3243\nF4832.0\ntp3256\na(I6420000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0\\xd6\\xb5@'\np3257\ntp3258\nRp3259\ng3243\nF6182.0\ntp3260\na(I6430000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xc5\\xb5@'\np3261\ntp3262\nRp3263\ng3243\nF5608.0\ntp3264\na(I6440000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1\\xba\\xb5@'\np3265\ntp3266\nRp3267\ng3243\nF4770.0\ntp3268\na(I6450000\ng1\n(g5\nS'q=\\n\\xd7#\\xe9\\xb5@'\np3269\ntp3270\nRp3271\ng3243\nF6802.0\ntp3272\na(I6460000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\n\\xb6@'\np3273\ntp3274\nRp3275\ng3243\nF9760.0\ntp3276\na(I6470000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccL\\x18\\xb6@'\np3277\ntp3278\nRp3279\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccL\\x18\\xb6@'\np3280\ntp3281\nRp3282\nF6138.0\ntp3283\na(I6480000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fT\\xb6@'\np3284\ntp3285\nRp3286\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fT\\xb6@'\np3287\ntp3288\nRp3289\nF10290.0\ntp3290\na(I6490000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(h\\xb6@'\np3291\ntp3292\nRp3293\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(h\\xb6@'\np3294\ntp3295\nRp3296\nF4932.0\ntp3297\na(I6500000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc7s\\xb6@'\np3298\ntp3299\nRp3300\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x8c\\xb6@'\np3301\ntp3302\nRp3303\nF5246.0\ntp3304\na(I6510000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa[\\xb6@'\np3305\ntp3306\nRp3307\ng3303\nF5880.0\ntp3308\na(I6520000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x8b\\xb6@'\np3309\ntp3310\nRp3311\ng3303\nF4542.0\ntp3312\na(I6530000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x86\\xb6@'\np3313\ntp3314\nRp3315\ng3303\nF5070.0\ntp3316\na(I6540000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xa4\\xb6@'\np3317\ntp3318\nRp3319\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xa4\\xb6@'\np3320\ntp3321\nRp3322\nF5892.0\ntp3323\na(I6550000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa\\xa3\\xb6@'\np3324\ntp3325\nRp3326\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb7\\xb6@'\np3327\ntp3328\nRp3329\nF2608.0\ntp3330\na(I6560000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xcf\\xb6@'\np3331\ntp3332\nRp3333\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xcf\\xb6@'\np3334\ntp3335\nRp3336\nF9080.0\ntp3337\na(I6570000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xd4\\xb6@'\np3338\ntp3339\nRp3340\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xd4\\xb6@'\np3341\ntp3342\nRp3343\nF3196.0\ntp3344\na(I6580000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xda\\xb6@'\np3345\ntp3346\nRp3347\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xf6\\xb6@'\np3348\ntp3349\nRp3350\nF3720.0\ntp3351\na(I6590000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xea\\xb6@'\np3352\ntp3353\nRp3354\ng1\n(g5\nS'\\xaeG\\xe1z\\x94\\xf7\\xb6@'\np3355\ntp3356\nRp3357\nF3840.0\ntp3358\na(I6600000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8#\\xb7@'\np3359\ntp3360\nRp3361\ng1\n(g5\nS'\\x1f\\x85\\xebQ8#\\xb7@'\np3362\ntp3363\nRp3364\nF7314.0\ntp3365\na(I6610000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\n\\xb7@'\np3366\ntp3367\nRp3368\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85%\\xb7@'\np3369\ntp3370\nRp3371\nF3000.0\ntp3372\na(I6620000\ng1\n(g5\nS'R\\xb8\\x1e\\x85k-\\xb7@'\np3373\ntp3374\nRp3375\ng1\n(g5\nS'R\\xb8\\x1e\\x85k-\\xb7@'\np3376\ntp3377\nRp3378\nF8766.0\ntp3379\na(I6630000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94\\t\\xb7@'\np3380\ntp3381\nRp3382\ng3378\nF5676.0\ntp3383\na(I6640000\ng1\n(g5\nS'R\\xb8\\x1e\\x85k\\xcf\\xb6@'\np3384\ntp3385\nRp3386\ng3378\nF5926.0\ntp3387\na(I6650000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xef\\xb6@'\np3388\ntp3389\nRp3390\ng3378\nF6130.0\ntp3391\na(I6660000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x13\\xb7@'\np3392\ntp3393\nRp3394\ng3378\nF6232.0\ntp3395\na(I6670000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x05\\xb7@'\np3396\ntp3397\nRp3398\ng3378\nF5088.0\ntp3399\na(I6680000\ng1\n(g5\nS'H\\xe1z\\x14.\\xec\\xb6@'\np3400\ntp3401\nRp3402\ng3378\nF4670.0\ntp3403\na(I6690000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8\\x14\\xb7@'\np3404\ntp3405\nRp3406\ng3378\nF6742.0\ntp3407\na(I6700000\ng1\n(g5\nS'H\\xe1z\\x14.&\\xb7@'\np3408\ntp3409\nRp3410\ng3378\nF5952.0\ntp3411\na(I6710000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05m\\xb7@'\np3412\ntp3413\nRp3414\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05m\\xb7@'\np3415\ntp3416\nRp3417\nF5934.0\ntp3418\na(I6720000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQk\\xb7@'\np3419\ntp3420\nRp3421\ng3417\nF6334.0\ntp3422\na(I6730000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x80\\xa1\\xb7@'\np3423\ntp3424\nRp3425\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xa3\\xb7@'\np3426\ntp3427\nRp3428\nF7568.0\ntp3429\na(I6740000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xb9\\xb7@'\np3430\ntp3431\nRp3432\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xb9\\xb7@'\np3433\ntp3434\nRp3435\nF7566.0\ntp3436\na(I6750000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xca\\xb7@'\np3437\ntp3438\nRp3439\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xca\\xb7@'\np3440\ntp3441\nRp3442\nF5964.0\ntp3443\na(I6760000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xbe\\xb7@'\np3444\ntp3445\nRp3446\ng3442\nF6742.0\ntp3447\na(I6770000\ng1\n(g5\nS'\\xa4p=\\nW\\xd1\\xb7@'\np3448\ntp3449\nRp3450\ng1\n(g5\nS'\\xa4p=\\nW\\xd1\\xb7@'\np3451\ntp3452\nRp3453\nF8100.0\ntp3454\na(I6780000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xda\\xb7@'\np3455\ntp3456\nRp3457\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xda\\xb7@'\np3458\ntp3459\nRp3460\nF5820.0\ntp3461\na(I6790000\ng1\n(g5\nS'{\\x14\\xaeGa\\xed\\xb7@'\np3462\ntp3463\nRp3464\ng1\n(g5\nS'{\\x14\\xaeGa\\xed\\xb7@'\np3465\ntp3466\nRp3467\nF7086.0\ntp3468\na(I6800000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94F\\xb8@'\np3469\ntp3470\nRp3471\ng1\n(g5\nS'\\xaeG\\xe1z\\x94F\\xb8@'\np3472\ntp3473\nRp3474\nF10300.0\ntp3475\na(I6810000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc77\\xb8@'\np3476\ntp3477\nRp3478\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5N\\xb8@'\np3479\ntp3480\nRp3481\nF6372.0\ntp3482\na(I6820000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x994\\xb8@'\np3483\ntp3484\nRp3485\ng3481\nF5608.0\ntp3486\na(I6830000\ng1\n(g5\nS'\\xa4p=\\n\\xd7d\\xb8@'\np3487\ntp3488\nRp3489\ng1\n(g5\nS'\\xa4p=\\n\\xd7d\\xb8@'\np3490\ntp3491\nRp3492\nF7486.0\ntp3493\na(I6840000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9eI\\xb8@'\np3494\ntp3495\nRp3496\ng3492\nF4670.0\ntp3497\na(I6850000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1s\\xb8@'\np3498\ntp3499\nRp3500\ng1\n(g5\nS'{\\x14\\xaeG\\xe1s\\xb8@'\np3501\ntp3502\nRp3503\nF6312.0\ntp3504\na(I6860000\ng1\n(g5\nS'H\\xe1z\\x14.z\\xb8@'\np3505\ntp3506\nRp3507\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x89\\xb8@'\np3508\ntp3509\nRp3510\nF8108.0\ntp3511\na(I6870000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x82\\xb8@'\np3512\ntp3513\nRp3514\ng3510\nF7446.0\ntp3515\na(I6880000\ng1\n(g5\nS'\\xd7\\xa3p=\\n}\\xb8@'\np3516\ntp3517\nRp3518\ng3510\nF6876.0\ntp3519\na(I6890000\ng1\n(g5\nS'ffffft\\xb8@'\np3520\ntp3521\nRp3522\ng3510\nF4092.0\ntp3523\na(I6900000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x97\\xb8@'\np3524\ntp3525\nRp3526\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\xa9\\xb8@'\np3527\ntp3528\nRp3529\nF4860.0\ntp3530\na(I6910000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9c\\xb8@'\np3531\ntp3532\nRp3533\ng3529\nF6462.0\ntp3534\na(I6920000\ng1\n(g5\nS'{\\x14\\xaeGa\\x95\\xb8@'\np3535\ntp3536\nRp3537\ng3529\nF7488.0\ntp3538\na(I6930000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x8d\\xb8@'\np3539\ntp3540\nRp3541\ng3529\nF4170.0\ntp3542\na(I6940000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xa5\\xb8@'\np3543\ntp3544\nRp3545\ng3529\nF5308.0\ntp3546\na(I6950000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xc7\\xb8@'\np3547\ntp3548\nRp3549\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xc7\\xb8@'\np3550\ntp3551\nRp3552\nF6176.0\ntp3553\na(I6960000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xb7\\xb8@'\np3554\ntp3555\nRp3556\ng3552\nF4092.0\ntp3557\na(I6970000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xbf\\xb8@'\np3558\ntp3559\nRp3560\ng3552\nF7492.0\ntp3561\na(I6980000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8\\xa0\\xb8@'\np3562\ntp3563\nRp3564\ng3552\nF6262.0\ntp3565\na(I6990000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccL\\xa2\\xb8@'\np3566\ntp3567\nRp3568\ng3552\nF5248.0\ntp3569\na(I7000000\ng1\n(g5\nS'R\\xb8\\x1e\\x85kz\\xb8@'\np3570\ntp3571\nRp3572\ng3552\nF4220.0\ntp3573\na(I7010000\ng1\n(g5\nS'q=\\n\\xd7\\xa3L\\xb8@'\np3574\ntp3575\nRp3576\ng3552\nF5608.0\ntp3577\na(I7020000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8H\\xb8@'\np3578\ntp3579\nRp3580\ng3552\nF5696.0\ntp3581\na(I7030000\ng1\n(g5\nS'33333\\x16\\xb8@'\np3582\ntp3583\nRp3584\ng3552\nF3000.0\ntp3585\na(I7040000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xe0\\xb7@'\np3586\ntp3587\nRp3588\ng3552\nF1380.0\ntp3589\na(I7050000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x19\\x06\\xb8@'\np3590\ntp3591\nRp3592\ng3552\nF7314.0\ntp3593\na(I7060000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa\\xe9\\xb7@'\np3594\ntp3595\nRp3596\ng3552\nF4092.0\ntp3597\na(I7070000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xf1\\xb7@'\np3598\ntp3599\nRp3600\ng3552\nF8340.0\ntp3601\na(I7080000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdb\\xb7@'\np3602\ntp3603\nRp3604\ng3552\nF6894.0\ntp3605\na(I7090000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe0\\xb7@'\np3606\ntp3607\nRp3608\ng3552\nF7050.0\ntp3609\na(I7100000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94\\x12\\xb8@'\np3610\ntp3611\nRp3612\ng3552\nF5410.0\ntp3613\na(I7110000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x0c\\xb8@'\np3614\ntp3615\nRp3616\ng3552\nF4290.0\ntp3617\na(I7120000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x12\\xb8@'\np3618\ntp3619\nRp3620\ng3552\nF6948.0\ntp3621\na(I7130000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x01\\xb8@'\np3622\ntp3623\nRp3624\ng3552\nF6240.0\ntp3625\na(I7140000\ng1\n(g5\nS'R\\xb8\\x1e\\x85k\\x8a\\xb7@'\np3626\ntp3627\nRp3628\ng3552\nF4110.0\ntp3629\na(I7150000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8\\xaa\\xb7@'\np3630\ntp3631\nRp3632\ng3552\nF6224.0\ntp3633\na(I7160000\ng1\n(g5\nS'H\\xe1z\\x14.\\x9a\\xb7@'\np3634\ntp3635\nRp3636\ng3552\nF7776.0\ntp3637\na(I7170000\ng1\n(g5\nS'\\xd7\\xa3p=\\x8a\\xa2\\xb7@'\np3638\ntp3639\nRp3640\ng3552\nF5280.0\ntp3641\na(I7180000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xa1\\xb7@'\np3642\ntp3643\nRp3644\ng3552\nF6892.0\ntp3645\na(I7190000\ng1\n(g5\nS'3333\\xb3\\xc0\\xb7@'\np3646\ntp3647\nRp3648\ng3552\nF9220.0\ntp3649\na(I7200000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xa0\\xb7@'\np3650\ntp3651\nRp3652\ng3552\nF4860.0\ntp3653\na(I7210000\ng1\n(g5\nS'R\\xb8\\x1e\\x85k\\x83\\xb7@'\np3654\ntp3655\nRp3656\ng3552\nF3570.0\ntp3657\na(I7220000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xb4\\xb7@'\np3658\ntp3659\nRp3660\ng3552\nF11358.0\ntp3661\na(I7230000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8\\xd5\\xb7@'\np3662\ntp3663\nRp3664\ng3552\nF7068.0\ntp3665\na(I7240000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05\\xd3\\xb7@'\np3666\ntp3667\nRp3668\ng3552\nF6478.0\ntp3669\na(I7250000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xc8\\xb7@'\np3670\ntp3671\nRp3672\ng3552\nF7476.0\ntp3673\na(I7260000\ng1\n(g5\nS'R\\xb8\\x1e\\x85k\\xe3\\xb7@'\np3674\ntp3675\nRp3676\ng3552\nF6168.0\ntp3677\na(I7270000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xcf\\xb7@'\np3678\ntp3679\nRp3680\ng3552\nF7986.0\ntp3681\na(I7280000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf1\\xb7@'\np3682\ntp3683\nRp3684\ng3552\nF7818.0\ntp3685\na(I7290000\ng1\n(g5\nS'\\xd7\\xa3p=\\x8a\\xf3\\xb7@'\np3686\ntp3687\nRp3688\ng3552\nF7224.0\ntp3689\na(I7300000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xf4\\xb7@'\np3690\ntp3691\nRp3692\ng3552\nF4898.0\ntp3693\na(I7310000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xf7\\xb7@'\np3694\ntp3695\nRp3696\ng3552\nF7050.0\ntp3697\na(I7320000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xec\\xb7@'\np3698\ntp3699\nRp3700\ng3552\nF6894.0\ntp3701\na(I7330000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x0c\\xb8@'\np3702\ntp3703\nRp3704\ng3552\nF9044.0\ntp3705\na(I7340000\ng1\n(g5\nS'H\\xe1z\\x14\\xae(\\xb8@'\np3706\ntp3707\nRp3708\ng3552\nF10040.0\ntp3709\na(I7350000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa\\x13\\xb8@'\np3710\ntp3711\nRp3712\ng3552\nF6100.0\ntp3713\na(I7360000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xea\\xb7@'\np3714\ntp3715\nRp3716\ng3552\nF5182.0\ntp3717\na(I7370000\ng1\n(g5\nS'33333\\xdc\\xb7@'\np3718\ntp3719\nRp3720\ng3552\nF4414.0\ntp3721\na(I7380000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xd7\\xb7@'\np3722\ntp3723\nRp3724\ng3552\nF6978.0\ntp3725\na(I7390000\ng1\n(g5\nS'\\xd7\\xa3p=\\x8a\\xd5\\xb7@'\np3726\ntp3727\nRp3728\ng3552\nF6262.0\ntp3729\na(I7400000\ng1\n(g5\nS'3333\\xb3\\xdf\\xb7@'\np3730\ntp3731\nRp3732\ng3552\nF8820.0\ntp3733\na(I7410000\ng1\n(g5\nS'\\xd7\\xa3p=\\x8a\\xb7\\xb7@'\np3734\ntp3735\nRp3736\ng3552\nF4092.0\ntp3737\na(I7420000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xe3\\xb7@'\np3738\ntp3739\nRp3740\ng3552\nF9288.0\ntp3741\na(I7430000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xcb\\xb7@'\np3742\ntp3743\nRp3744\ng3552\nF6704.0\ntp3745\na(I7440000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05\\xd9\\xb7@'\np3746\ntp3747\nRp3748\ng3552\nF8346.0\ntp3749\na(I7450000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xd4\\xb7@'\np3750\ntp3751\nRp3752\ng3552\nF4962.0\ntp3753\na(I7460000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa\\xbd\\xb7@'\np3754\ntp3755\nRp3756\ng3552\nF5310.0\ntp3757\na(I7470000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94\\xc5\\xb7@'\np3758\ntp3759\nRp3760\ng3552\nF6330.0\ntp3761\na(I7480000\ng1\n(g5\nS'3333\\xb3\\xcf\\xb7@'\np3762\ntp3763\nRp3764\ng3552\nF5182.0\ntp3765\na(I7490000\ng1\n(g5\nS'H\\xe1z\\x14.\\xa8\\xb7@'\np3766\ntp3767\nRp3768\ng3552\nF2496.0\ntp3769\na(I7500000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xab\\xb7@'\np3770\ntp3771\nRp3772\ng3552\nF6534.0\ntp3773\na(I7510000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xed\\xb7@'\np3774\ntp3775\nRp3776\ng3552\nF7200.0\ntp3777\na(I7520000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x19\\xd2\\xb7@'\np3778\ntp3779\nRp3780\ng3552\nF4734.0\ntp3781\na(I7530000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xe7\\xb7@'\np3782\ntp3783\nRp3784\ng3552\nF1380.0\ntp3785\na(I7540000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\7\\xb8@'\np3786\ntp3787\nRp3788\ng3552\nF10610.0\ntp3789\na(I7550000\ng1\n(g5\nS'\\xd7\\xa3p=\\x8aT\\xb8@'\np3790\ntp3791\nRp3792\ng3552\nF8166.0\ntp3793\na(I7560000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zn\\xb8@'\np3794\ntp3795\nRp3796\ng3552\nF8940.0\ntp3797\na(I7570000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xa6\\xb8@'\np3798\ntp3799\nRp3800\ng3552\nF5054.0\ntp3801\na(I7580000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xc4\\xb8@'\np3802\ntp3803\nRp3804\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xce\\xb8@'\np3805\ntp3806\nRp3807\nF4764.0\ntp3808\na(I7590000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc7\\xb3\\xb8@'\np3809\ntp3810\nRp3811\ng3807\nF7416.0\ntp3812\na(I7600000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xfd\\xb8@'\np3813\ntp3814\nRp3815\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xfd\\xb8@'\np3816\ntp3817\nRp3818\nF10350.0\ntp3819\na(I7610000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f;\\xb9@'\np3820\ntp3821\nRp3822\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f;\\xb9@'\np3823\ntp3824\nRp3825\nF6618.0\ntp3826\na(I7620000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0?\\xb9@'\np3827\ntp3828\nRp3829\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0?\\xb9@'\np3830\ntp3831\nRp3832\nF8022.0\ntp3833\na(I7630000\ng1\n(g5\nS'\\xa4p=\\n\\xd7[\\xb9@'\np3834\ntp3835\nRp3836\ng1\n(g5\nS'\\xa4p=\\n\\xd7[\\xb9@'\np3837\ntp3838\nRp3839\nF7652.0\ntp3840\na(I7640000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x8e\\xb9@'\np3841\ntp3842\nRp3843\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x8e\\xb9@'\np3844\ntp3845\nRp3846\nF5880.0\ntp3847\na(I7650000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x9e\\xb9@'\np3848\ntp3849\nRp3850\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x9e\\xb9@'\np3851\ntp3852\nRp3853\nF9960.0\ntp3854\na(I7660000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc7\\x81\\xb9@'\np3855\ntp3856\nRp3857\ng3853\nF4220.0\ntp3858\na(I7670000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e~\\xb9@'\np3859\ntp3860\nRp3861\ng3853\nF7320.0\ntp3862\na(I7680000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8k\\xb9@'\np3863\ntp3864\nRp3865\ng3853\nF5340.0\ntp3866\na(I7690000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xbc\\xb9@'\np3867\ntp3868\nRp3869\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xbc\\xb9@'\np3870\ntp3871\nRp3872\nF12696.0\ntp3873\na(I7700000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xc0\\xb9@'\np3874\ntp3875\nRp3876\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xcb\\xb9@'\np3877\ntp3878\nRp3879\nF5880.0\ntp3880\na(I7710000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x05\\xba@'\np3881\ntp3882\nRp3883\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x05\\xba@'\np3884\ntp3885\nRp3886\nF8736.0\ntp3887\na(I7720000\ng1\n(g5\nS'R\\xb8\\x1e\\x85k#\\xba@'\np3888\ntp3889\nRp3890\ng1\n(g5\nS'R\\xb8\\x1e\\x85k#\\xba@'\np3891\ntp3892\nRp3893\nF9282.0\ntp3894\na(I7730000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xc1\\xba@'\np3895\ntp3896\nRp3897\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xc1\\xba@'\np3898\ntp3899\nRp3900\nF5280.0\ntp3901\na(I7740000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ*\\xbb@'\np3902\ntp3903\nRp3904\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ*\\xbb@'\np3905\ntp3906\nRp3907\nF14594.0\ntp3908\na(I7750000\ng1\n(g5\nS'H\\xe1z\\x14\\xae>\\xbb@'\np3909\ntp3910\nRp3911\ng1\n(g5\nS'H\\xe1z\\x14\\xae>\\xbb@'\np3912\ntp3913\nRp3914\nF8260.0\ntp3915\na(I7760000\ng1\n(g5\nS\"\\xcd\\xcc\\xcc\\xcc\\xcc'\\xbb@\"\np3916\ntp3917\nRp3918\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\S\\xbb@'\np3919\ntp3920\nRp3921\nF3420.0\ntp3922\na(I7770000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8>\\xbb@'\np3923\ntp3924\nRp3925\ng3921\nF5676.0\ntp3926\na(I7780000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGo\\xbb@'\np3927\ntp3928\nRp3929\ng1\n(g5\nS'\\xe1z\\x14\\xaeGo\\xbb@'\np3930\ntp3931\nRp3932\nF12068.0\ntp3933\na(I7790000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e^\\xbb@'\np3934\ntp3935\nRp3936\ng1\n(g5\nS'\\x14\\xaeG\\xe1zq\\xbb@'\np3937\ntp3938\nRp3939\nF7284.0\ntp3940\na(I7800000\ng1\n(g5\nS'\\xd7\\xa3p=\\n{\\xbb@'\np3941\ntp3942\nRp3943\ng1\n(g5\nS'\\xd7\\xa3p=\\n{\\xbb@'\np3944\ntp3945\nRp3946\nF9636.0\ntp3947\na(I7810000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xa3\\xbb@'\np3948\ntp3949\nRp3950\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xa3\\xbb@'\np3951\ntp3952\nRp3953\nF4860.0\ntp3954\na(I7820000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbf\\xbb@'\np3955\ntp3956\nRp3957\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbf\\xbb@'\np3958\ntp3959\nRp3960\nF6390.0\ntp3961\na(I7830000\ng1\n(g5\nS'q=\\n\\xd7\\xa3v\\xbb@'\np3962\ntp3963\nRp3964\ng3960\nF6028.0\ntp3965\na(I7840000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xbdZ\\xbb@'\np3966\ntp3967\nRp3968\ng3960\nF4156.0\ntp3969\na(I7850000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQW\\xbb@'\np3970\ntp3971\nRp3972\ng3960\nF6888.0\ntp3973\na(I7860000\ng1\n(g5\nS'H\\xe1z\\x14./\\xbb@'\np3974\ntp3975\nRp3976\ng3960\nF4796.0\ntp3977\na(I7870000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8n\\xbb@'\np3978\ntp3979\nRp3980\ng3960\nF12472.0\ntp3981\na(I7880000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00m\\xbb@'\np3982\ntp3983\nRp3984\ng3960\nF8164.0\ntp3985\na(I7890000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x196\\xbb@'\np3986\ntp3987\nRp3988\ng3960\nF4956.0\ntp3989\na(I7900000\ng1\n(g5\nS'\\xa4p=\\nW.\\xbb@'\np3990\ntp3991\nRp3992\ng3960\nF5182.0\ntp3993\na(I7910000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x19\\xbb@'\np3994\ntp3995\nRp3996\ng3960\nF2664.0\ntp3997\na(I7920000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e.\\xbb@'\np3998\ntp3999\nRp4000\ng3960\nF9720.0\ntp4001\na(I7930000\ng1\n(g5\nS'\\n\\xd7\\xa3p=0\\xbb@'\np4002\ntp4003\nRp4004\ng3960\nF6390.0\ntp4005\na(I7940000\ng1\n(g5\nS'{\\x14\\xaeGa\\xfc\\xba@'\np4006\ntp4007\nRp4008\ng3960\nF4860.0\ntp4009\na(I7950000\ng1\n(g5\nS'R\\xb8\\x1e\\x85k\\xf5\\xba@'\np4010\ntp4011\nRp4012\ng3960\nF5404.0\ntp4013\na(I7960000\ng1\n(g5\nS'\\xf6(\\\\\\x8fB\\x14\\xbb@'\np4014\ntp4015\nRp4016\ng3960\nF7112.0\ntp4017\na(I7970000\ng1\n(g5\nS'ffff\\xe6:\\xbb@'\np4018\ntp4019\nRp4020\ng3960\nF6644.0\ntp4021\na(I7980000\ng1\n(g5\nS'\\xf6(\\\\\\x8fB7\\xbb@'\np4022\ntp4023\nRp4024\ng3960\nF5148.0\ntp4025\na(I7990000\ng1\n(g5\nS'q=\\n\\xd7#\\x1e\\xbb@'\np4026\ntp4027\nRp4028\ng3960\nF6292.0\ntp4029\na(I8000000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x15\\xbb@'\np4030\ntp4031\nRp4032\ng3960\nF5024.0\ntp4033\na(I8010000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc24\\xbb@'\np4034\ntp4035\nRp4036\ng3960\nF7212.0\ntp4037\na(I8020000\ng1\n(g5\nS'{\\x14\\xaeGa\\x03\\xbb@'\np4038\ntp4039\nRp4040\ng3960\nF5200.0\ntp4041\na(I8030000\ng1\n(g5\nS'R\\xb8\\x1e\\x85kT\\xbb@'\np4042\ntp4043\nRp4044\ng3960\nF9030.0\ntp4045\na(I8040000\ng1\n(g5\nS'\\xf6(\\\\\\x8fB\\x03\\xbb@'\np4046\ntp4047\nRp4048\ng3960\nF6840.0\ntp4049\na(I8050000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\>\\xbb@'\np4050\ntp4051\nRp4052\ng3960\nF10872.0\ntp4053\na(I8060000\ng1\n(g5\nS'fffffk\\xbb@'\np4054\ntp4055\nRp4056\ng3960\nF8916.0\ntp4057\na(I8070000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc7\\x8e\\xbb@'\np4058\ntp4059\nRp4060\ng3960\nF6508.0\ntp4061\na(I8080000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc1\\xbb@'\np4062\ntp4063\nRp4064\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc1\\xbb@'\np4065\ntp4066\nRp4067\nF6732.0\ntp4068\na(I8090000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x80\\xab\\xbb@'\np4069\ntp4070\nRp4071\ng4067\nF5312.0\ntp4072\na(I8100000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xfb\\xbb@'\np4073\ntp4074\nRp4075\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xfb\\xbb@'\np4076\ntp4077\nRp4078\nF5216.0\ntp4079\na(I8110000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xb8\\xbb@'\np4080\ntp4081\nRp4082\ng4078\nF4348.0\ntp4083\na(I8120000\ng1\n(g5\nS'33333\\xb6\\xbb@'\np4084\ntp4085\nRp4086\ng4078\nF6936.0\ntp4087\na(I8130000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8\\xb6\\xbb@'\np4088\ntp4089\nRp4090\ng4078\nF4700.0\ntp4091\na(I8140000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05\\xf1\\xbb@'\np4092\ntp4093\nRp4094\ng4078\nF6996.0\ntp4095\na(I8150000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05\\xc7\\xbb@'\np4096\ntp4097\nRp4098\ng4078\nF6410.0\ntp4099\na(I8160000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x9e\\xbb@'\np4100\ntp4101\nRp4102\ng4078\nF5132.0\ntp4103\na(I8170000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\x96\\xbb@'\np4104\ntp4105\nRp4106\ng4078\nF6840.0\ntp4107\na(I8180000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x99\\xbb@'\np4108\ntp4109\nRp4110\ng4078\nF5246.0\ntp4111\na(I8190000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x9c\\xbb@'\np4112\ntp4113\nRp4114\ng4078\nF6024.0\ntp4115\na(I8200000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8v\\xbb@'\np4116\ntp4117\nRp4118\ng4078\nF6610.0\ntp4119\na(I8210000\ng1\n(g5\nS'3333\\xb3\\x86\\xbb@'\np4120\ntp4121\nRp4122\ng4078\nF8024.0\ntp4123\na(I8220000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x19\\xb6\\xbb@'\np4124\ntp4125\nRp4126\ng4078\nF12030.0\ntp4127\na(I8230000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xbc\\xbb@'\np4128\ntp4129\nRp4130\ng4078\nF7476.0\ntp4131\na(I8240000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8\\xc9\\xbb@'\np4132\ntp4133\nRp4134\ng4078\nF7614.0\ntp4135\na(I8250000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc7\\xa5\\xbb@'\np4136\ntp4137\nRp4138\ng4078\nF8032.0\ntp4139\na(I8260000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc7\\xf8\\xbb@'\np4140\ntp4141\nRp4142\ng4078\nF10630.0\ntp4143\na(I8270000\ng1\n(g5\nS'{\\x14\\xaeGa\\x06\\xbc@'\np4144\ntp4145\nRp4146\ng1\n(g5\nS'{\\x14\\xaeGa\\x06\\xbc@'\np4147\ntp4148\nRp4149\nF7410.0\ntp4150\na(I8280000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa\\x1e\\xbc@'\np4151\ntp4152\nRp4153\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa\\x1e\\xbc@'\np4154\ntp4155\nRp4156\nF9780.0\ntp4157\na(I8290000\ng1\n(g5\nS'\\xd7\\xa3p=\\nm\\xbc@'\np4158\ntp4159\nRp4160\ng1\n(g5\nS'\\xd7\\xa3p=\\nm\\xbc@'\np4161\ntp4162\nRp4163\nF7486.0\ntp4164\na(I8300000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc7]\\xbc@'\np4165\ntp4166\nRp4167\ng4163\nF11170.0\ntp4168\na(I8310000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x86\\xbc@'\np4169\ntp4170\nRp4171\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x86\\xbc@'\np4172\ntp4173\nRp4174\nF9880.0\ntp4175\na(I8320000\ng1\n(g5\nS'\\xa4p=\\nW\\xe6\\xbc@'\np4176\ntp4177\nRp4178\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xe6\\xbc@'\np4179\ntp4180\nRp4181\nF6186.0\ntp4182\na(I8330000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xad\\xbc@'\np4183\ntp4184\nRp4185\ng4181\nF7080.0\ntp4186\na(I8340000\ng1\n(g5\nS'33333\\x83\\xbc@'\np4187\ntp4188\nRp4189\ng4181\nF10150.0\ntp4190\na(I8350000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc2\\xbc@'\np4191\ntp4192\nRp4193\ng4181\nF11560.0\ntp4194\na(I8360000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x92\\xbc@'\np4195\ntp4196\nRp4197\ng4181\nF9810.0\ntp4198\na(I8370000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc7\\xd5\\xbc@'\np4199\ntp4200\nRp4201\ng4181\nF5934.0\ntp4202\na(I8380000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xf7\\xbc@'\np4203\ntp4204\nRp4205\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xf7\\xbc@'\np4206\ntp4207\nRp4208\nF10368.0\ntp4209\na(I8390000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa\\x12\\xbd@'\np4210\ntp4211\nRp4212\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa\\x12\\xbd@'\np4213\ntp4214\nRp4215\nF8406.0\ntp4216\na(I8400000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xfb\\xbc@'\np4217\ntp4218\nRp4219\ng4215\nF7492.0\ntp4220\na(I8410000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x19\\xd0\\xbc@'\np4221\ntp4222\nRp4223\ng4215\nF5790.0\ntp4224\na(I8420000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x19\\xe1\\xbc@'\np4225\ntp4226\nRp4227\ng4215\nF8316.0\ntp4228\na(I8430000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xee\\xbc@'\np4229\ntp4230\nRp4231\ng4215\nF7776.0\ntp4232\na(I8440000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0\\xc5\\xbc@'\np4233\ntp4234\nRp4235\ng4215\nF1588.0\ntp4236\na(I8450000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\t\\xbd@'\np4237\ntp4238\nRp4239\ng4215\nF4350.0\ntp4240\na(I8460000\ng1\n(g5\nS'\\xf6(\\\\\\x8fB\\xf5\\xbc@'\np4241\ntp4242\nRp4243\ng4215\nF4320.0\ntp4244\na(I8470000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xce\\xbc@'\np4245\ntp4246\nRp4247\ng4215\nF6644.0\ntp4248\na(I8480000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1\\xb5\\xbc@'\np4249\ntp4250\nRp4251\ng4215\nF9468.0\ntp4252\na(I8490000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f\\x01\\xbd@'\np4253\ntp4254\nRp4255\ng4215\nF11424.0\ntp4256\na(I8500000\ng1\n(g5\nS'{\\x14\\xaeGa>\\xbd@'\np4257\ntp4258\nRp4259\ng1\n(g5\nS'{\\x14\\xaeGa>\\xbd@'\np4260\ntp4261\nRp4262\nF11088.0\ntp4263\na(I8510000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc=\\xbd@'\np4264\ntp4265\nRp4266\ng4262\nF6720.0\ntp4267\na(I8520000\ng1\n(g5\nS'fffffU\\xbd@'\np4268\ntp4269\nRp4270\ng1\n(g5\nS'fffffU\\xbd@'\np4271\ntp4272\nRp4273\nF2888.0\ntp4274\na(I8530000\ng1\n(g5\nS')\\\\\\x8f\\xc2u\\xfe\\xbc@'\np4275\ntp4276\nRp4277\ng4273\nF6194.0\ntp4278\na(I8540000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x01\\xbd@'\np4279\ntp4280\nRp4281\ng4273\nF6606.0\ntp4282\na(I8550000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccL\\x12\\xbd@'\np4283\ntp4284\nRp4285\ng4273\nF6538.0\ntp4286\na(I8560000\ng1\n(g5\nS\"\\x1f\\x85\\xebQ\\xb8'\\xbd@\"\np4287\ntp4288\nRp4289\ng4273\nF7866.0\ntp4290\na(I8570000\ng1\n(g5\nS'R\\xb8\\x1e\\x85k\\xfe\\xbc@'\np4291\ntp4292\nRp4293\ng4273\nF7860.0\ntp4294\na(I8580000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x13\\xbd@'\np4295\ntp4296\nRp4297\ng4273\nF7950.0\ntp4298\na(I8590000\ng1\n(g5\nS'33333 \\xbd@'\np4299\ntp4300\nRp4301\ng4273\nF6456.0\ntp4302\na(I8600000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x7f\\xbd@'\np4303\ntp4304\nRp4305\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x7f\\xbd@'\np4306\ntp4307\nRp4308\nF10130.0\ntp4309\na(I8610000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x80\\x93\\xbd@'\np4310\ntp4311\nRp4312\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x80\\x93\\xbd@'\np4313\ntp4314\nRp4315\nF9580.0\ntp4316\na(I8620000\ng1\n(g5\nS'33333\\x88\\xbd@'\np4317\ntp4318\nRp4319\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xa5\\xbd@'\np4320\ntp4321\nRp4322\nF4284.0\ntp4323\na(I8630000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xaa\\xbd@'\np4324\ntp4325\nRp4326\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xaa\\xbd@'\np4327\ntp4328\nRp4329\nF9320.0\ntp4330\na(I8640000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1\\x9d\\xbd@'\np4331\ntp4332\nRp4333\ng4329\nF6636.0\ntp4334\na(I8650000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8\\x8b\\xbd@'\np4335\ntp4336\nRp4337\ng4329\nF7170.0\ntp4338\na(I8660000\ng1\n(g5\nS'H\\xe1z\\x14.\\x02\\xbe@'\np4339\ntp4340\nRp4341\ng1\n(g5\nS'H\\xe1z\\x14.\\x02\\xbe@'\np4342\ntp4343\nRp4344\nF9540.0\ntp4345\na(I8670000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x00\\xbe@'\np4346\ntp4347\nRp4348\ng4344\nF6678.0\ntp4349\na(I8680000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xfc\\xbd@'\np4350\ntp4351\nRp4352\ng4344\nF9800.0\ntp4353\na(I8690000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xc1\\xbd@'\np4354\ntp4355\nRp4356\ng4344\nF5268.0\ntp4357\na(I8700000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb9\\xbd@'\np4358\ntp4359\nRp4360\ng4344\nF8022.0\ntp4361\na(I8710000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xc3\\xbd@'\np4362\ntp4363\nRp4364\ng4344\nF6312.0\ntp4365\na(I8720000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc7\\xbf\\xbd@'\np4366\ntp4367\nRp4368\ng4344\nF10030.0\ntp4369\na(I8730000\ng1\n(g5\nS')\\\\\\x8f\\xc2u\\xcc\\xbd@'\np4370\ntp4371\nRp4372\ng4344\nF5744.0\ntp4373\na(I8740000\ng1\n(g5\nS'\\xd7\\xa3p=\\x8a\\x05\\xbe@'\np4374\ntp4375\nRp4376\ng1\n(g5\nS'\\xd7\\xa3p=\\x8a\\x05\\xbe@'\np4377\ntp4378\nRp4379\nF10602.0\ntp4380\na(I8750000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0\\xf5\\xbd@'\np4381\ntp4382\nRp4383\ng4379\nF9360.0\ntp4384\na(I8760000\ng1\n(g5\nS'fffff\\xef\\xbd@'\np4385\ntp4386\nRp4387\ng4379\nF7470.0\ntp4388\na(I8770000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xe5\\xbd@'\np4389\ntp4390\nRp4391\ng4379\nF5896.0\ntp4392\na(I8780000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x80\\xcf\\xbd@'\np4393\ntp4394\nRp4395\ng4379\nF5756.0\ntp4396\na(I8790000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xdf\\xbd@'\np4397\ntp4398\nRp4399\ng4379\nF7224.0\ntp4400\na(I8800000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8\\x1a\\xbe@'\np4401\ntp4402\nRp4403\ng1\n(g5\nS'\\x1f\\x85\\xebQ8\\x1a\\xbe@'\np4404\ntp4405\nRp4406\nF15274.0\ntp4407\na(I8810000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc7\\x18\\xbe@'\np4408\ntp4409\nRp4410\ng4406\nF6232.0\ntp4411\na(I8820000\ng1\n(g5\nS'3333\\xb3\\x19\\xbe@'\np4412\ntp4413\nRp4414\ng1\n(g5\nS\"\\x00\\x00\\x00\\x00\\x00'\\xbe@\"\np4415\ntp4416\nRp4417\nF5280.0\ntp4418\na(I8830000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x16\\xbe@'\np4419\ntp4420\nRp4421\ng1\n(g5\nS'fffff2\\xbe@'\np4422\ntp4423\nRp4424\nF5248.0\ntp4425\na(I8840000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xe0\\xbd@'\np4426\ntp4427\nRp4428\ng4424\nF6628.0\ntp4429\na(I8850000\ng1\n(g5\nS'fffff\\x11\\xbe@'\np4430\ntp4431\nRp4432\ng4424\nF9464.0\ntp4433\na(I8860000\ng1\n(g5\nS'H\\xe1z\\x14.\\xdc\\xbd@'\np4434\ntp4435\nRp4436\ng4424\nF5132.0\ntp4437\na(I8870000\ng1\n(g5\nS'\\xf6(\\\\\\x8fB\\xee\\xbd@'\np4438\ntp4439\nRp4440\ng4424\nF9840.0\ntp4441\na(I8880000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xf7\\xbd@'\np4442\ntp4443\nRp4444\ng4424\nF10230.0\ntp4445\na(I8890000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd8\\xbd@'\np4446\ntp4447\nRp4448\ng4424\nF8362.0\ntp4449\na(I8900000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5q\\xbd@'\np4450\ntp4451\nRp4452\ng4424\nF4110.0\ntp4453\na(I8910000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14:\\xbd@'\np4454\ntp4455\nRp4456\ng4424\nF7704.0\ntp4457\na(I8920000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xf6\\xbc@'\np4458\ntp4459\nRp4460\ng4424\nF7398.0\ntp4461\na(I8930000\ng1\n(g5\nS'q=\\n\\xd7#\\xf2\\xbc@'\np4462\ntp4463\nRp4464\ng4424\nF3600.0\ntp4465\na(I8940000\ng1\n(g5\nS'\\xf6(\\\\\\x8fB\\xc5\\xbc@'\np4466\ntp4467\nRp4468\ng4424\nF5662.0\ntp4469\na(I8950000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\xae\\xbc@'\np4470\ntp4471\nRp4472\ng4424\nF11300.0\ntp4473\na(I8960000\ng1\n(g5\nS'fffff<\\xbc@'\np4474\ntp4475\nRp4476\ng4424\nF2160.0\ntp4477\na(I8970000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xc6\\xbc@'\np4478\ntp4479\nRp4480\ng4424\nF19730.0\ntp4481\na(I8980000\ng1\n(g5\nS'q=\\n\\xd7#\\xac\\xbc@'\np4482\ntp4483\nRp4484\ng4424\nF6292.0\ntp4485\na(I8990000\ng1\n(g5\nS'ffff\\xe6\\xa6\\xbc@'\np4486\ntp4487\nRp4488\ng4424\nF8826.0\ntp4489\na(I9000000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x92\\xbc@'\np4490\ntp4491\nRp4492\ng4424\nF6516.0\ntp4493\na(I9010000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa6\\xbc@'\np4494\ntp4495\nRp4496\ng4424\nF7818.0\ntp4497\na(I9020000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xd5\\xbc@'\np4498\ntp4499\nRp4500\ng4424\nF6266.0\ntp4501\na(I9030000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xcc\\xbc@'\np4502\ntp4503\nRp4504\ng4424\nF6906.0\ntp4505\na(I9040000\ng1\n(g5\nS'\\xa4p=\\nWJ\\xbd@'\np4506\ntp4507\nRp4508\ng4424\nF5540.0\ntp4509\na(I9050000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ*\\xbd@'\np4510\ntp4511\nRp4512\ng4424\nF8592.0\ntp4513\na(I9060000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z3\\xbd@'\np4514\ntp4515\nRp4516\ng4424\nF8764.0\ntp4517\na(I9070000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(R\\xbd@'\np4518\ntp4519\nRp4520\ng4424\nF5602.0\ntp4521\na(I9080000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xb5\\xbd@'\np4522\ntp4523\nRp4524\ng4424\nF16572.0\ntp4525\na(I9090000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xe4\\xbd@'\np4526\ntp4527\nRp4528\ng4424\nF8704.0\ntp4529\na(I9100000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x9a\\xbd@'\np4530\ntp4531\nRp4532\ng4424\nF8178.0\ntp4533\na(I9110000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(n\\xbd@'\np4534\ntp4535\nRp4536\ng4424\nF6652.0\ntp4537\na(I9120000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xda\\xbd@'\np4538\ntp4539\nRp4540\ng4424\nF12000.0\ntp4541\na(I9130000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xe3\\xbd@'\np4542\ntp4543\nRp4544\ng4424\nF6810.0\ntp4545\na(I9140000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8\\x07\\xbe@'\np4546\ntp4547\nRp4548\ng4424\nF8148.0\ntp4549\na(I9150000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x80\\xfb\\xbd@'\np4550\ntp4551\nRp4552\ng4424\nF7152.0\ntp4553\na(I9160000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8*\\xbe@'\np4554\ntp4555\nRp4556\ng4424\nF11328.0\ntp4557\na(I9170000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5M\\xbe@'\np4558\ntp4559\nRp4560\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8]\\xbe@'\np4561\ntp4562\nRp4563\nF5216.0\ntp4564\na(I9180000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85C\\xbe@'\np4565\ntp4566\nRp4567\ng4563\nF6822.0\ntp4568\na(I9190000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fZ\\xbe@'\np4569\ntp4570\nRp4571\ng4563\nF7920.0\ntp4572\na(I9200000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14[\\xbe@'\np4573\ntp4574\nRp4575\ng4563\nF8002.0\ntp4576\na(I9210000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa\\x86\\xbe@'\np4577\ntp4578\nRp4579\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x91\\xbe@'\np4580\ntp4581\nRp4582\nF9850.0\ntp4583\na(I9220000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x7f\\xbe@'\np4584\ntp4585\nRp4586\ng4582\nF9356.0\ntp4587\na(I9230000\ng1\n(g5\nS'ffff\\xe6\\x90\\xbe@'\np4588\ntp4589\nRp4590\ng4582\nF11346.0\ntp4591\na(I9240000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xa5\\xbe@'\np4592\ntp4593\nRp4594\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xa5\\xbe@'\np4595\ntp4596\nRp4597\nF8832.0\ntp4598\na(I9250000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xd7\\xbe@'\np4599\ntp4600\nRp4601\ng1\n(g5\nS'\\xf6(\\\\\\x8fB\\xeb\\xbe@'\np4602\ntp4603\nRp4604\nF5760.0\ntp4605\na(I9260000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x90\\xbe@'\np4606\ntp4607\nRp4608\ng4604\nF4020.0\ntp4609\na(I9270000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xa5\\xbe@'\np4610\ntp4611\nRp4612\ng4604\nF6600.0\ntp4613\na(I9280000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x86\\xbe@'\np4614\ntp4615\nRp4616\ng4604\nF6444.0\ntp4617\na(I9290000\ng1\n(g5\nS'fffff\\x93\\xbe@'\np4618\ntp4619\nRp4620\ng4604\nF7942.0\ntp4621\na(I9300000\ng1\n(g5\nS'q=\\n\\xd7#\\xd4\\xbe@'\np4622\ntp4623\nRp4624\ng4604\nF8208.0\ntp4625\na(I9310000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05\\xf3\\xbe@'\np4626\ntp4627\nRp4628\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05\\xf3\\xbe@'\np4629\ntp4630\nRp4631\nF6384.0\ntp4632\na(I9320000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xeb\\xbe@'\np4633\ntp4634\nRp4635\ng4631\nF9266.0\ntp4636\na(I9330000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xc9\\xbe@'\np4637\ntp4638\nRp4639\ng4631\nF2832.0\ntp4640\na(I9340000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x9a\\xbe@'\np4641\ntp4642\nRp4643\ng4631\nF5310.0\ntp4644\na(I9350000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xf3\\xbe@'\np4645\ntp4646\nRp4647\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xf3\\xbe@'\np4648\ntp4649\nRp4650\nF6330.0\ntp4651\na(I9360000\ng1\n(g5\nS'33333\\xc4\\xbe@'\np4652\ntp4653\nRp4654\ng4650\nF5922.0\ntp4655\na(I9370000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xf4\\xbe@'\np4656\ntp4657\nRp4658\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xf4\\xbe@'\np4659\ntp4660\nRp4661\nF9090.0\ntp4662\na(I9380000\ng1\n(g5\nS'ffff\\xe6\\xf3\\xbe@'\np4663\ntp4664\nRp4665\ng4661\nF7380.0\ntp4666\na(I9390000\ng1\n(g5\nS'=\\n\\xd7\\xa3p/\\xbf@'\np4667\ntp4668\nRp4669\ng1\n(g5\nS'=\\n\\xd7\\xa3p/\\xbf@'\np4670\ntp4671\nRp4672\nF7314.0\ntp4673\na(I9400000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdcD\\xbf@'\np4674\ntp4675\nRp4676\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdcD\\xbf@'\np4677\ntp4678\nRp4679\nF7260.0\ntp4680\na(I9410000\ng1\n(g5\nS'3333\\xb3#\\xbf@'\np4681\ntp4682\nRp4683\ng1\n(g5\nS'{\\x14\\xaeG\\xe1[\\xbf@'\np4684\ntp4685\nRp4686\nF7820.0\ntp4687\na(I9420000\ng1\n(g5\nS'3333\\xb3#\\xbf@'\np4688\ntp4689\nRp4690\ng4686\nF7820.0\ntp4691\na(I9430000\ng1\n(g5\nS'=\\n\\xd7\\xa3pP\\xbf@'\np4692\ntp4693\nRp4694\ng4686\nF12060.0\ntp4695\na(I9440000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x97\\xbf@'\np4696\ntp4697\nRp4698\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x97\\xbf@'\np4699\ntp4700\nRp4701\nF13304.0\ntp4702\na(I9450000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccL\\xd3\\xbf@'\np4703\ntp4704\nRp4705\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccL\\xd3\\xbf@'\np4706\ntp4707\nRp4708\nF13460.0\ntp4709\na(I9460000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x80\\xfa\\xbf@'\np4710\ntp4711\nRp4712\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x80\\xfa\\xbf@'\np4713\ntp4714\nRp4715\nF9200.0\ntp4716\na(I9470000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa\\x0c\\xc0@'\np4717\ntp4718\nRp4719\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa\\x0c\\xc0@'\np4720\ntp4721\nRp4722\nF11088.0\ntp4723\na(I9480000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\r\\xc0@'\np4724\ntp4725\nRp4726\ng1\n(g5\nS'ffff\\xa6\\x10\\xc0@'\np4727\ntp4728\nRp4729\nF5954.0\ntp4730\na(I9490000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xe6\\xbf@'\np4731\ntp4732\nRp4733\ng4729\nF5828.0\ntp4734\na(I9500000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xfd\\xbf@'\np4735\ntp4736\nRp4737\ng4729\nF4156.0\ntp4738\na(I9510000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\xf0\\xbf@'\np4739\ntp4740\nRp4741\ng4729\nF8518.0\ntp4742\na(I9520000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xfe\\xbf@'\np4743\ntp4744\nRp4745\ng4729\nF7488.0\ntp4746\na(I9530000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xfe\\xbf@'\np4747\ntp4748\nRp4749\ng4729\nF7488.0\ntp4750\na(I9540000\ng1\n(g5\nS'H\\xe1z\\x14\\xae;\\xc0@'\np4751\ntp4752\nRp4753\ng1\n(g5\nS'H\\xe1z\\x14\\xae;\\xc0@'\np4754\ntp4755\nRp4756\nF6096.0\ntp4757\na(I9550000\ng1\n(g5\nS'\\xaeG\\xe1z\\xd48\\xc0@'\np4758\ntp4759\nRp4760\ng4756\nF7188.0\ntp4761\na(I9560000\ng1\n(g5\nS'\\xecQ\\xb8\\x1eEd\\xc0@'\np4762\ntp4763\nRp4764\ng1\n(g5\nS'\\xecQ\\xb8\\x1eEd\\xc0@'\np4765\ntp4766\nRp4767\nF16392.0\ntp4768\na(I9570000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99s\\xc0@'\np4769\ntp4770\nRp4771\ng1\n(g5\nS'\\x1f\\x85\\xebQxt\\xc0@'\np4772\ntp4773\nRp4774\nF7224.0\ntp4775\na(I9580000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa\\x91\\xbf@'\np4776\ntp4777\nRp4778\ng4774\nF352.0\ntp4779\na(I9590000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xe9\\xbd@'\np4780\ntp4781\nRp4782\ng4774\nF440.0\ntp4783\na(I9600000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zn\\xbd@'\np4784\ntp4785\nRp4786\ng4774\nF852.0\ntp4787\na(I9610000\ng1\n(g5\nS')\\\\\\x8f\\xc2u\\xf2\\xbc@'\np4788\ntp4789\nRp4790\ng4774\nF4542.0\ntp4791\na(I9620000\ng1\n(g5\nS'\\xd7\\xa3p=\\x8a\\xaf\\xbc@'\np4792\ntp4793\nRp4794\ng4774\nF4320.0\ntp4795\na(I9630000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0}\\xbc@'\np4796\ntp4797\nRp4798\ng4774\nF6028.0\ntp4799\na(I9640000\ng1\n(g5\nS'ffff\\xe6x\\xbc@'\np4800\ntp4801\nRp4802\ng4774\nF8916.0\ntp4803\na(I9650000\ng1\n(g5\nS')\\\\\\x8f\\xc2uu\\xbc@'\np4804\ntp4805\nRp4806\ng4774\nF8420.0\ntp4807\na(I9660000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebf\\xbc@'\np4808\ntp4809\nRp4810\ng4774\nF5582.0\ntp4811\na(I9670000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa\\xde\\xbb@'\np4812\ntp4813\nRp4814\ng4774\nF6720.0\ntp4815\na(I9680000\ng1\n(g5\nS'fffff\\xe8\\xbb@'\np4816\ntp4817\nRp4818\ng4774\nF5582.0\ntp4819\na(I9690000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xb8\\xbb@'\np4820\ntp4821\nRp4822\ng4774\nF7476.0\ntp4823\na(I9700000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94r\\xbb@'\np4824\ntp4825\nRp4826\ng4774\nF5480.0\ntp4827\na(I9710000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14g\\xbb@'\np4828\ntp4829\nRp4830\ng4774\nF4668.0\ntp4831\na(I9720000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x91\\xbb@'\np4832\ntp4833\nRp4834\ng4774\nF11430.0\ntp4835\na(I9730000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5K\\xbb@'\np4836\ntp4837\nRp4838\ng4774\nF5216.0\ntp4839\na(I9740000\ng1\n(g5\nS'\\xf6(\\\\\\x8fB\\x0e\\xbb@'\np4840\ntp4841\nRp4842\ng4774\nF3964.0\ntp4843\na(I9750000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8\\x9e\\xba@'\np4844\ntp4845\nRp4846\ng4774\nF3420.0\ntp4847\na(I9760000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x90\\xba@'\np4848\ntp4849\nRp4850\ng4774\nF6660.0\ntp4851\na(I9770000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5L\\xba@'\np4852\ntp4853\nRp4854\ng4774\nF7080.0\ntp4855\na(I9780000\ng1\n(g5\nS'R\\xb8\\x1e\\x85k\\xf0\\xb9@'\np4856\ntp4857\nRp4858\ng4774\nF4740.0\ntp4859\na(I9790000\ng1\n(g5\nS'ffff\\xe6\\xe1\\xb9@'\np4860\ntp4861\nRp4862\ng4774\nF7380.0\ntp4863\na(I9800000\ng1\n(g5\nS'ffff\\xe6\\x15\\xba@'\np4864\ntp4865\nRp4866\ng4774\nF9130.0\ntp4867\na(I9810000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccL\\xa2\\xba@'\np4868\ntp4869\nRp4870\ng4774\nF18900.0\ntp4871\na(I9820000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x85\\xba@'\np4872\ntp4873\nRp4874\ng4774\nF4800.0\ntp4875\na(I9830000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f\\x84\\xba@'\np4876\ntp4877\nRp4878\ng4774\nF6478.0\ntp4879\na(I9840000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f\\x99\\xba@'\np4880\ntp4881\nRp4882\ng4774\nF5896.0\ntp4883\na(I9850000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xfa\\xb9@'\np4884\ntp4885\nRp4886\ng4774\nF3750.0\ntp4887\na(I9860000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x14\\xba@'\np4888\ntp4889\nRp4890\ng4774\nF9300.0\ntp4891\na(I9870000\ng1\n(g5\nS'ffff\\xe6.\\xba@'\np4892\ntp4893\nRp4894\ng4774\nF8436.0\ntp4895\na(I9880000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa\\x1b\\xba@'\np4896\ntp4897\nRp4898\ng4774\nF5922.0\ntp4899\na(I9890000\ng1\n(g5\nS'\\xd7\\xa3p=\\x8a*\\xba@'\np4900\ntp4901\nRp4902\ng4774\nF2776.0\ntp4903\na(I9900000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xed\\xb9@'\np4904\ntp4905\nRp4906\ng4774\nF6300.0\ntp4907\na(I9910000\ng1\n(g5\nS'\\xd7\\xa3p=\\x8a\\xf4\\xb9@'\np4908\ntp4909\nRp4910\ng4774\nF10430.0\ntp4911\na(I9920000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x04\\xba@'\np4912\ntp4913\nRp4914\ng4774\nF10700.0\ntp4915\na(I9930000\ng1\n(g5\nS'33333\\xd6\\xb9@'\np4916\ntp4917\nRp4918\ng4774\nF6720.0\ntp4919\na(I9935208\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8\\xf6\\xb9@'\np4920\ntp4921\nRp4922\ng4774\nF10560.0\ntp4923\na.(lp0\nF528.0\naF352.0\naF396.0\naF220.0\naF264.0\naF396.0\naF88.0\naF396.0\naF352.0\naF308.0\naF572.0\naF88.0\naF264.0\naF220.0\naF44.0\naF440.0\naF484.0\naF308.0\naF220.0\naF616.0\naF440.0\naF264.0\naF176.0\naF352.0\naF220.0\naF352.0\naF396.0\naF132.0\naF220.0\naF132.0\naF484.0\naF572.0\naF220.0\naF616.0\naF176.0\naF264.0\naF660.0\naF484.0\naF308.0\naF264.0\naF176.0\naF660.0\naF264.0\naF396.0\naF396.0\naF352.0\naF484.0\naF220.0\naF264.0\naF132.0\naF756.0\naF220.0\naF396.0\naF528.0\naF220.0\naF220.0\naF396.0\naF308.0\naF352.0\naF308.0\naF396.0\naF264.0\naF528.0\naF264.0\naF308.0\naF440.0\naF660.0\naF352.0\naF264.0\naF484.0\naF308.0\naF176.0\naF352.0\naF352.0\naF900.0\naF176.0\naF528.0\naF440.0\naF708.0\naF352.0\naF176.0\naF308.0\naF220.0\naF308.0\naF484.0\naF220.0\naF484.0\naF440.0\naF176.0\naF264.0\naF484.0\naF308.0\naF132.0\naF264.0\naF440.0\naF264.0\naF308.0\naF220.0\naF352.0\naF264.0\naF572.0\naF484.0\naF132.0\naF308.0\naF264.0\naF308.0\naF220.0\naF220.0\naF264.0\naF132.0\naF440.0\naF220.0\naF220.0\naF352.0\naF396.0\naF708.0\naF572.0\naF176.0\naF352.0\naF440.0\naF308.0\naF352.0\naF308.0\naF484.0\naF528.0\naF396.0\naF220.0\naF528.0\naF352.0\naF484.0\naF264.0\naF528.0\naF660.0\naF220.0\naF264.0\naF440.0\naF572.0\naF132.0\naF396.0\naF308.0\naF220.0\naF484.0\naF308.0\naF396.0\naF352.0\naF660.0\naF528.0\naF308.0\naF396.0\naF308.0\naF264.0\naF440.0\naF308.0\naF88.0\naF264.0\naF220.0\naF352.0\naF396.0\naF308.0\naF176.0\naF176.0\naF616.0\naF264.0\naF616.0\naF396.0\naF352.0\naF176.0\naF660.0\naF352.0\naF132.0\naF308.0\naF220.0\naF756.0\naF264.0\naF352.0\naF396.0\naF396.0\naF308.0\naF220.0\naF804.0\naF440.0\naF352.0\naF308.0\naF396.0\naF220.0\naF352.0\naF308.0\naF572.0\naF308.0\naF264.0\naF396.0\naF396.0\naF484.0\naF528.0\naF352.0\naF440.0\naF132.0\naF440.0\naF616.0\naF308.0\naF352.0\naF352.0\naF220.0\naF264.0\naF220.0\naF264.0\naF352.0\naF396.0\naF616.0\naF176.0\naF220.0\naF176.0\naF308.0\naF352.0\naF44.0\naF308.0\naF352.0\naF440.0\naF132.0\naF308.0\naF396.0\naF484.0\naF220.0\naF132.0\naF220.0\naF132.0\naF660.0\naF220.0\naF440.0\naF440.0\naF352.0\naF572.0\naF484.0\naF572.0\naF572.0\naF176.0\naF616.0\naF528.0\naF308.0\naF308.0\naF176.0\naF220.0\naF572.0\naF264.0\naF220.0\naF572.0\naF352.0\naF176.0\naF132.0\naF484.0\naF352.0\naF440.0\naF264.0\naF308.0\naF484.0\naF176.0\naF352.0\naF660.0\naF616.0\naF616.0\naF220.0\naF484.0\naF660.0\naF132.0\naF440.0\naF176.0\naF484.0\naF484.0\naF220.0\naF352.0\naF484.0\naF220.0\naF308.0\naF264.0\naF308.0\naF528.0\naF572.0\naF264.0\naF484.0\naF308.0\naF396.0\naF484.0\naF308.0\naF440.0\naF352.0\naF484.0\naF352.0\naF352.0\naF396.0\naF440.0\naF264.0\naF88.0\naF220.0\naF308.0\naF572.0\naF440.0\naF572.0\naF132.0\naF220.0\naF264.0\naF352.0\naF572.0\naF308.0\naF528.0\naF484.0\naF308.0\naF572.0\naF352.0\naF616.0\naF176.0\naF352.0\naF176.0\naF220.0\naF440.0\naF660.0\naF440.0\naF132.0\naF440.0\naF352.0\naF264.0\naF352.0\naF528.0\naF756.0\naF616.0\naF308.0\naF176.0\naF660.0\naF616.0\naF264.0\naF220.0\naF132.0\naF264.0\naF132.0\naF308.0\naF264.0\naF804.0\naF88.0\naF660.0\naF352.0\naF132.0\naF308.0\naF484.0\naF264.0\naF660.0\naF396.0\naF352.0\naF660.0\naF132.0\naF264.0\naF440.0\naF352.0\naF176.0\naF352.0\naF176.0\naF484.0\naF396.0\naF484.0\naF176.0\naF528.0\naF352.0\naF396.0\naF396.0\naF220.0\naF264.0\naF660.0\naF308.0\naF440.0\naF264.0\naF220.0\naF484.0\naF660.0\naF396.0\naF220.0\naF352.0\naF352.0\naF440.0\naF264.0\naF660.0\naF352.0\naF484.0\naF616.0\naF440.0\naF220.0\naF440.0\naF396.0\naF756.0\naF352.0\naF440.0\naF484.0\naF440.0\naF308.0\naF308.0\naF352.0\naF264.0\naF264.0\naF176.0\naF88.0\naF308.0\naF440.0\naF176.0\naF616.0\naF264.0\naF352.0\naF396.0\naF264.0\naF572.0\naF484.0\naF132.0\naF176.0\naF220.0\naF264.0\naF352.0\naF484.0\naF528.0\naF308.0\naF264.0\naF88.0\naF352.0\naF572.0\naF132.0\naF264.0\naF132.0\naF176.0\naF220.0\naF396.0\naF132.0\naF264.0\naF176.0\naF804.0\naF528.0\naF572.0\naF220.0\naF352.0\naF176.0\naF528.0\naF528.0\naF308.0\naF88.0\naF396.0\naF440.0\naF396.0\naF440.0\naF352.0\naF396.0\naF264.0\naF352.0\naF352.0\naF440.0\naF88.0\naF352.0\naF484.0\naF308.0\naF396.0\naF440.0\naF264.0\naF264.0\naF572.0\naF308.0\naF396.0\naF440.0\naF264.0\naF220.0\naF308.0\naF264.0\naF132.0\naF308.0\naF308.0\naF264.0\naF220.0\naF220.0\naF220.0\naF440.0\naF484.0\naF220.0\naF264.0\naF484.0\naF616.0\naF352.0\naF176.0\naF756.0\naF264.0\naF440.0\naF528.0\naF264.0\naF264.0\naF396.0\naF308.0\naF220.0\naF132.0\naF132.0\naF616.0\naF528.0\naF220.0\naF528.0\naF176.0\naF44.0\naF264.0\naF440.0\naF352.0\naF220.0\naF396.0\naF352.0\naF572.0\naF352.0\naF528.0\naF396.0\naF264.0\naF176.0\naF220.0\naF264.0\naF396.0\naF396.0\naF440.0\naF308.0\naF220.0\naF528.0\naF88.0\naF132.0\naF756.0\naF352.0\naF264.0\naF440.0\naF220.0\naF264.0\naF352.0\naF396.0\naF264.0\naF660.0\naF220.0\naF572.0\naF308.0\naF396.0\naF132.0\naF396.0\naF528.0\naF132.0\naF440.0\naF352.0\naF176.0\naF528.0\naF484.0\naF176.0\naF308.0\naF352.0\naF176.0\naF484.0\naF440.0\naF440.0\naF660.0\naF308.0\naF176.0\naF176.0\naF264.0\naF572.0\naF484.0\naF572.0\naF176.0\naF616.0\naF264.0\naF440.0\naF308.0\naF484.0\naF176.0\naF616.0\naF396.0\naF484.0\naF264.0\naF308.0\naF396.0\naF264.0\naF220.0\naF308.0\naF660.0\naF660.0\naF308.0\naF528.0\naF264.0\naF440.0\naF308.0\naF264.0\naF660.0\naF220.0\naF176.0\naF352.0\naF264.0\naF528.0\naF220.0\naF264.0\naF176.0\naF220.0\naF396.0\naF132.0\naF220.0\naF220.0\naF528.0\naF220.0\naF220.0\naF264.0\naF264.0\naF572.0\naF708.0\naF308.0\naF660.0\naF528.0\naF264.0\naF484.0\naF308.0\naF616.0\naF484.0\naF308.0\naF352.0\naF484.0\naF264.0\naF352.0\naF220.0\naF132.0\naF484.0\naF264.0\naF396.0\naF396.0\naF176.0\naF616.0\naF396.0\naF308.0\naF176.0\naF396.0\naF176.0\naF220.0\naF132.0\naF88.0\naF44.0\naF220.0\naF308.0\naF352.0\naF484.0\naF352.0\naF308.0\naF88.0\naF176.0\naF396.0\naF264.0\naF220.0\naF264.0\naF176.0\naF396.0\naF176.0\naF176.0\naF352.0\naF804.0\naF88.0\naF440.0\naF660.0\naF528.0\naF660.0\naF616.0\naF176.0\naF660.0\naF528.0\naF88.0\naF176.0\naF572.0\naF0.0\naF440.0\naF264.0\naF484.0\naF176.0\naF616.0\naF176.0\naF660.0\naF176.0\naF616.0\naF264.0\naF572.0\naF396.0\naF352.0\naF88.0\naF220.0\naF484.0\naF88.0\naF132.0\naF176.0\naF308.0\naF616.0\naF88.0\naF484.0\naF308.0\naF616.0\naF616.0\naF660.0\naF352.0\naF660.0\naF528.0\naF572.0\naF572.0\naF572.0\naF396.0\naF132.0\naF264.0\naF308.0\naF308.0\naF220.0\naF352.0\naF308.0\naF308.0\naF176.0\naF308.0\naF440.0\naF132.0\naF484.0\naF308.0\naF132.0\naF484.0\naF132.0\naF220.0\naF264.0\naF176.0\naF396.0\naF264.0\naF352.0\naF176.0\naF660.0\naF440.0\naF88.0\naF308.0\naF176.0\naF132.0\naF264.0\naF132.0\naF616.0\naF660.0\naF756.0\naF264.0\naF308.0\naF484.0\naF220.0\naF132.0\naF352.0\naF484.0\naF132.0\naF308.0\naF528.0\naF264.0\naF176.0\naF528.0\naF220.0\naF308.0\naF440.0\naF44.0\naF396.0\naF220.0\naF220.0\naF352.0\naF396.0\naF132.0\naF176.0\naF528.0\naF352.0\naF88.0\naF132.0\naF220.0\naF264.0\naF132.0\naF572.0\naF308.0\naF440.0\naF308.0\naF264.0\naF220.0\naF528.0\naF440.0\naF264.0\naF440.0\naF660.0\naF88.0\naF352.0\naF616.0\naF176.0\naF220.0\naF308.0\naF220.0\naF616.0\naF88.0\naF484.0\naF264.0\naF132.0\naF440.0\naF220.0\naF396.0\naF352.0\naF528.0\naF484.0\naF660.0\naF308.0\naF440.0\naF660.0\naF352.0\naF220.0\naF528.0\naF528.0\naF308.0\naF616.0\naF308.0\naF264.0\naF572.0\naF440.0\naF528.0\naF264.0\naF88.0\naF528.0\naF308.0\naF528.0\naF176.0\naF352.0\naF528.0\naF484.0\naF440.0\naF176.0\naF176.0\naF528.0\naF220.0\naF220.0\naF616.0\naF352.0\naF308.0\naF176.0\naF220.0\naF220.0\naF176.0\naF264.0\naF264.0\naF440.0\naF264.0\naF264.0\naF308.0\naF220.0\naF176.0\naF220.0\naF264.0\naF220.0\naF88.0\naF396.0\naF264.0\naF484.0\naF88.0\naF176.0\naF440.0\naF264.0\naF440.0\naF176.0\naF44.0\naF220.0\naF132.0\naF396.0\naF220.0\naF572.0\naF308.0\naF440.0\naF572.0\naF440.0\naF396.0\naF352.0\naF440.0\naF220.0\naF264.0\naF396.0\naF264.0\naF220.0\naF176.0\naF352.0\naF484.0\naF660.0\naF440.0\naF176.0\naF396.0\naF132.0\naF220.0\naF132.0\naF660.0\naF352.0\naF352.0\naF484.0\naF264.0\naF440.0\naF176.0\naF308.0\naF528.0\naF396.0\naF484.0\naF616.0\naF220.0\naF396.0\naF132.0\naF308.0\naF396.0\naF440.0\naF220.0\naF220.0\naF132.0\naF484.0\naF132.0\naF352.0\naF440.0\naF396.0\naF708.0\naF484.0\naF396.0\naF352.0\naF176.0\naF264.0\naF352.0\naF88.0\naF88.0\naF308.0\naF484.0\naF264.0\naF220.0\naF132.0\naF220.0\naF352.0\naF352.0\naF660.0\naF660.0\naF352.0\naF352.0\naF176.0\naF572.0\naF308.0\naF88.0\naF220.0\naF264.0\naF396.0\naF396.0\naF396.0\naF176.0\naF264.0\naF572.0\naF484.0\naF484.0\naF396.0\naF308.0\naF176.0\naF220.0\naF176.0\naF352.0\naF528.0\naF484.0\naF132.0\naF132.0\naF308.0\naF352.0\naF440.0\naF572.0\naF308.0\naF88.0\naF220.0\naF176.0\naF484.0\naF440.0\naF132.0\naF132.0\naF396.0\naF440.0\naF440.0\naF264.0\naF132.0\naF220.0\naF264.0\naF220.0\naF264.0\naF88.0\naF440.0\naF264.0\naF308.0\naF176.0\naF572.0\naF176.0\naF352.0\naF352.0\naF264.0\naF396.0\naF440.0\naF660.0\naF660.0\naF264.0\naF264.0\naF396.0\naF132.0\naF308.0\naF352.0\naF132.0\naF484.0\naF352.0\naF308.0\naF308.0\naF352.0\naF572.0\naF132.0\naF352.0\naF88.0\naF308.0\naF440.0\naF660.0\naF572.0\naF616.0\naF616.0\naF352.0\naF308.0\naF396.0\naF660.0\naF660.0\naF660.0\naF264.0\naF616.0\naF352.0\naF264.0\naF176.0\naF176.0\naF132.0\naF352.0\naF484.0\naF528.0\naF44.0\naF220.0\naF220.0\naF132.0\naF440.0\naF484.0\naF264.0\naF176.0\naF308.0\naF528.0\naF352.0\naF308.0\naF176.0\naF220.0\naF352.0\naF528.0\naF352.0\naF308.0\naF264.0\naF396.0\naF528.0\naF220.0\naF308.0\naF44.0\naF660.0\naF528.0\naF396.0\naF176.0\naF572.0\naF484.0\naF132.0\naF220.0\naF308.0\naF484.0\naF352.0\naF176.0\naF176.0\naF176.0\naF220.0\naF176.0\naF440.0\naF220.0\naF308.0\naF352.0\naF264.0\naF352.0\naF484.0\naF440.0\naF176.0\naF396.0\naF660.0\naF176.0\naF396.0\naF220.0\naF264.0\naF264.0\naF220.0\naF572.0\naF484.0\naF220.0\naF132.0\naF308.0\naF264.0\naF396.0\naF220.0\naF572.0\naF132.0\naF352.0\naF308.0\naF220.0\naF440.0\naF352.0\naF264.0\naF176.0\naF308.0\naF528.0\naF220.0\naF308.0\naF176.0\naF440.0\naF220.0\naF264.0\naF308.0\naF220.0\naF176.0\naF176.0\naF264.0\naF264.0\naF660.0\naF264.0\naF352.0\naF352.0\naF484.0\naF308.0\naF176.0\naF176.0\naF440.0\naF220.0\naF660.0\naF308.0\naF220.0\naF396.0\naF396.0\naF660.0\naF396.0\naF176.0\naF352.0\naF132.0\naF396.0\naF132.0\naF220.0\naF660.0\naF220.0\naF88.0\naF220.0\naF352.0\naF396.0\naF352.0\naF352.0\naF264.0\naF264.0\naF88.0\naF220.0\naF308.0\naF264.0\naF220.0\naF352.0\naF572.0\naF308.0\naF484.0\naF132.0\naF88.0\naF396.0\naF176.0\naF220.0\naF176.0\naF528.0\naF220.0\naF352.0\naF132.0\naF176.0\naF572.0\naF176.0\naF396.0\naF484.0\naF308.0\naF660.0\naF132.0\naF220.0\naF352.0\naF132.0\naF396.0\naF396.0\naF308.0\naF440.0\naF352.0\naF396.0\naF176.0\naF396.0\naF308.0\naF220.0\naF352.0\naF220.0\naF308.0\naF308.0\naF484.0\naF528.0\naF132.0\naF660.0\naF176.0\naF440.0\naF132.0\naF308.0\naF484.0\naF176.0\naF264.0\naF132.0\naF220.0\naF308.0\naF396.0\naF220.0\naF220.0\naF88.0\naF308.0\naF616.0\naF528.0\naF44.0\naF220.0\naF264.0\naF176.0\naF132.0\naF176.0\naF440.0\naF308.0\naF176.0\naF88.0\naF572.0\naF220.0\naF220.0\naF484.0\naF572.0\naF308.0\naF352.0\naF88.0\naF308.0\naF220.0\naF484.0\naF572.0\naF220.0\naF88.0\naF440.0\naF264.0\naF396.0\naF88.0\naF440.0\naF308.0\naF352.0\naF132.0\naF396.0\naF264.0\naF132.0\naF352.0\naF88.0\naF176.0\naF572.0\naF396.0\naF572.0\naF176.0\naF220.0\naF352.0\naF132.0\naF88.0\naF88.0\naF176.0\naF220.0\naF88.0\naF308.0\naF308.0\naF220.0\naF88.0\naF132.0\naF440.0\naF176.0\naF440.0\naF352.0\naF264.0\naF220.0\naF220.0\naF572.0\naF308.0\naF396.0\naF396.0\naF88.0\naF88.0\naF132.0\naF484.0\naF440.0\naF220.0\naF88.0\naF264.0\naF572.0\naF176.0\naF396.0\naF396.0\naF396.0\naF440.0\naF88.0\naF352.0\naF396.0\naF88.0\naF396.0\naF308.0\naF396.0\naF220.0\naF308.0\naF528.0\naF308.0\naF88.0\naF176.0\naF88.0\naF308.0\naF176.0\naF528.0\naF352.0\naF220.0\naF484.0\naF352.0\naF132.0\naF484.0\naF484.0\naF132.0\naF440.0\naF396.0\naF176.0\naF352.0\naF264.0\naF660.0\naF352.0\naF484.0\naF264.0\naF264.0\naF176.0\naF220.0\naF308.0\naF176.0\naF220.0\naF352.0\naF176.0\naF352.0\naF352.0\naF308.0\naF264.0\naF308.0\naF132.0\naF176.0\naF440.0\naF484.0\naF440.0\naF264.0\naF308.0\naF352.0\naF176.0\naF352.0\naF396.0\naF352.0\naF220.0\naF132.0\naF308.0\naF176.0\naF132.0\naF220.0\naF264.0\naF660.0\naF220.0\naF396.0\naF352.0\naF616.0\naF484.0\naF440.0\naF264.0\naF352.0\naF484.0\naF132.0\naF528.0\naF220.0\naF440.0\naF88.0\naF132.0\naF440.0\naF264.0\naF396.0\naF396.0\naF88.0\naF88.0\naF176.0\naF176.0\naF264.0\naF88.0\naF176.0\naF132.0\naF220.0\naF484.0\naF176.0\naF264.0\naF220.0\naF176.0\naF308.0\naF352.0\naF308.0\naF176.0\naF176.0\naF220.0\naF308.0\naF308.0\naF132.0\naF308.0\naF264.0\naF220.0\naF264.0\naF220.0\naF132.0\naF176.0\naF176.0\naF264.0\naF352.0\naF396.0\naF352.0\naF132.0\naF264.0\naF440.0\naF396.0\naF352.0\naF352.0\naF264.0\naF176.0\naF132.0\naF352.0\naF660.0\naF88.0\naF308.0\naF176.0\naF264.0\naF484.0\naF352.0\naF352.0\naF440.0\naF660.0\naF308.0\naF220.0\naF308.0\naF264.0\naF572.0\naF396.0\naF176.0\naF132.0\naF308.0\naF220.0\naF352.0\naF264.0\naF220.0\naF220.0\naF484.0\naF308.0\naF176.0\naF132.0\naF352.0\naF264.0\naF396.0\naF264.0\naF220.0\naF352.0\naF132.0\naF220.0\naF220.0\naF440.0\naF264.0\naF132.0\naF220.0\naF176.0\naF220.0\naF132.0\naF396.0\naF132.0\naF308.0\naF352.0\naF176.0\naF484.0\naF352.0\naF308.0\naF220.0\naF528.0\naF528.0\naF352.0\naF616.0\naF220.0\naF264.0\naF264.0\naF484.0\naF176.0\naF88.0\naF88.0\naF308.0\naF132.0\naF440.0\naF176.0\naF88.0\naF308.0\naF528.0\naF396.0\naF264.0\naF88.0\naF352.0\naF176.0\naF44.0\naF176.0\naF660.0\naF308.0\naF220.0\naF264.0\naF176.0\naF176.0\naF176.0\naF220.0\naF308.0\naF396.0\naF308.0\naF308.0\naF176.0\naF220.0\naF308.0\naF352.0\naF264.0\naF308.0\naF88.0\naF176.0\naF176.0\naF132.0\naF176.0\naF660.0\naF308.0\naF264.0\naF396.0\naF308.0\naF264.0\naF220.0\naF308.0\naF88.0\naF132.0\naF88.0\naF308.0\naF352.0\naF220.0\naF396.0\naF44.0\naF220.0\naF220.0\naF220.0\naF396.0\naF352.0\naF396.0\naF88.0\naF264.0\naF484.0\naF88.0\naF132.0\naF176.0\naF88.0\naF264.0\naF176.0\naF352.0\naF396.0\naF308.0\naF264.0\naF220.0\naF308.0\naF484.0\naF352.0\naF176.0\naF528.0\naF132.0\naF176.0\naF308.0\naF484.0\naF396.0\naF176.0\naF132.0\naF396.0\naF572.0\naF308.0\naF440.0\naF132.0\naF220.0\naF484.0\naF484.0\naF176.0\naF132.0\naF352.0\naF132.0\naF264.0\naF308.0\naF264.0\naF264.0\naF396.0\naF440.0\naF308.0\naF264.0\naF308.0\naF352.0\naF264.0\naF0.0\naF616.0\naF308.0\naF176.0\naF352.0\naF220.0\naF352.0\naF528.0\naF528.0\naF132.0\naF440.0\naF264.0\naF132.0\naF440.0\naF176.0\naF176.0\naF264.0\naF220.0\naF396.0\naF264.0\naF132.0\naF176.0\naF220.0\naF308.0\naF44.0\naF352.0\naF220.0\naF176.0\naF396.0\naF132.0\naF132.0\naF308.0\naF0.0\naF44.0\naF132.0\naF176.0\naF0.0\naF176.0\naF88.0\naF88.0\naF44.0\naF220.0\naF176.0\naF176.0\naF528.0\naF176.0\naF132.0\naF264.0\naF396.0\naF88.0\naF528.0\naF132.0\naF220.0\naF264.0\naF528.0\naF132.0\naF572.0\naF308.0\naF484.0\naF616.0\naF308.0\naF264.0\naF308.0\naF308.0\naF176.0\naF176.0\naF440.0\naF528.0\naF308.0\naF176.0\naF484.0\naF132.0\naF44.0\naF88.0\naF132.0\naF396.0\naF264.0\naF528.0\naF484.0\naF176.0\naF484.0\naF440.0\naF176.0\naF484.0\naF308.0\naF396.0\naF220.0\naF264.0\naF264.0\naF264.0\naF264.0\naF132.0\naF308.0\naF176.0\naF440.0\naF572.0\naF176.0\naF88.0\naF132.0\naF308.0\naF352.0\naF484.0\naF132.0\naF396.0\naF132.0\naF176.0\naF176.0\naF616.0\naF308.0\naF132.0\naF264.0\naF220.0\naF308.0\naF308.0\naF264.0\naF308.0\naF264.0\naF396.0\naF220.0\naF220.0\naF176.0\naF352.0\naF264.0\naF264.0\naF176.0\naF616.0\naF528.0\naF264.0\naF220.0\naF396.0\naF352.0\naF176.0\naF0.0\naF220.0\naF484.0\naF220.0\naF176.0\naF132.0\naF440.0\naF308.0\naF176.0\naF396.0\naF440.0\naF352.0\naF572.0\naF440.0\naF176.0\naF308.0\naF352.0\naF484.0\naF352.0\naF396.0\naF660.0\naF528.0\naF132.0\naF132.0\naF132.0\naF132.0\naF572.0\naF572.0\naF484.0\naF220.0\naF132.0\naF220.0\naF132.0\naF220.0\naF220.0\naF308.0\naF396.0\naF176.0\naF484.0\naF308.0\naF440.0\naF616.0\naF616.0\naF308.0\naF440.0\naF88.0\naF572.0\naF396.0\naF660.0\naF396.0\naF484.0\naF660.0\naF352.0\naF352.0\naF528.0\naF264.0\naF852.0\naF264.0\naF528.0\naF352.0\naF396.0\naF440.0\naF528.0\naF264.0\naF308.0\naF572.0\naF132.0\naF308.0\naF308.0\naF484.0\naF528.0\naF572.0\naF264.0\naF308.0\naF44.0\naF132.0\naF264.0\naF572.0\naF352.0\naF264.0\naF220.0\naF616.0\naF220.0\naF440.0\naF352.0\naF396.0\naF528.0\naF88.0\naF308.0\naF352.0\naF484.0\naF352.0\naF308.0\naF352.0\naF440.0\naF220.0\naF396.0\naF264.0\naF264.0\naF88.0\naF132.0\naF396.0\naF308.0\naF616.0\naF616.0\naF616.0\naF88.0\naF708.0\naF352.0\naF132.0\naF616.0\naF440.0\naF616.0\naF660.0\naF616.0\naF996.0\naF572.0\naF484.0\naF484.0\naF396.0\naF440.0\naF708.0\naF132.0\naF708.0\naF484.0\naF176.0\naF88.0\naF616.0\naF660.0\naF572.0\naF660.0\naF132.0\naF44.0\naF132.0\naF308.0\naF308.0\naF176.0\naF352.0\naF264.0\naF660.0\naF176.0\naF132.0\naF352.0\naF660.0\naF804.0\naF308.0\naF484.0\naF308.0\naF440.0\naF220.0\naF528.0\naF440.0\naF396.0\naF572.0\naF352.0\naF308.0\naF352.0\naF528.0\naF616.0\naF660.0\naF572.0\naF220.0\naF528.0\naF264.0\naF440.0\naF396.0\naF440.0\naF528.0\naF176.0\naF220.0\naF572.0\naF572.0\naF660.0\naF176.0\naF308.0\naF264.0\naF176.0\naF264.0\naF484.0\naF396.0\naF660.0\naF900.0\naF484.0\naF396.0\naF308.0\naF308.0\naF176.0\naF660.0\naF440.0\naF440.0\naF220.0\naF396.0\naF484.0\naF308.0\naF572.0\naF660.0\naF308.0\naF264.0\naF308.0\naF396.0\naF660.0\naF352.0\naF308.0\naF396.0\naF220.0\naF88.0\naF396.0\naF660.0\naF308.0\naF484.0\naF352.0\naF660.0\naF528.0\naF708.0\naF572.0\naF484.0\naF44.0\naF660.0\naF660.0\naF660.0\naF396.0\naF396.0\naF708.0\naF264.0\naF308.0\naF660.0\naF660.0\naF660.0\naF264.0\naF616.0\naF660.0\naF756.0\naF220.0\naF132.0\naF220.0\naF176.0\naF88.0\naF88.0\naF352.0\naF176.0\naF264.0\naF132.0\naF264.0\naF132.0\naF132.0\naF308.0\naF132.0\naF176.0\naF396.0\naF352.0\naF220.0\naF132.0\naF88.0\naF396.0\naF88.0\naF572.0\naF264.0\naF308.0\naF264.0\naF440.0\naF132.0\naF264.0\naF264.0\naF528.0\naF264.0\naF308.0\naF572.0\naF264.0\naF396.0\naF352.0\naF572.0\naF264.0\naF616.0\naF572.0\naF528.0\naF572.0\naF440.0\naF308.0\naF484.0\naF528.0\naF484.0\naF264.0\naF484.0\naF308.0\naF352.0\naF132.0\naF220.0\naF484.0\naF220.0\naF220.0\naF660.0\naF176.0\naF176.0\naF264.0\naF440.0\naF660.0\naF132.0\naF352.0\naF264.0\naF176.0\naF616.0\naF352.0\naF572.0\naF352.0\naF308.0\naF660.0\naF660.0\naF440.0\naF616.0\naF308.0\naF396.0\naF396.0\naF352.0\naF660.0\naF528.0\naF352.0\naF264.0\naF484.0\naF484.0\naF352.0\naF220.0\naF440.0\naF352.0\naF220.0\naF616.0\naF756.0\naF572.0\naF352.0\naF616.0\naF352.0\naF616.0\naF264.0\naF484.0\naF176.0\naF660.0\naF264.0\naF616.0\naF440.0\naF440.0\naF132.0\naF88.0\naF528.0\naF660.0\naF528.0\naF264.0\naF264.0\naF176.0\naF660.0\naF352.0\naF440.0\naF660.0\naF528.0\naF440.0\naF264.0\naF396.0\naF708.0\naF308.0\naF352.0\naF616.0\naF396.0\naF484.0\naF660.0\naF660.0\naF440.0\naF660.0\naF660.0\naF660.0\naF528.0\naF264.0\naF484.0\naF660.0\naF616.0\naF396.0\naF484.0\naF572.0\naF176.0\naF220.0\naF220.0\naF308.0\naF484.0\naF396.0\naF660.0\naF616.0\naF572.0\naF352.0\naF660.0\naF572.0\naF804.0\naF528.0\naF484.0\naF264.0\naF396.0\naF484.0\naF660.0\naF572.0\naF708.0\naF352.0\naF484.0\naF484.0\naF660.0\naF660.0\naF616.0\naF220.0\naF396.0\naF220.0\naF308.0\naF352.0\naF756.0\naF616.0\naF572.0\naF484.0\naF660.0\naF804.0\naF900.0\naF756.0\naF616.0\naF616.0\naF756.0\naF308.0\naF660.0\naF264.0\naF660.0\naF528.0\naF484.0\naF660.0\naF308.0\naF572.0\naF660.0\naF708.0\naF572.0\naF396.0\naF660.0\naF396.0\naF176.0\naF264.0\naF308.0\naF264.0\naF396.0\naF660.0\naF440.0\naF572.0\naF308.0\naF176.0\naF220.0\naF660.0\naF660.0\naF264.0\naF484.0\naF220.0\naF660.0\naF616.0\naF396.0\naF616.0\naF708.0\naF660.0\naF308.0\naF660.0\naF660.0\naF440.0\naF660.0\naF132.0\naF88.0\naF88.0\naF88.0\naF616.0\naF176.0\naF396.0\naF572.0\naF528.0\naF352.0\naF176.0\naF572.0\naF352.0\naF396.0\naF396.0\naF132.0\naF220.0\naF352.0\naF440.0\naF264.0\naF528.0\naF660.0\naF264.0\naF484.0\naF308.0\naF528.0\naF396.0\naF308.0\naF616.0\naF396.0\naF396.0\naF396.0\naF220.0\naF88.0\naF220.0\naF528.0\naF572.0\naF132.0\naF264.0\naF264.0\naF440.0\naF220.0\naF660.0\naF396.0\naF484.0\naF396.0\naF352.0\naF572.0\naF660.0\naF572.0\naF220.0\naF660.0\naF616.0\naF220.0\naF352.0\naF484.0\naF352.0\naF440.0\naF440.0\naF616.0\naF264.0\naF660.0\naF264.0\naF660.0\naF484.0\naF708.0\naF352.0\naF440.0\naF660.0\naF396.0\naF484.0\naF440.0\naF616.0\naF440.0\naF572.0\naF660.0\naF708.0\naF484.0\naF572.0\naF528.0\naF396.0\naF616.0\naF396.0\naF396.0\naF660.0\naF440.0\naF396.0\naF264.0\naF996.0\naF264.0\naF660.0\naF1284.0\naF308.0\naF396.0\naF396.0\naF708.0\naF804.0\naF616.0\naF396.0\naF484.0\naF900.0\naF352.0\naF220.0\naF528.0\naF440.0\naF528.0\naF176.0\naF264.0\naF660.0\naF264.0\naF660.0\naF528.0\naF528.0\naF572.0\naF660.0\naF660.0\naF396.0\naF308.0\naF660.0\naF308.0\naF572.0\naF804.0\naF528.0\naF264.0\naF440.0\naF484.0\naF616.0\naF660.0\naF660.0\naF264.0\naF176.0\naF804.0\naF352.0\naF352.0\naF352.0\naF660.0\naF660.0\naF396.0\naF660.0\naF484.0\naF528.0\naF660.0\naF396.0\naF484.0\naF484.0\naF616.0\naF756.0\naF264.0\naF484.0\naF572.0\naF264.0\naF352.0\naF852.0\naF1140.0\naF804.0\naF660.0\naF660.0\naF660.0\naF708.0\naF440.0\naF660.0\naF1044.0\naF396.0\naF852.0\naF308.0\naF660.0\naF660.0\naF660.0\naF660.0\naF396.0\naF660.0\naF756.0\naF572.0\naF308.0\naF616.0\naF660.0\naF572.0\naF660.0\naF708.0\naF660.0\naF484.0\naF1236.0\naF616.0\naF660.0\naF528.0\naF396.0\naF660.0\naF660.0\naF804.0\naF572.0\naF660.0\naF660.0\naF264.0\naF660.0\naF756.0\naF528.0\naF708.0\naF264.0\naF660.0\naF616.0\naF708.0\naF616.0\naF308.0\naF756.0\naF948.0\naF660.0\naF1092.0\naF572.0\naF440.0\naF660.0\naF660.0\naF176.0\naF660.0\naF352.0\naF528.0\naF528.0\naF484.0\naF708.0\naF852.0\naF484.0\naF264.0\naF852.0\naF440.0\naF396.0\naF264.0\naF572.0\naF660.0\naF948.0\naF756.0\naF660.0\naF484.0\naF396.0\naF352.0\naF660.0\naF660.0\naF528.0\naF264.0\naF948.0\naF616.0\naF660.0\naF528.0\naF572.0\naF900.0\naF616.0\naF616.0\naF660.0\naF756.0\naF616.0\naF660.0\naF572.0\naF660.0\naF660.0\naF616.0\naF572.0\naF1284.0\naF440.0\naF708.0\naF660.0\naF660.0\naF396.0\naF616.0\naF1140.0\naF220.0\naF572.0\naF1092.0\naF528.0\naF616.0\naF660.0\naF572.0\naF660.0\naF352.0\naF1140.0\naF660.0\naF572.0\naF264.0\naF708.0\naF528.0\naF660.0\naF948.0\naF900.0\naF528.0\naF572.0\naF660.0\naF616.0\naF528.0\naF660.0\naF572.0\naF660.0\naF708.0\naF660.0\naF308.0\naF484.0\naF660.0\naF708.0\naF572.0\naF616.0\naF660.0\naF708.0\naF616.0\naF616.0\naF440.0\naF708.0\naF660.0\naF352.0\naF660.0\naF1284.0\naF528.0\naF1092.0\naF528.0\naF804.0\naF900.0\naF616.0\naF660.0\naF264.0\naF220.0\naF756.0\naF616.0\naF616.0\naF660.0\naF660.0\naF660.0\naF616.0\naF660.0\naF804.0\naF1236.0\naF660.0\naF660.0\naF616.0\naF1092.0\naF440.0\naF708.0\naF616.0\naF572.0\naF900.0\naF708.0\naF616.0\naF756.0\naF1332.0\naF616.0\naF264.0\naF804.0\naF616.0\naF616.0\naF264.0\naF708.0\naF804.0\naF660.0\naF616.0\naF900.0\naF1092.0\naF804.0\naF756.0\naF660.0\naF660.0\naF708.0\naF804.0\naF572.0\naF708.0\naF756.0\naF660.0\naF756.0\naF852.0\naF1140.0\naF756.0\naF660.0\naF948.0\naF572.0\naF1284.0\naF756.0\naF396.0\naF756.0\naF948.0\naF660.0\naF660.0\naF660.0\naF852.0\naF708.0\naF852.0\naF572.0\naF756.0\naF176.0\naF660.0\naF660.0\naF1432.0\naF756.0\naF900.0\naF804.0\naF528.0\naF572.0\naF660.0\naF660.0\naF660.0\naF756.0\naF660.0\naF660.0\naF804.0\naF996.0\naF572.0\naF616.0\naF572.0\naF528.0\naF708.0\naF616.0\naF660.0\naF440.0\naF708.0\naF616.0\naF616.0\naF1188.0\naF1380.0\naF484.0\naF572.0\naF660.0\naF660.0\naF756.0\naF660.0\naF804.0\naF708.0\naF852.0\naF616.0\naF572.0\naF660.0\naF572.0\naF948.0\naF660.0\naF852.0\naF484.0\naF996.0\naF616.0\naF440.0\naF756.0\naF1044.0\naF1092.0\naF1044.0\naF756.0\naF1044.0\naF660.0\naF1284.0\naF220.0\naF660.0\naF708.0\naF572.0\naF660.0\naF708.0\naF660.0\naF948.0\naF756.0\naF484.0\naF804.0\naF660.0\naF804.0\naF756.0\naF852.0\naF660.0\naF660.0\naF804.0\naF708.0\naF308.0\naF1332.0\naF396.0\naF948.0\naF660.0\naF660.0\naF484.0\naF660.0\naF1188.0\naF528.0\naF708.0\naF1236.0\naF948.0\naF1140.0\naF948.0\naF660.0\naF660.0\naF484.0\naF948.0\naF660.0\naF900.0\naF1284.0\naF660.0\naF900.0\naF1092.0\naF660.0\naF708.0\naF660.0\naF900.0\naF660.0\naF220.0\naF660.0\naF660.0\naF1380.0\naF804.0\naF1332.0\naF1640.0\naF1848.0\naF1284.0\naF900.0\naF660.0\naF572.0\naF1380.0\naF1692.0\naF1484.0\naF900.0\naF708.0\naF1044.0\naF948.0\naF1380.0\naF1536.0\naF440.0\naF2160.0\naF900.0\naF1332.0\naF1236.0\naF660.0\naF1332.0\naF1236.0\naF1380.0\naF804.0\naF1140.0\naF1640.0\naF804.0\naF1092.0\naF1380.0\naF1284.0\naF1432.0\naF948.0\naF2004.0\naF2916.0\naF1536.0\naF1092.0\naF1284.0\naF1092.0\naF804.0\naF2004.0\naF1900.0\naF708.0\naF1284.0\naF804.0\naF708.0\naF852.0\naF660.0\naF948.0\naF1484.0\naF1484.0\naF1952.0\naF1284.0\naF1332.0\naF804.0\naF3084.0\naF2440.0\naF708.0\naF1900.0\naF1952.0\naF1236.0\naF900.0\naF1188.0\naF1432.0\naF2004.0\naF1188.0\naF1380.0\naF1848.0\naF660.0\naF1432.0\naF2108.0\naF1380.0\naF660.0\naF1380.0\naF852.0\naF1380.0\naF1380.0\naF1044.0\naF852.0\naF2440.0\naF1432.0\naF1952.0\naF756.0\naF756.0\naF804.0\naF1284.0\naF3420.0\naF1332.0\naF1640.0\naF1284.0\naF2636.0\naF1188.0\naF1640.0\naF1692.0\naF1900.0\naF1380.0\naF2384.0\naF2160.0\naF1332.0\naF996.0\naF2328.0\naF3420.0\naF2004.0\naF2004.0\naF1236.0\naF1140.0\naF1380.0\naF1640.0\naF4080.0\naF1140.0\naF1092.0\naF1284.0\naF948.0\naF2720.0\naF660.0\naF948.0\naF3000.0\naF2160.0\naF1380.0\naF3084.0\naF2776.0\naF2272.0\naF1380.0\naF2552.0\naF1332.0\naF1332.0\naF1284.0\naF4156.0\naF2160.0\naF2832.0\naF1432.0\naF2160.0\naF2832.0\naF2608.0\naF4028.0\naF1640.0\naF2056.0\naF852.0\naF2160.0\naF1380.0\naF3840.0\naF3300.0\naF1432.0\naF1332.0\naF2108.0\naF3360.0\naF3560.0\naF1536.0\naF1744.0\naF1236.0\naF4992.0\naF2944.0\naF2720.0\naF2832.0\naF3780.0\naF4960.0\naF1900.0\naF4320.0\naF3600.0\naF3240.0\naF2944.0\naF1588.0\naF2160.0\naF2160.0\naF2440.0\naF2056.0\naF3084.0\naF2160.0\naF4470.0\naF1952.0\naF3810.0\naF6092.0\naF3840.0\naF3420.0\naF3600.0\naF3196.0\naF3784.0\naF3480.0\naF8724.0\naF5246.0\naF4892.0\naF3870.0\naF5070.0\naF3196.0\naF4560.0\naF3420.0\naF4412.0\naF4414.0\naF3600.0\naF2944.0\naF2944.0\naF6724.0\naF2944.0\naF4892.0\naF4732.0\naF1640.0\naF4704.0\naF3840.0\naF5246.0\naF5340.0\naF2160.0\naF5212.0\naF4734.0\naF4732.0\naF1140.0\naF2160.0\naF5184.0\naF3252.0\naF2664.0\naF1744.0\naF5340.0\naF3660.0\naF1848.0\naF3840.0\naF1952.0\naF6150.0\naF4606.0\naF1380.0\naF2160.0\naF3028.0\naF4384.0\naF6344.0\naF4412.0\naF3000.0\naF4734.0\naF3180.0\naF4290.0\naF4140.0\naF2160.0\naF3420.0\naF4892.0\naF6312.0\naF4620.0\naF1952.0\naF4512.0\naF5340.0\naF5762.0\naF5632.0\naF2888.0\naF2004.0\naF5340.0\naF5154.0\naF4500.0\naF1692.0\naF5276.0\naF7416.0\naF6304.0\naF2160.0\naF4028.0\naF3964.0\naF5748.0\naF2108.0\naF5152.0\naF3840.0\naF8256.0\naF5504.0\naF5020.0\naF2608.0\naF3780.0\naF3000.0\naF5650.0\naF2160.0\naF3900.0\naF3300.0\naF5636.0\naF6262.0\naF5798.0\naF4412.0\naF3900.0\naF8132.0\naF6096.0\naF3180.0\naF2384.0\naF4740.0\naF3420.0\naF4576.0\naF3420.0\naF4640.0\naF2608.0\naF3660.0\naF5504.0\naF6920.0\naF4860.0\naF5248.0\naF2944.0\naF6882.0\naF3660.0\naF5246.0\naF4928.0\naF5964.0\naF4540.0\naF3990.0\naF6028.0\naF1380.0\naF5280.0\naF2608.0\naF1744.0\naF5024.0\naF6474.0\naF2160.0\naF1952.0\naF5798.0\naF3720.0\naF4350.0\naF2692.0\naF3196.0\naF5608.0\naF3000.0\naF3900.0\naF4050.0\naF4156.0\naF3964.0\naF4604.0\naF1536.0\naF4668.0\naF6508.0\naF2608.0\naF2748.0\naF4800.0\naF6096.0\naF4668.0\naF5412.0\naF4508.0\naF2160.0\naF3900.0\naF5348.0\naF6146.0\naF3600.0\naF5952.0\naF4200.0\naF6804.0\naF4348.0\naF3240.0\naF5054.0\naF5602.0\naF5598.0\naF4606.0\naF4862.0\naF5812.0\naF4284.0\naF5154.0\naF1900.0\naF4156.0\naF5632.0\naF5748.0\naF3900.0\naF7242.0\naF5540.0\naF4704.0\naF6606.0\naF5348.0\naF5408.0\naF9680.0\naF8256.0\naF3360.0\naF4080.0\naF3990.0\naF2944.0\naF7818.0\naF7182.0\naF4348.0\naF1848.0\naF6876.0\naF5958.0\naF2944.0\naF4860.0\naF3000.0\naF4898.0\naF2832.0\naF9276.0\naF3672.0\naF6538.0\naF3000.0\naF6164.0\naF4028.0\naF5790.0\naF3540.0\naF5700.0\naF4320.0\naF4284.0\naF2888.0\naF3000.0\naF3900.0\naF5880.0\naF4320.0\naF6240.0\naF5896.0\naF4348.0\naF3840.0\naF7920.0\naF5798.0\naF7494.0\naF8970.0\naF5336.0\naF4290.0\naF5216.0\naF4640.0\naF1796.0\naF3660.0\naF4860.0\naF3840.0\naF3900.0\naF1588.0\naF8076.0\naF4414.0\naF5336.0\naF7260.0\naF5760.0\naF3308.0\naF5952.0\naF5282.0\naF4092.0\naF6384.0\naF5154.0\naF4796.0\naF2664.0\naF5088.0\naF5608.0\naF5182.0\naF9014.0\naF4290.0\naF3000.0\naF8010.0\naF4640.0\naF4542.0\naF9000.0\naF6096.0\naF7224.0\naF7140.0\naF5760.0\naF4764.0\naF4320.0\naF5602.0\naF6462.0\naF6568.0\naF4796.0\naF7212.0\naF3364.0\naF4412.0\naF3420.0\naF2496.0\naF7684.0\naF8260.0\naF4860.0\naF2160.0\naF6734.0\naF4320.0\naF5182.0\naF4680.0\naF4542.0\naF4542.0\naF3900.0\naF5310.0\naF3840.0\naF1380.0\naF2832.0\naF6600.0\naF5574.0\naF5130.0\naF7254.0\naF1484.0\naF5310.0\naF5666.0\naF5310.0\naF9820.0\naF6088.0\naF7950.0\naF7692.0\naF4476.0\naF6682.0\naF6864.0\naF4350.0\naF2776.0\naF8552.0\naF5582.0\naF8064.0\naF4704.0\naF5268.0\naF4156.0\naF4260.0\naF4220.0\naF6504.0\naF4284.0\naF7806.0\naF4512.0\naF5620.0\naF4220.0\naF6474.0\naF7020.0\naF4796.0\naF6198.0\naF6690.0\naF5632.0\naF6936.0\naF5536.0\naF1380.0\naF6146.0\naF8690.0\naF5926.0\naF5952.0\naF5376.0\naF7392.0\naF6538.0\naF5118.0\naF3900.0\naF9674.0\naF5540.0\naF7760.0\naF5310.0\naF6562.0\naF4956.0\naF6024.0\naF6742.0\naF7046.0\naF5280.0\naF5132.0\naF8604.0\naF5812.0\naF4320.0\naF6674.0\naF2972.0\naF4734.0\naF5700.0\naF6262.0\naF4832.0\naF6732.0\naF6182.0\naF6966.0\naF5608.0\naF4732.0\naF4770.0\naF7752.0\naF6802.0\naF6644.0\naF9760.0\naF6138.0\naF6312.0\naF10290.0\naF4860.0\naF4932.0\naF6096.0\naF5246.0\naF5880.0\naF7224.0\naF4542.0\naF5508.0\naF5070.0\naF6906.0\naF5892.0\naF6470.0\naF2608.0\naF4476.0\naF9080.0\naF2496.0\naF3196.0\naF6300.0\naF3720.0\naF8528.0\naF3840.0\naF7078.0\naF7314.0\naF5540.0\naF3000.0\naF8766.0\naF6648.0\naF5676.0\naF3900.0\naF5926.0\naF8202.0\naF6130.0\naF8634.0\naF6232.0\naF4828.0\naF5088.0\naF6438.0\naF4670.0\naF7234.0\naF6742.0\naF5952.0\naF9630.0\naF5934.0\naF6334.0\naF9940.0\naF7568.0\naF4928.0\naF7566.0\naF5964.0\naF6424.0\naF3900.0\naF6742.0\naF8100.0\naF7428.0\naF5820.0\naF7264.0\naF7086.0\naF10300.0\naF6984.0\naF6372.0\naF5608.0\naF8666.0\naF7486.0\naF4670.0\naF9570.0\naF6312.0\naF6096.0\naF8108.0\naF6724.0\naF7446.0\naF4412.0\naF6876.0\naF4092.0\naF11370.0\naF4860.0\naF6432.0\naF6462.0\naF5514.0\naF7488.0\naF5132.0\naF4170.0\naF6792.0\naF5308.0\naF7604.0\naF6176.0\naF5446.0\naF4092.0\naF7492.0\naF3840.0\naF6262.0\naF5612.0\naF4414.0\naF5248.0\naF6346.0\naF4220.0\naF6218.0\naF5608.0\naF5696.0\naF7500.0\naF5960.0\naF3000.0\naF4290.0\naF1380.0\naF7560.0\naF7314.0\naF4862.0\naF4092.0\naF3000.0\naF8340.0\naF3660.0\naF6894.0\naF7050.0\naF6636.0\naF5410.0\naF5246.0\naF4606.0\naF4290.0\naF6948.0\naF3810.0\naF4350.0\naF6240.0\naF1380.0\naF2496.0\naF4110.0\naF6224.0\naF5990.0\naF7776.0\naF5132.0\naF5280.0\naF7162.0\naF6892.0\naF9220.0\naF6744.0\naF4860.0\naF3480.0\naF3570.0\naF11358.0\naF8140.0\naF7068.0\naF6478.0\naF7036.0\naF7476.0\naF8810.0\naF6168.0\naF7986.0\naF8022.0\naF7818.0\naF6528.0\naF7224.0\naF5476.0\naF4898.0\naF7050.0\naF7590.0\naF6894.0\naF9044.0\naF10040.0\naF9216.0\naF6100.0\naF4028.0\naF5182.0\naF8428.0\naF4414.0\naF6978.0\naF7820.0\naF6262.0\naF4604.0\naF8820.0\naF4092.0\naF9280.0\naF9288.0\naF2160.0\naF6704.0\naF8490.0\naF8346.0\naF5880.0\naF4962.0\naF4412.0\naF5310.0\naF7050.0\naF6330.0\naF5182.0\naF7530.0\naF5726.0\naF2496.0\naF6534.0\naF8930.0\naF7200.0\naF4734.0\naF10884.0\naF1380.0\naF7380.0\naF10610.0\naF8166.0\naF8940.0\naF10960.0\naF5054.0\naF9588.0\naF4764.0\naF4350.0\naF7416.0\naF10350.0\naF5280.0\naF6618.0\naF7290.0\naF8022.0\naF7652.0\naF6300.0\naF5880.0\naF9960.0\naF3420.0\naF4220.0\naF6050.0\naF7320.0\naF3420.0\naF5340.0\naF12696.0\naF5786.0\naF5880.0\naF6240.0\naF8736.0\naF9282.0\naF14402.0\naF5280.0\naF14594.0\naF8260.0\naF8058.0\naF3420.0\naF6978.0\naF5676.0\naF12068.0\naF7112.0\naF7284.0\naF9636.0\naF7500.0\naF4860.0\naF6390.0\naF6190.0\naF6028.0\naF6600.0\naF4156.0\naF7282.0\naF6888.0\naF4796.0\naF12472.0\naF7722.0\naF8164.0\naF3900.0\naF4956.0\naF6742.0\naF5182.0\naF7182.0\naF2664.0\naF9720.0\naF9710.0\naF6390.0\naF9210.0\naF4860.0\naF5404.0\naF7112.0\naF10830.0\naF6644.0\naF5880.0\naF5148.0\naF5278.0\naF6292.0\naF7542.0\naF5024.0\naF7212.0\naF8430.0\naF5200.0\naF7938.0\naF9030.0\naF6764.0\naF996.0\naF6840.0\naF10872.0\naF8916.0\naF9390.0\naF6508.0\naF9870.0\naF6732.0\naF5312.0\naF10980.0\naF5216.0\naF4476.0\naF4348.0\naF6936.0\naF10920.0\naF4700.0\naF7644.0\naF6996.0\naF6410.0\naF7896.0\naF5132.0\naF8412.0\naF6840.0\naF9408.0\naF5246.0\naF5990.0\naF6024.0\naF6610.0\naF5472.0\naF8024.0\naF12030.0\naF8840.0\naF7476.0\naF7614.0\naF4220.0\naF8032.0\naF5310.0\naF10630.0\naF7410.0\naF9780.0\naF9080.0\naF7486.0\naF11170.0\naF9880.0\naF15496.0\naF6186.0\naF5276.0\naF7080.0\naF10150.0\naF11560.0\naF9810.0\naF16410.0\naF4156.0\naF5934.0\naF10368.0\naF8406.0\naF9350.0\naF7492.0\naF6780.0\naF5790.0\naF5744.0\naF8316.0\naF7776.0\naF6528.0\naF1588.0\naF13140.0\naF4350.0\naF7848.0\naF4320.0\naF6734.0\naF6644.0\naF3964.0\naF9468.0\naF11424.0\naF11088.0\naF5152.0\naF6720.0\naF9312.0\naF2888.0\naF4542.0\naF6194.0\naF9300.0\naF6606.0\naF6538.0\naF6792.0\naF7866.0\naF5484.0\naF7860.0\naF7950.0\naF6456.0\naF10932.0\naF10130.0\naF9580.0\naF6822.0\naF4284.0\naF7774.0\naF9320.0\naF6636.0\naF7170.0\naF10116.0\naF9540.0\naF6678.0\naF9594.0\naF9800.0\naF4740.0\naF5268.0\naF7740.0\naF8022.0\naF6312.0\naF5812.0\naF10030.0\naF5744.0\naF6390.0\naF10602.0\naF9360.0\naF4220.0\naF7470.0\naF6474.0\naF5896.0\naF5118.0\naF5756.0\naF9634.0\naF7224.0\naF15274.0\naF4860.0\naF6232.0\naF7446.0\naF5280.0\naF7942.0\naF5248.0\naF6628.0\naF11730.0\naF9464.0\naF1380.0\naF5132.0\naF9840.0\naF6672.0\naF10230.0\naF5732.0\naF8362.0\naF2160.0\naF4110.0\naF7758.0\naF7704.0\naF7500.0\naF7398.0\naF8346.0\naF3600.0\naF5662.0\naF7830.0\naF11300.0\naF6960.0\naF2160.0\naF19730.0\naF9860.0\naF6292.0\naF8826.0\naF5666.0\naF6516.0\naF7818.0\naF12528.0\naF6266.0\naF6906.0\naF15118.0\naF5540.0\naF5696.0\naF8592.0\naF8764.0\naF8520.0\naF5602.0\naF16572.0\naF8704.0\naF5282.0\naF8178.0\naF6652.0\naF10700.0\naF12000.0\naF6262.0\naF6810.0\naF8148.0\naF7170.0\naF7152.0\naF11328.0\naF11638.0\naF5216.0\naF6822.0\naF7728.0\naF7920.0\naF8002.0\naF11928.0\naF9850.0\naF9356.0\naF11346.0\naF8832.0\naF11310.0\naF5760.0\naF4860.0\naF4020.0\naF12822.0\naF6600.0\naF6444.0\naF7942.0\naF17660.0\naF8208.0\naF6712.0\naF6384.0\naF5790.0\naF9266.0\naF5880.0\naF2832.0\naF5310.0\naF14640.0\naF6330.0\naF5922.0\naF9350.0\naF9090.0\naF7380.0\naF11010.0\naF7314.0\naF7260.0\naF8058.0\naF3420.0\naF7820.0\naF12548.0\naF12060.0\naF13304.0\naF13460.0\naF9200.0\naF11088.0\naF5982.0\naF5954.0\naF10154.0\naF5828.0\naF4680.0\naF4156.0\naF6712.0\naF8518.0\naF9850.0\naF7488.0\naF17610.0\naF3000.0\naF6096.0\naF7188.0\naF16392.0\naF10740.0\naF7224.0\naF528.0\naF900.0\naF176.0\naF660.0\naF352.0\naF484.0\naF352.0\naF528.0\naF708.0\naF440.0\naF1380.0\naF852.0\naF6498.0\naF3420.0\naF4542.0\naF2160.0\naF4320.0\naF9670.0\naF6028.0\naF4868.0\naF8916.0\naF8420.0\naF7086.0\naF5582.0\naF4962.0\naF6720.0\naF8820.0\naF5582.0\naF5064.0\naF7476.0\naF5812.0\naF5480.0\naF9140.0\naF4668.0\naF11430.0\naF6292.0\naF5216.0\naF6720.0\naF3964.0\naF3690.0\naF4156.0\naF3420.0\naF6660.0\naF7914.0\naF7080.0\naF6708.0\naF4740.0\naF7380.0\naF13140.0\naF9130.0\naF18900.0\naF9140.0\naF4800.0\naF6478.0\naF10590.0\naF5896.0\naF6292.0\naF3750.0\naF6360.0\naF9300.0\naF8436.0\naF7332.0\naF5922.0\naF6822.0\naF2776.0\naF8604.0\naF6300.0\naF5508.0\naF10430.0\naF10700.0\naF7026.0\naF6720.0\naF10560.0\na."
  },
  {
    "path": "dqn/logs_pkls/BeamRider_s002.pkl",
    "content": "(lp0\n(I60000\ncnumpy.core.multiarray\nscalar\np1\n(cnumpy\ndtype\np2\n(S'f8'\np3\nI0\nI1\ntp4\nRp5\n(I3\nS'<'\np6\nNNNI-1\nI-1\nI0\ntp7\nbS'\\xc7q\\x1c\\xc7q\\x9cv@'\np8\ntp9\nRp10\nF-inf\nF220.0\ntp11\na(I70000\ng1\n(g5\nS';\\xb1\\x13;\\xb1\\xf3v@'\np12\ntp13\nRp14\nF-inf\nF220.0\ntp15\na(I80000\ng1\n(g5\nS'd+\\x82\\x86\\x93\\xfav@'\np16\ntp17\nRp18\nF-inf\nF352.0\ntp19\na(I90000\ng1\n(g5\nS'\\xa8\\x9c\\xdd\\xc2\\xaf\\x06w@'\np20\ntp21\nRp22\nF-inf\nF440.0\ntp23\na(I100000\ng1\n(g5\nS'`,\\xf9\\xc5\\x92\\x9fv@'\np24\ntp25\nRp26\nF-inf\nF176.0\ntp27\na(I110000\ng1\n(g5\nS'}\\x0c\\xce\\xc7\\xe0\\xbcv@'\np28\ntp29\nRp30\nF-inf\nF440.0\ntp31\na(I120000\ng1\n(g5\nS'\\xd6\\\\\\xcd\\xd5\\\\Mv@'\np32\ntp33\nRp34\nF-inf\nF308.0\ntp35\na(I130000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x80v@'\np36\ntp37\nRp38\nF-inf\nF132.0\ntp39\na(I140000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x9av@'\np40\ntp41\nRp42\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8v@'\np43\ntp44\nRp45\nF440.0\ntp46\na(I150000\ng1\n(g5\nS\"H\\xe1z\\x14\\xae'w@\"\np47\ntp48\nRp49\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc25w@'\np50\ntp51\nRp52\nF132.0\ntp53\na(I160000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc25w@'\np54\ntp55\nRp56\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQw@'\np57\ntp58\nRp59\nF352.0\ntp60\na(I170000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14nw@'\np61\ntp62\nRp63\ng1\n(g5\nS'\\xaeG\\xe1z\\x14nw@'\np64\ntp65\nRp66\nF308.0\ntp67\na(I180000\ng1\n(g5\nS'\\xa4p=\\n\\xd7Cw@'\np68\ntp69\nRp70\ng1\n(g5\nS'33333\\x83w@'\np71\ntp72\nRp73\nF264.0\ntp74\na(I190000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfdv@'\np75\ntp76\nRp77\ng73\nF308.0\ntp78\na(I200000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8cv@'\np79\ntp80\nRp81\ng73\nF352.0\ntp82\na(I210000\ng1\n(g5\nS'fffff\\xf6v@'\np83\ntp84\nRp85\ng73\nF352.0\ntp86\na(I220000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1Jw@'\np87\ntp88\nRp89\ng73\nF220.0\ntp90\na(I230000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x10x@'\np91\ntp92\nRp93\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x10x@'\np94\ntp95\nRp96\nF616.0\ntp97\na(I240000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xbbw@'\np98\ntp99\nRp100\ng1\n(g5\nS'fffffVx@'\np101\ntp102\nRp103\nF176.0\ntp104\na(I250000\ng1\n(g5\nS'=\\n\\xd7\\xa3p]x@'\np105\ntp106\nRp107\ng1\n(g5\nS'=\\n\\xd7\\xa3p]x@'\np108\ntp109\nRp110\nF352.0\ntp111\na(I260000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x10x@'\np112\ntp113\nRp114\ng110\nF396.0\ntp115\na(I270000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x01x@'\np116\ntp117\nRp118\ng110\nF396.0\ntp119\na(I280000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x91w@'\np120\ntp121\nRp122\ng110\nF308.0\ntp123\na(I290000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1euw@'\np124\ntp125\nRp126\ng110\nF308.0\ntp127\na(I300000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xefv@'\np128\ntp129\nRp130\ng110\nF396.0\ntp131\na(I310000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xbev@'\np132\ntp133\nRp134\ng110\nF440.0\ntp135\na(I320000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8~v@'\np136\ntp137\nRp138\ng110\nF396.0\ntp139\na(I330000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xdav@'\np140\ntp141\nRp142\ng110\nF440.0\ntp143\na(I340000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x85v@'\np144\ntp145\nRp146\ng110\nF132.0\ntp147\na(I350000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x9du@'\np148\ntp149\nRp150\ng110\nF484.0\ntp151\na(I360000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5Hu@'\np152\ntp153\nRp154\ng110\nF440.0\ntp155\na(I370000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xdft@'\np156\ntp157\nRp158\ng110\nF484.0\ntp159\na(I380000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xf5t@'\np160\ntp161\nRp162\ng110\nF708.0\ntp163\na(I390000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xa5u@'\np164\ntp165\nRp166\ng110\nF660.0\ntp167\na(I400000\ng1\n(g5\nS'fffff\\xd6u@'\np168\ntp169\nRp170\ng110\nF396.0\ntp171\na(I410000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeWu@'\np172\ntp173\nRp174\ng110\nF484.0\ntp175\na(I420000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^u@'\np176\ntp177\nRp178\ng110\nF308.0\ntp179\na(I430000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x97u@'\np180\ntp181\nRp182\ng110\nF440.0\ntp183\na(I440000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x88u@'\np184\ntp185\nRp186\ng110\nF528.0\ntp187\na(I450000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x1cv@'\np188\ntp189\nRp190\ng110\nF308.0\ntp191\na(I460000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf58v@'\np192\ntp193\nRp194\ng110\nF132.0\ntp195\na(I470000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xddu@'\np196\ntp197\nRp198\ng110\nF264.0\ntp199\na(I480000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x0ev@'\np200\ntp201\nRp202\ng110\nF572.0\ntp203\na(I490000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@v@'\np204\ntp205\nRp206\ng110\nF220.0\ntp207\na(I500000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGqv@'\np208\ntp209\nRp210\ng110\nF660.0\ntp211\na(I510000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x8dv@'\np212\ntp213\nRp214\ng110\nF308.0\ntp215\na(I520000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xa1v@'\np216\ntp217\nRp218\ng110\nF528.0\ntp219\na(I530000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eeu@'\np220\ntp221\nRp222\ng110\nF308.0\ntp223\na(I540000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xceu@'\np224\ntp225\nRp226\ng110\nF308.0\ntp227\na(I550000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG1v@'\np228\ntp229\nRp230\ng110\nF396.0\ntp231\na(I560000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x0ev@'\np232\ntp233\nRp234\ng110\nF308.0\ntp235\na(I570000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xc0u@'\np236\ntp237\nRp238\ng110\nF176.0\ntp239\na(I580000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\?v@'\np240\ntp241\nRp242\ng110\nF176.0\ntp243\na(I590000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG1v@'\np244\ntp245\nRp246\ng110\nF176.0\ntp247\na(I600000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8~v@'\np248\ntp249\nRp250\ng110\nF220.0\ntp251\na(I610000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x94v@'\np252\ntp253\nRp254\ng110\nF220.0\ntp255\na(I620000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x8dv@'\np256\ntp257\nRp258\ng110\nF660.0\ntp259\na(I630000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x0cw@'\np260\ntp261\nRp262\ng110\nF220.0\ntp263\na(I640000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ(w@'\np264\ntp265\nRp266\ng110\nF132.0\ntp267\na(I650000\ng1\n(g5\nS'\\xa4p=\\n\\xd7Sw@'\np268\ntp269\nRp270\ng110\nF132.0\ntp271\na(I660000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\rw@'\np272\ntp273\nRp274\ng110\nF220.0\ntp275\na(I670000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xcev@'\np276\ntp277\nRp278\ng110\nF176.0\ntp279\na(I680000\ng1\n(g5\nS'33333\\x93w@'\np280\ntp281\nRp282\ng110\nF308.0\ntp283\na(I690000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xeew@'\np284\ntp285\nRp286\ng110\nF352.0\ntp287\na(I700000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbdw@'\np288\ntp289\nRp290\ng110\nF484.0\ntp291\na(I710000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xcbw@'\np292\ntp293\nRp294\ng110\nF132.0\ntp295\na(I720000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGQx@'\np296\ntp297\nRp298\ng110\nF528.0\ntp299\na(I730000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e5x@'\np300\ntp301\nRp302\ng1\n(g5\nS'=\\n\\xd7\\xa3pmx@'\np303\ntp304\nRp305\nF220.0\ntp306\na(I740000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbdw@'\np307\ntp308\nRp309\ng305\nF528.0\ntp310\na(I750000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85w@'\np311\ntp312\nRp313\ng305\nF352.0\ntp314\na(I760000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eEw@'\np315\ntp316\nRp317\ng305\nF308.0\ntp318\na(I770000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xe9v@'\np319\ntp320\nRp321\ng305\nF440.0\ntp322\na(I780000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x95v@'\np323\ntp324\nRp325\ng305\nF396.0\ntp326\na(I790000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQxv@'\np327\ntp328\nRp329\ng305\nF660.0\ntp330\na(I800000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x85v@'\np331\ntp332\nRp333\ng305\nF132.0\ntp334\na(I810000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG1v@'\np335\ntp336\nRp337\ng305\nF44.0\ntp338\na(I820000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8cv@'\np339\ntp340\nRp341\ng305\nF528.0\ntp342\na(I830000\ng1\n(g5\nS'fffffFv@'\np343\ntp344\nRp345\ng305\nF264.0\ntp346\na(I840000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x9du@'\np347\ntp348\nRp349\ng305\nF308.0\ntp350\na(I850000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\tu@'\np351\ntp352\nRp353\ng305\nF176.0\ntp354\na(I860000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xcat@'\np355\ntp356\nRp357\ng305\nF352.0\ntp358\na(I870000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc|t@'\np359\ntp360\nRp361\ng305\nF440.0\ntp362\na(I880000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xbct@'\np363\ntp364\nRp365\ng305\nF484.0\ntp366\na(I890000\ng1\n(g5\nS'33333\\xc3t@'\np367\ntp368\nRp369\ng305\nF660.0\ntp370\na(I900000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xedt@'\np371\ntp372\nRp373\ng305\nF132.0\ntp374\na(I910000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x17u@'\np375\ntp376\nRp377\ng305\nF352.0\ntp378\na(I920000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xf4t@'\np379\ntp380\nRp381\ng305\nF484.0\ntp382\na(I930000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xcat@'\np383\ntp384\nRp385\ng305\nF660.0\ntp386\na(I940000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z4u@'\np387\ntp388\nRp389\ng305\nF308.0\ntp390\na(I950000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^u@'\np391\ntp392\nRp393\ng305\nF484.0\ntp394\na(I960000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1*v@'\np395\ntp396\nRp397\ng305\nF308.0\ntp398\na(I970000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@v@'\np399\ntp400\nRp401\ng305\nF352.0\ntp402\na(I980000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xc8u@'\np403\ntp404\nRp405\ng305\nF396.0\ntp406\na(I990000\ng1\n(g5\nS'\\n\\xd7\\xa3p=jv@'\np407\ntp408\nRp409\ng305\nF132.0\ntp410\na(I1000000\ng1\n(g5\nS'\\n\\xd7\\xa3p=jv@'\np411\ntp412\nRp413\ng305\nF264.0\ntp414\na(I1010000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xa9v@'\np415\ntp416\nRp417\ng305\nF528.0\ntp418\na(I1020000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xa2v@'\np419\ntp420\nRp421\ng305\nF616.0\ntp422\na(I1030000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x8dv@'\np423\ntp424\nRp425\ng305\nF176.0\ntp426\na(I1040000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xd3v@'\np427\ntp428\nRp429\ng305\nF660.0\ntp430\na(I1050000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14Nv@'\np431\ntp432\nRp433\ng305\nF264.0\ntp434\na(I1060000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x1cv@'\np435\ntp436\nRp437\ng305\nF264.0\ntp438\na(I1070000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xccv@'\np439\ntp440\nRp441\ng305\nF440.0\ntp442\na(I1080000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05w@'\np443\ntp444\nRp445\ng305\nF308.0\ntp446\na(I1090000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x93v@'\np447\ntp448\nRp449\ng305\nF264.0\ntp450\na(I1100000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\?v@'\np451\ntp452\nRp453\ng305\nF440.0\ntp454\na(I1110000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xf8u@'\np455\ntp456\nRp457\ng305\nF176.0\ntp458\na(I1120000\ng1\n(g5\nS'=\\n\\xd7\\xa3pMv@'\np459\ntp460\nRp461\ng305\nF484.0\ntp462\na(I1130000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xa1v@'\np463\ntp464\nRp465\ng305\nF616.0\ntp466\na(I1140000\ng1\n(g5\nS'fffffFv@'\np467\ntp468\nRp469\ng305\nF572.0\ntp470\na(I1150000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8~v@'\np471\ntp472\nRp473\ng305\nF44.0\ntp474\na(I1160000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQw@'\np475\ntp476\nRp477\ng305\nF352.0\ntp478\na(I1170000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x19w@'\np479\ntp480\nRp481\ng305\nF264.0\ntp482\na(I1180000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8.w@'\np483\ntp484\nRp485\ng305\nF308.0\ntp486\na(I1190000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xdew@'\np487\ntp488\nRp489\ng305\nF484.0\ntp490\na(I1200000\ng1\n(g5\nS'q=\\n\\xd7\\xa3 w@'\np491\ntp492\nRp493\ng305\nF88.0\ntp494\na(I1210000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xd0w@'\np495\ntp496\nRp497\ng305\nF660.0\ntp498\na(I1220000\ng1\n(g5\nS'=\\n\\xd7\\xa3p]x@'\np499\ntp500\nRp501\ng305\nF660.0\ntp502\na(I1230000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xf8x@'\np503\ntp504\nRp505\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x15y@'\np506\ntp507\nRp508\nF484.0\ntp509\na(I1240000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xf1x@'\np510\ntp511\nRp512\ng508\nF440.0\ntp513\na(I1250000\ng1\n(g5\nS'33333sx@'\np514\ntp515\nRp516\ng508\nF132.0\ntp517\na(I1260000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8fx@'\np518\ntp519\nRp520\ng508\nF264.0\ntp521\na(I1270000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xc0x@'\np522\ntp523\nRp524\ng508\nF176.0\ntp525\na(I1280000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc7x@'\np526\ntp527\nRp528\ng508\nF528.0\ntp529\na(I1290000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xecx@'\np530\ntp531\nRp532\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e%y@'\np533\ntp534\nRp535\nF176.0\ntp536\na(I1300000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQHy@'\np537\ntp538\nRp539\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQHy@'\np540\ntp541\nRp542\nF528.0\ntp543\na(I1310000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xacy@'\np544\ntp545\nRp546\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xacy@'\np547\ntp548\nRp549\nF804.0\ntp550\na(I1320000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebqz@'\np551\ntp552\nRp553\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebqz@'\np554\ntp555\nRp556\nF616.0\ntp557\na(I1330000\ng1\n(g5\nS'33333\\xe3z@'\np558\ntp559\nRp560\ng1\n(g5\nS'33333\\xe3z@'\np561\ntp562\nRp563\nF660.0\ntp564\na(I1340000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xffz@'\np565\ntp566\nRp567\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xffz@'\np568\ntp569\nRp570\nF440.0\ntp571\na(I1350000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8frz@'\np572\ntp573\nRp574\ng570\nF308.0\ntp575\na(I1360000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xc1z@'\np576\ntp577\nRp578\ng570\nF308.0\ntp579\na(I1370000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGq{@'\np580\ntp581\nRp582\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x7f{@'\np583\ntp584\nRp585\nF308.0\ntp586\na(I1380000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x7f{@'\np587\ntp588\nRp589\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xa2{@'\np590\ntp591\nRp592\nF396.0\ntp593\na(I1390000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xcd{@'\np594\ntp595\nRp596\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xfe{@'\np597\ntp598\nRp599\nF528.0\ntp600\na(I1400000\ng1\n(g5\nS'33333c{@'\np601\ntp602\nRp603\ng599\nF440.0\ntp604\na(I1410000\ng1\n(g5\nS'fffff\\xc6{@'\np605\ntp606\nRp607\ng599\nF352.0\ntp608\na(I1420000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99|@'\np609\ntp610\nRp611\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99|@'\np612\ntp613\nRp614\nF660.0\ntp615\na(I1430000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\o|@'\np616\ntp617\nRp618\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xbc|@'\np619\ntp620\nRp621\nF352.0\ntp622\na(I1440000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc5|@'\np623\ntp624\nRp625\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc5|@'\np626\ntp627\nRp628\nF660.0\ntp629\na(I1450000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x83}@'\np630\ntp631\nRp632\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x83}@'\np633\ntp634\nRp635\nF396.0\ntp636\na(I1460000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xe7}@'\np637\ntp638\nRp639\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xe7}@'\np640\ntp641\nRp642\nF756.0\ntp643\na(I1470000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGA~@'\np644\ntp645\nRp646\ng1\n(g5\nS'\\xe1z\\x14\\xaeGA~@'\np647\ntp648\nRp649\nF484.0\ntp650\na(I1480000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x95~@'\np651\ntp652\nRp653\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x95~@'\np654\ntp655\nRp656\nF660.0\ntp657\na(I1490000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x95~@'\np658\ntp659\nRp660\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x9c~@'\np661\ntp662\nRp663\nF804.0\ntp664\na(I1500000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x999\\x7f@'\np665\ntp666\nRp667\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x999\\x7f@'\np668\ntp669\nRp670\nF660.0\ntp671\na(I1510000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2%\\x7f@'\np672\ntp673\nRp674\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00P\\x7f@'\np675\ntp676\nRp677\nF396.0\ntp678\na(I1520000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde\\x7f@'\np679\ntp680\nRp681\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde\\x7f@'\np682\ntp683\nRp684\nF484.0\ntp685\na(I1530000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99)\\x80@'\np686\ntp687\nRp688\ng1\n(g5\nS'\\xa4p=\\n\\xd7S\\x80@'\np689\ntp690\nRp691\nF132.0\ntp692\na(I1540000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2]\\x80@'\np693\ntp694\nRp695\ng1\n(g5\nS'=\\n\\xd7\\xa3pe\\x80@'\np696\ntp697\nRp698\nF660.0\ntp699\na(I1550000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x9b\\x80@'\np700\ntp701\nRp702\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x9b\\x80@'\np703\ntp704\nRp705\nF900.0\ntp706\na(I1560000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x07\\x81@'\np707\ntp708\nRp709\ng1\n(g5\nS'fffff\\x0e\\x81@'\np710\ntp711\nRp712\nF220.0\ntp713\na(I1570000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG!\\x81@'\np714\ntp715\nRp716\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\/\\x81@'\np717\ntp718\nRp719\nF528.0\ntp720\na(I1580000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85+\\x81@'\np721\ntp722\nRp723\ng719\nF660.0\ntp724\na(I1590000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2=\\x81@'\np725\ntp726\nRp727\ng1\n(g5\nS'\\xa4p=\\n\\xd7K\\x81@'\np728\ntp729\nRp730\nF352.0\ntp731\na(I1600000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85;\\x81@'\np732\ntp733\nRp734\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eM\\x81@'\np735\ntp736\nRp737\nF352.0\ntp738\na(I1610000\ng1\n(g5\nS'\\xa4p=\\n\\xd7s\\x81@'\np739\ntp740\nRp741\ng1\n(g5\nS'\\xa4p=\\n\\xd7s\\x81@'\np742\ntp743\nRp744\nF660.0\ntp745\na(I1620000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xf1\\x81@'\np746\ntp747\nRp748\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xf1\\x81@'\np749\ntp750\nRp751\nF660.0\ntp752\na(I1630000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x82\\x82@'\np753\ntp754\nRp755\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x82\\x82@'\np756\ntp757\nRp758\nF708.0\ntp759\na(I1640000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x89\\x82@'\np760\ntp761\nRp762\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x9b\\x82@'\np763\ntp764\nRp765\nF396.0\ntp766\na(I1650000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xea\\x82@'\np767\ntp768\nRp769\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xea\\x82@'\np770\ntp771\nRp772\nF900.0\ntp773\na(I1660000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y\\x83@'\np774\ntp775\nRp776\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y\\x83@'\np777\ntp778\nRp779\nF1140.0\ntp780\na(I1670000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8n\\x83@'\np781\ntp782\nRp783\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc|\\x83@'\np784\ntp785\nRp786\nF528.0\ntp787\na(I1680000\ng1\n(g5\nS'33333\\x93\\x83@'\np788\ntp789\nRp790\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x9d\\x83@'\np791\ntp792\nRp793\nF660.0\ntp794\na(I1690000\ng1\n(g5\nS'\\xd7\\xa3p=\\nw\\x83@'\np795\ntp796\nRp797\ng793\nF572.0\ntp798\na(I1700000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x91\\x83@'\np799\ntp800\nRp801\ng793\nF852.0\ntp802\na(I1710000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14~\\x83@'\np803\ntp804\nRp805\ng1\n(g5\nS'fffff\\xbe\\x83@'\np806\ntp807\nRp808\nF616.0\ntp809\na(I1720000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c\\x83@'\np810\ntp811\nRp812\ng808\nF440.0\ntp813\na(I1730000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc5\\x83@'\np814\ntp815\nRp816\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc5\\x83@'\np817\ntp818\nRp819\nF852.0\ntp820\na(I1740000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xaf\\x83@'\np821\ntp822\nRp823\ng819\nF660.0\ntp824\na(I1750000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xfa\\x83@'\np825\ntp826\nRp827\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xfa\\x83@'\np828\ntp829\nRp830\nF484.0\ntp831\na(I1760000\ng1\n(g5\nS'\\n\\xd7\\xa3p=Z\\x84@'\np832\ntp833\nRp834\ng1\n(g5\nS'\\n\\xd7\\xa3p=Z\\x84@'\np835\ntp836\nRp837\nF1044.0\ntp838\na(I1770000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5x\\x84@'\np839\ntp840\nRp841\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc|\\x84@'\np842\ntp843\nRp844\nF948.0\ntp845\na(I1780000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x89\\x84@'\np846\ntp847\nRp848\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x9b\\x84@'\np849\ntp850\nRp851\nF440.0\ntp852\na(I1790000\ng1\n(g5\nS'33333\\xd3\\x84@'\np853\ntp854\nRp855\ng1\n(g5\nS'33333\\xd3\\x84@'\np856\ntp857\nRp858\nF1236.0\ntp859\na(I1800000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x0c\\x85@'\np860\ntp861\nRp862\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x0c\\x85@'\np863\ntp864\nRp865\nF756.0\ntp866\na(I1810000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k\\x85@'\np867\ntp868\nRp869\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k\\x85@'\np870\ntp871\nRp872\nF1380.0\ntp873\na(I1820000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xd2\\x85@'\np874\ntp875\nRp876\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xd2\\x85@'\np877\ntp878\nRp879\nF804.0\ntp880\na(I1830000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xf7\\x85@'\np881\ntp882\nRp883\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xf7\\x85@'\np884\ntp885\nRp886\nF352.0\ntp887\na(I1840000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\x85@'\np888\ntp889\nRp890\ng886\nF660.0\ntp891\na(I1850000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccd\\x85@'\np892\ntp893\nRp894\ng886\nF660.0\ntp895\na(I1860000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(t\\x85@'\np896\ntp897\nRp898\ng886\nF852.0\ntp899\na(I1870000\ng1\n(g5\nS'fffff\\xa6\\x85@'\np900\ntp901\nRp902\ng886\nF308.0\ntp903\na(I1880000\ng1\n(g5\nS'fffff\\xa6\\x85@'\np904\ntp905\nRp906\ng886\nF756.0\ntp907\na(I1890000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xb6\\x85@'\np908\ntp909\nRp910\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x07\\x86@'\np911\ntp912\nRp913\nF396.0\ntp914\na(I1900000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xfd\\x85@'\np915\ntp916\nRp917\ng913\nF756.0\ntp918\na(I1910000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ@\\x86@'\np919\ntp920\nRp921\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ@\\x86@'\np922\ntp923\nRp924\nF756.0\ntp925\na(I1920000\ng1\n(g5\nS'33333\\xfb\\x86@'\np926\ntp927\nRp928\ng1\n(g5\nS'33333\\xfb\\x86@'\np929\ntp930\nRp931\nF2108.0\ntp932\na(I1930000\ng1\n(g5\nS'fffff\\x86\\x87@'\np933\ntp934\nRp935\ng1\n(g5\nS'fffff\\x86\\x87@'\np936\ntp937\nRp938\nF440.0\ntp939\na(I1940000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xde\\x87@'\np940\ntp941\nRp942\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xe1\\x87@'\np943\ntp944\nRp945\nF756.0\ntp946\na(I1950000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGQ\\x88@'\np947\ntp948\nRp949\ng1\n(g5\nS'\\xe1z\\x14\\xaeGQ\\x88@'\np950\ntp951\nRp952\nF1092.0\ntp953\na(I1960000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x88@'\np954\ntp955\nRp956\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x86\\x88@'\np957\ntp958\nRp959\nF528.0\ntp960\na(I1970000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd4\\x88@'\np961\ntp962\nRp963\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd4\\x88@'\np964\ntp965\nRp966\nF1588.0\ntp967\na(I1980000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQP\\x89@'\np968\ntp969\nRp970\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQP\\x89@'\np971\ntp972\nRp973\nF1380.0\ntp974\na(I1990000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x80\\x89@'\np975\ntp976\nRp977\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x80\\x89@'\np978\ntp979\nRp980\nF1380.0\ntp981\na(I2000000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x08\\x8a@'\np982\ntp983\nRp984\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x08\\x8a@'\np985\ntp986\nRp987\nF1380.0\ntp988\na(I2010000\ng1\n(g5\nS'33333\\x03\\x8a@'\np989\ntp990\nRp991\ng987\nF660.0\ntp992\na(I2020000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x8a@'\np993\ntp994\nRp995\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x8a@'\np996\ntp997\nRp998\nF1380.0\ntp999\na(I2030000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xf7\\x8a@'\np1000\ntp1001\nRp1002\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xf7\\x8a@'\np1003\ntp1004\nRp1005\nF1380.0\ntp1006\na(I2040000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e5\\x8b@'\np1007\ntp1008\nRp1009\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e5\\x8b@'\np1010\ntp1011\nRp1012\nF660.0\ntp1013\na(I2050000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2-\\x8b@'\np1014\ntp1015\nRp1016\ng1\n(g5\nS'\\xa4p=\\n\\xd7S\\x8b@'\np1017\ntp1018\nRp1019\nF948.0\ntp1020\na(I2060000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f*\\x8b@'\np1021\ntp1022\nRp1023\ng1019\nF660.0\ntp1024\na(I2070000\ng1\n(g5\nS'q=\\n\\xd7\\xa38\\x8b@'\np1025\ntp1026\nRp1027\ng1019\nF660.0\ntp1028\na(I2080000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x93\\x8b@'\np1029\ntp1030\nRp1031\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x93\\x8b@'\np1032\ntp1033\nRp1034\nF1380.0\ntp1035\na(I2090000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xf9\\x8b@'\np1036\ntp1037\nRp1038\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xf9\\x8b@'\np1039\ntp1040\nRp1041\nF1692.0\ntp1042\na(I2100000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99)\\x8c@'\np1043\ntp1044\nRp1045\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99)\\x8c@'\np1046\ntp1047\nRp1048\nF1744.0\ntp1049\na(I2110000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x00\\x8d@'\np1050\ntp1051\nRp1052\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x00\\x8d@'\np1053\ntp1054\nRp1055\nF756.0\ntp1056\na(I2120000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x81\\x8d@'\np1057\ntp1058\nRp1059\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x81\\x8d@'\np1060\ntp1061\nRp1062\nF1284.0\ntp1063\na(I2130000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xf1\\x8d@'\np1064\ntp1065\nRp1066\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xf1\\x8d@'\np1067\ntp1068\nRp1069\nF1432.0\ntp1070\na(I2140000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x1d\\x8f@'\np1071\ntp1072\nRp1073\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x1d\\x8f@'\np1074\ntp1075\nRp1076\nF4230.0\ntp1077\na(I2150000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x81\\x8f@'\np1078\ntp1079\nRp1080\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x81\\x8f@'\np1081\ntp1082\nRp1083\nF756.0\ntp1084\na(I2160000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x11\\x90@'\np1085\ntp1086\nRp1087\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x11\\x90@'\np1088\ntp1089\nRp1090\nF1380.0\ntp1091\na(I2170000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\"\\x90@'\np1092\ntp1093\nRp1094\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\"\\x90@'\np1095\ntp1096\nRp1097\nF1536.0\ntp1098\na(I2180000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x03\\x90@'\np1099\ntp1100\nRp1101\ng1097\nF660.0\ntp1102\na(I2190000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeQ\\x90@'\np1103\ntp1104\nRp1105\ng1\n(g5\nS'H\\xe1z\\x14\\xaeQ\\x90@'\np1106\ntp1107\nRp1108\nF852.0\ntp1109\na(I2200000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ&\\x90@'\np1110\ntp1111\nRp1112\ng1108\nF352.0\ntp1113\na(I2210000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14x\\x90@'\np1114\ntp1115\nRp1116\ng1\n(g5\nS'\\xaeG\\xe1z\\x14x\\x90@'\np1117\ntp1118\nRp1119\nF2160.0\ntp1120\na(I2220000\ng1\n(g5\nS'fffff\\xc8\\x90@'\np1121\ntp1122\nRp1123\ng1\n(g5\nS'fffff\\xc8\\x90@'\np1124\ntp1125\nRp1126\nF2860.0\ntp1127\na(I2230000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xf2\\x90@'\np1128\ntp1129\nRp1130\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xfa\\x90@'\np1131\ntp1132\nRp1133\nF1092.0\ntp1134\na(I2240000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xee\\x90@'\np1135\ntp1136\nRp1137\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(&\\x91@'\np1138\ntp1139\nRp1140\nF708.0\ntp1141\na(I2250000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xee\\x90@'\np1142\ntp1143\nRp1144\ng1140\nF1284.0\ntp1145\na(I2260000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xff\\x90@'\np1146\ntp1147\nRp1148\ng1140\nF1380.0\ntp1149\na(I2270000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xb9\\x91@'\np1150\ntp1151\nRp1152\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xb9\\x91@'\np1153\ntp1154\nRp1155\nF2272.0\ntp1156\na(I2280000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\G\\x92@'\np1157\ntp1158\nRp1159\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccT\\x92@'\np1160\ntp1161\nRp1162\nF756.0\ntp1163\na(I2290000\ng1\n(g5\nS'\\xa4p=\\n\\xd7k\\x92@'\np1164\ntp1165\nRp1166\ng1\n(g5\nS'\\xa4p=\\n\\xd7k\\x92@'\np1167\ntp1168\nRp1169\nF1380.0\ntp1170\na(I2300000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x04\\x93@'\np1171\ntp1172\nRp1173\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x04\\x93@'\np1174\ntp1175\nRp1176\nF2552.0\ntp1177\na(I2310000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xd7\\x92@'\np1178\ntp1179\nRp1180\ng1176\nF996.0\ntp1181\na(I2320000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x07\\x93@'\np1182\ntp1183\nRp1184\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x07\\x93@'\np1185\ntp1186\nRp1187\nF1044.0\ntp1188\na(I2330000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0b\\x93@'\np1189\ntp1190\nRp1191\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x1e\\x93@'\np1192\ntp1193\nRp1194\nF996.0\ntp1195\na(I2340000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x89\\x93@'\np1196\ntp1197\nRp1198\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x89\\x93@'\np1199\ntp1200\nRp1201\nF2108.0\ntp1202\na(I2350000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xb6\\x93@'\np1203\ntp1204\nRp1205\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xb6\\x93@'\np1206\ntp1207\nRp1208\nF1484.0\ntp1209\na(I2360000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x95\\x93@'\np1210\ntp1211\nRp1212\ng1208\nF1432.0\ntp1213\na(I2370000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xaa\\x93@'\np1214\ntp1215\nRp1216\ng1208\nF1140.0\ntp1217\na(I2380000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x9e\\x93@'\np1218\ntp1219\nRp1220\ng1208\nF1380.0\ntp1221\na(I2390000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd\\x93@'\np1222\ntp1223\nRp1224\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd\\x93@'\np1225\ntp1226\nRp1227\nF1380.0\ntp1228\na(I2400000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xde\\x93@'\np1229\ntp1230\nRp1231\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xde\\x93@'\np1232\ntp1233\nRp1234\nF1044.0\ntp1235\na(I2410000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeS\\x94@'\np1236\ntp1237\nRp1238\ng1\n(g5\nS'H\\xe1z\\x14\\xaeS\\x94@'\np1239\ntp1240\nRp1241\nF1044.0\ntp1242\na(I2420000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x8d\\x94@'\np1243\ntp1244\nRp1245\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x8f\\x94@'\np1246\ntp1247\nRp1248\nF1092.0\ntp1249\na(I2430000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\r\\x95@'\np1250\ntp1251\nRp1252\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\r\\x95@'\np1253\ntp1254\nRp1255\nF2160.0\ntp1256\na(I2440000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^\\x95@'\np1257\ntp1258\nRp1259\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^\\x95@'\np1260\ntp1261\nRp1262\nF2692.0\ntp1263\na(I2450000\ng1\n(g5\nS'{\\x14\\xaeG\\xe12\\x95@'\np1264\ntp1265\nRp1266\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc`\\x95@'\np1267\ntp1268\nRp1269\nF616.0\ntp1270\na(I2460000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xa0\\x95@'\np1271\ntp1272\nRp1273\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xa0\\x95@'\np1274\ntp1275\nRp1276\nF1380.0\ntp1277\na(I2470000\ng1\n(g5\nS'q=\\n\\xd7\\xa3l\\x95@'\np1278\ntp1279\nRp1280\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb0\\x95@'\np1281\ntp1282\nRp1283\nF756.0\ntp1284\na(I2480000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x92\\x95@'\np1285\ntp1286\nRp1287\ng1283\nF2160.0\ntp1288\na(I2490000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xbe\\x95@'\np1289\ntp1290\nRp1291\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xbe\\x95@'\np1292\ntp1293\nRp1294\nF1952.0\ntp1295\na(I2500000\ng1\n(g5\nS'q=\\n\\xd7\\xa3~\\x95@'\np1296\ntp1297\nRp1298\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xee\\x95@'\np1299\ntp1300\nRp1301\nF2056.0\ntp1302\na(I2510000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xd3\\x95@'\np1303\ntp1304\nRp1305\ng1301\nF2056.0\ntp1306\na(I2520000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2/\\x96@'\np1307\ntp1308\nRp1309\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2/\\x96@'\np1310\ntp1311\nRp1312\nF3060.0\ntp1313\na(I2530000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebg\\x96@'\np1314\ntp1315\nRp1316\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebg\\x96@'\np1317\ntp1318\nRp1319\nF1332.0\ntp1320\na(I2540000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zb\\x96@'\np1321\ntp1322\nRp1323\ng1319\nF1692.0\ntp1324\na(I2550000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xa6\\x96@'\np1325\ntp1326\nRp1327\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xa6\\x96@'\np1328\ntp1329\nRp1330\nF1692.0\ntp1331\na(I2560000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xe5\\x96@'\np1332\ntp1333\nRp1334\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xe5\\x96@'\np1335\ntp1336\nRp1337\nF1744.0\ntp1338\na(I2570000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xce\\x96@'\np1339\ntp1340\nRp1341\ng1337\nF852.0\ntp1342\na(I2580000\ng1\n(g5\nS'H\\xe1z\\x14\\xae)\\x97@'\np1343\ntp1344\nRp1345\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85-\\x97@'\np1346\ntp1347\nRp1348\nF708.0\ntp1349\na(I2590000\ng1\n(g5\nS'=\\n\\xd7\\xa3pC\\x97@'\np1350\ntp1351\nRp1352\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e[\\x97@'\np1353\ntp1354\nRp1355\nF996.0\ntp1356\na(I2600000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xf8\\x97@'\np1357\ntp1358\nRp1359\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xf8\\x97@'\np1360\ntp1361\nRp1362\nF2692.0\ntp1363\na(I2610000\ng1\n(g5\nS'fffff\\xae\\x97@'\np1364\ntp1365\nRp1366\ng1362\nF1332.0\ntp1367\na(I2620000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x1d\\x98@'\np1368\ntp1369\nRp1370\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x1d\\x98@'\np1371\ntp1372\nRp1373\nF3870.0\ntp1374\na(I2630000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xa4\\x98@'\np1375\ntp1376\nRp1377\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xa4\\x98@'\np1378\ntp1379\nRp1380\nF2972.0\ntp1381\na(I2640000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xb4\\x98@'\np1382\ntp1383\nRp1384\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xb4\\x98@'\np1385\ntp1386\nRp1387\nF1484.0\ntp1388\na(I2650000\ng1\n(g5\nS'\\xaeG\\xe1z\\x144\\x99@'\np1389\ntp1390\nRp1391\ng1\n(g5\nS'\\xaeG\\xe1z\\x144\\x99@'\np1392\ntp1393\nRp1394\nF3084.0\ntp1395\na(I2660000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xce\\x98@'\np1396\ntp1397\nRp1398\ng1394\nF2860.0\ntp1399\na(I2670000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8\\x98@'\np1400\ntp1401\nRp1402\ng1394\nF2108.0\ntp1403\na(I2680000\ng1\n(g5\nS'fffff\\xa2\\x98@'\np1404\ntp1405\nRp1406\ng1394\nF2916.0\ntp1407\na(I2690000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x95\\x98@'\np1408\ntp1409\nRp1410\ng1394\nF1796.0\ntp1411\na(I2700000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xad\\x98@'\np1412\ntp1413\nRp1414\ng1394\nF2160.0\ntp1415\na(I2710000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xa9\\x98@'\np1416\ntp1417\nRp1418\ng1394\nF1284.0\ntp1419\na(I2720000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x9e\\x98@'\np1420\ntp1421\nRp1422\ng1394\nF660.0\ntp1423\na(I2730000\ng1\n(g5\nS'fffff\\xfe\\x98@'\np1424\ntp1425\nRp1426\ng1394\nF2108.0\ntp1427\na(I2740000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeby\\x99@'\np1428\ntp1429\nRp1430\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeby\\x99@'\np1431\ntp1432\nRp1433\nF3900.0\ntp1434\na(I2750000\ng1\n(g5\nS'\\n\\xd7\\xa3p=n\\x99@'\np1435\ntp1436\nRp1437\ng1\n(g5\nS'33333\\x8b\\x99@'\np1438\ntp1439\nRp1440\nF1044.0\ntp1441\na(I2760000\ng1\n(g5\nS'fffff\\xae\\x99@'\np1442\ntp1443\nRp1444\ng1\n(g5\nS'fffff\\xae\\x99@'\np1445\ntp1446\nRp1447\nF2888.0\ntp1448\na(I2770000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xb6\\x99@'\np1449\ntp1450\nRp1451\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xb8\\x99@'\np1452\ntp1453\nRp1454\nF1140.0\ntp1455\na(I2780000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99%\\x9a@'\np1456\ntp1457\nRp1458\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99%\\x9a@'\np1459\ntp1460\nRp1461\nF3000.0\ntp1462\na(I2790000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x08\\x9a@'\np1463\ntp1464\nRp1465\ng1\n(g5\nS'\\xd7\\xa3p=\\n3\\x9a@'\np1466\ntp1467\nRp1468\nF1092.0\ntp1469\na(I2800000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fv\\x9a@'\np1470\ntp1471\nRp1472\ng1\n(g5\nS'q=\\n\\xd7\\xa3x\\x9a@'\np1473\ntp1474\nRp1475\nF2108.0\ntp1476\na(I2810000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x88\\x9a@'\np1477\ntp1478\nRp1479\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x88\\x9a@'\np1480\ntp1481\nRp1482\nF1900.0\ntp1483\na(I2820000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xa1\\x9a@'\np1484\ntp1485\nRp1486\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xa1\\x9a@'\np1487\ntp1488\nRp1489\nF2004.0\ntp1490\na(I2830000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc4\\x9a@'\np1491\ntp1492\nRp1493\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc4\\x9a@'\np1494\ntp1495\nRp1496\nF1188.0\ntp1497\na(I2840000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xee\\x9a@'\np1498\ntp1499\nRp1500\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb1\\x9b@'\np1501\ntp1502\nRp1503\nF1380.0\ntp1504\na(I2850000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x80\\x9b@'\np1505\ntp1506\nRp1507\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x80\\x9b@'\np1508\ntp1509\nRp1510\nF2972.0\ntp1511\na(I2860000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xda\\x9b@'\np1512\ntp1513\nRp1514\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xe9\\x9b@'\np1515\ntp1516\nRp1517\nF804.0\ntp1518\na(I2870000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14~\\x9b@'\np1519\ntp1520\nRp1521\ng1517\nF852.0\ntp1522\na(I2880000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xa3\\x9b@'\np1523\ntp1524\nRp1525\ng1517\nF1380.0\ntp1526\na(I2890000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xca\\x9b@'\np1527\ntp1528\nRp1529\ng1517\nF3420.0\ntp1530\na(I2900000\ng1\n(g5\nS'q=\\n\\xd7\\xa34\\x9c@'\np1531\ntp1532\nRp1533\ng1\n(g5\nS'q=\\n\\xd7\\xa34\\x9c@'\np1534\ntp1535\nRp1536\nF2888.0\ntp1537\na(I2910000\ng1\n(g5\nS'H\\xe1z\\x14\\xaec\\x9c@'\np1538\ntp1539\nRp1540\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(p\\x9c@'\np1541\ntp1542\nRp1543\nF1380.0\ntp1544\na(I2920000\ng1\n(g5\nS'33333\\xab\\x9c@'\np1545\ntp1546\nRp1547\ng1\n(g5\nS'33333\\xab\\x9c@'\np1548\ntp1549\nRp1550\nF1380.0\ntp1551\na(I2930000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xbb\\x9c@'\np1552\ntp1553\nRp1554\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc8\\x9c@'\np1555\ntp1556\nRp1557\nF1380.0\ntp1558\na(I2940000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x02\\x9d@'\np1559\ntp1560\nRp1561\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x02\\x9d@'\np1562\ntp1563\nRp1564\nF1380.0\ntp1565\na(I2950000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xc2\\x9c@'\np1566\ntp1567\nRp1568\ng1\n(g5\nS'{\\x14\\xaeG\\xe12\\x9d@'\np1569\ntp1570\nRp1571\nF1536.0\ntp1572\na(I2960000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xe2\\x9c@'\np1573\ntp1574\nRp1575\ng1571\nF3900.0\ntp1576\na(I2970000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xf1\\x9d@'\np1577\ntp1578\nRp1579\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xf1\\x9d@'\np1580\ntp1581\nRp1582\nF3480.0\ntp1583\na(I2980000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xe4\\x9d@'\np1584\ntp1585\nRp1586\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00j\\x9e@'\np1587\ntp1588\nRp1589\nF1380.0\ntp1590\na(I2990000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xa1\\x9d@'\np1591\ntp1592\nRp1593\ng1589\nF1380.0\ntp1594\na(I3000000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQP\\x9d@'\np1595\ntp1596\nRp1597\ng1589\nF2160.0\ntp1598\na(I3010000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x06\\x9e@'\np1599\ntp1600\nRp1601\ng1589\nF2160.0\ntp1602\na(I3020000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xe4\\x9e@'\np1603\ntp1604\nRp1605\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xe4\\x9e@'\np1606\ntp1607\nRp1608\nF4448.0\ntp1609\na(I3030000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eY\\x9f@'\np1610\ntp1611\nRp1612\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa\\x9f@'\np1613\ntp1614\nRp1615\nF2160.0\ntp1616\na(I3040000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb1\\x9f@'\np1617\ntp1618\nRp1619\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb1\\x9f@'\np1620\ntp1621\nRp1622\nF1692.0\ntp1623\na(I3050000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x11\\xa0@'\np1624\ntp1625\nRp1626\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x11\\xa0@'\np1627\ntp1628\nRp1629\nF3364.0\ntp1630\na(I3060000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1c\\xa0@'\np1631\ntp1632\nRp1633\ng1\n(g5\nS'\\xe1z\\x14\\xaeG/\\xa0@'\np1634\ntp1635\nRp1636\nF1952.0\ntp1637\na(I3070000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x16\\xa0@'\np1638\ntp1639\nRp1640\ng1\n(g5\nS'\\xd7\\xa3p=\\n7\\xa0@'\np1641\ntp1642\nRp1643\nF1332.0\ntp1644\na(I3080000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x07\\xa0@'\np1645\ntp1646\nRp1647\ng1643\nF1640.0\ntp1648\na(I3090000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(l\\xa0@'\np1649\ntp1650\nRp1651\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(l\\xa0@'\np1652\ntp1653\nRp1654\nF2056.0\ntp1655\na(I3100000\ng1\n(g5\nS'\\n\\xd7\\xa3p=t\\xa0@'\np1656\ntp1657\nRp1658\ng1\n(g5\nS'fffff\\x92\\xa0@'\np1659\ntp1660\nRp1661\nF1380.0\ntp1662\na(I3110000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(t\\xa0@'\np1663\ntp1664\nRp1665\ng1661\nF1332.0\ntp1666\na(I3120000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xbe\\xa0@'\np1667\ntp1668\nRp1669\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xbe\\xa0@'\np1670\ntp1671\nRp1672\nF4740.0\ntp1673\na(I3130000\ng1\n(g5\nS'fffff)\\xa1@'\np1674\ntp1675\nRp1676\ng1\n(g5\nS'fffff)\\xa1@'\np1677\ntp1678\nRp1679\nF3840.0\ntp1680\na(I3140000\ng1\n(g5\nS'\\xa4p=\\n\\xd7;\\xa1@'\np1681\ntp1682\nRp1683\ng1\n(g5\nS'\\xa4p=\\n\\xd7;\\xa1@'\np1684\ntp1685\nRp1686\nF4478.0\ntp1687\na(I3150000\ng1\n(g5\nS'fffff\\xa6\\xa1@'\np1688\ntp1689\nRp1690\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xaf\\xa1@'\np1691\ntp1692\nRp1693\nF1692.0\ntp1694\na(I3160000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xee\\xa1@'\np1695\ntp1696\nRp1697\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xee\\xa1@'\np1698\ntp1699\nRp1700\nF4350.0\ntp1701\na(I3170000\ng1\n(g5\nS'33333|\\xa2@'\np1702\ntp1703\nRp1704\ng1\n(g5\nS'33333|\\xa2@'\np1705\ntp1706\nRp1707\nF5474.0\ntp1708\na(I3180000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xb9\\xa2@'\np1709\ntp1710\nRp1711\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xb9\\xa2@'\np1712\ntp1713\nRp1714\nF2860.0\ntp1715\na(I3190000\ng1\n(g5\nS'\\xd7\\xa3p=\\n)\\xa3@'\np1716\ntp1717\nRp1718\ng1\n(g5\nS'\\xd7\\xa3p=\\n)\\xa3@'\np1719\ntp1720\nRp1721\nF5268.0\ntp1722\na(I3200000\ng1\n(g5\nS'\\n\\xd7\\xa3p={\\xa3@'\np1723\ntp1724\nRp1725\ng1\n(g5\nS'\\n\\xd7\\xa3p={\\xa3@'\np1726\ntp1727\nRp1728\nF3660.0\ntp1729\na(I3210000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x9a\\xa3@'\np1730\ntp1731\nRp1732\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x9a\\xa3@'\np1733\ntp1734\nRp1735\nF2664.0\ntp1736\na(I3220000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x10\\xa4@'\np1737\ntp1738\nRp1739\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x10\\xa4@'\np1740\ntp1741\nRp1742\nF2328.0\ntp1743\na(I3230000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fi\\xa4@'\np1744\ntp1745\nRp1746\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fi\\xa4@'\np1747\ntp1748\nRp1749\nF2552.0\ntp1750\na(I3240000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe8\\xa4@'\np1751\ntp1752\nRp1753\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe8\\xa4@'\np1754\ntp1755\nRp1756\nF2160.0\ntp1757\na(I3250000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xe0\\xa4@'\np1758\ntp1759\nRp1760\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xee\\xa4@'\np1761\ntp1762\nRp1763\nF2720.0\ntp1764\na(I3260000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85 \\xa5@'\np1765\ntp1766\nRp1767\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85 \\xa5@'\np1768\ntp1769\nRp1770\nF2440.0\ntp1771\na(I3270000\ng1\n(g5\nS'\\x14\\xaeG\\xe1za\\xa5@'\np1772\ntp1773\nRp1774\ng1\n(g5\nS'\\x14\\xaeG\\xe1za\\xa5@'\np1775\ntp1776\nRp1777\nF4156.0\ntp1778\na(I3280000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xdb\\xa5@'\np1779\ntp1780\nRp1781\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xdb\\xa5@'\np1782\ntp1783\nRp1784\nF4320.0\ntp1785\na(I3290000\ng1\n(g5\nS'H\\xe1z\\x14\\xae(\\xa6@'\np1786\ntp1787\nRp1788\ng1\n(g5\nS'H\\xe1z\\x14\\xae(\\xa6@'\np1789\ntp1790\nRp1791\nF4156.0\ntp1792\na(I3300000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xf5\\xa6@'\np1793\ntp1794\nRp1795\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xf5\\xa6@'\np1796\ntp1797\nRp1798\nF5734.0\ntp1799\na(I3310000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eT\\xa7@'\np1800\ntp1801\nRp1802\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eT\\xa7@'\np1803\ntp1804\nRp1805\nF3420.0\ntp1806\na(I3320000\ng1\n(g5\nS'q=\\n\\xd7\\xa3]\\xa7@'\np1807\ntp1808\nRp1809\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebd\\xa7@'\np1810\ntp1811\nRp1812\nF2440.0\ntp1813\na(I3330000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xb9\\xa7@'\np1814\ntp1815\nRp1816\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xb9\\xa7@'\np1817\ntp1818\nRp1819\nF2004.0\ntp1820\na(I3340000\ng1\n(g5\nS'=\\n\\xd7\\xa3p/\\xa8@'\np1821\ntp1822\nRp1823\ng1\n(g5\nS'=\\n\\xd7\\xa3p/\\xa8@'\np1824\ntp1825\nRp1826\nF5602.0\ntp1827\na(I3350000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x19\\xa8@'\np1828\ntp1829\nRp1830\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQP\\xa8@'\np1831\ntp1832\nRp1833\nF3000.0\ntp1834\na(I3360000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x03\\xa8@'\np1835\ntp1836\nRp1837\ng1833\nF1744.0\ntp1838\na(I3370000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fs\\xa8@'\np1839\ntp1840\nRp1841\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fs\\xa8@'\np1842\ntp1843\nRp1844\nF4320.0\ntp1845\na(I3380000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xe1\\xa8@'\np1846\ntp1847\nRp1848\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xe1\\xa8@'\np1849\ntp1850\nRp1851\nF3900.0\ntp1852\na(I3390000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x8d\\xa9@'\np1853\ntp1854\nRp1855\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x8d\\xa9@'\np1856\ntp1857\nRp1858\nF5508.0\ntp1859\na(I3400000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xb4\\xa9@'\np1860\ntp1861\nRp1862\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xbb\\xa9@'\np1863\ntp1864\nRp1865\nF1796.0\ntp1866\na(I3410000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x8c\\xa9@'\np1867\ntp1868\nRp1869\ng1865\nF4734.0\ntp1870\na(I3420000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xab\\xa9@'\np1871\ntp1872\nRp1873\ng1865\nF4960.0\ntp1874\na(I3430000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xff\\xa9@'\np1875\ntp1876\nRp1877\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xff\\xa9@'\np1878\ntp1879\nRp1880\nF5310.0\ntp1881\na(I3440000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x02\\xaa@'\np1882\ntp1883\nRp1884\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x02\\xaa@'\np1885\ntp1886\nRp1887\nF2888.0\ntp1888\na(I3450000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x1f\\xaa@'\np1889\ntp1890\nRp1891\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x1f\\xaa@'\np1892\ntp1893\nRp1894\nF3000.0\ntp1895\na(I3460000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa0\\xaa@'\np1896\ntp1897\nRp1898\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa0\\xaa@'\np1899\ntp1900\nRp1901\nF5340.0\ntp1902\na(I3470000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xcf\\xaa@'\np1903\ntp1904\nRp1905\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xcf\\xaa@'\np1906\ntp1907\nRp1908\nF1848.0\ntp1909\na(I3480000\ng1\n(g5\nS'\\n\\xd7\\xa3p=:\\xab@'\np1910\ntp1911\nRp1912\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(N\\xab@'\np1913\ntp1914\nRp1915\nF2004.0\ntp1916\na(I3490000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xc0\\xab@'\np1917\ntp1918\nRp1919\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xc0\\xab@'\np1920\ntp1921\nRp1922\nF6596.0\ntp1923\na(I3500000\ng1\n(g5\nS\")\\\\\\x8f\\xc2\\xf5'\\xac@\"\np1924\ntp1925\nRp1926\ng1\n(g5\nS\")\\\\\\x8f\\xc2\\xf5'\\xac@\"\np1927\ntp1928\nRp1929\nF5190.0\ntp1930\na(I3510000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xd9\\xac@'\np1931\ntp1932\nRp1933\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xd9\\xac@'\np1934\ntp1935\nRp1936\nF5676.0\ntp1937\na(I3520000\ng1\n(g5\nS'33333\\x0e\\xad@'\np1938\ntp1939\nRp1940\ng1\n(g5\nS'33333\\x0e\\xad@'\np1941\ntp1942\nRp1943\nF4320.0\ntp1944\na(I3530000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xf9\\xad@'\np1945\ntp1946\nRp1947\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xf9\\xad@'\np1948\ntp1949\nRp1950\nF5662.0\ntp1951\na(I3540000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zp\\xad@'\np1952\ntp1953\nRp1954\ng1950\nF2160.0\ntp1955\na(I3550000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85{\\xad@'\np1956\ntp1957\nRp1958\ng1950\nF1640.0\ntp1959\na(I3560000\ng1\n(g5\nS'fffffy\\xad@'\np1960\ntp1961\nRp1962\ng1950\nF4050.0\ntp1963\na(I3570000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb4\\xad@'\np1964\ntp1965\nRp1966\ng1950\nF5884.0\ntp1967\na(I3580000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xf2\\xad@'\np1968\ntp1969\nRp1970\ng1950\nF4604.0\ntp1971\na(I3590000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ \\xae@'\np1972\ntp1973\nRp1974\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ \\xae@'\np1975\ntp1976\nRp1977\nF5312.0\ntp1978\na(I3600000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xf5\\xad@'\np1979\ntp1980\nRp1981\ng1977\nF5312.0\ntp1982\na(I3610000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xf0\\xad@'\np1983\ntp1984\nRp1985\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ&\\xae@'\np1986\ntp1987\nRp1988\nF3000.0\ntp1989\na(I3620000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xb1\\xad@'\np1990\ntp1991\nRp1992\ng1988\nF4540.0\ntp1993\na(I3630000\ng1\n(g5\nS'33333\\xbe\\xad@'\np1994\ntp1995\nRp1996\ng1988\nF3900.0\ntp1997\na(I3640000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xf9\\xad@'\np1998\ntp1999\nRp2000\ng1988\nF3420.0\ntp2001\na(I3650000\ng1\n(g5\nS\"{\\x14\\xaeG\\xe1'\\xae@\"\np2002\ntp2003\nRp2004\ng1\n(g5\nS'\\xd7\\xa3p=\\n(\\xae@'\np2005\ntp2006\nRp2007\nF5718.0\ntp2008\na(I3660000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99H\\xae@'\np2009\ntp2010\nRp2011\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99H\\xae@'\np2012\ntp2013\nRp2014\nF4640.0\ntp2015\na(I3670000\ng1\n(g5\nS'fffff\\x8a\\xae@'\np2016\ntp2017\nRp2018\ng1\n(g5\nS'fffff\\x8a\\xae@'\np2019\ntp2020\nRp2021\nF5446.0\ntp2022\na(I3680000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xd1\\xae@'\np2023\ntp2024\nRp2025\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xd1\\xae@'\np2026\ntp2027\nRp2028\nF5726.0\ntp2029\na(I3690000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xd8\\xae@'\np2030\ntp2031\nRp2032\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xd8\\xae@'\np2033\ntp2034\nRp2035\nF4604.0\ntp2036\na(I3700000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xd6\\xae@'\np2037\ntp2038\nRp2039\ng2035\nF4140.0\ntp2040\na(I3710000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x97\\xae@'\np2041\ntp2042\nRp2043\ng1\n(g5\nS'33333\\x13\\xaf@'\np2044\ntp2045\nRp2046\nF1952.0\ntp2047\na(I3720000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xc2\\xae@'\np2048\ntp2049\nRp2050\ng2046\nF5786.0\ntp2051\na(I3730000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xb7\\xae@'\np2052\ntp2053\nRp2054\ng2046\nF3060.0\ntp2055\na(I3740000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x96\\xaf@'\np2056\ntp2057\nRp2058\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x96\\xaf@'\np2059\ntp2060\nRp2061\nF8512.0\ntp2062\na(I3750000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85c\\xaf@'\np2063\ntp2064\nRp2065\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x9b\\xaf@'\np2066\ntp2067\nRp2068\nF1952.0\ntp2069\na(I3760000\ng1\n(g5\nS'33333\\x8d\\xaf@'\np2070\ntp2071\nRp2072\ng2068\nF6082.0\ntp2073\na(I3770000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x9a\\xaf@'\np2074\ntp2075\nRp2076\ng2068\nF5378.0\ntp2077\na(I3780000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x90\\xaf@'\np2078\ntp2079\nRp2080\ng2068\nF3900.0\ntp2081\na(I3790000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x9d\\xaf@'\np2082\ntp2083\nRp2084\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xb7\\xaf@'\np2085\ntp2086\nRp2087\nF3000.0\ntp2088\na(I3800000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xed\\xaf@'\np2089\ntp2090\nRp2091\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xed\\xaf@'\np2092\ntp2093\nRp2094\nF6576.0\ntp2095\na(I3810000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xbc\\xaf@'\np2096\ntp2097\nRp2098\ng2094\nF4960.0\ntp2099\na(I3820000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f\\x04\\xb0@'\np2100\ntp2101\nRp2102\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f\\x04\\xb0@'\np2103\ntp2104\nRp2105\nF3900.0\ntp2106\na(I3830000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xe5\\xaf@'\np2107\ntp2108\nRp2109\ng1\n(g5\nS'33333\\x0e\\xb0@'\np2110\ntp2111\nRp2112\nF2004.0\ntp2113\na(I3840000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xc0\\xaf@'\np2114\ntp2115\nRp2116\ng2112\nF3660.0\ntp2117\na(I3850000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xb4\\xaf@'\np2118\ntp2119\nRp2120\ng2112\nF3900.0\ntp2121\na(I3860000\ng1\n(g5\nS\"=\\n\\xd7\\xa3p'\\xb0@\"\np2122\ntp2123\nRp2124\ng1\n(g5\nS\"=\\n\\xd7\\xa3p'\\xb0@\"\np2125\ntp2126\nRp2127\nF4156.0\ntp2128\na(I3870000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd16\\xb0@'\np2129\ntp2130\nRp2131\ng1\n(g5\nS')\\\\\\x8f\\xc2uE\\xb0@'\np2132\ntp2133\nRp2134\nF1536.0\ntp2135\na(I3880000\ng1\n(g5\nS'H\\xe1z\\x14\\xae2\\xb0@'\np2136\ntp2137\nRp2138\ng2134\nF4448.0\ntp2139\na(I3890000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0fg\\xb0@'\np2140\ntp2141\nRp2142\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0fg\\xb0@'\np2143\ntp2144\nRp2145\nF6894.0\ntp2146\na(I3900000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x83\\xb0@'\np2147\ntp2148\nRp2149\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x83\\xb0@'\np2150\ntp2151\nRp2152\nF6978.0\ntp2153\na(I3910000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xa3\\xb0@'\np2154\ntp2155\nRp2156\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xa3\\xb0@'\np2157\ntp2158\nRp2159\nF6164.0\ntp2160\na(I3920000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94[\\xb0@'\np2161\ntp2162\nRp2163\ng2159\nF2160.0\ntp2164\na(I3930000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8K\\xb0@'\np2165\ntp2166\nRp2167\ng2159\nF4350.0\ntp2168\na(I3940000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc7h\\xb0@'\np2169\ntp2170\nRp2171\ng2159\nF4996.0\ntp2172\na(I3950000\ng1\n(g5\nS'\\n\\xd7\\xa3p=v\\xb0@'\np2173\ntp2174\nRp2175\ng2159\nF4768.0\ntp2176\na(I3960000\ng1\n(g5\nS'H\\xe1z\\x14.g\\xb0@'\np2177\ntp2178\nRp2179\ng2159\nF4092.0\ntp2180\na(I3970000\ng1\n(g5\nS')\\\\\\x8f\\xc2u\\x91\\xb0@'\np2181\ntp2182\nRp2183\ng2159\nF3900.0\ntp2184\na(I3980000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\xae\\xb0@'\np2185\ntp2186\nRp2187\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\xae\\xb0@'\np2188\ntp2189\nRp2190\nF6780.0\ntp2191\na(I3990000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\xb0@'\np2192\ntp2193\nRp2194\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\xb0@'\np2195\ntp2196\nRp2197\nF4220.0\ntp2198\na(I4000000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x0f\\xb1@'\np2199\ntp2200\nRp2201\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x0f\\xb1@'\np2202\ntp2203\nRp2204\nF3720.0\ntp2205\na(I4010000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0\\x1a\\xb1@'\np2206\ntp2207\nRp2208\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x1b\\xb1@'\np2209\ntp2210\nRp2211\nF4670.0\ntp2212\na(I4020000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z)\\xb1@'\np2213\ntp2214\nRp2215\ng1\n(g5\nS'q=\\n\\xd7#A\\xb1@'\np2216\ntp2217\nRp2218\nF2944.0\ntp2219\na(I4030000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99G\\xb1@'\np2220\ntp2221\nRp2222\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99G\\xb1@'\np2223\ntp2224\nRp2225\nF5440.0\ntp2226\na(I4040000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa=\\xb1@'\np2227\ntp2228\nRp2229\ng1\n(g5\nS'\\xaeG\\xe1z\\x94H\\xb1@'\np2230\ntp2231\nRp2232\nF4220.0\ntp2233\na(I4050000\ng1\n(g5\nS'{\\x14\\xaeGaS\\xb1@'\np2234\ntp2235\nRp2236\ng1\n(g5\nS'{\\x14\\xaeGaS\\xb1@'\np2237\ntp2238\nRp2239\nF5952.0\ntp2240\na(I4060000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x85\\xb1@'\np2241\ntp2242\nRp2243\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x85\\xb1@'\np2244\ntp2245\nRp2246\nF5064.0\ntp2247\na(I4070000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\xaa\\xb1@'\np2248\ntp2249\nRp2250\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\xaa\\xb1@'\np2251\ntp2252\nRp2253\nF6562.0\ntp2254\na(I4080000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xe4\\xb1@'\np2255\ntp2256\nRp2257\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xe4\\xb1@'\np2258\ntp2259\nRp2260\nF6840.0\ntp2261\na(I4090000\ng1\n(g5\nS'R\\xb8\\x1e\\x85k\\x11\\xb2@'\np2262\ntp2263\nRp2264\ng1\n(g5\nS'R\\xb8\\x1e\\x85k\\x11\\xb2@'\np2265\ntp2266\nRp2267\nF4832.0\ntp2268\na(I4100000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xe5\\xb1@'\np2269\ntp2270\nRp2271\ng2267\nF2160.0\ntp2272\na(I4110000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xf5\\xb1@'\np2273\ntp2274\nRp2275\ng2267\nF5084.0\ntp2276\na(I4120000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xef\\xb1@'\np2277\ntp2278\nRp2279\ng2267\nF4410.0\ntp2280\na(I4130000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x19\\x03\\xb2@'\np2281\ntp2282\nRp2283\ng2267\nF6780.0\ntp2284\na(I4140000\ng1\n(g5\nS'H\\xe1z\\x14\\xae&\\xb2@'\np2285\ntp2286\nRp2287\ng1\n(g5\nS'H\\xe1z\\x14\\xae&\\xb2@'\np2288\ntp2289\nRp2290\nF7834.0\ntp2291\na(I4150000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99/\\xb2@'\np2292\ntp2293\nRp2294\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99/\\xb2@'\np2295\ntp2296\nRp2297\nF4576.0\ntp2298\na(I4160000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xbdQ\\xb2@'\np2299\ntp2300\nRp2301\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xbdQ\\xb2@'\np2302\ntp2303\nRp2304\nF8214.0\ntp2305\na(I4170000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1M\\xb2@'\np2306\ntp2307\nRp2308\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8i\\xb2@'\np2309\ntp2310\nRp2311\nF3240.0\ntp2312\na(I4180000\ng1\n(g5\nS'q=\\n\\xd7\\xa3!\\xb2@'\np2313\ntp2314\nRp2315\ng2311\nF4092.0\ntp2316\na(I4190000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x14\\xb2@'\np2317\ntp2318\nRp2319\ng2311\nF4704.0\ntp2320\na(I4200000\ng1\n(g5\nS'\\xa4p=\\n\\xd7V\\xb2@'\np2321\ntp2322\nRp2323\ng2311\nF5408.0\ntp2324\na(I4210000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccn\\xb2@'\np2325\ntp2326\nRp2327\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x83\\xb2@'\np2328\ntp2329\nRp2330\nF4050.0\ntp2331\na(I4220000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1\\x87\\xb2@'\np2332\ntp2333\nRp2334\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1\\x87\\xb2@'\np2335\ntp2336\nRp2337\nF6342.0\ntp2338\na(I4230000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1\\xeb\\xb2@'\np2339\ntp2340\nRp2341\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1\\xeb\\xb2@'\np2342\ntp2343\nRp2344\nF6728.0\ntp2345\na(I4240000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0\\x04\\xb3@'\np2346\ntp2347\nRp2348\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xbd\\t\\xb3@'\np2349\ntp2350\nRp2351\nF5700.0\ntp2352\na(I4250000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x055\\xb3@'\np2353\ntp2354\nRp2355\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x055\\xb3@'\np2356\ntp2357\nRp2358\nF6810.0\ntp2359\na(I4260000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdcI\\xb3@'\np2360\ntp2361\nRp2362\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdcI\\xb3@'\np2363\ntp2364\nRp2365\nF8660.0\ntp2366\na(I4270000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdcV\\xb3@'\np2367\ntp2368\nRp2369\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdcV\\xb3@'\np2370\ntp2371\nRp2372\nF5744.0\ntp2373\na(I4280000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1M\\xb3@'\np2374\ntp2375\nRp2376\ng2372\nF4260.0\ntp2377\na(I4290000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccLo\\xb3@'\np2378\ntp2379\nRp2380\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccLo\\xb3@'\np2381\ntp2382\nRp2383\nF5926.0\ntp2384\na(I4300000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xb6\\xb3@'\np2385\ntp2386\nRp2387\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xb6\\xb3@'\np2388\ntp2389\nRp2390\nF4200.0\ntp2391\na(I4310000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xe0\\xb3@'\np2392\ntp2393\nRp2394\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xe0\\xb3@'\np2395\ntp2396\nRp2397\nF2832.0\ntp2398\na(I4320000\ng1\n(g5\nS\"=\\n\\xd7\\xa3p'\\xb4@\"\np2399\ntp2400\nRp2401\ng1\n(g5\nS\"=\\n\\xd7\\xa3p'\\xb4@\"\np2402\ntp2403\nRp2404\nF5200.0\ntp2405\na(I4330000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ7\\xb4@'\np2406\ntp2407\nRp2408\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc7;\\xb4@'\np2409\ntp2410\nRp2411\nF5054.0\ntp2412\na(I4340000\ng1\n(g5\nS'\\xa4p=\\n\\xd7Z\\xb4@'\np2413\ntp2414\nRp2415\ng1\n(g5\nS'\\xa4p=\\n\\xd7Z\\xb4@'\np2416\ntp2417\nRp2418\nF5820.0\ntp2419\na(I4350000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f`\\xb4@'\np2420\ntp2421\nRp2422\ng1\n(g5\nS'\\x14\\xaeG\\xe1za\\xb4@'\np2423\ntp2424\nRp2425\nF5378.0\ntp2426\na(I4360000\ng1\n(g5\nS'ffff\\xe6\\x93\\xb4@'\np2427\ntp2428\nRp2429\ng1\n(g5\nS'ffff\\xe6\\x93\\xb4@'\np2430\ntp2431\nRp2432\nF5484.0\ntp2433\na(I4370000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1\\xde\\xb4@'\np2434\ntp2435\nRp2436\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1\\xde\\xb4@'\np2437\ntp2438\nRp2439\nF10302.0\ntp2440\na(I4380000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x8a\\xb4@'\np2441\ntp2442\nRp2443\ng2439\nF1900.0\ntp2444\na(I4390000\ng1\n(g5\nS'33333\\xa3\\xb4@'\np2445\ntp2446\nRp2447\ng2439\nF7182.0\ntp2448\na(I4400000\ng1\n(g5\nS'33333\\xb9\\xb4@'\np2449\ntp2450\nRp2451\ng2439\nF6100.0\ntp2452\na(I4410000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xf6\\xb4@'\np2453\ntp2454\nRp2455\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xfe\\xb4@'\np2456\ntp2457\nRp2458\nF4542.0\ntp2459\na(I4420000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xef\\xb4@'\np2460\ntp2461\nRp2462\ng2458\nF4156.0\ntp2463\na(I4430000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc$\\xb5@'\np2464\ntp2465\nRp2466\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc$\\xb5@'\np2467\ntp2468\nRp2469\nF10320.0\ntp2470\na(I4440000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ5\\xb5@'\np2471\ntp2472\nRp2473\ng1\n(g5\nS'fffffB\\xb5@'\np2474\ntp2475\nRp2476\nF4732.0\ntp2477\na(I4450000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcci\\xb5@'\np2478\ntp2479\nRp2480\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcci\\xb5@'\np2481\ntp2482\nRp2483\nF7800.0\ntp2484\na(I4460000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8\\x9b\\xb5@'\np2485\ntp2486\nRp2487\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05\\xa0\\xb5@'\np2488\ntp2489\nRp2490\nF3420.0\ntp2491\na(I4470000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0s\\xb5@'\np2492\ntp2493\nRp2494\ng2490\nF5602.0\ntp2495\na(I4480000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x88\\xb5@'\np2496\ntp2497\nRp2498\ng2490\nF4860.0\ntp2499\na(I4490000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb0\\xb5@'\np2500\ntp2501\nRp2502\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb0\\xb5@'\np2503\ntp2504\nRp2505\nF5540.0\ntp2506\na(I4500000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94\\x86\\xb5@'\np2507\ntp2508\nRp2509\ng2505\nF5340.0\ntp2510\na(I4510000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\xa8\\xb5@'\np2511\ntp2512\nRp2513\ng2505\nF9486.0\ntp2514\na(I4520000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0\\x98\\xb5@'\np2515\ntp2516\nRp2517\ng2505\nF6732.0\ntp2518\na(I4530000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xaf\\xb5@'\np2519\ntp2520\nRp2521\ng2505\nF5744.0\ntp2522\na(I4540000\ng1\n(g5\nS')\\\\\\x8f\\xc2u\\x96\\xb5@'\np2523\ntp2524\nRp2525\ng2505\nF4560.0\ntp2526\na(I4550000\ng1\n(g5\nS')\\\\\\x8f\\xc2u\\x9c\\xb5@'\np2527\ntp2528\nRp2529\ng2505\nF4320.0\ntp2530\na(I4560000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xd4\\xb5@'\np2531\ntp2532\nRp2533\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xe3\\xb5@'\np2534\ntp2535\nRp2536\nF5024.0\ntp2537\na(I4570000\ng1\n(g5\nS'33333\\xd0\\xb5@'\np2538\ntp2539\nRp2540\ng2536\nF7164.0\ntp2541\na(I4580000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f\\xd9\\xb5@'\np2542\ntp2543\nRp2544\ng1\n(g5\nS'{\\x14\\xaeGa\\xea\\xb5@'\np2545\ntp2546\nRp2547\nF6300.0\ntp2548\na(I4590000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xf9\\xb5@'\np2549\ntp2550\nRp2551\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xf9\\xb5@'\np2552\ntp2553\nRp2554\nF3060.0\ntp2555\na(I4600000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccL\\x05\\xb6@'\np2556\ntp2557\nRp2558\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccL\\x05\\xb6@'\np2559\ntp2560\nRp2561\nF5154.0\ntp2562\na(I4610000\ng1\n(g5\nS'fffff\\x01\\xb6@'\np2563\ntp2564\nRp2565\ng1\n(g5\nS'\\xf6(\\\\\\x8fB\\x07\\xb6@'\np2566\ntp2567\nRp2568\nF4478.0\ntp2569\na(I4620000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccL2\\xb6@'\np2570\ntp2571\nRp2572\ng1\n(g5\nS'ffff\\xe67\\xb6@'\np2573\ntp2574\nRp2575\nF4640.0\ntp2576\na(I4630000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9eE\\xb6@'\np2577\ntp2578\nRp2579\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9eE\\xb6@'\np2580\ntp2581\nRp2582\nF8712.0\ntp2583\na(I4640000\ng1\n(g5\nS'q=\\n\\xd7#C\\xb6@'\np2584\ntp2585\nRp2586\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ]\\xb6@'\np2587\ntp2588\nRp2589\nF5216.0\ntp2590\na(I4650000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8n\\xb6@'\np2591\ntp2592\nRp2593\ng1\n(g5\nS'\\x1f\\x85\\xebQ8n\\xb6@'\np2594\ntp2595\nRp2596\nF5700.0\ntp2597\na(I4660000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0fS\\xb6@'\np2598\ntp2599\nRp2600\ng2596\nF5756.0\ntp2601\na(I4670000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x82\\xb6@'\np2602\ntp2603\nRp2604\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x82\\xb6@'\np2605\ntp2606\nRp2607\nF6062.0\ntp2608\na(I4680000\ng1\n(g5\nS'{\\x14\\xaeGa\\x94\\xb6@'\np2609\ntp2610\nRp2611\ng1\n(g5\nS'{\\x14\\xaeGa\\x94\\xb6@'\np2612\ntp2613\nRp2614\nF5410.0\ntp2615\na(I4690000\ng1\n(g5\nS')\\\\\\x8f\\xc2u\\xc2\\xb6@'\np2616\ntp2617\nRp2618\ng1\n(g5\nS'\\xa4p=\\nW\\xf9\\xb6@'\np2619\ntp2620\nRp2621\nF1796.0\ntp2622\na(I4700000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xca\\xb6@'\np2623\ntp2624\nRp2625\ng2621\nF7098.0\ntp2626\na(I4710000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xd3\\xb6@'\np2627\ntp2628\nRp2629\ng2621\nF5280.0\ntp2630\na(I4720000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94\\xb8\\xb6@'\np2631\ntp2632\nRp2633\ng2621\nF2552.0\ntp2634\na(I4730000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x97\\xb6@'\np2635\ntp2636\nRp2637\ng2621\nF6096.0\ntp2638\na(I4740000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94\\x9e\\xb6@'\np2639\ntp2640\nRp2641\ng2621\nF4796.0\ntp2642\na(I4750000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x9a\\xb6@'\np2643\ntp2644\nRp2645\ng2621\nF4576.0\ntp2646\na(I4760000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccL\\x99\\xb6@'\np2647\ntp2648\nRp2649\ng2621\nF6732.0\ntp2650\na(I4770000\ng1\n(g5\nS'fffff\\xf4\\xb6@'\np2651\ntp2652\nRp2653\ng2621\nF5880.0\ntp2654\na(I4780000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xef\\xb6@'\np2655\ntp2656\nRp2657\ng2621\nF5280.0\ntp2658\na(I4790000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x1a\\xb7@'\np2659\ntp2660\nRp2661\ng1\n(g5\nS\"H\\xe1z\\x14.'\\xb7@\"\np2662\ntp2663\nRp2664\nF4412.0\ntp2665\na(I4800000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f\\xfd\\xb6@'\np2666\ntp2667\nRp2668\ng2664\nF3300.0\ntp2669\na(I4810000\ng1\n(g5\nS')\\\\\\x8f\\xc2u\\x13\\xb7@'\np2670\ntp2671\nRp2672\ng2664\nF10230.0\ntp2673\na(I4820000\ng1\n(g5\nS'H\\xe1z\\x14\\xae*\\xb7@'\np2674\ntp2675\nRp2676\ng1\n(g5\nS'H\\xe1z\\x14\\xae*\\xb7@'\np2677\ntp2678\nRp2679\nF5154.0\ntp2680\na(I4830000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1\\x1a\\xb7@'\np2681\ntp2682\nRp2683\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc26\\xb7@'\np2684\ntp2685\nRp2686\nF3140.0\ntp2687\na(I4840000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x0e\\xb7@'\np2688\ntp2689\nRp2690\ng2686\nF3360.0\ntp2691\na(I4850000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xe9\\xb6@'\np2692\ntp2693\nRp2694\ng2686\nF3000.0\ntp2695\na(I4860000\ng1\n(g5\nS'fffff\\xeb\\xb6@'\np2696\ntp2697\nRp2698\ng2686\nF5246.0\ntp2699\na(I4870000\ng1\n(g5\nS'fffff\\xb6\\xb6@'\np2700\ntp2701\nRp2702\ng2686\nF4448.0\ntp2703\na(I4880000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xdf\\xb6@'\np2704\ntp2705\nRp2706\ng2686\nF8224.0\ntp2707\na(I4890000\ng1\n(g5\nS'\\xf6(\\\\\\x8fBK\\xb7@'\np2708\ntp2709\nRp2710\ng1\n(g5\nS'\\xf6(\\\\\\x8fBK\\xb7@'\np2711\ntp2712\nRp2713\nF8024.0\ntp2714\na(I4900000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99=\\xb7@'\np2715\ntp2716\nRp2717\ng2713\nF5820.0\ntp2718\na(I4910000\ng1\n(g5\nS'q=\\n\\xd7#\\xe0\\xb6@'\np2719\ntp2720\nRp2721\ng2713\nF3600.0\ntp2722\na(I4920000\ng1\n(g5\nS'33333\\xde\\xb6@'\np2723\ntp2724\nRp2725\ng2713\nF6002.0\ntp2726\na(I4930000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x80\\x9a\\xb6@'\np2727\ntp2728\nRp2729\ng2713\nF3840.0\ntp2730\na(I4940000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8\\xc7\\xb6@'\np2731\ntp2732\nRp2733\ng2713\nF5340.0\ntp2734\na(I4950000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc7\\xd6\\xb6@'\np2735\ntp2736\nRp2737\ng2713\nF7188.0\ntp2738\na(I4960000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xea\\xb6@'\np2739\ntp2740\nRp2741\ng2713\nF5280.0\ntp2742\na(I4970000\ng1\n(g5\nS'q=\\n\\xd7#*\\xb7@'\np2743\ntp2744\nRp2745\ng2713\nF6096.0\ntp2746\na(I4980000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1J\\xb7@'\np2747\ntp2748\nRp2749\ng2713\nF8870.0\ntp2750\na(I4990000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14;\\xb7@'\np2751\ntp2752\nRp2753\ng2713\nF5152.0\ntp2754\na(I5000000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xbdI\\xb7@'\np2755\ntp2756\nRp2757\ng1\n(g5\nS'\\xaeG\\xe1z\\x94W\\xb7@'\np2758\ntp2759\nRp2760\nF4156.0\ntp2761\na(I5010000\ng1\n(g5\nS'{\\x14\\xaeGan\\xb7@'\np2762\ntp2763\nRp2764\ng1\n(g5\nS'{\\x14\\xaeGan\\xb7@'\np2765\ntp2766\nRp2767\nF5824.0\ntp2768\na(I5020000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc7n\\xb7@'\np2769\ntp2770\nRp2771\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x99\\xb7@'\np2772\ntp2773\nRp2774\nF5212.0\ntp2775\na(I5030000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x9b\\xb7@'\np2776\ntp2777\nRp2778\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x9b\\xb7@'\np2779\ntp2780\nRp2781\nF7446.0\ntp2782\na(I5040000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f\\xb8\\xb7@'\np2783\ntp2784\nRp2785\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f\\xb8\\xb7@'\np2786\ntp2787\nRp2788\nF4508.0\ntp2789\na(I5050000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xcb\\xb7@'\np2790\ntp2791\nRp2792\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xde\\xb7@'\np2793\ntp2794\nRp2795\nF3840.0\ntp2796\na(I5060000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xcf\\xb7@'\np2797\ntp2798\nRp2799\ng2795\nF5200.0\ntp2800\na(I5070000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8\\t\\xb8@'\np2801\ntp2802\nRp2803\ng1\n(g5\nS'\\x1f\\x85\\xebQ8\\t\\xb8@'\np2804\ntp2805\nRp2806\nF10290.0\ntp2807\na(I5080000\ng1\n(g5\nS'fffff\\x0f\\xb8@'\np2808\ntp2809\nRp2810\ng1\n(g5\nS'\\xf6(\\\\\\x8fBe\\xb8@'\np2811\ntp2812\nRp2813\nF3240.0\ntp2814\na(I5090000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x1e\\xb8@'\np2815\ntp2816\nRp2817\ng2813\nF8660.0\ntp2818\na(I5100000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x0f\\xb8@'\np2819\ntp2820\nRp2821\ng2813\nF7998.0\ntp2822\na(I5110000\ng1\n(g5\nS'\\n\\xd7\\xa3p=J\\xb8@'\np2823\ntp2824\nRp2825\ng2813\nF9960.0\ntp2826\na(I5120000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x92\\xb8@'\np2827\ntp2828\nRp2829\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x92\\xb8@'\np2830\ntp2831\nRp2832\nF10260.0\ntp2833\na(I5130000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\xfa\\xb8@'\np2834\ntp2835\nRp2836\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\xfa\\xb8@'\np2837\ntp2838\nRp2839\nF6852.0\ntp2840\na(I5140000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05*\\xb9@'\np2841\ntp2842\nRp2843\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05*\\xb9@'\np2844\ntp2845\nRp2846\nF9870.0\ntp2847\na(I5150000\ng1\n(g5\nS'H\\xe1z\\x14\\xae`\\xb9@'\np2848\ntp2849\nRp2850\ng1\n(g5\nS'H\\xe1z\\x14\\xae`\\xb9@'\np2851\ntp2852\nRp2853\nF9030.0\ntp2854\na(I5160000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\T\\xb9@'\np2855\ntp2856\nRp2857\ng2853\nF8628.0\ntp2858\na(I5170000\ng1\n(g5\nS'\\xd7\\xa3p=\\x8a}\\xb9@'\np2859\ntp2860\nRp2861\ng1\n(g5\nS'\\xd7\\xa3p=\\x8a}\\xb9@'\np2862\ntp2863\nRp2864\nF12510.0\ntp2865\na(I5180000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x86\\xb9@'\np2866\ntp2867\nRp2868\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x86\\xb9@'\np2869\ntp2870\nRp2871\nF8232.0\ntp2872\na(I5190000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94\\x8f\\xb9@'\np2873\ntp2874\nRp2875\ng1\n(g5\nS'\\xaeG\\xe1z\\x94\\x8f\\xb9@'\np2876\ntp2877\nRp2878\nF6456.0\ntp2879\na(I5200000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xd3\\xb9@'\np2880\ntp2881\nRp2882\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xd3\\xb9@'\np2883\ntp2884\nRp2885\nF8388.0\ntp2886\na(I5210000\ng1\n(g5\nS'ffff\\xe6\\xee\\xb9@'\np2887\ntp2888\nRp2889\ng1\n(g5\nS'ffff\\xe6\\xee\\xb9@'\np2890\ntp2891\nRp2892\nF7128.0\ntp2893\na(I5220000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xfe\\xb9@'\np2894\ntp2895\nRp2896\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xfe\\xb9@'\np2897\ntp2898\nRp2899\nF7192.0\ntp2900\na(I5230000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\x1f\\xba@'\np2901\ntp2902\nRp2903\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\x1f\\xba@'\np2904\ntp2905\nRp2906\nF7112.0\ntp2907\na(I5240000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccL\\xc2\\xb9@'\np2908\ntp2909\nRp2910\ng2906\nF4832.0\ntp2911\na(I5250000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\?\\xba@'\np2912\ntp2913\nRp2914\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\?\\xba@'\np2915\ntp2916\nRp2917\nF6456.0\ntp2918\na(I5260000\ng1\n(g5\nS'q=\\n\\xd7\\xa38\\xba@'\np2919\ntp2920\nRp2921\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x19A\\xba@'\np2922\ntp2923\nRp2924\nF7650.0\ntp2925\na(I5270000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x81\\xba@'\np2926\ntp2927\nRp2928\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x81\\xba@'\np2929\ntp2930\nRp2931\nF10760.0\ntp2932\na(I5280000\ng1\n(g5\nS'\\xf6(\\\\\\x8fB\\x91\\xba@'\np2933\ntp2934\nRp2935\ng1\n(g5\nS'\\xf6(\\\\\\x8fB\\x91\\xba@'\np2936\ntp2937\nRp2938\nF6322.0\ntp2939\na(I5290000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xad\\xba@'\np2940\ntp2941\nRp2942\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccL\\xb1\\xba@'\np2943\ntp2944\nRp2945\nF7498.0\ntp2946\na(I5300000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xe6\\xba@'\np2947\ntp2948\nRp2949\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xe6\\xba@'\np2950\ntp2951\nRp2952\nF9390.0\ntp2953\na(I5310000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xf1\\xba@'\np2954\ntp2955\nRp2956\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xf1\\xba@'\np2957\ntp2958\nRp2959\nF7620.0\ntp2960\na(I5320000\ng1\n(g5\nS'H\\xe1z\\x14.\\x04\\xbb@'\np2961\ntp2962\nRp2963\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x10\\xbb@'\np2964\ntp2965\nRp2966\nF5538.0\ntp2967\na(I5330000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xbd\\x8d\\xba@'\np2968\ntp2969\nRp2970\ng2966\nF6810.0\ntp2971\na(I5340000\ng1\n(g5\nS'3333\\xb3\\x8c\\xba@'\np2972\ntp2973\nRp2974\ng2966\nF5756.0\ntp2975\na(I5350000\ng1\n(g5\nS'\\xd7\\xa3p=\\x8a,\\xba@'\np2976\ntp2977\nRp2978\ng2966\nF3300.0\ntp2979\na(I5360000\ng1\n(g5\nS'q=\\n\\xd7#k\\xba@'\np2980\ntp2981\nRp2982\ng2966\nF9560.0\ntp2983\na(I5370000\ng1\n(g5\nS'\\xa4p=\\n\\xd7>\\xba@'\np2984\ntp2985\nRp2986\ng2966\nF5200.0\ntp2987\na(I5380000\ng1\n(g5\nS'\\xaeG\\xe1z\\x149\\xba@'\np2988\ntp2989\nRp2990\ng2966\nF7212.0\ntp2991\na(I5390000\ng1\n(g5\nS'\\xa4p=\\nW~\\xba@'\np2992\ntp2993\nRp2994\ng2966\nF5544.0\ntp2995\na(I5400000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94\\xb1\\xba@'\np2996\ntp2997\nRp2998\ng2966\nF10400.0\ntp2999\na(I5410000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x03\\xbb@'\np3000\ntp3001\nRp3002\ng2966\nF11598.0\ntp3003\na(I5420000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0f\\xbb@'\np3004\ntp3005\nRp3006\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0f\\xbb@'\np3007\ntp3008\nRp3009\nF9124.0\ntp3010\na(I5430000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfaK\\xbb@'\np3011\ntp3012\nRp3013\ng1\n(g5\nS'\\xa4p=\\n\\xd7j\\xbb@'\np3014\ntp3015\nRp3016\nF2160.0\ntp3017\na(I5440000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9eZ\\xbb@'\np3018\ntp3019\nRp3020\ng3016\nF8820.0\ntp3021\na(I5450000\ng1\n(g5\nS'q=\\n\\xd7#\\xb8\\xbb@'\np3022\ntp3023\nRp3024\ng1\n(g5\nS'q=\\n\\xd7#\\xb8\\xbb@'\np3025\ntp3026\nRp3027\nF5130.0\ntp3028\na(I5460000\ng1\n(g5\nS'33333\\x93\\xbb@'\np3029\ntp3030\nRp3031\ng3027\nF8584.0\ntp3032\na(I5470000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xa1\\xbb@'\np3033\ntp3034\nRp3035\ng3027\nF8482.0\ntp3036\na(I5480000\ng1\n(g5\nS'\\xa4p=\\nW\\xac\\xbb@'\np3037\ntp3038\nRp3039\ng3027\nF6894.0\ntp3040\na(I5490000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xcf\\xbb@'\np3041\ntp3042\nRp3043\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xcf\\xbb@'\np3044\ntp3045\nRp3046\nF8214.0\ntp3047\na(I5500000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8J\\xbc@'\np3048\ntp3049\nRp3050\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8J\\xbc@'\np3051\ntp3052\nRp3053\nF10230.0\ntp3054\na(I5510000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xbd\\x99\\xbc@'\np3055\ntp3056\nRp3057\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xbd\\x99\\xbc@'\np3058\ntp3059\nRp3060\nF8644.0\ntp3061\na(I5520000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa\\x90\\xbc@'\np3062\ntp3063\nRp3064\ng3060\nF9174.0\ntp3065\na(I5530000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xdc\\xbc@'\np3066\ntp3067\nRp3068\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc7\\xef\\xbc@'\np3069\ntp3070\nRp3071\nF5090.0\ntp3072\na(I5540000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xe6\\xbc@'\np3073\ntp3074\nRp3075\ng3071\nF6340.0\ntp3076\na(I5550000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94\\xb6\\xbc@'\np3077\ntp3078\nRp3079\ng3071\nF7170.0\ntp3080\na(I5560000\ng1\n(g5\nS'H\\xe1z\\x14.\\xb1\\xbc@'\np3081\ntp3082\nRp3083\ng3071\nF3900.0\ntp3084\na(I5570000\ng1\n(g5\nS'ffff\\xe6\\x81\\xbc@'\np3085\ntp3086\nRp3087\ng3071\nF3140.0\ntp3088\na(I5580000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xb8\\xbc@'\np3089\ntp3090\nRp3091\ng3071\nF10630.0\ntp3092\na(I5590000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f\\xd1\\xbc@'\np3093\ntp3094\nRp3095\ng3071\nF5884.0\ntp3096\na(I5600000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ%\\xbd@'\np3097\ntp3098\nRp3099\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ%\\xbd@'\np3100\ntp3101\nRp3102\nF14250.0\ntp3103\na(I5610000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xe9\\xbc@'\np3104\ntp3105\nRp3106\ng3102\nF4050.0\ntp3107\na(I5620000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\x19\\xbd@'\np3108\ntp3109\nRp3110\ng3102\nF10030.0\ntp3111\na(I5630000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x93\\xbd@'\np3112\ntp3113\nRp3114\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x93\\xbd@'\np3115\ntp3116\nRp3117\nF19656.0\ntp3118\na(I5640000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x95\\xbd@'\np3119\ntp3120\nRp3121\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x95\\xbd@'\np3122\ntp3123\nRp3124\nF9270.0\ntp3125\na(I5650000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f\\xb8\\xbd@'\np3126\ntp3127\nRp3128\ng1\n(g5\nS'\\xd7\\xa3p=\\x8a\\xcb\\xbd@'\np3129\ntp3130\nRp3131\nF6742.0\ntp3132\na(I5660000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f\\xe5\\xbd@'\np3133\ntp3134\nRp3135\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f\\xe5\\xbd@'\np3136\ntp3137\nRp3138\nF8340.0\ntp3139\na(I5670000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x08\\xbe@'\np3140\ntp3141\nRp3142\ng1\n(g5\nS'\\xf6(\\\\\\x8fB\\x18\\xbe@'\np3143\ntp3144\nRp3145\nF8736.0\ntp3146\na(I5680000\ng1\n(g5\nS')\\\\\\x8f\\xc2u\\xd4\\xbd@'\np3147\ntp3148\nRp3149\ng3145\nF8298.0\ntp3150\na(I5690000\ng1\n(g5\nS'fffff.\\xbe@'\np3151\ntp3152\nRp3153\ng1\n(g5\nS'fffff.\\xbe@'\np3154\ntp3155\nRp3156\nF14372.0\ntp3157\na(I5700000\ng1\n(g5\nS'3333\\xb3\\x80\\xbe@'\np3158\ntp3159\nRp3160\ng1\n(g5\nS'3333\\xb3\\x80\\xbe@'\np3161\ntp3162\nRp3163\nF10980.0\ntp3164\na(I5710000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x93\\xbe@'\np3165\ntp3166\nRp3167\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x93\\xbe@'\np3168\ntp3169\nRp3170\nF9840.0\ntp3171\na(I5720000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\~\\xbe@'\np3172\ntp3173\nRp3174\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x9e\\xbe@'\np3175\ntp3176\nRp3177\nF6704.0\ntp3178\na(I5730000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdcx\\xbe@'\np3179\ntp3180\nRp3181\ng3177\nF9710.0\ntp3182\na(I5740000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eh\\xbe@'\np3183\ntp3184\nRp3185\ng3177\nF9336.0\ntp3186\na(I5750000\ng1\n(g5\nS'fffff@\\xbe@'\np3187\ntp3188\nRp3189\ng3177\nF4860.0\ntp3190\na(I5760000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1z\\xbe@'\np3191\ntp3192\nRp3193\ng3177\nF12036.0\ntp3194\na(I5770000\ng1\n(g5\nS')\\\\\\x8f\\xc2u\\x89\\xbe@'\np3195\ntp3196\nRp3197\ng3177\nF10494.0\ntp3198\na(I5780000\ng1\n(g5\nS'{\\x14\\xaeGa\\xfc\\xbe@'\np3199\ntp3200\nRp3201\ng1\n(g5\nS'{\\x14\\xaeGa\\xfc\\xbe@'\np3202\ntp3203\nRp3204\nF10978.0\ntp3205\na(I5790000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xbc\\xbe@'\np3206\ntp3207\nRp3208\ng3204\nF5880.0\ntp3209\na(I5800000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xbc\\xbe@'\np3210\ntp3211\nRp3212\ng3204\nF5880.0\ntp3213\na(I5810000\ng1\n(g5\nS'\\xa4p=\\n\\xd7X\\xbf@'\np3214\ntp3215\nRp3216\ng1\n(g5\nS'\\xa4p=\\n\\xd7X\\xbf@'\np3217\ntp3218\nRp3219\nF11532.0\ntp3220\na(I5820000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05\\x07\\xbf@'\np3221\ntp3222\nRp3223\ng3219\nF4350.0\ntp3224\na(I5830000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94*\\xbf@'\np3225\ntp3226\nRp3227\ng3219\nF6240.0\ntp3228\na(I5840000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1*\\xbf@'\np3229\ntp3230\nRp3231\ng3219\nF8330.0\ntp3232\na(I5850000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x19\\xbf@'\np3233\ntp3234\nRp3235\ng3219\nF3964.0\ntp3236\na(I5860000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc(\\xbf@'\np3237\ntp3238\nRp3239\ng3219\nF11928.0\ntp3240\na(I5870000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc>\\xbf@'\np3241\ntp3242\nRp3243\ng3219\nF6804.0\ntp3244\na(I5880000\ng1\n(g5\nS'\\xaeG\\xe1z\\x142\\xbf@'\np3245\ntp3246\nRp3247\ng3219\nF6372.0\ntp3248\na(I5890000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xf4\\xbe@'\np3249\ntp3250\nRp3251\ng3219\nF5024.0\ntp3252\na(I5900000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xde\\xbe@'\np3253\ntp3254\nRp3255\ng3219\nF7098.0\ntp3256\na(I5910000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xe3\\xbe@'\np3257\ntp3258\nRp3259\ng3219\nF8208.0\ntp3260\na(I5920000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xcc\\xbe@'\np3261\ntp3262\nRp3263\ng3219\nF7026.0\ntp3264\na(I5930000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x07\\xbf@'\np3265\ntp3266\nRp3267\ng3219\nF5246.0\ntp3268\na(I5940000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0b\\xbf@'\np3269\ntp3270\nRp3271\ng3219\nF8162.0\ntp3272\na(I5950000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5F\\xbf@'\np3273\ntp3274\nRp3275\ng3219\nF8210.0\ntp3276\na(I5960000\ng1\n(g5\nS'3333\\xb3i\\xbf@'\np3277\ntp3278\nRp3279\ng1\n(g5\nS'3333\\xb3i\\xbf@'\np3280\ntp3281\nRp3282\nF7758.0\ntp3283\na(I5970000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8\\x8b\\xbf@'\np3284\ntp3285\nRp3286\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\x91\\xbf@'\np3287\ntp3288\nRp3289\nF3720.0\ntp3290\na(I5980000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xfc\\xbf@'\np3291\ntp3292\nRp3293\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xfc\\xbf@'\np3294\ntp3295\nRp3296\nF6508.0\ntp3297\na(I5990000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccL\\xf3\\xbf@'\np3298\ntp3299\nRp3300\ng3296\nF7154.0\ntp3301\na(I6000000\ng1\n(g5\nS'H\\xe1z\\x14n\\x0c\\xc0@'\np3302\ntp3303\nRp3304\ng1\n(g5\nS'H\\xe1z\\x14n\\x0c\\xc0@'\np3305\ntp3306\nRp3307\nF8956.0\ntp3308\na(I6010000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\x9c\\x1f\\xc0@'\np3309\ntp3310\nRp3311\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\x8c%\\xc0@'\np3312\ntp3313\nRp3314\nF6024.0\ntp3315\na(I6020000\ng1\n(g5\nS'\\xa4p=\\n\\x97\\x0b\\xc0@'\np3316\ntp3317\nRp3318\ng3314\nF6716.0\ntp3319\na(I6030000\ng1\n(g5\nS'\\xaeG\\xe1zT%\\xc0@'\np3320\ntp3321\nRp3322\ng3314\nF10692.0\ntp3323\na(I6040000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e!\\xc0@'\np3324\ntp3325\nRp3326\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\xcf6\\xc0@'\np3327\ntp3328\nRp3329\nF7260.0\ntp3330\na(I6050000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc7\\x0f\\xc0@'\np3331\ntp3332\nRp3333\ng3329\nF5990.0\ntp3334\na(I6060000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2+\\xc0@'\np3335\ntp3336\nRp3337\ng3329\nF7284.0\ntp3338\na(I6070000\ng1\n(g5\nS'fffff\\xf3\\xbf@'\np3339\ntp3340\nRp3341\ng3329\nF6644.0\ntp3342\na(I6080000\ng1\n(g5\nS'\\xa4p=\\n\\x97\\n\\xc0@'\np3343\ntp3344\nRp3345\ng3329\nF8508.0\ntp3346\na(I6090000\ng1\n(g5\nS\"\\xb8\\x1e\\x85\\xeb\\x91'\\xc0@\"\np3347\ntp3348\nRp3349\ng3329\nF9700.0\ntp3350\na(I6100000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\x1c/\\xc0@'\np3351\ntp3352\nRp3353\ng3329\nF7702.0\ntp3354\na(I6110000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\x912\\xc0@'\np3355\ntp3356\nRp3357\ng1\n(g5\nS'\\xd7\\xa3p=J?\\xc0@'\np3358\ntp3359\nRp3360\nF4350.0\ntp3361\na(I6120000\ng1\n(g5\nS'H\\xe1z\\x14\\xee9\\xc0@'\np3362\ntp3363\nRp3364\ng3360\nF8568.0\ntp3365\na(I6130000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x1a\\xc0@'\np3366\ntp3367\nRp3368\ng3360\nF6508.0\ntp3369\na(I6140000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xab4\\xc0@'\np3370\ntp3371\nRp3372\ng3360\nF13842.0\ntp3373\na(I6150000\ng1\n(g5\nS'ffff\\xe6\\x00\\xc0@'\np3374\ntp3375\nRp3376\ng3360\nF6924.0\ntp3377\na(I6160000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99Y$\\xc0@'\np3378\ntp3379\nRp3380\ng3360\nF12180.0\ntp3381\na(I6170000\ng1\n(g5\nS'\\n\\xd7\\xa3p}\\x1d\\xc0@'\np3382\ntp3383\nRp3384\ng3360\nF7494.0\ntp3385\na(I6180000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\t\\xc0@'\np3386\ntp3387\nRp3388\ng3360\nF4768.0\ntp3389\na(I6190000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x1d\\xc0@'\np3390\ntp3391\nRp3392\ng3360\nF2832.0\ntp3393\na(I6200000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\4\\xc0@'\np3394\ntp3395\nRp3396\ng3360\nF6810.0\ntp3397\na(I6210000\ng1\n(g5\nS'3333s\\x05\\xc0@'\np3398\ntp3399\nRp3400\ng3360\nF6546.0\ntp3401\na(I6220000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xc0\\xbf@'\np3402\ntp3403\nRp3404\ng3360\nF5812.0\ntp3405\na(I6230000\ng1\n(g5\nS'{\\x14\\xaeGa\\xdb\\xbf@'\np3406\ntp3407\nRp3408\ng3360\nF8232.0\ntp3409\na(I6240000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc=\\xbf@'\np3410\ntp3411\nRp3412\ng3360\nF7914.0\ntp3413\na(I6250000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zv\\xbf@'\np3414\ntp3415\nRp3416\ng3360\nF14932.0\ntp3417\na(I6260000\ng1\n(g5\nS'33333H\\xbf@'\np3418\ntp3419\nRp3420\ng3360\nF4576.0\ntp3421\na(I6270000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x80\\xf7\\xbe@'\np3422\ntp3423\nRp3424\ng3360\nF8430.0\ntp3425\na(I6280000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0\\x0f\\xbf@'\np3426\ntp3427\nRp3428\ng3360\nF11180.0\ntp3429\na(I6290000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x197\\xbf@'\np3430\ntp3431\nRp3432\ng3360\nF12214.0\ntp3433\na(I6300000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f(\\xbf@'\np3434\ntp3435\nRp3436\ng3360\nF9410.0\ntp3437\na(I6310000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccL-\\xbf@'\np3438\ntp3439\nRp3440\ng3360\nF11454.0\ntp3441\na(I6320000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x04\\xbf@'\np3442\ntp3443\nRp3444\ng3360\nF5730.0\ntp3445\na(I6330000\ng1\n(g5\nS'\\xf6(\\\\\\x8fB\\xfc\\xbe@'\np3446\ntp3447\nRp3448\ng3360\nF5926.0\ntp3449\na(I6340000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xeb\\xbe@'\np3450\ntp3451\nRp3452\ng3360\nF8322.0\ntp3453\na(I6350000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xd7\\xbe@'\np3454\ntp3455\nRp3456\ng3360\nF5856.0\ntp3457\na(I6360000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05\\xf1\\xbe@'\np3458\ntp3459\nRp3460\ng3360\nF9900.0\ntp3461\na(I6370000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xd7\\xbe@'\np3462\ntp3463\nRp3464\ng3360\nF7908.0\ntp3465\na(I6380000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xbd\\x9c\\xbe@'\np3466\ntp3467\nRp3468\ng3360\nF8260.0\ntp3469\na(I6390000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xbd\\xe2\\xbe@'\np3470\ntp3471\nRp3472\ng3360\nF6146.0\ntp3473\na(I6400000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xea\\xbe@'\np3474\ntp3475\nRp3476\ng3360\nF6618.0\ntp3477\na(I6410000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xa2\\xbe@'\np3478\ntp3479\nRp3480\ng3360\nF6198.0\ntp3481\na(I6420000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xba\\xbe@'\np3482\ntp3483\nRp3484\ng3360\nF7692.0\ntp3485\na(I6430000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xf9\\xbe@'\np3486\ntp3487\nRp3488\ng3360\nF9396.0\ntp3489\na(I6440000\ng1\n(g5\nS'q=\\n\\xd7\\xa3<\\xbf@'\np3490\ntp3491\nRp3492\ng3360\nF12924.0\ntp3493\na(I6450000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94#\\xbf@'\np3494\ntp3495\nRp3496\ng3360\nF6546.0\ntp3497\na(I6460000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8j\\xbf@'\np3498\ntp3499\nRp3500\ng3360\nF13312.0\ntp3501\na(I6470000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xa4\\xbf@'\np3502\ntp3503\nRp3504\ng3360\nF9804.0\ntp3505\na(I6480000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x997\\xbf@'\np3506\ntp3507\nRp3508\ng3360\nF4680.0\ntp3509\na(I6490000\ng1\n(g5\nS'\\n\\xd7\\xa3p=T\\xbf@'\np3510\ntp3511\nRp3512\ng3360\nF8720.0\ntp3513\na(I6500000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x98\\xbf@'\np3514\ntp3515\nRp3516\ng3360\nF15444.0\ntp3517\na(I6510000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x80\\xfa\\xbf@'\np3518\ntp3519\nRp3520\ng3360\nF12842.0\ntp3521\na(I6520000\ng1\n(g5\nS'q=\\n\\xd7c.\\xc0@'\np3522\ntp3523\nRp3524\ng3360\nF5070.0\ntp3525\na(I6530000\ng1\n(g5\nS'ffff\\xe6*\\xc0@'\np3526\ntp3527\nRp3528\ng3360\nF9716.0\ntp3529\na(I6540000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\x11)\\xc0@'\np3530\ntp3531\nRp3532\ng3360\nF6660.0\ntp3533\na(I6550000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.\\xc0@'\np3534\ntp3535\nRp3536\ng3360\nF7652.0\ntp3537\na(I6560000\ng1\n(g5\nS'q=\\n\\xd7c8\\xc0@'\np3538\ntp3539\nRp3540\ng3360\nF7470.0\ntp3541\na(I6570000\ng1\n(g5\nS'q=\\n\\xd7#7\\xc0@'\np3542\ntp3543\nRp3544\ng3360\nF9640.0\ntp3545\na(I6580000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f)\\xc0@'\np3546\ntp3547\nRp3548\ng3360\nF6096.0\ntp3549\na(I6590000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\"\\xc0@'\np3550\ntp3551\nRp3552\ng3360\nF7920.0\ntp3553\na(I6600000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00H\\xc0@'\np3554\ntp3555\nRp3556\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00H\\xc0@'\np3557\ntp3558\nRp3559\nF18930.0\ntp3560\na(I6610000\ng1\n(g5\nS'q=\\n\\xd7\\xa3C\\xc0@'\np3561\ntp3562\nRp3563\ng3559\nF5636.0\ntp3564\na(I6620000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\x11B\\xc0@'\np3565\ntp3566\nRp3567\ng3559\nF7692.0\ntp3568\na(I6630000\ng1\n(g5\nS'\\xecQ\\xb8\\x1eE3\\xc0@'\np3569\ntp3570\nRp3571\ng1\n(g5\nS'\\xd7\\xa3p=\\x8aL\\xc0@'\np3572\ntp3573\nRp3574\nF6126.0\ntp3575\na(I6640000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa7\\xc0@'\np3576\ntp3577\nRp3578\ng3574\nF8886.0\ntp3579\na(I6650000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x855\\xc0@'\np3580\ntp3581\nRp3582\ng3574\nF10200.0\ntp3583\na(I6660000\ng1\n(g5\nS'\\xf6(\\\\\\x8fB\\x1c\\xc0@'\np3584\ntp3585\nRp3586\ng3574\nF9010.0\ntp3587\na(I6670000\ng1\n(g5\nS'\\n\\xd7\\xa3p}.\\xc0@'\np3588\ntp3589\nRp3590\ng3574\nF11946.0\ntp3591\na(I6680000\ng1\n(g5\nS'fffff*\\xc0@'\np3592\ntp3593\nRp3594\ng3574\nF5440.0\ntp3595\na(I6690000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\x8c\\x1c\\xc0@'\np3596\ntp3597\nRp3598\ng3574\nF4606.0\ntp3599\na(I6700000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\xc5+\\xc0@'\np3600\ntp3601\nRp3602\ng3574\nF7896.0\ntp3603\na(I6710000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\x824\\xc0@'\np3604\ntp3605\nRp3606\ng3574\nF10968.0\ntp3607\na(I6720000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\x8c\"\\xc0@'\np3608\ntp3609\nRp3610\ng3574\nF7098.0\ntp3611\na(I6730000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xe8\\x1c\\xc0@'\np3612\ntp3613\nRp3614\ng3574\nF10590.0\ntp3615\na(I6740000\ng1\n(g5\nS\"R\\xb8\\x1e\\x85\\xab'\\xc0@\"\np3616\ntp3617\nRp3618\ng3574\nF8444.0\ntp3619\na(I6750000\ng1\n(g5\nS'\\xaeG\\xe1z\\xd4B\\xc0@'\np3620\ntp3621\nRp3622\ng3574\nF14000.0\ntp3623\na(I6760000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa[\\xc0@'\np3624\ntp3625\nRp3626\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa[\\xc0@'\np3627\ntp3628\nRp3629\nF8310.0\ntp3630\na(I6770000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\M\\xc0@'\np3631\ntp3632\nRp3633\ng3629\nF5880.0\ntp3634\na(I6780000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\xc5A\\xc0@'\np3635\ntp3636\nRp3637\ng3629\nF4606.0\ntp3638\na(I6790000\ng1\n(g5\nS'q=\\n\\xd7\\xe3/\\xc0@'\np3639\ntp3640\nRp3641\ng3629\nF3990.0\ntp3642\na(I6800000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\x0c9\\xc0@'\np3643\ntp3644\nRp3645\ng3629\nF6712.0\ntp3646\na(I6810000\ng1\n(g5\nS'q=\\n\\xd7c\\x1f\\xc0@'\np3647\ntp3648\nRp3649\ng3629\nF6864.0\ntp3650\na(I6820000\ng1\n(g5\nS'\\xc3\\xf5(\\\\OS\\xc0@'\np3651\ntp3652\nRp3653\ng3629\nF13216.0\ntp3654\na(I6830000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94V\\xc0@'\np3655\ntp3656\nRp3657\ng3629\nF8226.0\ntp3658\na(I6840000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x8c\\xc0@'\np3659\ntp3660\nRp3661\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x8c\\xc0@'\np3662\ntp3663\nRp3664\nF10360.0\ntp3665\na(I6850000\ng1\n(g5\nS'\\x85\\xebQ\\xb8^\\x80\\xc0@'\np3666\ntp3667\nRp3668\ng3664\nF4028.0\ntp3669\na(I6860000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x9d\\xc0@'\np3670\ntp3671\nRp3672\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x9d\\xc0@'\np3673\ntp3674\nRp3675\nF12716.0\ntp3676\na(I6870000\ng1\n(g5\nS'ffff&\\xe6\\xc0@'\np3677\ntp3678\nRp3679\ng1\n(g5\nS'ffff&\\xe6\\xc0@'\np3680\ntp3681\nRp3682\nF8346.0\ntp3683\na(I6880000\ng1\n(g5\nS'q=\\n\\xd7#\\x05\\xc1@'\np3684\ntp3685\nRp3686\ng1\n(g5\nS'q=\\n\\xd7#\\x05\\xc1@'\np3687\ntp3688\nRp3689\nF14430.0\ntp3690\na(I6890000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8\\xea\\xc0@'\np3691\ntp3692\nRp3693\ng3689\nF4230.0\ntp3694\na(I6900000\ng1\n(g5\nS'\\xa4p=\\n\\x97\\xd5\\xc0@'\np3695\ntp3696\nRp3697\ng3689\nF5280.0\ntp3698\na(I6910000\ng1\n(g5\nS'ffff\\xe6\\xe1\\xc0@'\np3699\ntp3700\nRp3701\ng3689\nF7038.0\ntp3702\na(I6920000\ng1\n(g5\nS'ffff&\\x12\\xc1@'\np3703\ntp3704\nRp3705\ng1\n(g5\nS'ffff&\\x12\\xc1@'\np3706\ntp3707\nRp3708\nF9800.0\ntp3709\na(I6930000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa\\xdf\\xc0@'\np3710\ntp3711\nRp3712\ng3708\nF9268.0\ntp3713\na(I6940000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xfd\\xb8\\xc0@'\np3714\ntp3715\nRp3716\ng3708\nF4860.0\ntp3717\na(I6950000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f\\x89\\xc0@'\np3718\ntp3719\nRp3720\ng3708\nF2108.0\ntp3721\na(I6960000\ng1\n(g5\nS'\\xa4p=\\n\\x17|\\xc0@'\np3722\ntp3723\nRp3724\ng3708\nF8740.0\ntp3725\na(I6970000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\xae\\xc0@'\np3726\ntp3727\nRp3728\ng3708\nF7530.0\ntp3729\na(I6980000\ng1\n(g5\nS'\\xc3\\xf5(\\\\O\\xae\\xc0@'\np3730\ntp3731\nRp3732\ng3708\nF8950.0\ntp3733\na(I6990000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\xde\\xb4\\xc0@'\np3734\ntp3735\nRp3736\ng3708\nF5760.0\ntp3737\na(I7000000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ{\\xc0@'\np3738\ntp3739\nRp3740\ng3708\nF5866.0\ntp3741\na(I7010000\ng1\n(g5\nS'\\xecQ\\xb8\\x1eE\\x90\\xc0@'\np3742\ntp3743\nRp3744\ng3708\nF12450.0\ntp3745\na(I7020000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^\\xc0@'\np3746\ntp3747\nRp3748\ng3708\nF7200.0\ntp3749\na(I7030000\ng1\n(g5\nS'q=\\n\\xd7#\\x8b\\xc0@'\np3750\ntp3751\nRp3752\ng3708\nF8580.0\ntp3753\na(I7040000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8V\\xc0@'\np3754\ntp3755\nRp3756\ng3708\nF6384.0\ntp3757\na(I7050000\ng1\n(g5\nS'=\\n\\xd7\\xa3pw\\xc0@'\np3758\ntp3759\nRp3760\ng3708\nF13352.0\ntp3761\na(I7060000\ng1\n(g5\nS'=\\n\\xd7\\xa30e\\xc0@'\np3762\ntp3763\nRp3764\ng3708\nF7530.0\ntp3765\na(I7070000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xabQ\\xc0@'\np3766\ntp3767\nRp3768\ng3708\nF5216.0\ntp3769\na(I7080000\ng1\n(g5\nS'R\\xb8\\x1e\\x85+V\\xc0@'\np3770\ntp3771\nRp3772\ng3708\nF6516.0\ntp3773\na(I7090000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xfd\\x7f\\xc0@'\np3774\ntp3775\nRp3776\ng3708\nF21676.0\ntp3777\na(I7100000\ng1\n(g5\nS'3333sm\\xc0@'\np3778\ntp3779\nRp3780\ng3708\nF6096.0\ntp3781\na(I7110000\ng1\n(g5\nS'ffff\\xe6\\x95\\xc0@'\np3782\ntp3783\nRp3784\ng3708\nF5280.0\ntp3785\na(I7120000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8~\\xc0@'\np3786\ntp3787\nRp3788\ng3708\nF7428.0\ntp3789\na(I7130000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x90\\xc0@'\np3790\ntp3791\nRp3792\ng3708\nF18920.0\ntp3793\na(I7140000\ng1\n(g5\nS'R\\xb8\\x1e\\x85+y\\xc0@'\np3794\ntp3795\nRp3796\ng3708\nF8268.0\ntp3797\na(I7150000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05\\xb0\\xc0@'\np3798\ntp3799\nRp3800\ng3708\nF24716.0\ntp3801\na(I7160000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd4\\xc0@'\np3802\ntp3803\nRp3804\ng3708\nF12450.0\ntp3805\na(I7170000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x1a\\xc1@'\np3806\ntp3807\nRp3808\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x1a\\xc1@'\np3809\ntp3810\nRp3811\nF18756.0\ntp3812\na(I7180000\ng1\n(g5\nS'R\\xb8\\x1e\\x85k\\x18\\xc1@'\np3813\ntp3814\nRp3815\ng3811\nF7230.0\ntp3816\na(I7190000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0\\x11\\xc1@'\np3817\ntp3818\nRp3819\ng3811\nF9810.0\ntp3820\na(I7200000\ng1\n(g5\nS'H\\xe1z\\x14\\xeeS\\xc1@'\np3821\ntp3822\nRp3823\ng1\n(g5\nS'H\\xe1z\\x14\\xeeS\\xc1@'\np3824\ntp3825\nRp3826\nF20850.0\ntp3827\na(I7210000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\\\\\xc1@'\np3828\ntp3829\nRp3830\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\\\\\xc1@'\np3831\ntp3832\nRp3833\nF6804.0\ntp3834\na(I7220000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eL\\xc1@'\np3835\ntp3836\nRp3837\ng3833\nF6456.0\ntp3838\na(I7230000\ng1\n(g5\nS'q=\\n\\xd7c\\x9d\\xc1@'\np3839\ntp3840\nRp3841\ng1\n(g5\nS'q=\\n\\xd7c\\x9d\\xc1@'\np3842\ntp3843\nRp3844\nF23310.0\ntp3845\na(I7240000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\xc8\\xc1@'\np3846\ntp3847\nRp3848\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\xc8\\xc1@'\np3849\ntp3850\nRp3851\nF14790.0\ntp3852\na(I7250000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0\\x02\\xc2@'\np3853\ntp3854\nRp3855\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0\\x02\\xc2@'\np3856\ntp3857\nRp3858\nF15936.0\ntp3859\na(I7260000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x18\\xc2@'\np3860\ntp3861\nRp3862\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x18\\xc2@'\np3863\ntp3864\nRp3865\nF12180.0\ntp3866\na(I7270000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\xcfJ\\xc2@'\np3867\ntp3868\nRp3869\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\xcfJ\\xc2@'\np3870\ntp3871\nRp3872\nF29044.0\ntp3873\na(I7280000\ng1\n(g5\nS'H\\xe1z\\x14n\\x81\\xc2@'\np3874\ntp3875\nRp3876\ng1\n(g5\nS'H\\xe1z\\x14n\\x81\\xc2@'\np3877\ntp3878\nRp3879\nF16560.0\ntp3880\na(I7290000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x9c\\xc2@'\np3881\ntp3882\nRp3883\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x9c\\xc2@'\np3884\ntp3885\nRp3886\nF11820.0\ntp3887\na(I7300000\ng1\n(g5\nS'\\xa4p=\\nW\\x96\\xc2@'\np3888\ntp3889\nRp3890\ng3886\nF6456.0\ntp3891\na(I7310000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xb5\\xc2@'\np3892\ntp3893\nRp3894\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xb5\\xc2@'\np3895\ntp3896\nRp3897\nF12132.0\ntp3898\na(I7320000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb3\\xc2@'\np3899\ntp3900\nRp3901\ng3897\nF4540.0\ntp3902\na(I7330000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xc1\\xc2@'\np3903\ntp3904\nRp3905\ng1\n(g5\nS'\\xd7\\xa3p=J\\xcd\\xc2@'\np3906\ntp3907\nRp3908\nF7758.0\ntp3909\na(I7340000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\x1c\\xb1\\xc2@'\np3910\ntp3911\nRp3912\ng3908\nF3900.0\ntp3913\na(I7350000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xc9\\xc2@'\np3914\ntp3915\nRp3916\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\xcf\\xe4\\xc2@'\np3917\ntp3918\nRp3919\nF6528.0\ntp3920\na(I7360000\ng1\n(g5\nS'ffff\\xe6\\xea\\xc2@'\np3921\ntp3922\nRp3923\ng1\n(g5\nS'ffff\\xe6\\xea\\xc2@'\np3924\ntp3925\nRp3926\nF13530.0\ntp3927\na(I7370000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xe8\\x13\\xc3@'\np3928\ntp3929\nRp3930\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xe8\\x13\\xc3@'\np3931\ntp3932\nRp3933\nF13642.0\ntp3934\na(I7380000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa$\\xc3@'\np3935\ntp3936\nRp3937\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa$\\xc3@'\np3938\ntp3939\nRp3940\nF7320.0\ntp3941\na(I7390000\ng1\n(g5\nS')\\\\\\x8f\\xc25\\x13\\xc3@'\np3942\ntp3943\nRp3944\ng3940\nF9750.0\ntp3945\na(I7400000\ng1\n(g5\nS'H\\xe1z\\x14.\\x06\\xc3@'\np3946\ntp3947\nRp3948\ng3940\nF8362.0\ntp3949\na(I7410000\ng1\n(g5\nS'=\\n\\xd7\\xa30\\x18\\xc3@'\np3950\ntp3951\nRp3952\ng3940\nF8740.0\ntp3953\na(I7420000\ng1\n(g5\nS'fffff\\x03\\xc3@'\np3954\ntp3955\nRp3956\ng3940\nF6432.0\ntp3957\na(I7430000\ng1\n(g5\nS'q=\\n\\xd7c\\x0f\\xc3@'\np3958\ntp3959\nRp3960\ng3940\nF4606.0\ntp3961\na(I7440000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xfd\\xf6\\xc2@'\np3962\ntp3963\nRp3964\ng3940\nF5086.0\ntp3965\na(I7450000\ng1\n(g5\nS'q=\\n\\xd7\\xe3\\xf4\\xc2@'\np3966\ntp3967\nRp3968\ng3940\nF7890.0\ntp3969\na(I7460000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\x8c\\xec\\xc2@'\np3970\ntp3971\nRp3972\ng3940\nF8600.0\ntp3973\na(I7470000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfd\\xc2@'\np3974\ntp3975\nRp3976\ng3940\nF6648.0\ntp3977\na(I7480000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xfa\\xc2@'\np3978\ntp3979\nRp3980\ng3940\nF5472.0\ntp3981\na(I7490000\ng1\n(g5\nS'{\\x14\\xaeGa\\x12\\xc3@'\np3982\ntp3983\nRp3984\ng3940\nF11436.0\ntp3985\na(I7500000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\x82)\\xc3@'\np3986\ntp3987\nRp3988\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\x82)\\xc3@'\np3989\ntp3990\nRp3991\nF9422.0\ntp3992\na(I7510000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x16\\xc3@'\np3993\ntp3994\nRp3995\ng1\n(g5\nS'\\xa4p=\\nW5\\xc3@'\np3996\ntp3997\nRp3998\nF7092.0\ntp3999\na(I7520000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf9\\xc2@'\np4000\ntp4001\nRp4002\ng3998\nF7060.0\ntp4003\na(I7530000\ng1\n(g5\nS'\\xa4p=\\n\\x17\\xe9\\xc2@'\np4004\ntp4005\nRp4006\ng3998\nF7026.0\ntp4007\na(I7540000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xf6\\xc2@'\np4008\ntp4009\nRp4010\ng3998\nF4860.0\ntp4011\na(I7550000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\x02\\xc9\\xc2@'\np4012\ntp4013\nRp4014\ng3998\nF6254.0\ntp4015\na(I7560000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xf8\\xdd\\xc2@'\np4016\ntp4017\nRp4018\ng3998\nF12538.0\ntp4019\na(I7570000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94\\xe3\\xc2@'\np4020\ntp4021\nRp4022\ng3998\nF15552.0\ntp4023\na(I7580000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xb5>\\xc3@'\np4024\ntp4025\nRp4026\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xb5>\\xc3@'\np4027\ntp4028\nRp4029\nF22546.0\ntp4030\na(I7590000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xb0N\\xc3@'\np4031\ntp4032\nRp4033\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\x82Z\\xc3@'\np4034\ntp4035\nRp4036\nF10590.0\ntp4037\na(I7600000\ng1\n(g5\nS'q=\\n\\xd7\\xa3d\\xc3@'\np4038\ntp4039\nRp4040\ng1\n(g5\nS'q=\\n\\xd7\\xa3d\\xc3@'\np4041\ntp4042\nRp4043\nF9670.0\ntp4044\na(I7610000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xbd\\x88\\xc3@'\np4045\ntp4046\nRp4047\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xbd\\x88\\xc3@'\np4048\ntp4049\nRp4050\nF14258.0\ntp4051\na(I7620000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1b\\xc3@'\np4052\ntp4053\nRp4054\ng4050\nF5632.0\ntp4055\na(I7630000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\x0c\\x90\\xc3@'\np4056\ntp4057\nRp4058\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\x0c\\x90\\xc3@'\np4059\ntp4060\nRp4061\nF13126.0\ntp4062\na(I7640000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8\\xb1\\xc3@'\np4063\ntp4064\nRp4065\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8\\xb1\\xc3@'\np4066\ntp4067\nRp4068\nF15990.0\ntp4069\na(I7650000\ng1\n(g5\nS'{\\x14\\xaeG\\xa1\\xb8\\xc3@'\np4070\ntp4071\nRp4072\ng1\n(g5\nS'{\\x14\\xaeG\\xa1\\xb8\\xc3@'\np4073\ntp4074\nRp4075\nF6254.0\ntp4076\na(I7660000\ng1\n(g5\nS'3333\\xb3\\xe0\\xc3@'\np4077\ntp4078\nRp4079\ng1\n(g5\nS'3333\\xb3\\xe0\\xc3@'\np4080\ntp4081\nRp4082\nF17184.0\ntp4083\na(I7670000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xf1\\xc3@'\np4084\ntp4085\nRp4086\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xff\\xc3@'\np4087\ntp4088\nRp4089\nF5880.0\ntp4090\na(I7680000\ng1\n(g5\nS'\\x85\\xebQ\\xb8^\\xd7\\xc3@'\np4091\ntp4092\nRp4093\ng4089\nF9030.0\ntp4094\na(I7690000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\x1c\\xf8\\xc3@'\np4095\ntp4096\nRp4097\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\x8c\\x05\\xc4@'\np4098\ntp4099\nRp4100\nF6262.0\ntp4101\na(I7700000\ng1\n(g5\nS'q=\\n\\xd7#2\\xc4@'\np4102\ntp4103\nRp4104\ng1\n(g5\nS'q=\\n\\xd7#2\\xc4@'\np4105\ntp4106\nRp4107\nF21336.0\ntp4108\na(I7710000\ng1\n(g5\nS'q=\\n\\xd7#2\\xc4@'\np4109\ntp4110\nRp4111\ng4107\nF21336.0\ntp4112\na(I7720000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\xd9\\x87\\xc4@'\np4113\ntp4114\nRp4115\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\xd9\\x87\\xc4@'\np4116\ntp4117\nRp4118\nF4992.0\ntp4119\na(I7730000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\xd9\\x87\\xc4@'\np4120\ntp4121\nRp4122\ng4118\nF4992.0\ntp4123\na(I7740000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xb9\\xc4@'\np4124\ntp4125\nRp4126\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xdc\\xc4@'\np4127\ntp4128\nRp4129\nF5410.0\ntp4130\na(I7750000\ng1\n(g5\nS'\\xd7\\xa3p=J\\x9b\\xc4@'\np4131\ntp4132\nRp4133\ng4129\nF6996.0\ntp4134\na(I7760000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x98\\xc4@'\np4135\ntp4136\nRp4137\ng4129\nF8010.0\ntp4138\na(I7770000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xc4\\xc4@'\np4139\ntp4140\nRp4141\ng4129\nF15216.0\ntp4142\na(I7780000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xd3\\xc4@'\np4143\ntp4144\nRp4145\ng1\n(g5\nS'\\xc3\\xf5(\\\\O\\xea\\xc4@'\np4146\ntp4147\nRp4148\nF8850.0\ntp4149\na(I7790000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\xde\\xd3\\xc4@'\np4150\ntp4151\nRp4152\ng4148\nF7544.0\ntp4153\na(I7800000\ng1\n(g5\nS'\\x1f\\x85\\xebQx\\xe8\\xc4@'\np4154\ntp4155\nRp4156\ng4148\nF8734.0\ntp4157\na(I7810000\ng1\n(g5\nS'H\\xe1z\\x14\\xee\\xe2\\xc4@'\np4158\ntp4159\nRp4160\ng4148\nF5676.0\ntp4161\na(I7820000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\x87\\x96\\xc4@'\np4162\ntp4163\nRp4164\ng4148\nF6384.0\ntp4165\na(I7830000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x87\\xc4@'\np4166\ntp4167\nRp4168\ng4148\nF4384.0\ntp4169\na(I7840000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xae\\xc4@'\np4170\ntp4171\nRp4172\ng4148\nF5598.0\ntp4173\na(I7850000\ng1\n(g5\nS'\\n\\xd7\\xa3p=_\\xc4@'\np4174\ntp4175\nRp4176\ng4148\nF4796.0\ntp4177\na(I7860000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0Q\\xc4@'\np4178\ntp4179\nRp4180\ng4148\nF5608.0\ntp4181\na(I7870000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9e\\xf2\\xc3@'\np4182\ntp4183\nRp4184\ng4148\nF6300.0\ntp4185\na(I7880000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\xcf\\xab\\xc3@'\np4186\ntp4187\nRp4188\ng4148\nF6470.0\ntp4189\na(I7890000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\x1c\\xbb\\xc3@'\np4190\ntp4191\nRp4192\ng4148\nF10290.0\ntp4193\na(I7900000\ng1\n(g5\nS'H\\xe1z\\x14.p\\xc3@'\np4194\ntp4195\nRp4196\ng4148\nF6690.0\ntp4197\na(I7910000\ng1\n(g5\nS'=\\n\\xd7\\xa3pV\\xc3@'\np4198\ntp4199\nRp4200\ng4148\nF1284.0\ntp4201\na(I7920000\ng1\n(g5\nS'\\xa4p=\\n\\x17\\x19\\xc3@'\np4202\ntp4203\nRp4204\ng4148\nF11040.0\ntp4205\na(I7930000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\x8c\\xd7\\xc2@'\np4206\ntp4207\nRp4208\ng4148\nF8298.0\ntp4209\na(I7940000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\xc5\\xd7\\xc2@'\np4210\ntp4211\nRp4212\ng4148\nF12224.0\ntp4213\na(I7950000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99Y5\\xc2@'\np4214\ntp4215\nRp4216\ng4148\nF4092.0\ntp4217\na(I7960000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\xc5\\x0f\\xc2@'\np4218\ntp4219\nRp4220\ng4148\nF4832.0\ntp4221\na(I7970000\ng1\n(g5\nS'fffff\\x06\\xc2@'\np4222\ntp4223\nRp4224\ng4148\nF9310.0\ntp4225\na(I7980000\ng1\n(g5\nS'\\xd7\\xa3p=\\x8a\\xf8\\xc1@'\np4226\ntp4227\nRp4228\ng4148\nF7264.0\ntp4229\na(I7990000\ng1\n(g5\nS'fffff\\xd0\\xc1@'\np4230\ntp4231\nRp4232\ng4148\nF5964.0\ntp4233\na(I8000000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f\\xfe\\xc1@'\np4234\ntp4235\nRp4236\ng4148\nF8012.0\ntp4237\na(I8010000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc7\\xe6\\xc1@'\np4238\ntp4239\nRp4240\ng4148\nF14694.0\ntp4241\na(I8020000\ng1\n(g5\nS'\\x85\\xebQ\\xb8^\\n\\xc2@'\np4242\ntp4243\nRp4244\ng4148\nF13646.0\ntp4245\na(I8030000\ng1\n(g5\nS'\\xa4p=\\n\\x97\\xc8\\xc1@'\np4246\ntp4247\nRp4248\ng4148\nF6864.0\ntp4249\na(I8040000\ng1\n(g5\nS'q=\\n\\xd7c\\xd8\\xc1@'\np4250\ntp4251\nRp4252\ng4148\nF9014.0\ntp4253\na(I8050000\ng1\n(g5\nS'\\n\\xd7\\xa3p}\\n\\xc2@'\np4254\ntp4255\nRp4256\ng4148\nF17340.0\ntp4257\na(I8060000\ng1\n(g5\nS'\\n\\xd7\\xa3p}\\x0b\\xc2@'\np4258\ntp4259\nRp4260\ng4148\nF5880.0\ntp4261\na(I8070000\ng1\n(g5\nS'\\x1f\\x85\\xebQx\\xf9\\xc1@'\np4262\ntp4263\nRp4264\ng4148\nF5924.0\ntp4265\na(I8080000\ng1\n(g5\nS'3333s\\x1b\\xc2@'\np4266\ntp4267\nRp4268\ng4148\nF15536.0\ntp4269\na(I8090000\ng1\n(g5\nS'\\n\\xd7\\xa3p}G\\xc2@'\np4270\ntp4271\nRp4272\ng4148\nF15240.0\ntp4273\na(I8100000\ng1\n(g5\nS'R\\xb8\\x1e\\x85kY\\xc2@'\np4274\ntp4275\nRp4276\ng4148\nF16788.0\ntp4277\na(I8110000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x8b\\xc2@'\np4278\ntp4279\nRp4280\ng4148\nF14618.0\ntp4281\na(I8120000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\x1c\\x87\\xc2@'\np4282\ntp4283\nRp4284\ng4148\nF8764.0\ntp4285\na(I8130000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f\\x8a\\xc2@'\np4286\ntp4287\nRp4288\ng4148\nF7446.0\ntp4289\na(I8140000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f\\x8a\\xc2@'\np4290\ntp4291\nRp4292\ng4148\nF7446.0\ntp4293\na(I8150000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5h\\xa2\\xc2@'\np4294\ntp4295\nRp4296\ng4148\nF6762.0\ntp4297\na(I8160000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\xcf\\xa2\\xc2@'\np4298\ntp4299\nRp4300\ng4148\nF8962.0\ntp4301\na(I8170000\ng1\n(g5\nS'\\xd7\\xa3p=J\\x7f\\xc2@'\np4302\ntp4303\nRp4304\ng4148\nF6804.0\ntp4305\na(I8180000\ng1\n(g5\nS'=\\n\\xd7\\xa30x\\xc2@'\np4306\ntp4307\nRp4308\ng4148\nF8172.0\ntp4309\na(I8190000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xf8t\\xc2@'\np4310\ntp4311\nRp4312\ng4148\nF7576.0\ntp4313\na(I8200000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xf8\\x80\\xc2@'\np4314\ntp4315\nRp4316\ng4148\nF9460.0\ntp4317\na(I8210000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\x82b\\xc2@'\np4318\ntp4319\nRp4320\ng4148\nF5730.0\ntp4321\na(I8220000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\\\\\xc2@'\np4322\ntp4323\nRp4324\ng4148\nF4928.0\ntp4325\na(I8230000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1A\\xc2@'\np4326\ntp4327\nRp4328\ng4148\nF7230.0\ntp4329\na(I8240000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeL\\xc2@'\np4330\ntp4331\nRp4332\ng4148\nF17724.0\ntp4333\na(I8250000\ng1\n(g5\nS'\\xd7\\xa3p=\\x8a\\x10\\xc2@'\np4334\ntp4335\nRp4336\ng4148\nF8584.0\ntp4337\na(I8260000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xde\\xc1@'\np4338\ntp4339\nRp4340\ng4148\nF4320.0\ntp4341\na(I8270000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xe2\\xc1@'\np4342\ntp4343\nRp4344\ng4148\nF15090.0\ntp4345\na(I8280000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xf5\\xc1@'\np4346\ntp4347\nRp4348\ng4148\nF6864.0\ntp4349\na(I8290000\ng1\n(g5\nS'q=\\n\\xd7c\\xa3\\xc1@'\np4350\ntp4351\nRp4352\ng4148\nF7380.0\ntp4353\na(I8300000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\x91\\xc9\\xc1@'\np4354\ntp4355\nRp4356\ng4148\nF13890.0\ntp4357\na(I8310000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8\\xa4\\xc1@'\np4358\ntp4359\nRp4360\ng4148\nF4604.0\ntp4361\na(I8320000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\x02\\xb3\\xc1@'\np4362\ntp4363\nRp4364\ng4148\nF8838.0\ntp4365\na(I8330000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\xcd\\xc1@'\np4366\ntp4367\nRp4368\ng4148\nF14400.0\ntp4369\na(I8340000\ng1\n(g5\nS'{\\x14\\xaeG\\xa1\\xac\\xc1@'\np4370\ntp4371\nRp4372\ng4148\nF7762.0\ntp4373\na(I8350000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\"\\xc1@'\np4374\ntp4375\nRp4376\ng4148\nF7622.0\ntp4377\na(I8360000\ng1\n(g5\nS'{\\x14\\xaeG\\xa1 \\xc1@'\np4378\ntp4379\nRp4380\ng4148\nF6810.0\ntp4381\na(I8370000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xdf\\xc0@'\np4382\ntp4383\nRp4384\ng4148\nF6414.0\ntp4385\na(I8380000\ng1\n(g5\nS'H\\xe1z\\x14n\\xfc\\xc0@'\np4386\ntp4387\nRp4388\ng4148\nF9044.0\ntp4389\na(I8390000\ng1\n(g5\nS'H\\xe1z\\x14\\xee\\xf5\\xc0@'\np4390\ntp4391\nRp4392\ng4148\nF5696.0\ntp4393\na(I8400000\ng1\n(g5\nS'{\\x14\\xaeG!\\x1d\\xc1@'\np4394\ntp4395\nRp4396\ng4148\nF15850.0\ntp4397\na(I8410000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\xd9\\xf3\\xc0@'\np4398\ntp4399\nRp4400\ng4148\nF6960.0\ntp4401\na(I8420000\ng1\n(g5\nS')\\\\\\x8f\\xc2u\\x03\\xc1@'\np4402\ntp4403\nRp4404\ng4148\nF7386.0\ntp4405\na(I8430000\ng1\n(g5\nS'H\\xe1z\\x14n\\xfe\\xc0@'\np4406\ntp4407\nRp4408\ng4148\nF6538.0\ntp4409\na(I8440000\ng1\n(g5\nS'{\\x14\\xaeG\\xa1\\xf7\\xc0@'\np4410\ntp4411\nRp4412\ng4148\nF6390.0\ntp4413\na(I8450000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x19@\\xc1@'\np4414\ntp4415\nRp4416\ng4148\nF20170.0\ntp4417\na(I8460000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\xc7\\x82\\xc1@'\np4418\ntp4419\nRp4420\ng4148\nF19864.0\ntp4421\na(I8470000\ng1\n(g5\nS')\\\\\\x8f\\xc25j\\xc1@'\np4422\ntp4423\nRp4424\ng4148\nF4860.0\ntp4425\na(I8480000\ng1\n(g5\nS'\\xa4p=\\n\\x17\\x9c\\xc1@'\np4426\ntp4427\nRp4428\ng4148\nF14360.0\ntp4429\na(I8490000\ng1\n(g5\nS'3333\\xf3\\x87\\xc1@'\np4430\ntp4431\nRp4432\ng4148\nF7486.0\ntp4433\na(I8500000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\xd1\\xa7\\xc1@'\np4434\ntp4435\nRp4436\ng4148\nF11972.0\ntp4437\na(I8510000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\x8c\\xe5\\xc1@'\np4438\ntp4439\nRp4440\ng4148\nF9098.0\ntp4441\na(I8520000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xfc\\xc1@'\np4442\ntp4443\nRp4444\ng4148\nF10170.0\ntp4445\na(I8530000\ng1\n(g5\nS'3333\\xb3\\x08\\xc2@'\np4446\ntp4447\nRp4448\ng4148\nF10680.0\ntp4449\na(I8540000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x19.\\xc2@'\np4450\ntp4451\nRp4452\ng4148\nF14386.0\ntp4453\na(I8550000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x19H\\xc2@'\np4454\ntp4455\nRp4456\ng4148\nF11670.0\ntp4457\na(I8560000\ng1\n(g5\nS'3333\\xf3Y\\xc2@'\np4458\ntp4459\nRp4460\ng4148\nF13860.0\ntp4461\na(I8570000\ng1\n(g5\nS'\\xa4p=\\nWl\\xc2@'\np4462\ntp4463\nRp4464\ng4148\nF11112.0\ntp4465\na(I8580000\ng1\n(g5\nS'=\\n\\xd7\\xa30a\\xc2@'\np4466\ntp4467\nRp4468\ng4148\nF5544.0\ntp4469\na(I8590000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xfa\\x83\\xc2@'\np4470\ntp4471\nRp4472\ng4148\nF6402.0\ntp4473\na(I8600000\ng1\n(g5\nS'\\n\\xd7\\xa3p=u\\xc2@'\np4474\ntp4475\nRp4476\ng4148\nF6652.0\ntp4477\na(I8610000\ng1\n(g5\nS'\\x14\\xaeG\\xe1:j\\xc2@'\np4478\ntp4479\nRp4480\ng4148\nF6096.0\ntp4481\na(I8620000\ng1\n(g5\nS'\\xe1z\\x14\\xae\\x87J\\xc2@'\np4482\ntp4483\nRp4484\ng4148\nF7290.0\ntp4485\na(I8630000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x96\\xc2@'\np4486\ntp4487\nRp4488\ng4148\nF19202.0\ntp4489\na(I8640000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xbb\\xc2@'\np4490\ntp4491\nRp4492\ng4148\nF4898.0\ntp4493\na(I8650000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xf8\\xa5\\xc2@'\np4494\ntp4495\nRp4496\ng4148\nF4928.0\ntp4497\na(I8660000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xe8\\xbb\\xc2@'\np4498\ntp4499\nRp4500\ng4148\nF7038.0\ntp4501\na(I8670000\ng1\n(g5\nS'\\xc3\\xf5(\\\\O\\x9f\\xc2@'\np4502\ntp4503\nRp4504\ng4148\nF5666.0\ntp4505\na(I8680000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xfd\\xc2@'\np4506\ntp4507\nRp4508\ng4148\nF26910.0\ntp4509\na(I8690000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99Y\\xcb\\xc2@'\np4510\ntp4511\nRp4512\ng4148\nF4604.0\ntp4513\na(I8700000\ng1\n(g5\nS'{\\x14\\xaeG!\\xe0\\xc2@'\np4514\ntp4515\nRp4516\ng4148\nF7416.0\ntp4517\na(I8710000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\xcf\\xf8\\xc2@'\np4518\ntp4519\nRp4520\ng4148\nF11800.0\ntp4521\na(I8720000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x15\\xc3@'\np4522\ntp4523\nRp4524\ng4148\nF14756.0\ntp4525\na(I8730000\ng1\n(g5\nS'\\x14\\xaeG\\xe1:\\xe9\\xc2@'\np4526\ntp4527\nRp4528\ng4148\nF8482.0\ntp4529\na(I8740000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8\\x05\\xc3@'\np4530\ntp4531\nRp4532\ng4148\nF6156.0\ntp4533\na(I8750000\ng1\n(g5\nS'\\xd7\\xa3p=\\xca\\t\\xc3@'\np4534\ntp4535\nRp4536\ng4148\nF8420.0\ntp4537\na(I8760000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\xde!\\xc3@'\np4538\ntp4539\nRp4540\ng4148\nF10740.0\ntp4541\na(I8770000\ng1\n(g5\nS'\\xa4p=\\nW\\x19\\xc3@'\np4542\ntp4543\nRp4544\ng4148\nF10490.0\ntp4545\na(I8780000\ng1\n(g5\nS'ffff\\xe6\\xe4\\xc2@'\np4546\ntp4547\nRp4548\ng4148\nF6300.0\ntp4549\na(I8790000\ng1\n(g5\nS'\\x85\\xebQ\\xb8^\\xcf\\xc2@'\np4550\ntp4551\nRp4552\ng4148\nF10312.0\ntp4553\na(I8800000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xee\\xc2@'\np4554\ntp4555\nRp4556\ng4148\nF9660.0\ntp4557\na(I8810000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xf7\\xc2@'\np4558\ntp4559\nRp4560\ng4148\nF10566.0\ntp4561\na(I8820000\ng1\n(g5\nS'\\n\\xd7\\xa3p}\\xa7\\xc2@'\np4562\ntp4563\nRp4564\ng4148\nF4320.0\ntp4565\na(I8830000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\xa2\\xc2@'\np4566\ntp4567\nRp4568\ng4148\nF6690.0\ntp4569\na(I8840000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xca\\xc2@'\np4570\ntp4571\nRp4572\ng4148\nF12420.0\ntp4573\na(I8850000\ng1\n(g5\nS'q=\\n\\xd7c\\xc5\\xc2@'\np4574\ntp4575\nRp4576\ng4148\nF8010.0\ntp4577\na(I8860000\ng1\n(g5\nS'\\xc3\\xf5(\\\\O\\xab\\xc2@'\np4578\ntp4579\nRp4580\ng4148\nF6274.0\ntp4581\na(I8870000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xa0\\xc2@'\np4582\ntp4583\nRp4584\ng4148\nF7326.0\ntp4585\na(I8880000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xb6\\xc2@'\np4586\ntp4587\nRp4588\ng4148\nF13064.0\ntp4589\na(I8890000\ng1\n(g5\nS'{\\x14\\xaeGa\\xc5\\xc2@'\np4590\ntp4591\nRp4592\ng4148\nF5348.0\ntp4593\na(I8900000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xc6\\xc2@'\np4594\ntp4595\nRp4596\ng4148\nF7386.0\ntp4597\na(I8910000\ng1\n(g5\nS'{\\x14\\xaeG!\\x9f\\xc2@'\np4598\ntp4599\nRp4600\ng4148\nF15312.0\ntp4601\na(I8920000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xf8\\x8f\\xc2@'\np4602\ntp4603\nRp4604\ng4148\nF5552.0\ntp4605\na(I8930000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\xbe\\xc2@'\np4606\ntp4607\nRp4608\ng4148\nF8690.0\ntp4609\na(I8940000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5h\\xab\\xc2@'\np4610\ntp4611\nRp4612\ng4148\nF11200.0\ntp4613\na(I8950000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\x11\\xa8\\xc2@'\np4614\ntp4615\nRp4616\ng4148\nF5212.0\ntp4617\na(I8960000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xac\\xc2@'\np4618\ntp4619\nRp4620\ng4148\nF5812.0\ntp4621\na(I8970000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\xcf\\xb5\\xc2@'\np4622\ntp4623\nRp4624\ng4148\nF15660.0\ntp4625\na(I8980000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xf8\\xaf\\xc2@'\np4626\ntp4627\nRp4628\ng4148\nF12294.0\ntp4629\na(I8990000\ng1\n(g5\nS'33333\\xf7\\xc2@'\np4630\ntp4631\nRp4632\ng4148\nF18850.0\ntp4633\na(I9000000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccL\\xf5\\xc2@'\np4634\ntp4635\nRp4636\ng4148\nF8458.0\ntp4637\na(I9010000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x80\\x04\\xc3@'\np4638\ntp4639\nRp4640\ng4148\nF8750.0\ntp4641\na(I9020000\ng1\n(g5\nS'{\\x14\\xaeGa\\xf1\\xc2@'\np4642\ntp4643\nRp4644\ng4148\nF4284.0\ntp4645\na(I9030000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xc3\\xc2@'\np4646\ntp4647\nRp4648\ng4148\nF2552.0\ntp4649\na(I9040000\ng1\n(g5\nS'=\\n\\xd7\\xa30\\xf6\\xc2@'\np4650\ntp4651\nRp4652\ng4148\nF16460.0\ntp4653\na(I9050000\ng1\n(g5\nS'=\\n\\xd7\\xa30\\xf6\\xc2@'\np4654\ntp4655\nRp4656\ng4148\nF16460.0\ntp4657\na(I9060000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x19A\\xc3@'\np4658\ntp4659\nRp4660\ng4148\nF14310.0\ntp4661\na(I9070000\ng1\n(g5\nS'\\x85\\xebQ\\xb8^X\\xc3@'\np4662\ntp4663\nRp4664\ng4148\nF10350.0\ntp4665\na(I9080000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8,\\xc3@'\np4666\ntp4667\nRp4668\ng4148\nF8764.0\ntp4669\na(I9090000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\x11\\xfb\\xc2@'\np4670\ntp4671\nRp4672\ng4148\nF9480.0\ntp4673\na(I9100000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x0e\\xc3@'\np4674\ntp4675\nRp4676\ng4148\nF7956.0\ntp4677\na(I9110000\ng1\n(g5\nS'R\\xb8\\x1e\\x85k\\x06\\xc3@'\np4678\ntp4679\nRp4680\ng4148\nF13094.0\ntp4681\na(I9120000\ng1\n(g5\nS\"\\x1f\\x85\\xebQx'\\xc3@\"\np4682\ntp4683\nRp4684\ng4148\nF13000.0\ntp4685\na(I9130000\ng1\n(g5\nS'\\xecQ\\xb8\\x1eE\\xab\\xc2@'\np4686\ntp4687\nRp4688\ng4148\nF5858.0\ntp4689\na(I9140000\ng1\n(g5\nS'q=\\n\\xd7c\\xa6\\xc2@'\np4690\ntp4691\nRp4692\ng4148\nF5726.0\ntp4693\na(I9150000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5h\\xdb\\xc2@'\np4694\ntp4695\nRp4696\ng4148\nF24964.0\ntp4697\na(I9160000\ng1\n(g5\nS'\\x14\\xaeG\\xe1:\\xaf\\xc2@'\np4698\ntp4699\nRp4700\ng4148\nF6210.0\ntp4701\na(I9170000\ng1\n(g5\nS'\\xd7\\xa3p=J\\x93\\xc2@'\np4702\ntp4703\nRp4704\ng4148\nF8132.0\ntp4705\na(I9180000\ng1\n(g5\nS'3333s\\x91\\xc2@'\np4706\ntp4707\nRp4708\ng4148\nF4350.0\ntp4709\na(I9190000\ng1\n(g5\nS'R\\xb8\\x1e\\x85k\\xc0\\xc2@'\np4710\ntp4711\nRp4712\ng4148\nF19284.0\ntp4713\na(I9200000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eu\\xc2@'\np4714\ntp4715\nRp4716\ng4148\nF8002.0\ntp4717\na(I9210000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99?\\xc2@'\np4718\ntp4719\nRp4720\ng4148\nF8386.0\ntp4721\na(I9220000\ng1\n(g5\nS'\\x85\\xebQ\\xb8^B\\xc2@'\np4722\ntp4723\nRp4724\ng4148\nF8794.0\ntp4725\na(I9230000\ng1\n(g5\nS'\\xecQ\\xb8\\x1eEP\\xc2@'\np4726\ntp4727\nRp4728\ng4148\nF13892.0\ntp4729\na(I9240000\ng1\n(g5\nS'q=\\n\\xd7#\\x7f\\xc2@'\np4730\ntp4731\nRp4732\ng4148\nF6678.0\ntp4733\na(I9250000\ng1\n(g5\nS'\\x14\\xaeG\\xe1\\xba\\x86\\xc2@'\np4734\ntp4735\nRp4736\ng4148\nF7920.0\ntp4737\na(I9260000\ng1\n(g5\nS'\\xa4p=\\nW\\x93\\xc2@'\np4738\ntp4739\nRp4740\ng4148\nF7500.0\ntp4741\na(I9270000\ng1\n(g5\nS'ffff&\\x95\\xc2@'\np4742\ntp4743\nRp4744\ng4148\nF6724.0\ntp4745\na(I9280000\ng1\n(g5\nS'\\xaeG\\xe1zT\\xc8\\xc2@'\np4746\ntp4747\nRp4748\ng4148\nF17526.0\ntp4749\na(I9290000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\x11\\x9e\\xc2@'\np4750\ntp4751\nRp4752\ng4148\nF10750.0\ntp4753\na(I9300000\ng1\n(g5\nS'R\\xb8\\x1e\\x85k\\xa8\\xc2@'\np4754\ntp4755\nRp4756\ng4148\nF10920.0\ntp4757\na(I9310000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xb0\\xb6\\xc2@'\np4758\ntp4759\nRp4760\ng4148\nF7782.0\ntp4761\na(I9320000\ng1\n(g5\nS'ffff\\xa6\\xdb\\xc2@'\np4762\ntp4763\nRp4764\ng4148\nF18642.0\ntp4765\na(I9330000\ng1\n(g5\nS'3333\\xf3\\xd3\\xc2@'\np4766\ntp4767\nRp4768\ng4148\nF8346.0\ntp4769\na(I9340000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xa8w\\xc2@'\np4770\ntp4771\nRp4772\ng4148\nF8452.0\ntp4773\na(I9350000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xe8n\\xc2@'\np4774\ntp4775\nRp4776\ng4148\nF8122.0\ntp4777\na(I9360000\ng1\n(g5\nS'\\xd7\\xa3p=\\xcat\\xc2@'\np4778\ntp4779\nRp4780\ng4148\nF8592.0\ntp4781\na(I9370000\ng1\n(g5\nS'{\\x14\\xaeGa\\x8f\\xc2@'\np4782\ntp4783\nRp4784\ng4148\nF17118.0\ntp4785\na(I9380000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\x9ch\\xc2@'\np4786\ntp4787\nRp4788\ng4148\nF7264.0\ntp4789\na(I9390000\ng1\n(g5\nS'\\n\\xd7\\xa3p=C\\xc2@'\np4790\ntp4791\nRp4792\ng4148\nF6810.0\ntp4793\na(I9400000\ng1\n(g5\nS'\\n\\xd7\\xa3p=@\\xc2@'\np4794\ntp4795\nRp4796\ng4148\nF5952.0\ntp4797\na(I9410000\ng1\n(g5\nS'H\\xe1z\\x14.5\\xc2@'\np4798\ntp4799\nRp4800\ng4148\nF8528.0\ntp4801\na(I9420000\ng1\n(g5\nS'ffff\\xe6\\x0c\\xc2@'\np4802\ntp4803\nRp4804\ng4148\nF5854.0\ntp4805\na(I9430000\ng1\n(g5\nS'3333\\xb3\\x0b\\xc2@'\np4806\ntp4807\nRp4808\ng4148\nF7912.0\ntp4809\na(I9440000\ng1\n(g5\nS'\\xd7\\xa3p=\\x8a\\xe2\\xc1@'\np4810\ntp4811\nRp4812\ng4148\nF5440.0\ntp4813\na(I9450000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x17\\xc2@'\np4814\ntp4815\nRp4816\ng4148\nF7668.0\ntp4817\na(I9460000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\xc5\\x19\\xc2@'\np4818\ntp4819\nRp4820\ng4148\nF11120.0\ntp4821\na(I9470000\ng1\n(g5\nS'\\xecQ\\xb8\\x1eE(\\xc2@'\np4822\ntp4823\nRp4824\ng4148\nF5666.0\ntp4825\na(I9480000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xf85\\xc2@'\np4826\ntp4827\nRp4828\ng4148\nF5500.0\ntp4829\na(I9490000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85/\\xc2@'\np4830\ntp4831\nRp4832\ng4148\nF11130.0\ntp4833\na(I9500000\ng1\n(g5\nS\"\\n\\xd7\\xa3p\\xfd'\\xc2@\"\np4834\ntp4835\nRp4836\ng4148\nF6504.0\ntp4837\na(I9510000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\x9cc\\xc2@'\np4838\ntp4839\nRp4840\ng4148\nF7176.0\ntp4841\na(I9520000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xa4\\xc2@'\np4842\ntp4843\nRp4844\ng4148\nF19240.0\ntp4845\na(I9530000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\x02\\xb1\\xc2@'\np4846\ntp4847\nRp4848\ng4148\nF9840.0\ntp4849\na(I9540000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xccL\\xcd\\xc2@'\np4850\ntp4851\nRp4852\ng4148\nF12618.0\ntp4853\na(I9550000\ng1\n(g5\nS'\\xaeG\\xe1z\\xd4\\xe5\\xc2@'\np4854\ntp4855\nRp4856\ng4148\nF17970.0\ntp4857\na(I9560000\ng1\n(g5\nS'{\\x14\\xaeGa\\x12\\xc3@'\np4858\ntp4859\nRp4860\ng4148\nF16338.0\ntp4861\na(I9570000\ng1\n(g5\nS'\\xa4p=\\nWl\\xc3@'\np4862\ntp4863\nRp4864\ng4148\nF23340.0\ntp4865\na(I9580000\ng1\n(g5\nS'\\xc3\\xf5(\\\\O\\x84\\xc3@'\np4866\ntp4867\nRp4868\ng4148\nF12180.0\ntp4869\na(I9590000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\xdeG\\xc3@'\np4870\ntp4871\nRp4872\ng4148\nF3964.0\ntp4873\na(I9600000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85e\\xc3@'\np4874\ntp4875\nRp4876\ng4148\nF16890.0\ntp4877\na(I9610000\ng1\n(g5\nS'\\x1f\\x85\\xebQ8p\\xc3@'\np4878\ntp4879\nRp4880\ng4148\nF10830.0\ntp4881\na(I9620000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x9eT\\xc3@'\np4882\ntp4883\nRp4884\ng4148\nF8734.0\ntp4885\na(I9630000\ng1\n(g5\nS'\\xaeG\\xe1z\\x94_\\xc3@'\np4886\ntp4887\nRp4888\ng4148\nF4928.0\ntp4889\na(I9640000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebt\\xc3@'\np4890\ntp4891\nRp4892\ng4148\nF10080.0\ntp4893\na(I9650000\ng1\n(g5\nS'=\\n\\xd7\\xa30N\\xc3@'\np4894\ntp4895\nRp4896\ng4148\nF11118.0\ntp4897\na(I9660000\ng1\n(g5\nS\"q=\\n\\xd7c'\\xc3@\"\np4898\ntp4899\nRp4900\ng4148\nF11090.0\ntp4901\na(I9670000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xeb\\x91,\\xc3@'\np4902\ntp4903\nRp4904\ng4148\nF9494.0\ntp4905\na(I9680000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5\\xe8,\\xc3@'\np4906\ntp4907\nRp4908\ng4148\nF17378.0\ntp4909\na(I9690000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\x9c=\\xc3@'\np4910\ntp4911\nRp4912\ng4148\nF12090.0\ntp4913\na(I9700000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x80\\xc3@'\np4914\ntp4915\nRp4916\ng4148\nF10848.0\ntp4917\na(I9710000\ng1\n(g5\nS'fffff\\x96\\xc3@'\np4918\ntp4919\nRp4920\ng4148\nF9888.0\ntp4921\na(I9720000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xfd\\xb6\\xc3@'\np4922\ntp4923\nRp4924\ng4148\nF8610.0\ntp4925\na(I9730000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x8c\\xc3@'\np4926\ntp4927\nRp4928\ng4148\nF7926.0\ntp4929\na(I9740000\ng1\n(g5\nS'\\xa4p=\\n\\x17s\\xc3@'\np4930\ntp4931\nRp4932\ng4148\nF14100.0\ntp4933\na(I9750000\ng1\n(g5\nS'\\xd7\\xa3p=\\n0\\xc3@'\np4934\ntp4935\nRp4936\ng4148\nF1380.0\ntp4937\na(I9760000\ng1\n(g5\nS'\\xf6(\\\\\\x8fBT\\xc3@'\np4938\ntp4939\nRp4940\ng4148\nF12460.0\ntp4941\na(I9770000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\xc0\\x9f\\xc3@'\np4942\ntp4943\nRp4944\ng4148\nF23862.0\ntp4945\na(I9780000\ng1\n(g5\nS'\\xaeG\\xe1z\\xd4\\xae\\xc3@'\np4946\ntp4947\nRp4948\ng4148\nF10018.0\ntp4949\na(I9790000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\x82\\x88\\xc3@'\np4950\ntp4951\nRp4952\ng4148\nF6322.0\ntp4953\na(I9800000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5x\\xc3@'\np4954\ntp4955\nRp4956\ng4148\nF9890.0\ntp4957\na(I9810000\ng1\n(g5\nS')\\\\\\x8f\\xc2u~\\xc3@'\np4958\ntp4959\nRp4960\ng4148\nF5608.0\ntp4961\na(I9820000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xfd\\x8f\\xc3@'\np4962\ntp4963\nRp4964\ng4148\nF9896.0\ntp4965\na(I9830000\ng1\n(g5\nS'{\\x14\\xaeG!O\\xc3@'\np4966\ntp4967\nRp4968\ng4148\nF6444.0\ntp4969\na(I9840000\ng1\n(g5\nS'\\n\\xd7\\xa3p\\xfd|\\xc3@'\np4970\ntp4971\nRp4972\ng4148\nF13584.0\ntp4973\na(I9850000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xa9\\xc3@'\np4974\ntp4975\nRp4976\ng4148\nF15116.0\ntp4977\na(I9860000\ng1\n(g5\nS')\\\\\\x8f\\xc2u\\xc0\\xc3@'\np4978\ntp4979\nRp4980\ng4148\nF12720.0\ntp4981\na(I9870000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\xdc\\xb2\\xc3@'\np4982\ntp4983\nRp4984\ng4148\nF9220.0\ntp4985\na(I9880000\ng1\n(g5\nS'=\\n\\xd7\\xa3\\xf0\\x85\\xc3@'\np4986\ntp4987\nRp4988\ng4148\nF10300.0\ntp4989\na(I9890000\ng1\n(g5\nS'=\\n\\xd7\\xa30\\xaf\\xc3@'\np4990\ntp4991\nRp4992\ng4148\nF10254.0\ntp4993\na(I9900000\ng1\n(g5\nS'\\xaeG\\xe1z\\xd4\\xbd\\xc3@'\np4994\ntp4995\nRp4996\ng4148\nF5730.0\ntp4997\na(I9910000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\x8c\\xb9\\xc3@'\np4998\ntp4999\nRp5000\ng4148\nF8374.0\ntp5001\na(I9920000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x05\\x99\\xc3@'\np5002\ntp5003\nRp5004\ng4148\nF7386.0\ntp5005\na(I9930000\ng1\n(g5\nS'\\n\\xd7\\xa3p}\\x93\\xc3@'\np5006\ntp5007\nRp5008\ng4148\nF6258.0\ntp5009\na(I9940000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x91\\xc3@'\np5010\ntp5011\nRp5012\ng4148\nF7470.0\ntp5013\na(I9950000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x0f\\xae\\xc3@'\np5014\ntp5015\nRp5016\ng4148\nF18198.0\ntp5017\na(I9953926\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa2\\xc3@'\np5018\ntp5019\nRp5020\ng4148\nF5280.0\ntp5021\na.(lp0\nF308.0\naF176.0\naF308.0\naF264.0\naF440.0\naF176.0\naF528.0\naF528.0\naF176.0\naF484.0\naF176.0\naF264.0\naF396.0\naF220.0\naF484.0\naF352.0\naF176.0\naF660.0\naF352.0\naF440.0\naF440.0\naF572.0\naF616.0\naF132.0\naF308.0\naF308.0\naF220.0\naF352.0\naF440.0\naF264.0\naF528.0\naF396.0\naF264.0\naF484.0\naF616.0\naF440.0\naF264.0\naF220.0\naF440.0\naF572.0\naF528.0\naF132.0\naF396.0\naF220.0\naF220.0\naF352.0\naF484.0\naF440.0\naF572.0\naF352.0\naF396.0\naF220.0\naF352.0\naF572.0\naF264.0\naF176.0\naF660.0\naF220.0\naF352.0\naF528.0\naF396.0\naF308.0\naF220.0\naF352.0\naF484.0\naF264.0\naF440.0\naF176.0\naF220.0\naF352.0\naF220.0\naF440.0\naF528.0\naF352.0\naF176.0\naF220.0\naF572.0\naF440.0\naF572.0\naF308.0\naF132.0\naF440.0\naF264.0\naF396.0\naF88.0\naF264.0\naF528.0\naF264.0\naF264.0\naF264.0\naF308.0\naF528.0\naF264.0\naF308.0\naF352.0\naF572.0\naF572.0\naF440.0\naF132.0\naF308.0\naF220.0\naF264.0\naF440.0\naF264.0\naF440.0\naF352.0\naF440.0\naF396.0\naF572.0\naF660.0\naF308.0\naF660.0\naF396.0\naF132.0\naF660.0\naF220.0\naF396.0\naF352.0\naF528.0\naF484.0\naF352.0\naF176.0\naF440.0\naF616.0\naF352.0\naF616.0\naF308.0\naF440.0\naF264.0\naF484.0\naF176.0\naF528.0\naF396.0\naF528.0\naF264.0\naF440.0\naF176.0\naF352.0\naF176.0\naF220.0\naF396.0\naF352.0\naF352.0\naF308.0\naF176.0\naF176.0\naF176.0\naF616.0\naF308.0\naF308.0\naF220.0\naF352.0\naF440.0\naF440.0\naF660.0\naF660.0\naF220.0\naF484.0\naF352.0\naF440.0\naF528.0\naF528.0\naF396.0\naF308.0\naF660.0\naF220.0\naF660.0\naF484.0\naF572.0\naF264.0\naF484.0\naF616.0\naF352.0\naF396.0\naF528.0\naF440.0\naF220.0\naF220.0\naF176.0\naF220.0\naF396.0\naF616.0\naF264.0\naF396.0\naF660.0\naF352.0\naF220.0\naF220.0\naF220.0\naF220.0\naF440.0\naF352.0\naF176.0\naF396.0\naF308.0\naF176.0\naF220.0\naF572.0\naF352.0\naF440.0\naF308.0\naF440.0\naF396.0\naF396.0\naF660.0\naF264.0\naF264.0\naF528.0\naF0.0\naF308.0\naF440.0\naF440.0\naF616.0\naF220.0\naF220.0\naF352.0\naF308.0\naF176.0\naF484.0\naF88.0\naF396.0\naF396.0\naF308.0\naF220.0\naF396.0\naF528.0\naF264.0\naF264.0\naF308.0\naF308.0\naF396.0\naF440.0\naF264.0\naF220.0\naF220.0\naF396.0\naF264.0\naF264.0\naF264.0\naF264.0\naF396.0\naF660.0\naF220.0\naF220.0\naF396.0\naF484.0\naF308.0\naF440.0\naF132.0\naF572.0\naF440.0\naF220.0\naF264.0\naF440.0\naF132.0\naF352.0\naF264.0\naF220.0\naF484.0\naF220.0\naF220.0\naF176.0\naF44.0\naF484.0\naF396.0\naF572.0\naF176.0\naF528.0\naF220.0\naF440.0\naF528.0\naF308.0\naF660.0\naF176.0\naF44.0\naF176.0\naF484.0\naF308.0\naF220.0\naF220.0\naF352.0\naF220.0\naF708.0\naF440.0\naF484.0\naF264.0\naF660.0\naF396.0\naF484.0\naF660.0\naF528.0\naF308.0\naF220.0\naF44.0\naF220.0\naF660.0\naF396.0\naF308.0\naF440.0\naF176.0\naF352.0\naF44.0\naF308.0\naF484.0\naF440.0\naF440.0\naF440.0\naF528.0\naF88.0\naF264.0\naF308.0\naF528.0\naF440.0\naF440.0\naF396.0\naF528.0\naF132.0\naF264.0\naF440.0\naF132.0\naF132.0\naF484.0\naF308.0\naF396.0\naF264.0\naF528.0\naF528.0\naF440.0\naF440.0\naF528.0\naF660.0\naF264.0\naF308.0\naF176.0\naF308.0\naF396.0\naF220.0\naF264.0\naF572.0\naF132.0\naF484.0\naF88.0\naF88.0\naF352.0\naF352.0\naF484.0\naF264.0\naF528.0\naF264.0\naF440.0\naF176.0\naF264.0\naF440.0\naF176.0\naF440.0\naF572.0\naF132.0\naF352.0\naF308.0\naF220.0\naF484.0\naF220.0\naF220.0\naF572.0\naF396.0\naF352.0\naF484.0\naF220.0\naF440.0\naF660.0\naF308.0\naF528.0\naF264.0\naF484.0\naF176.0\naF308.0\naF440.0\naF440.0\naF440.0\naF396.0\naF176.0\naF220.0\naF528.0\naF220.0\naF132.0\naF440.0\naF264.0\naF220.0\naF132.0\naF220.0\naF308.0\naF660.0\naF308.0\naF220.0\naF616.0\naF396.0\naF308.0\naF308.0\naF528.0\naF528.0\naF308.0\naF484.0\naF176.0\naF396.0\naF264.0\naF616.0\naF308.0\naF352.0\naF440.0\naF0.0\naF308.0\naF220.0\naF352.0\naF528.0\naF264.0\naF440.0\naF176.0\naF352.0\naF572.0\naF616.0\naF528.0\naF176.0\naF616.0\naF660.0\naF396.0\naF396.0\naF132.0\naF440.0\naF176.0\naF572.0\naF616.0\naF616.0\naF264.0\naF308.0\naF528.0\naF220.0\naF308.0\naF176.0\naF708.0\naF308.0\naF176.0\naF220.0\naF176.0\naF396.0\naF264.0\naF352.0\naF308.0\naF132.0\naF660.0\naF660.0\naF396.0\naF352.0\naF528.0\naF572.0\naF220.0\naF572.0\naF440.0\naF264.0\naF264.0\naF308.0\naF484.0\naF132.0\naF440.0\naF440.0\naF708.0\naF708.0\naF220.0\naF308.0\naF132.0\naF352.0\naF572.0\naF176.0\naF396.0\naF352.0\naF220.0\naF220.0\naF396.0\naF352.0\naF264.0\naF352.0\naF220.0\naF484.0\naF176.0\naF440.0\naF352.0\naF440.0\naF572.0\naF528.0\naF308.0\naF440.0\naF660.0\naF220.0\naF440.0\naF616.0\naF572.0\naF352.0\naF264.0\naF352.0\naF264.0\naF264.0\naF528.0\naF484.0\naF484.0\naF484.0\naF264.0\naF352.0\naF484.0\naF132.0\naF616.0\naF132.0\naF396.0\naF396.0\naF396.0\naF484.0\naF528.0\naF572.0\naF176.0\naF396.0\naF440.0\naF572.0\naF308.0\naF220.0\naF352.0\naF220.0\naF220.0\naF132.0\naF440.0\naF396.0\naF352.0\naF528.0\naF440.0\naF616.0\naF264.0\naF352.0\naF176.0\naF352.0\naF484.0\naF176.0\naF220.0\naF132.0\naF396.0\naF176.0\naF176.0\naF308.0\naF616.0\naF176.0\naF220.0\naF484.0\naF44.0\naF220.0\naF352.0\naF440.0\naF264.0\naF484.0\naF308.0\naF264.0\naF176.0\naF440.0\naF396.0\naF440.0\naF264.0\naF132.0\naF616.0\naF220.0\naF660.0\naF440.0\naF352.0\naF440.0\naF352.0\naF660.0\naF132.0\naF44.0\naF176.0\naF528.0\naF176.0\naF352.0\naF264.0\naF264.0\naF44.0\naF484.0\naF308.0\naF308.0\naF440.0\naF528.0\naF528.0\naF528.0\naF308.0\naF396.0\naF484.0\naF528.0\naF264.0\naF396.0\naF308.0\naF396.0\naF132.0\naF88.0\naF176.0\naF220.0\naF308.0\naF44.0\naF264.0\naF308.0\naF484.0\naF308.0\naF176.0\naF220.0\naF176.0\naF176.0\naF220.0\naF132.0\naF572.0\naF660.0\naF352.0\naF484.0\naF308.0\naF352.0\naF528.0\naF396.0\naF176.0\naF440.0\naF660.0\naF264.0\naF176.0\naF176.0\naF220.0\naF308.0\naF484.0\naF440.0\naF220.0\naF440.0\naF396.0\naF484.0\naF660.0\naF352.0\naF572.0\naF396.0\naF308.0\naF264.0\naF132.0\naF220.0\naF88.0\naF484.0\naF264.0\naF660.0\naF352.0\naF176.0\naF132.0\naF308.0\naF308.0\naF88.0\naF352.0\naF132.0\naF484.0\naF528.0\naF44.0\naF220.0\naF308.0\naF176.0\naF308.0\naF660.0\naF616.0\naF484.0\naF708.0\naF440.0\naF308.0\naF220.0\naF616.0\naF572.0\naF616.0\naF484.0\naF572.0\naF264.0\naF660.0\naF484.0\naF396.0\naF308.0\naF220.0\naF176.0\naF176.0\naF528.0\naF440.0\naF352.0\naF352.0\naF220.0\naF132.0\naF440.0\naF396.0\naF396.0\naF572.0\naF396.0\naF308.0\naF484.0\naF484.0\naF484.0\naF484.0\naF396.0\naF132.0\naF308.0\naF132.0\naF264.0\naF176.0\naF484.0\naF264.0\naF132.0\naF132.0\naF176.0\naF176.0\naF528.0\naF132.0\naF528.0\naF352.0\naF572.0\naF308.0\naF484.0\naF484.0\naF396.0\naF616.0\naF484.0\naF440.0\naF396.0\naF220.0\naF264.0\naF176.0\naF88.0\naF352.0\naF660.0\naF220.0\naF352.0\naF396.0\naF660.0\naF176.0\naF220.0\naF616.0\naF660.0\naF264.0\naF132.0\naF264.0\naF220.0\naF264.0\naF264.0\naF440.0\naF176.0\naF176.0\naF264.0\naF484.0\naF220.0\naF132.0\naF440.0\naF440.0\naF660.0\naF440.0\naF660.0\naF88.0\naF440.0\naF264.0\naF308.0\naF484.0\naF264.0\naF616.0\naF616.0\naF176.0\naF132.0\naF264.0\naF528.0\naF440.0\naF132.0\naF440.0\naF264.0\naF440.0\naF352.0\naF396.0\naF308.0\naF352.0\naF484.0\naF660.0\naF176.0\naF572.0\naF308.0\naF308.0\naF396.0\naF352.0\naF484.0\naF264.0\naF660.0\naF264.0\naF176.0\naF484.0\naF616.0\naF484.0\naF396.0\naF396.0\naF132.0\naF176.0\naF572.0\naF220.0\naF484.0\naF616.0\naF440.0\naF264.0\naF44.0\naF396.0\naF352.0\naF616.0\naF352.0\naF484.0\naF308.0\naF352.0\naF264.0\naF616.0\naF528.0\naF264.0\naF220.0\naF396.0\naF264.0\naF660.0\naF660.0\naF308.0\naF616.0\naF308.0\naF484.0\naF440.0\naF396.0\naF440.0\naF352.0\naF484.0\naF396.0\naF352.0\naF176.0\naF220.0\naF88.0\naF352.0\naF440.0\naF88.0\naF484.0\naF660.0\naF264.0\naF220.0\naF616.0\naF660.0\naF88.0\naF396.0\naF396.0\naF660.0\naF660.0\naF660.0\naF352.0\naF484.0\naF708.0\naF660.0\naF484.0\naF176.0\naF396.0\naF264.0\naF220.0\naF660.0\naF440.0\naF308.0\naF220.0\naF308.0\naF264.0\naF220.0\naF308.0\naF132.0\naF616.0\naF528.0\naF220.0\naF616.0\naF176.0\naF264.0\naF660.0\naF572.0\naF528.0\naF396.0\naF528.0\naF176.0\naF440.0\naF572.0\naF176.0\naF132.0\naF308.0\naF528.0\naF660.0\naF132.0\naF660.0\naF804.0\naF132.0\naF176.0\naF660.0\naF396.0\naF396.0\naF616.0\naF528.0\naF308.0\naF308.0\naF660.0\naF616.0\naF804.0\naF484.0\naF660.0\naF660.0\naF308.0\naF616.0\naF708.0\naF176.0\naF572.0\naF572.0\naF396.0\naF660.0\naF660.0\naF484.0\naF176.0\naF264.0\naF440.0\naF440.0\naF352.0\naF264.0\naF528.0\naF220.0\naF264.0\naF660.0\naF308.0\naF484.0\naF616.0\naF176.0\naF756.0\naF572.0\naF308.0\naF660.0\naF616.0\naF176.0\naF572.0\naF132.0\naF308.0\naF660.0\naF352.0\naF660.0\naF264.0\naF396.0\naF708.0\naF528.0\naF660.0\naF440.0\naF484.0\naF528.0\naF308.0\naF528.0\naF264.0\naF660.0\naF440.0\naF660.0\naF88.0\naF708.0\naF660.0\naF352.0\naF352.0\naF484.0\naF572.0\naF440.0\naF660.0\naF264.0\naF660.0\naF396.0\naF264.0\naF44.0\naF308.0\naF484.0\naF484.0\naF352.0\naF756.0\naF572.0\naF572.0\naF572.0\naF352.0\naF660.0\naF308.0\naF528.0\naF616.0\naF708.0\naF440.0\naF396.0\naF616.0\naF660.0\naF572.0\naF756.0\naF264.0\naF660.0\naF528.0\naF528.0\naF660.0\naF484.0\naF660.0\naF352.0\naF616.0\naF660.0\naF660.0\naF660.0\naF660.0\naF440.0\naF660.0\naF804.0\naF660.0\naF852.0\naF660.0\naF660.0\naF660.0\naF264.0\naF756.0\naF660.0\naF396.0\naF660.0\naF264.0\naF440.0\naF660.0\naF804.0\naF484.0\naF528.0\naF616.0\naF948.0\naF440.0\naF132.0\naF660.0\naF660.0\naF660.0\naF352.0\naF660.0\naF756.0\naF660.0\naF900.0\naF948.0\naF660.0\naF660.0\naF660.0\naF220.0\naF660.0\naF852.0\naF396.0\naF220.0\naF528.0\naF440.0\naF660.0\naF528.0\naF660.0\naF660.0\naF528.0\naF308.0\naF440.0\naF756.0\naF572.0\naF352.0\naF484.0\naF264.0\naF900.0\naF440.0\naF352.0\naF616.0\naF660.0\naF616.0\naF660.0\naF996.0\naF660.0\naF1236.0\naF660.0\naF616.0\naF708.0\naF708.0\naF660.0\naF708.0\naF660.0\naF660.0\naF616.0\naF396.0\naF900.0\naF996.0\naF900.0\naF660.0\naF1092.0\naF660.0\naF1140.0\naF660.0\naF616.0\naF484.0\naF660.0\naF528.0\naF948.0\naF660.0\naF396.0\naF528.0\naF660.0\naF484.0\naF352.0\naF616.0\naF396.0\naF572.0\naF660.0\naF804.0\naF852.0\naF852.0\naF804.0\naF132.0\naF572.0\naF616.0\naF852.0\naF572.0\naF660.0\naF852.0\naF660.0\naF440.0\naF484.0\naF352.0\naF996.0\naF852.0\naF396.0\naF484.0\naF572.0\naF660.0\naF996.0\naF660.0\naF1332.0\naF484.0\naF756.0\naF852.0\naF660.0\naF352.0\naF1044.0\naF1092.0\naF660.0\naF660.0\naF948.0\naF1044.0\naF708.0\naF948.0\naF440.0\naF440.0\naF660.0\naF708.0\naF1236.0\naF660.0\naF484.0\naF660.0\naF756.0\naF1044.0\naF484.0\naF660.0\naF1380.0\naF804.0\naF756.0\naF996.0\naF804.0\naF484.0\naF572.0\naF176.0\naF1236.0\naF440.0\naF352.0\naF616.0\naF660.0\naF264.0\naF484.0\naF220.0\naF660.0\naF660.0\naF708.0\naF660.0\naF660.0\naF660.0\naF756.0\naF852.0\naF996.0\naF996.0\naF756.0\naF804.0\naF308.0\naF708.0\naF1092.0\naF756.0\naF2160.0\naF804.0\naF396.0\naF396.0\naF804.0\naF900.0\naF708.0\naF756.0\naF1332.0\naF756.0\naF756.0\naF1284.0\naF616.0\naF2108.0\naF1284.0\naF1380.0\naF440.0\naF1380.0\naF996.0\naF756.0\naF1380.0\naF948.0\naF660.0\naF1092.0\naF1188.0\naF660.0\naF756.0\naF528.0\naF1044.0\naF1588.0\naF1092.0\naF660.0\naF1380.0\naF660.0\naF756.0\naF1380.0\naF1380.0\naF396.0\naF660.0\naF1380.0\naF756.0\naF900.0\naF1092.0\naF660.0\naF2108.0\naF1380.0\naF996.0\naF852.0\naF1380.0\naF572.0\naF1952.0\naF660.0\naF1332.0\naF616.0\naF660.0\naF948.0\naF440.0\naF352.0\naF756.0\naF660.0\naF1140.0\naF756.0\naF660.0\naF660.0\naF1332.0\naF708.0\naF1380.0\naF1332.0\naF1092.0\naF1692.0\naF660.0\naF756.0\naF1744.0\naF948.0\naF2216.0\naF756.0\naF660.0\naF1692.0\naF1284.0\naF660.0\naF852.0\naF1432.0\naF4230.0\naF1044.0\naF996.0\naF756.0\naF1796.0\naF900.0\naF616.0\naF1380.0\naF616.0\naF900.0\naF1536.0\naF220.0\naF528.0\naF660.0\naF660.0\naF1284.0\naF2384.0\naF852.0\naF900.0\naF616.0\naF804.0\naF352.0\naF1588.0\naF2160.0\naF1236.0\naF708.0\naF2860.0\naF708.0\naF2056.0\naF1092.0\naF1900.0\naF708.0\naF1380.0\naF440.0\naF1284.0\naF1432.0\naF1380.0\naF4500.0\naF2272.0\naF4170.0\naF1332.0\naF756.0\naF1380.0\naF1380.0\naF2552.0\naF2552.0\naF708.0\naF900.0\naF996.0\naF948.0\naF1900.0\naF1044.0\naF1332.0\naF1284.0\naF996.0\naF2108.0\naF2108.0\naF660.0\naF2004.0\naF1484.0\naF660.0\naF948.0\naF1432.0\naF1332.0\naF1284.0\naF1140.0\naF948.0\naF1284.0\naF1380.0\naF1188.0\naF804.0\naF1380.0\naF1380.0\naF1044.0\naF2160.0\naF1284.0\naF1044.0\naF2160.0\naF1092.0\naF2160.0\naF948.0\naF2160.0\naF1380.0\naF2692.0\naF1432.0\naF660.0\naF616.0\naF3364.0\naF1092.0\naF1380.0\naF2160.0\naF708.0\naF756.0\naF708.0\naF1188.0\naF2160.0\naF1092.0\naF1952.0\naF2056.0\naF804.0\naF2056.0\naF2108.0\naF2056.0\naF3060.0\naF2004.0\naF1380.0\naF1332.0\naF708.0\naF1044.0\naF852.0\naF1692.0\naF756.0\naF1692.0\naF1140.0\naF1284.0\naF1744.0\naF1332.0\naF1380.0\naF852.0\naF3000.0\naF708.0\naF1588.0\naF996.0\naF4350.0\naF1588.0\naF2692.0\naF1588.0\naF852.0\naF1332.0\naF3870.0\naF3000.0\naF2972.0\naF756.0\naF1484.0\naF3196.0\naF996.0\naF3084.0\naF1380.0\naF2860.0\naF2160.0\naF1044.0\naF2108.0\naF996.0\naF1236.0\naF2916.0\naF1140.0\naF900.0\naF1796.0\naF996.0\naF1284.0\naF2160.0\naF996.0\naF1284.0\naF2860.0\naF1332.0\naF1380.0\naF660.0\naF2944.0\naF2108.0\naF1332.0\naF3900.0\naF1380.0\naF1284.0\naF996.0\naF1044.0\naF1236.0\naF852.0\naF2888.0\naF1640.0\naF1140.0\naF1952.0\naF3000.0\naF1380.0\naF1380.0\naF1092.0\naF3028.0\naF2108.0\naF2108.0\naF1380.0\naF1380.0\naF1900.0\naF2160.0\naF2004.0\naF3308.0\naF1140.0\naF1188.0\naF3364.0\naF1380.0\naF1380.0\naF2160.0\naF2776.0\naF2972.0\naF2720.0\naF1380.0\naF804.0\naF1380.0\naF2056.0\naF660.0\naF852.0\naF1380.0\naF3140.0\naF1380.0\naF2664.0\naF3420.0\naF2108.0\naF2384.0\naF2888.0\naF1380.0\naF1332.0\naF1380.0\naF1380.0\naF996.0\naF3000.0\naF1380.0\naF2004.0\naF1380.0\naF1380.0\naF1380.0\naF2160.0\naF2804.0\naF1380.0\naF2552.0\naF1236.0\naF1536.0\naF1188.0\naF3900.0\naF5726.0\naF3480.0\naF4350.0\naF2160.0\naF1380.0\naF1536.0\naF1848.0\naF1952.0\naF1380.0\naF2004.0\naF996.0\naF1140.0\naF2160.0\naF5610.0\naF2160.0\naF4200.0\naF4448.0\naF4350.0\naF1692.0\naF2160.0\naF2160.0\naF2056.0\naF1692.0\naF1744.0\naF2160.0\naF3364.0\naF2776.0\naF1284.0\naF1952.0\naF1692.0\naF1692.0\naF1332.0\naF1952.0\naF3000.0\naF1640.0\naF3900.0\naF2720.0\naF2056.0\naF1744.0\naF1140.0\naF2160.0\naF1380.0\naF1236.0\naF2160.0\naF1332.0\naF3364.0\naF4740.0\naF4670.0\naF2328.0\naF3840.0\naF660.0\naF4478.0\naF4540.0\naF3000.0\naF2916.0\naF1692.0\naF4542.0\naF4350.0\naF3964.0\naF5474.0\naF4958.0\naF2860.0\naF3840.0\naF5268.0\naF6198.0\naF3660.0\naF3000.0\naF2664.0\naF3420.0\naF4384.0\naF2328.0\naF3420.0\naF2552.0\naF5726.0\naF4384.0\naF2160.0\naF2916.0\naF2720.0\naF5278.0\naF2440.0\naF3360.0\naF4156.0\naF4500.0\naF4320.0\naF4220.0\naF852.0\naF4156.0\naF7878.0\naF5734.0\naF1848.0\naF3616.0\naF3420.0\naF3000.0\naF2440.0\naF5280.0\naF2496.0\naF2004.0\naF3000.0\naF5602.0\naF5544.0\naF3000.0\naF3000.0\naF4110.0\naF1744.0\naF4220.0\naF4320.0\naF3360.0\naF3420.0\naF3900.0\naF6112.0\naF5508.0\naF3420.0\naF1796.0\naF3336.0\naF1900.0\naF4734.0\naF5408.0\naF4960.0\naF2720.0\naF2160.0\naF5310.0\naF1380.0\naF996.0\naF2552.0\naF2888.0\naF4604.0\naF3000.0\naF4320.0\naF5340.0\naF3900.0\naF1848.0\naF4140.0\naF5474.0\naF2004.0\naF5676.0\naF6596.0\naF4740.0\naF5190.0\naF6092.0\naF5676.0\naF1848.0\naF4320.0\naF6482.0\naF4348.0\naF5662.0\naF1044.0\naF2720.0\naF2160.0\naF3840.0\naF1900.0\naF1640.0\naF4862.0\naF4050.0\naF3000.0\naF5884.0\naF4700.0\naF4604.0\naF5310.0\naF5312.0\naF3000.0\naF5312.0\naF5280.0\naF3420.0\naF3000.0\naF3964.0\naF1188.0\naF4540.0\naF2832.0\naF3900.0\naF4770.0\naF4926.0\naF3420.0\naF4860.0\naF5718.0\naF3540.0\naF4640.0\naF3480.0\naF5446.0\naF4640.0\naF4260.0\naF5726.0\naF4412.0\naF4604.0\naF4284.0\naF4140.0\naF3900.0\naF3900.0\naF1952.0\naF3964.0\naF5786.0\naF3060.0\naF9050.0\naF8512.0\naF2664.0\naF2160.0\naF2888.0\naF1952.0\naF4604.0\naF6082.0\naF3840.0\naF5378.0\naF1900.0\naF2552.0\naF3900.0\naF6180.0\naF3000.0\naF4220.0\naF6576.0\naF3660.0\naF4444.0\naF4960.0\naF5090.0\naF3900.0\naF4350.0\naF1900.0\naF2004.0\naF5444.0\naF2108.0\naF3660.0\naF3000.0\naF3900.0\naF5500.0\naF2972.0\naF4156.0\naF5024.0\naF5470.0\naF1536.0\naF4798.0\naF4448.0\naF4092.0\naF6894.0\naF6978.0\naF4470.0\naF6164.0\naF3810.0\naF3900.0\naF2160.0\naF5340.0\naF4350.0\naF5440.0\naF4996.0\naF7380.0\naF4768.0\naF4412.0\naF4092.0\naF4092.0\naF2160.0\naF3900.0\naF6780.0\naF6410.0\naF4220.0\naF6876.0\naF3900.0\naF3720.0\naF7048.0\naF4670.0\naF8424.0\naF2944.0\naF5884.0\naF5440.0\naF5410.0\naF4220.0\naF2608.0\naF5952.0\naF5926.0\naF3720.0\naF5064.0\naF6562.0\naF7568.0\naF6840.0\naF8032.0\naF4832.0\naF3000.0\naF4576.0\naF2160.0\naF4604.0\naF5084.0\naF5064.0\naF4410.0\naF5200.0\naF6780.0\naF4740.0\naF7834.0\naF4740.0\naF4576.0\naF3000.0\naF8214.0\naF4350.0\naF3720.0\naF3240.0\naF3600.0\naF4092.0\naF5132.0\naF4704.0\naF6300.0\naF5408.0\naF5376.0\naF5608.0\naF4050.0\naF6342.0\naF10550.0\naF6728.0\naF4448.0\naF4996.0\naF5700.0\naF5218.0\naF6810.0\naF8660.0\naF3660.0\naF5744.0\naF4892.0\naF4260.0\naF5666.0\naF5926.0\naF6810.0\naF4200.0\naF8908.0\naF2832.0\naF8580.0\naF5200.0\naF5934.0\naF5054.0\naF4860.0\naF5820.0\naF5688.0\naF5378.0\naF5984.0\naF5484.0\naF5730.0\naF10302.0\naF4156.0\naF3900.0\naF1900.0\naF5216.0\naF7182.0\naF6100.0\naF9100.0\naF4542.0\naF4928.0\naF4156.0\naF10320.0\naF10340.0\naF3140.0\naF4732.0\naF5632.0\naF7800.0\naF7582.0\naF3420.0\naF3660.0\naF5602.0\naF8310.0\naF4860.0\naF6088.0\naF5540.0\naF2160.0\naF5340.0\naF5310.0\naF9486.0\naF3000.0\naF6732.0\naF3964.0\naF4832.0\naF5744.0\naF4768.0\naF4560.0\naF4320.0\naF12180.0\naF5024.0\naF7164.0\naF9458.0\naF6300.0\naF7982.0\naF3060.0\naF5552.0\naF1848.0\naF5154.0\naF5280.0\naF4478.0\naF9860.0\naF4640.0\naF8712.0\naF7110.0\naF5216.0\naF5582.0\naF5342.0\naF5700.0\naF4092.0\naF5756.0\naF5620.0\naF6062.0\naF5410.0\naF14188.0\naF2552.0\naF1796.0\naF7098.0\naF8496.0\naF3480.0\naF5280.0\naF5190.0\naF2552.0\naF7920.0\naF6096.0\naF5310.0\naF4796.0\naF5892.0\naF4576.0\naF6732.0\naF15550.0\naF5880.0\naF4864.0\naF5280.0\naF9830.0\naF4412.0\naF6478.0\naF3300.0\naF5118.0\naF10230.0\naF5154.0\naF8790.0\naF6198.0\naF3140.0\naF5276.0\naF3360.0\naF4860.0\naF3000.0\naF6300.0\naF5246.0\naF7356.0\naF4412.0\naF4448.0\naF8224.0\naF8594.0\naF8024.0\naF5212.0\naF5820.0\naF4740.0\naF2056.0\naF3600.0\naF2888.0\naF6002.0\naF10050.0\naF3840.0\naF7004.0\naF5340.0\naF7188.0\naF12084.0\naF5280.0\naF7338.0\naF6096.0\naF8870.0\naF6444.0\naF5152.0\naF8938.0\naF4156.0\naF5824.0\naF9460.0\naF5504.0\naF5212.0\naF7446.0\naF9070.0\naF4508.0\naF8690.0\naF3840.0\naF5200.0\naF10290.0\naF13524.0\naF5378.0\naF3240.0\naF8660.0\naF7998.0\naF10170.0\naF9960.0\naF10260.0\naF11010.0\naF6852.0\naF9870.0\naF6194.0\naF9030.0\naF8628.0\naF4960.0\naF12510.0\naF5024.0\naF8232.0\naF6456.0\naF9460.0\naF8388.0\naF5446.0\naF7128.0\naF7192.0\naF7684.0\naF7112.0\naF4832.0\naF10398.0\naF6456.0\naF7272.0\naF7650.0\naF10760.0\naF5730.0\naF6322.0\naF5756.0\naF7498.0\naF7720.0\naF9390.0\naF4200.0\naF7620.0\naF7644.0\naF5538.0\naF2776.0\naF6810.0\naF4284.0\naF5756.0\naF4384.0\naF3420.0\naF3300.0\naF9560.0\naF5718.0\naF5200.0\naF6156.0\naF7212.0\naF10720.0\naF5544.0\naF10400.0\naF11598.0\naF8634.0\naF9124.0\naF6690.0\naF2160.0\naF8820.0\naF13082.0\naF5130.0\naF4540.0\naF8584.0\naF6194.0\naF8482.0\naF6894.0\naF8214.0\naF7790.0\naF10230.0\naF8148.0\naF8644.0\naF9174.0\naF13320.0\naF5090.0\naF6340.0\naF7296.0\naF7170.0\naF8178.0\naF3900.0\naF6780.0\naF6762.0\naF3140.0\naF10630.0\naF9648.0\naF5884.0\naF14250.0\naF4926.0\naF4050.0\naF10030.0\naF19656.0\naF9270.0\naF9890.0\naF6742.0\naF8340.0\naF10320.0\naF8736.0\naF8298.0\naF14372.0\naF9150.0\naF10980.0\naF9840.0\naF11350.0\naF6704.0\naF9710.0\naF9336.0\naF7890.0\naF4860.0\naF12036.0\naF10494.0\naF14102.0\naF10978.0\naF5278.0\naF5880.0\naF18778.0\naF11532.0\naF5316.0\naF4350.0\naF9890.0\naF6240.0\naF6576.0\naF8330.0\naF6248.0\naF3964.0\naF11928.0\naF9124.0\naF6804.0\naF6372.0\naF8660.0\naF3000.0\naF5024.0\naF3964.0\naF7098.0\naF8208.0\naF7026.0\naF12510.0\naF5246.0\naF5408.0\naF8162.0\naF7336.0\naF8210.0\naF7758.0\naF9772.0\naF3720.0\naF11490.0\naF6508.0\naF7254.0\naF7154.0\naF8956.0\naF11180.0\naF6024.0\naF6716.0\naF10692.0\naF13896.0\naF7260.0\naF8300.0\naF5990.0\naF7162.0\naF7284.0\naF5246.0\naF6644.0\naF8508.0\naF9220.0\naF9700.0\naF7702.0\naF11718.0\naF4350.0\naF8908.0\naF8568.0\naF5620.0\naF6508.0\naF13842.0\naF5216.0\naF6924.0\naF12180.0\naF4770.0\naF7494.0\naF6498.0\naF4768.0\naF12024.0\naF2832.0\naF7572.0\naF6810.0\naF4350.0\naF6546.0\naF6894.0\naF5812.0\naF3420.0\naF8232.0\naF6020.0\naF7914.0\naF14932.0\naF7428.0\naF4576.0\naF2160.0\naF8430.0\naF11180.0\naF12214.0\naF12658.0\naF9410.0\naF11454.0\naF11334.0\naF5730.0\naF5926.0\naF9060.0\naF8322.0\naF5856.0\naF9570.0\naF9900.0\naF7908.0\naF8260.0\naF17110.0\naF6146.0\naF6618.0\naF16968.0\naF6198.0\naF7692.0\naF11180.0\naF9396.0\naF12924.0\naF5854.0\naF6546.0\naF13312.0\naF9804.0\naF5470.0\naF4680.0\naF7320.0\naF8720.0\naF15444.0\naF12842.0\naF13746.0\naF5070.0\naF4892.0\naF9716.0\naF6660.0\naF11106.0\naF7652.0\naF7470.0\naF5608.0\naF9640.0\naF7056.0\naF6096.0\naF4320.0\naF7920.0\naF18930.0\naF5636.0\naF6402.0\naF7692.0\naF11050.0\naF6126.0\naF4796.0\naF8886.0\naF10200.0\naF7094.0\naF9010.0\naF11946.0\naF6894.0\naF5440.0\naF5154.0\naF4606.0\naF10300.0\naF7896.0\naF10968.0\naF6712.0\naF7098.0\naF10590.0\naF6966.0\naF8444.0\naF14000.0\naF8848.0\naF8310.0\naF10254.0\naF5880.0\naF4606.0\naF9384.0\naF3990.0\naF9112.0\naF6712.0\naF4796.0\naF6864.0\naF13216.0\naF8226.0\naF11676.0\naF10360.0\naF4028.0\naF12716.0\naF15420.0\naF8346.0\naF14430.0\naF4320.0\naF4230.0\naF12954.0\naF5280.0\naF7038.0\naF10440.0\naF9800.0\naF4092.0\naF9268.0\naF4860.0\naF9170.0\naF2108.0\naF8740.0\naF14280.0\naF7530.0\naF8950.0\naF9730.0\naF5760.0\naF5352.0\naF4650.0\naF5866.0\naF12450.0\naF7200.0\naF13068.0\naF8580.0\naF6384.0\naF7182.0\naF13352.0\naF7530.0\naF13200.0\naF5216.0\naF6784.0\naF6516.0\naF21676.0\naF6096.0\naF12960.0\naF5280.0\naF3964.0\naF7428.0\naF18920.0\naF8268.0\naF24716.0\naF12450.0\naF18756.0\naF8782.0\naF7230.0\naF9810.0\naF20850.0\naF7896.0\naF6804.0\naF6456.0\naF23310.0\naF14790.0\naF15936.0\naF12180.0\naF29044.0\naF16560.0\naF11820.0\naF6456.0\naF11184.0\naF12132.0\naF4540.0\naF13992.0\naF7758.0\naF3900.0\naF19350.0\naF6528.0\naF13530.0\naF13642.0\naF5854.0\naF7320.0\naF4892.0\naF9750.0\naF8362.0\naF8672.0\naF8740.0\naF6432.0\naF13202.0\naF4606.0\naF12882.0\naF5086.0\naF7890.0\naF5866.0\naF8600.0\naF10720.0\naF6648.0\naF7094.0\naF5472.0\naF11436.0\naF9422.0\naF9230.0\naF7092.0\naF7050.0\naF7060.0\naF7026.0\naF14634.0\naF4860.0\naF6254.0\naF12538.0\naF15552.0\naF22546.0\naF9790.0\naF10590.0\naF9670.0\naF14258.0\naF7036.0\naF5632.0\naF13126.0\naF15990.0\naF6254.0\naF17184.0\naF8352.0\naF5880.0\naF9030.0\naF16766.0\naF6262.0\naF21336.0\naF20700.0\naF7212.0\naF4992.0\naF22752.0\naF5410.0\naF7314.0\naF6996.0\naF8010.0\naF15216.0\naF14724.0\naF8850.0\naF7544.0\naF13802.0\naF8734.0\naF5676.0\naF6528.0\naF6384.0\naF11622.0\naF4384.0\naF11514.0\naF5598.0\naF5676.0\naF4796.0\naF5608.0\naF11802.0\naF6300.0\naF6906.0\naF6470.0\naF10290.0\naF8984.0\naF6690.0\naF7774.0\naF6950.0\naF1284.0\naF11040.0\naF9320.0\naF8298.0\naF12224.0\naF9028.0\naF4092.0\naF5928.0\naF4832.0\naF9310.0\naF6636.0\naF7264.0\naF5964.0\naF12778.0\naF8012.0\naF14694.0\naF13646.0\naF7152.0\naF6864.0\naF9014.0\naF17340.0\naF8962.0\naF5880.0\naF7506.0\naF5924.0\naF15536.0\naF15240.0\naF16788.0\naF14618.0\naF8330.0\naF8764.0\naF6900.0\naF7446.0\naF17428.0\naF6762.0\naF4860.0\naF8962.0\naF3000.0\naF6804.0\naF9060.0\naF8172.0\naF5922.0\naF7576.0\naF9460.0\naF9838.0\naF5730.0\naF4956.0\naF4928.0\naF7230.0\naF17724.0\naF11724.0\naF8584.0\naF5952.0\naF4320.0\naF15090.0\naF9588.0\naF6864.0\naF5278.0\naF7380.0\naF13890.0\naF13462.0\naF4604.0\naF8838.0\naF14400.0\naF8620.0\naF7762.0\naF6816.0\naF7622.0\naF6810.0\naF8340.0\naF6414.0\naF9430.0\naF9044.0\naF5696.0\naF15850.0\naF6960.0\naF19310.0\naF7386.0\naF6538.0\naF14786.0\naF6390.0\naF20170.0\naF19864.0\naF8232.0\naF4860.0\naF14360.0\naF7486.0\naF11972.0\naF13720.0\naF9098.0\naF10170.0\naF9890.0\naF10680.0\naF14386.0\naF11670.0\naF13860.0\naF8240.0\naF11112.0\naF5544.0\naF8790.0\naF6402.0\naF10760.0\naF6652.0\naF6096.0\naF7622.0\naF7290.0\naF19202.0\naF13422.0\naF4898.0\naF4928.0\naF11250.0\naF7038.0\naF7356.0\naF5666.0\naF26910.0\naF4604.0\naF17538.0\naF7416.0\naF11800.0\naF14756.0\naF8482.0\naF14284.0\naF6156.0\naF8420.0\naF10740.0\naF18580.0\naF10490.0\naF6300.0\naF10312.0\naF13672.0\naF9660.0\naF5476.0\naF10566.0\naF3960.0\naF4320.0\naF6206.0\naF6690.0\naF5340.0\naF12420.0\naF8010.0\naF7264.0\naF2916.0\naF6274.0\naF7326.0\naF6960.0\naF13064.0\naF7428.0\naF5348.0\naF7386.0\naF6330.0\naF15312.0\naF5552.0\naF10960.0\naF8690.0\naF11200.0\naF10572.0\naF5212.0\naF7824.0\naF5812.0\naF15660.0\naF12294.0\naF18850.0\naF8458.0\naF17310.0\naF8750.0\naF6470.0\naF4284.0\naF5568.0\naF5568.0\naF2552.0\naF16460.0\naF19146.0\naF14310.0\naF10350.0\naF5216.0\naF8764.0\naF9480.0\naF9930.0\naF7956.0\naF13094.0\naF13000.0\naF9336.0\naF5858.0\naF6390.0\naF5726.0\naF24964.0\naF4412.0\naF6210.0\naF8132.0\naF14550.0\naF4350.0\naF19284.0\naF2004.0\naF8002.0\naF6440.0\naF8386.0\naF8794.0\naF13892.0\naF17030.0\naF6678.0\naF7920.0\naF12434.0\naF7500.0\naF7356.0\naF6724.0\naF17526.0\naF10750.0\naF9470.0\naF10920.0\naF7782.0\naF18642.0\naF5378.0\naF4796.0\naF8346.0\naF8452.0\naF12270.0\naF8122.0\naF8592.0\naF17118.0\naF8220.0\naF7264.0\naF6810.0\naF8024.0\naF5952.0\naF8528.0\naF15160.0\naF5854.0\naF8460.0\naF7912.0\naF5440.0\naF17960.0\naF7668.0\naF11120.0\naF4860.0\naF6860.0\naF5666.0\naF9270.0\naF5500.0\naF11130.0\naF6504.0\naF14928.0\naF7176.0\naF19240.0\naF9840.0\naF12618.0\naF17970.0\naF16338.0\naF23340.0\naF12180.0\naF7242.0\naF3900.0\naF3964.0\naF16890.0\naF10830.0\naF7518.0\naF8734.0\naF10300.0\naF4928.0\naF10080.0\naF9090.0\naF11118.0\naF11090.0\naF9494.0\naF17378.0\naF12090.0\naF13344.0\naF10848.0\naF9888.0\naF6028.0\naF8610.0\naF7926.0\naF14100.0\naF9870.0\naF1380.0\naF12460.0\naF23862.0\naF12408.0\naF10018.0\naF7064.0\naF6322.0\naF9890.0\naF10686.0\naF5608.0\naF9896.0\naF11274.0\naF6444.0\naF13584.0\naF15116.0\naF12720.0\naF6960.0\naF9220.0\naF10300.0\naF10254.0\naF11640.0\naF5730.0\naF7950.0\naF8374.0\naF7386.0\naF16344.0\naF6258.0\naF7470.0\naF18198.0\naF5280.0\na."
  },
  {
    "path": "dqn/logs_pkls/Breakout_s001.pkl",
    "content": "(lp0\n(I60000\ncnumpy.core.multiarray\nscalar\np1\n(cnumpy\ndtype\np2\n(S'f8'\np3\nI0\nI1\ntp4\nRp5\n(I3\nS'<'\np6\nNNNI-1\nI-1\nI0\ntp7\nbS'R\\xb8\\x1e\\x85\\xebQ\\xf8?'\np8\ntp9\nRp10\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e\\xfd?'\np11\ntp12\nRp13\nF1.0\ntp14\na(I70000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\xf8?'\np15\ntp16\nRp17\ng13\nF1.0\ntp18\na(I80000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\xfb?'\np19\ntp20\nRp21\ng13\nF1.0\ntp22\na(I90000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\xf7?'\np23\ntp24\nRp25\ng13\nF5.0\ntp26\na(I100000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xfb?'\np27\ntp28\nRp29\ng13\nF3.0\ntp30\na(I110000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xf8?'\np31\ntp32\nRp33\ng13\nF2.0\ntp34\na(I120000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\xf6?'\np35\ntp36\nRp37\ng13\nF2.0\ntp38\na(I130000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\xfc?'\np39\ntp40\nRp41\ng13\nF7.0\ntp42\na(I140000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7\\xfb?'\np43\ntp44\nRp45\ng13\nF4.0\ntp46\na(I150000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\xf8?'\np47\ntp48\nRp49\ng13\nF1.0\ntp50\na(I160000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xf8?'\np51\ntp52\nRp53\ng13\nF1.0\ntp54\na(I170000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xf6?'\np55\ntp56\nRp57\ng13\nF0.0\ntp58\na(I180000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\xf8?'\np59\ntp60\nRp61\ng13\nF2.0\ntp62\na(I190000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xf9?'\np63\ntp64\nRp65\ng13\nF0.0\ntp66\na(I200000\ng1\n(g5\nS'ffffff\\xf6?'\np67\ntp68\nRp69\ng13\nF1.0\ntp70\na(I210000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\xf8?'\np71\ntp72\nRp73\ng13\nF3.0\ntp74\na(I220000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xfa?'\np75\ntp76\nRp77\ng13\nF4.0\ntp78\na(I230000\ng1\n(g5\nS'ffffff\\xfe?'\np79\ntp80\nRp81\ng1\n(g5\nS'ffffff\\xfe?'\np82\ntp83\nRp84\nF3.0\ntp85\na(I240000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\\x00@'\np86\ntp87\nRp88\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\x00@'\np89\ntp90\nRp91\nF4.0\ntp92\na(I250000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\xfe?'\np93\ntp94\nRp95\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x01@'\np96\ntp97\nRp98\nF2.0\ntp99\na(I260000\ng1\n(g5\nS'ffffff\\xfe?'\np100\ntp101\nRp102\ng98\nF0.0\ntp103\na(I270000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e\\x01@'\np104\ntp105\nRp106\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e\\x01@'\np107\ntp108\nRp109\nF4.0\ntp110\na(I280000\ng1\n(g5\nS'333333\\x03@'\np111\ntp112\nRp113\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\x03@'\np114\ntp115\nRp116\nF2.0\ntp117\na(I290000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x04@'\np118\ntp119\nRp120\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x04@'\np121\ntp122\nRp123\nF0.0\ntp124\na(I300000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x06@'\np125\ntp126\nRp127\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x06@'\np128\ntp129\nRp130\nF5.0\ntp131\na(I310000\ng1\n(g5\nS'333333\\t@'\np132\ntp133\nRp134\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\t@'\np135\ntp136\nRp137\nF4.0\ntp138\na(I320000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x0c@'\np139\ntp140\nRp141\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\x0c@'\np142\ntp143\nRp144\nF3.0\ntp145\na(I330000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e\\x10@'\np146\ntp147\nRp148\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e\\x10@'\np149\ntp150\nRp151\nF5.0\ntp152\na(I340000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\x10@'\np153\ntp154\nRp155\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\x10@'\np156\ntp157\nRp158\nF4.0\ntp159\na(I350000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e\\x12@'\np160\ntp161\nRp162\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x12@'\np163\ntp164\nRp165\nF3.0\ntp166\na(I360000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x12@'\np167\ntp168\nRp169\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\x12@'\np170\ntp171\nRp172\nF2.0\ntp173\na(I370000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e\\x14@'\np174\ntp175\nRp176\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\\x14@'\np177\ntp178\nRp179\nF6.0\ntp180\na(I380000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x14@'\np181\ntp182\nRp183\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x15@'\np184\ntp185\nRp186\nF3.0\ntp187\na(I390000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x16@'\np188\ntp189\nRp190\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x16@'\np191\ntp192\nRp193\nF6.0\ntp194\na(I400000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x16@'\np195\ntp196\nRp197\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x17@'\np198\ntp199\nRp200\nF5.0\ntp201\na(I410000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\x16@'\np202\ntp203\nRp204\ng200\nF2.0\ntp205\na(I420000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\x16@'\np206\ntp207\nRp208\ng200\nF4.0\ntp209\na(I430000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\x16@'\np210\ntp211\nRp212\ng200\nF9.0\ntp213\na(I440000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x17@'\np214\ntp215\nRp216\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\x17@'\np217\ntp218\nRp219\nF5.0\ntp220\na(I450000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\\x18@'\np221\ntp222\nRp223\ng1\n(g5\nS'ffffff\\x18@'\np224\ntp225\nRp226\nF5.0\ntp227\na(I460000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\x18@'\np228\ntp229\nRp230\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\x18@'\np231\ntp232\nRp233\nF5.0\ntp234\na(I470000\ng1\n(g5\nS'ffffff\\x19@'\np235\ntp236\nRp237\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7\\x19@'\np238\ntp239\nRp240\nF7.0\ntp241\na(I480000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\x18@'\np242\ntp243\nRp244\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x1a@'\np245\ntp246\nRp247\nF7.0\ntp248\na(I490000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\\x1a@'\np249\ntp250\nRp251\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x1a@'\np252\ntp253\nRp254\nF9.0\ntp255\na(I500000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\x1b@'\np256\ntp257\nRp258\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\x1b@'\np259\ntp260\nRp261\nF13.0\ntp262\na(I510000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\x1c@'\np263\ntp264\nRp265\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\x1d@'\np266\ntp267\nRp268\nF4.0\ntp269\na(I520000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\x1d@'\np270\ntp271\nRp272\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x1d@'\np273\ntp274\nRp275\nF10.0\ntp276\na(I530000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\x1e@'\np277\ntp278\nRp279\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\x1f@'\np280\ntp281\nRp282\nF4.0\ntp283\na(I540000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x1e@'\np284\ntp285\nRp286\ng282\nF2.0\ntp287\na(I550000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\x1e@'\np288\ntp289\nRp290\ng282\nF8.0\ntp291\na(I560000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\x1d@'\np292\ntp293\nRp294\ng282\nF7.0\ntp295\na(I570000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x1e@'\np296\ntp297\nRp298\ng282\nF6.0\ntp299\na(I580000\ng1\n(g5\nS'333333\\x1e@'\np300\ntp301\nRp302\ng282\nF10.0\ntp303\na(I590000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\x1f@'\np304\ntp305\nRp306\ng282\nF8.0\ntp307\na(I600000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x80 @'\np308\ntp309\nRp310\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x80 @'\np311\ntp312\nRp313\nF5.0\ntp314\na(I610000\ng1\n(g5\nS'333333!@'\np315\ntp316\nRp317\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f!@'\np318\ntp319\nRp320\nF8.0\ntp321\na(I620000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae!@'\np322\ntp323\nRp324\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8!@'\np325\ntp326\nRp327\nF7.0\ntp328\na(I630000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f!@'\np329\ntp330\nRp331\ng1\n(g5\nS'fffff\\xe6!@'\np332\ntp333\nRp334\nF15.0\ntp335\na(I640000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e!@'\np336\ntp337\nRp338\ng334\nF3.0\ntp339\na(I650000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB!@'\np340\ntp341\nRp342\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x19\"@'\np343\ntp344\nRp345\nF5.0\ntp346\na(I660000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb!@'\np347\ntp348\nRp349\ng345\nF10.0\ntp350\na(I670000\ng1\n(g5\nS'fffff\\xe6\"@'\np351\ntp352\nRp353\ng1\n(g5\nS'fffff\\xe6\"@'\np354\ntp355\nRp356\nF19.0\ntp357\na(I680000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd#@'\np358\ntp359\nRp360\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n$@'\np361\ntp362\nRp363\nF7.0\ntp364\na(I690000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5#@'\np365\ntp366\nRp367\ng363\nF9.0\ntp368\na(I700000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8$@'\np369\ntp370\nRp371\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd1$@'\np372\ntp373\nRp374\nF1.0\ntp375\na(I710000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k$@'\np376\ntp377\nRp378\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5$@'\np379\ntp380\nRp381\nF15.0\ntp382\na(I720000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99$@'\np383\ntp384\nRp385\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n%@'\np386\ntp387\nRp388\nF11.0\ntp389\na(I730000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb$@'\np390\ntp391\nRp392\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG%@'\np393\ntp394\nRp395\nF9.0\ntp396\na(I740000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05%@'\np397\ntp398\nRp399\ng395\nF15.0\ntp400\na(I750000\ng1\n(g5\nS'ffffff&@'\np401\ntp402\nRp403\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u&@'\np404\ntp405\nRp406\nF11.0\ntp407\na(I760000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW(@'\np408\ntp409\nRp410\ng1\n(g5\nS'\\xd7\\xa3p=\\nW(@'\np411\ntp412\nRp413\nF5.0\ntp414\na(I770000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(*@'\np415\ntp416\nRp417\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8*@'\np418\ntp419\nRp420\nF16.0\ntp421\na(I780000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05+@'\np422\ntp423\nRp424\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05+@'\np425\ntp426\nRp427\nF21.0\ntp428\na(I790000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u,@'\np429\ntp430\nRp431\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e,@'\np432\ntp433\nRp434\nF10.0\ntp435\na(I800000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85,@'\np436\ntp437\nRp438\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00-@'\np439\ntp440\nRp441\nF13.0\ntp442\na(I810000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8,@'\np443\ntp444\nRp445\ng1\n(g5\nS'333333-@'\np446\ntp447\nRp448\nF13.0\ntp449\na(I820000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8-@'\np450\ntp451\nRp452\ng1\n(g5\nS'fffff\\xe6-@'\np453\ntp454\nRp455\nF18.0\ntp456\na(I830000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc.@'\np457\ntp458\nRp459\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f/@'\np460\ntp461\nRp462\nF15.0\ntp463\na(I840000\ng1\n(g5\nS'fffff\\xa60@'\np464\ntp465\nRp466\ng1\n(g5\nS'fffff\\xa60@'\np467\ntp468\nRp469\nF38.0\ntp470\na(I850000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e1@'\np471\ntp472\nRp473\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e1@'\np474\ntp475\nRp476\nF28.0\ntp477\na(I860000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ2@'\np478\ntp479\nRp480\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ2@'\np481\ntp482\nRp483\nF31.0\ntp484\na(I870000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x173@'\np485\ntp486\nRp487\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x173@'\np488\ntp489\nRp490\nF39.0\ntp491\na(I880000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x974@'\np492\ntp493\nRp494\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x974@'\np495\ntp496\nRp497\nF28.0\ntp498\na(I890000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p5@'\np499\ntp500\nRp501\ng1\n(g5\nS'q=\\n\\xd7\\xa3p5@'\np502\ntp503\nRp504\nF33.0\ntp505\na(I900000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc5@'\np506\ntp507\nRp508\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x076@'\np509\ntp510\nRp511\nF23.0\ntp512\na(I910000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x806@'\np513\ntp514\nRp515\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x806@'\np516\ntp517\nRp518\nF33.0\ntp519\na(I920000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x027@'\np520\ntp521\nRp522\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x027@'\np523\ntp524\nRp525\nF32.0\ntp526\na(I930000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x078@'\np527\ntp528\nRp529\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x078@'\np530\ntp531\nRp532\nF30.0\ntp533\na(I940000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=9@'\np534\ntp535\nRp536\ng1\n(g5\nS'=\\n\\xd7\\xa3p=9@'\np537\ntp538\nRp539\nF42.0\ntp540\na(I950000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW:@'\np541\ntp542\nRp543\ng1\n(g5\nS'\\xd7\\xa3p=\\nW:@'\np544\ntp545\nRp546\nF34.0\ntp547\na(I960000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\;@'\np548\ntp549\nRp550\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k;@'\np551\ntp552\nRp553\nF42.0\ntp554\na(I970000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ<@'\np555\ntp556\nRp557\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ<@'\np558\ntp559\nRp560\nF37.0\ntp561\na(I980000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x11=@'\np562\ntp563\nRp564\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x11=@'\np565\ntp566\nRp567\nF34.0\ntp568\na(I990000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe8>@'\np569\ntp570\nRp571\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5>@'\np572\ntp573\nRp574\nF11.0\ntp575\na(I1000000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGA@@'\np576\ntp577\nRp578\ng1\n(g5\nS'\\xe1z\\x14\\xaeGA@@'\np579\ntp580\nRp581\nF25.0\ntp582\na(I1010000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x1dA@'\np583\ntp584\nRp585\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x1dA@'\np586\ntp587\nRp588\nF19.0\ntp589\na(I1020000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xbcA@'\np590\ntp591\nRp592\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xbcA@'\np593\ntp594\nRp595\nF42.0\ntp596\na(I1030000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85B@'\np597\ntp598\nRp599\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85B@'\np600\ntp601\nRp602\nF78.0\ntp603\na(I1040000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf0B@'\np604\ntp605\nRp606\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf0B@'\np607\ntp608\nRp609\nF58.0\ntp610\na(I1050000\ng1\n(g5\nS'fffff\\xc6C@'\np611\ntp612\nRp613\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xcbC@'\np614\ntp615\nRp616\nF46.0\ntp617\na(I1060000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1eD@'\np618\ntp619\nRp620\ng1\n(g5\nS'fffff&D@'\np621\ntp622\nRp623\nF38.0\ntp624\na(I1070000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00`D@'\np625\ntp626\nRp627\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00`D@'\np628\ntp629\nRp630\nF74.0\ntp631\na(I1080000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb5D@'\np632\ntp633\nRp634\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb5D@'\np635\ntp636\nRp637\nF24.0\ntp638\na(I1090000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x08E@'\np639\ntp640\nRp641\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x08E@'\np642\ntp643\nRp644\nF86.0\ntp645\na(I1100000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x9aE@'\np646\ntp647\nRp648\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x9aE@'\np649\ntp650\nRp651\nF77.0\ntp652\na(I1110000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xeaE@'\np653\ntp654\nRp655\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xeaE@'\np656\ntp657\nRp658\nF54.0\ntp659\na(I1120000\ng1\n(g5\nS'\\xd7\\xa3p=\\nWF@'\np660\ntp661\nRp662\ng1\n(g5\nS'\\xd7\\xa3p=\\nWF@'\np663\ntp664\nRp665\nF46.0\ntp666\na(I1130000\ng1\n(g5\nS'33333sF@'\np667\ntp668\nRp669\ng1\n(g5\nS'33333sF@'\np670\ntp671\nRp672\nF61.0\ntp673\na(I1140000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8F@'\np674\ntp675\nRp676\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xe2F@'\np677\ntp678\nRp679\nF45.0\ntp680\na(I1150000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcfF@'\np681\ntp682\nRp683\ng679\nF40.0\ntp684\na(I1160000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xbeF@'\np685\ntp686\nRp687\ng1\n(g5\nS'fffffFG@'\np688\ntp689\nRp690\nF33.0\ntp691\na(I1170000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\"G@'\np692\ntp693\nRp694\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8fG@'\np695\ntp696\nRp697\nF48.0\ntp698\na(I1180000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcclG@'\np699\ntp700\nRp701\ng697\nF64.0\ntp702\na(I1190000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf8G@'\np703\ntp704\nRp705\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf8G@'\np706\ntp707\nRp708\nF75.0\ntp709\na(I1200000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05H@'\np710\ntp711\nRp712\ng1\n(g5\nS'33333\\x13H@'\np713\ntp714\nRp715\nF33.0\ntp716\na(I1210000\ng1\n(g5\nS\"H\\xe1z\\x14\\xae'H@\"\np717\ntp718\nRp719\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(<H@'\np720\ntp721\nRp722\nF82.0\ntp723\na(I1220000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1ZH@'\np724\ntp725\nRp726\ng1\n(g5\nS'{\\x14\\xaeG\\xe1ZH@'\np727\ntp728\nRp729\nF50.0\ntp730\na(I1230000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eeH@'\np731\ntp732\nRp733\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xbcH@'\np734\ntp735\nRp736\nF0.0\ntp737\na(I1240000\ng1\n(g5\nS'fffff&H@'\np738\ntp739\nRp740\ng736\nF19.0\ntp741\na(I1250000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc,H@'\np742\ntp743\nRp744\ng736\nF76.0\ntp745\na(I1260000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x9aH@'\np746\ntp747\nRp748\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xd5H@'\np749\ntp750\nRp751\nF56.0\ntp752\na(I1270000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xe0H@'\np753\ntp754\nRp755\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xe0H@'\np756\ntp757\nRp758\nF59.0\ntp759\na(I1280000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\OI@'\np760\ntp761\nRp762\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\OI@'\np763\ntp764\nRp765\nF69.0\ntp766\na(I1290000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85I@'\np767\ntp768\nRp769\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99I@'\np770\ntp771\nRp772\nF74.0\ntp773\na(I1300000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x80J@'\np774\ntp775\nRp776\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x80J@'\np777\ntp778\nRp779\nF70.0\ntp780\na(I1310000\ng1\n(g5\nS'\\xd7\\xa3p=\\n7J@'\np781\ntp782\nRp783\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x88J@'\np784\ntp785\nRp786\nF64.0\ntp787\na(I1320000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x8bJ@'\np788\ntp789\nRp790\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9eJ@'\np791\ntp792\nRp793\nF61.0\ntp794\na(I1330000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x91J@'\np795\ntp796\nRp797\ng793\nF61.0\ntp798\na(I1340000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.J@'\np799\ntp800\nRp801\ng793\nF57.0\ntp802\na(I1350000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xfeI@'\np803\ntp804\nRp805\ng793\nF95.0\ntp806\na(I1360000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x999J@'\np807\ntp808\nRp809\ng793\nF59.0\ntp810\na(I1370000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xb9J@'\np811\ntp812\nRp813\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xcbJ@'\np814\ntp815\nRp816\nF41.0\ntp817\na(I1380000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfdJ@'\np818\ntp819\nRp820\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x03K@'\np821\ntp822\nRp823\nF57.0\ntp824\na(I1390000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99YK@'\np825\ntp826\nRp827\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99YK@'\np828\ntp829\nRp830\nF60.0\ntp831\na(I1400000\ng1\n(g5\nS'\\n\\xd7\\xa3p=JK@'\np832\ntp833\nRp834\ng830\nF70.0\ntp835\na(I1410000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x07K@'\np836\ntp837\nRp838\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x82K@'\np839\ntp840\nRp841\nF76.0\ntp842\na(I1420000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05J@'\np843\ntp844\nRp845\ng841\nF70.0\ntp846\na(I1430000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zTJ@'\np847\ntp848\nRp849\ng841\nF51.0\ntp850\na(I1440000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x94J@'\np851\ntp852\nRp853\ng841\nF51.0\ntp854\na(I1450000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xfeJ@'\np855\ntp856\nRp857\ng841\nF85.0\ntp858\na(I1460000\ng1\n(g5\nS'33333SK@'\np859\ntp860\nRp861\ng841\nF86.0\ntp862\na(I1470000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x91L@'\np863\ntp864\nRp865\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x91L@'\np866\ntp867\nRp868\nF83.0\ntp869\na(I1480000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.M@'\np870\ntp871\nRp872\ng1\n(g5\nS'33333SM@'\np873\ntp874\nRp875\nF37.0\ntp876\na(I1490000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x81M@'\np877\ntp878\nRp879\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x81M@'\np880\ntp881\nRp882\nF74.0\ntp883\na(I1500000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x02N@'\np884\ntp885\nRp886\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x0bN@'\np887\ntp888\nRp889\nF63.0\ntp890\na(I1510000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQXO@'\np891\ntp892\nRp893\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQXO@'\np894\ntp895\nRp896\nF76.0\ntp897\na(I1520000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xe5J@'\np898\ntp899\nRp900\ng896\nF8.0\ntp901\na(I1530000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e%H@'\np902\ntp903\nRp904\ng896\nF65.0\ntp905\na(I1540000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1eH@'\np906\ntp907\nRp908\ng896\nF63.0\ntp909\na(I1550000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x9aH@'\np910\ntp911\nRp912\ng896\nF66.0\ntp913\na(I1560000\ng1\n(g5\nS'\\xa4p=\\n\\xd7CH@'\np914\ntp915\nRp916\ng896\nF4.0\ntp917\na(I1570000\ng1\n(g5\nS'fffff\\xe6G@'\np918\ntp919\nRp920\ng896\nF86.0\ntp921\na(I1580000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xdaG@'\np922\ntp923\nRp924\ng896\nF92.0\ntp925\na(I1590000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9eB@'\np926\ntp927\nRp928\ng896\nF67.0\ntp929\na(I1600000\ng1\n(g5\nS'fffff\\x86C@'\np930\ntp931\nRp932\ng896\nF50.0\ntp933\na(I1610000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8aE@'\np934\ntp935\nRp936\ng896\nF67.0\ntp937\na(I1620000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xafG@'\np938\ntp939\nRp940\ng896\nF48.0\ntp941\na(I1630000\ng1\n(g5\nS'H\\xe1z\\x14\\xaegI@'\np942\ntp943\nRp944\ng896\nF5.0\ntp945\na(I1640000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xfeF@'\np946\ntp947\nRp948\ng896\nF44.0\ntp949\na(I1650000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2UH@'\np950\ntp951\nRp952\ng896\nF214.0\ntp953\na(I1660000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x82G@'\np954\ntp955\nRp956\ng896\nF80.0\ntp957\na(I1670000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3F@'\np958\ntp959\nRp960\ng896\nF13.0\ntp961\na(I1680000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14NI@'\np962\ntp963\nRp964\ng896\nF35.0\ntp965\na(I1690000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xcaI@'\np966\ntp967\nRp968\ng896\nF69.0\ntp969\na(I1700000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x10H@'\np970\ntp971\nRp972\ng896\nF82.0\ntp973\na(I1710000\ng1\n(g5\nS'33333\\x13I@'\np974\ntp975\nRp976\ng896\nF85.0\ntp977\na(I1720000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc5G@'\np978\ntp979\nRp980\ng896\nF2.0\ntp981\na(I1730000\ng1\n(g5\nS'33333\\x13I@'\np982\ntp983\nRp984\ng896\nF16.0\ntp985\na(I1740000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfaG@'\np986\ntp987\nRp988\ng896\nF57.0\ntp989\na(I1750000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xa2G@'\np990\ntp991\nRp992\ng896\nF60.0\ntp993\na(I1760000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xd9G@'\np994\ntp995\nRp996\ng896\nF51.0\ntp997\na(I1770000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x17I@'\np998\ntp999\nRp1000\ng896\nF74.0\ntp1001\na(I1780000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc,I@'\np1002\ntp1003\nRp1004\ng896\nF83.0\ntp1005\na(I1790000\ng1\n(g5\nS'33333\\xd3I@'\np1006\ntp1007\nRp1008\ng896\nF55.0\ntp1009\na(I1800000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99YJ@'\np1010\ntp1011\nRp1012\ng896\nF62.0\ntp1013\na(I1810000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05K@'\np1014\ntp1015\nRp1016\ng896\nF77.0\ntp1017\na(I1820000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x9dJ@'\np1018\ntp1019\nRp1020\ng896\nF67.0\ntp1021\na(I1830000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb5L@'\np1022\ntp1023\nRp1024\ng896\nF25.0\ntp1025\na(I1840000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x08M@'\np1026\ntp1027\nRp1028\ng896\nF93.0\ntp1029\na(I1850000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x87O@'\np1030\ntp1031\nRp1032\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x87O@'\np1033\ntp1034\nRp1035\nF94.0\ntp1036\na(I1860000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\nP@'\np1037\ntp1038\nRp1039\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x18P@'\np1040\ntp1041\nRp1042\nF82.0\ntp1043\na(I1870000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\nP@'\np1044\ntp1045\nRp1046\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2UP@'\np1047\ntp1048\nRp1049\nF71.0\ntp1050\na(I1880000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xebO@'\np1051\ntp1052\nRp1053\ng1049\nF53.0\ntp1054\na(I1890000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99yO@'\np1055\ntp1056\nRp1057\ng1049\nF42.0\ntp1058\na(I1900000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2EP@'\np1059\ntp1060\nRp1061\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\P@'\np1062\ntp1063\nRp1064\nF27.0\ntp1065\na(I1910000\ng1\n(g5\nS'=\\n\\xd7\\xa3p]P@'\np1066\ntp1067\nRp1068\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x91P@'\np1069\ntp1070\nRp1071\nF52.0\ntp1072\na(I1920000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x9cP@'\np1073\ntp1074\nRp1075\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x9cP@'\np1076\ntp1077\nRp1078\nF77.0\ntp1079\na(I1930000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\nQ@'\np1080\ntp1081\nRp1082\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb!Q@'\np1083\ntp1084\nRp1085\nF23.0\ntp1086\na(I1940000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdcP@'\np1087\ntp1088\nRp1089\ng1\n(g5\nS'\\xe1z\\x14\\xaeGQQ@'\np1090\ntp1091\nRp1092\nF64.0\ntp1093\na(I1950000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xf1P@'\np1094\ntp1095\nRp1096\ng1092\nF100.0\ntp1097\na(I1960000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xb9P@'\np1098\ntp1099\nRp1100\ng1\n(g5\nS'\\xe1z\\x14\\xaeGaQ@'\np1101\ntp1102\nRp1103\nF31.0\ntp1104\na(I1970000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xa4P@'\np1105\ntp1106\nRp1107\ng1103\nF42.0\ntp1108\na(I1980000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x95P@'\np1109\ntp1110\nRp1111\ng1103\nF71.0\ntp1112\na(I1990000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xabN@'\np1113\ntp1114\nRp1115\ng1103\nF226.0\ntp1116\na(I2000000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x00P@'\np1117\ntp1118\nRp1119\ng1103\nF53.0\ntp1120\na(I2010000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc25N@'\np1121\ntp1122\nRp1123\ng1103\nF45.0\ntp1124\na(I2020000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05N@'\np1125\ntp1126\nRp1127\ng1103\nF63.0\ntp1128\na(I2030000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc,O@'\np1129\ntp1130\nRp1131\ng1103\nF123.0\ntp1132\na(I2040000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99yO@'\np1133\ntp1134\nRp1135\ng1103\nF67.0\ntp1136\na(I2050000\ng1\n(g5\nS'\\n\\xd7\\xa3p=ZP@'\np1137\ntp1138\nRp1139\ng1103\nF78.0\ntp1140\na(I2060000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eeP@'\np1141\ntp1142\nRp1143\ng1103\nF63.0\ntp1144\na(I2070000\ng1\n(g5\nS'33333\\xd3P@'\np1145\ntp1146\nRp1147\ng1103\nF62.0\ntp1148\na(I2080000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x15R@'\np1149\ntp1150\nRp1151\ng1\n(g5\nS'fffff6R@'\np1152\ntp1153\nRp1154\nF99.0\ntp1155\na(I2090000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xabR@'\np1156\ntp1157\nRp1158\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xacR@'\np1159\ntp1160\nRp1161\nF59.0\ntp1162\na(I2100000\ng1\n(g5\nS\"H\\xe1z\\x14\\xae'S@\"\np1163\ntp1164\nRp1165\ng1\n(g5\nS\"H\\xe1z\\x14\\xae'S@\"\np1166\ntp1167\nRp1168\nF88.0\ntp1169\na(I2110000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xf7T@'\np1170\ntp1171\nRp1172\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xf7T@'\np1173\ntp1174\nRp1175\nF74.0\ntp1176\na(I2120000\ng1\n(g5\nS'fffffFU@'\np1177\ntp1178\nRp1179\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xcaU@'\np1180\ntp1181\nRp1182\nF120.0\ntp1183\na(I2130000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z$U@'\np1184\ntp1185\nRp1186\ng1182\nF99.0\ntp1187\na(I2140000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xbfU@'\np1188\ntp1189\nRp1190\ng1182\nF113.0\ntp1191\na(I2150000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fBV@'\np1192\ntp1193\nRp1194\ng1\n(g5\nS'q=\\n\\xd7\\xa3PV@'\np1195\ntp1196\nRp1197\nF32.0\ntp1198\na(I2160000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\"V@'\np1199\ntp1200\nRp1201\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x81V@'\np1202\ntp1203\nRp1204\nF56.0\ntp1205\na(I2170000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1jU@'\np1206\ntp1207\nRp1208\ng1204\nF68.0\ntp1209\na(I2180000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xa0U@'\np1210\ntp1211\nRp1212\ng1204\nF115.0\ntp1213\na(I2190000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x8aV@'\np1214\ntp1215\nRp1216\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x8aV@'\np1217\ntp1218\nRp1219\nF102.0\ntp1220\na(I2200000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zTU@'\np1221\ntp1222\nRp1223\ng1219\nF40.0\ntp1224\na(I2210000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGaS@'\np1225\ntp1226\nRp1227\ng1219\nF61.0\ntp1228\na(I2220000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00S@'\np1229\ntp1230\nRp1231\ng1219\nF50.0\ntp1232\na(I2230000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xacS@'\np1233\ntp1234\nRp1235\ng1219\nF102.0\ntp1236\na(I2240000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xb0S@'\np1237\ntp1238\nRp1239\ng1219\nF109.0\ntp1240\na(I2250000\ng1\n(g5\nS'fffff\\x06T@'\np1241\ntp1242\nRp1243\ng1219\nF122.0\ntp1244\na(I2260000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8T@'\np1245\ntp1246\nRp1247\ng1219\nF69.0\ntp1248\na(I2270000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x8dT@'\np1249\ntp1250\nRp1251\ng1219\nF134.0\ntp1252\na(I2280000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe8T@'\np1253\ntp1254\nRp1255\ng1219\nF45.0\ntp1256\na(I2290000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7U@'\np1257\ntp1258\nRp1259\ng1219\nF239.0\ntp1260\na(I2300000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00 V@'\np1261\ntp1262\nRp1263\ng1219\nF73.0\ntp1264\na(I2310000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xd0U@'\np1265\ntp1266\nRp1267\ng1219\nF155.0\ntp1268\na(I2320000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xa0U@'\np1269\ntp1270\nRp1271\ng1219\nF76.0\ntp1272\na(I2330000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xdeV@'\np1273\ntp1274\nRp1275\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xdeV@'\np1276\ntp1277\nRp1278\nF174.0\ntp1279\na(I2340000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xb8W@'\np1280\ntp1281\nRp1282\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xb8W@'\np1283\ntp1284\nRp1285\nF77.0\ntp1286\na(I2350000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x0bX@'\np1287\ntp1288\nRp1289\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85[X@'\np1290\ntp1291\nRp1292\nF131.0\ntp1293\na(I2360000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x88X@'\np1294\ntp1295\nRp1296\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xeeX@'\np1297\ntp1298\nRp1299\nF11.0\ntp1300\na(I2370000\ng1\n(g5\nS'\\x14\\xaeG\\xe1ztX@'\np1301\ntp1302\nRp1303\ng1299\nF132.0\ntp1304\na(I2380000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xf7X@'\np1305\ntp1306\nRp1307\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xf7X@'\np1308\ntp1309\nRp1310\nF106.0\ntp1311\na(I2390000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccLY@'\np1312\ntp1313\nRp1314\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb0Y@'\np1315\ntp1316\nRp1317\nF131.0\ntp1318\na(I2400000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xe5Y@'\np1319\ntp1320\nRp1321\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x18Z@'\np1322\ntp1323\nRp1324\nF97.0\ntp1325\na(I2410000\ng1\n(g5\nS'H\\xe1z\\x14\\xae7Z@'\np1326\ntp1327\nRp1328\ng1\n(g5\nS'\\n\\xd7\\xa3p=zZ@'\np1329\ntp1330\nRp1331\nF23.0\ntp1332\na(I2420000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x05Z@'\np1333\ntp1334\nRp1335\ng1331\nF40.0\ntp1336\na(I2430000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5hY@'\np1337\ntp1338\nRp1339\ng1331\nF58.0\ntp1340\na(I2440000\ng1\n(g5\nS'fffff\\x96Y@'\np1341\ntp1342\nRp1343\ng1331\nF31.0\ntp1344\na(I2450000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xf0Y@'\np1345\ntp1346\nRp1347\ng1331\nF121.0\ntp1348\na(I2460000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x13Z@'\np1349\ntp1350\nRp1351\ng1331\nF186.0\ntp1352\na(I2470000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x11Z@'\np1353\ntp1354\nRp1355\ng1331\nF75.0\ntp1356\na(I2480000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(|[@'\np1357\ntp1358\nRp1359\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(|[@'\np1360\ntp1361\nRp1362\nF108.0\ntp1363\na(I2490000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae[@'\np1364\ntp1365\nRp1366\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae[@'\np1367\ntp1368\nRp1369\nF146.0\ntp1370\na(I2500000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x82[@'\np1371\ntp1372\nRp1373\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xc8[@'\np1374\ntp1375\nRp1376\nF115.0\ntp1377\na(I2510000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x95[@'\np1378\ntp1379\nRp1380\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xe3[@'\np1381\ntp1382\nRp1383\nF105.0\ntp1384\na(I2520000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14^[@'\np1385\ntp1386\nRp1387\ng1383\nF139.0\ntp1388\na(I2530000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8>[@'\np1389\ntp1390\nRp1391\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xe5[@'\np1392\ntp1393\nRp1394\nF115.0\ntp1395\na(I2540000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xd1[@'\np1396\ntp1397\nRp1398\ng1394\nF136.0\ntp1399\na(I2550000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05\\\\@'\np1400\ntp1401\nRp1402\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8n\\\\@'\np1403\ntp1404\nRp1405\nF101.0\ntp1406\na(I2560000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\\\@'\np1407\ntp1408\nRp1409\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x8a\\\\@'\np1410\ntp1411\nRp1412\nF78.0\ntp1413\na(I2570000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xe4\\\\@'\np1414\ntp1415\nRp1416\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xe4\\\\@'\np1417\ntp1418\nRp1419\nF227.0\ntp1420\na(I2580000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zT]@'\np1421\ntp1422\nRp1423\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x9a]@'\np1424\ntp1425\nRp1426\nF89.0\ntp1427\na(I2590000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xe1]@'\np1428\ntp1429\nRp1430\ng1\n(g5\nS'33333\\x03^@'\np1431\ntp1432\nRp1433\nF95.0\ntp1434\na(I2600000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ^@'\np1435\ntp1436\nRp1437\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ^@'\np1438\ntp1439\nRp1440\nF165.0\ntp1441\na(I2610000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1j]@'\np1442\ntp1443\nRp1444\ng1\n(g5\nS'q=\\n\\xd7\\xa3`^@'\np1445\ntp1446\nRp1447\nF73.0\ntp1448\na(I2620000\ng1\n(g5\nS'H\\xe1z\\x14\\xae7]@'\np1449\ntp1450\nRp1451\ng1447\nF170.0\ntp1452\na(I2630000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e]@'\np1453\ntp1454\nRp1455\ng1447\nF91.0\ntp1456\na(I2640000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xd0^@'\np1457\ntp1458\nRp1459\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf8^@'\np1460\ntp1461\nRp1462\nF170.0\ntp1463\na(I2650000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x11_@'\np1464\ntp1465\nRp1466\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fb_@'\np1467\ntp1468\nRp1469\nF106.0\ntp1470\na(I2660000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xc4^@'\np1471\ntp1472\nRp1473\ng1469\nF49.0\ntp1474\na(I2670000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xda^@'\np1475\ntp1476\nRp1477\ng1469\nF180.0\ntp1478\na(I2680000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x8e]@'\np1479\ntp1480\nRp1481\ng1469\nF53.0\ntp1482\na(I2690000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc,]@'\np1483\ntp1484\nRp1485\ng1469\nF151.0\ntp1486\na(I2700000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x18^@'\np1487\ntp1488\nRp1489\ng1469\nF135.0\ntp1490\na(I2710000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c]@'\np1491\ntp1492\nRp1493\ng1469\nF54.0\ntp1494\na(I2720000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x12]@'\np1495\ntp1496\nRp1497\ng1469\nF57.0\ntp1498\na(I2730000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebA]@'\np1499\ntp1500\nRp1501\ng1469\nF276.0\ntp1502\na(I2740000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae]@'\np1503\ntp1504\nRp1505\ng1469\nF126.0\ntp1506\na(I2750000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zD_@'\np1507\ntp1508\nRp1509\ng1469\nF270.0\ntp1510\na(I2760000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\n`@'\np1511\ntp1512\nRp1513\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\n`@'\np1514\ntp1515\nRp1516\nF185.0\ntp1517\na(I2770000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xa0_@'\np1518\ntp1519\nRp1520\ng1516\nF230.0\ntp1521\na(I2780000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd4^@'\np1522\ntp1523\nRp1524\ng1516\nF154.0\ntp1525\na(I2790000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2%^@'\np1526\ntp1527\nRp1528\ng1516\nF87.0\ntp1529\na(I2800000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xce]@'\np1530\ntp1531\nRp1532\ng1516\nF82.0\ntp1533\na(I2810000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ(]@'\np1534\ntp1535\nRp1536\ng1516\nF106.0\ntp1537\na(I2820000\ng1\n(g5\nS'33333\\x13]@'\np1538\ntp1539\nRp1540\ng1516\nF276.0\ntp1541\na(I2830000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE\\\\@'\np1542\ntp1543\nRp1544\ng1516\nF130.0\ntp1545\na(I2840000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xcaZ@'\np1546\ntp1547\nRp1548\ng1516\nF39.0\ntp1549\na(I2850000\ng1\n(g5\nS'\\xd7\\xa3p=\\n7Y@'\np1550\ntp1551\nRp1552\ng1516\nF32.0\ntp1553\na(I2860000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x04V@'\np1554\ntp1555\nRp1556\ng1516\nF21.0\ntp1557\na(I2870000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xaeP@'\np1558\ntp1559\nRp1560\ng1516\nF15.0\ntp1561\na(I2880000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9cF@'\np1562\ntp1563\nRp1564\ng1516\nF4.0\ntp1565\na(I2890000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc257@'\np1566\ntp1567\nRp1568\ng1516\nF13.0\ntp1569\na(I2900000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u @'\np1570\ntp1571\nRp1572\ng1516\nF3.0\ntp1573\na(I2910000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\r@'\np1574\ntp1575\nRp1576\ng1516\nF1.0\ntp1577\na(I2920000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7\\x01@'\np1578\ntp1579\nRp1580\ng1516\nF6.0\ntp1581\na(I2930000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\x00@'\np1582\ntp1583\nRp1584\ng1516\nF4.0\ntp1585\na(I2940000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\\x00@'\np1586\ntp1587\nRp1588\ng1516\nF1.0\ntp1589\na(I2950000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\x03@'\np1590\ntp1591\nRp1592\ng1516\nF3.0\ntp1593\na(I2960000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\x07@'\np1594\ntp1595\nRp1596\ng1516\nF4.0\ntp1597\na(I2970000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x08@'\np1598\ntp1599\nRp1600\ng1516\nF6.0\ntp1601\na(I2980000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e\\x07@'\np1602\ntp1603\nRp1604\ng1516\nF5.0\ntp1605\na(I2990000\ng1\n(g5\nS'333333\\x03@'\np1606\ntp1607\nRp1608\ng1516\nF0.0\ntp1609\na(I3000000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7\\x01@'\np1610\ntp1611\nRp1612\ng1516\nF3.0\ntp1613\na(I3010000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x02@'\np1614\ntp1615\nRp1616\ng1516\nF2.0\ntp1617\na(I3020000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x03@'\np1618\ntp1619\nRp1620\ng1516\nF2.0\ntp1621\na(I3030000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x03@'\np1622\ntp1623\nRp1624\ng1516\nF2.0\ntp1625\na(I3040000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\x04@'\np1626\ntp1627\nRp1628\ng1516\nF1.0\ntp1629\na(I3050000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\x02@'\np1630\ntp1631\nRp1632\ng1516\nF1.0\ntp1633\na(I3060000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00@'\np1634\ntp1635\nRp1636\ng1516\nF3.0\ntp1637\na(I3070000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\x03@'\np1638\ntp1639\nRp1640\ng1516\nF7.0\ntp1641\na(I3080000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\x0b@'\np1642\ntp1643\nRp1644\ng1516\nF4.0\ntp1645\na(I3090000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x0f@'\np1646\ntp1647\nRp1648\ng1516\nF5.0\ntp1649\na(I3100000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x12@'\np1650\ntp1651\nRp1652\ng1516\nF2.0\ntp1653\na(I3110000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\x12@'\np1654\ntp1655\nRp1656\ng1516\nF6.0\ntp1657\na(I3120000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\x12@'\np1658\ntp1659\nRp1660\ng1516\nF2.0\ntp1661\na(I3130000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x11@'\np1662\ntp1663\nRp1664\ng1516\nF3.0\ntp1665\na(I3140000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\x10@'\np1666\ntp1667\nRp1668\ng1516\nF1.0\ntp1669\na(I3150000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\x10@'\np1670\ntp1671\nRp1672\ng1516\nF1.0\ntp1673\na(I3160000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\x10@'\np1674\ntp1675\nRp1676\ng1516\nF4.0\ntp1677\na(I3170000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\x12@'\np1678\ntp1679\nRp1680\ng1516\nF17.0\ntp1681\na(I3180000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e\\x13@'\np1682\ntp1683\nRp1684\ng1516\nF3.0\ntp1685\na(I3190000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x13@'\np1686\ntp1687\nRp1688\ng1516\nF0.0\ntp1689\na(I3200000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x11@'\np1690\ntp1691\nRp1692\ng1516\nF4.0\ntp1693\na(I3210000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x10@'\np1694\ntp1695\nRp1696\ng1516\nF7.0\ntp1697\na(I3220000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x12@'\np1698\ntp1699\nRp1700\ng1516\nF6.0\ntp1701\na(I3230000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\x14@'\np1702\ntp1703\nRp1704\ng1516\nF8.0\ntp1705\na(I3240000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\x15@'\np1706\ntp1707\nRp1708\ng1516\nF5.0\ntp1709\na(I3250000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x18@'\np1710\ntp1711\nRp1712\ng1516\nF7.0\ntp1713\na(I3260000\ng1\n(g5\nS'ffffff\\x16@'\np1714\ntp1715\nRp1716\ng1516\nF8.0\ntp1717\na(I3270000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\x16@'\np1718\ntp1719\nRp1720\ng1516\nF1.0\ntp1721\na(I3280000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x16@'\np1722\ntp1723\nRp1724\ng1516\nF5.0\ntp1725\na(I3290000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x17@'\np1726\ntp1727\nRp1728\ng1516\nF5.0\ntp1729\na(I3300000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\x16@'\np1730\ntp1731\nRp1732\ng1516\nF5.0\ntp1733\na(I3310000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x15@'\np1734\ntp1735\nRp1736\ng1516\nF2.0\ntp1737\na(I3320000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x16@'\np1738\ntp1739\nRp1740\ng1516\nF6.0\ntp1741\na(I3330000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x19@'\np1742\ntp1743\nRp1744\ng1516\nF2.0\ntp1745\na(I3340000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\x1b@'\np1746\ntp1747\nRp1748\ng1516\nF6.0\ntp1749\na(I3350000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\x1d@'\np1750\ntp1751\nRp1752\ng1516\nF11.0\ntp1753\na(I3360000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\x1f@'\np1754\ntp1755\nRp1756\ng1516\nF12.0\ntp1757\na(I3370000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8 @'\np1758\ntp1759\nRp1760\ng1516\nF7.0\ntp1761\na(I3380000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa!@'\np1762\ntp1763\nRp1764\ng1516\nF5.0\ntp1765\na(I3390000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL#@'\np1766\ntp1767\nRp1768\ng1516\nF5.0\ntp1769\na(I3400000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00%@'\np1770\ntp1771\nRp1772\ng1516\nF8.0\ntp1773\na(I3410000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc7$@'\np1774\ntp1775\nRp1776\ng1516\nF8.0\ntp1777\na(I3420000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfa$@'\np1778\ntp1779\nRp1780\ng1516\nF13.0\ntp1781\na(I3430000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfa%@'\np1782\ntp1783\nRp1784\ng1516\nF18.0\ntp1785\na(I3440000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x94&@'\np1786\ntp1787\nRp1788\ng1516\nF15.0\ntp1789\na(I3450000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2%@'\np1790\ntp1791\nRp1792\ng1516\nF9.0\ntp1793\na(I3460000\ng1\n(g5\nS\"\\xb8\\x1e\\x85\\xebQ8'@\"\np1794\ntp1795\nRp1796\ng1516\nF9.0\ntp1797\na(I3470000\ng1\n(g5\nS'fffff\\xe6(@'\np1798\ntp1799\nRp1800\ng1516\nF13.0\ntp1801\na(I3480000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05+@'\np1802\ntp1803\nRp1804\ng1516\nF11.0\ntp1805\na(I3490000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14*@'\np1806\ntp1807\nRp1808\ng1516\nF5.0\ntp1809\na(I3500000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8*@'\np1810\ntp1811\nRp1812\ng1516\nF19.0\ntp1813\na(I3510000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14,@'\np1814\ntp1815\nRp1816\ng1516\nF17.0\ntp1817\na(I3520000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB-@'\np1818\ntp1819\nRp1820\ng1516\nF21.0\ntp1821\na(I3530000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc,@'\np1822\ntp1823\nRp1824\ng1516\nF12.0\ntp1825\na(I3540000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7+@'\np1826\ntp1827\nRp1828\ng1516\nF7.0\ntp1829\na(I3550000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa.@'\np1830\ntp1831\nRp1832\ng1516\nF30.0\ntp1833\na(I3560000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=/@'\np1834\ntp1835\nRp1836\ng1516\nF8.0\ntp1837\na(I3570000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k/@'\np1838\ntp1839\nRp1840\ng1516\nF18.0\ntp1841\na(I3580000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2.@'\np1842\ntp1843\nRp1844\ng1516\nF26.0\ntp1845\na(I3590000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa0@'\np1846\ntp1847\nRp1848\ng1516\nF28.0\ntp1849\na(I3600000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:1@'\np1850\ntp1851\nRp1852\ng1516\nF22.0\ntp1853\na(I3610000\ng1\n(g5\nS'ffffff1@'\np1854\ntp1855\nRp1856\ng1516\nF17.0\ntp1857\na(I3620000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfa1@'\np1858\ntp1859\nRp1860\ng1516\nF18.0\ntp1861\na(I3630000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf52@'\np1862\ntp1863\nRp1864\ng1516\nF12.0\ntp1865\na(I3640000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba3@'\np1866\ntp1867\nRp1868\ng1516\nF30.0\ntp1869\na(I3650000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np1870\ntp1871\nRp1872\ng1516\nF34.0\ntp1873\na(I3660000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xe34@'\np1874\ntp1875\nRp1876\ng1516\nF20.0\ntp1877\na(I3670000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n4@'\np1878\ntp1879\nRp1880\ng1516\nF19.0\ntp1881\na(I3680000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np1882\ntp1883\nRp1884\ng1516\nF17.0\ntp1885\na(I3690000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ85@'\np1886\ntp1887\nRp1888\ng1516\nF30.0\ntp1889\na(I3700000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:5@'\np1890\ntp1891\nRp1892\ng1516\nF27.0\ntp1893\na(I3710000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=5@'\np1894\ntp1895\nRp1896\ng1516\nF10.0\ntp1897\na(I3720000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x945@'\np1898\ntp1899\nRp1900\ng1516\nF19.0\ntp1901\na(I3730000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab5@'\np1902\ntp1903\nRp1904\ng1516\nF17.0\ntp1905\na(I3740000\ng1\n(g5\nS'33333\\xf35@'\np1906\ntp1907\nRp1908\ng1516\nF40.0\ntp1909\na(I3750000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h7@'\np1910\ntp1911\nRp1912\ng1516\nF36.0\ntp1913\na(I3760000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x828@'\np1914\ntp1915\nRp1916\ng1516\nF23.0\ntp1917\na(I3770000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc08@'\np1918\ntp1919\nRp1920\ng1516\nF31.0\ntp1921\na(I3780000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x949@'\np1922\ntp1923\nRp1924\ng1516\nF22.0\ntp1925\na(I3790000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05:@'\np1926\ntp1927\nRp1928\ng1516\nF14.0\ntp1929\na(I3800000\ng1\n(g5\nS'q=\\n\\xd7\\xa30:@'\np1930\ntp1931\nRp1932\ng1516\nF17.0\ntp1933\na(I3810000\ng1\n(g5\nS'33333s:@'\np1934\ntp1935\nRp1936\ng1516\nF19.0\ntp1937\na(I3820000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y;@'\np1938\ntp1939\nRp1940\ng1516\nF34.0\ntp1941\na(I3830000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h;@'\np1942\ntp1943\nRp1944\ng1516\nF50.0\ntp1945\na(I3840000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x91;@'\np1946\ntp1947\nRp1948\ng1516\nF21.0\ntp1949\na(I3850000\ng1\n(g5\nS'fffff\\xe6;@'\np1950\ntp1951\nRp1952\ng1516\nF24.0\ntp1953\na(I3860000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x07?@'\np1954\ntp1955\nRp1956\ng1516\nF56.0\ntp1957\na(I3870000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}?@'\np1958\ntp1959\nRp1960\ng1516\nF18.0\ntp1961\na(I3880000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x0e@@'\np1962\ntp1963\nRp1964\ng1516\nF36.0\ntp1965\na(I3890000\ng1\n(g5\nS'33333\\xd3@@'\np1966\ntp1967\nRp1968\ng1516\nF73.0\ntp1969\na(I3900000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xa5A@'\np1970\ntp1971\nRp1972\ng1516\nF45.0\ntp1973\na(I3910000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\nB@'\np1974\ntp1975\nRp1976\ng1516\nF42.0\ntp1977\na(I3920000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x87B@'\np1978\ntp1979\nRp1980\ng1516\nF56.0\ntp1981\na(I3930000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(<C@'\np1982\ntp1983\nRp1984\ng1516\nF65.0\ntp1985\na(I3940000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xb1C@'\np1986\ntp1987\nRp1988\ng1516\nF21.0\ntp1989\na(I3950000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x01D@'\np1990\ntp1991\nRp1992\ng1516\nF57.0\ntp1993\na(I3960000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc,C@'\np1994\ntp1995\nRp1996\ng1516\nF22.0\ntp1997\na(I3970000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x17C@'\np1998\ntp1999\nRp2000\ng1516\nF31.0\ntp2001\na(I3980000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8C@'\np2002\ntp2003\nRp2004\ng1516\nF60.0\ntp2005\na(I3990000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14ND@'\np2006\ntp2007\nRp2008\ng1516\nF42.0\ntp2009\na(I4000000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeGD@'\np2010\ntp2011\nRp2012\ng1516\nF40.0\ntp2013\na(I4010000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xd9D@'\np2014\ntp2015\nRp2016\ng1516\nF54.0\ntp2017\na(I4020000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xf7D@'\np2018\ntp2019\nRp2020\ng1516\nF44.0\ntp2021\na(I4030000\ng1\n(g5\nS'\\xa4p=\\n\\xd7CE@'\np2022\ntp2023\nRp2024\ng1516\nF38.0\ntp2025\na(I4040000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xe0E@'\np2026\ntp2027\nRp2028\ng1516\nF48.0\ntp2029\na(I4050000\ng1\n(g5\nS'\\xd7\\xa3p=\\n7F@'\np2030\ntp2031\nRp2032\ng1516\nF41.0\ntp2033\na(I4060000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xd0F@'\np2034\ntp2035\nRp2036\ng1516\nF62.0\ntp2037\na(I4070000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8~G@'\np2038\ntp2039\nRp2040\ng1516\nF66.0\ntp2041\na(I4080000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x9dG@'\np2042\ntp2043\nRp2044\ng1516\nF52.0\ntp2045\na(I4090000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xc3G@'\np2046\ntp2047\nRp2048\ng1516\nF22.0\ntp2049\na(I4100000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xe2G@'\np2050\ntp2051\nRp2052\ng1516\nF39.0\ntp2053\na(I4110000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xd0G@'\np2054\ntp2055\nRp2056\ng1516\nF37.0\ntp2057\na(I4120000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1ZH@'\np2058\ntp2059\nRp2060\ng1516\nF53.0\ntp2061\na(I4130000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xaaH@'\np2062\ntp2063\nRp2064\ng1516\nF72.0\ntp2065\na(I4140000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd1H@'\np2066\ntp2067\nRp2068\ng1516\nF33.0\ntp2069\na(I4150000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1H@'\np2070\ntp2071\nRp2072\ng1516\nF62.0\ntp2073\na(I4160000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0fI@'\np2074\ntp2075\nRp2076\ng1516\nF57.0\ntp2077\na(I4170000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00`I@'\np2078\ntp2079\nRp2080\ng1516\nF56.0\ntp2081\na(I4180000\ng1\n(g5\nS'q=\\n\\xd7\\xa3pI@'\np2082\ntp2083\nRp2084\ng1516\nF69.0\ntp2085\na(I4190000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xa2I@'\np2086\ntp2087\nRp2088\ng1516\nF53.0\ntp2089\na(I4200000\ng1\n(g5\nS'33333SJ@'\np2090\ntp2091\nRp2092\ng1516\nF70.0\ntp2093\na(I4210000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQxJ@'\np2094\ntp2095\nRp2096\ng1516\nF26.0\ntp2097\na(I4220000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05K@'\np2098\ntp2099\nRp2100\ng1516\nF72.0\ntp2101\na(I4230000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xbaK@'\np2102\ntp2103\nRp2104\ng1516\nF73.0\ntp2105\na(I4240000\ng1\n(g5\nS'fffff\\xe6K@'\np2106\ntp2107\nRp2108\ng1516\nF36.0\ntp2109\na(I4250000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xa7K@'\np2110\ntp2111\nRp2112\ng1516\nF34.0\ntp2113\na(I4260000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQxK@'\np2114\ntp2115\nRp2116\ng1516\nF32.0\ntp2117\na(I4270000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14L@'\np2118\ntp2119\nRp2120\ng1516\nF53.0\ntp2121\na(I4280000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebqL@'\np2122\ntp2123\nRp2124\ng1516\nF78.0\ntp2125\na(I4290000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcclL@'\np2126\ntp2127\nRp2128\ng1516\nF70.0\ntp2129\na(I4300000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xf7L@'\np2130\ntp2131\nRp2132\ng1516\nF76.0\ntp2133\na(I4310000\ng1\n(g5\nS'fffff\\x86L@'\np2134\ntp2135\nRp2136\ng1516\nF64.0\ntp2137\na(I4320000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xfcL@'\np2138\ntp2139\nRp2140\ng1516\nF84.0\ntp2141\na(I4330000\ng1\n(g5\nS'33333sM@'\np2142\ntp2143\nRp2144\ng1516\nF54.0\ntp2145\na(I4340000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xd8M@'\np2146\ntp2147\nRp2148\ng1516\nF66.0\ntp2149\na(I4350000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG!N@'\np2150\ntp2151\nRp2152\ng1516\nF65.0\ntp2153\na(I4360000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(|N@'\np2154\ntp2155\nRp2156\ng1516\nF81.0\ntp2157\na(I4370000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf0N@'\np2158\ntp2159\nRp2160\ng1516\nF89.0\ntp2161\na(I4380000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#O@'\np2162\ntp2163\nRp2164\ng1516\nF39.0\ntp2165\na(I4390000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xe0O@'\np2166\ntp2167\nRp2168\ng1516\nF45.0\ntp2169\na(I4400000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xc3O@'\np2170\ntp2171\nRp2172\ng1516\nF61.0\ntp2173\na(I4410000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xceO@'\np2174\ntp2175\nRp2176\ng1516\nF72.0\ntp2177\na(I4420000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb0O@'\np2178\ntp2179\nRp2180\ng1516\nF94.0\ntp2181\na(I4430000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x12P@'\np2182\ntp2183\nRp2184\ng1516\nF101.0\ntp2185\na(I4440000\ng1\n(g5\nS\"\\xd7\\xa3p=\\n'P@\"\np2186\ntp2187\nRp2188\ng1516\nF72.0\ntp2189\na(I4450000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x1dP@'\np2190\ntp2191\nRp2192\ng1516\nF62.0\ntp2193\na(I4460000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGAP@'\np2194\ntp2195\nRp2196\ng1516\nF60.0\ntp2197\na(I4470000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\\\P@'\np2198\ntp2199\nRp2200\ng1516\nF89.0\ntp2201\na(I4480000\ng1\n(g5\nS'fffffvP@'\np2202\ntp2203\nRp2204\ng1516\nF63.0\ntp2205\na(I4490000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xacP@'\np2206\ntp2207\nRp2208\ng1516\nF121.0\ntp2209\na(I4500000\ng1\n(g5\nS'fffff\\x96P@'\np2210\ntp2211\nRp2212\ng1516\nF63.0\ntp2213\na(I4510000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xd2P@'\np2214\ntp2215\nRp2216\ng1516\nF91.0\ntp2217\na(I4520000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc0P@'\np2218\ntp2219\nRp2220\ng1516\nF61.0\ntp2221\na(I4530000\ng1\n(g5\nS'fffff\\x06Q@'\np2222\ntp2223\nRp2224\ng1516\nF60.0\ntp2225\na(I4540000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcclQ@'\np2226\ntp2227\nRp2228\ng1516\nF81.0\ntp2229\na(I4550000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9cQ@'\np2230\ntp2231\nRp2232\ng1516\nF56.0\ntp2233\na(I4560000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xe5Q@'\np2234\ntp2235\nRp2236\ng1516\nF69.0\ntp2237\na(I4570000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2%R@'\np2238\ntp2239\nRp2240\ng1516\nF109.0\ntp2241\na(I4580000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99iR@'\np2242\ntp2243\nRp2244\ng1516\nF101.0\ntp2245\na(I4590000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xeaI@'\np2246\ntp2247\nRp2248\ng1516\nF2.0\ntp2249\na(I4600000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5@@'\np2250\ntp2251\nRp2252\ng1516\nF10.0\ntp2253\na(I4610000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z8@'\np2254\ntp2255\nRp2256\ng1516\nF32.0\ntp2257\na(I4620000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb86@'\np2258\ntp2259\nRp2260\ng1516\nF43.0\ntp2261\na(I4630000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x175@'\np2262\ntp2263\nRp2264\ng1516\nF91.0\ntp2265\na(I4640000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e5@'\np2266\ntp2267\nRp2268\ng1516\nF76.0\ntp2269\na(I4650000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x82:@'\np2270\ntp2271\nRp2272\ng1516\nF89.0\ntp2273\na(I4660000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd1?@'\np2274\ntp2275\nRp2276\ng1516\nF81.0\ntp2277\na(I4670000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x0eC@'\np2278\ntp2279\nRp2280\ng1516\nF106.0\ntp2281\na(I4680000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x81E@'\np2282\ntp2283\nRp2284\ng1516\nF105.0\ntp2285\na(I4690000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x8eH@'\np2286\ntp2287\nRp2288\ng1516\nF77.0\ntp2289\na(I4700000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcclK@'\np2290\ntp2291\nRp2292\ng1516\nF64.0\ntp2293\na(I4710000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xf1N@'\np2294\ntp2295\nRp2296\ng1516\nF78.0\ntp2297\na(I4720000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xf8P@'\np2298\ntp2299\nRp2300\ng1516\nF85.0\ntp2301\na(I4730000\ng1\n(g5\nS'\\n\\xd7\\xa3p=JR@'\np2302\ntp2303\nRp2304\ng1516\nF121.0\ntp2305\na(I4740000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xf5S@'\np2306\ntp2307\nRp2308\ng1516\nF101.0\ntp2309\na(I4750000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5hU@'\np2310\ntp2311\nRp2312\ng1516\nF197.0\ntp2313\na(I4760000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xf0U@'\np2314\ntp2315\nRp2316\ng1516\nF86.0\ntp2317\na(I4770000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x8eV@'\np2318\ntp2319\nRp2320\ng1516\nF114.0\ntp2321\na(I4780000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xb9V@'\np2322\ntp2323\nRp2324\ng1516\nF104.0\ntp2325\na(I4790000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5XW@'\np2326\ntp2327\nRp2328\ng1516\nF79.0\ntp2329\na(I4800000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xedW@'\np2330\ntp2331\nRp2332\ng1516\nF71.0\ntp2333\na(I4810000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xf5V@'\np2334\ntp2335\nRp2336\ng1516\nF78.0\ntp2337\na(I4820000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\OW@'\np2338\ntp2339\nRp2340\ng1516\nF45.0\ntp2341\na(I4830000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0cW@'\np2342\ntp2343\nRp2344\ng1516\nF69.0\ntp2345\na(I4840000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xd7W@'\np2346\ntp2347\nRp2348\ng1516\nF115.0\ntp2349\na(I4850000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd1W@'\np2350\ntp2351\nRp2352\ng1516\nF84.0\ntp2353\na(I4860000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0cX@'\np2354\ntp2355\nRp2356\ng1516\nF116.0\ntp2357\na(I4870000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x83X@'\np2358\ntp2359\nRp2360\ng1516\nF166.0\ntp2361\na(I4880000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xc8X@'\np2362\ntp2363\nRp2364\ng1516\nF116.0\ntp2365\na(I4890000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xe8X@'\np2366\ntp2367\nRp2368\ng1516\nF145.0\ntp2369\na(I4900000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xb0X@'\np2370\ntp2371\nRp2372\ng1516\nF89.0\ntp2373\na(I4910000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xf1X@'\np2374\ntp2375\nRp2376\ng1516\nF118.0\ntp2377\na(I4920000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x84Y@'\np2378\ntp2379\nRp2380\ng1516\nF132.0\ntp2381\na(I4930000\ng1\n(g5\nS'fffffvY@'\np2382\ntp2383\nRp2384\ng1516\nF80.0\ntp2385\na(I4940000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x88Y@'\np2386\ntp2387\nRp2388\ng1516\nF120.0\ntp2389\na(I4950000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x1c[@'\np2390\ntp2391\nRp2392\ng1516\nF81.0\ntp2393\na(I4960000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x8a[@'\np2394\ntp2395\nRp2396\ng1516\nF110.0\ntp2397\na(I4970000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\r\\\\@'\np2398\ntp2399\nRp2400\ng1516\nF90.0\ntp2401\na(I4980000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xba\\\\@'\np2402\ntp2403\nRp2404\ng1516\nF231.0\ntp2405\na(I4990000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x98\\\\@'\np2406\ntp2407\nRp2408\ng1516\nF155.0\ntp2409\na(I5000000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xb5\\\\@'\np2410\ntp2411\nRp2412\ng1516\nF166.0\ntp2413\na(I5010000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fb]@'\np2414\ntp2415\nRp2416\ng1516\nF84.0\ntp2417\na(I5020000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xee]@'\np2418\ntp2419\nRp2420\ng1516\nF282.0\ntp2421\na(I5030000\ng1\n(g5\nS\"H\\xe1z\\x14\\xae'^@\"\np2422\ntp2423\nRp2424\ng1516\nF241.0\ntp2425\na(I5040000\ng1\n(g5\nS\"H\\xe1z\\x14\\xae'_@\"\np2426\ntp2427\nRp2428\ng1516\nF153.0\ntp2429\na(I5050000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c_@'\np2430\ntp2431\nRp2432\ng1516\nF73.0\ntp2433\na(I5060000\ng1\n(g5\nS'33333S`@'\np2434\ntp2435\nRp2436\ng1\n(g5\nS'33333S`@'\np2437\ntp2438\nRp2439\nF225.0\ntp2440\na(I5070000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x92`@'\np2441\ntp2442\nRp2443\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x94`@'\np2444\ntp2445\nRp2446\nF109.0\ntp2447\na(I5080000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1em`@'\np2448\ntp2449\nRp2450\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x95`@'\np2451\ntp2452\nRp2453\nF105.0\ntp2454\na(I5090000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fb`@'\np2455\ntp2456\nRp2457\ng2453\nF92.0\ntp2458\na(I5100000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14N`@'\np2459\ntp2460\nRp2461\ng2453\nF150.0\ntp2462\na(I5110000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xc6`@'\np2463\ntp2464\nRp2465\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xc6`@'\np2466\ntp2467\nRp2468\nF168.0\ntp2469\na(I5120000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xff`@'\np2470\ntp2471\nRp2472\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x00a@'\np2473\ntp2474\nRp2475\nF102.0\ntp2476\na(I5130000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGIa@'\np2477\ntp2478\nRp2479\ng1\n(g5\nS'\\xe1z\\x14\\xaeGIa@'\np2480\ntp2481\nRp2482\nF178.0\ntp2483\na(I5140000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xeea@'\np2484\ntp2485\nRp2486\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xeea@'\np2487\ntp2488\nRp2489\nF246.0\ntp2490\na(I5150000\ng1\n(g5\nS'\\xa4p=\\n\\xd73b@'\np2491\ntp2492\nRp2493\ng1\n(g5\nS'\\xa4p=\\n\\xd73b@'\np2494\ntp2495\nRp2496\nF198.0\ntp2497\na(I5160000\ng1\n(g5\nS'\\xa4p=\\n\\xd7[b@'\np2498\ntp2499\nRp2500\ng1\n(g5\nS'\\xa4p=\\n\\xd7[b@'\np2501\ntp2502\nRp2503\nF256.0\ntp2504\na(I5170000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xe6b@'\np2505\ntp2506\nRp2507\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xefb@'\np2508\ntp2509\nRp2510\nF144.0\ntp2511\na(I5180000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xf2b@'\np2512\ntp2513\nRp2514\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x10c@'\np2515\ntp2516\nRp2517\nF95.0\ntp2518\na(I5190000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xdeb@'\np2519\ntp2520\nRp2521\ng2517\nF242.0\ntp2522\na(I5200000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fjc@'\np2523\ntp2524\nRp2525\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fjc@'\np2526\ntp2527\nRp2528\nF265.0\ntp2529\na(I5210000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xffb@'\np2530\ntp2531\nRp2532\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x8dc@'\np2533\ntp2534\nRp2535\nF90.0\ntp2536\na(I5220000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x08c@'\np2537\ntp2538\nRp2539\ng2535\nF191.0\ntp2540\na(I5230000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGYc@'\np2541\ntp2542\nRp2543\ng2535\nF192.0\ntp2544\na(I5240000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xe8c@'\np2545\ntp2546\nRp2547\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xe8c@'\np2548\ntp2549\nRp2550\nF132.0\ntp2551\na(I5250000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5`d@'\np2552\ntp2553\nRp2554\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99ad@'\np2555\ntp2556\nRp2557\nF207.0\ntp2558\na(I5260000\ng1\n(g5\nS'\\n\\xd7\\xa3p=Zd@'\np2559\ntp2560\nRp2561\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x80d@'\np2562\ntp2563\nRp2564\nF216.0\ntp2565\na(I5270000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x8ed@'\np2566\ntp2567\nRp2568\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x8ed@'\np2569\ntp2570\nRp2571\nF231.0\ntp2572\na(I5280000\ng1\n(g5\nS'=\\n\\xd7\\xa3p5e@'\np2573\ntp2574\nRp2575\ng1\n(g5\nS'=\\n\\xd7\\xa3p5e@'\np2576\ntp2577\nRp2578\nF141.0\ntp2579\na(I5290000\ng1\n(g5\nS'fffff^e@'\np2580\ntp2581\nRp2582\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(te@'\np2583\ntp2584\nRp2585\nF165.0\ntp2586\na(I5300000\ng1\n(g5\nS'33333#f@'\np2587\ntp2588\nRp2589\ng1\n(g5\nS'33333#f@'\np2590\ntp2591\nRp2592\nF284.0\ntp2593\na(I5310000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8frf@'\np2594\ntp2595\nRp2596\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x80f@'\np2597\ntp2598\nRp2599\nF221.0\ntp2600\na(I5320000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x07f@'\np2601\ntp2602\nRp2603\ng2599\nF206.0\ntp2604\na(I5330000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGqf@'\np2605\ntp2606\nRp2607\ng2599\nF176.0\ntp2608\na(I5340000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xcaf@'\np2609\ntp2610\nRp2611\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xcaf@'\np2612\ntp2613\nRp2614\nF178.0\ntp2615\na(I5350000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x02g@'\np2616\ntp2617\nRp2618\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x02g@'\np2619\ntp2620\nRp2621\nF260.0\ntp2622\na(I5360000\ng1\n(g5\nS'33333+f@'\np2623\ntp2624\nRp2625\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.g@'\np2626\ntp2627\nRp2628\nF61.0\ntp2629\na(I5370000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xbdf@'\np2630\ntp2631\nRp2632\ng2628\nF212.0\ntp2633\na(I5380000\ng1\n(g5\nS'33333\\xb3f@'\np2634\ntp2635\nRp2636\ng2628\nF127.0\ntp2637\na(I5390000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x8af@'\np2638\ntp2639\nRp2640\ng2628\nF274.0\ntp2641\na(I5400000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\7f@'\np2642\ntp2643\nRp2644\ng2628\nF116.0\ntp2645\na(I5410000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xfde@'\np2646\ntp2647\nRp2648\ng2628\nF151.0\ntp2649\na(I5420000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xece@'\np2650\ntp2651\nRp2652\ng2628\nF308.0\ntp2653\na(I5430000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x94e@'\np2654\ntp2655\nRp2656\ng2628\nF85.0\ntp2657\na(I5440000\ng1\n(g5\nS'q=\\n\\xd7\\xa3`e@'\np2658\ntp2659\nRp2660\ng2628\nF263.0\ntp2661\na(I5450000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x86e@'\np2662\ntp2663\nRp2664\ng2628\nF310.0\ntp2665\na(I5460000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8&e@'\np2666\ntp2667\nRp2668\ng2628\nF130.0\ntp2669\na(I5470000\ng1\n(g5\nS'\\xa4p=\\n\\xd7ce@'\np2670\ntp2671\nRp2672\ng2628\nF85.0\ntp2673\na(I5480000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc4f@'\np2674\ntp2675\nRp2676\ng2628\nF269.0\ntp2677\na(I5490000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x82f@'\np2678\ntp2679\nRp2680\ng2628\nF334.0\ntp2681\na(I5500000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x90f@'\np2682\ntp2683\nRp2684\ng2628\nF211.0\ntp2685\na(I5510000\ng1\n(g5\nS'\\xa4p=\\n\\xd7kf@'\np2686\ntp2687\nRp2688\ng2628\nF229.0\ntp2689\na(I5520000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14vg@'\np2690\ntp2691\nRp2692\ng1\n(g5\nS'\\xaeG\\xe1z\\x14vg@'\np2693\ntp2694\nRp2695\nF256.0\ntp2696\na(I5530000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00(h@'\np2697\ntp2698\nRp2699\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00(h@'\np2700\ntp2701\nRp2702\nF232.0\ntp2703\na(I5540000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xa0h@'\np2704\ntp2705\nRp2706\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xa0h@'\np2707\ntp2708\nRp2709\nF228.0\ntp2710\na(I5550000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x13i@'\np2711\ntp2712\nRp2713\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x13i@'\np2714\ntp2715\nRp2716\nF252.0\ntp2717\na(I5560000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x8di@'\np2718\ntp2719\nRp2720\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x8ei@'\np2721\ntp2722\nRp2723\nF255.0\ntp2724\na(I5570000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x9aj@'\np2725\ntp2726\nRp2727\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x9aj@'\np2728\ntp2729\nRp2730\nF233.0\ntp2731\na(I5580000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14Vk@'\np2732\ntp2733\nRp2734\ng1\n(g5\nS'\\xaeG\\xe1z\\x14Vk@'\np2735\ntp2736\nRp2737\nF271.0\ntp2738\na(I5590000\ng1\n(g5\nS'\\n\\xd7\\xa3p=Bl@'\np2739\ntp2740\nRp2741\ng1\n(g5\nS'\\n\\xd7\\xa3p=Bl@'\np2742\ntp2743\nRp2744\nF283.0\ntp2745\na(I5600000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x19m@'\np2746\ntp2747\nRp2748\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x19m@'\np2749\ntp2750\nRp2751\nF317.0\ntp2752\na(I5610000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb9m@'\np2753\ntp2754\nRp2755\ng1\n(g5\nS'\\xd7\\xa3p=\\n_m@'\np2756\ntp2757\nRp2758\nF133.0\ntp2759\na(I5620000\ng1\n(g5\nS'H\\xe1z\\x14\\xae?m@'\np2760\ntp2761\nRp2762\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x82m@'\np2763\ntp2764\nRp2765\nF270.0\ntp2766\na(I5630000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x96m@'\np2767\ntp2768\nRp2769\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xe2m@'\np2770\ntp2771\nRp2772\nF182.0\ntp2773\na(I5640000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xd2m@'\np2774\ntp2775\nRp2776\ng2772\nF245.0\ntp2777\na(I5650000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xe4m@'\np2778\ntp2779\nRp2780\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xe4m@'\np2781\ntp2782\nRp2783\nF336.0\ntp2784\na(I5660000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xd6m@'\np2785\ntp2786\nRp2787\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00 n@'\np2788\ntp2789\nRp2790\nF140.0\ntp2791\na(I5670000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x17n@'\np2792\ntp2793\nRp2794\ng2790\nF281.0\ntp2795\na(I5680000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xcen@'\np2796\ntp2797\nRp2798\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xcen@'\np2799\ntp2800\nRp2801\nF286.0\ntp2802\na(I5690000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xe3n@'\np2803\ntp2804\nRp2805\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xe4n@'\np2806\ntp2807\nRp2808\nF251.0\ntp2809\na(I5700000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99qo@'\np2810\ntp2811\nRp2812\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99qo@'\np2813\ntp2814\nRp2815\nF324.0\ntp2816\na(I5710000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x17p@'\np2817\ntp2818\nRp2819\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x17p@'\np2820\ntp2821\nRp2822\nF271.0\ntp2823\na(I5720000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zDp@'\np2824\ntp2825\nRp2826\ng1\n(g5\nS'\\x14\\xaeG\\xe1zDp@'\np2827\ntp2828\nRp2829\nF413.0\ntp2830\na(I5730000\ng1\n(g5\nS'\\n\\xd7\\xa3p=Rp@'\np2831\ntp2832\nRp2833\ng1\n(g5\nS'\\n\\xd7\\xa3p=Rp@'\np2834\ntp2835\nRp2836\nF265.0\ntp2837\na(I5740000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eep@'\np2838\ntp2839\nRp2840\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eep@'\np2841\ntp2842\nRp2843\nF257.0\ntp2844\na(I5750000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x83p@'\np2845\ntp2846\nRp2847\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x83p@'\np2848\ntp2849\nRp2850\nF372.0\ntp2851\na(I5760000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5lp@'\np2852\ntp2853\nRp2854\ng1\n(g5\nS'33333\\xa3p@'\np2855\ntp2856\nRp2857\nF281.0\ntp2858\na(I5770000\ng1\n(g5\nS'\\xa4p=\\n\\xd7+p@'\np2859\ntp2860\nRp2861\ng2857\nF116.0\ntp2862\na(I5780000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14*p@'\np2863\ntp2864\nRp2865\ng2857\nF252.0\ntp2866\na(I5790000\ng1\n(g5\nS'fffffJp@'\np2867\ntp2868\nRp2869\ng2857\nF218.0\ntp2870\na(I5800000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQdp@'\np2871\ntp2872\nRp2873\ng2857\nF277.0\ntp2874\na(I5810000\ng1\n(g5\nS'fffff\\x86p@'\np2875\ntp2876\nRp2877\ng2857\nF249.0\ntp2878\na(I5820000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xa9p@'\np2879\ntp2880\nRp2881\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xb6p@'\np2882\ntp2883\nRp2884\nF268.0\ntp2885\na(I5830000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xcep@'\np2886\ntp2887\nRp2888\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xd8p@'\np2889\ntp2890\nRp2891\nF233.0\ntp2892\na(I5840000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x0eq@'\np2893\ntp2894\nRp2895\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x0eq@'\np2896\ntp2897\nRp2898\nF406.0\ntp2899\na(I5850000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\tq@'\np2900\ntp2901\nRp2902\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0fq@'\np2903\ntp2904\nRp2905\nF317.0\ntp2906\na(I5860000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGEq@'\np2907\ntp2908\nRp2909\ng1\n(g5\nS'\\xe1z\\x14\\xaeGEq@'\np2910\ntp2911\nRp2912\nF297.0\ntp2913\na(I5870000\ng1\n(g5\nS'33333Wq@'\np2914\ntp2915\nRp2916\ng1\n(g5\nS'\\xd7\\xa3p=\\ncq@'\np2917\ntp2918\nRp2919\nF288.0\ntp2920\na(I5880000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fFq@'\np2921\ntp2922\nRp2923\ng2919\nF400.0\ntp2924\na(I5890000\ng1\n(g5\nS'q=\\n\\xd7\\xa3tq@'\np2925\ntp2926\nRp2927\ng1\n(g5\nS'q=\\n\\xd7\\xa3tq@'\np2928\ntp2929\nRp2930\nF292.0\ntp2931\na(I5900000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x9bq@'\np2932\ntp2933\nRp2934\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8q@'\np2935\ntp2936\nRp2937\nF226.0\ntp2938\na(I5910000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xa4q@'\np2939\ntp2940\nRp2941\ng2937\nF375.0\ntp2942\na(I5920000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb9q@'\np2943\ntp2944\nRp2945\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb9q@'\np2946\ntp2947\nRp2948\nF297.0\ntp2949\na(I5930000\ng1\n(g5\nS'33333\\x83q@'\np2950\ntp2951\nRp2952\ng2948\nF357.0\ntp2953\na(I5940000\ng1\n(g5\nS'33333\\xcfq@'\np2954\ntp2955\nRp2956\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xd2q@'\np2957\ntp2958\nRp2959\nF142.0\ntp2960\na(I5950000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x03r@'\np2961\ntp2962\nRp2963\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\rr@'\np2964\ntp2965\nRp2966\nF253.0\ntp2967\na(I5960000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x82r@'\np2968\ntp2969\nRp2970\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x8er@'\np2971\ntp2972\nRp2973\nF275.0\ntp2974\na(I5970000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x83r@'\np2975\ntp2976\nRp2977\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xb1r@'\np2978\ntp2979\nRp2980\nF251.0\ntp2981\na(I5980000\ng1\n(g5\nS'33333\\x8br@'\np2982\ntp2983\nRp2984\ng2980\nF296.0\ntp2985\na(I5990000\ng1\n(g5\nS'33333\\xabr@'\np2986\ntp2987\nRp2988\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb8r@'\np2989\ntp2990\nRp2991\nF264.0\ntp2992\na(I6000000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x98r@'\np2993\ntp2994\nRp2995\ng2991\nF296.0\ntp2996\na(I6010000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xadr@'\np2997\ntp2998\nRp2999\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xbbr@'\np3000\ntp3001\nRp3002\nF211.0\ntp3003\na(I6020000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x95r@'\np3004\ntp3005\nRp3006\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xbcr@'\np3007\ntp3008\nRp3009\nF284.0\ntp3010\na(I6030000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x9ar@'\np3011\ntp3012\nRp3013\ng3009\nF365.0\ntp3014\na(I6040000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8Vr@'\np3015\ntp3016\nRp3017\ng3009\nF232.0\ntp3018\na(I6050000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:r@'\np3019\ntp3020\nRp3021\ng3009\nF313.0\ntp3022\na(I6060000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99]r@'\np3023\ntp3024\nRp3025\ng3009\nF387.0\ntp3026\na(I6070000\ng1\n(g5\nS'\\xa4p=\\n\\xd7gr@'\np3027\ntp3028\nRp3029\ng3009\nF379.0\ntp3030\na(I6080000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x88r@'\np3031\ntp3032\nRp3033\ng3009\nF407.0\ntp3034\na(I6090000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x97r@'\np3035\ntp3036\nRp3037\ng3009\nF229.0\ntp3038\na(I6100000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xa3r@'\np3039\ntp3040\nRp3041\ng3009\nF410.0\ntp3042\na(I6110000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85{r@'\np3043\ntp3044\nRp3045\ng3009\nF305.0\ntp3046\na(I6120000\ng1\n(g5\nS'fffffrr@'\np3047\ntp3048\nRp3049\ng3009\nF375.0\ntp3050\na(I6130000\ng1\n(g5\nS'H\\xe1z\\x14\\xae{r@'\np3051\ntp3052\nRp3053\ng3009\nF399.0\ntp3054\na(I6140000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb0r@'\np3055\ntp3056\nRp3057\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xc2r@'\np3058\ntp3059\nRp3060\nF323.0\ntp3061\na(I6150000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xaer@'\np3062\ntp3063\nRp3064\ng3060\nF338.0\ntp3065\na(I6160000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xdbr@'\np3066\ntp3067\nRp3068\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xdbr@'\np3069\ntp3070\nRp3071\nF314.0\ntp3072\na(I6170000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x06s@'\np3073\ntp3074\nRp3075\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x07s@'\np3076\ntp3077\nRp3078\nF249.0\ntp3079\na(I6180000\ng1\n(g5\nS'fffff\\x12s@'\np3080\ntp3081\nRp3082\ng1\n(g5\nS'fffff\\x12s@'\np3083\ntp3084\nRp3085\nF389.0\ntp3086\na(I6190000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1Zs@'\np3087\ntp3088\nRp3089\ng1\n(g5\nS'{\\x14\\xaeG\\xe1Zs@'\np3090\ntp3091\nRp3092\nF314.0\ntp3093\na(I6200000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fbs@'\np3094\ntp3095\nRp3096\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x83s@'\np3097\ntp3098\nRp3099\nF361.0\ntp3100\na(I6210000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc`s@'\np3101\ntp3102\nRp3103\ng3099\nF270.0\ntp3104\na(I6220000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x9ds@'\np3105\ntp3106\nRp3107\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x9ds@'\np3108\ntp3109\nRp3110\nF306.0\ntp3111\na(I6230000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xc8s@'\np3112\ntp3113\nRp3114\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xc8s@'\np3115\ntp3116\nRp3117\nF406.0\ntp3118\na(I6240000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xf4s@'\np3119\ntp3120\nRp3121\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xf8s@'\np3122\ntp3123\nRp3124\nF350.0\ntp3125\na(I6250000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x18t@'\np3126\ntp3127\nRp3128\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x18t@'\np3129\ntp3130\nRp3131\nF358.0\ntp3132\na(I6260000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xe8s@'\np3133\ntp3134\nRp3135\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x1ft@'\np3136\ntp3137\nRp3138\nF350.0\ntp3139\na(I6270000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xd7s@'\np3140\ntp3141\nRp3142\ng3138\nF338.0\ntp3143\na(I6280000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbds@'\np3144\ntp3145\nRp3146\ng3138\nF329.0\ntp3147\na(I6290000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xc6s@'\np3148\ntp3149\nRp3150\ng3138\nF358.0\ntp3151\na(I6300000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xe0s@'\np3152\ntp3153\nRp3154\ng3138\nF312.0\ntp3155\na(I6310000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xf4s@'\np3156\ntp3157\nRp3158\ng3138\nF354.0\ntp3159\na(I6320000\ng1\n(g5\nS'=\\n\\xd7\\xa3p)t@'\np3160\ntp3161\nRp3162\ng1\n(g5\nS'=\\n\\xd7\\xa3p)t@'\np3163\ntp3164\nRp3165\nF371.0\ntp3166\na(I6330000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eQt@'\np3167\ntp3168\nRp3169\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eQt@'\np3170\ntp3171\nRp3172\nF340.0\ntp3173\na(I6340000\ng1\n(g5\nS'33333;t@'\np3174\ntp3175\nRp3176\ng3172\nF335.0\ntp3177\na(I6350000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8.t@'\np3178\ntp3179\nRp3180\ng3172\nF376.0\ntp3181\na(I6360000\ng1\n(g5\nS'\\xa4p=\\n\\xd7Ot@'\np3182\ntp3183\nRp3184\ng3172\nF440.0\ntp3185\na(I6370000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x857t@'\np3186\ntp3187\nRp3188\ng1\n(g5\nS'q=\\n\\xd7\\xa3Tt@'\np3189\ntp3190\nRp3191\nF290.0\ntp3192\na(I6380000\ng1\n(g5\nS'\\xd7\\xa3p=\\ngt@'\np3193\ntp3194\nRp3195\ng1\n(g5\nS'\\xd7\\xa3p=\\ngt@'\np3196\ntp3197\nRp3198\nF401.0\ntp3199\na(I6390000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85ot@'\np3200\ntp3201\nRp3202\ng1\n(g5\nS'\\xe1z\\x14\\xaeGut@'\np3203\ntp3204\nRp3205\nF417.0\ntp3206\na(I6400000\ng1\n(g5\nS'=\\n\\xd7\\xa3pmt@'\np3207\ntp3208\nRp3209\ng3205\nF422.0\ntp3210\na(I6410000\ng1\n(g5\nS'fffff\\x92t@'\np3211\ntp3212\nRp3213\ng1\n(g5\nS'fffff\\x92t@'\np3214\ntp3215\nRp3216\nF408.0\ntp3217\na(I6420000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xaft@'\np3218\ntp3219\nRp3220\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xaft@'\np3221\ntp3222\nRp3223\nF404.0\ntp3224\na(I6430000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xc9t@'\np3225\ntp3226\nRp3227\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xd2t@'\np3228\ntp3229\nRp3230\nF368.0\ntp3231\na(I6440000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xdft@'\np3232\ntp3233\nRp3234\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xdft@'\np3235\ntp3236\nRp3237\nF363.0\ntp3238\na(I6450000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xe7t@'\np3239\ntp3240\nRp3241\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xe7t@'\np3242\ntp3243\nRp3244\nF391.0\ntp3245\na(I6460000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xd8t@'\np3246\ntp3247\nRp3248\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xfdt@'\np3249\ntp3250\nRp3251\nF279.0\ntp3252\na(I6470000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xfct@'\np3253\ntp3254\nRp3255\ng3251\nF334.0\ntp3256\na(I6480000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x17u@'\np3257\ntp3258\nRp3259\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x17u@'\np3260\ntp3261\nRp3262\nF299.0\ntp3263\na(I6490000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG9u@'\np3264\ntp3265\nRp3266\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eEu@'\np3267\ntp3268\nRp3269\nF264.0\ntp3270\na(I6500000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc21u@'\np3271\ntp3272\nRp3273\ng1\n(g5\nS'q=\\n\\xd7\\xa3Lu@'\np3274\ntp3275\nRp3276\nF232.0\ntp3277\na(I6510000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00Hu@'\np3278\ntp3279\nRp3280\ng3276\nF382.0\ntp3281\na(I6520000\ng1\n(g5\nS'\\xa4p=\\n\\xd7_u@'\np3282\ntp3283\nRp3284\ng1\n(g5\nS'\\xa4p=\\n\\xd7_u@'\np3285\ntp3286\nRp3287\nF373.0\ntp3288\na(I6530000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x80u@'\np3289\ntp3290\nRp3291\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x90u@'\np3292\ntp3293\nRp3294\nF209.0\ntp3295\na(I6540000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85cu@'\np3296\ntp3297\nRp3298\ng3294\nF315.0\ntp3299\na(I6550000\ng1\n(g5\nS'\\n\\xd7\\xa3p=~u@'\np3300\ntp3301\nRp3302\ng3294\nF417.0\ntp3303\na(I6560000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x90u@'\np3304\ntp3305\nRp3306\ng3294\nF403.0\ntp3307\na(I6570000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xadu@'\np3308\ntp3309\nRp3310\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xadu@'\np3311\ntp3312\nRp3313\nF391.0\ntp3314\na(I6580000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xefu@'\np3315\ntp3316\nRp3317\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xefu@'\np3318\ntp3319\nRp3320\nF397.0\ntp3321\na(I6590000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xecu@'\np3322\ntp3323\nRp3324\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xf0u@'\np3325\ntp3326\nRp3327\nF405.0\ntp3328\na(I6600000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xc4u@'\np3329\ntp3330\nRp3331\ng3327\nF302.0\ntp3332\na(I6610000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xcfu@'\np3333\ntp3334\nRp3335\ng3327\nF404.0\ntp3336\na(I6620000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xe0u@'\np3337\ntp3338\nRp3339\ng3327\nF320.0\ntp3340\na(I6630000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xdbu@'\np3341\ntp3342\nRp3343\ng3327\nF355.0\ntp3344\na(I6640000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xd6u@'\np3345\ntp3346\nRp3347\ng3327\nF227.0\ntp3348\na(I6650000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd0u@'\np3349\ntp3350\nRp3351\ng3327\nF424.0\ntp3352\na(I6660000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xb0u@'\np3353\ntp3354\nRp3355\ng3327\nF318.0\ntp3356\na(I6670000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xb0u@'\np3357\ntp3358\nRp3359\ng3327\nF358.0\ntp3360\na(I6680000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xbau@'\np3361\ntp3362\nRp3363\ng3327\nF398.0\ntp3364\na(I6690000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xd8u@'\np3365\ntp3366\nRp3367\ng3327\nF359.0\ntp3368\na(I6700000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xeau@'\np3369\ntp3370\nRp3371\ng3327\nF386.0\ntp3372\na(I6710000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xf3u@'\np3373\ntp3374\nRp3375\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xf3u@'\np3376\ntp3377\nRp3378\nF398.0\ntp3379\na(I6720000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xfdu@'\np3380\ntp3381\nRp3382\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x07v@'\np3383\ntp3384\nRp3385\nF367.0\ntp3386\na(I6730000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x0ev@'\np3387\ntp3388\nRp3389\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x0ev@'\np3390\ntp3391\nRp3392\nF420.0\ntp3393\na(I6740000\ng1\n(g5\nS'\\xd7\\xa3p=\\n7v@'\np3394\ntp3395\nRp3396\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb9v@'\np3397\ntp3398\nRp3399\nF373.0\ntp3400\na(I6750000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb=v@'\np3401\ntp3402\nRp3403\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb=v@'\np3404\ntp3405\nRp3406\nF373.0\ntp3407\na(I6760000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8&v@'\np3408\ntp3409\nRp3410\ng3406\nF377.0\ntp3411\na(I6770000\ng1\n(g5\nS'q=\\n\\xd7\\xa3Lv@'\np3412\ntp3413\nRp3414\ng1\n(g5\nS'q=\\n\\xd7\\xa3Lv@'\np3415\ntp3416\nRp3417\nF374.0\ntp3418\na(I6780000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8cv@'\np3419\ntp3420\nRp3421\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x8fv@'\np3422\ntp3423\nRp3424\nF309.0\ntp3425\na(I6790000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}v@'\np3426\ntp3427\nRp3428\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x90v@'\np3429\ntp3430\nRp3431\nF379.0\ntp3432\na(I6800000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1bv@'\np3433\ntp3434\nRp3435\ng3431\nF301.0\ntp3436\na(I6810000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1^v@'\np3437\ntp3438\nRp3439\ng3431\nF398.0\ntp3440\na(I6820000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00Lv@'\np3441\ntp3442\nRp3443\ng3431\nF417.0\ntp3444\na(I6830000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGAv@'\np3445\ntp3446\nRp3447\ng3431\nF375.0\ntp3448\na(I6840000\ng1\n(g5\nS'\\xa4p=\\n\\xd7sv@'\np3449\ntp3450\nRp3451\ng3431\nF373.0\ntp3452\na(I6850000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85{v@'\np3453\ntp3454\nRp3455\ng3431\nF380.0\ntp3456\na(I6860000\ng1\n(g5\nS'H\\xe1z\\x14\\xae?v@'\np3457\ntp3458\nRp3459\ng3431\nF373.0\ntp3460\na(I6870000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1^v@'\np3461\ntp3462\nRp3463\ng3431\nF413.0\ntp3464\na(I6880000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zTv@'\np3465\ntp3466\nRp3467\ng3431\nF206.0\ntp3468\na(I6890000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85;v@'\np3469\ntp3470\nRp3471\ng3431\nF365.0\ntp3472\na(I6900000\ng1\n(g5\nS'q=\\n\\xd7\\xa3Xv@'\np3473\ntp3474\nRp3475\ng3431\nF325.0\ntp3476\na(I6910000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x89v@'\np3477\ntp3478\nRp3479\ng3431\nF421.0\ntp3480\na(I6920000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xc4v@'\np3481\ntp3482\nRp3483\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xc9v@'\np3484\ntp3485\nRp3486\nF362.0\ntp3487\na(I6930000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xc6v@'\np3488\ntp3489\nRp3490\ng3486\nF355.0\ntp3491\na(I6940000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xbcv@'\np3492\ntp3493\nRp3494\ng3486\nF392.0\ntp3495\na(I6950000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xc6v@'\np3496\ntp3497\nRp3498\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xcdv@'\np3499\ntp3500\nRp3501\nF380.0\ntp3502\na(I6960000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd9v@'\np3503\ntp3504\nRp3505\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd9v@'\np3506\ntp3507\nRp3508\nF400.0\ntp3509\na(I6970000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xd9v@'\np3510\ntp3511\nRp3512\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xdcv@'\np3513\ntp3514\nRp3515\nF402.0\ntp3516\na(I6980000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xc8v@'\np3517\ntp3518\nRp3519\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xedv@'\np3520\ntp3521\nRp3522\nF346.0\ntp3523\na(I6990000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x8cv@'\np3524\ntp3525\nRp3526\ng3522\nF65.0\ntp3527\na(I7000000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xb2v@'\np3528\ntp3529\nRp3530\ng3522\nF374.0\ntp3531\na(I7010000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xabv@'\np3532\ntp3533\nRp3534\ng3522\nF283.0\ntp3535\na(I7020000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa7v@'\np3536\ntp3537\nRp3538\ng3522\nF386.0\ntp3539\na(I7030000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xb9v@'\np3540\ntp3541\nRp3542\ng3522\nF407.0\ntp3543\na(I7040000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xcev@'\np3544\ntp3545\nRp3546\ng3522\nF343.0\ntp3547\na(I7050000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xcfv@'\np3548\ntp3549\nRp3550\ng3522\nF388.0\ntp3551\na(I7060000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xeav@'\np3552\ntp3553\nRp3554\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xf5v@'\np3555\ntp3556\nRp3557\nF346.0\ntp3558\na(I7070000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1v@'\np3559\ntp3560\nRp3561\ng3557\nF404.0\ntp3562\na(I7080000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xd8v@'\np3563\ntp3564\nRp3565\ng3557\nF385.0\ntp3566\na(I7090000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xc6v@'\np3567\ntp3568\nRp3569\ng3557\nF322.0\ntp3570\na(I7100000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xd2v@'\np3571\ntp3572\nRp3573\ng3557\nF428.0\ntp3574\na(I7110000\ng1\n(g5\nS'33333\\xdfv@'\np3575\ntp3576\nRp3577\ng3557\nF332.0\ntp3578\na(I7120000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x06w@'\np3579\ntp3580\nRp3581\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x06w@'\np3582\ntp3583\nRp3584\nF383.0\ntp3585\na(I7130000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xf1v@'\np3586\ntp3587\nRp3588\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x08w@'\np3589\ntp3590\nRp3591\nF424.0\ntp3592\na(I7140000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xf9v@'\np3593\ntp3594\nRp3595\ng3591\nF412.0\ntp3596\na(I7150000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc w@'\np3597\ntp3598\nRp3599\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc w@'\np3600\ntp3601\nRp3602\nF442.0\ntp3603\na(I7160000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z8w@'\np3604\ntp3605\nRp3606\ng1\n(g5\nS'\\x14\\xaeG\\xe1z8w@'\np3607\ntp3608\nRp3609\nF417.0\ntp3610\na(I7170000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xfdv@'\np3611\ntp3612\nRp3613\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@w@'\np3614\ntp3615\nRp3616\nF399.0\ntp3617\na(I7180000\ng1\n(g5\nS'33333\\xefv@'\np3618\ntp3619\nRp3620\ng3616\nF277.0\ntp3621\na(I7190000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb-w@'\np3622\ntp3623\nRp3624\ng3616\nF458.0\ntp3625\na(I7200000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85/w@'\np3626\ntp3627\nRp3628\ng3616\nF385.0\ntp3629\na(I7210000\ng1\n(g5\nS'H\\xe1z\\x14\\xae+w@'\np3630\ntp3631\nRp3632\ng3616\nF416.0\ntp3633\na(I7220000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1.w@'\np3634\ntp3635\nRp3636\ng3616\nF360.0\ntp3637\na(I7230000\ng1\n(g5\nS'33333\\x0bw@'\np3638\ntp3639\nRp3640\ng3616\nF360.0\ntp3641\na(I7240000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f&w@'\np3642\ntp3643\nRp3644\ng3616\nF398.0\ntp3645\na(I7250000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8ew@'\np3646\ntp3647\nRp3648\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8ew@'\np3649\ntp3650\nRp3651\nF330.0\ntp3652\na(I7260000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xc9w@'\np3653\ntp3654\nRp3655\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xc9w@'\np3656\ntp3657\nRp3658\nF423.0\ntp3659\na(I7270000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xc4w@'\np3660\ntp3661\nRp3662\ng3658\nF359.0\ntp3663\na(I7280000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xd9w@'\np3664\ntp3665\nRp3666\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xd9w@'\np3667\ntp3668\nRp3669\nF340.0\ntp3670\na(I7290000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xe2w@'\np3671\ntp3672\nRp3673\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xe2w@'\np3674\ntp3675\nRp3676\nF425.0\ntp3677\na(I7300000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xc5w@'\np3678\ntp3679\nRp3680\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xe8w@'\np3681\ntp3682\nRp3683\nF425.0\ntp3684\na(I7310000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xacw@'\np3685\ntp3686\nRp3687\ng3683\nF228.0\ntp3688\na(I7320000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xaaw@'\np3689\ntp3690\nRp3691\ng3683\nF354.0\ntp3692\na(I7330000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x89w@'\np3693\ntp3694\nRp3695\ng3683\nF377.0\ntp3696\na(I7340000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xcew@'\np3697\ntp3698\nRp3699\ng3683\nF416.0\ntp3700\na(I7350000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xc8w@'\np3701\ntp3702\nRp3703\ng3683\nF452.0\ntp3704\na(I7360000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xb5w@'\np3705\ntp3706\nRp3707\ng3683\nF334.0\ntp3708\na(I7370000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x9fw@'\np3709\ntp3710\nRp3711\ng3683\nF408.0\ntp3712\na(I7380000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xb1w@'\np3713\ntp3714\nRp3715\ng3683\nF387.0\ntp3716\na(I7390000\ng1\n(g5\nS'fffff\\xb6w@'\np3717\ntp3718\nRp3719\ng3683\nF361.0\ntp3720\na(I7400000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x88w@'\np3721\ntp3722\nRp3723\ng3683\nF278.0\ntp3724\na(I7410000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x95w@'\np3725\ntp3726\nRp3727\ng3683\nF424.0\ntp3728\na(I7420000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xb2w@'\np3729\ntp3730\nRp3731\ng3683\nF407.0\ntp3732\na(I7430000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xb4w@'\np3733\ntp3734\nRp3735\ng3683\nF421.0\ntp3736\na(I7440000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xa5w@'\np3737\ntp3738\nRp3739\ng3683\nF404.0\ntp3740\na(I7450000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x8fw@'\np3741\ntp3742\nRp3743\ng3683\nF294.0\ntp3744\na(I7460000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xd9w@'\np3745\ntp3746\nRp3747\ng3683\nF398.0\ntp3748\na(I7470000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xdaw@'\np3749\ntp3750\nRp3751\ng3683\nF417.0\ntp3752\na(I7480000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xe5w@'\np3753\ntp3754\nRp3755\ng3683\nF379.0\ntp3756\na(I7490000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xd0w@'\np3757\ntp3758\nRp3759\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xfbw@'\np3760\ntp3761\nRp3762\nF379.0\ntp3763\na(I7500000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xbaw@'\np3764\ntp3765\nRp3766\ng3762\nF262.0\ntp3767\na(I7510000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x99w@'\np3768\ntp3769\nRp3770\ng3762\nF242.0\ntp3771\na(I7520000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8w@'\np3772\ntp3773\nRp3774\ng3762\nF329.0\ntp3775\na(I7530000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xa8w@'\np3776\ntp3777\nRp3778\ng3762\nF389.0\ntp3779\na(I7540000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f^w@'\np3780\ntp3781\nRp3782\ng3762\nF377.0\ntp3783\na(I7550000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zdw@'\np3784\ntp3785\nRp3786\ng3762\nF382.0\ntp3787\na(I7560000\ng1\n(g5\nS'33333[w@'\np3788\ntp3789\nRp3790\ng3762\nF307.0\ntp3791\na(I7570000\ng1\n(g5\nS'33333kw@'\np3792\ntp3793\nRp3794\ng3762\nF345.0\ntp3795\na(I7580000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\kw@'\np3796\ntp3797\nRp3798\ng3762\nF427.0\ntp3799\na(I7590000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x99w@'\np3800\ntp3801\nRp3802\ng3762\nF411.0\ntp3803\na(I7600000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x80w@'\np3804\ntp3805\nRp3806\ng3762\nF374.0\ntp3807\na(I7610000\ng1\n(g5\nS'33333gw@'\np3808\ntp3809\nRp3810\ng3762\nF190.0\ntp3811\na(I7620000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebiw@'\np3812\ntp3813\nRp3814\ng3762\nF396.0\ntp3815\na(I7630000\ng1\n(g5\nS'H\\xe1z\\x14\\xae[w@'\np3816\ntp3817\nRp3818\ng3762\nF396.0\ntp3819\na(I7640000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5pw@'\np3820\ntp3821\nRp3822\ng3762\nF424.0\ntp3823\na(I7650000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8nw@'\np3824\ntp3825\nRp3826\ng3762\nF381.0\ntp3827\na(I7660000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xa2w@'\np3828\ntp3829\nRp3830\ng3762\nF461.0\ntp3831\na(I7670000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x9ew@'\np3832\ntp3833\nRp3834\ng3762\nF414.0\ntp3835\na(I7680000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x9dw@'\np3836\ntp3837\nRp3838\ng3762\nF373.0\ntp3839\na(I7690000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xbcw@'\np3840\ntp3841\nRp3842\ng3762\nF418.0\ntp3843\na(I7700000\ng1\n(g5\nS'33333\\x07x@'\np3844\ntp3845\nRp3846\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x19x@'\np3847\ntp3848\nRp3849\nF305.0\ntp3850\na(I7710000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xfew@'\np3851\ntp3852\nRp3853\ng3849\nF397.0\ntp3854\na(I7720000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xe3w@'\np3855\ntp3856\nRp3857\ng3849\nF409.0\ntp3858\na(I7730000\ng1\n(g5\nS'fffff\\xfew@'\np3859\ntp3860\nRp3861\ng3849\nF620.0\ntp3862\na(I7740000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x14x@'\np3863\ntp3864\nRp3865\ng3849\nF459.0\ntp3866\na(I7750000\ng1\n(g5\nS'\\n\\xd7\\xa3p=*x@'\np3867\ntp3868\nRp3869\ng1\n(g5\nS'\\n\\xd7\\xa3p=*x@'\np3870\ntp3871\nRp3872\nF404.0\ntp3873\na(I7760000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x06x@'\np3874\ntp3875\nRp3876\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc@x@'\np3877\ntp3878\nRp3879\nF409.0\ntp3880\na(I7770000\ng1\n(g5\nS'33333\\xefw@'\np3881\ntp3882\nRp3883\ng3879\nF413.0\ntp3884\na(I7780000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xd1w@'\np3885\ntp3886\nRp3887\ng3879\nF309.0\ntp3888\na(I7790000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5w@'\np3889\ntp3890\nRp3891\ng3879\nF388.0\ntp3892\na(I7800000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x0bx@'\np3893\ntp3894\nRp3895\ng3879\nF333.0\ntp3896\na(I7810000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc25x@'\np3897\ntp3898\nRp3899\ng3879\nF428.0\ntp3900\na(I7820000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f:x@'\np3901\ntp3902\nRp3903\ng3879\nF425.0\ntp3904\na(I7830000\ng1\n(g5\nS'{\\x14\\xaeG\\xe16x@'\np3905\ntp3906\nRp3907\ng3879\nF399.0\ntp3908\na(I7840000\ng1\n(g5\nS'33333/x@'\np3909\ntp3910\nRp3911\ng3879\nF384.0\ntp3912\na(I7850000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG-x@'\np3913\ntp3914\nRp3915\ng3879\nF392.0\ntp3916\na(I7860000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x004x@'\np3917\ntp3918\nRp3919\ng3879\nF408.0\ntp3920\na(I7870000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00Px@'\np3921\ntp3922\nRp3923\ng1\n(g5\nS'=\\n\\xd7\\xa3pQx@'\np3924\ntp3925\nRp3926\nF396.0\ntp3927\na(I7880000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8Bx@'\np3928\ntp3929\nRp3930\ng1\n(g5\nS'\\xd7\\xa3p=\\ngx@'\np3931\ntp3932\nRp3933\nF297.0\ntp3934\na(I7890000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\tx@'\np3935\ntp3936\nRp3937\ng3933\nF117.0\ntp3938\na(I7900000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x06x@'\np3939\ntp3940\nRp3941\ng3933\nF435.0\ntp3942\na(I7910000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x15x@'\np3943\ntp3944\nRp3945\ng3933\nF371.0\ntp3946\na(I7920000\ng1\n(g5\nS'\\n\\xd7\\xa3p=*x@'\np3947\ntp3948\nRp3949\ng3933\nF530.0\ntp3950\na(I7930000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8&x@'\np3951\ntp3952\nRp3953\ng3933\nF396.0\ntp3954\na(I7940000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc x@'\np3955\ntp3956\nRp3957\ng3933\nF381.0\ntp3958\na(I7950000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xefw@'\np3959\ntp3960\nRp3961\ng3933\nF94.0\ntp3962\na(I7960000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xf8w@'\np3963\ntp3964\nRp3965\ng3933\nF399.0\ntp3966\na(I7970000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xf3w@'\np3967\ntp3968\nRp3969\ng3933\nF387.0\ntp3970\na(I7980000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2!x@'\np3971\ntp3972\nRp3973\ng3933\nF444.0\ntp3974\na(I7990000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xc1w@'\np3975\ntp3976\nRp3977\ng3933\nF386.0\ntp3978\na(I8000000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xa8w@'\np3979\ntp3980\nRp3981\ng3933\nF166.0\ntp3982\na(I8010000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xb8w@'\np3983\ntp3984\nRp3985\ng3933\nF420.0\ntp3986\na(I8020000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8cw@'\np3987\ntp3988\nRp3989\ng3933\nF377.0\ntp3990\na(I8030000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\{w@'\np3991\ntp3992\nRp3993\ng3933\nF428.0\ntp3994\na(I8040000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebMw@'\np3995\ntp3996\nRp3997\ng3933\nF390.0\ntp3998\na(I8050000\ng1\n(g5\nS'\\xd7\\xa3p=\\now@'\np3999\ntp4000\nRp4001\ng3933\nF347.0\ntp4002\na(I8060000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x19w@'\np4003\ntp4004\nRp4005\ng3933\nF234.0\ntp4006\na(I8070000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14w@'\np4007\ntp4008\nRp4009\ng3933\nF403.0\ntp4010\na(I8080000\ng1\n(g5\nS'fffffVw@'\np4011\ntp4012\nRp4013\ng3933\nF416.0\ntp4014\na(I8090000\ng1\n(g5\nS'fffff>w@'\np4015\ntp4016\nRp4017\ng3933\nF416.0\ntp4018\na(I8100000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x98w@'\np4019\ntp4020\nRp4021\ng3933\nF830.0\ntp4022\na(I8110000\ng1\n(g5\nS'33333\\x8bw@'\np4023\ntp4024\nRp4025\ng3933\nF424.0\ntp4026\na(I8120000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x92w@'\np4027\ntp4028\nRp4029\ng3933\nF425.0\ntp4030\na(I8130000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x9aw@'\np4031\ntp4032\nRp4033\ng3933\nF411.0\ntp4034\na(I8140000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xa1w@'\np4035\ntp4036\nRp4037\ng3933\nF414.0\ntp4038\na(I8150000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xafw@'\np4039\ntp4040\nRp4041\ng3933\nF408.0\ntp4042\na(I8160000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xa5w@'\np4043\ntp4044\nRp4045\ng3933\nF413.0\ntp4046\na(I8170000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x91w@'\np4047\ntp4048\nRp4049\ng3933\nF428.0\ntp4050\na(I8180000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa9w@'\np4051\ntp4052\nRp4053\ng3933\nF435.0\ntp4054\na(I8190000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xb8w@'\np4055\ntp4056\nRp4057\ng3933\nF359.0\ntp4058\na(I8200000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xf7w@'\np4059\ntp4060\nRp4061\ng3933\nF424.0\ntp4062\na(I8210000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xeew@'\np4063\ntp4064\nRp4065\ng3933\nF310.0\ntp4066\na(I8220000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xc0w@'\np4067\ntp4068\nRp4069\ng3933\nF90.0\ntp4070\na(I8230000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeww@'\np4071\ntp4072\nRp4073\ng3933\nF124.0\ntp4074\na(I8240000\ng1\n(g5\nS'\\n\\xd7\\xa3p=^w@'\np4075\ntp4076\nRp4077\ng3933\nF275.0\ntp4078\na(I8250000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(hw@'\np4079\ntp4080\nRp4081\ng3933\nF428.0\ntp4082\na(I8260000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xa3w@'\np4083\ntp4084\nRp4085\ng3933\nF220.0\ntp4086\na(I8270000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x82w@'\np4087\ntp4088\nRp4089\ng3933\nF381.0\ntp4090\na(I8280000\ng1\n(g5\nS'\\n\\xd7\\xa3p=fw@'\np4091\ntp4092\nRp4093\ng3933\nF227.0\ntp4094\na(I8290000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x8cw@'\np4095\ntp4096\nRp4097\ng3933\nF435.0\ntp4098\na(I8300000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x91w@'\np4099\ntp4100\nRp4101\ng3933\nF332.0\ntp4102\na(I8310000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x98w@'\np4103\ntp4104\nRp4105\ng3933\nF334.0\ntp4106\na(I8320000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa7w@'\np4107\ntp4108\nRp4109\ng3933\nF426.0\ntp4110\na(I8330000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9cw@'\np4111\ntp4112\nRp4113\ng3933\nF382.0\ntp4114\na(I8340000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb8w@'\np4115\ntp4116\nRp4117\ng3933\nF388.0\ntp4118\na(I8350000\ng1\n(g5\nS'33333\\xa3w@'\np4119\ntp4120\nRp4121\ng3933\nF313.0\ntp4122\na(I8360000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xa8w@'\np4123\ntp4124\nRp4125\ng3933\nF437.0\ntp4126\na(I8370000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xcdw@'\np4127\ntp4128\nRp4129\ng3933\nF392.0\ntp4130\na(I8380000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x05x@'\np4131\ntp4132\nRp4133\ng3933\nF315.0\ntp4134\na(I8390000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x9fw@'\np4135\ntp4136\nRp4137\ng3933\nF216.0\ntp4138\na(I8400000\ng1\n(g5\nS'\\xa4p=\\n\\xd7?w@'\np4139\ntp4140\nRp4141\ng3933\nF360.0\ntp4142\na(I8410000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8:w@'\np4143\ntp4144\nRp4145\ng3933\nF321.0\ntp4146\na(I8420000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x9fv@'\np4147\ntp4148\nRp4149\ng3933\nF107.0\ntp4150\na(I8430000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xa5v@'\np4151\ntp4152\nRp4153\ng3933\nF422.0\ntp4154\na(I8440000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x87v@'\np4155\ntp4156\nRp4157\ng3933\nF425.0\ntp4158\na(I8450000\ng1\n(g5\nS'fffffzv@'\np4159\ntp4160\nRp4161\ng3933\nF409.0\ntp4162\na(I8460000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e}v@'\np4163\ntp4164\nRp4165\ng3933\nF418.0\ntp4166\na(I8470000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x85v@'\np4167\ntp4168\nRp4169\ng3933\nF425.0\ntp4170\na(I8480000\ng1\n(g5\nS'\\n\\xd7\\xa3p=~v@'\np4171\ntp4172\nRp4173\ng3933\nF391.0\ntp4174\na(I8490000\ng1\n(g5\nS'fffff\\xbev@'\np4175\ntp4176\nRp4177\ng3933\nF395.0\ntp4178\na(I8500000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xe6v@'\np4179\ntp4180\nRp4181\ng3933\nF156.0\ntp4182\na(I8510000\ng1\n(g5\nS'q=\\n\\xd7\\xa34w@'\np4183\ntp4184\nRp4185\ng3933\nF298.0\ntp4186\na(I8520000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eaw@'\np4187\ntp4188\nRp4189\ng3933\nF402.0\ntp4190\na(I8530000\ng1\n(g5\nS'q=\\n\\xd7\\xa3tw@'\np4191\ntp4192\nRp4193\ng3933\nF386.0\ntp4194\na(I8540000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG1w@'\np4195\ntp4196\nRp4197\ng3933\nF393.0\ntp4198\na(I8550000\ng1\n(g5\nS'fffffNw@'\np4199\ntp4200\nRp4201\ng3933\nF402.0\ntp4202\na(I8560000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14>w@'\np4203\ntp4204\nRp4205\ng3933\nF299.0\ntp4206\na(I8570000\ng1\n(g5\nS'33333Ow@'\np4207\ntp4208\nRp4209\ng3933\nF373.0\ntp4210\na(I8580000\ng1\n(g5\nS'\\n\\xd7\\xa3p=Zw@'\np4211\ntp4212\nRp4213\ng3933\nF422.0\ntp4214\na(I8590000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14jw@'\np4215\ntp4216\nRp4217\ng3933\nF411.0\ntp4218\na(I8600000\ng1\n(g5\nS'33333Sw@'\np4219\ntp4220\nRp4221\ng3933\nF347.0\ntp4222\na(I8610000\ng1\n(g5\nS'=\\n\\xd7\\xa3p]w@'\np4223\ntp4224\nRp4225\ng3933\nF327.0\ntp4226\na(I8620000\ng1\n(g5\nS'\\xa4p=\\n\\xd7[w@'\np4227\ntp4228\nRp4229\ng3933\nF363.0\ntp4230\na(I8630000\ng1\n(g5\nS'33333Kw@'\np4231\ntp4232\nRp4233\ng3933\nF324.0\ntp4234\na(I8640000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb]w@'\np4235\ntp4236\nRp4237\ng3933\nF398.0\ntp4238\na(I8650000\ng1\n(g5\nS'\\xa4p=\\n\\xd7/w@'\np4239\ntp4240\nRp4241\ng3933\nF347.0\ntp4242\na(I8660000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb1w@'\np4243\ntp4244\nRp4245\ng3933\nF427.0\ntp4246\na(I8670000\ng1\n(g5\nS\"H\\xe1z\\x14\\xae'w@\"\np4247\ntp4248\nRp4249\ng3933\nF436.0\ntp4250\na(I8680000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\Ww@'\np4251\ntp4252\nRp4253\ng3933\nF408.0\ntp4254\na(I8690000\ng1\n(g5\nS'\\xa4p=\\n\\xd7Sw@'\np4255\ntp4256\nRp4257\ng3933\nF377.0\ntp4258\na(I8700000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ|w@'\np4259\ntp4260\nRp4261\ng3933\nF348.0\ntp4262\na(I8710000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Uw@'\np4263\ntp4264\nRp4265\ng3933\nF193.0\ntp4266\na(I8720000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x84w@'\np4267\ntp4268\nRp4269\ng3933\nF419.0\ntp4270\na(I8730000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x89w@'\np4271\ntp4272\nRp4273\ng3933\nF258.0\ntp4274\na(I8740000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x9cw@'\np4275\ntp4276\nRp4277\ng3933\nF344.0\ntp4278\na(I8750000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x99w@'\np4279\ntp4280\nRp4281\ng3933\nF379.0\ntp4282\na(I8760000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8frw@'\np4283\ntp4284\nRp4285\ng3933\nF434.0\ntp4286\na(I8770000\ng1\n(g5\nS'33333sw@'\np4287\ntp4288\nRp4289\ng3933\nF342.0\ntp4290\na(I8780000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQXw@'\np4291\ntp4292\nRp4293\ng3933\nF427.0\ntp4294\na(I8790000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc0w@'\np4295\ntp4296\nRp4297\ng3933\nF104.0\ntp4298\na(I8800000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xf8v@'\np4299\ntp4300\nRp4301\ng3933\nF380.0\ntp4302\na(I8810000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x15w@'\np4303\ntp4304\nRp4305\ng3933\nF428.0\ntp4306\na(I8820000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xfdv@'\np4307\ntp4308\nRp4309\ng3933\nF410.0\ntp4310\na(I8830000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x06w@'\np4311\ntp4312\nRp4313\ng3933\nF422.0\ntp4314\na(I8840000\ng1\n(g5\nS'fffff*w@'\np4315\ntp4316\nRp4317\ng3933\nF395.0\ntp4318\na(I8850000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x0fw@'\np4319\ntp4320\nRp4321\ng3933\nF372.0\ntp4322\na(I8860000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x17w@'\np4323\ntp4324\nRp4325\ng3933\nF338.0\ntp4326\na(I8870000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x11w@'\np4327\ntp4328\nRp4329\ng3933\nF390.0\ntp4330\na(I8880000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xf6v@'\np4331\ntp4332\nRp4333\ng3933\nF268.0\ntp4334\na(I8890000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x14w@'\np4335\ntp4336\nRp4337\ng3933\nF416.0\ntp4338\na(I8900000\ng1\n(g5\nS'=\\n\\xd7\\xa3p!w@'\np4339\ntp4340\nRp4341\ng3933\nF441.0\ntp4342\na(I8910000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x0fw@'\np4343\ntp4344\nRp4345\ng3933\nF423.0\ntp4346\na(I8920000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xcav@'\np4347\ntp4348\nRp4349\ng3933\nF405.0\ntp4350\na(I8930000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\tw@'\np4351\ntp4352\nRp4353\ng3933\nF406.0\ntp4354\na(I8940000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x1cw@'\np4355\ntp4356\nRp4357\ng3933\nF417.0\ntp4358\na(I8950000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xf5v@'\np4359\ntp4360\nRp4361\ng3933\nF415.0\ntp4362\na(I8960000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5( w@'\np4363\ntp4364\nRp4365\ng3933\nF418.0\ntp4366\na(I8970000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x10w@'\np4367\ntp4368\nRp4369\ng3933\nF200.0\ntp4370\na(I8980000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x04w@'\np4371\ntp4372\nRp4373\ng3933\nF428.0\ntp4374\na(I8990000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\#w@'\np4375\ntp4376\nRp4377\ng3933\nF431.0\ntp4378\na(I9000000\ng1\n(g5\nS'\\xa4p=\\n\\xd7_w@'\np4379\ntp4380\nRp4381\ng3933\nF416.0\ntp4382\na(I9010000\ng1\n(g5\nS'\\n\\xd7\\xa3p=fw@'\np4383\ntp4384\nRp4385\ng3933\nF417.0\ntp4386\na(I9020000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99}w@'\np4387\ntp4388\nRp4389\ng3933\nF393.0\ntp4390\na(I9030000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x83w@'\np4391\ntp4392\nRp4393\ng3933\nF428.0\ntp4394\na(I9040000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00xw@'\np4395\ntp4396\nRp4397\ng3933\nF399.0\ntp4398\na(I9050000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x9aw@'\np4399\ntp4400\nRp4401\ng3933\nF344.0\ntp4402\na(I9060000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x9aw@'\np4403\ntp4404\nRp4405\ng3933\nF422.0\ntp4406\na(I9070000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xa5w@'\np4407\ntp4408\nRp4409\ng3933\nF424.0\ntp4410\na(I9080000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xacw@'\np4411\ntp4412\nRp4413\ng3933\nF398.0\ntp4414\na(I9090000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x97w@'\np4415\ntp4416\nRp4417\ng3933\nF306.0\ntp4418\na(I9100000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xc1w@'\np4419\ntp4420\nRp4421\ng3933\nF791.0\ntp4422\na(I9110000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x9bw@'\np4423\ntp4424\nRp4425\ng3933\nF424.0\ntp4426\na(I9120000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x8ew@'\np4427\ntp4428\nRp4429\ng3933\nF459.0\ntp4430\na(I9130000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb0w@'\np4431\ntp4432\nRp4433\ng3933\nF412.0\ntp4434\na(I9140000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb4w@'\np4435\ntp4436\nRp4437\ng3933\nF401.0\ntp4438\na(I9150000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xbew@'\np4439\ntp4440\nRp4441\ng3933\nF420.0\ntp4442\na(I9160000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xe8w@'\np4443\ntp4444\nRp4445\ng3933\nF423.0\ntp4446\na(I9170000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xdcw@'\np4447\ntp4448\nRp4449\ng3933\nF357.0\ntp4450\na(I9180000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x11x@'\np4451\ntp4452\nRp4453\ng3933\nF412.0\ntp4454\na(I9190000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@x@'\np4455\ntp4456\nRp4457\ng3933\nF667.0\ntp4458\na(I9200000\ng1\n(g5\nS'fffff\\xeaw@'\np4459\ntp4460\nRp4461\ng3933\nF92.0\ntp4462\na(I9210000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xf8w@'\np4463\ntp4464\nRp4465\ng3933\nF419.0\ntp4466\na(I9220000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z@x@'\np4467\ntp4468\nRp4469\ng3933\nF342.0\ntp4470\na(I9230000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(`x@'\np4471\ntp4472\nRp4473\ng3933\nF379.0\ntp4474\na(I9240000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8frx@'\np4475\ntp4476\nRp4477\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8frx@'\np4478\ntp4479\nRp4480\nF434.0\ntp4481\na(I9250000\ng1\n(g5\nS'33333wx@'\np4482\ntp4483\nRp4484\ng1\n(g5\nS'\\xd7\\xa3p=\\n{x@'\np4485\ntp4486\nRp4487\nF387.0\ntp4488\na(I9260000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xacx@'\np4489\ntp4490\nRp4491\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xacx@'\np4492\ntp4493\nRp4494\nF328.0\ntp4495\na(I9270000\ng1\n(g5\nS'33333\\xa7x@'\np4496\ntp4497\nRp4498\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xafx@'\np4499\ntp4500\nRp4501\nF393.0\ntp4502\na(I9280000\ng1\n(g5\nS'33333\\xcbx@'\np4503\ntp4504\nRp4505\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xd8x@'\np4506\ntp4507\nRp4508\nF402.0\ntp4509\na(I9290000\ng1\n(g5\nS'fffff\\xcax@'\np4510\ntp4511\nRp4512\ng4508\nF418.0\ntp4513\na(I9300000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xbcx@'\np4514\ntp4515\nRp4516\ng4508\nF380.0\ntp4517\na(I9310000\ng1\n(g5\nS'\\n\\xd7\\xa3p=nx@'\np4518\ntp4519\nRp4520\ng4508\nF381.0\ntp4521\na(I9320000\ng1\n(g5\nS'33333\\x93x@'\np4522\ntp4523\nRp4524\ng4508\nF411.0\ntp4525\na(I9330000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x92x@'\np4526\ntp4527\nRp4528\ng4508\nF369.0\ntp4529\na(I9340000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x94x@'\np4530\ntp4531\nRp4532\ng4508\nF425.0\ntp4533\na(I9350000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x8bx@'\np4534\ntp4535\nRp4536\ng4508\nF398.0\ntp4537\na(I9360000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x8dx@'\np4538\ntp4539\nRp4540\ng4508\nF125.0\ntp4541\na(I9370000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1~x@'\np4542\ntp4543\nRp4544\ng4508\nF405.0\ntp4545\na(I9380000\ng1\n(g5\nS'fffff\\x8ax@'\np4546\ntp4547\nRp4548\ng4508\nF410.0\ntp4549\na(I9390000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGax@'\np4550\ntp4551\nRp4552\ng4508\nF421.0\ntp4553\na(I9400000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGex@'\np4554\ntp4555\nRp4556\ng4508\nF428.0\ntp4557\na(I9410000\ng1\n(g5\nS'\\n\\xd7\\xa3p=~x@'\np4558\ntp4559\nRp4560\ng4508\nF300.0\ntp4561\na(I9420000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x81x@'\np4562\ntp4563\nRp4564\ng4508\nF420.0\ntp4565\na(I9430000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eIx@'\np4566\ntp4567\nRp4568\ng4508\nF390.0\ntp4569\na(I9440000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f:x@'\np4570\ntp4571\nRp4572\ng4508\nF369.0\ntp4573\na(I9450000\ng1\n(g5\nS'\\xd7\\xa3p=\\n3x@'\np4574\ntp4575\nRp4576\ng4508\nF428.0\ntp4577\na(I9460000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\rx@'\np4578\ntp4579\nRp4580\ng4508\nF417.0\ntp4581\na(I9470000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8*x@'\np4582\ntp4583\nRp4584\ng4508\nF424.0\ntp4585\na(I9480000\ng1\n(g5\nS'\\n\\xd7\\xa3p=.x@'\np4586\ntp4587\nRp4588\ng4508\nF437.0\ntp4589\na(I9490000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3x@'\np4590\ntp4591\nRp4592\ng4508\nF420.0\ntp4593\na(I9500000\ng1\n(g5\nS'33333\\xb3x@'\np4594\ntp4595\nRp4596\ng4508\nF366.0\ntp4597\na(I9510000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zTx@'\np4598\ntp4599\nRp4600\ng4508\nF131.0\ntp4601\na(I9520000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14^x@'\np4602\ntp4603\nRp4604\ng4508\nF421.0\ntp4605\na(I9530000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(,x@'\np4606\ntp4607\nRp4608\ng4508\nF415.0\ntp4609\na(I9540000\ng1\n(g5\nS'\\xa4p=\\n\\xd7;x@'\np4610\ntp4611\nRp4612\ng4508\nF412.0\ntp4613\na(I9550000\ng1\n(g5\nS'\\xd7\\xa3p=\\n7x@'\np4614\ntp4615\nRp4616\ng4508\nF412.0\ntp4617\na(I9560000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x1ex@'\np4618\ntp4619\nRp4620\ng4508\nF428.0\ntp4621\na(I9570000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb)x@'\np4622\ntp4623\nRp4624\ng4508\nF297.0\ntp4625\na(I9580000\ng1\n(g5\nS'33333gx@'\np4626\ntp4627\nRp4628\ng4508\nF810.0\ntp4629\na(I9590000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xc4x@'\np4630\ntp4631\nRp4632\ng4508\nF427.0\ntp4633\na(I9600000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xc8x@'\np4634\ntp4635\nRp4636\ng4508\nF421.0\ntp4637\na(I9610000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xa3x@'\np4638\ntp4639\nRp4640\ng4508\nF194.0\ntp4641\na(I9620000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xa4x@'\np4642\ntp4643\nRp4644\ng4508\nF283.0\ntp4645\na(I9630000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xa4x@'\np4646\ntp4647\nRp4648\ng4508\nF406.0\ntp4649\na(I9640000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xb8x@'\np4650\ntp4651\nRp4652\ng4508\nF424.0\ntp4653\na(I9650000\ng1\n(g5\nS'33333\\xbbx@'\np4654\ntp4655\nRp4656\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xe1x@'\np4657\ntp4658\nRp4659\nF375.0\ntp4660\na(I9660000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xb4x@'\np4661\ntp4662\nRp4663\ng4659\nF331.0\ntp4664\na(I9670000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xcax@'\np4665\ntp4666\nRp4667\ng4659\nF412.0\ntp4668\na(I9680000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xd7x@'\np4669\ntp4670\nRp4671\ng4659\nF416.0\ntp4672\na(I9690000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xcdx@'\np4673\ntp4674\nRp4675\ng4659\nF334.0\ntp4676\na(I9700000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xafx@'\np4677\ntp4678\nRp4679\ng4659\nF401.0\ntp4680\na(I9710000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xcfx@'\np4681\ntp4682\nRp4683\ng4659\nF626.0\ntp4684\na(I9713708\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xb8x@'\np4685\ntp4686\nRp4687\ng4659\nF253.0\ntp4688\na.(lp0\nF4.0\naF3.0\naF0.0\naF3.0\naF1.0\naF1.0\naF0.0\naF0.0\naF3.0\naF1.0\naF0.0\naF4.0\naF2.0\naF3.0\naF1.0\naF1.0\naF3.0\naF2.0\naF2.0\naF1.0\naF7.0\naF2.0\naF4.0\naF2.0\naF0.0\naF4.0\naF1.0\naF1.0\naF2.0\naF1.0\naF1.0\naF1.0\naF2.0\naF5.0\naF1.0\naF2.0\naF1.0\naF2.0\naF1.0\naF1.0\naF0.0\naF1.0\naF2.0\naF2.0\naF0.0\naF0.0\naF0.0\naF1.0\naF1.0\naF2.0\naF7.0\naF1.0\naF3.0\naF1.0\naF2.0\naF0.0\naF1.0\naF0.0\naF0.0\naF2.0\naF0.0\naF3.0\naF4.0\naF2.0\naF1.0\naF0.0\naF1.0\naF0.0\naF4.0\naF3.0\naF3.0\naF3.0\naF0.0\naF2.0\naF0.0\naF0.0\naF2.0\naF2.0\naF0.0\naF1.0\naF0.0\naF5.0\naF0.0\naF3.0\naF1.0\naF3.0\naF1.0\naF2.0\naF1.0\naF3.0\naF1.0\naF2.0\naF1.0\naF3.0\naF1.0\naF0.0\naF0.0\naF3.0\naF3.0\naF1.0\naF1.0\naF0.0\naF3.0\naF1.0\naF1.0\naF1.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF3.0\naF0.0\naF0.0\naF1.0\naF2.0\naF1.0\naF1.0\naF2.0\naF2.0\naF2.0\naF3.0\naF0.0\naF4.0\naF2.0\naF1.0\naF3.0\naF0.0\naF1.0\naF3.0\naF0.0\naF2.0\naF2.0\naF1.0\naF2.0\naF0.0\naF3.0\naF0.0\naF1.0\naF1.0\naF5.0\naF2.0\naF1.0\naF3.0\naF5.0\naF4.0\naF0.0\naF0.0\naF4.0\naF1.0\naF0.0\naF4.0\naF4.0\naF2.0\naF1.0\naF4.0\naF0.0\naF2.0\naF3.0\naF2.0\naF1.0\naF2.0\naF2.0\naF1.0\naF2.0\naF1.0\naF2.0\naF2.0\naF1.0\naF0.0\naF3.0\naF1.0\naF0.0\naF0.0\naF0.0\naF3.0\naF3.0\naF3.0\naF0.0\naF1.0\naF3.0\naF2.0\naF1.0\naF2.0\naF0.0\naF0.0\naF0.0\naF3.0\naF4.0\naF2.0\naF0.0\naF1.0\naF3.0\naF4.0\naF3.0\naF3.0\naF2.0\naF0.0\naF0.0\naF4.0\naF0.0\naF2.0\naF1.0\naF3.0\naF1.0\naF2.0\naF2.0\naF3.0\naF1.0\naF1.0\naF1.0\naF0.0\naF1.0\naF1.0\naF0.0\naF0.0\naF1.0\naF0.0\naF3.0\naF5.0\naF2.0\naF2.0\naF1.0\naF1.0\naF2.0\naF3.0\naF2.0\naF5.0\naF1.0\naF0.0\naF3.0\naF1.0\naF1.0\naF9.0\naF1.0\naF0.0\naF1.0\naF1.0\naF2.0\naF0.0\naF4.0\naF1.0\naF0.0\naF1.0\naF4.0\naF4.0\naF0.0\naF1.0\naF4.0\naF1.0\naF3.0\naF0.0\naF5.0\naF1.0\naF0.0\naF1.0\naF2.0\naF3.0\naF3.0\naF3.0\naF2.0\naF3.0\naF2.0\naF0.0\naF0.0\naF1.0\naF1.0\naF1.0\naF1.0\naF0.0\naF3.0\naF0.0\naF2.0\naF5.0\naF1.0\naF4.0\naF0.0\naF2.0\naF2.0\naF3.0\naF1.0\naF1.0\naF4.0\naF2.0\naF1.0\naF1.0\naF1.0\naF5.0\naF0.0\naF0.0\naF1.0\naF2.0\naF2.0\naF1.0\naF3.0\naF0.0\naF3.0\naF1.0\naF0.0\naF2.0\naF0.0\naF2.0\naF2.0\naF0.0\naF2.0\naF1.0\naF0.0\naF0.0\naF0.0\naF1.0\naF1.0\naF3.0\naF1.0\naF2.0\naF3.0\naF0.0\naF1.0\naF0.0\naF0.0\naF1.0\naF1.0\naF1.0\naF5.0\naF1.0\naF1.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF1.0\naF2.0\naF2.0\naF0.0\naF0.0\naF0.0\naF1.0\naF1.0\naF2.0\naF0.0\naF2.0\naF3.0\naF0.0\naF3.0\naF1.0\naF2.0\naF1.0\naF3.0\naF2.0\naF2.0\naF0.0\naF0.0\naF4.0\naF1.0\naF4.0\naF3.0\naF1.0\naF2.0\naF1.0\naF3.0\naF2.0\naF5.0\naF2.0\naF0.0\naF2.0\naF1.0\naF0.0\naF4.0\naF3.0\naF2.0\naF2.0\naF2.0\naF2.0\naF3.0\naF0.0\naF0.0\naF0.0\naF1.0\naF1.0\naF4.0\naF4.0\naF7.0\naF3.0\naF0.0\naF1.0\naF1.0\naF4.0\naF0.0\naF2.0\naF0.0\naF2.0\naF1.0\naF3.0\naF1.0\naF0.0\naF2.0\naF2.0\naF1.0\naF1.0\naF3.0\naF3.0\naF0.0\naF1.0\naF1.0\naF1.0\naF3.0\naF1.0\naF2.0\naF1.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF3.0\naF0.0\naF3.0\naF2.0\naF1.0\naF2.0\naF4.0\naF6.0\naF1.0\naF3.0\naF2.0\naF2.0\naF1.0\naF0.0\naF2.0\naF2.0\naF3.0\naF0.0\naF1.0\naF0.0\naF2.0\naF1.0\naF1.0\naF1.0\naF3.0\naF1.0\naF1.0\naF1.0\naF2.0\naF1.0\naF1.0\naF1.0\naF0.0\naF0.0\naF1.0\naF0.0\naF1.0\naF1.0\naF0.0\naF0.0\naF0.0\naF1.0\naF2.0\naF2.0\naF2.0\naF1.0\naF1.0\naF1.0\naF2.0\naF0.0\naF7.0\naF0.0\naF1.0\naF3.0\naF1.0\naF3.0\naF1.0\naF0.0\naF2.0\naF0.0\naF0.0\naF2.0\naF3.0\naF1.0\naF3.0\naF4.0\naF1.0\naF2.0\naF1.0\naF0.0\naF3.0\naF3.0\naF0.0\naF1.0\naF3.0\naF2.0\naF0.0\naF0.0\naF3.0\naF4.0\naF1.0\naF0.0\naF0.0\naF5.0\naF2.0\naF2.0\naF0.0\naF0.0\naF2.0\naF2.0\naF2.0\naF2.0\naF1.0\naF1.0\naF2.0\naF1.0\naF0.0\naF1.0\naF3.0\naF2.0\naF0.0\naF0.0\naF4.0\naF0.0\naF2.0\naF0.0\naF1.0\naF0.0\naF5.0\naF1.0\naF3.0\naF3.0\naF1.0\naF2.0\naF3.0\naF1.0\naF1.0\naF9.0\naF1.0\naF0.0\naF1.0\naF3.0\naF0.0\naF2.0\naF3.0\naF2.0\naF1.0\naF7.0\naF0.0\naF0.0\naF5.0\naF0.0\naF3.0\naF0.0\naF4.0\naF2.0\naF1.0\naF0.0\naF3.0\naF0.0\naF0.0\naF2.0\naF3.0\naF0.0\naF0.0\naF1.0\naF1.0\naF0.0\naF0.0\naF4.0\naF0.0\naF0.0\naF1.0\naF0.0\naF1.0\naF0.0\naF2.0\naF0.0\naF1.0\naF3.0\naF1.0\naF0.0\naF1.0\naF3.0\naF2.0\naF3.0\naF2.0\naF1.0\naF0.0\naF1.0\naF0.0\naF0.0\naF1.0\naF0.0\naF3.0\naF3.0\naF0.0\naF1.0\naF0.0\naF1.0\naF0.0\naF0.0\naF4.0\naF2.0\naF4.0\naF2.0\naF0.0\naF3.0\naF2.0\naF3.0\naF2.0\naF3.0\naF2.0\naF1.0\naF3.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF3.0\naF3.0\naF2.0\naF2.0\naF1.0\naF1.0\naF1.0\naF0.0\naF1.0\naF6.0\naF3.0\naF0.0\naF2.0\naF9.0\naF0.0\naF2.0\naF1.0\naF0.0\naF1.0\naF0.0\naF0.0\naF1.0\naF1.0\naF1.0\naF1.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF3.0\naF1.0\naF1.0\naF1.0\naF2.0\naF4.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF2.0\naF0.0\naF1.0\naF3.0\naF1.0\naF3.0\naF2.0\naF2.0\naF3.0\naF3.0\naF2.0\naF6.0\naF3.0\naF3.0\naF0.0\naF1.0\naF3.0\naF2.0\naF4.0\naF0.0\naF3.0\naF4.0\naF1.0\naF0.0\naF0.0\naF3.0\naF1.0\naF0.0\naF4.0\naF3.0\naF0.0\naF4.0\naF0.0\naF3.0\naF2.0\naF4.0\naF4.0\naF0.0\naF0.0\naF2.0\naF2.0\naF1.0\naF3.0\naF1.0\naF0.0\naF3.0\naF3.0\naF1.0\naF2.0\naF2.0\naF0.0\naF4.0\naF3.0\naF2.0\naF0.0\naF3.0\naF3.0\naF0.0\naF2.0\naF2.0\naF7.0\naF3.0\naF2.0\naF0.0\naF1.0\naF0.0\naF1.0\naF0.0\naF2.0\naF3.0\naF2.0\naF1.0\naF5.0\naF0.0\naF3.0\naF3.0\naF1.0\naF0.0\naF1.0\naF1.0\naF0.0\naF1.0\naF1.0\naF0.0\naF1.0\naF2.0\naF2.0\naF0.0\naF1.0\naF0.0\naF2.0\naF0.0\naF1.0\naF3.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF2.0\naF3.0\naF1.0\naF1.0\naF0.0\naF8.0\naF2.0\naF4.0\naF1.0\naF7.0\naF2.0\naF2.0\naF1.0\naF2.0\naF4.0\naF2.0\naF4.0\naF1.0\naF2.0\naF1.0\naF2.0\naF1.0\naF1.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF1.0\naF1.0\naF0.0\naF3.0\naF1.0\naF0.0\naF2.0\naF3.0\naF0.0\naF0.0\naF0.0\naF1.0\naF3.0\naF2.0\naF3.0\naF0.0\naF1.0\naF3.0\naF1.0\naF1.0\naF2.0\naF5.0\naF2.0\naF2.0\naF0.0\naF1.0\naF2.0\naF3.0\naF4.0\naF0.0\naF3.0\naF2.0\naF4.0\naF2.0\naF0.0\naF5.0\naF2.0\naF0.0\naF3.0\naF2.0\naF1.0\naF0.0\naF0.0\naF5.0\naF1.0\naF2.0\naF2.0\naF2.0\naF0.0\naF1.0\naF0.0\naF3.0\naF2.0\naF0.0\naF3.0\naF1.0\naF1.0\naF4.0\naF1.0\naF2.0\naF1.0\naF0.0\naF2.0\naF2.0\naF2.0\naF4.0\naF0.0\naF0.0\naF2.0\naF0.0\naF1.0\naF0.0\naF1.0\naF4.0\naF0.0\naF0.0\naF4.0\naF1.0\naF0.0\naF3.0\naF0.0\naF0.0\naF1.0\naF3.0\naF3.0\naF0.0\naF2.0\naF0.0\naF0.0\naF2.0\naF2.0\naF1.0\naF0.0\naF1.0\naF2.0\naF1.0\naF0.0\naF0.0\naF0.0\naF4.0\naF2.0\naF3.0\naF2.0\naF1.0\naF3.0\naF3.0\naF3.0\naF3.0\naF3.0\naF1.0\naF1.0\naF0.0\naF1.0\naF0.0\naF6.0\naF1.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF1.0\naF1.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF3.0\naF5.0\naF3.0\naF0.0\naF3.0\naF1.0\naF1.0\naF2.0\naF0.0\naF0.0\naF2.0\naF1.0\naF2.0\naF3.0\naF2.0\naF1.0\naF0.0\naF0.0\naF0.0\naF3.0\naF2.0\naF2.0\naF1.0\naF2.0\naF9.0\naF1.0\naF2.0\naF0.0\naF0.0\naF3.0\naF0.0\naF3.0\naF1.0\naF3.0\naF1.0\naF2.0\naF0.0\naF0.0\naF1.0\naF2.0\naF0.0\naF4.0\naF3.0\naF2.0\naF1.0\naF2.0\naF1.0\naF3.0\naF1.0\naF4.0\naF2.0\naF2.0\naF1.0\naF2.0\naF3.0\naF1.0\naF1.0\naF1.0\naF1.0\naF1.0\naF1.0\naF0.0\naF1.0\naF1.0\naF0.0\naF2.0\naF3.0\naF2.0\naF1.0\naF0.0\naF4.0\naF0.0\naF2.0\naF3.0\naF1.0\naF2.0\naF2.0\naF2.0\naF3.0\naF4.0\naF2.0\naF0.0\naF3.0\naF0.0\naF2.0\naF2.0\naF5.0\naF1.0\naF4.0\naF2.0\naF0.0\naF0.0\naF0.0\naF3.0\naF4.0\naF3.0\naF0.0\naF0.0\naF3.0\naF2.0\naF3.0\naF2.0\naF2.0\naF1.0\naF2.0\naF0.0\naF2.0\naF2.0\naF1.0\naF0.0\naF0.0\naF1.0\naF1.0\naF1.0\naF1.0\naF4.0\naF0.0\naF1.0\naF1.0\naF2.0\naF0.0\naF9.0\naF1.0\naF1.0\naF0.0\naF2.0\naF1.0\naF2.0\naF0.0\naF1.0\naF0.0\naF4.0\naF0.0\naF1.0\naF4.0\naF0.0\naF2.0\naF1.0\naF0.0\naF1.0\naF0.0\naF0.0\naF3.0\naF2.0\naF3.0\naF2.0\naF0.0\naF1.0\naF2.0\naF0.0\naF4.0\naF0.0\naF2.0\naF0.0\naF1.0\naF0.0\naF5.0\naF0.0\naF1.0\naF2.0\naF3.0\naF2.0\naF4.0\naF2.0\naF1.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF3.0\naF3.0\naF1.0\naF1.0\naF2.0\naF4.0\naF0.0\naF2.0\naF1.0\naF1.0\naF3.0\naF0.0\naF2.0\naF0.0\naF2.0\naF4.0\naF1.0\naF0.0\naF2.0\naF2.0\naF0.0\naF0.0\naF3.0\naF2.0\naF0.0\naF1.0\naF5.0\naF2.0\naF2.0\naF0.0\naF3.0\naF0.0\naF3.0\naF1.0\naF2.0\naF2.0\naF2.0\naF2.0\naF1.0\naF4.0\naF0.0\naF1.0\naF0.0\naF0.0\naF1.0\naF3.0\naF1.0\naF2.0\naF0.0\naF0.0\naF5.0\naF3.0\naF0.0\naF2.0\naF1.0\naF1.0\naF1.0\naF2.0\naF0.0\naF2.0\naF0.0\naF3.0\naF0.0\naF2.0\naF2.0\naF1.0\naF0.0\naF1.0\naF3.0\naF1.0\naF1.0\naF0.0\naF4.0\naF4.0\naF2.0\naF3.0\naF1.0\naF3.0\naF0.0\naF3.0\naF1.0\naF5.0\naF1.0\naF1.0\naF3.0\naF3.0\naF0.0\naF1.0\naF2.0\naF4.0\naF1.0\naF0.0\naF4.0\naF0.0\naF0.0\naF5.0\naF0.0\naF3.0\naF0.0\naF2.0\naF0.0\naF3.0\naF3.0\naF2.0\naF0.0\naF1.0\naF4.0\naF2.0\naF1.0\naF3.0\naF0.0\naF0.0\naF1.0\naF3.0\naF2.0\naF0.0\naF2.0\naF2.0\naF3.0\naF5.0\naF1.0\naF3.0\naF1.0\naF0.0\naF2.0\naF0.0\naF0.0\naF2.0\naF2.0\naF1.0\naF4.0\naF2.0\naF0.0\naF4.0\naF4.0\naF2.0\naF5.0\naF0.0\naF2.0\naF3.0\naF1.0\naF1.0\naF1.0\naF3.0\naF1.0\naF2.0\naF2.0\naF0.0\naF1.0\naF0.0\naF3.0\naF1.0\naF2.0\naF4.0\naF2.0\naF2.0\naF1.0\naF1.0\naF4.0\naF0.0\naF2.0\naF2.0\naF4.0\naF2.0\naF0.0\naF2.0\naF3.0\naF6.0\naF0.0\naF1.0\naF1.0\naF0.0\naF0.0\naF2.0\naF3.0\naF2.0\naF0.0\naF2.0\naF0.0\naF5.0\naF9.0\naF3.0\naF3.0\naF3.0\naF4.0\naF4.0\naF3.0\naF1.0\naF2.0\naF2.0\naF2.0\naF3.0\naF4.0\naF2.0\naF3.0\naF3.0\naF3.0\naF5.0\naF4.0\naF2.0\naF2.0\naF3.0\naF0.0\naF1.0\naF0.0\naF2.0\naF3.0\naF2.0\naF2.0\naF0.0\naF1.0\naF1.0\naF3.0\naF1.0\naF3.0\naF1.0\naF1.0\naF3.0\naF0.0\naF4.0\naF1.0\naF1.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF2.0\naF1.0\naF2.0\naF3.0\naF0.0\naF4.0\naF4.0\naF4.0\naF2.0\naF0.0\naF3.0\naF1.0\naF2.0\naF3.0\naF3.0\naF0.0\naF2.0\naF1.0\naF2.0\naF4.0\naF0.0\naF1.0\naF0.0\naF4.0\naF0.0\naF3.0\naF0.0\naF4.0\naF3.0\naF2.0\naF2.0\naF3.0\naF1.0\naF0.0\naF0.0\naF2.0\naF4.0\naF3.0\naF6.0\naF3.0\naF1.0\naF3.0\naF4.0\naF3.0\naF0.0\naF2.0\naF2.0\naF2.0\naF2.0\naF1.0\naF1.0\naF1.0\naF2.0\naF0.0\naF0.0\naF3.0\naF2.0\naF3.0\naF1.0\naF0.0\naF2.0\naF3.0\naF2.0\naF1.0\naF3.0\naF2.0\naF2.0\naF2.0\naF0.0\naF0.0\naF1.0\naF1.0\naF3.0\naF0.0\naF7.0\naF2.0\naF3.0\naF0.0\naF2.0\naF6.0\naF2.0\naF0.0\naF0.0\naF2.0\naF5.0\naF1.0\naF0.0\naF0.0\naF0.0\naF2.0\naF2.0\naF3.0\naF8.0\naF4.0\naF0.0\naF3.0\naF1.0\naF1.0\naF3.0\naF3.0\naF0.0\naF1.0\naF2.0\naF0.0\naF1.0\naF1.0\naF2.0\naF2.0\naF2.0\naF3.0\naF4.0\naF1.0\naF3.0\naF0.0\naF2.0\naF4.0\naF1.0\naF4.0\naF2.0\naF3.0\naF2.0\naF1.0\naF5.0\naF2.0\naF4.0\naF0.0\naF4.0\naF2.0\naF2.0\naF3.0\naF3.0\naF2.0\naF2.0\naF3.0\naF2.0\naF2.0\naF2.0\naF2.0\naF4.0\naF1.0\naF2.0\naF2.0\naF6.0\naF0.0\naF3.0\naF3.0\naF4.0\naF2.0\naF1.0\naF0.0\naF5.0\naF3.0\naF3.0\naF2.0\naF1.0\naF1.0\naF1.0\naF3.0\naF1.0\naF1.0\naF4.0\naF2.0\naF4.0\naF0.0\naF3.0\naF3.0\naF2.0\naF0.0\naF2.0\naF2.0\naF2.0\naF2.0\naF3.0\naF4.0\naF2.0\naF1.0\naF3.0\naF6.0\naF1.0\naF1.0\naF0.0\naF3.0\naF2.0\naF1.0\naF3.0\naF8.0\naF5.0\naF1.0\naF2.0\naF4.0\naF2.0\naF3.0\naF0.0\naF3.0\naF3.0\naF0.0\naF3.0\naF3.0\naF1.0\naF3.0\naF3.0\naF6.0\naF0.0\naF2.0\naF3.0\naF5.0\naF1.0\naF2.0\naF5.0\naF4.0\naF5.0\naF1.0\naF1.0\naF1.0\naF4.0\naF5.0\naF7.0\naF1.0\naF1.0\naF2.0\naF1.0\naF3.0\naF0.0\naF0.0\naF2.0\naF3.0\naF2.0\naF2.0\naF3.0\naF4.0\naF5.0\naF2.0\naF8.0\naF2.0\naF5.0\naF3.0\naF2.0\naF1.0\naF4.0\naF6.0\naF3.0\naF0.0\naF1.0\naF3.0\naF2.0\naF0.0\naF3.0\naF3.0\naF0.0\naF3.0\naF3.0\naF5.0\naF0.0\naF2.0\naF2.0\naF5.0\naF4.0\naF2.0\naF2.0\naF4.0\naF1.0\naF2.0\naF4.0\naF3.0\naF4.0\naF4.0\naF1.0\naF3.0\naF3.0\naF1.0\naF6.0\naF7.0\naF1.0\naF2.0\naF1.0\naF4.0\naF4.0\naF0.0\naF5.0\naF6.0\naF0.0\naF1.0\naF1.0\naF1.0\naF12.0\naF6.0\naF3.0\naF1.0\naF3.0\naF1.0\naF4.0\naF3.0\naF3.0\naF3.0\naF0.0\naF4.0\naF5.0\naF4.0\naF1.0\naF1.0\naF3.0\naF4.0\naF3.0\naF5.0\naF2.0\naF3.0\naF1.0\naF3.0\naF5.0\naF3.0\naF5.0\naF1.0\naF11.0\naF3.0\naF4.0\naF3.0\naF5.0\naF9.0\naF5.0\naF4.0\naF6.0\naF3.0\naF3.0\naF6.0\naF2.0\naF1.0\naF4.0\naF4.0\naF5.0\naF2.0\naF5.0\naF3.0\naF2.0\naF1.0\naF4.0\naF4.0\naF1.0\naF5.0\naF3.0\naF4.0\naF1.0\naF2.0\naF3.0\naF5.0\naF2.0\naF3.0\naF3.0\naF7.0\naF3.0\naF2.0\naF4.0\naF10.0\naF1.0\naF8.0\naF5.0\naF2.0\naF4.0\naF7.0\naF4.0\naF7.0\naF5.0\naF3.0\naF2.0\naF1.0\naF3.0\naF3.0\naF1.0\naF2.0\naF6.0\naF1.0\naF2.0\naF7.0\naF2.0\naF3.0\naF7.0\naF7.0\naF7.0\naF5.0\naF10.0\naF6.0\naF6.0\naF3.0\naF3.0\naF5.0\naF5.0\naF1.0\naF3.0\naF2.0\naF3.0\naF5.0\naF0.0\naF9.0\naF0.0\naF3.0\naF3.0\naF5.0\naF4.0\naF2.0\naF2.0\naF6.0\naF10.0\naF3.0\naF5.0\naF4.0\naF6.0\naF2.0\naF4.0\naF7.0\naF5.0\naF1.0\naF4.0\naF3.0\naF2.0\naF2.0\naF3.0\naF3.0\naF4.0\naF4.0\naF6.0\naF3.0\naF3.0\naF3.0\naF3.0\naF5.0\naF4.0\naF5.0\naF4.0\naF3.0\naF8.0\naF2.0\naF2.0\naF5.0\naF5.0\naF4.0\naF3.0\naF4.0\naF2.0\naF4.0\naF6.0\naF5.0\naF4.0\naF4.0\naF6.0\naF4.0\naF5.0\naF4.0\naF7.0\naF4.0\naF5.0\naF3.0\naF2.0\naF5.0\naF1.0\naF2.0\naF3.0\naF2.0\naF6.0\naF7.0\naF5.0\naF12.0\naF11.0\naF7.0\naF5.0\naF7.0\naF8.0\naF5.0\naF5.0\naF9.0\naF6.0\naF6.0\naF8.0\naF7.0\naF4.0\naF10.0\naF2.0\naF3.0\naF7.0\naF4.0\naF6.0\naF4.0\naF3.0\naF5.0\naF6.0\naF6.0\naF7.0\naF2.0\naF4.0\naF4.0\naF5.0\naF4.0\naF2.0\naF2.0\naF3.0\naF7.0\naF8.0\naF3.0\naF3.0\naF7.0\naF6.0\naF2.0\naF1.0\naF5.0\naF3.0\naF8.0\naF7.0\naF7.0\naF5.0\naF2.0\naF5.0\naF3.0\naF2.0\naF4.0\naF4.0\naF4.0\naF4.0\naF9.0\naF4.0\naF3.0\naF7.0\naF11.0\naF0.0\naF7.0\naF6.0\naF3.0\naF6.0\naF9.0\naF5.0\naF10.0\naF2.0\naF2.0\naF7.0\naF4.0\naF9.0\naF3.0\naF6.0\naF3.0\naF5.0\naF6.0\naF6.0\naF3.0\naF1.0\naF6.0\naF8.0\naF6.0\naF4.0\naF6.0\naF5.0\naF15.0\naF10.0\naF6.0\naF4.0\naF1.0\naF4.0\naF5.0\naF5.0\naF11.0\naF4.0\naF6.0\naF3.0\naF6.0\naF3.0\naF2.0\naF5.0\naF7.0\naF7.0\naF8.0\naF0.0\naF5.0\naF8.0\naF7.0\naF5.0\naF11.0\naF3.0\naF7.0\naF4.0\naF3.0\naF12.0\naF7.0\naF5.0\naF8.0\naF7.0\naF2.0\naF8.0\naF4.0\naF5.0\naF10.0\naF5.0\naF4.0\naF9.0\naF8.0\naF14.0\naF2.0\naF4.0\naF8.0\naF5.0\naF7.0\naF2.0\naF5.0\naF9.0\naF6.0\naF2.0\naF6.0\naF6.0\naF0.0\naF9.0\naF9.0\naF10.0\naF4.0\naF5.0\naF3.0\naF3.0\naF2.0\naF4.0\naF6.0\naF4.0\naF4.0\naF7.0\naF8.0\naF2.0\naF11.0\naF5.0\naF6.0\naF4.0\naF12.0\naF3.0\naF6.0\naF4.0\naF4.0\naF4.0\naF7.0\naF3.0\naF3.0\naF5.0\naF5.0\naF2.0\naF6.0\naF6.0\naF5.0\naF6.0\naF4.0\naF7.0\naF7.0\naF10.0\naF5.0\naF2.0\naF5.0\naF6.0\naF2.0\naF3.0\naF10.0\naF7.0\naF4.0\naF11.0\naF8.0\naF6.0\naF0.0\naF4.0\naF5.0\naF9.0\naF10.0\naF3.0\naF6.0\naF9.0\naF2.0\naF5.0\naF3.0\naF5.0\naF6.0\naF10.0\naF5.0\naF3.0\naF8.0\naF4.0\naF8.0\naF5.0\naF4.0\naF5.0\naF8.0\naF6.0\naF4.0\naF11.0\naF6.0\naF6.0\naF9.0\naF5.0\naF7.0\naF5.0\naF6.0\naF6.0\naF5.0\naF7.0\naF4.0\naF8.0\naF8.0\naF4.0\naF9.0\naF4.0\naF2.0\naF2.0\naF4.0\naF3.0\naF8.0\naF3.0\naF8.0\naF7.0\naF6.0\naF1.0\naF7.0\naF7.0\naF2.0\naF6.0\naF5.0\naF8.0\naF7.0\naF3.0\naF8.0\naF4.0\naF2.0\naF3.0\naF6.0\naF6.0\naF10.0\naF4.0\naF9.0\naF5.0\naF2.0\naF6.0\naF3.0\naF10.0\naF11.0\naF6.0\naF10.0\naF6.0\naF4.0\naF5.0\naF5.0\naF5.0\naF12.0\naF7.0\naF1.0\naF9.0\naF3.0\naF12.0\naF1.0\naF11.0\naF6.0\naF9.0\naF6.0\naF2.0\naF13.0\naF5.0\naF12.0\naF4.0\naF3.0\naF8.0\naF7.0\naF3.0\naF5.0\naF6.0\naF8.0\naF9.0\naF6.0\naF17.0\naF4.0\naF2.0\naF5.0\naF8.0\naF4.0\naF2.0\naF4.0\naF7.0\naF10.0\naF4.0\naF8.0\naF4.0\naF11.0\naF4.0\naF8.0\naF2.0\naF5.0\naF6.0\naF5.0\naF5.0\naF8.0\naF10.0\naF4.0\naF5.0\naF6.0\naF3.0\naF3.0\naF12.0\naF4.0\naF4.0\naF3.0\naF8.0\naF5.0\naF5.0\naF5.0\naF11.0\naF5.0\naF6.0\naF10.0\naF5.0\naF4.0\naF8.0\naF5.0\naF6.0\naF3.0\naF5.0\naF6.0\naF10.0\naF9.0\naF12.0\naF7.0\naF7.0\naF10.0\naF9.0\naF6.0\naF8.0\naF8.0\naF5.0\naF5.0\naF2.0\naF3.0\naF7.0\naF4.0\naF11.0\naF9.0\naF8.0\naF7.0\naF6.0\naF1.0\naF5.0\naF7.0\naF5.0\naF7.0\naF3.0\naF8.0\naF7.0\naF17.0\naF4.0\naF3.0\naF7.0\naF14.0\naF3.0\naF8.0\naF12.0\naF10.0\naF5.0\naF7.0\naF7.0\naF1.0\naF5.0\naF6.0\naF8.0\naF3.0\naF5.0\naF2.0\naF6.0\naF5.0\naF11.0\naF3.0\naF7.0\naF12.0\naF17.0\naF5.0\naF8.0\naF3.0\naF6.0\naF10.0\naF5.0\naF3.0\naF3.0\naF9.0\naF13.0\naF13.0\naF8.0\naF4.0\naF2.0\naF11.0\naF3.0\naF4.0\naF7.0\naF5.0\naF6.0\naF5.0\naF5.0\naF2.0\naF3.0\naF9.0\naF12.0\naF16.0\naF3.0\naF10.0\naF8.0\naF4.0\naF5.0\naF5.0\naF5.0\naF4.0\naF6.0\naF7.0\naF15.0\naF16.0\naF10.0\naF5.0\naF3.0\naF4.0\naF13.0\naF7.0\naF6.0\naF8.0\naF9.0\naF5.0\naF11.0\naF13.0\naF11.0\naF7.0\naF3.0\naF7.0\naF1.0\naF9.0\naF7.0\naF6.0\naF12.0\naF13.0\naF7.0\naF3.0\naF8.0\naF6.0\naF5.0\naF15.0\naF6.0\naF21.0\naF9.0\naF5.0\naF7.0\naF5.0\naF10.0\naF6.0\naF4.0\naF8.0\naF6.0\naF5.0\naF7.0\naF3.0\naF6.0\naF11.0\naF8.0\naF9.0\naF4.0\naF5.0\naF8.0\naF6.0\naF12.0\naF14.0\naF8.0\naF7.0\naF1.0\naF7.0\naF5.0\naF11.0\naF5.0\naF9.0\naF8.0\naF8.0\naF10.0\naF8.0\naF10.0\naF5.0\naF11.0\naF7.0\naF17.0\naF3.0\naF18.0\naF12.0\naF11.0\naF5.0\naF9.0\naF7.0\naF3.0\naF2.0\naF5.0\naF15.0\naF7.0\naF10.0\naF15.0\naF2.0\naF4.0\naF5.0\naF9.0\naF5.0\naF4.0\naF6.0\naF5.0\naF6.0\naF8.0\naF2.0\naF7.0\naF14.0\naF12.0\naF7.0\naF5.0\naF11.0\naF7.0\naF9.0\naF10.0\naF5.0\naF2.0\naF4.0\naF5.0\naF2.0\naF4.0\naF8.0\naF3.0\naF11.0\naF14.0\naF4.0\naF13.0\naF9.0\naF2.0\naF7.0\naF10.0\naF8.0\naF3.0\naF7.0\naF5.0\naF4.0\naF12.0\naF7.0\naF8.0\naF14.0\naF10.0\naF4.0\naF10.0\naF8.0\naF9.0\naF5.0\naF11.0\naF13.0\naF5.0\naF4.0\naF10.0\naF4.0\naF5.0\naF8.0\naF8.0\naF8.0\naF10.0\naF17.0\naF4.0\naF7.0\naF8.0\naF9.0\naF11.0\naF7.0\naF4.0\naF10.0\naF14.0\naF6.0\naF4.0\naF8.0\naF13.0\naF8.0\naF5.0\naF2.0\naF8.0\naF2.0\naF5.0\naF6.0\naF3.0\naF0.0\naF4.0\naF7.0\naF9.0\naF6.0\naF8.0\naF6.0\naF9.0\naF14.0\naF2.0\naF4.0\naF5.0\naF11.0\naF14.0\naF7.0\naF7.0\naF6.0\naF6.0\naF10.0\naF13.0\naF4.0\naF13.0\naF5.0\naF12.0\naF6.0\naF13.0\naF6.0\naF6.0\naF9.0\naF5.0\naF9.0\naF8.0\naF3.0\naF14.0\naF10.0\naF9.0\naF2.0\naF7.0\naF7.0\naF12.0\naF7.0\naF8.0\naF4.0\naF6.0\naF12.0\naF3.0\naF5.0\naF6.0\naF7.0\naF16.0\naF6.0\naF5.0\naF2.0\naF10.0\naF9.0\naF5.0\naF8.0\naF6.0\naF3.0\naF5.0\naF16.0\naF12.0\naF8.0\naF12.0\naF8.0\naF8.0\naF15.0\naF7.0\naF10.0\naF8.0\naF7.0\naF10.0\naF9.0\naF6.0\naF8.0\naF18.0\naF8.0\naF8.0\naF9.0\naF4.0\naF10.0\naF13.0\naF10.0\naF8.0\naF15.0\naF8.0\naF12.0\naF6.0\naF11.0\naF10.0\naF10.0\naF5.0\naF13.0\naF7.0\naF5.0\naF10.0\naF16.0\naF2.0\naF17.0\naF5.0\naF10.0\naF11.0\naF7.0\naF8.0\naF12.0\naF9.0\naF8.0\naF6.0\naF6.0\naF15.0\naF7.0\naF20.0\naF6.0\naF9.0\naF21.0\naF7.0\naF9.0\naF7.0\naF7.0\naF5.0\naF3.0\naF4.0\naF8.0\naF8.0\naF8.0\naF8.0\naF10.0\naF9.0\naF8.0\naF6.0\naF11.0\naF5.0\naF10.0\naF5.0\naF11.0\naF3.0\naF12.0\naF10.0\naF16.0\naF5.0\naF11.0\naF17.0\naF10.0\naF2.0\naF8.0\naF7.0\naF7.0\naF4.0\naF10.0\naF11.0\naF11.0\naF6.0\naF0.0\naF12.0\naF10.0\naF10.0\naF10.0\naF7.0\naF2.0\naF4.0\naF11.0\naF9.0\naF6.0\naF4.0\naF8.0\naF6.0\naF6.0\naF13.0\naF7.0\naF11.0\naF15.0\naF9.0\naF8.0\naF5.0\naF10.0\naF6.0\naF3.0\naF9.0\naF7.0\naF9.0\naF22.0\naF7.0\naF11.0\naF10.0\naF5.0\naF17.0\naF18.0\naF9.0\naF12.0\naF6.0\naF12.0\naF16.0\naF3.0\naF12.0\naF6.0\naF17.0\naF9.0\naF11.0\naF12.0\naF4.0\naF6.0\naF8.0\naF7.0\naF14.0\naF10.0\naF14.0\naF11.0\naF13.0\naF9.0\naF3.0\naF4.0\naF8.0\naF12.0\naF1.0\naF8.0\naF11.0\naF5.0\naF10.0\naF11.0\naF4.0\naF5.0\naF8.0\naF7.0\naF3.0\naF6.0\naF15.0\naF21.0\naF12.0\naF6.0\naF6.0\naF11.0\naF5.0\naF13.0\naF11.0\naF10.0\naF6.0\naF11.0\naF10.0\naF27.0\naF3.0\naF3.0\naF12.0\naF16.0\naF6.0\naF6.0\naF17.0\naF10.0\naF9.0\naF16.0\naF13.0\naF7.0\naF8.0\naF16.0\naF9.0\naF13.0\naF4.0\naF2.0\naF12.0\naF5.0\naF7.0\naF19.0\naF10.0\naF11.0\naF13.0\naF27.0\naF13.0\naF13.0\naF6.0\naF5.0\naF4.0\naF5.0\naF12.0\naF17.0\naF12.0\naF5.0\naF22.0\naF4.0\naF8.0\naF12.0\naF8.0\naF8.0\naF7.0\naF13.0\naF12.0\naF2.0\naF9.0\naF7.0\naF18.0\naF15.0\naF9.0\naF5.0\naF9.0\naF13.0\naF12.0\naF13.0\naF10.0\naF12.0\naF15.0\naF11.0\naF10.0\naF9.0\naF9.0\naF9.0\naF3.0\naF9.0\naF11.0\naF4.0\naF8.0\naF21.0\naF16.0\naF15.0\naF8.0\naF7.0\naF7.0\naF13.0\naF5.0\naF14.0\naF16.0\naF13.0\naF12.0\naF11.0\naF7.0\naF9.0\naF5.0\naF1.0\naF12.0\naF14.0\naF10.0\naF10.0\naF19.0\naF8.0\naF15.0\naF6.0\naF7.0\naF16.0\naF4.0\naF9.0\naF6.0\naF10.0\naF15.0\naF7.0\naF10.0\naF5.0\naF5.0\naF3.0\naF15.0\naF10.0\naF15.0\naF11.0\naF9.0\naF13.0\naF16.0\naF24.0\naF4.0\naF2.0\naF9.0\naF6.0\naF14.0\naF16.0\naF14.0\naF19.0\naF8.0\naF18.0\naF4.0\naF11.0\naF18.0\naF11.0\naF19.0\naF7.0\naF12.0\naF9.0\naF5.0\naF17.0\naF7.0\naF7.0\naF18.0\naF16.0\naF7.0\naF10.0\naF10.0\naF2.0\naF14.0\naF15.0\naF6.0\naF7.0\naF6.0\naF18.0\naF6.0\naF9.0\naF10.0\naF4.0\naF6.0\naF20.0\naF6.0\naF4.0\naF8.0\naF15.0\naF10.0\naF10.0\naF10.0\naF5.0\naF15.0\naF10.0\naF9.0\naF14.0\naF9.0\naF15.0\naF5.0\naF22.0\naF16.0\naF15.0\naF14.0\naF24.0\naF12.0\naF22.0\naF13.0\naF9.0\naF19.0\naF15.0\naF16.0\naF8.0\naF8.0\naF9.0\naF18.0\naF10.0\naF15.0\naF11.0\naF21.0\naF17.0\naF3.0\naF13.0\naF17.0\naF27.0\naF22.0\naF8.0\naF5.0\naF18.0\naF5.0\naF25.0\naF6.0\naF16.0\naF15.0\naF11.0\naF28.0\naF5.0\naF27.0\naF11.0\naF14.0\naF28.0\naF13.0\naF9.0\naF4.0\naF20.0\naF19.0\naF10.0\naF12.0\naF24.0\naF13.0\naF14.0\naF54.0\naF16.0\naF20.0\naF11.0\naF16.0\naF10.0\naF14.0\naF10.0\naF10.0\naF25.0\naF11.0\naF13.0\naF13.0\naF10.0\naF23.0\naF9.0\naF6.0\naF7.0\naF15.0\naF13.0\naF21.0\naF12.0\naF8.0\naF16.0\naF12.0\naF12.0\naF8.0\naF12.0\naF20.0\naF23.0\naF18.0\naF21.0\naF7.0\naF19.0\naF13.0\naF3.0\naF17.0\naF7.0\naF10.0\naF18.0\naF29.0\naF5.0\naF6.0\naF12.0\naF6.0\naF9.0\naF24.0\naF7.0\naF2.0\naF9.0\naF27.0\naF11.0\naF12.0\naF12.0\naF15.0\naF21.0\naF14.0\naF13.0\naF22.0\naF26.0\naF21.0\naF12.0\naF14.0\naF5.0\naF19.0\naF10.0\naF17.0\naF17.0\naF11.0\naF11.0\naF7.0\naF17.0\naF18.0\naF16.0\naF13.0\naF33.0\naF22.0\naF7.0\naF11.0\naF9.0\naF7.0\naF18.0\naF11.0\naF24.0\naF34.0\naF20.0\naF24.0\naF22.0\naF9.0\naF16.0\naF18.0\naF18.0\naF23.0\naF23.0\naF22.0\naF10.0\naF20.0\naF22.0\naF40.0\naF17.0\naF26.0\naF19.0\naF29.0\naF15.0\naF15.0\naF28.0\naF12.0\naF30.0\naF17.0\naF29.0\naF24.0\naF11.0\naF13.0\naF11.0\naF29.0\naF25.0\naF19.0\naF38.0\naF20.0\naF24.0\naF17.0\naF17.0\naF12.0\naF11.0\naF5.0\naF14.0\naF21.0\naF15.0\naF10.0\naF19.0\naF21.0\naF17.0\naF22.0\naF24.0\naF28.0\naF24.0\naF14.0\naF13.0\naF12.0\naF12.0\naF17.0\naF27.0\naF38.0\naF22.0\naF25.0\naF9.0\naF14.0\naF17.0\naF31.0\naF11.0\naF16.0\naF14.0\naF20.0\naF26.0\naF28.0\naF27.0\naF15.0\naF30.0\naF27.0\naF21.0\naF18.0\naF39.0\naF24.0\naF21.0\naF22.0\naF32.0\naF12.0\naF22.0\naF10.0\naF48.0\naF34.0\naF18.0\naF29.0\naF25.0\naF28.0\naF20.0\naF11.0\naF36.0\naF23.0\naF17.0\naF17.0\naF22.0\naF35.0\naF26.0\naF38.0\naF27.0\naF33.0\naF38.0\naF13.0\naF14.0\naF29.0\naF35.0\naF12.0\naF38.0\naF17.0\naF10.0\naF27.0\naF29.0\naF23.0\naF51.0\naF16.0\naF14.0\naF14.0\naF14.0\naF15.0\naF36.0\naF63.0\naF18.0\naF15.0\naF15.0\naF22.0\naF26.0\naF8.0\naF33.0\naF19.0\naF14.0\naF26.0\naF26.0\naF12.0\naF32.0\naF16.0\naF25.0\naF27.0\naF39.0\naF32.0\naF48.0\naF29.0\naF17.0\naF35.0\naF14.0\naF35.0\naF30.0\naF29.0\naF23.0\naF21.0\naF20.0\naF30.0\naF46.0\naF32.0\naF39.0\naF20.0\naF19.0\naF29.0\naF21.0\naF30.0\naF18.0\naF36.0\naF26.0\naF42.0\naF52.0\naF26.0\naF34.0\naF36.0\naF31.0\naF22.0\naF16.0\naF27.0\naF17.0\naF50.0\naF34.0\naF30.0\naF29.0\naF35.0\naF32.0\naF32.0\naF24.0\naF33.0\naF44.0\naF49.0\naF42.0\naF26.0\naF21.0\naF31.0\naF27.0\naF40.0\naF33.0\naF26.0\naF42.0\naF40.0\naF31.0\naF37.0\naF33.0\naF58.0\naF25.0\naF21.0\naF55.0\naF21.0\naF45.0\naF32.0\naF26.0\naF34.0\naF37.0\naF27.0\naF42.0\naF49.0\naF57.0\naF73.0\naF39.0\naF20.0\naF87.0\naF11.0\naF33.0\naF34.0\naF53.0\naF41.0\naF39.0\naF42.0\naF36.0\naF40.0\naF43.0\naF25.0\naF32.0\naF47.0\naF40.0\naF72.0\naF38.0\naF36.0\naF23.0\naF39.0\naF38.0\naF19.0\naF60.0\naF59.0\naF58.0\naF44.0\naF23.0\naF46.0\naF35.0\naF26.0\naF32.0\naF42.0\naF58.0\naF37.0\naF29.0\naF53.0\naF31.0\naF45.0\naF57.0\naF78.0\naF31.0\naF26.0\naF53.0\naF32.0\naF26.0\naF42.0\naF28.0\naF41.0\naF27.0\naF58.0\naF41.0\naF49.0\naF26.0\naF52.0\naF74.0\naF62.0\naF72.0\naF10.0\naF46.0\naF46.0\naF30.0\naF37.0\naF20.0\naF15.0\naF53.0\naF48.0\naF64.0\naF57.0\naF38.0\naF46.0\naF18.0\naF39.0\naF41.0\naF33.0\naF37.0\naF29.0\naF29.0\naF74.0\naF30.0\naF45.0\naF44.0\naF25.0\naF39.0\naF49.0\naF51.0\naF69.0\naF54.0\naF24.0\naF34.0\naF29.0\naF54.0\naF50.0\naF44.0\naF38.0\naF42.0\naF37.0\naF86.0\naF41.0\naF56.0\naF64.0\naF75.0\naF64.0\naF33.0\naF54.0\naF77.0\naF32.0\naF37.0\naF47.0\naF32.0\naF51.0\naF80.0\naF27.0\naF54.0\naF53.0\naF52.0\naF62.0\naF44.0\naF57.0\naF41.0\naF47.0\naF35.0\naF46.0\naF45.0\naF46.0\naF58.0\naF53.0\naF48.0\naF45.0\naF17.0\naF61.0\naF60.0\naF38.0\naF60.0\naF34.0\naF60.0\naF53.0\naF64.0\naF24.0\naF45.0\naF27.0\naF18.0\naF48.0\naF33.0\naF64.0\naF70.0\naF49.0\naF26.0\naF40.0\naF75.0\naF85.0\naF59.0\naF33.0\naF22.0\naF49.0\naF30.0\naF62.0\naF33.0\naF69.0\naF52.0\naF49.0\naF38.0\naF51.0\naF58.0\naF50.0\naF29.0\naF3.0\naF48.0\naF51.0\naF53.0\naF26.0\naF56.0\naF14.0\naF39.0\naF58.0\naF35.0\naF64.0\naF45.0\naF50.0\naF40.0\naF52.0\naF55.0\naF43.0\naF84.0\naF75.0\naF51.0\naF31.0\naF56.0\naF36.0\naF40.0\naF51.0\naF53.0\naF68.0\naF33.0\naF40.0\naF60.0\naF60.0\naF56.0\naF71.0\naF38.0\naF59.0\naF82.0\naF50.0\naF32.0\naF58.0\naF72.0\naF45.0\naF60.0\naF49.0\naF50.0\naF53.0\naF83.0\naF65.0\naF70.0\naF51.0\naF61.0\naF72.0\naF33.0\naF0.0\naF5.0\naF40.0\naF67.0\naF51.0\naF47.0\naF34.0\naF27.0\naF80.0\naF19.0\naF46.0\naF53.0\naF35.0\naF49.0\naF61.0\naF34.0\naF18.0\naF61.0\naF76.0\naF48.0\naF55.0\naF39.0\naF66.0\naF84.0\naF42.0\naF57.0\naF32.0\naF56.0\naF47.0\naF61.0\naF46.0\naF46.0\naF70.0\naF59.0\naF55.0\naF59.0\naF34.0\naF64.0\naF76.0\naF42.0\naF66.0\naF72.0\naF46.0\naF69.0\naF52.0\naF71.0\naF43.0\naF59.0\naF24.0\naF18.0\naF24.0\naF46.0\naF74.0\naF59.0\naF90.0\naF78.0\naF87.0\naF62.0\naF61.0\naF70.0\naF47.0\naF20.0\naF65.0\naF65.0\naF50.0\naF19.0\naF51.0\naF43.0\naF64.0\naF61.0\naF72.0\naF54.0\naF39.0\naF58.0\naF54.0\naF80.0\naF24.0\naF61.0\naF54.0\naF74.0\naF48.0\naF62.0\naF55.0\naF82.0\naF17.0\naF61.0\naF50.0\naF33.0\naF56.0\naF42.0\naF55.0\naF77.0\naF46.0\naF41.0\naF57.0\naF39.0\naF72.0\naF36.0\naF4.0\naF3.0\naF38.0\naF39.0\naF38.0\naF49.0\naF95.0\naF32.0\naF64.0\naF46.0\naF39.0\naF41.0\naF40.0\naF66.0\naF59.0\naF80.0\naF66.0\naF29.0\naF78.0\naF61.0\naF65.0\naF82.0\naF41.0\naF48.0\naF38.0\naF71.0\naF71.0\naF70.0\naF80.0\naF41.0\naF57.0\naF50.0\naF73.0\naF56.0\naF38.0\naF49.0\naF91.0\naF85.0\naF60.0\naF62.0\naF50.0\naF62.0\naF37.0\naF85.0\naF54.0\naF55.0\naF70.0\naF58.0\naF70.0\naF12.0\naF66.0\naF7.0\naF70.0\naF22.0\naF47.0\naF28.0\naF76.0\naF58.0\naF35.0\naF14.0\naF2.0\naF11.0\naF9.0\naF60.0\naF86.0\naF58.0\naF70.0\naF115.0\naF41.0\naF46.0\naF63.0\naF60.0\naF50.0\naF51.0\naF84.0\naF68.0\naF50.0\naF60.0\naF45.0\naF92.0\naF36.0\naF56.0\naF51.0\naF57.0\naF41.0\naF75.0\naF39.0\naF68.0\naF49.0\naF85.0\naF85.0\naF58.0\naF57.0\naF52.0\naF62.0\naF29.0\naF86.0\naF65.0\naF86.0\naF54.0\naF70.0\naF85.0\naF79.0\naF30.0\naF55.0\naF83.0\naF60.0\naF58.0\naF110.0\naF35.0\naF100.0\naF76.0\naF69.0\naF37.0\naF69.0\naF81.0\naF76.0\naF62.0\naF55.0\naF86.0\naF74.0\naF78.0\naF75.0\naF68.0\naF81.0\naF81.0\naF76.0\naF63.0\naF252.0\naF47.0\naF82.0\naF89.0\naF40.0\naF76.0\naF76.0\naF38.0\naF58.0\naF55.0\naF39.0\naF3.0\naF3.0\naF0.0\naF47.0\naF12.0\naF8.0\naF13.0\naF8.0\naF4.0\naF10.0\naF2.0\naF7.0\naF2.0\naF2.0\naF1.0\naF2.0\naF4.0\naF8.0\naF3.0\naF1.0\naF5.0\naF2.0\naF14.0\naF6.0\naF5.0\naF8.0\naF3.0\naF8.0\naF16.0\naF22.0\naF12.0\naF26.0\naF36.0\naF47.0\naF65.0\naF30.0\naF74.0\naF54.0\naF76.0\naF76.0\naF57.0\naF63.0\naF89.0\naF84.0\naF39.0\naF105.0\naF33.0\naF54.0\naF63.0\naF66.0\naF64.0\naF72.0\naF81.0\naF66.0\naF31.0\naF73.0\naF75.0\naF45.0\naF4.0\naF10.0\naF41.0\naF46.0\naF121.0\naF42.0\naF69.0\naF54.0\naF86.0\naF80.0\naF61.0\naF93.0\naF32.0\naF59.0\naF48.0\naF71.0\naF92.0\naF41.0\naF20.0\naF3.0\naF0.0\naF0.0\naF0.0\naF6.0\naF2.0\naF2.0\naF0.0\naF4.0\naF3.0\naF5.0\naF8.0\naF32.0\naF68.0\naF63.0\naF164.0\naF67.0\naF55.0\naF75.0\naF66.0\naF65.0\naF61.0\naF108.0\naF49.0\naF50.0\naF125.0\naF31.0\naF46.0\naF38.0\naF88.0\naF48.0\naF62.0\naF67.0\naF68.0\naF86.0\naF10.0\naF7.0\naF19.0\naF36.0\naF26.0\naF107.0\naF54.0\naF48.0\naF31.0\naF67.0\naF68.0\naF242.0\naF65.0\naF71.0\naF47.0\naF5.0\naF5.0\naF5.0\naF2.0\naF2.0\naF2.0\naF2.0\naF5.0\naF4.0\naF3.0\naF6.0\naF7.0\naF61.0\naF65.0\naF68.0\naF54.0\naF1.0\naF3.0\naF12.0\naF24.0\naF44.0\naF64.0\naF52.0\naF97.0\naF86.0\naF105.0\naF93.0\naF214.0\naF80.0\naF48.0\naF1.0\naF2.0\naF1.0\naF1.0\naF27.0\naF67.0\naF53.0\naF55.0\naF80.0\naF67.0\naF117.0\naF112.0\naF67.0\naF50.0\naF78.0\naF4.0\naF0.0\naF1.0\naF3.0\naF0.0\naF13.0\naF56.0\naF90.0\naF103.0\naF64.0\naF37.0\naF88.0\naF74.0\naF35.0\naF67.0\naF61.0\naF18.0\naF7.0\naF66.0\naF93.0\naF96.0\naF85.0\naF69.0\naF42.0\naF64.0\naF71.0\naF51.0\naF95.0\naF0.0\naF1.0\naF3.0\naF8.0\naF3.0\naF37.0\naF82.0\naF80.0\naF49.0\naF117.0\naF102.0\naF13.0\naF64.0\naF59.0\naF85.0\naF65.0\naF32.0\naF46.0\naF18.0\naF68.0\naF92.0\naF84.0\naF55.0\naF21.0\naF2.0\naF10.0\naF5.0\naF4.0\naF3.0\naF15.0\naF44.0\naF35.0\naF65.0\naF26.0\naF71.0\naF120.0\naF16.0\naF92.0\naF19.0\naF2.0\naF1.0\naF1.0\naF3.0\naF4.0\naF2.0\naF2.0\naF7.0\naF23.0\naF83.0\naF62.0\naF67.0\naF57.0\naF56.0\naF79.0\naF86.0\naF52.0\naF22.0\naF10.0\naF66.0\naF45.0\naF60.0\naF55.0\naF86.0\naF102.0\naF86.0\naF84.0\naF43.0\naF114.0\naF51.0\naF31.0\naF105.0\naF32.0\naF90.0\naF84.0\naF35.0\naF74.0\naF58.0\naF32.0\naF127.0\naF59.0\naF46.0\naF67.0\naF18.0\naF52.0\naF83.0\naF87.0\naF72.0\naF104.0\naF41.0\naF62.0\naF56.0\naF55.0\naF65.0\naF253.0\naF4.0\naF1.0\naF12.0\naF57.0\naF73.0\naF78.0\naF74.0\naF62.0\naF78.0\naF14.0\naF41.0\naF71.0\naF111.0\naF60.0\naF61.0\naF77.0\naF36.0\naF2.0\naF60.0\naF103.0\naF33.0\naF13.0\naF2.0\naF2.0\naF22.0\naF260.0\naF47.0\naF67.0\naF65.0\naF75.0\naF72.0\naF40.0\naF82.0\naF99.0\naF76.0\naF25.0\naF85.0\naF50.0\naF47.0\naF39.0\naF52.0\naF47.0\naF31.0\naF59.0\naF52.0\naF93.0\naF83.0\naF114.0\naF83.0\naF64.0\naF74.0\naF94.0\naF67.0\naF95.0\naF57.0\naF57.0\naF3.0\naF55.0\naF129.0\naF82.0\naF92.0\naF62.0\naF58.0\naF75.0\naF4.0\naF30.0\naF56.0\naF87.0\naF49.0\naF71.0\naF101.0\naF10.0\naF83.0\naF62.0\naF101.0\naF76.0\naF27.0\naF53.0\naF74.0\naF91.0\naF68.0\naF48.0\naF157.0\naF9.0\naF2.0\naF25.0\naF42.0\naF84.0\naF49.0\naF71.0\naF67.0\naF61.0\naF31.0\naF75.0\naF335.0\naF27.0\naF84.0\naF94.0\naF116.0\naF58.0\naF50.0\naF18.0\naF68.0\naF52.0\naF52.0\naF117.0\naF47.0\naF130.0\naF62.0\naF34.0\naF77.0\naF77.0\naF78.0\naF96.0\naF61.0\naF116.0\naF77.0\naF121.0\naF23.0\naF66.0\naF35.0\naF42.0\naF47.0\naF49.0\naF47.0\naF65.0\naF62.0\naF64.0\naF75.0\naF94.0\naF40.0\naF68.0\naF47.0\naF70.0\naF73.0\naF100.0\naF76.0\naF93.0\naF80.0\naF124.0\naF48.0\naF74.0\naF16.0\naF6.0\naF0.0\naF3.0\naF31.0\naF52.0\naF39.0\naF150.0\naF75.0\naF113.0\naF87.0\naF42.0\naF58.0\naF29.0\naF60.0\naF57.0\naF96.0\naF80.0\naF63.0\naF71.0\naF44.0\naF1.0\naF2.0\naF4.0\naF3.0\naF1.0\naF3.0\naF3.0\naF4.0\naF6.0\naF3.0\naF6.0\naF14.0\naF47.0\naF78.0\naF72.0\naF226.0\naF78.0\naF102.0\naF96.0\naF76.0\naF109.0\naF79.0\naF116.0\naF53.0\naF50.0\naF1.0\naF6.0\naF18.0\naF94.0\naF81.0\naF61.0\naF85.0\naF45.0\naF69.0\naF50.0\naF24.0\naF73.0\naF49.0\naF74.0\naF100.0\naF63.0\naF62.0\naF113.0\naF48.0\naF87.0\naF117.0\naF194.0\naF83.0\naF123.0\naF107.0\naF69.0\naF60.0\naF68.0\naF75.0\naF186.0\naF67.0\naF84.0\naF105.0\naF122.0\naF84.0\naF80.0\naF44.0\naF78.0\naF105.0\naF97.0\naF45.0\naF41.0\naF61.0\naF115.0\naF41.0\naF42.0\naF63.0\naF34.0\naF85.0\naF123.0\naF73.0\naF249.0\naF121.0\naF36.0\naF62.0\naF85.0\naF50.0\naF107.0\naF243.0\naF146.0\naF55.0\naF99.0\naF104.0\naF67.0\naF169.0\naF78.0\naF145.0\naF76.0\naF59.0\naF90.0\naF101.0\naF78.0\naF98.0\naF95.0\naF56.0\naF88.0\naF67.0\naF31.0\naF273.0\naF21.0\naF139.0\naF139.0\naF74.0\naF84.0\naF60.0\naF124.0\naF76.0\naF62.0\naF11.0\naF39.0\naF120.0\naF17.0\naF83.0\naF66.0\naF85.0\naF109.0\naF144.0\naF99.0\naF67.0\naF62.0\naF85.0\naF63.0\naF87.0\naF58.0\naF71.0\naF113.0\naF105.0\naF118.0\naF89.0\naF75.0\naF113.0\naF68.0\naF32.0\naF107.0\naF86.0\naF91.0\naF114.0\naF60.0\naF24.0\naF76.0\naF56.0\naF46.0\naF49.0\naF96.0\naF51.0\naF66.0\naF83.0\naF33.0\naF68.0\naF106.0\naF29.0\naF91.0\naF88.0\naF241.0\naF142.0\naF115.0\naF130.0\naF78.0\naF36.0\naF119.0\naF261.0\naF111.0\naF102.0\naF56.0\naF10.0\naF2.0\naF44.0\naF69.0\naF54.0\naF40.0\naF55.0\naF91.0\naF40.0\naF98.0\naF4.0\naF22.0\naF23.0\naF12.0\naF12.0\naF22.0\naF9.0\naF80.0\naF34.0\naF66.0\naF61.0\naF6.0\naF53.0\naF64.0\naF238.0\naF73.0\naF31.0\naF58.0\naF50.0\naF135.0\naF56.0\naF159.0\naF98.0\naF239.0\naF111.0\naF102.0\naF73.0\naF63.0\naF133.0\naF112.0\naF70.0\naF142.0\naF109.0\naF61.0\naF53.0\naF66.0\naF92.0\naF72.0\naF67.0\naF122.0\naF257.0\naF47.0\naF80.0\naF267.0\naF76.0\naF109.0\naF69.0\naF68.0\naF54.0\naF33.0\naF46.0\naF139.0\naF59.0\naF128.0\naF134.0\naF44.0\naF275.0\naF153.0\naF65.0\naF105.0\naF28.0\naF45.0\naF53.0\naF65.0\naF85.0\naF108.0\naF49.0\naF198.0\naF239.0\naF102.0\naF106.0\naF80.0\naF157.0\naF46.0\naF70.0\naF12.0\naF73.0\naF87.0\naF55.0\naF33.0\naF106.0\naF175.0\naF149.0\naF155.0\naF45.0\naF106.0\naF77.0\naF66.0\naF28.0\naF145.0\naF79.0\naF76.0\naF51.0\naF82.0\naF331.0\naF54.0\naF111.0\naF87.0\naF174.0\naF59.0\naF62.0\naF72.0\naF47.0\naF63.0\naF68.0\naF96.0\naF77.0\naF35.0\naF231.0\naF83.0\naF46.0\naF57.0\naF102.0\naF46.0\naF131.0\naF260.0\naF111.0\naF97.0\naF98.0\naF44.0\naF136.0\naF11.0\naF96.0\naF149.0\naF143.0\naF121.0\naF73.0\naF74.0\naF132.0\naF105.0\naF247.0\naF86.0\naF97.0\naF110.0\naF106.0\naF86.0\naF157.0\naF91.0\naF253.0\naF92.0\naF131.0\naF299.0\naF147.0\naF117.0\naF42.0\naF104.0\naF149.0\naF97.0\naF99.0\naF118.0\naF51.0\naF203.0\naF92.0\naF122.0\naF57.0\naF23.0\naF21.0\naF136.0\naF92.0\naF114.0\naF59.0\naF184.0\naF40.0\naF106.0\naF64.0\naF113.0\naF43.0\naF162.0\naF96.0\naF65.0\naF58.0\naF35.0\naF87.0\naF144.0\naF107.0\naF95.0\naF97.0\naF31.0\naF213.0\naF142.0\naF150.0\naF77.0\naF89.0\naF66.0\naF121.0\naF125.0\naF79.0\naF47.0\naF52.0\naF92.0\naF52.0\naF186.0\naF96.0\naF91.0\naF121.0\naF117.0\naF166.0\naF68.0\naF212.0\naF75.0\naF92.0\naF77.0\naF158.0\naF190.0\naF234.0\naF192.0\naF108.0\naF51.0\naF136.0\naF88.0\naF142.0\naF69.0\naF146.0\naF87.0\naF72.0\naF44.0\naF91.0\naF97.0\naF233.0\naF116.0\naF115.0\naF103.0\naF156.0\naF35.0\naF104.0\naF179.0\naF14.0\naF105.0\naF126.0\naF146.0\naF141.0\naF88.0\naF51.0\naF139.0\naF317.0\naF73.0\naF54.0\naF122.0\naF92.0\naF94.0\naF115.0\naF218.0\naF263.0\naF157.0\naF187.0\naF126.0\naF136.0\naF92.0\naF144.0\naF242.0\naF133.0\naF8.0\naF79.0\naF121.0\naF101.0\naF172.0\naF81.0\naF118.0\naF12.0\naF146.0\naF116.0\naF50.0\naF78.0\naF84.0\naF85.0\naF76.0\naF235.0\naF124.0\naF63.0\naF227.0\naF131.0\naF205.0\naF129.0\naF86.0\naF61.0\naF89.0\naF120.0\naF251.0\naF128.0\naF257.0\naF77.0\naF92.0\naF95.0\naF51.0\naF96.0\naF110.0\naF220.0\naF108.0\naF11.0\naF48.0\naF165.0\naF209.0\naF55.0\naF98.0\naF59.0\naF71.0\naF68.0\naF63.0\naF73.0\naF70.0\naF156.0\naF89.0\naF109.0\naF152.0\naF170.0\naF114.0\naF126.0\naF75.0\naF193.0\naF101.0\naF98.0\naF295.0\naF91.0\naF278.0\naF174.0\naF174.0\naF137.0\naF168.0\naF170.0\naF106.0\naF179.0\naF185.0\naF181.0\naF103.0\naF40.0\naF24.0\naF106.0\naF41.0\naF155.0\naF126.0\naF115.0\naF110.0\naF80.0\naF49.0\naF84.0\naF90.0\naF67.0\naF108.0\naF294.0\naF78.0\naF180.0\naF88.0\naF72.0\naF90.0\naF52.0\naF69.0\naF267.0\naF113.0\naF53.0\naF77.0\naF237.0\naF48.0\naF35.0\naF85.0\naF71.0\naF151.0\naF155.0\naF104.0\naF88.0\naF118.0\naF275.0\naF94.0\naF135.0\naF190.0\naF72.0\naF127.0\naF108.0\naF46.0\naF79.0\naF54.0\naF60.0\naF185.0\naF70.0\naF108.0\naF83.0\naF13.0\naF305.0\naF57.0\naF138.0\naF146.0\naF56.0\naF86.0\naF90.0\naF78.0\naF276.0\naF51.0\naF271.0\naF159.0\naF108.0\naF116.0\naF126.0\naF149.0\naF203.0\naF152.0\naF224.0\naF182.0\naF78.0\naF270.0\naF271.0\naF145.0\naF182.0\naF108.0\naF85.0\naF185.0\naF97.0\naF22.0\naF83.0\naF71.0\naF118.0\naF73.0\naF230.0\naF139.0\naF114.0\naF68.0\naF106.0\naF133.0\naF284.0\naF154.0\naF62.0\naF81.0\naF96.0\naF99.0\naF130.0\naF136.0\naF87.0\naF118.0\naF94.0\naF98.0\naF33.0\naF18.0\naF123.0\naF59.0\naF45.0\naF82.0\naF61.0\naF56.0\naF249.0\naF36.0\naF53.0\naF106.0\naF62.0\naF106.0\naF139.0\naF83.0\naF75.0\naF6.0\naF52.0\naF70.0\naF59.0\naF276.0\naF62.0\naF48.0\naF143.0\naF48.0\naF30.0\naF60.0\naF43.0\naF130.0\naF69.0\naF5.0\naF55.0\naF36.0\naF43.0\naF291.0\naF42.0\naF35.0\naF39.0\naF47.0\naF57.0\naF81.0\naF19.0\naF18.0\naF17.0\naF12.0\naF77.0\naF45.0\naF25.0\naF32.0\naF30.0\naF56.0\naF32.0\naF6.0\naF18.0\naF42.0\naF19.0\naF24.0\naF21.0\naF18.0\naF9.0\naF21.0\naF23.0\naF23.0\naF32.0\naF9.0\naF25.0\naF6.0\naF9.0\naF39.0\naF20.0\naF34.0\naF29.0\naF17.0\naF20.0\naF22.0\naF15.0\naF15.0\naF21.0\naF24.0\naF13.0\naF10.0\naF4.0\naF7.0\naF16.0\naF39.0\naF15.0\naF24.0\naF7.0\naF9.0\naF7.0\naF3.0\naF4.0\naF14.0\naF9.0\naF4.0\naF4.0\naF4.0\naF17.0\naF4.0\naF5.0\naF6.0\naF9.0\naF4.0\naF7.0\naF5.0\naF9.0\naF3.0\naF8.0\naF1.0\naF4.0\naF1.0\naF3.0\naF6.0\naF3.0\naF1.0\naF5.0\naF6.0\naF9.0\naF8.0\naF7.0\naF7.0\naF1.0\naF5.0\naF9.0\naF5.0\naF13.0\naF10.0\naF10.0\naF4.0\naF2.0\naF2.0\naF12.0\naF3.0\naF2.0\naF1.0\naF1.0\naF2.0\naF2.0\naF1.0\naF3.0\naF3.0\naF1.0\naF3.0\naF5.0\naF9.0\naF14.0\naF6.0\naF3.0\naF2.0\naF0.0\naF5.0\naF5.0\naF2.0\naF7.0\naF1.0\naF3.0\naF3.0\naF1.0\naF4.0\naF5.0\naF3.0\naF9.0\naF2.0\naF3.0\naF3.0\naF1.0\naF6.0\naF2.0\naF1.0\naF2.0\naF3.0\naF4.0\naF3.0\naF5.0\naF4.0\naF1.0\naF5.0\naF5.0\naF3.0\naF5.0\naF5.0\naF11.0\naF2.0\naF1.0\naF10.0\naF4.0\naF0.0\naF5.0\naF5.0\naF6.0\naF0.0\naF1.0\naF3.0\naF1.0\naF1.0\naF2.0\naF0.0\naF0.0\naF5.0\naF3.0\naF0.0\naF1.0\naF2.0\naF2.0\naF0.0\naF3.0\naF2.0\naF1.0\naF1.0\naF1.0\naF1.0\naF1.0\naF1.0\naF5.0\naF0.0\naF3.0\naF0.0\naF1.0\naF2.0\naF0.0\naF0.0\naF2.0\naF0.0\naF2.0\naF3.0\naF1.0\naF0.0\naF3.0\naF0.0\naF3.0\naF1.0\naF4.0\naF3.0\naF1.0\naF3.0\naF1.0\naF0.0\naF3.0\naF1.0\naF0.0\naF0.0\naF3.0\naF0.0\naF0.0\naF1.0\naF2.0\naF3.0\naF0.0\naF0.0\naF4.0\naF1.0\naF6.0\naF1.0\naF5.0\naF3.0\naF0.0\naF0.0\naF1.0\naF1.0\naF1.0\naF6.0\naF2.0\naF1.0\naF6.0\naF3.0\naF7.0\naF2.0\naF4.0\naF2.0\naF2.0\naF4.0\naF1.0\naF1.0\naF2.0\naF1.0\naF6.0\naF4.0\naF2.0\naF1.0\naF2.0\naF1.0\naF3.0\naF1.0\naF0.0\naF0.0\naF1.0\naF1.0\naF1.0\naF3.0\naF2.0\naF3.0\naF1.0\naF4.0\naF3.0\naF3.0\naF4.0\naF0.0\naF2.0\naF0.0\naF1.0\naF4.0\naF4.0\naF5.0\naF1.0\naF0.0\naF1.0\naF3.0\naF1.0\naF2.0\naF2.0\naF5.0\naF5.0\naF4.0\naF6.0\naF1.0\naF2.0\naF0.0\naF0.0\naF2.0\naF3.0\naF2.0\naF0.0\naF1.0\naF1.0\naF1.0\naF1.0\naF3.0\naF4.0\naF2.0\naF4.0\naF2.0\naF2.0\naF3.0\naF3.0\naF2.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF3.0\naF3.0\naF2.0\naF2.0\naF1.0\naF1.0\naF5.0\naF1.0\naF3.0\naF3.0\naF1.0\naF0.0\naF3.0\naF6.0\naF0.0\naF3.0\naF0.0\naF3.0\naF0.0\naF2.0\naF0.0\naF1.0\naF4.0\naF3.0\naF1.0\naF3.0\naF1.0\naF2.0\naF2.0\naF1.0\naF10.0\naF6.0\naF2.0\naF6.0\naF1.0\naF1.0\naF2.0\naF3.0\naF4.0\naF1.0\naF5.0\naF5.0\naF3.0\naF4.0\naF2.0\naF2.0\naF6.0\naF2.0\naF4.0\naF0.0\naF1.0\naF13.0\naF1.0\naF2.0\naF2.0\naF3.0\naF0.0\naF3.0\naF3.0\naF2.0\naF4.0\naF1.0\naF10.0\naF3.0\naF0.0\naF2.0\naF2.0\naF3.0\naF2.0\naF3.0\naF3.0\naF5.0\naF4.0\naF3.0\naF1.0\naF6.0\naF7.0\naF1.0\naF1.0\naF1.0\naF2.0\naF5.0\naF2.0\naF2.0\naF4.0\naF5.0\naF4.0\naF1.0\naF3.0\naF2.0\naF0.0\naF6.0\naF3.0\naF0.0\naF0.0\naF5.0\naF4.0\naF1.0\naF4.0\naF3.0\naF4.0\naF1.0\naF4.0\naF5.0\naF5.0\naF6.0\naF3.0\naF4.0\naF1.0\naF4.0\naF4.0\naF2.0\naF9.0\naF2.0\naF3.0\naF5.0\naF5.0\naF6.0\naF3.0\naF2.0\naF5.0\naF1.0\naF0.0\naF3.0\naF4.0\naF1.0\naF4.0\naF2.0\naF1.0\naF1.0\naF2.0\naF3.0\naF4.0\naF5.0\naF2.0\naF1.0\naF3.0\naF1.0\naF3.0\naF1.0\naF1.0\naF1.0\naF0.0\naF2.0\naF2.0\naF2.0\naF0.0\naF2.0\naF3.0\naF6.0\naF5.0\naF7.0\naF3.0\naF7.0\naF6.0\naF2.0\naF4.0\naF2.0\naF2.0\naF1.0\naF1.0\naF3.0\naF2.0\naF4.0\naF4.0\naF2.0\naF2.0\naF2.0\naF0.0\naF3.0\naF1.0\naF7.0\naF3.0\naF3.0\naF3.0\naF4.0\naF4.0\naF2.0\naF5.0\naF1.0\naF2.0\naF2.0\naF4.0\naF3.0\naF4.0\naF4.0\naF2.0\naF0.0\naF5.0\naF3.0\naF2.0\naF0.0\naF4.0\naF1.0\naF2.0\naF1.0\naF4.0\naF1.0\naF1.0\naF5.0\naF3.0\naF2.0\naF0.0\naF0.0\naF2.0\naF4.0\naF1.0\naF1.0\naF3.0\naF2.0\naF2.0\naF1.0\naF2.0\naF5.0\naF1.0\naF2.0\naF6.0\naF4.0\naF3.0\naF1.0\naF1.0\naF2.0\naF1.0\naF6.0\naF2.0\naF1.0\naF0.0\naF3.0\naF3.0\naF2.0\naF1.0\naF1.0\naF4.0\naF4.0\naF1.0\naF2.0\naF0.0\naF3.0\naF2.0\naF2.0\naF8.0\naF2.0\naF2.0\naF2.0\naF2.0\naF3.0\naF2.0\naF2.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF4.0\naF4.0\naF4.0\naF3.0\naF5.0\naF4.0\naF6.0\naF1.0\naF1.0\naF2.0\naF1.0\naF3.0\naF1.0\naF3.0\naF1.0\naF2.0\naF1.0\naF1.0\naF2.0\naF4.0\naF1.0\naF3.0\naF2.0\naF2.0\naF0.0\naF2.0\naF1.0\naF1.0\naF3.0\naF1.0\naF3.0\naF4.0\naF2.0\naF3.0\naF4.0\naF0.0\naF2.0\naF2.0\naF3.0\naF6.0\naF3.0\naF3.0\naF1.0\naF4.0\naF0.0\naF0.0\naF4.0\naF3.0\naF4.0\naF2.0\naF1.0\naF2.0\naF0.0\naF1.0\naF4.0\naF3.0\naF1.0\naF4.0\naF6.0\naF4.0\naF5.0\naF2.0\naF1.0\naF2.0\naF1.0\naF1.0\naF3.0\naF3.0\naF2.0\naF3.0\naF4.0\naF1.0\naF7.0\naF1.0\naF0.0\naF3.0\naF1.0\naF2.0\naF0.0\naF5.0\naF5.0\naF1.0\naF3.0\naF1.0\naF3.0\naF2.0\naF1.0\naF7.0\naF4.0\naF0.0\naF1.0\naF2.0\naF1.0\naF0.0\naF2.0\naF1.0\naF2.0\naF4.0\naF4.0\naF1.0\naF0.0\naF2.0\naF7.0\naF1.0\naF0.0\naF4.0\naF1.0\naF3.0\naF7.0\naF1.0\naF4.0\naF1.0\naF1.0\naF3.0\naF2.0\naF4.0\naF0.0\naF1.0\naF3.0\naF4.0\naF5.0\naF2.0\naF4.0\naF0.0\naF5.0\naF5.0\naF2.0\naF3.0\naF2.0\naF2.0\naF3.0\naF1.0\naF4.0\naF2.0\naF3.0\naF3.0\naF1.0\naF2.0\naF4.0\naF2.0\naF1.0\naF3.0\naF2.0\naF3.0\naF1.0\naF1.0\naF3.0\naF2.0\naF5.0\naF3.0\naF0.0\naF4.0\naF0.0\naF1.0\naF1.0\naF3.0\naF1.0\naF0.0\naF5.0\naF5.0\naF1.0\naF1.0\naF3.0\naF3.0\naF1.0\naF4.0\naF2.0\naF1.0\naF0.0\naF2.0\naF4.0\naF4.0\naF1.0\naF5.0\naF1.0\naF2.0\naF2.0\naF3.0\naF4.0\naF6.0\naF8.0\naF1.0\naF2.0\naF3.0\naF1.0\naF3.0\naF2.0\naF1.0\naF3.0\naF2.0\naF5.0\naF4.0\naF2.0\naF3.0\naF3.0\naF6.0\naF2.0\naF2.0\naF1.0\naF0.0\naF3.0\naF2.0\naF1.0\naF0.0\naF1.0\naF4.0\naF1.0\naF2.0\naF4.0\naF3.0\naF9.0\naF3.0\naF2.0\naF1.0\naF3.0\naF3.0\naF0.0\naF2.0\naF5.0\naF2.0\naF2.0\naF7.0\naF1.0\naF3.0\naF3.0\naF3.0\naF2.0\naF6.0\naF1.0\naF1.0\naF1.0\naF6.0\naF4.0\naF8.0\naF1.0\naF2.0\naF5.0\naF4.0\naF3.0\naF0.0\naF0.0\naF5.0\naF1.0\naF1.0\naF1.0\naF1.0\naF4.0\naF2.0\naF2.0\naF0.0\naF4.0\naF8.0\naF1.0\naF0.0\naF1.0\naF1.0\naF4.0\naF0.0\naF2.0\naF1.0\naF1.0\naF1.0\naF1.0\naF1.0\naF0.0\naF2.0\naF2.0\naF4.0\naF0.0\naF3.0\naF1.0\naF3.0\naF4.0\naF2.0\naF5.0\naF0.0\naF3.0\naF3.0\naF0.0\naF1.0\naF1.0\naF2.0\naF0.0\naF1.0\naF1.0\naF1.0\naF5.0\naF1.0\naF1.0\naF3.0\naF2.0\naF2.0\naF2.0\naF0.0\naF0.0\naF5.0\naF0.0\naF1.0\naF3.0\naF0.0\naF3.0\naF1.0\naF1.0\naF4.0\naF0.0\naF2.0\naF2.0\naF2.0\naF4.0\naF1.0\naF2.0\naF4.0\naF3.0\naF3.0\naF1.0\naF1.0\naF3.0\naF3.0\naF2.0\naF4.0\naF5.0\naF2.0\naF6.0\naF5.0\naF0.0\naF1.0\naF4.0\naF0.0\naF2.0\naF0.0\naF2.0\naF3.0\naF1.0\naF2.0\naF3.0\naF1.0\naF3.0\naF5.0\naF1.0\naF2.0\naF2.0\naF1.0\naF1.0\naF4.0\naF2.0\naF3.0\naF6.0\naF2.0\naF3.0\naF2.0\naF4.0\naF2.0\naF4.0\naF4.0\naF1.0\naF5.0\naF3.0\naF4.0\naF4.0\naF2.0\naF5.0\naF1.0\naF1.0\naF4.0\naF3.0\naF3.0\naF3.0\naF1.0\naF2.0\naF1.0\naF2.0\naF4.0\naF2.0\naF2.0\naF4.0\naF1.0\naF2.0\naF5.0\naF4.0\naF4.0\naF7.0\naF2.0\naF2.0\naF8.0\naF4.0\naF3.0\naF5.0\naF5.0\naF6.0\naF6.0\naF2.0\naF2.0\naF7.0\naF7.0\naF7.0\naF7.0\naF2.0\naF3.0\naF9.0\naF7.0\naF6.0\naF9.0\naF3.0\naF6.0\naF2.0\naF6.0\naF5.0\naF7.0\naF6.0\naF4.0\naF3.0\naF2.0\naF5.0\naF4.0\naF3.0\naF1.0\naF5.0\naF1.0\naF3.0\naF4.0\naF10.0\naF2.0\naF5.0\naF6.0\naF5.0\naF8.0\naF6.0\naF1.0\naF3.0\naF6.0\naF3.0\naF2.0\naF6.0\naF4.0\naF3.0\naF1.0\naF3.0\naF1.0\naF0.0\naF7.0\naF4.0\naF3.0\naF2.0\naF3.0\naF4.0\naF4.0\naF2.0\naF5.0\naF1.0\naF4.0\naF6.0\naF4.0\naF5.0\naF5.0\naF9.0\naF8.0\naF5.0\naF11.0\naF5.0\naF4.0\naF7.0\naF2.0\naF5.0\naF2.0\naF5.0\naF9.0\naF3.0\naF3.0\naF7.0\naF4.0\naF5.0\naF3.0\naF12.0\naF4.0\naF4.0\naF6.0\naF14.0\naF3.0\naF2.0\naF2.0\naF5.0\naF10.0\naF7.0\naF2.0\naF2.0\naF7.0\naF5.0\naF3.0\naF5.0\naF5.0\naF4.0\naF8.0\naF4.0\naF6.0\naF5.0\naF3.0\naF0.0\naF6.0\naF8.0\naF7.0\naF3.0\naF4.0\naF6.0\naF1.0\naF7.0\naF0.0\naF5.0\naF5.0\naF5.0\naF6.0\naF3.0\naF5.0\naF4.0\naF8.0\naF8.0\naF7.0\naF3.0\naF6.0\naF3.0\naF3.0\naF3.0\naF2.0\naF0.0\naF2.0\naF3.0\naF4.0\naF5.0\naF2.0\naF1.0\naF1.0\naF5.0\naF4.0\naF4.0\naF3.0\naF6.0\naF5.0\naF3.0\naF0.0\naF6.0\naF8.0\naF6.0\naF5.0\naF3.0\naF6.0\naF1.0\naF4.0\naF3.0\naF5.0\naF3.0\naF4.0\naF7.0\naF7.0\naF7.0\naF14.0\naF2.0\naF5.0\naF7.0\naF5.0\naF6.0\naF2.0\naF3.0\naF5.0\naF3.0\naF3.0\naF2.0\naF11.0\naF7.0\naF5.0\naF10.0\naF1.0\naF2.0\naF2.0\naF5.0\naF4.0\naF4.0\naF1.0\naF3.0\naF3.0\naF7.0\naF9.0\naF1.0\naF3.0\naF9.0\naF4.0\naF3.0\naF2.0\naF2.0\naF4.0\naF8.0\naF5.0\naF0.0\naF3.0\naF3.0\naF4.0\naF3.0\naF12.0\naF7.0\naF4.0\naF2.0\naF3.0\naF1.0\naF3.0\naF1.0\naF3.0\naF7.0\naF4.0\naF4.0\naF3.0\naF2.0\naF1.0\naF3.0\naF2.0\naF1.0\naF2.0\naF1.0\naF5.0\naF3.0\naF4.0\naF11.0\naF6.0\naF6.0\naF6.0\naF3.0\naF4.0\naF3.0\naF1.0\naF5.0\naF5.0\naF6.0\naF2.0\naF1.0\naF2.0\naF0.0\naF7.0\naF2.0\naF1.0\naF1.0\naF3.0\naF4.0\naF3.0\naF12.0\naF5.0\naF5.0\naF15.0\naF10.0\naF1.0\naF0.0\naF4.0\naF8.0\naF1.0\naF3.0\naF1.0\naF3.0\naF9.0\naF9.0\naF4.0\naF9.0\naF7.0\naF3.0\naF5.0\naF5.0\naF2.0\naF5.0\naF5.0\naF5.0\naF6.0\naF1.0\naF2.0\naF0.0\naF3.0\naF4.0\naF6.0\naF5.0\naF7.0\naF6.0\naF6.0\naF1.0\naF4.0\naF4.0\naF2.0\naF2.0\naF6.0\naF5.0\naF7.0\naF4.0\naF4.0\naF4.0\naF2.0\naF1.0\naF5.0\naF6.0\naF12.0\naF2.0\naF6.0\naF8.0\naF1.0\naF9.0\naF2.0\naF4.0\naF4.0\naF1.0\naF4.0\naF4.0\naF4.0\naF3.0\naF6.0\naF3.0\naF5.0\naF6.0\naF6.0\naF2.0\naF5.0\naF3.0\naF2.0\naF8.0\naF8.0\naF1.0\naF5.0\naF4.0\naF4.0\naF5.0\naF2.0\naF4.0\naF2.0\naF2.0\naF5.0\naF3.0\naF6.0\naF4.0\naF8.0\naF4.0\naF2.0\naF3.0\naF2.0\naF9.0\naF7.0\naF1.0\naF17.0\naF10.0\naF2.0\naF3.0\naF3.0\naF5.0\naF13.0\naF3.0\naF8.0\naF8.0\naF5.0\naF3.0\naF5.0\naF6.0\naF5.0\naF8.0\naF7.0\naF4.0\naF3.0\naF4.0\naF4.0\naF7.0\naF3.0\naF5.0\naF4.0\naF5.0\naF5.0\naF6.0\naF6.0\naF8.0\naF7.0\naF2.0\naF3.0\naF3.0\naF4.0\naF4.0\naF7.0\naF10.0\naF7.0\naF4.0\naF5.0\naF9.0\naF7.0\naF7.0\naF7.0\naF5.0\naF3.0\naF11.0\naF1.0\naF4.0\naF3.0\naF3.0\naF4.0\naF4.0\naF1.0\naF5.0\naF4.0\naF5.0\naF3.0\naF2.0\naF1.0\naF4.0\naF2.0\naF0.0\naF8.0\naF3.0\naF2.0\naF2.0\naF7.0\naF0.0\naF0.0\naF1.0\naF2.0\naF1.0\naF2.0\naF4.0\naF2.0\naF4.0\naF4.0\naF5.0\naF7.0\naF3.0\naF4.0\naF1.0\naF5.0\naF1.0\naF0.0\naF4.0\naF7.0\naF6.0\naF5.0\naF3.0\naF5.0\naF5.0\naF4.0\naF4.0\naF5.0\naF4.0\naF7.0\naF4.0\naF4.0\naF3.0\naF5.0\naF5.0\naF4.0\naF5.0\naF4.0\naF9.0\naF7.0\naF5.0\naF1.0\naF9.0\naF7.0\naF1.0\naF4.0\naF7.0\naF3.0\naF4.0\naF0.0\naF6.0\naF4.0\naF6.0\naF5.0\naF3.0\naF8.0\naF3.0\naF1.0\naF1.0\naF4.0\naF7.0\naF6.0\naF1.0\naF5.0\naF7.0\naF2.0\naF2.0\naF2.0\naF0.0\naF5.0\naF5.0\naF5.0\naF8.0\naF7.0\naF5.0\naF4.0\naF5.0\naF5.0\naF5.0\naF4.0\naF6.0\naF2.0\naF7.0\naF6.0\naF5.0\naF12.0\naF4.0\naF8.0\naF0.0\naF5.0\naF5.0\naF4.0\naF1.0\naF2.0\naF6.0\naF9.0\naF7.0\naF9.0\naF5.0\naF4.0\naF8.0\naF7.0\naF3.0\naF8.0\naF6.0\naF5.0\naF6.0\naF7.0\naF9.0\naF9.0\naF4.0\naF5.0\naF6.0\naF5.0\naF11.0\naF1.0\naF8.0\naF1.0\naF2.0\naF5.0\naF8.0\naF5.0\naF1.0\naF8.0\naF6.0\naF11.0\naF5.0\naF5.0\naF5.0\naF7.0\naF1.0\naF0.0\naF7.0\naF5.0\naF9.0\naF8.0\naF5.0\naF6.0\naF8.0\naF2.0\naF5.0\naF6.0\naF4.0\naF6.0\naF9.0\naF4.0\naF6.0\naF4.0\naF5.0\naF1.0\naF10.0\naF1.0\naF5.0\naF4.0\naF7.0\naF6.0\naF7.0\naF19.0\naF5.0\naF6.0\naF6.0\naF3.0\naF7.0\naF5.0\naF6.0\naF5.0\naF11.0\naF9.0\naF4.0\naF7.0\naF10.0\naF17.0\naF7.0\naF2.0\naF13.0\naF11.0\naF5.0\naF7.0\naF2.0\naF2.0\naF6.0\naF6.0\naF11.0\naF8.0\naF4.0\naF6.0\naF2.0\naF6.0\naF3.0\naF6.0\naF4.0\naF3.0\naF3.0\naF7.0\naF9.0\naF2.0\naF5.0\naF6.0\naF3.0\naF1.0\naF2.0\naF4.0\naF4.0\naF5.0\naF3.0\naF4.0\naF2.0\naF5.0\naF3.0\naF4.0\naF9.0\naF6.0\naF5.0\naF9.0\naF8.0\naF4.0\naF6.0\naF1.0\naF4.0\naF4.0\naF7.0\naF4.0\naF6.0\naF2.0\naF7.0\naF7.0\naF4.0\naF8.0\naF3.0\naF7.0\naF6.0\naF7.0\naF7.0\naF7.0\naF7.0\naF9.0\naF8.0\naF6.0\naF6.0\naF3.0\naF3.0\naF9.0\naF4.0\naF3.0\naF2.0\naF6.0\naF4.0\naF9.0\naF9.0\naF3.0\naF4.0\naF6.0\naF6.0\naF6.0\naF5.0\naF6.0\naF8.0\naF1.0\naF5.0\naF11.0\naF7.0\naF6.0\naF10.0\naF7.0\naF6.0\naF8.0\naF6.0\naF9.0\naF5.0\naF8.0\naF5.0\naF3.0\naF12.0\naF7.0\naF5.0\naF4.0\naF6.0\naF5.0\naF9.0\naF6.0\naF8.0\naF6.0\naF2.0\naF9.0\naF4.0\naF5.0\naF6.0\naF8.0\naF3.0\naF3.0\naF10.0\naF4.0\naF6.0\naF3.0\naF1.0\naF2.0\naF8.0\naF12.0\naF10.0\naF5.0\naF5.0\naF5.0\naF5.0\naF8.0\naF10.0\naF6.0\naF7.0\naF3.0\naF6.0\naF9.0\naF5.0\naF4.0\naF7.0\naF9.0\naF4.0\naF0.0\naF5.0\naF8.0\naF2.0\naF2.0\naF4.0\naF5.0\naF4.0\naF3.0\naF9.0\naF3.0\naF3.0\naF5.0\naF8.0\naF6.0\naF2.0\naF2.0\naF5.0\naF7.0\naF6.0\naF8.0\naF3.0\naF9.0\naF10.0\naF6.0\naF13.0\naF8.0\naF10.0\naF1.0\naF2.0\naF2.0\naF5.0\naF0.0\naF5.0\naF5.0\naF5.0\naF5.0\naF8.0\naF5.0\naF3.0\naF4.0\naF5.0\naF9.0\naF4.0\naF3.0\naF3.0\naF2.0\naF12.0\naF9.0\naF3.0\naF1.0\naF5.0\naF6.0\naF3.0\naF8.0\naF7.0\naF2.0\naF2.0\naF6.0\naF4.0\naF11.0\naF6.0\naF4.0\naF7.0\naF3.0\naF7.0\naF2.0\naF6.0\naF4.0\naF4.0\naF4.0\naF10.0\naF7.0\naF10.0\naF11.0\naF4.0\naF6.0\naF10.0\naF17.0\naF3.0\naF8.0\naF6.0\naF12.0\naF7.0\naF5.0\naF6.0\naF7.0\naF10.0\naF6.0\naF7.0\naF4.0\naF4.0\naF6.0\naF8.0\naF8.0\naF7.0\naF8.0\naF7.0\naF3.0\naF7.0\naF2.0\naF3.0\naF8.0\naF8.0\naF8.0\naF8.0\naF10.0\naF6.0\naF6.0\naF11.0\naF4.0\naF10.0\naF15.0\naF5.0\naF7.0\naF4.0\naF0.0\naF10.0\naF16.0\naF2.0\naF9.0\naF8.0\naF12.0\naF8.0\naF4.0\naF4.0\naF14.0\naF7.0\naF7.0\naF6.0\naF15.0\naF15.0\naF14.0\naF3.0\naF7.0\naF6.0\naF7.0\naF9.0\naF9.0\naF12.0\naF4.0\naF7.0\naF6.0\naF4.0\naF6.0\naF11.0\naF5.0\naF3.0\naF4.0\naF5.0\naF7.0\naF6.0\naF5.0\naF5.0\naF7.0\naF6.0\naF3.0\naF7.0\naF11.0\naF6.0\naF4.0\naF5.0\naF10.0\naF8.0\naF9.0\naF10.0\naF12.0\naF12.0\naF10.0\naF6.0\naF11.0\naF7.0\naF5.0\naF4.0\naF8.0\naF6.0\naF3.0\naF9.0\naF9.0\naF9.0\naF21.0\naF5.0\naF13.0\naF9.0\naF5.0\naF3.0\naF5.0\naF5.0\naF17.0\naF17.0\naF6.0\naF15.0\naF11.0\naF9.0\naF12.0\naF11.0\naF5.0\naF9.0\naF11.0\naF7.0\naF11.0\naF12.0\naF14.0\naF9.0\naF11.0\naF9.0\naF13.0\naF6.0\naF10.0\naF12.0\naF13.0\naF12.0\naF11.0\naF3.0\naF8.0\naF7.0\naF12.0\naF9.0\naF12.0\naF7.0\naF9.0\naF15.0\naF8.0\naF12.0\naF6.0\naF12.0\naF6.0\naF8.0\naF8.0\naF5.0\naF8.0\naF20.0\naF8.0\naF15.0\naF14.0\naF8.0\naF9.0\naF5.0\naF13.0\naF10.0\naF4.0\naF12.0\naF6.0\naF11.0\naF11.0\naF17.0\naF8.0\naF15.0\naF21.0\naF15.0\naF10.0\naF15.0\naF13.0\naF10.0\naF12.0\naF5.0\naF17.0\naF6.0\naF13.0\naF9.0\naF18.0\naF9.0\naF25.0\naF13.0\naF12.0\naF8.0\naF5.0\naF17.0\naF13.0\naF13.0\naF20.0\naF8.0\naF10.0\naF9.0\naF8.0\naF16.0\naF10.0\naF6.0\naF5.0\naF17.0\naF15.0\naF13.0\naF3.0\naF8.0\naF9.0\naF8.0\naF4.0\naF13.0\naF10.0\naF11.0\naF6.0\naF4.0\naF7.0\naF7.0\naF7.0\naF8.0\naF8.0\naF11.0\naF8.0\naF11.0\naF5.0\naF7.0\naF11.0\naF13.0\naF9.0\naF11.0\naF7.0\naF12.0\naF12.0\naF14.0\naF13.0\naF6.0\naF7.0\naF13.0\naF11.0\naF9.0\naF17.0\naF10.0\naF13.0\naF13.0\naF18.0\naF10.0\naF25.0\naF13.0\naF10.0\naF16.0\naF16.0\naF13.0\naF19.0\naF12.0\naF9.0\naF11.0\naF10.0\naF3.0\naF0.0\naF2.0\naF15.0\naF18.0\naF14.0\naF18.0\naF14.0\naF11.0\naF21.0\naF5.0\naF12.0\naF11.0\naF18.0\naF13.0\naF8.0\naF13.0\naF11.0\naF17.0\naF12.0\naF16.0\naF9.0\naF15.0\naF10.0\naF2.0\naF11.0\naF17.0\naF10.0\naF3.0\naF10.0\naF14.0\naF5.0\naF10.0\naF10.0\naF14.0\naF9.0\naF19.0\naF14.0\naF8.0\naF5.0\naF12.0\naF16.0\naF10.0\naF9.0\naF6.0\naF18.0\naF12.0\naF13.0\naF16.0\naF9.0\naF9.0\naF9.0\naF6.0\naF10.0\naF15.0\naF17.0\naF26.0\naF13.0\naF16.0\naF10.0\naF12.0\naF9.0\naF19.0\naF23.0\naF9.0\naF8.0\naF9.0\naF17.0\naF15.0\naF8.0\naF13.0\naF13.0\naF17.0\naF10.0\naF19.0\naF19.0\naF17.0\naF21.0\naF13.0\naF17.0\naF13.0\naF11.0\naF24.0\naF34.0\naF21.0\naF26.0\naF37.0\naF22.0\naF15.0\naF12.0\naF32.0\naF11.0\naF12.0\naF19.0\naF13.0\naF11.0\naF17.0\naF10.0\naF10.0\naF11.0\naF12.0\naF4.0\naF3.0\naF0.0\naF13.0\naF6.0\naF12.0\naF13.0\naF11.0\naF12.0\naF15.0\naF7.0\naF5.0\naF5.0\naF12.0\naF9.0\naF8.0\naF9.0\naF9.0\naF16.0\naF14.0\naF11.0\naF16.0\naF22.0\naF6.0\naF5.0\naF10.0\naF10.0\naF18.0\naF17.0\naF12.0\naF12.0\naF19.0\naF11.0\naF9.0\naF18.0\naF30.0\naF21.0\naF18.0\naF11.0\naF32.0\naF13.0\naF15.0\naF16.0\naF18.0\naF5.0\naF12.0\naF16.0\naF17.0\naF25.0\naF12.0\naF17.0\naF25.0\naF15.0\naF16.0\naF16.0\naF19.0\naF14.0\naF12.0\naF28.0\naF15.0\naF9.0\naF18.0\naF21.0\naF8.0\naF15.0\naF23.0\naF11.0\naF22.0\naF10.0\naF4.0\naF7.0\naF6.0\naF6.0\naF16.0\naF12.0\naF16.0\naF10.0\naF18.0\naF13.0\naF20.0\naF12.0\naF28.0\naF18.0\naF15.0\naF13.0\naF14.0\naF15.0\naF12.0\naF10.0\naF16.0\naF17.0\naF22.0\naF24.0\naF18.0\naF26.0\naF7.0\naF14.0\naF8.0\naF15.0\naF31.0\naF13.0\naF16.0\naF15.0\naF27.0\naF11.0\naF20.0\naF8.0\naF16.0\naF17.0\naF16.0\naF14.0\naF30.0\naF12.0\naF13.0\naF22.0\naF18.0\naF6.0\naF18.0\naF13.0\naF28.0\naF28.0\naF13.0\naF13.0\naF7.0\naF10.0\naF10.0\naF12.0\naF9.0\naF8.0\naF18.0\naF11.0\naF18.0\naF35.0\naF8.0\naF22.0\naF25.0\naF29.0\naF10.0\naF9.0\naF7.0\naF23.0\naF21.0\naF10.0\naF18.0\naF10.0\naF14.0\naF8.0\naF13.0\naF15.0\naF14.0\naF12.0\naF9.0\naF20.0\naF13.0\naF16.0\naF11.0\naF9.0\naF20.0\naF18.0\naF12.0\naF26.0\naF20.0\naF10.0\naF29.0\naF14.0\naF30.0\naF12.0\naF37.0\naF13.0\naF14.0\naF23.0\naF16.0\naF8.0\naF25.0\naF28.0\naF18.0\naF20.0\naF16.0\naF34.0\naF28.0\naF34.0\naF11.0\naF19.0\naF29.0\naF21.0\naF20.0\naF17.0\naF22.0\naF9.0\naF27.0\naF25.0\naF22.0\naF29.0\naF16.0\naF17.0\naF14.0\naF9.0\naF19.0\naF18.0\naF16.0\naF17.0\naF14.0\naF17.0\naF46.0\naF24.0\naF33.0\naF29.0\naF11.0\naF19.0\naF11.0\naF13.0\naF20.0\naF10.0\naF34.0\naF14.0\naF18.0\naF38.0\naF17.0\naF32.0\naF12.0\naF22.0\naF17.0\naF21.0\naF32.0\naF24.0\naF13.0\naF19.0\naF21.0\naF14.0\naF15.0\naF11.0\naF12.0\naF18.0\naF28.0\naF18.0\naF28.0\naF22.0\naF17.0\naF17.0\naF31.0\naF19.0\naF21.0\naF45.0\naF30.0\naF15.0\naF10.0\naF10.0\naF15.0\naF24.0\naF24.0\naF16.0\naF10.0\naF31.0\naF29.0\naF24.0\naF14.0\naF27.0\naF15.0\naF34.0\naF16.0\naF18.0\naF19.0\naF21.0\naF24.0\naF28.0\naF28.0\naF23.0\naF21.0\naF18.0\naF24.0\naF20.0\naF25.0\naF27.0\naF25.0\naF18.0\naF28.0\naF22.0\naF29.0\naF35.0\naF4.0\naF1.0\naF7.0\naF6.0\naF22.0\naF16.0\naF14.0\naF19.0\naF33.0\naF29.0\naF18.0\naF36.0\naF8.0\naF16.0\naF27.0\naF11.0\naF18.0\naF19.0\naF23.0\naF16.0\naF17.0\naF29.0\naF26.0\naF12.0\naF40.0\naF33.0\naF12.0\naF23.0\naF56.0\naF16.0\naF16.0\naF12.0\naF30.0\naF25.0\naF21.0\naF17.0\naF22.0\naF20.0\naF16.0\naF22.0\naF22.0\naF24.0\naF20.0\naF28.0\naF28.0\naF27.0\naF10.0\naF7.0\naF12.0\naF22.0\naF25.0\naF12.0\naF28.0\naF15.0\naF46.0\naF11.0\naF26.0\naF17.0\naF25.0\naF19.0\naF10.0\naF53.0\naF16.0\naF19.0\naF30.0\naF8.0\naF17.0\naF25.0\naF21.0\naF24.0\naF24.0\naF21.0\naF27.0\naF19.0\naF24.0\naF30.0\naF19.0\naF39.0\naF18.0\naF17.0\naF19.0\naF12.0\naF26.0\naF17.0\naF40.0\naF17.0\naF11.0\naF28.0\naF11.0\naF32.0\naF28.0\naF21.0\naF18.0\naF32.0\naF25.0\naF24.0\naF37.0\naF40.0\naF22.0\naF21.0\naF24.0\naF30.0\naF43.0\naF36.0\naF26.0\naF34.0\naF34.0\naF26.0\naF36.0\naF27.0\naF31.0\naF37.0\naF34.0\naF25.0\naF15.0\naF25.0\naF30.0\naF38.0\naF46.0\naF23.0\naF34.0\naF21.0\naF27.0\naF15.0\naF47.0\naF28.0\naF39.0\naF24.0\naF21.0\naF14.0\naF15.0\naF31.0\naF22.0\naF17.0\naF41.0\naF21.0\naF41.0\naF28.0\naF22.0\naF24.0\naF46.0\naF38.0\naF22.0\naF24.0\naF23.0\naF26.0\naF25.0\naF22.0\naF33.0\naF31.0\naF28.0\naF26.0\naF33.0\naF19.0\naF14.0\naF21.0\naF24.0\naF27.0\naF21.0\naF19.0\naF30.0\naF29.0\naF21.0\naF25.0\naF13.0\naF25.0\naF21.0\naF17.0\naF28.0\naF21.0\naF28.0\naF18.0\naF19.0\naF26.0\naF25.0\naF33.0\naF32.0\naF43.0\naF17.0\naF19.0\naF25.0\naF19.0\naF35.0\naF29.0\naF24.0\naF48.0\naF22.0\naF44.0\naF20.0\naF31.0\naF34.0\naF28.0\naF41.0\naF40.0\naF27.0\naF24.0\naF17.0\naF28.0\naF14.0\naF18.0\naF36.0\naF20.0\naF50.0\naF21.0\naF42.0\naF33.0\naF21.0\naF19.0\naF20.0\naF29.0\naF55.0\naF25.0\naF76.0\naF21.0\naF26.0\naF34.0\naF27.0\naF32.0\naF46.0\naF27.0\naF39.0\naF18.0\naF40.0\naF41.0\naF24.0\naF26.0\naF61.0\naF39.0\naF218.0\naF48.0\naF25.0\naF32.0\naF39.0\naF21.0\naF56.0\naF38.0\naF51.0\naF30.0\naF33.0\naF30.0\naF20.0\naF34.0\naF40.0\naF41.0\naF18.0\naF12.0\naF19.0\naF51.0\naF52.0\naF32.0\naF24.0\naF46.0\naF30.0\naF17.0\naF36.0\naF39.0\naF23.0\naF19.0\naF19.0\naF23.0\naF47.0\naF50.0\naF49.0\naF42.0\naF73.0\naF43.0\naF72.0\naF34.0\naF40.0\naF42.0\naF37.0\naF27.0\naF27.0\naF45.0\naF34.0\naF30.0\naF27.0\naF38.0\naF30.0\naF45.0\naF33.0\naF29.0\naF46.0\naF26.0\naF42.0\naF61.0\naF68.0\naF54.0\naF36.0\naF13.0\naF39.0\naF40.0\naF39.0\naF56.0\naF44.0\naF56.0\naF42.0\naF36.0\naF38.0\naF20.0\naF37.0\naF37.0\naF65.0\naF46.0\naF36.0\naF27.0\naF43.0\naF56.0\naF40.0\naF29.0\naF59.0\naF21.0\naF42.0\naF58.0\naF23.0\naF37.0\naF33.0\naF63.0\naF38.0\naF57.0\naF60.0\naF8.0\naF41.0\naF11.0\naF31.0\naF68.0\naF18.0\naF39.0\naF67.0\naF48.0\naF22.0\naF17.0\naF42.0\naF24.0\naF32.0\naF69.0\naF49.0\naF37.0\naF12.0\naF31.0\naF71.0\naF37.0\naF36.0\naF24.0\naF68.0\naF48.0\naF19.0\naF36.0\naF46.0\naF60.0\naF28.0\naF33.0\naF75.0\naF42.0\naF35.0\naF22.0\naF50.0\naF43.0\naF42.0\naF88.0\naF33.0\naF40.0\naF44.0\naF41.0\naF36.0\naF23.0\naF87.0\naF36.0\naF40.0\naF50.0\naF30.0\naF74.0\naF41.0\naF46.0\naF51.0\naF37.0\naF54.0\naF64.0\naF40.0\naF51.0\naF31.0\naF38.0\naF54.0\naF39.0\naF39.0\naF41.0\naF44.0\naF26.0\naF54.0\naF64.0\naF43.0\naF38.0\naF61.0\naF43.0\naF70.0\naF38.0\naF64.0\naF80.0\naF35.0\naF45.0\naF64.0\naF61.0\naF48.0\naF59.0\naF45.0\naF41.0\naF17.0\naF72.0\naF34.0\naF52.0\naF64.0\naF41.0\naF66.0\naF52.0\naF60.0\naF69.0\naF53.0\naF52.0\naF62.0\naF54.0\naF62.0\naF44.0\naF35.0\naF80.0\naF39.0\naF50.0\naF66.0\naF34.0\naF32.0\naF56.0\naF27.0\naF44.0\naF41.0\naF59.0\naF39.0\naF52.0\naF39.0\naF47.0\naF49.0\naF38.0\naF52.0\naF41.0\naF55.0\naF52.0\naF22.0\naF34.0\naF44.0\naF62.0\naF9.0\naF47.0\naF59.0\naF58.0\naF59.0\naF39.0\naF54.0\naF46.0\naF37.0\naF23.0\naF50.0\naF44.0\naF43.0\naF49.0\naF37.0\naF69.0\naF47.0\naF48.0\naF65.0\naF52.0\naF57.0\naF60.0\naF53.0\naF83.0\naF61.0\naF49.0\naF57.0\naF39.0\naF53.0\naF55.0\naF72.0\naF62.0\naF18.0\naF69.0\naF50.0\naF20.0\naF38.0\naF54.0\naF50.0\naF33.0\naF77.0\naF45.0\naF42.0\naF52.0\naF32.0\naF44.0\naF69.0\naF62.0\naF63.0\naF61.0\naF53.0\naF81.0\naF75.0\naF43.0\naF57.0\naF78.0\naF61.0\naF45.0\naF27.0\naF64.0\naF74.0\naF42.0\naF56.0\naF50.0\naF59.0\naF50.0\naF84.0\naF52.0\naF53.0\naF51.0\naF69.0\naF38.0\naF82.0\naF77.0\naF58.0\naF43.0\naF52.0\naF66.0\naF53.0\naF95.0\naF50.0\naF85.0\naF27.0\naF61.0\naF43.0\naF70.0\naF65.0\naF35.0\naF33.0\naF32.0\naF48.0\naF56.0\naF70.0\naF76.0\naF26.0\naF71.0\naF53.0\naF62.0\naF30.0\naF52.0\naF32.0\naF67.0\naF72.0\naF70.0\naF73.0\naF57.0\naF81.0\naF53.0\naF64.0\naF37.0\naF73.0\naF55.0\naF55.0\naF67.0\naF56.0\naF63.0\naF69.0\naF35.0\naF36.0\naF68.0\naF57.0\naF62.0\naF37.0\naF54.0\naF51.0\naF60.0\naF34.0\naF17.0\naF52.0\naF43.0\naF39.0\naF58.0\naF85.0\naF43.0\naF32.0\naF32.0\naF41.0\naF82.0\naF81.0\naF45.0\naF91.0\naF56.0\naF64.0\naF53.0\naF71.0\naF43.0\naF72.0\naF77.0\naF71.0\naF45.0\naF78.0\naF30.0\naF70.0\naF71.0\naF51.0\naF69.0\naF75.0\naF70.0\naF90.0\naF77.0\naF84.0\naF66.0\naF42.0\naF35.0\naF60.0\naF76.0\naF44.0\naF75.0\naF61.0\naF44.0\naF65.0\naF44.0\naF21.0\naF64.0\naF67.0\naF77.0\naF113.0\naF67.0\naF48.0\naF53.0\naF84.0\naF83.0\naF46.0\naF71.0\naF75.0\naF51.0\naF53.0\naF79.0\naF54.0\naF82.0\naF74.0\naF56.0\naF62.0\naF47.0\naF71.0\naF66.0\naF49.0\naF56.0\naF86.0\naF64.0\naF68.0\naF45.0\naF62.0\naF65.0\naF72.0\naF58.0\naF74.0\naF80.0\naF83.0\naF61.0\naF81.0\naF62.0\naF47.0\naF84.0\naF70.0\naF67.0\naF72.0\naF89.0\naF47.0\naF59.0\naF53.0\naF48.0\naF80.0\naF77.0\naF62.0\naF39.0\naF86.0\naF78.0\naF59.0\naF66.0\naF55.0\naF67.0\naF62.0\naF45.0\naF65.0\naF56.0\naF61.0\naF50.0\naF56.0\naF45.0\naF44.0\naF61.0\naF56.0\naF36.0\naF74.0\naF67.0\naF43.0\naF79.0\naF77.0\naF72.0\naF59.0\naF75.0\naF39.0\naF54.0\naF49.0\naF66.0\naF55.0\naF94.0\naF81.0\naF60.0\naF81.0\naF38.0\naF103.0\naF81.0\naF101.0\naF71.0\naF55.0\naF60.0\naF43.0\naF62.0\naF78.0\naF72.0\naF68.0\naF63.0\naF52.0\naF68.0\naF63.0\naF64.0\naF55.0\naF62.0\naF93.0\naF69.0\naF69.0\naF94.0\naF73.0\naF61.0\naF60.0\naF68.0\naF61.0\naF104.0\naF63.0\naF65.0\naF89.0\naF86.0\naF87.0\naF85.0\naF67.0\naF51.0\naF45.0\naF63.0\naF63.0\naF74.0\naF52.0\naF48.0\naF78.0\naF91.0\naF77.0\naF121.0\naF60.0\naF75.0\naF90.0\naF74.0\naF60.0\naF43.0\naF55.0\naF63.0\naF66.0\naF102.0\naF69.0\naF54.0\naF77.0\naF83.0\naF91.0\naF71.0\naF46.0\naF71.0\naF51.0\naF80.0\naF50.0\naF63.0\naF61.0\naF69.0\naF69.0\naF70.0\naF107.0\naF91.0\naF60.0\naF55.0\naF82.0\naF60.0\naF85.0\naF89.0\naF77.0\naF53.0\naF81.0\naF86.0\naF80.0\naF103.0\naF88.0\naF63.0\naF70.0\naF56.0\naF74.0\naF113.0\naF55.0\naF81.0\naF68.0\naF92.0\naF69.0\naF69.0\naF95.0\naF66.0\naF94.0\naF92.0\naF111.0\naF109.0\naF102.0\naF69.0\naF45.0\naF84.0\naF91.0\naF52.0\naF101.0\naF84.0\naF81.0\naF15.0\naF3.0\naF21.0\naF7.0\naF7.0\naF13.0\naF7.0\naF7.0\naF12.0\naF5.0\naF2.0\naF0.0\naF9.0\naF5.0\naF2.0\naF2.0\naF3.0\naF0.0\naF0.0\naF2.0\naF2.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF1.0\naF3.0\naF2.0\naF0.0\naF2.0\naF2.0\naF2.0\naF1.0\naF11.0\naF4.0\naF12.0\naF0.0\naF2.0\naF1.0\naF1.0\naF1.0\naF8.0\naF2.0\naF4.0\naF6.0\naF4.0\naF3.0\naF4.0\naF7.0\naF6.0\naF14.0\naF5.0\naF11.0\naF5.0\naF6.0\naF8.0\naF11.0\naF18.0\naF5.0\naF10.0\naF21.0\naF25.0\naF3.0\naF5.0\naF6.0\naF4.0\naF5.0\naF4.0\naF7.0\naF28.0\naF10.0\naF5.0\naF50.0\naF24.0\naF31.0\naF58.0\naF32.0\naF42.0\naF40.0\naF14.0\naF93.0\naF107.0\naF61.0\naF66.0\naF43.0\naF79.0\naF56.0\naF38.0\naF69.0\naF71.0\naF76.0\naF91.0\naF87.0\naF88.0\naF78.0\naF89.0\naF81.0\naF92.0\naF76.0\naF85.0\naF93.0\naF68.0\naF68.0\naF74.0\naF85.0\naF89.0\naF37.0\naF103.0\naF95.0\naF73.0\naF103.0\naF79.0\naF81.0\naF90.0\naF105.0\naF93.0\naF98.0\naF86.0\naF62.0\naF106.0\naF82.0\naF55.0\naF64.0\naF55.0\naF72.0\naF62.0\naF105.0\naF92.0\naF80.0\naF101.0\naF49.0\naF79.0\naF104.0\naF52.0\naF77.0\naF108.0\naF78.0\naF57.0\naF93.0\naF50.0\naF62.0\naF89.0\naF64.0\naF107.0\naF115.0\naF76.0\naF255.0\naF101.0\naF78.0\naF124.0\naF94.0\naF117.0\naF108.0\naF119.0\naF85.0\naF118.0\naF104.0\naF74.0\naF42.0\naF77.0\naF89.0\naF121.0\naF96.0\naF93.0\naF95.0\naF111.0\naF96.0\naF109.0\naF101.0\naF165.0\naF117.0\naF94.0\naF77.0\naF79.0\naF197.0\naF105.0\naF81.0\naF114.0\naF114.0\naF26.0\naF71.0\naF86.0\naF102.0\naF56.0\naF106.0\naF79.0\naF135.0\naF68.0\naF114.0\naF98.0\naF113.0\naF96.0\naF57.0\naF97.0\naF82.0\naF104.0\naF155.0\naF83.0\naF68.0\naF282.0\naF77.0\naF79.0\naF89.0\naF242.0\naF73.0\naF81.0\naF95.0\naF132.0\naF71.0\naF105.0\naF110.0\naF34.0\naF29.0\naF2.0\naF10.0\naF21.0\naF57.0\naF36.0\naF78.0\naF71.0\naF125.0\naF89.0\naF107.0\naF119.0\naF81.0\naF45.0\naF37.0\naF86.0\naF42.0\naF81.0\naF40.0\naF97.0\naF106.0\naF69.0\naF118.0\naF170.0\naF74.0\naF115.0\naF87.0\naF163.0\naF115.0\naF86.0\naF161.0\naF195.0\naF79.0\naF81.0\naF112.0\naF84.0\naF263.0\naF93.0\naF60.0\naF104.0\naF75.0\naF106.0\naF116.0\naF83.0\naF120.0\naF124.0\naF99.0\naF98.0\naF166.0\naF106.0\naF97.0\naF120.0\naF90.0\naF220.0\naF79.0\naF116.0\naF84.0\naF109.0\naF146.0\naF80.0\naF119.0\naF145.0\naF104.0\naF82.0\naF87.0\naF69.0\naF72.0\naF121.0\naF82.0\naF89.0\naF75.0\naF70.0\naF87.0\naF93.0\naF176.0\naF144.0\naF118.0\naF111.0\naF109.0\naF76.0\naF104.0\naF240.0\naF132.0\naF100.0\naF101.0\naF98.0\naF188.0\naF113.0\naF146.0\naF80.0\naF180.0\naF106.0\naF105.0\naF88.0\naF142.0\naF120.0\naF105.0\naF140.0\naF124.0\naF265.0\naF124.0\naF153.0\naF81.0\naF115.0\naF130.0\naF66.0\naF84.0\naF55.0\naF110.0\naF113.0\naF178.0\naF101.0\naF119.0\naF107.0\naF60.0\naF90.0\naF125.0\naF91.0\naF98.0\naF58.0\naF99.0\naF121.0\naF231.0\naF103.0\naF91.0\naF122.0\naF80.0\naF103.0\naF103.0\naF155.0\naF111.0\naF127.0\naF119.0\naF111.0\naF123.0\naF166.0\naF134.0\naF250.0\naF202.0\naF159.0\naF143.0\naF84.0\naF174.0\naF86.0\naF125.0\naF204.0\naF80.0\naF74.0\naF282.0\naF98.0\naF101.0\naF95.0\naF172.0\naF94.0\naF241.0\naF187.0\naF240.0\naF172.0\naF95.0\naF207.0\naF153.0\naF164.0\naF115.0\naF183.0\naF112.0\naF59.0\naF132.0\naF73.0\naF80.0\naF88.0\naF321.0\naF112.0\naF177.0\naF109.0\naF225.0\naF157.0\naF87.0\naF334.0\naF68.0\naF104.0\naF109.0\naF96.0\naF156.0\naF96.0\naF234.0\naF83.0\naF86.0\naF105.0\naF142.0\naF74.0\naF139.0\naF120.0\naF123.0\naF124.0\naF92.0\naF113.0\naF131.0\naF76.0\naF125.0\naF219.0\naF150.0\naF91.0\naF68.0\naF133.0\naF231.0\naF271.0\naF99.0\naF168.0\naF141.0\naF125.0\naF232.0\naF179.0\naF126.0\naF102.0\naF96.0\naF115.0\naF135.0\naF167.0\naF62.0\naF178.0\naF146.0\naF113.0\naF317.0\naF223.0\naF178.0\naF141.0\naF246.0\naF144.0\naF76.0\naF95.0\naF139.0\naF122.0\naF271.0\naF198.0\naF151.0\naF73.0\naF144.0\naF266.0\naF269.0\naF256.0\naF159.0\naF247.0\naF159.0\naF206.0\naF301.0\naF114.0\naF144.0\naF206.0\naF83.0\naF95.0\naF92.0\naF205.0\naF176.0\naF95.0\naF145.0\naF61.0\naF85.0\naF251.0\naF310.0\naF138.0\naF242.0\naF158.0\naF86.0\naF164.0\naF144.0\naF339.0\naF121.0\naF265.0\naF119.0\naF157.0\naF81.0\naF103.0\naF112.0\naF114.0\naF90.0\naF119.0\naF123.0\naF69.0\naF103.0\naF280.0\naF99.0\naF191.0\naF299.0\naF210.0\naF130.0\naF112.0\naF70.0\naF192.0\naF326.0\naF331.0\naF124.0\naF76.0\naF122.0\naF149.0\naF132.0\naF301.0\naF138.0\naF153.0\naF233.0\naF160.0\naF207.0\naF123.0\naF135.0\naF105.0\naF67.0\naF226.0\naF216.0\naF261.0\naF75.0\naF102.0\naF342.0\naF122.0\naF231.0\naF158.0\naF242.0\naF236.0\naF157.0\naF266.0\naF141.0\naF359.0\naF161.0\naF38.0\naF207.0\naF353.0\naF165.0\naF331.0\naF202.0\naF192.0\naF194.0\naF275.0\naF100.0\naF284.0\naF336.0\naF193.0\naF226.0\naF114.0\naF261.0\naF221.0\naF220.0\naF118.0\naF146.0\naF113.0\naF158.0\naF206.0\naF215.0\naF117.0\naF320.0\naF277.0\naF169.0\naF176.0\naF61.0\naF145.0\naF144.0\naF290.0\naF236.0\naF178.0\naF149.0\naF265.0\naF129.0\naF240.0\naF316.0\naF260.0\naF221.0\naF111.0\naF176.0\naF22.0\naF5.0\naF65.0\naF60.0\naF61.0\naF172.0\naF159.0\naF173.0\naF119.0\naF240.0\naF212.0\naF215.0\naF109.0\naF95.0\naF104.0\naF184.0\naF127.0\naF151.0\naF158.0\naF165.0\naF165.0\naF180.0\naF119.0\naF274.0\naF142.0\naF47.0\naF256.0\naF118.0\naF167.0\naF129.0\naF116.0\naF102.0\naF127.0\naF109.0\naF215.0\naF130.0\naF151.0\naF276.0\naF117.0\naF199.0\naF20.0\naF5.0\naF106.0\naF308.0\naF123.0\naF148.0\naF183.0\naF279.0\naF105.0\naF85.0\naF164.0\naF211.0\naF119.0\naF224.0\naF176.0\naF263.0\naF147.0\naF281.0\naF171.0\naF243.0\naF174.0\naF279.0\naF310.0\naF298.0\naF81.0\naF38.0\naF301.0\naF236.0\naF130.0\naF290.0\naF324.0\naF101.0\naF279.0\naF272.0\naF85.0\naF258.0\naF248.0\naF295.0\naF305.0\naF233.0\naF269.0\naF133.0\naF252.0\naF175.0\naF350.0\naF147.0\naF334.0\naF213.0\naF128.0\naF260.0\naF322.0\naF172.0\naF211.0\naF278.0\naF100.0\naF223.0\naF229.0\naF312.0\naF106.0\naF286.0\naF198.0\naF274.0\naF256.0\naF237.0\naF217.0\naF279.0\naF237.0\naF98.0\naF232.0\naF253.0\naF289.0\naF263.0\naF113.0\naF204.0\naF228.0\naF216.0\naF179.0\naF219.0\naF227.0\naF218.0\naF252.0\naF110.0\naF374.0\naF150.0\naF289.0\naF222.0\naF255.0\naF217.0\naF300.0\naF393.0\naF264.0\naF193.0\naF233.0\naF256.0\naF385.0\naF248.0\naF131.0\naF292.0\naF271.0\naF188.0\naF253.0\naF259.0\naF203.0\naF313.0\naF283.0\naF249.0\naF276.0\naF304.0\naF221.0\naF289.0\naF191.0\naF317.0\naF245.0\naF238.0\naF254.0\naF161.0\naF133.0\naF195.0\naF253.0\naF363.0\naF285.0\naF194.0\naF214.0\naF270.0\naF375.0\naF254.0\naF129.0\naF183.0\naF225.0\naF182.0\naF331.0\naF131.0\naF312.0\naF286.0\naF212.0\naF236.0\naF245.0\naF154.0\naF386.0\naF285.0\naF235.0\naF147.0\naF336.0\naF170.0\naF389.0\naF300.0\naF176.0\naF140.0\naF252.0\naF181.0\naF339.0\naF244.0\naF281.0\naF217.0\naF268.0\naF387.0\naF337.0\naF326.0\naF286.0\naF249.0\naF206.0\naF229.0\naF399.0\naF199.0\naF251.0\naF235.0\naF362.0\naF288.0\naF371.0\naF252.0\naF324.0\naF377.0\naF336.0\naF331.0\naF300.0\naF271.0\naF180.0\naF69.0\naF199.0\naF280.0\naF346.0\naF413.0\naF139.0\naF310.0\naF227.0\naF338.0\naF314.0\naF265.0\naF372.0\naF214.0\naF403.0\naF255.0\naF257.0\naF180.0\naF220.0\naF399.0\naF333.0\naF372.0\naF365.0\naF284.0\naF259.0\naF114.0\naF87.0\naF237.0\naF281.0\naF164.0\naF325.0\naF128.0\naF152.0\naF242.0\naF313.0\naF116.0\naF76.0\naF93.0\naF233.0\naF349.0\naF212.0\naF252.0\naF265.0\naF333.0\naF363.0\naF320.0\naF282.0\naF218.0\naF192.0\naF275.0\naF325.0\naF259.0\naF277.0\naF201.0\naF368.0\naF283.0\naF261.0\naF279.0\naF262.0\naF249.0\naF316.0\naF386.0\naF335.0\naF217.0\naF268.0\naF298.0\naF296.0\naF358.0\naF388.0\naF233.0\naF375.0\naF328.0\naF202.0\naF182.0\naF406.0\naF172.0\naF284.0\naF224.0\naF333.0\naF373.0\naF317.0\naF400.0\naF299.0\naF324.0\naF347.0\naF297.0\naF194.0\naF326.0\naF340.0\naF410.0\naF288.0\naF289.0\naF205.0\naF306.0\naF308.0\naF400.0\naF283.0\naF304.0\naF385.0\naF226.0\naF285.0\naF292.0\naF306.0\naF295.0\naF360.0\naF398.0\naF345.0\naF226.0\naF248.0\naF353.0\naF285.0\naF309.0\naF375.0\naF226.0\naF236.0\naF274.0\naF293.0\naF338.0\naF297.0\naF188.0\naF277.0\naF363.0\naF227.0\naF357.0\naF202.0\naF282.0\naF288.0\naF374.0\naF329.0\naF142.0\naF261.0\naF273.0\naF338.0\naF364.0\naF253.0\naF391.0\naF355.0\naF330.0\naF309.0\naF275.0\naF396.0\naF281.0\naF342.0\naF139.0\naF343.0\naF251.0\naF281.0\naF230.0\naF278.0\naF253.0\naF296.0\naF352.0\naF303.0\naF366.0\naF303.0\naF264.0\naF191.0\naF206.0\naF213.0\naF321.0\naF410.0\naF296.0\naF343.0\naF408.0\naF288.0\naF211.0\naF376.0\naF314.0\naF283.0\naF392.0\naF180.0\naF284.0\naF122.0\naF364.0\naF206.0\naF228.0\naF216.0\naF365.0\naF353.0\naF226.0\naF248.0\naF237.0\naF232.0\naF317.0\naF189.0\naF376.0\naF302.0\naF157.0\naF313.0\naF343.0\naF311.0\naF404.0\naF270.0\naF387.0\naF275.0\naF396.0\naF408.0\naF286.0\naF379.0\naF321.0\naF303.0\naF403.0\naF176.0\naF407.0\naF382.0\naF375.0\naF339.0\naF346.0\naF229.0\naF307.0\naF244.0\naF344.0\naF313.0\naF410.0\naF201.0\naF89.0\naF339.0\naF257.0\naF305.0\naF200.0\naF301.0\naF200.0\naF297.0\naF184.0\naF375.0\naF377.0\naF308.0\naF247.0\naF399.0\naF399.0\naF415.0\naF306.0\naF264.0\naF323.0\naF343.0\naF285.0\naF273.0\naF389.0\naF338.0\naF354.0\naF327.0\naF382.0\naF333.0\naF314.0\naF382.0\naF412.0\naF329.0\naF212.0\naF325.0\naF249.0\naF302.0\naF319.0\naF380.0\naF389.0\naF405.0\naF324.0\naF374.0\naF314.0\naF402.0\naF385.0\naF210.0\naF273.0\naF361.0\naF357.0\naF374.0\naF242.0\naF343.0\naF270.0\naF322.0\naF382.0\naF267.0\naF363.0\naF306.0\naF323.0\naF314.0\naF399.0\naF207.0\naF406.0\naF313.0\naF351.0\naF342.0\naF357.0\naF171.0\naF350.0\naF315.0\naF317.0\naF200.0\naF376.0\naF358.0\naF383.0\naF177.0\naF202.0\naF300.0\naF350.0\naF338.0\naF402.0\naF182.0\naF338.0\naF367.0\naF300.0\naF248.0\naF329.0\naF375.0\naF301.0\naF348.0\naF355.0\naF358.0\naF358.0\naF384.0\naF305.0\naF274.0\naF312.0\naF255.0\naF274.0\naF150.0\naF305.0\naF392.0\naF354.0\naF316.0\naF291.0\naF362.0\naF296.0\naF371.0\naF333.0\naF378.0\naF349.0\naF339.0\naF340.0\naF281.0\naF363.0\naF405.0\naF262.0\naF335.0\naF313.0\naF284.0\naF194.0\naF368.0\naF376.0\naF381.0\naF378.0\naF409.0\naF440.0\naF299.0\naF378.0\naF322.0\naF290.0\naF392.0\naF291.0\naF328.0\naF401.0\naF391.0\naF315.0\naF320.0\naF417.0\naF431.0\naF237.0\naF341.0\naF375.0\naF422.0\naF369.0\naF287.0\naF397.0\naF356.0\naF408.0\naF389.0\naF345.0\naF404.0\naF410.0\naF402.0\naF214.0\naF410.0\naF274.0\naF368.0\naF328.0\naF337.0\naF349.0\naF363.0\naF344.0\naF385.0\naF391.0\naF387.0\naF382.0\naF225.0\naF363.0\naF122.0\naF279.0\naF329.0\naF400.0\naF282.0\naF374.0\naF334.0\naF373.0\naF299.0\naF401.0\naF400.0\naF342.0\naF414.0\naF264.0\naF414.0\naF374.0\naF171.0\naF381.0\naF232.0\naF391.0\naF314.0\naF414.0\naF382.0\naF300.0\naF348.0\naF353.0\naF408.0\naF373.0\naF299.0\naF355.0\naF326.0\naF209.0\naF402.0\naF181.0\naF210.0\naF425.0\naF315.0\naF412.0\naF388.0\naF353.0\naF324.0\naF417.0\naF317.0\naF351.0\naF403.0\naF406.0\naF377.0\naF282.0\naF404.0\naF391.0\naF415.0\naF425.0\naF397.0\naF397.0\naF393.0\naF330.0\naF356.0\naF410.0\naF405.0\naF157.0\naF270.0\naF330.0\naF362.0\naF302.0\naF364.0\naF417.0\naF404.0\naF415.0\naF424.0\naF320.0\naF352.0\naF252.0\naF413.0\naF404.0\naF355.0\naF361.0\naF397.0\naF394.0\naF227.0\naF317.0\naF363.0\naF424.0\naF351.0\naF164.0\naF412.0\naF398.0\naF318.0\naF259.0\naF366.0\naF278.0\naF395.0\naF358.0\naF413.0\naF337.0\naF397.0\naF398.0\naF373.0\naF225.0\naF283.0\naF421.0\naF359.0\naF397.0\naF327.0\naF297.0\naF386.0\naF424.0\naF313.0\naF398.0\naF424.0\naF371.0\naF367.0\naF424.0\naF294.0\naF404.0\naF420.0\naF409.0\naF366.0\naF330.0\naF324.0\naF373.0\naF350.0\naF386.0\naF344.0\naF373.0\naF227.0\naF365.0\naF384.0\naF283.0\naF377.0\naF345.0\naF408.0\naF374.0\naF409.0\naF383.0\naF421.0\naF412.0\naF309.0\naF436.0\naF252.0\naF314.0\naF379.0\naF354.0\naF416.0\naF251.0\naF301.0\naF378.0\naF414.0\naF254.0\naF398.0\naF326.0\naF373.0\naF394.0\naF417.0\naF398.0\naF281.0\naF384.0\naF381.0\naF375.0\naF425.0\naF389.0\naF291.0\naF373.0\naF364.0\naF405.0\naF344.0\naF380.0\naF292.0\naF278.0\naF234.0\naF364.0\naF373.0\naF395.0\naF396.0\naF415.0\naF413.0\naF408.0\naF408.0\naF296.0\naF313.0\naF206.0\naF319.0\naF298.0\naF365.0\naF411.0\naF420.0\naF325.0\naF381.0\naF395.0\naF330.0\naF421.0\naF728.0\naF387.0\naF397.0\naF392.0\naF362.0\naF204.0\naF304.0\naF428.0\naF355.0\naF423.0\naF303.0\naF329.0\naF392.0\naF379.0\naF405.0\naF380.0\naF393.0\naF409.0\naF428.0\naF400.0\naF385.0\naF402.0\naF421.0\naF394.0\naF262.0\naF346.0\naF254.0\naF391.0\naF308.0\naF65.0\naF417.0\naF402.0\naF422.0\naF303.0\naF374.0\naF411.0\naF409.0\naF262.0\naF283.0\naF369.0\naF340.0\naF417.0\naF386.0\naF410.0\naF398.0\naF423.0\naF407.0\naF419.0\naF370.0\naF343.0\naF347.0\naF388.0\naF396.0\naF410.0\naF358.0\naF420.0\naF346.0\naF68.0\naF382.0\naF441.0\naF404.0\naF276.0\naF423.0\naF406.0\naF330.0\naF385.0\naF392.0\naF369.0\naF372.0\naF322.0\naF414.0\naF421.0\naF248.0\naF428.0\naF418.0\naF344.0\naF332.0\naF425.0\naF315.0\naF383.0\naF384.0\naF386.0\naF252.0\naF424.0\naF401.0\naF423.0\naF338.0\naF412.0\naF379.0\naF220.0\naF342.0\naF442.0\naF433.0\naF387.0\naF407.0\naF406.0\naF417.0\naF421.0\naF351.0\naF337.0\naF399.0\naF406.0\naF401.0\naF277.0\naF421.0\naF419.0\naF392.0\naF458.0\naF413.0\naF293.0\naF385.0\naF406.0\naF254.0\naF416.0\naF434.0\naF398.0\naF415.0\naF360.0\naF412.0\naF418.0\naF223.0\naF400.0\naF360.0\naF406.0\naF369.0\naF398.0\naF420.0\naF851.0\naF330.0\naF432.0\naF423.0\naF365.0\naF425.0\naF317.0\naF359.0\naF378.0\naF417.0\naF364.0\naF340.0\naF425.0\naF376.0\naF223.0\naF349.0\naF425.0\naF420.0\naF420.0\naF228.0\naF415.0\naF355.0\naF344.0\naF354.0\naF403.0\naF146.0\naF425.0\naF412.0\naF377.0\naF412.0\naF399.0\naF416.0\naF373.0\naF329.0\naF356.0\naF452.0\naF316.0\naF387.0\naF328.0\naF400.0\naF334.0\naF395.0\naF375.0\naF208.0\naF408.0\naF382.0\naF399.0\naF383.0\naF387.0\naF402.0\naF349.0\naF376.0\naF361.0\naF306.0\naF414.0\naF400.0\naF162.0\naF278.0\naF418.0\naF415.0\naF424.0\naF414.0\naF410.0\naF329.0\naF407.0\naF410.0\naF421.0\naF385.0\naF349.0\naF420.0\naF404.0\naF330.0\naF329.0\naF407.0\naF294.0\naF388.0\naF772.0\naF398.0\naF404.0\naF417.0\naF435.0\naF416.0\naF379.0\naF426.0\naF357.0\naF397.0\naF206.0\naF379.0\naF262.0\naF423.0\naF335.0\naF394.0\naF242.0\naF367.0\naF386.0\naF329.0\naF405.0\naF408.0\naF387.0\naF389.0\naF428.0\naF410.0\naF360.0\naF377.0\naF363.0\naF399.0\naF382.0\naF375.0\naF365.0\naF413.0\naF307.0\naF385.0\naF354.0\naF405.0\naF324.0\naF345.0\naF411.0\naF428.0\naF427.0\naF416.0\naF375.0\naF428.0\naF411.0\naF329.0\naF308.0\naF160.0\naF374.0\naF428.0\naF426.0\naF190.0\naF395.0\naF414.0\naF396.0\naF424.0\naF311.0\naF233.0\naF396.0\naF424.0\naF424.0\naF394.0\naF340.0\naF381.0\naF425.0\naF427.0\naF461.0\naF400.0\naF315.0\naF399.0\naF414.0\naF366.0\naF349.0\naF395.0\naF373.0\naF473.0\naF424.0\naF418.0\naF383.0\naF634.0\naF305.0\naF374.0\naF425.0\naF397.0\naF400.0\naF330.0\naF253.0\naF409.0\naF352.0\naF620.0\naF427.0\naF423.0\naF459.0\naF393.0\naF404.0\naF419.0\naF398.0\naF413.0\naF409.0\naF265.0\naF410.0\naF419.0\naF413.0\naF297.0\naF427.0\naF309.0\naF392.0\naF409.0\naF388.0\naF478.0\naF391.0\naF333.0\naF398.0\naF407.0\naF428.0\naF417.0\naF270.0\naF425.0\naF366.0\naF412.0\naF399.0\naF404.0\naF391.0\naF384.0\naF376.0\naF366.0\naF353.0\naF392.0\naF424.0\naF367.0\naF378.0\naF408.0\naF428.0\naF401.0\naF401.0\naF396.0\naF425.0\naF388.0\naF315.0\naF297.0\naF413.0\naF328.0\naF117.0\naF347.0\naF316.0\naF363.0\naF435.0\naF407.0\naF316.0\naF386.0\naF371.0\naF386.0\naF194.0\naF415.0\naF530.0\naF402.0\naF334.0\naF210.0\naF396.0\naF396.0\naF428.0\naF381.0\naF428.0\naF383.0\naF362.0\naF94.0\naF415.0\naF418.0\naF399.0\naF394.0\naF366.0\naF387.0\naF533.0\naF428.0\naF444.0\naF307.0\naF378.0\naF285.0\naF377.0\naF386.0\naF353.0\naF424.0\naF166.0\naF389.0\naF417.0\naF420.0\naF425.0\naF150.0\naF412.0\naF377.0\naF366.0\naF390.0\naF409.0\naF428.0\naF336.0\naF256.0\naF368.0\naF390.0\naF414.0\naF530.0\naF347.0\naF435.0\naF356.0\naF335.0\naF248.0\naF114.0\naF234.0\naF437.0\naF404.0\naF403.0\naF720.0\naF416.0\naF292.0\naF389.0\naF403.0\naF416.0\naF830.0\naF431.0\naF312.0\naF355.0\naF424.0\naF414.0\naF425.0\naF399.0\naF411.0\naF414.0\naF423.0\naF408.0\naF290.0\naF402.0\naF413.0\naF423.0\naF347.0\naF365.0\naF344.0\naF428.0\naF424.0\naF420.0\naF435.0\naF435.0\naF339.0\naF359.0\naF391.0\naF348.0\naF375.0\naF424.0\naF388.0\naF404.0\naF310.0\naF383.0\naF268.0\naF307.0\naF414.0\naF90.0\naF410.0\naF376.0\naF307.0\naF201.0\naF124.0\naF390.0\naF275.0\naF417.0\naF409.0\naF428.0\naF656.0\naF357.0\naF428.0\naF220.0\naF358.0\naF418.0\naF313.0\naF399.0\naF381.0\naF403.0\naF359.0\naF394.0\naF227.0\naF421.0\naF431.0\naF435.0\naF284.0\naF418.0\naF383.0\naF363.0\naF332.0\naF428.0\naF276.0\naF334.0\naF409.0\naF417.0\naF426.0\naF355.0\naF417.0\naF382.0\naF410.0\naF340.0\naF388.0\naF412.0\naF385.0\naF437.0\naF313.0\naF388.0\naF437.0\naF422.0\naF392.0\naF405.0\naF415.0\naF315.0\naF420.0\naF364.0\naF306.0\naF216.0\naF377.0\naF289.0\naF409.0\naF296.0\naF360.0\naF428.0\naF348.0\naF393.0\naF321.0\naF116.0\naF76.0\naF402.0\naF394.0\naF107.0\naF376.0\naF428.0\naF332.0\naF422.0\naF322.0\naF391.0\naF220.0\naF425.0\naF405.0\naF317.0\naF406.0\naF409.0\naF367.0\naF394.0\naF406.0\naF418.0\naF331.0\naF413.0\naF425.0\naF428.0\naF349.0\naF391.0\naF610.0\naF357.0\naF395.0\naF428.0\naF475.0\naF156.0\naF393.0\naF667.0\naF427.0\naF298.0\naF402.0\naF385.0\naF436.0\naF406.0\naF386.0\naF427.0\naF200.0\naF393.0\naF428.0\naF402.0\naF425.0\naF414.0\naF354.0\naF275.0\naF299.0\naF482.0\naF408.0\naF373.0\naF445.0\naF281.0\naF422.0\naF406.0\naF419.0\naF411.0\naF416.0\naF241.0\naF359.0\naF347.0\naF383.0\naF406.0\naF384.0\naF327.0\naF421.0\naF376.0\naF410.0\naF363.0\naF857.0\naF126.0\naF139.0\naF324.0\naF427.0\naF427.0\naF398.0\naF428.0\naF184.0\naF347.0\naF428.0\naF370.0\naF427.0\naF348.0\naF418.0\naF139.0\naF436.0\naF365.0\naF407.0\naF408.0\naF287.0\naF406.0\naF401.0\naF377.0\naF248.0\naF318.0\naF267.0\naF326.0\naF348.0\naF361.0\naF193.0\naF401.0\naF382.0\naF419.0\naF417.0\naF436.0\naF258.0\naF386.0\naF344.0\naF428.0\naF379.0\naF424.0\naF94.0\naF306.0\naF434.0\naF413.0\naF467.0\naF342.0\naF149.0\naF427.0\naF428.0\naF412.0\naF402.0\naF104.0\naF448.0\naF256.0\naF351.0\naF380.0\naF367.0\naF415.0\naF428.0\naF424.0\naF402.0\naF408.0\naF410.0\naF437.0\naF420.0\naF422.0\naF424.0\naF421.0\naF395.0\naF515.0\naF263.0\naF327.0\naF372.0\naF377.0\naF414.0\naF268.0\naF338.0\naF419.0\naF413.0\naF390.0\naF410.0\naF369.0\naF343.0\naF414.0\naF268.0\naF417.0\naF425.0\naF416.0\naF413.0\naF315.0\naF441.0\naF398.0\naF204.0\naF402.0\naF423.0\naF361.0\naF422.0\naF384.0\naF405.0\naF385.0\naF440.0\naF182.0\naF406.0\naF428.0\naF322.0\naF384.0\naF417.0\naF403.0\naF118.0\naF412.0\naF331.0\naF415.0\naF387.0\naF409.0\naF411.0\naF418.0\naF390.0\naF413.0\naF200.0\naF112.0\naF413.0\naF407.0\naF428.0\naF283.0\naF388.0\naF431.0\naF423.0\naF418.0\naF424.0\naF416.0\naF424.0\naF417.0\naF411.0\naF411.0\naF428.0\naF393.0\naF220.0\naF371.0\naF413.0\naF276.0\naF428.0\naF375.0\naF428.0\naF344.0\naF399.0\naF381.0\naF411.0\naF344.0\naF416.0\naF422.0\naF423.0\naF325.0\naF108.0\naF424.0\naF338.0\naF389.0\naF428.0\naF398.0\naF393.0\naF428.0\naF405.0\naF306.0\naF425.0\naF313.0\naF791.0\naF275.0\naF301.0\naF423.0\naF424.0\naF225.0\naF406.0\naF310.0\naF459.0\naF380.0\naF416.0\naF399.0\naF412.0\naF428.0\naF420.0\naF401.0\naF423.0\naF420.0\naF412.0\naF448.0\naF423.0\naF446.0\naF385.0\naF357.0\naF770.0\naF428.0\naF285.0\naF412.0\naF458.0\naF195.0\naF667.0\naF424.0\naF352.0\naF156.0\naF398.0\naF92.0\naF428.0\naF266.0\naF419.0\naF424.0\naF821.0\naF342.0\naF412.0\naF345.0\naF379.0\naF384.0\naF407.0\naF435.0\naF434.0\naF462.0\naF387.0\naF415.0\naF405.0\naF414.0\naF302.0\naF328.0\naF431.0\naF393.0\naF393.0\naF208.0\naF769.0\naF371.0\naF402.0\naF419.0\naF418.0\naF377.0\naF415.0\naF380.0\naF348.0\naF415.0\naF119.0\naF109.0\naF381.0\naF448.0\naF432.0\naF411.0\naF431.0\naF429.0\naF369.0\naF424.0\naF263.0\naF346.0\naF428.0\naF425.0\naF388.0\naF398.0\naF420.0\naF314.0\naF431.0\naF125.0\naF394.0\naF413.0\naF352.0\naF292.0\naF405.0\naF421.0\naF416.0\naF389.0\naF410.0\naF336.0\naF365.0\naF421.0\naF397.0\naF348.0\naF428.0\naF406.0\naF406.0\naF416.0\naF408.0\naF300.0\naF393.0\naF432.0\naF420.0\naF109.0\naF424.0\naF399.0\naF390.0\naF392.0\naF428.0\naF369.0\naF424.0\naF355.0\naF428.0\naF413.0\naF402.0\naF375.0\naF417.0\naF425.0\naF397.0\naF424.0\naF420.0\naF406.0\naF358.0\naF437.0\naF421.0\naF812.0\naF420.0\naF422.0\naF417.0\naF366.0\naF408.0\naF444.0\naF131.0\naF431.0\naF381.0\naF342.0\naF421.0\naF122.0\naF420.0\naF449.0\naF415.0\naF390.0\naF416.0\naF416.0\naF412.0\naF401.0\naF333.0\naF369.0\naF412.0\naF393.0\naF428.0\naF859.0\naF405.0\naF123.0\naF297.0\naF325.0\naF420.0\naF810.0\naF338.0\naF400.0\naF409.0\naF427.0\naF432.0\naF421.0\naF422.0\naF427.0\naF194.0\naF428.0\naF410.0\naF373.0\naF283.0\naF405.0\naF385.0\naF406.0\naF413.0\naF380.0\naF427.0\naF424.0\naF397.0\naF389.0\naF420.0\naF153.0\naF375.0\naF408.0\naF365.0\naF390.0\naF331.0\naF460.0\naF400.0\naF412.0\naF428.0\naF421.0\naF416.0\naF370.0\naF414.0\naF334.0\naF380.0\naF242.0\naF369.0\naF340.0\naF401.0\naF428.0\naF338.0\naF198.0\naF626.0\naF253.0\na."
  },
  {
    "path": "dqn/logs_pkls/Breakout_s002.pkl",
    "content": "(lp0\n(I60000\ncnumpy.core.multiarray\nscalar\np1\n(cnumpy\ndtype\np2\n(S'f8'\np3\nI0\nI1\ntp4\nRp5\n(I3\nS'<'\np6\nNNNI-1\nI-1\nI0\ntp7\nbS')\\\\\\x8f\\xc2\\xf5(\\xf8?'\np8\ntp9\nRp10\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xf9?'\np11\ntp12\nRp13\nF4.0\ntp14\na(I70000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\xf9?'\np15\ntp16\nRp17\ng13\nF2.0\ntp18\na(I80000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xf6?'\np19\ntp20\nRp21\ng13\nF0.0\ntp22\na(I90000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\xfa?'\np23\ntp24\nRp25\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7\\xfb?'\np26\ntp27\nRp28\nF3.0\ntp29\na(I100000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\xfb?'\np30\ntp31\nRp32\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xfc?'\np33\ntp34\nRp35\nF4.0\ntp36\na(I110000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\xfa?'\np37\ntp38\nRp39\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\xfc?'\np40\ntp41\nRp42\nF0.0\ntp43\na(I120000\ng1\n(g5\nS'ffffff\\xfa?'\np44\ntp45\nRp46\ng42\nF0.0\ntp47\na(I130000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e\\xfd?'\np48\ntp49\nRp50\ng1\n(g5\nS'ffffff\\xfe?'\np51\ntp52\nRp53\nF0.0\ntp54\na(I140000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xfb?'\np55\ntp56\nRp57\ng1\n(g5\nS'333333\\xff?'\np58\ntp59\nRp60\nF1.0\ntp61\na(I150000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\xf7?'\np62\ntp63\nRp64\ng60\nF0.0\ntp65\na(I160000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\xf6?'\np66\ntp67\nRp68\ng60\nF4.0\ntp69\na(I170000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\xf6?'\np70\ntp71\nRp72\ng60\nF2.0\ntp73\na(I180000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xf9?'\np74\ntp75\nRp76\ng60\nF2.0\ntp77\na(I190000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\xfc?'\np78\ntp79\nRp80\ng60\nF1.0\ntp81\na(I200000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\xfc?'\np82\ntp83\nRp84\ng60\nF6.0\ntp85\na(I210000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x03@'\np86\ntp87\nRp88\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x03@'\np89\ntp90\nRp91\nF8.0\ntp92\na(I220000\ng1\n(g5\nS'ffffff\\x04@'\np93\ntp94\nRp95\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\x04@'\np96\ntp97\nRp98\nF1.0\ntp99\na(I230000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\x04@'\np100\ntp101\nRp102\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\x05@'\np103\ntp104\nRp105\nF3.0\ntp106\na(I240000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\x04@'\np107\ntp108\nRp109\ng105\nF1.0\ntp110\na(I250000\ng1\n(g5\nS'333333\\x07@'\np111\ntp112\nRp113\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\x07@'\np114\ntp115\nRp116\nF0.0\ntp117\na(I260000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\t@'\np118\ntp119\nRp120\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\t@'\np121\ntp122\nRp123\nF4.0\ntp124\na(I270000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x0b@'\np125\ntp126\nRp127\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\x0c@'\np128\ntp129\nRp130\nF0.0\ntp131\na(I280000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\t@'\np132\ntp133\nRp134\ng130\nF1.0\ntp135\na(I290000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\x0e@'\np136\ntp137\nRp138\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\x0e@'\np139\ntp140\nRp141\nF2.0\ntp142\na(I300000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\x10@'\np143\ntp144\nRp145\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\x10@'\np146\ntp147\nRp148\nF2.0\ntp149\na(I310000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x12@'\np150\ntp151\nRp152\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x12@'\np153\ntp154\nRp155\nF7.0\ntp156\na(I320000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\x11@'\np157\ntp158\nRp159\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x13@'\np160\ntp161\nRp162\nF2.0\ntp163\na(I330000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x13@'\np164\ntp165\nRp166\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x13@'\np167\ntp168\nRp169\nF4.0\ntp170\na(I340000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7\\x13@'\np171\ntp172\nRp173\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x14@'\np174\ntp175\nRp176\nF2.0\ntp177\na(I350000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\x13@'\np178\ntp179\nRp180\ng176\nF9.0\ntp181\na(I360000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x12@'\np182\ntp183\nRp184\ng176\nF8.0\ntp185\na(I370000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x11@'\np186\ntp187\nRp188\ng176\nF6.0\ntp189\na(I380000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x11@'\np190\ntp191\nRp192\ng176\nF6.0\ntp193\na(I390000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e\\x11@'\np194\ntp195\nRp196\ng176\nF5.0\ntp197\na(I400000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\\x13@'\np198\ntp199\nRp200\ng176\nF2.0\ntp201\na(I410000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\x14@'\np202\ntp203\nRp204\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\x14@'\np205\ntp206\nRp207\nF3.0\ntp208\na(I420000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x15@'\np209\ntp210\nRp211\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\x15@'\np212\ntp213\nRp214\nF8.0\ntp215\na(I430000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7\\x15@'\np216\ntp217\nRp218\ng1\n(g5\nS'ffffff\\x16@'\np219\ntp220\nRp221\nF3.0\ntp222\na(I440000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x17@'\np223\ntp224\nRp225\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\x17@'\np226\ntp227\nRp228\nF5.0\ntp229\na(I450000\ng1\n(g5\nS'333333\\x19@'\np230\ntp231\nRp232\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\x19@'\np233\ntp234\nRp235\nF4.0\ntp236\na(I460000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\x19@'\np237\ntp238\nRp239\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\x1a@'\np240\ntp241\nRp242\nF3.0\ntp243\na(I470000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x1b@'\np244\ntp245\nRp246\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\x1b@'\np247\ntp248\nRp249\nF6.0\ntp250\na(I480000\ng1\n(g5\nS'ffffff\\x1a@'\np251\ntp252\nRp253\ng249\nF9.0\ntp254\na(I490000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\x1b@'\np255\ntp256\nRp257\ng249\nF7.0\ntp258\na(I500000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e\\x1b@'\np259\ntp260\nRp261\ng249\nF7.0\ntp262\na(I510000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x1a@'\np263\ntp264\nRp265\ng249\nF8.0\ntp266\na(I520000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7\\x19@'\np267\ntp268\nRp269\ng249\nF11.0\ntp270\na(I530000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\x1a@'\np271\ntp272\nRp273\ng249\nF6.0\ntp274\na(I540000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\x1b@'\np275\ntp276\nRp277\ng249\nF7.0\ntp278\na(I550000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\x1c@'\np279\ntp280\nRp281\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x1c@'\np282\ntp283\nRp284\nF4.0\ntp285\na(I560000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7\\x1e@'\np286\ntp287\nRp288\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\x1e@'\np289\ntp290\nRp291\nF3.0\ntp292\na(I570000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\x1f@'\np293\ntp294\nRp295\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\x1f@'\np296\ntp297\nRp298\nF10.0\ntp299\na(I580000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x1f@'\np300\ntp301\nRp302\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f @'\np303\ntp304\nRp305\nF10.0\ntp306\na(I590000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG @'\np307\ntp308\nRp309\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99 @'\np310\ntp311\nRp312\nF6.0\ntp313\na(I600000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5 @'\np314\ntp315\nRp316\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG!@'\np317\ntp318\nRp319\nF19.0\ntp320\na(I610000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z!@'\np321\ntp322\nRp323\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z!@'\np324\ntp325\nRp326\nF8.0\ntp327\na(I620000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14!@'\np328\ntp329\nRp330\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99!@'\np331\ntp332\nRp333\nF17.0\ntp334\na(I630000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u\"@'\np335\ntp336\nRp337\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u\"@'\np338\ntp339\nRp340\nF9.0\ntp341\na(I640000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\"@'\np342\ntp343\nRp344\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8\"@'\np345\ntp346\nRp347\nF5.0\ntp348\na(I650000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\"@'\np349\ntp350\nRp351\ng347\nF10.0\ntp352\na(I660000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\"@'\np353\ntp354\nRp355\ng347\nF7.0\ntp356\na(I670000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc!@'\np357\ntp358\nRp359\ng347\nF5.0\ntp360\na(I680000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL\"@'\np361\ntp362\nRp363\ng347\nF17.0\ntp364\na(I690000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14#@'\np365\ntp366\nRp367\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e#@'\np368\ntp369\nRp370\nF9.0\ntp371\na(I700000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.$@'\np372\ntp373\nRp374\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8$@'\np375\ntp376\nRp377\nF8.0\ntp378\na(I710000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(%@'\np379\ntp380\nRp381\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(%@'\np382\ntp383\nRp384\nF20.0\ntp385\na(I720000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x94&@'\np386\ntp387\nRp388\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x94&@'\np389\ntp390\nRp391\nF15.0\ntp392\na(I730000\ng1\n(g5\nS\"\\xa4p=\\n\\xd7\\xa3'@\"\np393\ntp394\nRp395\ng1\n(g5\nS\"\\xa4p=\\n\\xd7\\xa3'@\"\np396\ntp397\nRp398\nF12.0\ntp399\na(I740000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#)@'\np400\ntp401\nRp402\ng1\n(g5\nS'\\xa4p=\\n\\xd7#)@'\np403\ntp404\nRp405\nF9.0\ntp406\na(I750000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7)@'\np407\ntp408\nRp409\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb)@'\np410\ntp411\nRp412\nF7.0\ntp413\na(I760000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8+@'\np414\ntp415\nRp416\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8+@'\np417\ntp418\nRp419\nF17.0\ntp420\na(I770000\ng1\n(g5\nS'333333,@'\np421\ntp422\nRp423\ng1\n(g5\nS'333333,@'\np424\ntp425\nRp426\nF13.0\ntp427\na(I780000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05-@'\np428\ntp429\nRp430\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05-@'\np431\ntp432\nRp433\nF17.0\ntp434\na(I790000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k-@'\np435\ntp436\nRp437\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x80-@'\np438\ntp439\nRp440\nF12.0\ntp441\na(I800000\ng1\n(g5\nS'33333\\xb3-@'\np442\ntp443\nRp444\ng1\n(g5\nS'33333\\xb3-@'\np445\ntp446\nRp447\nF16.0\ntp448\na(I810000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb.@'\np449\ntp450\nRp451\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb.@'\np452\ntp453\nRp454\nF21.0\ntp455\na(I820000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f0@'\np456\ntp457\nRp458\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f0@'\np459\ntp460\nRp461\nF16.0\ntp462\na(I830000\ng1\n(g5\nS'3333330@'\np463\ntp464\nRp465\ng1\n(g5\nS'\\n\\xd7\\xa3p=J0@'\np466\ntp467\nRp468\nF16.0\ntp469\na(I840000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x001@'\np470\ntp471\nRp472\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x001@'\np473\ntp474\nRp475\nF24.0\ntp476\na(I850000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xee1@'\np477\ntp478\nRp479\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xee1@'\np480\ntp481\nRp482\nF32.0\ntp483\na(I860000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG2@'\np484\ntp485\nRp486\ng1\n(g5\nS'33333s2@'\np487\ntp488\nRp489\nF19.0\ntp490\na(I870000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f2@'\np491\ntp492\nRp493\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f2@'\np494\ntp495\nRp496\nF30.0\ntp497\na(I880000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc2@'\np498\ntp499\nRp500\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc2@'\np501\ntp502\nRp503\nF29.0\ntp504\na(I890000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f3@'\np505\ntp506\nRp507\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f3@'\np508\ntp509\nRp510\nF28.0\ntp511\na(I900000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85+4@'\np512\ntp513\nRp514\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE4@'\np515\ntp516\nRp517\nF6.0\ntp518\na(I910000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x025@'\np519\ntp520\nRp521\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x025@'\np522\ntp523\nRp524\nF33.0\ntp525\na(I920000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x975@'\np526\ntp527\nRp528\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x975@'\np529\ntp530\nRp531\nF18.0\ntp532\na(I930000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfa5@'\np533\ntp534\nRp535\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x176@'\np536\ntp537\nRp538\nF17.0\ntp539\na(I940000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e7@'\np540\ntp541\nRp542\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e7@'\np543\ntp544\nRp545\nF26.0\ntp546\na(I950000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab9@'\np547\ntp548\nRp549\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab9@'\np550\ntp551\nRp552\nF24.0\ntp553\na(I960000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(;@'\np554\ntp555\nRp556\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(;@'\np557\ntp558\nRp559\nF77.0\ntp560\na(I970000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1;@'\np561\ntp562\nRp563\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1;@'\np564\ntp565\nRp566\nF27.0\ntp567\na(I980000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x97<@'\np568\ntp569\nRp570\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e<@'\np571\ntp572\nRp573\nF23.0\ntp574\na(I990000\ng1\n(g5\nS'ffffff>@'\np575\ntp576\nRp577\ng1\n(g5\nS'ffffff>@'\np578\ntp579\nRp580\nF42.0\ntp581\na(I1000000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k?@'\np582\ntp583\nRp584\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k?@'\np585\ntp586\nRp587\nF37.0\ntp588\na(I1010000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB@@'\np589\ntp590\nRp591\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE@@'\np592\ntp593\nRp594\nF20.0\ntp595\na(I1020000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x8e@@'\np596\ntp597\nRp598\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x8e@@'\np599\ntp600\nRp601\nF37.0\ntp602\na(I1030000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQxA@'\np603\ntp604\nRp605\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQxA@'\np606\ntp607\nRp608\nF58.0\ntp609\na(I1040000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xe7A@'\np610\ntp611\nRp612\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xeeA@'\np613\ntp614\nRp615\nF34.0\ntp616\na(I1050000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xefA@'\np617\ntp618\nRp619\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x0eB@'\np620\ntp621\nRp622\nF36.0\ntp623\na(I1060000\ng1\n(g5\nS'33333\\x93B@'\np624\ntp625\nRp626\ng1\n(g5\nS'33333\\x93B@'\np627\ntp628\nRp629\nF25.0\ntp630\na(I1070000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0cC@'\np631\ntp632\nRp633\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(<C@'\np634\ntp635\nRp636\nF18.0\ntp637\na(I1080000\ng1\n(g5\nS'fffff\\x06D@'\np638\ntp639\nRp640\ng1\n(g5\nS'fffff\\x06D@'\np641\ntp642\nRp643\nF47.0\ntp644\na(I1090000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99YD@'\np645\ntp646\nRp647\ng1\n(g5\nS'=\\n\\xd7\\xa3p]D@'\np648\ntp649\nRp650\nF29.0\ntp651\na(I1100000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00`D@'\np652\ntp653\nRp654\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x90D@'\np655\ntp656\nRp657\nF15.0\ntp658\na(I1110000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1cE@'\np659\ntp660\nRp661\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1cE@'\np662\ntp663\nRp664\nF54.0\ntp665\na(I1120000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xa5E@'\np666\ntp667\nRp668\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xa5E@'\np669\ntp670\nRp671\nF30.0\ntp672\na(I1130000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x1aF@'\np673\ntp674\nRp675\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb1F@'\np676\ntp677\nRp678\nF41.0\ntp679\na(I1140000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xb4F@'\np680\ntp681\nRp682\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xb4F@'\np683\ntp684\nRp685\nF50.0\ntp686\na(I1150000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x87F@'\np687\ntp688\nRp689\ng685\nF52.0\ntp690\na(I1160000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xdeF@'\np691\ntp692\nRp693\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xdeF@'\np694\ntp695\nRp696\nF49.0\ntp697\na(I1170000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85G@'\np698\ntp699\nRp700\ng1\n(g5\nS'33333\\x93G@'\np701\ntp702\nRp703\nF43.0\ntp704\na(I1180000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x98G@'\np705\ntp706\nRp707\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xcbG@'\np708\ntp709\nRp710\nF38.0\ntp711\na(I1190000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xb9G@'\np712\ntp713\nRp714\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf8G@'\np715\ntp716\nRp717\nF46.0\ntp718\na(I1200000\ng1\n(g5\nS'=\\n\\xd7\\xa3p]H@'\np719\ntp720\nRp721\ng1\n(g5\nS'=\\n\\xd7\\xa3p]H@'\np722\ntp723\nRp724\nF65.0\ntp725\na(I1210000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa1H@'\np726\ntp727\nRp728\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xa7H@'\np729\ntp730\nRp731\nF47.0\ntp732\na(I1220000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x10I@'\np733\ntp734\nRp735\ng1\n(g5\nS'\\n\\xd7\\xa3p=*I@'\np736\ntp737\nRp738\nF67.0\ntp739\na(I1230000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGAI@'\np740\ntp741\nRp742\ng1\n(g5\nS'q=\\n\\xd7\\xa3PI@'\np743\ntp744\nRp745\nF44.0\ntp746\na(I1240000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xeaH@'\np747\ntp748\nRp749\ng745\nF50.0\ntp750\na(I1250000\ng1\n(g5\nS'33333\\x93H@'\np751\ntp752\nRp753\ng745\nF37.0\ntp754\na(I1260000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2H@'\np755\ntp756\nRp757\ng745\nF75.0\ntp758\na(I1270000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xaaI@'\np759\ntp760\nRp761\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xaaI@'\np762\ntp763\nRp764\nF51.0\ntp765\na(I1280000\ng1\n(g5\nS'\\xd7\\xa3p=\\nwI@'\np766\ntp767\nRp768\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x03J@'\np769\ntp770\nRp771\nF35.0\ntp772\na(I1290000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\/I@'\np773\ntp774\nRp775\ng771\nF52.0\ntp776\na(I1300000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xabI@'\np777\ntp778\nRp779\ng771\nF44.0\ntp780\na(I1310000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xb9I@'\np781\ntp782\nRp783\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x08J@'\np784\ntp785\nRp786\nF26.0\ntp787\na(I1320000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd4I@'\np788\ntp789\nRp790\ng786\nF57.0\ntp791\na(I1330000\ng1\n(g5\nS'33333\\xb3I@'\np792\ntp793\nRp794\ng786\nF33.0\ntp795\na(I1340000\ng1\n(g5\nS'33333\\xf3I@'\np796\ntp797\nRp798\ng786\nF63.0\ntp799\na(I1350000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^J@'\np800\ntp801\nRp802\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^J@'\np803\ntp804\nRp805\nF56.0\ntp806\na(I1360000\ng1\n(g5\nS'\\xd7\\xa3p=\\nwJ@'\np807\ntp808\nRp809\ng1\n(g5\nS'\\xd7\\xa3p=\\nwJ@'\np810\ntp811\nRp812\nF58.0\ntp813\na(I1370000\ng1\n(g5\nS'\\n\\xd7\\xa3p=jK@'\np814\ntp815\nRp816\ng1\n(g5\nS'\\n\\xd7\\xa3p=jK@'\np817\ntp818\nRp819\nF73.0\ntp820\na(I1380000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xf7K@'\np821\ntp822\nRp823\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\nL@'\np824\ntp825\nRp826\nF60.0\ntp827\na(I1390000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85KL@'\np828\ntp829\nRp830\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85KL@'\np831\ntp832\nRp833\nF75.0\ntp834\na(I1400000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xd9L@'\np835\ntp836\nRp837\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xf9L@'\np838\ntp839\nRp840\nF40.0\ntp841\na(I1410000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@M@'\np842\ntp843\nRp844\ng1\n(g5\nS'{\\x14\\xaeG\\xe1ZM@'\np845\ntp846\nRp847\nF57.0\ntp848\na(I1420000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8M@'\np849\ntp850\nRp851\ng847\nF60.0\ntp852\na(I1430000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5hM@'\np853\ntp854\nRp855\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x80M@'\np856\ntp857\nRp858\nF81.0\ntp859\na(I1440000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xecM@'\np860\ntp861\nRp862\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xecM@'\np863\ntp864\nRp865\nF71.0\ntp866\na(I1450000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eeN@'\np867\ntp868\nRp869\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eeN@'\np870\ntp871\nRp872\nF72.0\ntp873\na(I1460000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xaaN@'\np874\ntp875\nRp876\ng1\n(g5\nS'33333\\xb3N@'\np877\ntp878\nRp879\nF61.0\ntp880\na(I1470000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x17O@'\np881\ntp882\nRp883\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eEO@'\np884\ntp885\nRp886\nF119.0\ntp887\na(I1480000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xe0O@'\np888\ntp889\nRp890\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xe0O@'\np891\ntp892\nRp893\nF99.0\ntp894\na(I1490000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x1eP@'\np895\ntp896\nRp897\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x1eP@'\np898\ntp899\nRp900\nF59.0\ntp901\na(I1500000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xa4P@'\np902\ntp903\nRp904\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xb1P@'\np905\ntp906\nRp907\nF52.0\ntp908\na(I1510000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8nP@'\np909\ntp910\nRp911\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xc9P@'\np912\ntp913\nRp914\nF35.0\ntp915\na(I1520000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7M@'\np916\ntp917\nRp918\ng914\nF7.0\ntp919\na(I1530000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xddI@'\np920\ntp921\nRp922\ng914\nF41.0\ntp923\na(I1540000\ng1\n(g5\nS'\\n\\xd7\\xa3p=jJ@'\np924\ntp925\nRp926\ng914\nF85.0\ntp927\na(I1550000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1ZJ@'\np928\ntp929\nRp930\ng914\nF83.0\ntp931\na(I1560000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8J@'\np932\ntp933\nRp934\ng914\nF71.0\ntp935\na(I1570000\ng1\n(g5\nS'\\n\\xd7\\xa3p=JJ@'\np936\ntp937\nRp938\ng914\nF63.0\ntp939\na(I1580000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\/F@'\np940\ntp941\nRp942\ng914\nF57.0\ntp943\na(I1590000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xe3C@'\np944\ntp945\nRp946\ng914\nF28.0\ntp947\na(I1600000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xceA@'\np948\ntp949\nRp950\ng914\nF5.0\ntp951\na(I1610000\ng1\n(g5\nS'\\xa4p=\\n\\xd7cC@'\np952\ntp953\nRp954\ng914\nF72.0\ntp955\na(I1620000\ng1\n(g5\nS\"H\\xe1z\\x14\\xae'D@\"\np956\ntp957\nRp958\ng914\nF2.0\ntp959\na(I1630000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xaeC@'\np960\ntp961\nRp962\ng914\nF59.0\ntp963\na(I1640000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xa0C@'\np964\ntp965\nRp966\ng914\nF55.0\ntp967\na(I1650000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba>@'\np968\ntp969\nRp970\ng914\nF1.0\ntp971\na(I1660000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc-@'\np972\ntp973\nRp974\ng914\nF11.0\ntp975\na(I1670000\ng1\n(g5\nS\"\\xcd\\xcc\\xcc\\xcc\\xccL'@\"\np976\ntp977\nRp978\ng914\nF49.0\ntp979\na(I1680000\ng1\n(g5\nS\"\\x14\\xaeG\\xe1z\\x94'@\"\np980\ntp981\nRp982\ng914\nF68.0\ntp983\na(I1690000\ng1\n(g5\nS'ffffff,@'\np984\ntp985\nRp986\ng914\nF3.0\ntp987\na(I1700000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k1@'\np988\ntp989\nRp990\ng914\nF69.0\ntp991\na(I1710000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np992\ntp993\nRp994\ng914\nF24.0\ntp995\na(I1720000\ng1\n(g5\nS'\\n\\xd7\\xa3p=J9@'\np996\ntp997\nRp998\ng914\nF52.0\ntp999\na(I1730000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa>@'\np1000\ntp1001\nRp1002\ng914\nF84.0\ntp1003\na(I1740000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8~A@'\np1004\ntp1005\nRp1006\ng914\nF57.0\ntp1007\na(I1750000\ng1\n(g5\nS'fffff\\xc6C@'\np1008\ntp1009\nRp1010\ng914\nF87.0\ntp1011\na(I1760000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8aE@'\np1012\ntp1013\nRp1014\ng914\nF32.0\ntp1015\na(I1770000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8A@'\np1016\ntp1017\nRp1018\ng914\nF59.0\ntp1019\na(I1780000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^C@'\np1020\ntp1021\nRp1022\ng914\nF59.0\ntp1023\na(I1790000\ng1\n(g5\nS'\\xa4p=\\n\\xd7CD@'\np1024\ntp1025\nRp1026\ng914\nF71.0\ntp1027\na(I1800000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xf4@@'\np1028\ntp1029\nRp1030\ng914\nF2.0\ntp1031\na(I1810000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe85@'\np1032\ntp1033\nRp1034\ng914\nF46.0\ntp1035\na(I1820000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z8@'\np1036\ntp1037\nRp1038\ng914\nF52.0\ntp1039\na(I1830000\ng1\n(g5\nS'ffffff<@'\np1040\ntp1041\nRp1042\ng914\nF52.0\ntp1043\na(I1840000\ng1\n(g5\nS'ffffff@@'\np1044\ntp1045\nRp1046\ng914\nF62.0\ntp1047\na(I1850000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa?@'\np1048\ntp1049\nRp1050\ng914\nF73.0\ntp1051\na(I1860000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:?@'\np1052\ntp1053\nRp1054\ng914\nF104.0\ntp1055\na(I1870000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ?@'\np1056\ntp1057\nRp1058\ng914\nF20.0\ntp1059\na(I1880000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00 B@'\np1060\ntp1061\nRp1062\ng914\nF89.0\ntp1063\na(I1890000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}D@'\np1064\ntp1065\nRp1066\ng914\nF55.0\ntp1067\na(I1900000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x08G@'\np1068\ntp1069\nRp1070\ng914\nF48.0\ntp1071\na(I1910000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5hI@'\np1072\ntp1073\nRp1074\ng914\nF41.0\ntp1075\na(I1920000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xdeJ@'\np1076\ntp1077\nRp1078\ng914\nF51.0\ntp1079\na(I1930000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xebH@'\np1080\ntp1081\nRp1082\ng914\nF5.0\ntp1083\na(I1940000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xb1J@'\np1084\ntp1085\nRp1086\ng914\nF93.0\ntp1087\na(I1950000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xdaK@'\np1088\ntp1089\nRp1090\ng914\nF67.0\ntp1091\na(I1960000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xd0K@'\np1092\ntp1093\nRp1094\ng914\nF4.0\ntp1095\na(I1970000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xfeI@'\np1096\ntp1097\nRp1098\ng914\nF18.0\ntp1099\na(I1980000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=J@'\np1100\ntp1101\nRp1102\ng914\nF86.0\ntp1103\na(I1990000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbdG@'\np1104\ntp1105\nRp1106\ng914\nF49.0\ntp1107\na(I2000000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.G@'\np1108\ntp1109\nRp1110\ng914\nF23.0\ntp1111\na(I2010000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85kF@'\np1112\ntp1113\nRp1114\ng914\nF51.0\ntp1115\na(I2020000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x07F@'\np1116\ntp1117\nRp1118\ng914\nF103.0\ntp1119\na(I2030000\ng1\n(g5\nS'\\xa4p=\\n\\xd7CF@'\np1120\ntp1121\nRp1122\ng914\nF63.0\ntp1123\na(I2040000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00E@'\np1124\ntp1125\nRp1126\ng914\nF10.0\ntp1127\na(I2050000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\"D@'\np1128\ntp1129\nRp1130\ng914\nF79.0\ntp1131\na(I2060000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5hF@'\np1132\ntp1133\nRp1134\ng914\nF68.0\ntp1135\na(I2070000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2UG@'\np1136\ntp1137\nRp1138\ng914\nF1.0\ntp1139\na(I2080000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xcbG@'\np1140\ntp1141\nRp1142\ng914\nF13.0\ntp1143\na(I2090000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1ZE@'\np1144\ntp1145\nRp1146\ng914\nF41.0\ntp1147\na(I2100000\ng1\n(g5\nS'H\\xe1z\\x14\\xaegE@'\np1148\ntp1149\nRp1150\ng914\nF96.0\ntp1151\na(I2110000\ng1\n(g5\nS\"H\\xe1z\\x14\\xae'G@\"\np1152\ntp1153\nRp1154\ng914\nF59.0\ntp1155\na(I2120000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1zG@'\np1156\ntp1157\nRp1158\ng914\nF47.0\ntp1159\na(I2130000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xa5F@'\np1160\ntp1161\nRp1162\ng914\nF95.0\ntp1163\na(I2140000\ng1\n(g5\nS'\\xa4p=\\n\\xd7cG@'\np1164\ntp1165\nRp1166\ng914\nF64.0\ntp1167\na(I2150000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x95F@'\np1168\ntp1169\nRp1170\ng914\nF126.0\ntp1171\na(I2160000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8~E@'\np1172\ntp1173\nRp1174\ng914\nF63.0\ntp1175\na(I2170000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85KE@'\np1176\ntp1177\nRp1178\ng914\nF56.0\ntp1179\na(I2180000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x8bG@'\np1180\ntp1181\nRp1182\ng914\nF77.0\ntp1183\na(I2190000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc7J@'\np1184\ntp1185\nRp1186\ng914\nF50.0\ntp1187\na(I2200000\ng1\n(g5\nS'\\xd7\\xa3p=\\nwL@'\np1188\ntp1189\nRp1190\ng914\nF94.0\ntp1191\na(I2210000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9eL@'\np1192\ntp1193\nRp1194\ng914\nF53.0\ntp1195\na(I2220000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc7K@'\np1196\ntp1197\nRp1198\ng914\nF47.0\ntp1199\na(I2230000\ng1\n(g5\nS'33333\\x13K@'\np1200\ntp1201\nRp1202\ng914\nF62.0\ntp1203\na(I2240000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fBK@'\np1204\ntp1205\nRp1206\ng914\nF73.0\ntp1207\na(I2250000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^J@'\np1208\ntp1209\nRp1210\ng914\nF83.0\ntp1211\na(I2260000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0cK@'\np1212\ntp1213\nRp1214\ng914\nF53.0\ntp1215\na(I2270000\ng1\n(g5\nS'fffff\\x86L@'\np1216\ntp1217\nRp1218\ng914\nF85.0\ntp1219\na(I2280000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xc1L@'\np1220\ntp1221\nRp1222\ng914\nF74.0\ntp1223\na(I2290000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x94I@'\np1224\ntp1225\nRp1226\ng914\nF47.0\ntp1227\na(I2300000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG!I@'\np1228\ntp1229\nRp1230\ng914\nF94.0\ntp1231\na(I2310000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGaJ@'\np1232\ntp1233\nRp1234\ng914\nF127.0\ntp1235\na(I2320000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x10K@'\np1236\ntp1237\nRp1238\ng914\nF71.0\ntp1239\na(I2330000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc,L@'\np1240\ntp1241\nRp1242\ng914\nF54.0\ntp1243\na(I2340000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbdN@'\np1244\ntp1245\nRp1246\ng914\nF67.0\ntp1247\na(I2350000\ng1\n(g5\nS'ffffffO@'\np1248\ntp1249\nRp1250\ng914\nF73.0\ntp1251\na(I2360000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85{P@'\np1252\ntp1253\nRp1254\ng914\nF26.0\ntp1255\na(I2370000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGAP@'\np1256\ntp1257\nRp1258\ng914\nF88.0\ntp1259\na(I2380000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f2P@'\np1260\ntp1261\nRp1262\ng914\nF7.0\ntp1263\na(I2390000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8P@'\np1264\ntp1265\nRp1266\ng914\nF57.0\ntp1267\na(I2400000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xc4P@'\np1268\ntp1269\nRp1270\ng914\nF34.0\ntp1271\na(I2410000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\_Q@'\np1272\ntp1273\nRp1274\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x8aQ@'\np1275\ntp1276\nRp1277\nF3.0\ntp1278\na(I2420000\ng1\n(g5\nS'H\\xe1z\\x14\\xaegQ@'\np1279\ntp1280\nRp1281\ng1277\nF68.0\ntp1282\na(I2430000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x0bR@'\np1283\ntp1284\nRp1285\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x0bR@'\np1286\ntp1287\nRp1288\nF283.0\ntp1289\na(I2440000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xe1Q@'\np1290\ntp1291\nRp1292\ng1288\nF102.0\ntp1293\na(I2450000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x88Q@'\np1294\ntp1295\nRp1296\ng1288\nF117.0\ntp1297\na(I2460000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xdeP@'\np1298\ntp1299\nRp1300\ng1288\nF49.0\ntp1301\na(I2470000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x90O@'\np1302\ntp1303\nRp1304\ng1288\nF40.0\ntp1305\na(I2480000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x13P@'\np1306\ntp1307\nRp1308\ng1288\nF20.0\ntp1309\na(I2490000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zTQ@'\np1310\ntp1311\nRp1312\ng1288\nF114.0\ntp1313\na(I2500000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG1R@'\np1314\ntp1315\nRp1316\ng1\n(g5\nS'\\xe1z\\x14\\xaeG1R@'\np1317\ntp1318\nRp1319\nF44.0\ntp1320\na(I2510000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}R@'\np1321\ntp1322\nRp1323\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xbaR@'\np1324\ntp1325\nRp1326\nF88.0\ntp1327\na(I2520000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xd3R@'\np1328\ntp1329\nRp1330\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xd7R@'\np1331\ntp1332\nRp1333\nF65.0\ntp1334\na(I2530000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xa7R@'\np1335\ntp1336\nRp1337\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xdaR@'\np1338\ntp1339\nRp1340\nF100.0\ntp1341\na(I2540000\ng1\n(g5\nS'\\n\\xd7\\xa3p=jS@'\np1342\ntp1343\nRp1344\ng1\n(g5\nS'\\n\\xd7\\xa3p=jS@'\np1345\ntp1346\nRp1347\nF87.0\ntp1348\na(I2550000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x87S@'\np1349\ntp1350\nRp1351\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x8dS@'\np1352\ntp1353\nRp1354\nF71.0\ntp1355\na(I2560000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00S@'\np1356\ntp1357\nRp1358\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x92S@'\np1359\ntp1360\nRp1361\nF36.0\ntp1362\na(I2570000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeGR@'\np1363\ntp1364\nRp1365\ng1361\nF65.0\ntp1366\na(I2580000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z$R@'\np1367\ntp1368\nRp1369\ng1361\nF104.0\ntp1370\na(I2590000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00PR@'\np1371\ntp1372\nRp1373\ng1361\nF62.0\ntp1374\na(I2600000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@S@'\np1375\ntp1376\nRp1377\ng1361\nF100.0\ntp1378\na(I2610000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xa0S@'\np1379\ntp1380\nRp1381\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xb2S@'\np1382\ntp1383\nRp1384\nF51.0\ntp1385\na(I2620000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xb9R@'\np1386\ntp1387\nRp1388\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xb9S@'\np1389\ntp1390\nRp1391\nF111.0\ntp1392\na(I2630000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xbeR@'\np1393\ntp1394\nRp1395\ng1391\nF35.0\ntp1396\na(I2640000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85KR@'\np1397\ntp1398\nRp1399\ng1391\nF41.0\ntp1400\na(I2650000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x8dR@'\np1401\ntp1402\nRp1403\ng1391\nF35.0\ntp1404\na(I2660000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xf2Q@'\np1405\ntp1406\nRp1407\ng1391\nF91.0\ntp1408\na(I2670000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xc0R@'\np1409\ntp1410\nRp1411\ng1391\nF137.0\ntp1412\na(I2680000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xd9S@'\np1413\ntp1414\nRp1415\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xecS@'\np1416\ntp1417\nRp1418\nF82.0\ntp1419\na(I2690000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\\\T@'\np1420\ntp1421\nRp1422\ng1\n(g5\nS'\\xe1z\\x14\\xaeGqT@'\np1423\ntp1424\nRp1425\nF37.0\ntp1426\na(I2700000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2T@'\np1427\ntp1428\nRp1429\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xffT@'\np1430\ntp1431\nRp1432\nF54.0\ntp1433\na(I2710000\ng1\n(g5\nS'fffff\\x16U@'\np1434\ntp1435\nRp1436\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8U@'\np1437\ntp1438\nRp1439\nF45.0\ntp1440\na(I2720000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x05U@'\np1441\ntp1442\nRp1443\ng1439\nF72.0\ntp1444\na(I2730000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x8bU@'\np1445\ntp1446\nRp1447\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x9eU@'\np1448\ntp1449\nRp1450\nF124.0\ntp1451\na(I2740000\ng1\n(g5\nS'333333U@'\np1452\ntp1453\nRp1454\ng1450\nF126.0\ntp1455\na(I2750000\ng1\n(g5\nS'q=\\n\\xd7\\xa3@U@'\np1456\ntp1457\nRp1458\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xc8U@'\np1459\ntp1460\nRp1461\nF91.0\ntp1462\na(I2760000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:V@'\np1463\ntp1464\nRp1465\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:V@'\np1466\ntp1467\nRp1468\nF122.0\ntp1469\na(I2770000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcclV@'\np1470\ntp1471\nRp1472\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8frV@'\np1473\ntp1474\nRp1475\nF82.0\ntp1476\na(I2780000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2V@'\np1477\ntp1478\nRp1479\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2V@'\np1480\ntp1481\nRp1482\nF120.0\ntp1483\na(I2790000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xb7W@'\np1484\ntp1485\nRp1486\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xb7W@'\np1487\ntp1488\nRp1489\nF86.0\ntp1490\na(I2800000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xc3W@'\np1491\ntp1492\nRp1493\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xceW@'\np1494\ntp1495\nRp1496\nF137.0\ntp1497\na(I2810000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x1bW@'\np1498\ntp1499\nRp1500\ng1496\nF227.0\ntp1501\na(I2820000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xaaV@'\np1502\ntp1503\nRp1504\ng1496\nF35.0\ntp1505\na(I2830000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(,V@'\np1506\ntp1507\nRp1508\ng1496\nF115.0\ntp1509\na(I2840000\ng1\n(g5\nS'fffff\\xf6V@'\np1510\ntp1511\nRp1512\ng1496\nF177.0\ntp1513\na(I2850000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x08W@'\np1514\ntp1515\nRp1516\ng1496\nF235.0\ntp1517\na(I2860000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#V@'\np1518\ntp1519\nRp1520\ng1496\nF30.0\ntp1521\na(I2870000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x17V@'\np1522\ntp1523\nRp1524\ng1496\nF110.0\ntp1525\na(I2880000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8aT@'\np1526\ntp1527\nRp1528\ng1496\nF72.0\ntp1529\na(I2890000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xf2T@'\np1530\ntp1531\nRp1532\ng1496\nF80.0\ntp1533\na(I2900000\ng1\n(g5\nS\"H\\xe1z\\x14\\xae'V@\"\np1534\ntp1535\nRp1536\ng1496\nF139.0\ntp1537\na(I2910000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x15V@'\np1538\ntp1539\nRp1540\ng1496\nF81.0\ntp1541\na(I2920000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xdcU@'\np1542\ntp1543\nRp1544\ng1496\nF113.0\ntp1545\na(I2930000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGAV@'\np1546\ntp1547\nRp1548\ng1496\nF100.0\ntp1549\na(I2940000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x03V@'\np1550\ntp1551\nRp1552\ng1496\nF116.0\ntp1553\na(I2950000\ng1\n(g5\nS'fffff&W@'\np1554\ntp1555\nRp1556\ng1496\nF177.0\ntp1557\na(I2960000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQxW@'\np1558\ntp1559\nRp1560\ng1496\nF88.0\ntp1561\na(I2970000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGQW@'\np1562\ntp1563\nRp1564\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xd2W@'\np1565\ntp1566\nRp1567\nF116.0\ntp1568\na(I2980000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xbaV@'\np1569\ntp1570\nRp1571\ng1567\nF148.0\ntp1572\na(I2990000\ng1\n(g5\nS'\\xd7\\xa3p=\\ngW@'\np1573\ntp1574\nRp1575\ng1567\nF38.0\ntp1576\na(I3000000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x8cW@'\np1577\ntp1578\nRp1579\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xebW@'\np1580\ntp1581\nRp1582\nF73.0\ntp1583\na(I3010000\ng1\n(g5\nS'fffff\\xa6W@'\np1584\ntp1585\nRp1586\ng1582\nF93.0\ntp1587\na(I3020000\ng1\n(g5\nS'33333sX@'\np1588\ntp1589\nRp1590\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9eX@'\np1591\ntp1592\nRp1593\nF49.0\ntp1594\na(I3030000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xf0X@'\np1595\ntp1596\nRp1597\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xf0X@'\np1598\ntp1599\nRp1600\nF81.0\ntp1601\na(I3040000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xe9W@'\np1602\ntp1603\nRp1604\ng1\n(g5\nS'33333SY@'\np1605\ntp1606\nRp1607\nF10.0\ntp1608\na(I3050000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^X@'\np1609\ntp1610\nRp1611\ng1607\nF58.0\ntp1612\na(I3060000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9eW@'\np1613\ntp1614\nRp1615\ng1607\nF163.0\ntp1616\na(I3070000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x7fW@'\np1617\ntp1618\nRp1619\ng1607\nF9.0\ntp1620\na(I3080000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x95X@'\np1621\ntp1622\nRp1623\ng1607\nF153.0\ntp1624\na(I3090000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb!Y@'\np1625\ntp1626\nRp1627\ng1607\nF122.0\ntp1628\na(I3100000\ng1\n(g5\nS'33333\\xd3Y@'\np1629\ntp1630\nRp1631\ng1\n(g5\nS'33333\\xd3Y@'\np1632\ntp1633\nRp1634\nF283.0\ntp1635\na(I3110000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xe7Z@'\np1636\ntp1637\nRp1638\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf0Z@'\np1639\ntp1640\nRp1641\nF83.0\ntp1642\na(I3120000\ng1\n(g5\nS'33333\\xd3Z@'\np1643\ntp1644\nRp1645\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\t[@'\np1646\ntp1647\nRp1648\nF61.0\ntp1649\na(I3130000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xf3[@'\np1650\ntp1651\nRp1652\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xf3[@'\np1653\ntp1654\nRp1655\nF45.0\ntp1656\na(I3140000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xee[@'\np1657\ntp1658\nRp1659\ng1\n(g5\nS'H\\xe1z\\x14\\xaeW\\\\@'\np1660\ntp1661\nRp1662\nF97.0\ntp1663\na(I3150000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xdb\\\\@'\np1664\ntp1665\nRp1666\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xdb\\\\@'\np1667\ntp1668\nRp1669\nF187.0\ntp1670\na(I3160000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW^@'\np1671\ntp1672\nRp1673\ng1\n(g5\nS'\\xd7\\xa3p=\\nW^@'\np1674\ntp1675\nRp1676\nF174.0\ntp1677\na(I3170000\ng1\n(g5\nS'fffff\\xb6^@'\np1678\ntp1679\nRp1680\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8^@'\np1681\ntp1682\nRp1683\nF109.0\ntp1684\na(I3180000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\n_@'\np1685\ntp1686\nRp1687\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85K_@'\np1688\ntp1689\nRp1690\nF128.0\ntp1691\na(I3190000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x9d^@'\np1692\ntp1693\nRp1694\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x87_@'\np1695\ntp1696\nRp1697\nF16.0\ntp1698\na(I3200000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xa5^@'\np1699\ntp1700\nRp1701\ng1697\nF77.0\ntp1702\na(I3210000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xbc^@'\np1703\ntp1704\nRp1705\ng1697\nF126.0\ntp1706\na(I3220000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5H_@'\np1707\ntp1708\nRp1709\ng1697\nF143.0\ntp1710\na(I3230000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa_@'\np1711\ntp1712\nRp1713\ng1697\nF236.0\ntp1714\na(I3240000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x90^@'\np1715\ntp1716\nRp1717\ng1697\nF193.0\ntp1718\na(I3250000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@^@'\np1719\ntp1720\nRp1721\ng1697\nF63.0\ntp1722\na(I3260000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x90^@'\np1723\ntp1724\nRp1725\ng1697\nF89.0\ntp1726\na(I3270000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99y^@'\np1727\ntp1728\nRp1729\ng1697\nF204.0\ntp1730\na(I3280000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xe3^@'\np1731\ntp1732\nRp1733\ng1697\nF103.0\ntp1734\na(I3290000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x90^@'\np1735\ntp1736\nRp1737\ng1697\nF3.0\ntp1738\na(I3300000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xd7\\\\@'\np1739\ntp1740\nRp1741\ng1697\nF131.0\ntp1742\na(I3310000\ng1\n(g5\nS'33333\\xc3[@'\np1743\ntp1744\nRp1745\ng1697\nF113.0\ntp1746\na(I3320000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x83\\\\@'\np1747\ntp1748\nRp1749\ng1697\nF54.0\ntp1750\na(I3330000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8]@'\np1751\ntp1752\nRp1753\ng1697\nF125.0\ntp1754\na(I3340000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE_@'\np1755\ntp1756\nRp1757\ng1697\nF128.0\ntp1758\na(I3350000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f*`@'\np1759\ntp1760\nRp1761\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f*`@'\np1762\ntp1763\nRp1764\nF244.0\ntp1765\na(I3360000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xd2_@'\np1766\ntp1767\nRp1768\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc<`@'\np1769\ntp1770\nRp1771\nF81.0\ntp1772\na(I3370000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xc8_@'\np1773\ntp1774\nRp1775\ng1771\nF131.0\ntp1776\na(I3380000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x88`@'\np1777\ntp1778\nRp1779\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x88`@'\np1780\ntp1781\nRp1782\nF87.0\ntp1783\na(I3390000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xda`@'\np1784\ntp1785\nRp1786\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xe2`@'\np1787\ntp1788\nRp1789\nF135.0\ntp1790\na(I3400000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Qa@'\np1791\ntp1792\nRp1793\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Qa@'\np1794\ntp1795\nRp1796\nF279.0\ntp1797\na(I3410000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x9fa@'\np1798\ntp1799\nRp1800\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xb1a@'\np1801\ntp1802\nRp1803\nF260.0\ntp1804\na(I3420000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2Ea@'\np1805\ntp1806\nRp1807\ng1803\nF106.0\ntp1808\na(I3430000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeWa@'\np1809\ntp1810\nRp1811\ng1803\nF140.0\ntp1812\na(I3440000\ng1\n(g5\nS'33333\\x93b@'\np1813\ntp1814\nRp1815\ng1\n(g5\nS'33333\\x93b@'\np1816\ntp1817\nRp1818\nF96.0\ntp1819\na(I3450000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xd8b@'\np1820\ntp1821\nRp1822\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x04c@'\np1823\ntp1824\nRp1825\nF20.0\ntp1826\na(I3460000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5@b@'\np1827\ntp1828\nRp1829\ng1825\nF97.0\ntp1830\na(I3470000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Ab@'\np1831\ntp1832\nRp1833\ng1825\nF203.0\ntp1834\na(I3480000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xd4a@'\np1835\ntp1836\nRp1837\ng1825\nF100.0\ntp1838\na(I3490000\ng1\n(g5\nS'\\xd7\\xa3p=\\nwa@'\np1839\ntp1840\nRp1841\ng1825\nF92.0\ntp1842\na(I3500000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85sa@'\np1843\ntp1844\nRp1845\ng1825\nF113.0\ntp1846\na(I3510000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xc1`@'\np1847\ntp1848\nRp1849\ng1825\nF76.0\ntp1850\na(I3520000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x8e`@'\np1851\ntp1852\nRp1853\ng1825\nF139.0\ntp1854\na(I3530000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\`@'\np1855\ntp1856\nRp1857\ng1825\nF175.0\ntp1858\na(I3540000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x1e`@'\np1859\ntp1860\nRp1861\ng1825\nF109.0\ntp1862\na(I3550000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x97_@'\np1863\ntp1864\nRp1865\ng1825\nF20.0\ntp1866\na(I3560000\ng1\n(g5\nS'\\n\\xd7\\xa3p=:^@'\np1867\ntp1868\nRp1869\ng1825\nF75.0\ntp1870\na(I3570000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z4\\\\@'\np1871\ntp1872\nRp1873\ng1825\nF23.0\ntp1874\na(I3580000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xccY@'\np1875\ntp1876\nRp1877\ng1825\nF105.0\ntp1878\na(I3590000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xf7Y@'\np1879\ntp1880\nRp1881\ng1825\nF34.0\ntp1882\na(I3600000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1X@'\np1883\ntp1884\nRp1885\ng1825\nF112.0\ntp1886\na(I3610000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xa9X@'\np1887\ntp1888\nRp1889\ng1825\nF79.0\ntp1890\na(I3620000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xd0W@'\np1891\ntp1892\nRp1893\ng1825\nF39.0\ntp1894\na(I3630000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x04T@'\np1895\ntp1896\nRp1897\ng1825\nF50.0\ntp1898\na(I3640000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eeR@'\np1899\ntp1900\nRp1901\ng1825\nF47.0\ntp1902\na(I3650000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x9bP@'\np1903\ntp1904\nRp1905\ng1825\nF34.0\ntp1906\na(I3660000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x0eL@'\np1907\ntp1908\nRp1909\ng1825\nF26.0\ntp1910\na(I3670000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\OE@'\np1911\ntp1912\nRp1913\ng1825\nF14.0\ntp1914\na(I3680000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG!@@'\np1915\ntp1916\nRp1917\ng1825\nF5.0\ntp1918\na(I3690000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zT7@'\np1919\ntp1920\nRp1921\ng1825\nF10.0\ntp1922\na(I3700000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n%@'\np1923\ntp1924\nRp1925\ng1825\nF8.0\ntp1926\na(I3710000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e!@'\np1927\ntp1928\nRp1929\ng1825\nF10.0\ntp1930\na(I3720000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\x18@'\np1931\ntp1932\nRp1933\ng1825\nF8.0\ntp1934\na(I3730000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x12@'\np1935\ntp1936\nRp1937\ng1825\nF3.0\ntp1938\na(I3740000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\n@'\np1939\ntp1940\nRp1941\ng1825\nF2.0\ntp1942\na(I3750000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x03@'\np1943\ntp1944\nRp1945\ng1825\nF4.0\ntp1946\na(I3760000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\\x00@'\np1947\ntp1948\nRp1949\ng1825\nF3.0\ntp1950\na(I3770000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\xfc?'\np1951\ntp1952\nRp1953\ng1825\nF0.0\ntp1954\na(I3780000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\xfa?'\np1955\ntp1956\nRp1957\ng1825\nF4.0\ntp1958\na(I3790000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xfa?'\np1959\ntp1960\nRp1961\ng1825\nF3.0\ntp1962\na(I3800000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\xf7?'\np1963\ntp1964\nRp1965\ng1825\nF1.0\ntp1966\na(I3810000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\xfc?'\np1967\ntp1968\nRp1969\ng1825\nF0.0\ntp1970\na(I3820000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\xfc?'\np1971\ntp1972\nRp1973\ng1825\nF1.0\ntp1974\na(I3830000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\xf8?'\np1975\ntp1976\nRp1977\ng1825\nF1.0\ntp1978\na(I3840000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xfd?'\np1979\ntp1980\nRp1981\ng1825\nF2.0\ntp1982\na(I3850000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xff?'\np1983\ntp1984\nRp1985\ng1825\nF4.0\ntp1986\na(I3860000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\xff?'\np1987\ntp1988\nRp1989\ng1825\nF1.0\ntp1990\na(I3870000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\xfe?'\np1991\ntp1992\nRp1993\ng1825\nF5.0\ntp1994\na(I3880000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\\xfa?'\np1995\ntp1996\nRp1997\ng1825\nF1.0\ntp1998\na(I3890000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\xf8?'\np1999\ntp2000\nRp2001\ng1825\nF0.0\ntp2002\na(I3900000\ng1\n(g5\nS'ffffff\\xfa?'\np2003\ntp2004\nRp2005\ng1825\nF0.0\ntp2006\na(I3910000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\xf9?'\np2007\ntp2008\nRp2009\ng1825\nF2.0\ntp2010\na(I3920000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\xf2?'\np2011\ntp2012\nRp2013\ng1825\nF1.0\ntp2014\na(I3930000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\xf4?'\np2015\ntp2016\nRp2017\ng1825\nF0.0\ntp2018\na(I3940000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\xf8?'\np2019\ntp2020\nRp2021\ng1825\nF2.0\ntp2022\na(I3950000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x00@'\np2023\ntp2024\nRp2025\ng1825\nF1.0\ntp2026\na(I3960000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x01@'\np2027\ntp2028\nRp2029\ng1825\nF3.0\ntp2030\na(I3970000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\xff?'\np2031\ntp2032\nRp2033\ng1825\nF1.0\ntp2034\na(I3980000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\xfe?'\np2035\ntp2036\nRp2037\ng1825\nF0.0\ntp2038\na(I3990000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\x00@'\np2039\ntp2040\nRp2041\ng1825\nF3.0\ntp2042\na(I4000000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x02@'\np2043\ntp2044\nRp2045\ng1825\nF3.0\ntp2046\na(I4010000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\x02@'\np2047\ntp2048\nRp2049\ng1825\nF4.0\ntp2050\na(I4020000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x01@'\np2051\ntp2052\nRp2053\ng1825\nF7.0\ntp2054\na(I4030000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x01@'\np2055\ntp2056\nRp2057\ng1825\nF4.0\ntp2058\na(I4040000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x01@'\np2059\ntp2060\nRp2061\ng1825\nF4.0\ntp2062\na(I4050000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7\\xff?'\np2063\ntp2064\nRp2065\ng1825\nF0.0\ntp2066\na(I4060000\ng1\n(g5\nS'ffffff\\x00@'\np2067\ntp2068\nRp2069\ng1825\nF0.0\ntp2070\na(I4070000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\x00@'\np2071\ntp2072\nRp2073\ng1825\nF4.0\ntp2074\na(I4080000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x01@'\np2075\ntp2076\nRp2077\ng1825\nF4.0\ntp2078\na(I4090000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x03@'\np2079\ntp2080\nRp2081\ng1825\nF1.0\ntp2082\na(I4100000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\x04@'\np2083\ntp2084\nRp2085\ng1825\nF0.0\ntp2086\na(I4110000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x05@'\np2087\ntp2088\nRp2089\ng1825\nF3.0\ntp2090\na(I4120000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\x0b@'\np2091\ntp2092\nRp2093\ng1825\nF4.0\ntp2094\na(I4130000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x10@'\np2095\ntp2096\nRp2097\ng1825\nF5.0\ntp2098\na(I4140000\ng1\n(g5\nS'ffffff\\x11@'\np2099\ntp2100\nRp2101\ng1825\nF10.0\ntp2102\na(I4150000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e\\x12@'\np2103\ntp2104\nRp2105\ng1825\nF3.0\ntp2106\na(I4160000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x13@'\np2107\ntp2108\nRp2109\ng1825\nF3.0\ntp2110\na(I4170000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\x13@'\np2111\ntp2112\nRp2113\ng1825\nF3.0\ntp2114\na(I4180000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x14@'\np2115\ntp2116\nRp2117\ng1825\nF5.0\ntp2118\na(I4190000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\\x14@'\np2119\ntp2120\nRp2121\ng1825\nF2.0\ntp2122\na(I4200000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\x15@'\np2123\ntp2124\nRp2125\ng1825\nF4.0\ntp2126\na(I4210000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\x17@'\np2127\ntp2128\nRp2129\ng1825\nF5.0\ntp2130\na(I4220000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e\\x1a@'\np2131\ntp2132\nRp2133\ng1825\nF9.0\ntp2134\na(I4230000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x1d@'\np2135\ntp2136\nRp2137\ng1825\nF9.0\ntp2138\na(I4240000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\x1f@'\np2139\ntp2140\nRp2141\ng1825\nF7.0\ntp2142\na(I4250000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x19!@'\np2143\ntp2144\nRp2145\ng1825\nF6.0\ntp2146\na(I4260000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf0!@'\np2147\ntp2148\nRp2149\ng1825\nF6.0\ntp2150\na(I4270000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\"@'\np2151\ntp2152\nRp2153\ng1825\nF10.0\ntp2154\na(I4280000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8#@'\np2155\ntp2156\nRp2157\ng1825\nF15.0\ntp2158\na(I4290000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f$@'\np2159\ntp2160\nRp2161\ng1825\nF11.0\ntp2162\na(I4300000\ng1\n(g5\nS'fffff\\xe6$@'\np2163\ntp2164\nRp2165\ng1825\nF10.0\ntp2166\na(I4310000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG&@'\np2167\ntp2168\nRp2169\ng1825\nF23.0\ntp2170\na(I4320000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfa&@'\np2171\ntp2172\nRp2173\ng1825\nF9.0\ntp2174\na(I4330000\ng1\n(g5\nS\"R\\xb8\\x1e\\x85\\xebQ'@\"\np2175\ntp2176\nRp2177\ng1825\nF9.0\ntp2178\na(I4340000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1(@'\np2179\ntp2180\nRp2181\ng1825\nF11.0\ntp2182\na(I4350000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc7*@'\np2183\ntp2184\nRp2185\ng1825\nF13.0\ntp2186\na(I4360000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc,@'\np2187\ntp2188\nRp2189\ng1825\nF15.0\ntp2190\na(I4370000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8-@'\np2191\ntp2192\nRp2193\ng1825\nF12.0\ntp2194\na(I4380000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW/@'\np2195\ntp2196\nRp2197\ng1825\nF14.0\ntp2198\na(I4390000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:0@'\np2199\ntp2200\nRp2201\ng1825\nF19.0\ntp2202\na(I4400000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99/@'\np2203\ntp2204\nRp2205\ng1825\nF18.0\ntp2206\na(I4410000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f.@'\np2207\ntp2208\nRp2209\ng1825\nF17.0\ntp2210\na(I4420000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14/@'\np2211\ntp2212\nRp2213\ng1825\nF12.0\ntp2214\na(I4430000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p/@'\np2215\ntp2216\nRp2217\ng1825\nF16.0\ntp2218\na(I4440000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05/@'\np2219\ntp2220\nRp2221\ng1825\nF19.0\ntp2222\na(I4450000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2.@'\np2223\ntp2224\nRp2225\ng1825\nF13.0\ntp2226\na(I4460000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99/@'\np2227\ntp2228\nRp2229\ng1825\nF14.0\ntp2230\na(I4470000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG0@'\np2231\ntp2232\nRp2233\ng1825\nF11.0\ntp2234\na(I4480000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc250@'\np2235\ntp2236\nRp2237\ng1825\nF12.0\ntp2238\na(I4490000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x000@'\np2239\ntp2240\nRp2241\ng1825\nF12.0\ntp2242\na(I4500000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x820@'\np2243\ntp2244\nRp2245\ng1825\nF15.0\ntp2246\na(I4510000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\1@'\np2247\ntp2248\nRp2249\ng1825\nF27.0\ntp2250\na(I4520000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O2@'\np2251\ntp2252\nRp2253\ng1825\nF11.0\ntp2254\na(I4530000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e3@'\np2255\ntp2256\nRp2257\ng1825\nF35.0\ntp2258\na(I4540000\ng1\n(g5\nS'fffff&4@'\np2259\ntp2260\nRp2261\ng1825\nF27.0\ntp2262\na(I4550000\ng1\n(g5\nS'3333335@'\np2263\ntp2264\nRp2265\ng1825\nF20.0\ntp2266\na(I4560000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u6@'\np2267\ntp2268\nRp2269\ng1825\nF32.0\ntp2270\na(I4570000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx7@'\np2271\ntp2272\nRp2273\ng1825\nF40.0\ntp2274\na(I4580000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x179@'\np2275\ntp2276\nRp2277\ng1825\nF33.0\ntp2278\na(I4590000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x859@'\np2279\ntp2280\nRp2281\ng1825\nF22.0\ntp2282\na(I4600000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f9@'\np2283\ntp2284\nRp2285\ng1825\nF32.0\ntp2286\na(I4610000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1c:@'\np2287\ntp2288\nRp2289\ng1825\nF22.0\ntp2290\na(I4620000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba:@'\np2291\ntp2292\nRp2293\ng1825\nF20.0\ntp2294\na(I4630000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5:@'\np2295\ntp2296\nRp2297\ng1825\nF18.0\ntp2298\na(I4640000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85;@'\np2299\ntp2300\nRp2301\ng1825\nF46.0\ntp2302\na(I4650000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd4<@'\np2303\ntp2304\nRp2305\ng1825\nF29.0\ntp2306\na(I4660000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba=@'\np2307\ntp2308\nRp2309\ng1825\nF54.0\ntp2310\na(I4670000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}?@'\np2311\ntp2312\nRp2313\ng1825\nF50.0\ntp2314\na(I4680000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n@@'\np2315\ntp2316\nRp2317\ng1825\nF38.0\ntp2318\na(I4690000\ng1\n(g5\nS'fffff\\x06A@'\np2319\ntp2320\nRp2321\ng1825\nF47.0\ntp2322\na(I4700000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05B@'\np2323\ntp2324\nRp2325\ng1825\nF31.0\ntp2326\na(I4710000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}B@'\np2327\ntp2328\nRp2329\ng1825\nF26.0\ntp2330\na(I4720000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x03C@'\np2331\ntp2332\nRp2333\ng1825\nF70.0\ntp2334\na(I4730000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb1D@'\np2335\ntp2336\nRp2337\ng1825\nF62.0\ntp2338\na(I4740000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x11E@'\np2339\ntp2340\nRp2341\ng1825\nF39.0\ntp2342\na(I4750000\ng1\n(g5\nS'33333\\xd3E@'\np2343\ntp2344\nRp2345\ng1825\nF55.0\ntp2346\na(I4760000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xbaF@'\np2347\ntp2348\nRp2349\ng1825\nF67.0\ntp2350\na(I4770000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0cG@'\np2351\ntp2352\nRp2353\ng1825\nF64.0\ntp2354\na(I4780000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.G@'\np2355\ntp2356\nRp2357\ng1825\nF50.0\ntp2358\na(I4790000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc7G@'\np2359\ntp2360\nRp2361\ng1825\nF75.0\ntp2362\na(I4800000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeGH@'\np2363\ntp2364\nRp2365\ng1825\nF88.0\ntp2366\na(I4810000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0fI@'\np2367\ntp2368\nRp2369\ng1825\nF78.0\ntp2370\na(I4820000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x80I@'\np2371\ntp2372\nRp2373\ng1825\nF59.0\ntp2374\na(I4830000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1ZJ@'\np2375\ntp2376\nRp2377\ng1825\nF75.0\ntp2378\na(I4840000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8J@'\np2379\ntp2380\nRp2381\ng1825\nF37.0\ntp2382\na(I4850000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xdeJ@'\np2383\ntp2384\nRp2385\ng1825\nF63.0\ntp2386\na(I4860000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8fJ@'\np2387\ntp2388\nRp2389\ng1825\nF33.0\ntp2390\na(I4870000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQK@'\np2391\ntp2392\nRp2393\ng1825\nF67.0\ntp2394\na(I4880000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x0eK@'\np2395\ntp2396\nRp2397\ng1825\nF43.0\ntp2398\na(I4890000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xb4K@'\np2399\ntp2400\nRp2401\ng1825\nF55.0\ntp2402\na(I4900000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x1aL@'\np2403\ntp2404\nRp2405\ng1825\nF33.0\ntp2406\na(I4910000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(|L@'\np2407\ntp2408\nRp2409\ng1825\nF74.0\ntp2410\na(I4920000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8L@'\np2411\ntp2412\nRp2413\ng1825\nF68.0\ntp2414\na(I4930000\ng1\n(g5\nS'fffff\\xa6M@'\np2415\ntp2416\nRp2417\ng1825\nF87.0\ntp2418\na(I4940000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcfM@'\np2419\ntp2420\nRp2421\ng1825\nF86.0\ntp2422\na(I4950000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14nN@'\np2423\ntp2424\nRp2425\ng1825\nF73.0\ntp2426\na(I4960000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x07O@'\np2427\ntp2428\nRp2429\ng1825\nF110.0\ntp2430\na(I4970000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfaO@'\np2431\ntp2432\nRp2433\ng1825\nF72.0\ntp2434\na(I4980000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8cP@'\np2435\ntp2436\nRp2437\ng1825\nF74.0\ntp2438\na(I4990000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8Q@'\np2439\ntp2440\nRp2441\ng1825\nF61.0\ntp2442\na(I5000000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5HQ@'\np2443\ntp2444\nRp2445\ng1825\nF83.0\ntp2446\na(I5010000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x88Q@'\np2447\ntp2448\nRp2449\ng1825\nF82.0\ntp2450\na(I5020000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xfcQ@'\np2451\ntp2452\nRp2453\ng1825\nF53.0\ntp2454\na(I5030000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb5R@'\np2455\ntp2456\nRp2457\ng1825\nF69.0\ntp2458\na(I5040000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x85S@'\np2459\ntp2460\nRp2461\ng1825\nF109.0\ntp2462\na(I5050000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xd9S@'\np2463\ntp2464\nRp2465\ng1825\nF93.0\ntp2466\na(I5060000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xabS@'\np2467\ntp2468\nRp2469\ng1825\nF63.0\ntp2470\na(I5070000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9cS@'\np2471\ntp2472\nRp2473\ng1825\nF55.0\ntp2474\na(I5080000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8cS@'\np2475\ntp2476\nRp2477\ng1825\nF80.0\ntp2478\na(I5090000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1jS@'\np2479\ntp2480\nRp2481\ng1825\nF80.0\ntp2482\na(I5100000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x91S@'\np2483\ntp2484\nRp2485\ng1825\nF88.0\ntp2486\na(I5110000\ng1\n(g5\nS'33333\\xc3S@'\np2487\ntp2488\nRp2489\ng1825\nF129.0\ntp2490\na(I5120000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xe8S@'\np2491\ntp2492\nRp2493\ng1825\nF66.0\ntp2494\na(I5130000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xecT@'\np2495\ntp2496\nRp2497\ng1825\nF111.0\ntp2498\na(I5140000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x08U@'\np2499\ntp2500\nRp2501\ng1825\nF119.0\ntp2502\na(I5150000\ng1\n(g5\nS'H\\xe1z\\x14\\xae7U@'\np2503\ntp2504\nRp2505\ng1825\nF61.0\ntp2506\na(I5160000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQhU@'\np2507\ntp2508\nRp2509\ng1825\nF88.0\ntp2510\na(I5170000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x93T@'\np2511\ntp2512\nRp2513\ng1825\nF115.0\ntp2514\na(I5180000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.U@'\np2515\ntp2516\nRp2517\ng1825\nF90.0\ntp2518\na(I5190000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z4U@'\np2519\ntp2520\nRp2521\ng1825\nF66.0\ntp2522\na(I5200000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85U@'\np2523\ntp2524\nRp2525\ng1825\nF77.0\ntp2526\na(I5210000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2%V@'\np2527\ntp2528\nRp2529\ng1825\nF132.0\ntp2530\na(I5220000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xe7V@'\np2531\ntp2532\nRp2533\ng1825\nF86.0\ntp2534\na(I5230000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x18W@'\np2535\ntp2536\nRp2537\ng1825\nF103.0\ntp2538\na(I5240000\ng1\n(g5\nS'33333#W@'\np2539\ntp2540\nRp2541\ng1825\nF122.0\ntp2542\na(I5250000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xacW@'\np2543\ntp2544\nRp2545\ng1825\nF112.0\ntp2546\na(I5260000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\"X@'\np2547\ntp2548\nRp2549\ng1825\nF235.0\ntp2550\na(I5270000\ng1\n(g5\nS'q=\\n\\xd7\\xa3 W@'\np2551\ntp2552\nRp2553\ng1825\nF45.0\ntp2554\na(I5280000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x97W@'\np2555\ntp2556\nRp2557\ng1825\nF75.0\ntp2558\na(I5290000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99iW@'\np2559\ntp2560\nRp2561\ng1825\nF69.0\ntp2562\na(I5300000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99yX@'\np2563\ntp2564\nRp2565\ng1825\nF180.0\ntp2566\na(I5310000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb!Y@'\np2567\ntp2568\nRp2569\ng1825\nF93.0\ntp2570\na(I5320000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x10Y@'\np2571\ntp2572\nRp2573\ng1825\nF130.0\ntp2574\na(I5330000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xa8Y@'\np2575\ntp2576\nRp2577\ng1825\nF126.0\ntp2578\na(I5340000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb5Z@'\np2579\ntp2580\nRp2581\ng1825\nF171.0\ntp2582\na(I5350000\ng1\n(g5\nS'33333#[@'\np2583\ntp2584\nRp2585\ng1825\nF81.0\ntp2586\na(I5360000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00[@'\np2587\ntp2588\nRp2589\ng1825\nF94.0\ntp2590\na(I5370000\ng1\n(g5\nS'fffff\\xa6[@'\np2591\ntp2592\nRp2593\ng1825\nF46.0\ntp2594\na(I5380000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x82[@'\np2595\ntp2596\nRp2597\ng1825\nF77.0\ntp2598\na(I5390000\ng1\n(g5\nS'\\n\\xd7\\xa3p=:[@'\np2599\ntp2600\nRp2601\ng1825\nF55.0\ntp2602\na(I5400000\ng1\n(g5\nS'33333\\x13[@'\np2603\ntp2604\nRp2605\ng1825\nF192.0\ntp2606\na(I5410000\ng1\n(g5\nS'fffff\\x06[@'\np2607\ntp2608\nRp2609\ng1825\nF109.0\ntp2610\na(I5420000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeba[@'\np2611\ntp2612\nRp2613\ng1825\nF113.0\ntp2614\na(I5430000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x85[@'\np2615\ntp2616\nRp2617\ng1825\nF22.0\ntp2618\na(I5440000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xd2Z@'\np2619\ntp2620\nRp2621\ng1825\nF104.0\ntp2622\na(I5450000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fRZ@'\np2623\ntp2624\nRp2625\ng1825\nF69.0\ntp2626\na(I5460000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x9fZ@'\np2627\ntp2628\nRp2629\ng1825\nF135.0\ntp2630\na(I5470000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xd5Z@'\np2631\ntp2632\nRp2633\ng1825\nF141.0\ntp2634\na(I5480000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1Z@'\np2635\ntp2636\nRp2637\ng1825\nF96.0\ntp2638\na(I5490000\ng1\n(g5\nS'33333\\x83Z@'\np2639\ntp2640\nRp2641\ng1825\nF98.0\ntp2642\na(I5500000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xceZ@'\np2643\ntp2644\nRp2645\ng1825\nF107.0\ntp2646\na(I5510000\ng1\n(g5\nS'33333c[@'\np2647\ntp2648\nRp2649\ng1825\nF241.0\ntp2650\na(I5520000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xea\\\\@'\np2651\ntp2652\nRp2653\ng1825\nF189.0\ntp2654\na(I5530000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x83]@'\np2655\ntp2656\nRp2657\ng1825\nF166.0\ntp2658\na(I5540000\ng1\n(g5\nS'q=\\n\\xd7\\xa30^@'\np2659\ntp2660\nRp2661\ng1825\nF90.0\ntp2662\na(I5550000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xc8_@'\np2663\ntp2664\nRp2665\ng1825\nF128.0\ntp2666\na(I5560000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zt`@'\np2667\ntp2668\nRp2669\ng1825\nF147.0\ntp2670\na(I5570000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85C`@'\np2671\ntp2672\nRp2673\ng1825\nF74.0\ntp2674\na(I5580000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xd4`@'\np2675\ntp2676\nRp2677\ng1825\nF101.0\ntp2678\na(I5590000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\ra@'\np2679\ntp2680\nRp2681\ng1825\nF97.0\ntp2682\na(I5600000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2%a@'\np2683\ntp2684\nRp2685\ng1825\nF62.0\ntp2686\na(I5610000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccLa@'\np2687\ntp2688\nRp2689\ng1825\nF301.0\ntp2690\na(I5620000\ng1\n(g5\nS'33333\\xfb`@'\np2691\ntp2692\nRp2693\ng1825\nF95.0\ntp2694\na(I5630000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQha@'\np2695\ntp2696\nRp2697\ng1825\nF124.0\ntp2698\na(I5640000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xc9a@'\np2699\ntp2700\nRp2701\ng1825\nF150.0\ntp2702\na(I5650000\ng1\n(g5\nS'\\xd7\\xa3p=\\nGa@'\np2703\ntp2704\nRp2705\ng1825\nF107.0\ntp2706\na(I5660000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x90`@'\np2707\ntp2708\nRp2709\ng1825\nF122.0\ntp2710\na(I5670000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xcf`@'\np2711\ntp2712\nRp2713\ng1825\nF64.0\ntp2714\na(I5680000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x18a@'\np2715\ntp2716\nRp2717\ng1825\nF130.0\ntp2718\na(I5690000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x7f`@'\np2719\ntp2720\nRp2721\ng1825\nF147.0\ntp2722\na(I5700000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eu`@'\np2723\ntp2724\nRp2725\ng1825\nF165.0\ntp2726\na(I5710000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x84`@'\np2727\ntp2728\nRp2729\ng1825\nF186.0\ntp2730\na(I5720000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99!a@'\np2731\ntp2732\nRp2733\ng1825\nF168.0\ntp2734\na(I5730000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x1da@'\np2735\ntp2736\nRp2737\ng1825\nF100.0\ntp2738\na(I5740000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xe2`@'\np2739\ntp2740\nRp2741\ng1825\nF144.0\ntp2742\na(I5750000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e]a@'\np2743\ntp2744\nRp2745\ng1825\nF153.0\ntp2746\na(I5760000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x8da@'\np2747\ntp2748\nRp2749\ng1825\nF61.0\ntp2750\na(I5770000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xf3a@'\np2751\ntp2752\nRp2753\ng1825\nF148.0\ntp2754\na(I5780000\ng1\n(g5\nS'33333Sa@'\np2755\ntp2756\nRp2757\ng1825\nF197.0\ntp2758\na(I5790000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x01b@'\np2759\ntp2760\nRp2761\ng1825\nF269.0\ntp2762\na(I5800000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\_b@'\np2763\ntp2764\nRp2765\ng1825\nF176.0\ntp2766\na(I5810000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1zb@'\np2767\ntp2768\nRp2769\ng1825\nF136.0\ntp2770\na(I5820000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5Hb@'\np2771\ntp2772\nRp2773\ng1825\nF246.0\ntp2774\na(I5830000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x8cb@'\np2775\ntp2776\nRp2777\ng1825\nF120.0\ntp2778\na(I5840000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Ic@'\np2779\ntp2780\nRp2781\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Ic@'\np2782\ntp2783\nRp2784\nF324.0\ntp2785\na(I5850000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Yc@'\np2786\ntp2787\nRp2788\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQpc@'\np2789\ntp2790\nRp2791\nF103.0\ntp2792\na(I5860000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xa0c@'\np2793\ntp2794\nRp2795\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xa0c@'\np2796\ntp2797\nRp2798\nF307.0\ntp2799\na(I5870000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x1ac@'\np2800\ntp2801\nRp2802\ng2798\nF259.0\ntp2803\na(I5880000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x80c@'\np2804\ntp2805\nRp2806\ng2798\nF102.0\ntp2807\na(I5890000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xd2c@'\np2808\ntp2809\nRp2810\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf8c@'\np2811\ntp2812\nRp2813\nF61.0\ntp2814\na(I5900000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xf8c@'\np2815\ntp2816\nRp2817\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x18d@'\np2818\ntp2819\nRp2820\nF95.0\ntp2821\na(I5910000\ng1\n(g5\nS'q=\\n\\xd7\\xa3pc@'\np2822\ntp2823\nRp2824\ng2820\nF174.0\ntp2825\na(I5920000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\Oc@'\np2826\ntp2827\nRp2828\ng2820\nF204.0\ntp2829\na(I5930000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xf7c@'\np2830\ntp2831\nRp2832\ng2820\nF267.0\ntp2833\na(I5940000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xffc@'\np2834\ntp2835\nRp2836\ng2820\nF305.0\ntp2837\na(I5950000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x10e@'\np2838\ntp2839\nRp2840\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x10e@'\np2841\ntp2842\nRp2843\nF219.0\ntp2844\na(I5960000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x08f@'\np2845\ntp2846\nRp2847\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x08f@'\np2848\ntp2849\nRp2850\nF300.0\ntp2851\na(I5970000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xf5e@'\np2852\ntp2853\nRp2854\ng1\n(g5\nS'=\\n\\xd7\\xa3pUf@'\np2855\ntp2856\nRp2857\nF303.0\ntp2858\na(I5980000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x9fe@'\np2859\ntp2860\nRp2861\ng2857\nF101.0\ntp2862\na(I5990000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xd5e@'\np2863\ntp2864\nRp2865\ng2857\nF312.0\ntp2866\na(I6000000\ng1\n(g5\nS'=\\n\\xd7\\xa3pEf@'\np2867\ntp2868\nRp2869\ng2857\nF255.0\ntp2870\na(I6010000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00Hf@'\np2871\ntp2872\nRp2873\ng1\n(g5\nS'33333\\x93f@'\np2874\ntp2875\nRp2876\nF152.0\ntp2877\na(I6020000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xfef@'\np2878\ntp2879\nRp2880\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\ng@'\np2881\ntp2882\nRp2883\nF190.0\ntp2884\na(I6030000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x01g@'\np2885\ntp2886\nRp2887\ng1\n(g5\nS'fffffVg@'\np2888\ntp2889\nRp2890\nF184.0\ntp2891\na(I6040000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00Pg@'\np2892\ntp2893\nRp2894\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\og@'\np2895\ntp2896\nRp2897\nF128.0\ntp2898\na(I6050000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xfdg@'\np2899\ntp2900\nRp2901\ng1\n(g5\nS'{\\x14\\xaeG\\xe12h@'\np2902\ntp2903\nRp2904\nF105.0\ntp2905\na(I6060000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xd0h@'\np2906\ntp2907\nRp2908\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xd0h@'\np2909\ntp2910\nRp2911\nF147.0\ntp2912\na(I6070000\ng1\n(g5\nS'\\xd7\\xa3p=\\nGi@'\np2913\ntp2914\nRp2915\ng1\n(g5\nS'\\xd7\\xa3p=\\nGi@'\np2916\ntp2917\nRp2918\nF264.0\ntp2919\na(I6080000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGai@'\np2920\ntp2921\nRp2922\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2ei@'\np2923\ntp2924\nRp2925\nF315.0\ntp2926\na(I6090000\ng1\n(g5\nS'fffff\\x86i@'\np2927\ntp2928\nRp2929\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x9bi@'\np2930\ntp2931\nRp2932\nF275.0\ntp2933\na(I6100000\ng1\n(g5\nS'q=\\n\\xd7\\xa3pi@'\np2934\ntp2935\nRp2936\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xa7i@'\np2937\ntp2938\nRp2939\nF79.0\ntp2940\na(I6110000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2ei@'\np2941\ntp2942\nRp2943\ng2939\nF162.0\ntp2944\na(I6120000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xc6i@'\np2945\ntp2946\nRp2947\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xc6i@'\np2948\ntp2949\nRp2950\nF180.0\ntp2951\na(I6130000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x89j@'\np2952\ntp2953\nRp2954\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x89j@'\np2955\ntp2956\nRp2957\nF350.0\ntp2958\na(I6140000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\gk@'\np2959\ntp2960\nRp2961\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\gk@'\np2962\ntp2963\nRp2964\nF319.0\ntp2965\na(I6150000\ng1\n(g5\nS'33333\\xd3j@'\np2966\ntp2967\nRp2968\ng1\n(g5\nS'\\xaeG\\xe1z\\x14~k@'\np2969\ntp2970\nRp2971\nF177.0\ntp2972\na(I6160000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x04k@'\np2973\ntp2974\nRp2975\ng2971\nF192.0\ntp2976\na(I6170000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(|k@'\np2977\ntp2978\nRp2979\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x80k@'\np2980\ntp2981\nRp2982\nF236.0\ntp2983\na(I6180000\ng1\n(g5\nS'\\xd7\\xa3p=\\n/k@'\np2984\ntp2985\nRp2986\ng2982\nF68.0\ntp2987\na(I6190000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xffk@'\np2988\ntp2989\nRp2990\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xffk@'\np2991\ntp2992\nRp2993\nF328.0\ntp2994\na(I6200000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa9l@'\np2995\ntp2996\nRp2997\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa9l@'\np2998\ntp2999\nRp3000\nF319.0\ntp3001\na(I6210000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xd6l@'\np3002\ntp3003\nRp3004\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xf6l@'\np3005\ntp3006\nRp3007\nF232.0\ntp3008\na(I6220000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xa9l@'\np3009\ntp3010\nRp3011\ng3007\nF47.0\ntp3012\na(I6230000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x1cm@'\np3013\ntp3014\nRp3015\ng1\n(g5\nS'\\xd7\\xa3p=\\nWm@'\np3016\ntp3017\nRp3018\nF245.0\ntp3019\na(I6240000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xa6m@'\np3020\ntp3021\nRp3022\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xa6m@'\np3023\ntp3024\nRp3025\nF374.0\ntp3026\na(I6250000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x8cm@'\np3027\ntp3028\nRp3029\ng3025\nF315.0\ntp3030\na(I6260000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xd5m@'\np3031\ntp3032\nRp3033\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xe4m@'\np3034\ntp3035\nRp3036\nF280.0\ntp3037\na(I6270000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xbcm@'\np3038\ntp3039\nRp3040\ng3036\nF307.0\ntp3041\na(I6280000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x89n@'\np3042\ntp3043\nRp3044\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x89n@'\np3045\ntp3046\nRp3047\nF382.0\ntp3048\na(I6290000\ng1\n(g5\nS'33333\\x13o@'\np3049\ntp3050\nRp3051\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\"o@'\np3052\ntp3053\nRp3054\nF245.0\ntp3055\na(I6300000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xccn@'\np3056\ntp3057\nRp3058\ng3054\nF113.0\ntp3059\na(I6310000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xc5n@'\np3060\ntp3061\nRp3062\ng3054\nF264.0\ntp3063\na(I6320000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG!o@'\np3064\ntp3065\nRp3066\ng1\n(g5\nS'\\xaeG\\xe1z\\x14~o@'\np3067\ntp3068\nRp3069\nF98.0\ntp3070\na(I6330000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xa3o@'\np3071\ntp3072\nRp3073\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xa3o@'\np3074\ntp3075\nRp3076\nF385.0\ntp3077\na(I6340000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x86o@'\np3078\ntp3079\nRp3080\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xabo@'\np3081\ntp3082\nRp3083\nF237.0\ntp3084\na(I6350000\ng1\n(g5\nS'fffff\\x8eo@'\np3085\ntp3086\nRp3087\ng1\n(g5\nS'fffff\\x06p@'\np3088\ntp3089\nRp3090\nF164.0\ntp3091\na(I6360000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc0o@'\np3092\ntp3093\nRp3094\ng3090\nF312.0\ntp3095\na(I6370000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e-o@'\np3096\ntp3097\nRp3098\ng3090\nF316.0\ntp3099\na(I6380000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xd5o@'\np3100\ntp3101\nRp3102\ng3090\nF339.0\ntp3103\na(I6390000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xf9o@'\np3104\ntp3105\nRp3106\ng3090\nF255.0\ntp3107\na(I6400000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99ap@'\np3108\ntp3109\nRp3110\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99ap@'\np3111\ntp3112\nRp3113\nF336.0\ntp3114\na(I6410000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x83p@'\np3115\ntp3116\nRp3117\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x83p@'\np3118\ntp3119\nRp3120\nF327.0\ntp3121\na(I6420000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb4p@'\np3122\ntp3123\nRp3124\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb4p@'\np3125\ntp3126\nRp3127\nF241.0\ntp3128\na(I6430000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x95p@'\np3129\ntp3130\nRp3131\ng3127\nF254.0\ntp3132\na(I6440000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xc5p@'\np3133\ntp3134\nRp3135\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xc5p@'\np3136\ntp3137\nRp3138\nF204.0\ntp3139\na(I6450000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xbap@'\np3140\ntp3141\nRp3142\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe9p@'\np3143\ntp3144\nRp3145\nF213.0\ntp3146\na(I6460000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xb4p@'\np3147\ntp3148\nRp3149\ng3145\nF367.0\ntp3150\na(I6470000\ng1\n(g5\nS'fffff\\xfep@'\np3151\ntp3152\nRp3153\ng1\n(g5\nS'fffff\\xfep@'\np3154\ntp3155\nRp3156\nF369.0\ntp3157\na(I6480000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xffp@'\np3158\ntp3159\nRp3160\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x1dq@'\np3161\ntp3162\nRp3163\nF354.0\ntp3164\na(I6490000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xf8p@'\np3165\ntp3166\nRp3167\ng3163\nF371.0\ntp3168\na(I6500000\ng1\n(g5\nS'33333\\x07q@'\np3169\ntp3170\nRp3171\ng1\n(g5\nS'q=\\n\\xd7\\xa30q@'\np3172\ntp3173\nRp3174\nF74.0\ntp3175\na(I6510000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x10q@'\np3176\ntp3177\nRp3178\ng3174\nF337.0\ntp3179\na(I6520000\ng1\n(g5\nS'\\n\\xd7\\xa3p=6q@'\np3180\ntp3181\nRp3182\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8q@'\np3183\ntp3184\nRp3185\nF364.0\ntp3186\na(I6530000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xa0q@'\np3187\ntp3188\nRp3189\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xa0q@'\np3190\ntp3191\nRp3192\nF431.0\ntp3193\na(I6540000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x86q@'\np3194\ntp3195\nRp3196\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xaaq@'\np3197\ntp3198\nRp3199\nF317.0\ntp3200\na(I6550000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x89q@'\np3201\ntp3202\nRp3203\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xb4q@'\np3204\ntp3205\nRp3206\nF128.0\ntp3207\na(I6560000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14~q@'\np3208\ntp3209\nRp3210\ng3206\nF250.0\ntp3211\na(I6570000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x81q@'\np3212\ntp3213\nRp3214\ng3206\nF285.0\ntp3215\na(I6580000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x85q@'\np3216\ntp3217\nRp3218\ng3206\nF259.0\ntp3219\na(I6590000\ng1\n(g5\nS'H\\xe1z\\x14\\xaesq@'\np3220\ntp3221\nRp3222\ng3206\nF275.0\ntp3223\na(I6600000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xa2q@'\np3224\ntp3225\nRp3226\ng3206\nF213.0\ntp3227\na(I6610000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xadq@'\np3228\ntp3229\nRp3230\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xbcq@'\np3231\ntp3232\nRp3233\nF315.0\ntp3234\na(I6620000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xdbq@'\np3235\ntp3236\nRp3237\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xdbq@'\np3238\ntp3239\nRp3240\nF320.0\ntp3241\na(I6630000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xe1q@'\np3242\ntp3243\nRp3244\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xe3q@'\np3245\ntp3246\nRp3247\nF358.0\ntp3248\na(I6640000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd1q@'\np3249\ntp3250\nRp3251\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x04r@'\np3252\ntp3253\nRp3254\nF299.0\ntp3255\na(I6650000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x88q@'\np3256\ntp3257\nRp3258\ng3254\nF152.0\ntp3259\na(I6660000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xf6q@'\np3260\ntp3261\nRp3262\ng3254\nF198.0\ntp3263\na(I6670000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xfaq@'\np3264\ntp3265\nRp3266\ng3254\nF269.0\ntp3267\na(I6680000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xf6q@'\np3268\ntp3269\nRp3270\ng3254\nF331.0\ntp3271\na(I6690000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e%r@'\np3272\ntp3273\nRp3274\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e%r@'\np3275\ntp3276\nRp3277\nF404.0\ntp3278\na(I6700000\ng1\n(g5\nS'fffff\\x1er@'\np3279\ntp3280\nRp3281\ng3277\nF407.0\ntp3282\na(I6710000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\rr@'\np3283\ntp3284\nRp3285\ng3277\nF301.0\ntp3286\na(I6720000\ng1\n(g5\nS'\\xd7\\xa3p=\\n7r@'\np3287\ntp3288\nRp3289\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e9r@'\np3290\ntp3291\nRp3292\nF359.0\ntp3293\na(I6730000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeGr@'\np3294\ntp3295\nRp3296\ng1\n(g5\nS'\\n\\xd7\\xa3p=Rr@'\np3297\ntp3298\nRp3299\nF62.0\ntp3300\na(I6740000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5<r@'\np3301\ntp3302\nRp3303\ng3299\nF292.0\ntp3304\na(I6750000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGMr@'\np3305\ntp3306\nRp3307\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\Wr@'\np3308\ntp3309\nRp3310\nF317.0\ntp3311\na(I6760000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccxr@'\np3312\ntp3313\nRp3314\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85{r@'\np3315\ntp3316\nRp3317\nF319.0\ntp3318\na(I6770000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14jr@'\np3319\ntp3320\nRp3321\ng3317\nF287.0\ntp3322\na(I6780000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2yr@'\np3323\ntp3324\nRp3325\ng3317\nF365.0\ntp3326\na(I6790000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x87r@'\np3327\ntp3328\nRp3329\ng1\n(g5\nS'33333\\x93r@'\np3330\ntp3331\nRp3332\nF300.0\ntp3333\na(I6800000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14zr@'\np3334\ntp3335\nRp3336\ng3332\nF377.0\ntp3337\na(I6810000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x9fr@'\np3338\ntp3339\nRp3340\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x9fr@'\np3341\ntp3342\nRp3343\nF380.0\ntp3344\na(I6820000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xa7r@'\np3345\ntp3346\nRp3347\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xacr@'\np3348\ntp3349\nRp3350\nF292.0\ntp3351\na(I6830000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x01s@'\np3352\ntp3353\nRp3354\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x01s@'\np3355\ntp3356\nRp3357\nF393.0\ntp3358\na(I6840000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xc7r@'\np3359\ntp3360\nRp3361\ng3357\nF205.0\ntp3362\na(I6850000\ng1\n(g5\nS'33333\\xbfr@'\np3363\ntp3364\nRp3365\ng3357\nF222.0\ntp3366\na(I6860000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xd2r@'\np3367\ntp3368\nRp3369\ng3357\nF380.0\ntp3370\na(I6870000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\"s@'\np3371\ntp3372\nRp3373\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\"s@'\np3374\ntp3375\nRp3376\nF374.0\ntp3377\na(I6880000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x16s@'\np3378\ntp3379\nRp3380\ng3376\nF355.0\ntp3381\na(I6890000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ$s@'\np3382\ntp3383\nRp3384\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ$s@'\np3385\ntp3386\nRp3387\nF369.0\ntp3388\na(I6900000\ng1\n(g5\nS'fffff\\x16s@'\np3389\ntp3390\nRp3391\ng3387\nF264.0\ntp3392\na(I6910000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xe6r@'\np3393\ntp3394\nRp3395\ng3387\nF254.0\ntp3396\na(I6920000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\#s@'\np3397\ntp3398\nRp3399\ng3387\nF256.0\ntp3400\na(I6930000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z,s@'\np3401\ntp3402\nRp3403\ng1\n(g5\nS'33333/s@'\np3404\ntp3405\nRp3406\nF354.0\ntp3407\na(I6940000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebIs@'\np3408\ntp3409\nRp3410\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebIs@'\np3411\ntp3412\nRp3413\nF417.0\ntp3414\na(I6950000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb=s@'\np3415\ntp3416\nRp3417\ng3413\nF229.0\ntp3418\na(I6960000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebys@'\np3419\ntp3420\nRp3421\ng1\n(g5\nS'\\xe1z\\x14\\xaeG}s@'\np3422\ntp3423\nRp3424\nF317.0\ntp3425\na(I6970000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(ls@'\np3426\ntp3427\nRp3428\ng3424\nF335.0\ntp3429\na(I6980000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x81s@'\np3430\ntp3431\nRp3432\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x8ds@'\np3433\ntp3434\nRp3435\nF419.0\ntp3436\na(I6990000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebYs@'\np3437\ntp3438\nRp3439\ng3435\nF196.0\ntp3440\na(I7000000\ng1\n(g5\nS'=\\n\\xd7\\xa3pIs@'\np3441\ntp3442\nRp3443\ng3435\nF306.0\ntp3444\na(I7010000\ng1\n(g5\nS'H\\xe1z\\x14\\xae_s@'\np3445\ntp3446\nRp3447\ng3435\nF252.0\ntp3448\na(I7020000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xe9r@'\np3449\ntp3450\nRp3451\ng3435\nF1.0\ntp3452\na(I7030000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5$s@'\np3453\ntp3454\nRp3455\ng3435\nF412.0\ntp3456\na(I7040000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85ws@'\np3457\ntp3458\nRp3459\ng3435\nF374.0\ntp3460\na(I7050000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xb4s@'\np3461\ntp3462\nRp3463\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xb4s@'\np3464\ntp3465\nRp3466\nF411.0\ntp3467\na(I7060000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xd6s@'\np3468\ntp3469\nRp3470\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xd6s@'\np3471\ntp3472\nRp3473\nF405.0\ntp3474\na(I7070000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xa4s@'\np3475\ntp3476\nRp3477\ng3473\nF274.0\ntp3478\na(I7080000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xbcs@'\np3479\ntp3480\nRp3481\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xd9s@'\np3482\ntp3483\nRp3484\nF371.0\ntp3485\na(I7090000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\tt@'\np3486\ntp3487\nRp3488\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\tt@'\np3489\ntp3490\nRp3491\nF410.0\ntp3492\na(I7100000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x0ft@'\np3493\ntp3494\nRp3495\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x0ft@'\np3496\ntp3497\nRp3498\nF334.0\ntp3499\na(I7110000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5lt@'\np3500\ntp3501\nRp3502\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5lt@'\np3503\ntp3504\nRp3505\nF386.0\ntp3506\na(I7120000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x81t@'\np3507\ntp3508\nRp3509\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x8dt@'\np3510\ntp3511\nRp3512\nF345.0\ntp3513\na(I7130000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xb2t@'\np3514\ntp3515\nRp3516\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xb2t@'\np3517\ntp3518\nRp3519\nF334.0\ntp3520\na(I7140000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xd7t@'\np3521\ntp3522\nRp3523\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xd7t@'\np3524\ntp3525\nRp3526\nF373.0\ntp3527\na(I7150000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xe5t@'\np3528\ntp3529\nRp3530\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xe5t@'\np3531\ntp3532\nRp3533\nF406.0\ntp3534\na(I7160000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xdft@'\np3535\ntp3536\nRp3537\ng1\n(g5\nS'fffff\\xfet@'\np3538\ntp3539\nRp3540\nF389.0\ntp3541\na(I7170000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\"u@'\np3542\ntp3543\nRp3544\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\"u@'\np3545\ntp3546\nRp3547\nF347.0\ntp3548\na(I7180000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x1eu@'\np3549\ntp3550\nRp3551\ng3547\nF381.0\ntp3552\na(I7190000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5@u@'\np3553\ntp3554\nRp3555\ng1\n(g5\nS'q=\\n\\xd7\\xa3Du@'\np3556\ntp3557\nRp3558\nF396.0\ntp3559\na(I7200000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xafu@'\np3560\ntp3561\nRp3562\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xafu@'\np3563\ntp3564\nRp3565\nF402.0\ntp3566\na(I7210000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xcdu@'\np3567\ntp3568\nRp3569\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd8u@'\np3570\ntp3571\nRp3572\nF406.0\ntp3573\na(I7220000\ng1\n(g5\nS'fffff\\xe2u@'\np3574\ntp3575\nRp3576\ng1\n(g5\nS'fffff\\xe2u@'\np3577\ntp3578\nRp3579\nF373.0\ntp3580\na(I7230000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xd9u@'\np3581\ntp3582\nRp3583\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xe8u@'\np3584\ntp3585\nRp3586\nF345.0\ntp3587\na(I7240000\ng1\n(g5\nS'fffffbv@'\np3588\ntp3589\nRp3590\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQxv@'\np3591\ntp3592\nRp3593\nF241.0\ntp3594\na(I7250000\ng1\n(g5\nS'fffffnv@'\np3595\ntp3596\nRp3597\ng1\n(g5\nS'33333{v@'\np3598\ntp3599\nRp3600\nF348.0\ntp3601\na(I7260000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\gv@'\np3602\ntp3603\nRp3604\ng3600\nF332.0\ntp3605\na(I7270000\ng1\n(g5\nS'fffffbv@'\np3606\ntp3607\nRp3608\ng3600\nF388.0\ntp3609\na(I7280000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(Pv@'\np3610\ntp3611\nRp3612\ng3600\nF338.0\ntp3613\na(I7290000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x88v@'\np3614\ntp3615\nRp3616\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x88v@'\np3617\ntp3618\nRp3619\nF416.0\ntp3620\na(I7300000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xbav@'\np3621\ntp3622\nRp3623\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xbav@'\np3624\ntp3625\nRp3626\nF389.0\ntp3627\na(I7310000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xc7v@'\np3628\ntp3629\nRp3630\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xc7v@'\np3631\ntp3632\nRp3633\nF427.0\ntp3634\na(I7320000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xb0v@'\np3635\ntp3636\nRp3637\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc7v@'\np3638\ntp3639\nRp3640\nF404.0\ntp3641\na(I7330000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xccv@'\np3642\ntp3643\nRp3644\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xcev@'\np3645\ntp3646\nRp3647\nF389.0\ntp3648\na(I7340000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xeav@'\np3649\ntp3650\nRp3651\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xeav@'\np3652\ntp3653\nRp3654\nF421.0\ntp3655\na(I7350000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xd1v@'\np3656\ntp3657\nRp3658\ng3654\nF375.0\ntp3659\na(I7360000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xdev@'\np3660\ntp3661\nRp3662\ng3654\nF407.0\ntp3663\na(I7370000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xe7v@'\np3664\ntp3665\nRp3666\ng3654\nF427.0\ntp3667\na(I7380000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x05w@'\np3668\ntp3669\nRp3670\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x05w@'\np3671\ntp3672\nRp3673\nF413.0\ntp3674\na(I7390000\ng1\n(g5\nS'fffff\\x12w@'\np3675\ntp3676\nRp3677\ng1\n(g5\nS'fffff\\x12w@'\np3678\ntp3679\nRp3680\nF413.0\ntp3681\na(I7400000\ng1\n(g5\nS'q=\\n\\xd7\\xa30w@'\np3682\ntp3683\nRp3684\ng1\n(g5\nS'q=\\n\\xd7\\xa30w@'\np3685\ntp3686\nRp3687\nF324.0\ntp3688\na(I7410000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85#w@'\np3689\ntp3690\nRp3691\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8:w@'\np3692\ntp3693\nRp3694\nF254.0\ntp3695\na(I7420000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG-w@'\np3696\ntp3697\nRp3698\ng3694\nF417.0\ntp3699\na(I7430000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z$w@'\np3700\ntp3701\nRp3702\ng3694\nF328.0\ntp3703\na(I7440000\ng1\n(g5\nS'\\xd7\\xa3p=\\n7w@'\np3704\ntp3705\nRp3706\ng3694\nF395.0\ntp3707\na(I7450000\ng1\n(g5\nS'\\xd7\\xa3p=\\n#w@'\np3708\ntp3709\nRp3710\ng3694\nF427.0\ntp3711\na(I7460000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1cw@'\np3712\ntp3713\nRp3714\ng3694\nF392.0\ntp3715\na(I7470000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xd6v@'\np3716\ntp3717\nRp3718\ng3694\nF116.0\ntp3719\na(I7480000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe0v@'\np3720\ntp3721\nRp3722\ng3694\nF420.0\ntp3723\na(I7490000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xbev@'\np3724\ntp3725\nRp3726\ng3694\nF380.0\ntp3727\na(I7500000\ng1\n(g5\nS'fffff\\xcev@'\np3728\ntp3729\nRp3730\ng3694\nF260.0\ntp3731\na(I7510000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xd6v@'\np3732\ntp3733\nRp3734\ng3694\nF416.0\ntp3735\na(I7520000\ng1\n(g5\nS'33333\\xc3v@'\np3736\ntp3737\nRp3738\ng3694\nF265.0\ntp3739\na(I7530000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xbfv@'\np3740\ntp3741\nRp3742\ng3694\nF330.0\ntp3743\na(I7540000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x8bv@'\np3744\ntp3745\nRp3746\ng3694\nF374.0\ntp3747\na(I7550000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x86v@'\np3748\ntp3749\nRp3750\ng3694\nF330.0\ntp3751\na(I7560000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x89v@'\np3752\ntp3753\nRp3754\ng3694\nF400.0\ntp3755\na(I7570000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x93v@'\np3756\ntp3757\nRp3758\ng3694\nF382.0\ntp3759\na(I7580000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x84v@'\np3760\ntp3761\nRp3762\ng3694\nF424.0\ntp3763\na(I7590000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x84v@'\np3764\ntp3765\nRp3766\ng3694\nF374.0\ntp3767\na(I7600000\ng1\n(g5\nS'H\\xe1z\\x14\\xaewv@'\np3768\ntp3769\nRp3770\ng3694\nF397.0\ntp3771\na(I7610000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x88v@'\np3772\ntp3773\nRp3774\ng3694\nF374.0\ntp3775\na(I7620000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x93v@'\np3776\ntp3777\nRp3778\ng3694\nF419.0\ntp3779\na(I7630000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eEv@'\np3780\ntp3781\nRp3782\ng3694\nF306.0\ntp3783\na(I7640000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2!v@'\np3784\ntp3785\nRp3786\ng3694\nF359.0\ntp3787\na(I7650000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00$v@'\np3788\ntp3789\nRp3790\ng3694\nF395.0\ntp3791\na(I7660000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\nv@'\np3792\ntp3793\nRp3794\ng3694\nF119.0\ntp3795\na(I7670000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x1cv@'\np3796\ntp3797\nRp3798\ng3694\nF421.0\ntp3799\na(I7680000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x08v@'\np3800\ntp3801\nRp3802\ng3694\nF296.0\ntp3803\na(I7690000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x1bv@'\np3804\ntp3805\nRp3806\ng3694\nF385.0\ntp3807\na(I7700000\ng1\n(g5\nS\"\\xd7\\xa3p=\\n'v@\"\np3808\ntp3809\nRp3810\ng3694\nF353.0\ntp3811\na(I7710000\ng1\n(g5\nS'33333\\x0fv@'\np3812\ntp3813\nRp3814\ng3694\nF431.0\ntp3815\na(I7720000\ng1\n(g5\nS'fffffBv@'\np3816\ntp3817\nRp3818\ng3694\nF426.0\ntp3819\na(I7730000\ng1\n(g5\nS'fffff\\xeev@'\np3820\ntp3821\nRp3822\ng3694\nF820.0\ntp3823\na(I7740000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00 w@'\np3824\ntp3825\nRp3826\ng3694\nF391.0\ntp3827\na(I7750000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ0w@'\np3828\ntp3829\nRp3830\ng3694\nF345.0\ntp3831\na(I7760000\ng1\n(g5\nS'fffff*w@'\np3832\ntp3833\nRp3834\ng3694\nF349.0\ntp3835\na(I7770000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x04w@'\np3836\ntp3837\nRp3838\ng3694\nF424.0\ntp3839\na(I7780000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5v@'\np3840\ntp3841\nRp3842\ng3694\nF337.0\ntp3843\na(I7790000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x857w@'\np3844\ntp3845\nRp3846\ng3694\nF401.0\ntp3847\na(I7800000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x15w@'\np3848\ntp3849\nRp3850\ng1\n(g5\nS'fffffNw@'\np3851\ntp3852\nRp3853\nF53.0\ntp3854\na(I7810000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xbev@'\np3855\ntp3856\nRp3857\ng3853\nF202.0\ntp3858\na(I7820000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xc8v@'\np3859\ntp3860\nRp3861\ng3853\nF393.0\ntp3862\na(I7830000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xd4v@'\np3863\ntp3864\nRp3865\ng3853\nF376.0\ntp3866\na(I7840000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xb8v@'\np3867\ntp3868\nRp3869\ng3853\nF424.0\ntp3870\na(I7850000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdcv@'\np3871\ntp3872\nRp3873\ng3853\nF388.0\ntp3874\na(I7860000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xafv@'\np3875\ntp3876\nRp3877\ng3853\nF374.0\ntp3878\na(I7870000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xd0v@'\np3879\ntp3880\nRp3881\ng3853\nF409.0\ntp3882\na(I7880000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x03w@'\np3883\ntp3884\nRp3885\ng3853\nF367.0\ntp3886\na(I7890000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xb2v@'\np3887\ntp3888\nRp3889\ng3853\nF420.0\ntp3890\na(I7900000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xd5v@'\np3891\ntp3892\nRp3893\ng3853\nF384.0\ntp3894\na(I7910000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xebv@'\np3895\ntp3896\nRp3897\ng3853\nF335.0\ntp3898\na(I7920000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xc6v@'\np3899\ntp3900\nRp3901\ng3853\nF289.0\ntp3902\na(I7930000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xafv@'\np3903\ntp3904\nRp3905\ng3853\nF402.0\ntp3906\na(I7940000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xcfv@'\np3907\ntp3908\nRp3909\ng3853\nF410.0\ntp3910\na(I7950000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xccv@'\np3911\ntp3912\nRp3913\ng3853\nF413.0\ntp3914\na(I7960000\ng1\n(g5\nS'fffff\\xbav@'\np3915\ntp3916\nRp3917\ng3853\nF386.0\ntp3918\na(I7970000\ng1\n(g5\nS'q=\\n\\xd7\\xa3dv@'\np3919\ntp3920\nRp3921\ng3853\nF321.0\ntp3922\na(I7980000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8Jv@'\np3923\ntp3924\nRp3925\ng3853\nF291.0\ntp3926\na(I7990000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGav@'\np3927\ntp3928\nRp3929\ng3853\nF436.0\ntp3930\na(I8000000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#v@'\np3931\ntp3932\nRp3933\ng3853\nF264.0\ntp3934\na(I8010000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGav@'\np3935\ntp3936\nRp3937\ng3853\nF420.0\ntp3938\na(I8020000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14Zv@'\np3939\ntp3940\nRp3941\ng3853\nF336.0\ntp3942\na(I8030000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccTv@'\np3943\ntp3944\nRp3945\ng3853\nF351.0\ntp3946\na(I8040000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}v@'\np3947\ntp3948\nRp3949\ng3853\nF377.0\ntp3950\na(I8050000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xc0v@'\np3951\ntp3952\nRp3953\ng3853\nF419.0\ntp3954\na(I8060000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xb1v@'\np3955\ntp3956\nRp3957\ng3853\nF351.0\ntp3958\na(I8070000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5Pv@'\np3959\ntp3960\nRp3961\ng3853\nF279.0\ntp3962\na(I8080000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ<v@'\np3963\ntp3964\nRp3965\ng3853\nF325.0\ntp3966\na(I8090000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fJv@'\np3967\ntp3968\nRp3969\ng3853\nF304.0\ntp3970\na(I8100000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zLv@'\np3971\ntp3972\nRp3973\ng3853\nF404.0\ntp3974\na(I8110000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xf0u@'\np3975\ntp3976\nRp3977\ng3853\nF402.0\ntp3978\na(I8120000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xd9u@'\np3979\ntp3980\nRp3981\ng3853\nF416.0\ntp3982\na(I8130000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xd6u@'\np3983\ntp3984\nRp3985\ng3853\nF372.0\ntp3986\na(I8140000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe8u@'\np3987\ntp3988\nRp3989\ng3853\nF413.0\ntp3990\na(I8150000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xd1u@'\np3991\ntp3992\nRp3993\ng3853\nF292.0\ntp3994\na(I8160000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xe4u@'\np3995\ntp3996\nRp3997\ng3853\nF395.0\ntp3998\na(I8170000\ng1\n(g5\nS'33333\\xf3u@'\np3999\ntp4000\nRp4001\ng3853\nF350.0\ntp4002\na(I8180000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xd0u@'\np4003\ntp4004\nRp4005\ng3853\nF316.0\ntp4006\na(I8190000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xdeu@'\np4007\ntp4008\nRp4009\ng3853\nF387.0\ntp4010\na(I8200000\ng1\n(g5\nS'33333\\xcfu@'\np4011\ntp4012\nRp4013\ng3853\nF358.0\ntp4014\na(I8210000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xcfu@'\np4015\ntp4016\nRp4017\ng3853\nF409.0\ntp4018\na(I8220000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x91u@'\np4019\ntp4020\nRp4021\ng3853\nF71.0\ntp4022\na(I8230000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeWu@'\np4023\ntp4024\nRp4025\ng3853\nF396.0\ntp4026\na(I8240000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00Du@'\np4027\ntp4028\nRp4029\ng3853\nF384.0\ntp4030\na(I8250000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14:u@'\np4031\ntp4032\nRp4033\ng3853\nF371.0\ntp4034\na(I8260000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xect@'\np4035\ntp4036\nRp4037\ng3853\nF243.0\ntp4038\na(I8270000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x87t@'\np4039\ntp4040\nRp4041\ng3853\nF51.0\ntp4042\na(I8280000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xaet@'\np4043\ntp4044\nRp4045\ng3853\nF407.0\ntp4046\na(I8290000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd3t@'\np4047\ntp4048\nRp4049\ng3853\nF431.0\ntp4050\na(I8300000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ,u@'\np4051\ntp4052\nRp4053\ng3853\nF420.0\ntp4054\na(I8310000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG9u@'\np4055\ntp4056\nRp4057\ng3853\nF358.0\ntp4058\na(I8320000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x0cu@'\np4059\ntp4060\nRp4061\ng3853\nF215.0\ntp4062\na(I8330000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x0fu@'\np4063\ntp4064\nRp4065\ng3853\nF413.0\ntp4066\na(I8340000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\ru@'\np4067\ntp4068\nRp4069\ng3853\nF415.0\ntp4070\na(I8350000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGyu@'\np4071\ntp4072\nRp4073\ng3853\nF385.0\ntp4074\na(I8360000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xb0u@'\np4075\ntp4076\nRp4077\ng3853\nF408.0\ntp4078\na(I8370000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x05v@'\np4079\ntp4080\nRp4081\ng3853\nF385.0\ntp4082\na(I8380000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x1fv@'\np4083\ntp4084\nRp4085\ng3853\nF416.0\ntp4086\na(I8390000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00 v@'\np4087\ntp4088\nRp4089\ng3853\nF418.0\ntp4090\na(I8400000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2Iv@'\np4091\ntp4092\nRp4093\ng3853\nF404.0\ntp4094\na(I8410000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccTv@'\np4095\ntp4096\nRp4097\ng3853\nF420.0\ntp4098\na(I8420000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQhv@'\np4099\ntp4100\nRp4101\ng3853\nF431.0\ntp4102\na(I8430000\ng1\n(g5\nS'=\\n\\xd7\\xa3pYv@'\np4103\ntp4104\nRp4105\ng3853\nF415.0\ntp4106\na(I8440000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG]v@'\np4107\ntp4108\nRp4109\ng3853\nF407.0\ntp4110\na(I8450000\ng1\n(g5\nS'=\\n\\xd7\\xa3pev@'\np4111\ntp4112\nRp4113\ng3853\nF397.0\ntp4114\na(I8460000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85sv@'\np4115\ntp4116\nRp4117\ng3853\nF333.0\ntp4118\na(I8470000\ng1\n(g5\nS'\\n\\xd7\\xa3p=nv@'\np4119\ntp4120\nRp4121\ng3853\nF401.0\ntp4122\na(I8480000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x82v@'\np4123\ntp4124\nRp4125\ng3853\nF424.0\ntp4126\na(I8490000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xf2v@'\np4127\ntp4128\nRp4129\ng3853\nF795.0\ntp4130\na(I8500000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x05w@'\np4131\ntp4132\nRp4133\ng3853\nF421.0\ntp4134\na(I8510000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x15w@'\np4135\ntp4136\nRp4137\ng3853\nF399.0\ntp4138\na(I8520000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x14w@'\np4139\ntp4140\nRp4141\ng3853\nF402.0\ntp4142\na(I8530000\ng1\n(g5\nS'fffffjw@'\np4143\ntp4144\nRp4145\ng1\n(g5\nS'H\\xe1z\\x14\\xaekw@'\np4146\ntp4147\nRp4148\nF362.0\ntp4149\na(I8540000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xddw@'\np4150\ntp4151\nRp4152\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xddw@'\np4153\ntp4154\nRp4155\nF404.0\ntp4156\na(I8550000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xdcw@'\np4157\ntp4158\nRp4159\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xe0w@'\np4160\ntp4161\nRp4162\nF381.0\ntp4163\na(I8560000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xd3w@'\np4164\ntp4165\nRp4166\ng4162\nF334.0\ntp4167\na(I8570000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb8w@'\np4168\ntp4169\nRp4170\ng4162\nF122.0\ntp4171\na(I8580000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x13x@'\np4172\ntp4173\nRp4174\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x13x@'\np4175\ntp4176\nRp4177\nF433.0\ntp4178\na(I8590000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ4x@'\np4179\ntp4180\nRp4181\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ4x@'\np4182\ntp4183\nRp4184\nF262.0\ntp4185\na(I8600000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x17x@'\np4186\ntp4187\nRp4188\ng1\n(g5\nS'\\xaeG\\xe1z\\x14:x@'\np4189\ntp4190\nRp4191\nF177.0\ntp4192\na(I8610000\ng1\n(g5\nS'=\\n\\xd7\\xa3p%x@'\np4193\ntp4194\nRp4195\ng4191\nF412.0\ntp4196\na(I8620000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xcaw@'\np4197\ntp4198\nRp4199\ng4191\nF221.0\ntp4200\na(I8630000\ng1\n(g5\nS'33333\\xbfw@'\np4201\ntp4202\nRp4203\ng4191\nF424.0\ntp4204\na(I8640000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x8dw@'\np4205\ntp4206\nRp4207\ng4191\nF283.0\ntp4208\na(I8650000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x8ew@'\np4209\ntp4210\nRp4211\ng4191\nF398.0\ntp4212\na(I8660000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x8dw@'\np4213\ntp4214\nRp4215\ng4191\nF388.0\ntp4216\na(I8670000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x92w@'\np4217\ntp4218\nRp4219\ng4191\nF428.0\ntp4220\na(I8680000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(|w@'\np4221\ntp4222\nRp4223\ng4191\nF297.0\ntp4224\na(I8690000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1zw@'\np4225\ntp4226\nRp4227\ng4191\nF418.0\ntp4228\na(I8700000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9cw@'\np4229\ntp4230\nRp4231\ng4191\nF400.0\ntp4232\na(I8710000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x91w@'\np4233\ntp4234\nRp4235\ng4191\nF441.0\ntp4236\na(I8720000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x9ew@'\np4237\ntp4238\nRp4239\ng4191\nF378.0\ntp4240\na(I8730000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x9fw@'\np4241\ntp4242\nRp4243\ng4191\nF419.0\ntp4244\na(I8740000\ng1\n(g5\nS'fffff\\xa6w@'\np4245\ntp4246\nRp4247\ng4191\nF414.0\ntp4248\na(I8750000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9ew@'\np4249\ntp4250\nRp4251\ng4191\nF293.0\ntp4252\na(I8760000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd4w@'\np4253\ntp4254\nRp4255\ng4191\nF374.0\ntp4256\na(I8770000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x8bw@'\np4257\ntp4258\nRp4259\ng4191\nF357.0\ntp4260\na(I8780000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xbfw@'\np4261\ntp4262\nRp4263\ng4191\nF427.0\ntp4264\na(I8790000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb4w@'\np4265\ntp4266\nRp4267\ng4191\nF300.0\ntp4268\na(I8800000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x96w@'\np4269\ntp4270\nRp4271\ng4191\nF150.0\ntp4272\na(I8810000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2qw@'\np4273\ntp4274\nRp4275\ng4191\nF120.0\ntp4276\na(I8820000\ng1\n(g5\nS'33333{w@'\np4277\ntp4278\nRp4279\ng4191\nF428.0\ntp4280\na(I8830000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f6w@'\np4281\ntp4282\nRp4283\ng4191\nF280.0\ntp4284\na(I8840000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85cw@'\np4285\ntp4286\nRp4287\ng4191\nF425.0\ntp4288\na(I8850000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x18w@'\np4289\ntp4290\nRp4291\ng4191\nF377.0\ntp4292\na(I8860000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebAw@'\np4293\ntp4294\nRp4295\ng4191\nF277.0\ntp4296\na(I8870000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(Dw@'\np4297\ntp4298\nRp4299\ng4191\nF383.0\ntp4300\na(I8880000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8Zw@'\np4301\ntp4302\nRp4303\ng4191\nF337.0\ntp4304\na(I8890000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x84w@'\np4305\ntp4306\nRp4307\ng4191\nF416.0\ntp4308\na(I8900000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x8cw@'\np4309\ntp4310\nRp4311\ng4191\nF345.0\ntp4312\na(I8910000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xbdw@'\np4313\ntp4314\nRp4315\ng4191\nF399.0\ntp4316\na(I8920000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xd0w@'\np4317\ntp4318\nRp4319\ng4191\nF390.0\ntp4320\na(I8930000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xbfw@'\np4321\ntp4322\nRp4323\ng4191\nF392.0\ntp4324\na(I8940000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xbew@'\np4325\ntp4326\nRp4327\ng4191\nF399.0\ntp4328\na(I8950000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xd6w@'\np4329\ntp4330\nRp4331\ng4191\nF406.0\ntp4332\na(I8960000\ng1\n(g5\nS'33333\\xf3w@'\np4333\ntp4334\nRp4335\ng4191\nF367.0\ntp4336\na(I8970000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xecw@'\np4337\ntp4338\nRp4339\ng4191\nF427.0\ntp4340\na(I8980000\ng1\n(g5\nS'33333\\xcbw@'\np4341\ntp4342\nRp4343\ng4191\nF409.0\ntp4344\na(I8990000\ng1\n(g5\nS'33333\\xcfw@'\np4345\ntp4346\nRp4347\ng4191\nF270.0\ntp4348\na(I9000000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xccw@'\np4349\ntp4350\nRp4351\ng4191\nF395.0\ntp4352\na(I9010000\ng1\n(g5\nS'33333\\xcbw@'\np4353\ntp4354\nRp4355\ng4191\nF424.0\ntp4356\na(I9020000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xcfw@'\np4357\ntp4358\nRp4359\ng4191\nF394.0\ntp4360\na(I9030000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xd9w@'\np4361\ntp4362\nRp4363\ng4191\nF371.0\ntp4364\na(I9040000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xf6w@'\np4365\ntp4366\nRp4367\ng4191\nF419.0\ntp4368\na(I9050000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x08x@'\np4369\ntp4370\nRp4371\ng4191\nF399.0\ntp4372\na(I9060000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xe7w@'\np4373\ntp4374\nRp4375\ng4191\nF420.0\ntp4376\na(I9070000\ng1\n(g5\nS'33333\\xd7w@'\np4377\ntp4378\nRp4379\ng4191\nF411.0\ntp4380\na(I9080000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xdbw@'\np4381\ntp4382\nRp4383\ng4191\nF431.0\ntp4384\na(I9090000\ng1\n(g5\nS'fffff\\x02x@'\np4385\ntp4386\nRp4387\ng4191\nF384.0\ntp4388\na(I9100000\ng1\n(g5\nS'33333\\xebw@'\np4389\ntp4390\nRp4391\ng4191\nF294.0\ntp4392\na(I9110000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG-x@'\np4393\ntp4394\nRp4395\ng4191\nF293.0\ntp4396\na(I9120000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x1cx@'\np4397\ntp4398\nRp4399\ng1\n(g5\nS'\\xd7\\xa3p=\\nGx@'\np4400\ntp4401\nRp4402\nF162.0\ntp4403\na(I9130000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xe2w@'\np4404\ntp4405\nRp4406\ng4402\nF379.0\ntp4407\na(I9140000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xf2w@'\np4408\ntp4409\nRp4410\ng4402\nF417.0\ntp4411\na(I9150000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xfew@'\np4412\ntp4413\nRp4414\ng4402\nF412.0\ntp4415\na(I9160000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x11x@'\np4416\ntp4417\nRp4418\ng4402\nF320.0\ntp4419\na(I9170000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0bx@'\np4420\ntp4421\nRp4422\ng4402\nF303.0\ntp4423\na(I9180000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xdbw@'\np4424\ntp4425\nRp4426\ng4402\nF417.0\ntp4427\na(I9190000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xf2w@'\np4428\ntp4429\nRp4430\ng4402\nF432.0\ntp4431\na(I9200000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xdcw@'\np4432\ntp4433\nRp4434\ng4402\nF260.0\ntp4435\na(I9210000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xd8w@'\np4436\ntp4437\nRp4438\ng4402\nF412.0\ntp4439\na(I9220000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xa5w@'\np4440\ntp4441\nRp4442\ng4402\nF301.0\ntp4443\na(I9230000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85ww@'\np4444\ntp4445\nRp4446\ng4402\nF387.0\ntp4447\na(I9240000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\sw@'\np4448\ntp4449\nRp4450\ng4402\nF417.0\ntp4451\na(I9250000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14Vw@'\np4452\ntp4453\nRp4454\ng4402\nF393.0\ntp4455\na(I9260000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQTw@'\np4456\ntp4457\nRp4458\ng4402\nF381.0\ntp4459\na(I9270000\ng1\n(g5\nS'\\xaeG\\xe1z\\x142w@'\np4460\ntp4461\nRp4462\ng4402\nF342.0\ntp4463\na(I9280000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2Ew@'\np4464\ntp4465\nRp4466\ng4402\nF421.0\ntp4467\na(I9290000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1Jw@'\np4468\ntp4469\nRp4470\ng4402\nF399.0\ntp4471\na(I9300000\ng1\n(g5\nS'fffff>w@'\np4472\ntp4473\nRp4474\ng4402\nF374.0\ntp4475\na(I9310000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x1fw@'\np4476\ntp4477\nRp4478\ng4402\nF383.0\ntp4479\na(I9320000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x08w@'\np4480\ntp4481\nRp4482\ng4402\nF382.0\ntp4483\na(I9330000\ng1\n(g5\nS'fffff*w@'\np4484\ntp4485\nRp4486\ng4402\nF341.0\ntp4487\na(I9340000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8*w@'\np4488\ntp4489\nRp4490\ng4402\nF403.0\ntp4491\na(I9350000\ng1\n(g5\nS'\\xd7\\xa3p=\\nSw@'\np4492\ntp4493\nRp4494\ng4402\nF399.0\ntp4495\na(I9360000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf0v@'\np4496\ntp4497\nRp4498\ng4402\nF84.0\ntp4499\na(I9370000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xf9v@'\np4500\ntp4501\nRp4502\ng4402\nF422.0\ntp4503\na(I9380000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85Kw@'\np4504\ntp4505\nRp4506\ng4402\nF413.0\ntp4507\na(I9390000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x17w@'\np4508\ntp4509\nRp4510\ng4402\nF408.0\ntp4511\na(I9400000\ng1\n(g5\nS'\\xd7\\xa3p=\\nkw@'\np4512\ntp4513\nRp4514\ng4402\nF406.0\ntp4515\na(I9410000\ng1\n(g5\nS'=\\n\\xd7\\xa3p]w@'\np4516\ntp4517\nRp4518\ng4402\nF423.0\ntp4519\na(I9420000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccdw@'\np4520\ntp4521\nRp4522\ng4402\nF425.0\ntp4523\na(I9430000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeKw@'\np4524\ntp4525\nRp4526\ng4402\nF224.0\ntp4527\na(I9440000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fJw@'\np4528\ntp4529\nRp4530\ng4402\nF406.0\ntp4531\na(I9450000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85Ww@'\np4532\ntp4533\nRp4534\ng4402\nF411.0\ntp4535\na(I9460000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Aw@'\np4536\ntp4537\nRp4538\ng4402\nF406.0\ntp4539\na(I9470000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1Jw@'\np4540\ntp4541\nRp4542\ng4402\nF232.0\ntp4543\na(I9480000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccDw@'\np4544\ntp4545\nRp4546\ng4402\nF382.0\ntp4547\na(I9490000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebqw@'\np4548\ntp4549\nRp4550\ng4402\nF346.0\ntp4551\na(I9500000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x9fw@'\np4552\ntp4553\nRp4554\ng4402\nF421.0\ntp4555\na(I9510000\ng1\n(g5\nS'33333\\xafw@'\np4556\ntp4557\nRp4558\ng4402\nF410.0\ntp4559\na(I9520000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x99w@'\np4560\ntp4561\nRp4562\ng4402\nF393.0\ntp4563\na(I9530000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xa1w@'\np4564\ntp4565\nRp4566\ng4402\nF404.0\ntp4567\na(I9540000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xb0w@'\np4568\ntp4569\nRp4570\ng4402\nF433.0\ntp4571\na(I9550000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xccw@'\np4572\ntp4573\nRp4574\ng4402\nF246.0\ntp4575\na(I9560000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xb8w@'\np4576\ntp4577\nRp4578\ng4402\nF334.0\ntp4579\na(I9570000\ng1\n(g5\nS'33333{w@'\np4580\ntp4581\nRp4582\ng4402\nF410.0\ntp4583\na(I9580000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebuw@'\np4584\ntp4585\nRp4586\ng4402\nF401.0\ntp4587\na(I9590000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x98w@'\np4588\ntp4589\nRp4590\ng4402\nF354.0\ntp4591\na(I9600000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xb5w@'\np4592\ntp4593\nRp4594\ng4402\nF408.0\ntp4595\na(I9610000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xb9w@'\np4596\ntp4597\nRp4598\ng4402\nF424.0\ntp4599\na(I9620000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xacw@'\np4600\ntp4601\nRp4602\ng4402\nF346.0\ntp4603\na(I9630000\ng1\n(g5\nS'\\n\\xd7\\xa3p=bw@'\np4604\ntp4605\nRp4606\ng4402\nF113.0\ntp4607\na(I9640000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x81w@'\np4608\ntp4609\nRp4610\ng4402\nF424.0\ntp4611\na(I9650000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xbdw@'\np4612\ntp4613\nRp4614\ng4402\nF413.0\ntp4615\na(I9660000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xacw@'\np4616\ntp4617\nRp4618\ng4402\nF350.0\ntp4619\na(I9670000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xb3w@'\np4620\ntp4621\nRp4622\ng4402\nF423.0\ntp4623\na(I9680000\ng1\n(g5\nS'33333\\xa7w@'\np4624\ntp4625\nRp4626\ng4402\nF180.0\ntp4627\na(I9684338\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xa5w@'\np4628\ntp4629\nRp4630\ng4402\nF343.0\ntp4631\na.(lp0\nF5.0\naF0.0\naF0.0\naF2.0\naF0.0\naF1.0\naF2.0\naF2.0\naF0.0\naF0.0\naF2.0\naF1.0\naF1.0\naF1.0\naF1.0\naF2.0\naF4.0\naF1.0\naF3.0\naF0.0\naF4.0\naF1.0\naF3.0\naF0.0\naF0.0\naF3.0\naF1.0\naF0.0\naF0.0\naF1.0\naF1.0\naF2.0\naF0.0\naF2.0\naF0.0\naF4.0\naF2.0\naF6.0\naF1.0\naF2.0\naF0.0\naF0.0\naF2.0\naF2.0\naF0.0\naF3.0\naF3.0\naF0.0\naF0.0\naF1.0\naF1.0\naF2.0\naF2.0\naF1.0\naF1.0\naF5.0\naF2.0\naF2.0\naF2.0\naF2.0\naF1.0\naF1.0\naF3.0\naF0.0\naF3.0\naF1.0\naF1.0\naF2.0\naF3.0\naF1.0\naF2.0\naF1.0\naF3.0\naF2.0\naF2.0\naF0.0\naF1.0\naF7.0\naF1.0\naF3.0\naF1.0\naF3.0\naF0.0\naF0.0\naF1.0\naF0.0\naF1.0\naF1.0\naF1.0\naF2.0\naF3.0\naF0.0\naF0.0\naF1.0\naF0.0\naF2.0\naF1.0\naF2.0\naF4.0\naF2.0\naF1.0\naF1.0\naF0.0\naF3.0\naF0.0\naF0.0\naF1.0\naF1.0\naF5.0\naF1.0\naF0.0\naF1.0\naF2.0\naF3.0\naF0.0\naF1.0\naF3.0\naF0.0\naF0.0\naF2.0\naF1.0\naF1.0\naF1.0\naF2.0\naF5.0\naF0.0\naF3.0\naF4.0\naF2.0\naF1.0\naF2.0\naF0.0\naF2.0\naF1.0\naF3.0\naF2.0\naF0.0\naF0.0\naF3.0\naF4.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF1.0\naF1.0\naF0.0\naF2.0\naF2.0\naF1.0\naF4.0\naF2.0\naF0.0\naF0.0\naF0.0\naF2.0\naF1.0\naF0.0\naF4.0\naF0.0\naF0.0\naF1.0\naF3.0\naF0.0\naF1.0\naF1.0\naF2.0\naF2.0\naF1.0\naF1.0\naF4.0\naF1.0\naF5.0\naF6.0\naF2.0\naF1.0\naF2.0\naF1.0\naF2.0\naF2.0\naF1.0\naF1.0\naF1.0\naF1.0\naF1.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF1.0\naF2.0\naF2.0\naF4.0\naF1.0\naF2.0\naF0.0\naF3.0\naF3.0\naF1.0\naF2.0\naF2.0\naF1.0\naF0.0\naF1.0\naF3.0\naF3.0\naF2.0\naF1.0\naF1.0\naF2.0\naF3.0\naF1.0\naF0.0\naF0.0\naF2.0\naF2.0\naF3.0\naF3.0\naF0.0\naF0.0\naF0.0\naF3.0\naF2.0\naF2.0\naF0.0\naF0.0\naF1.0\naF1.0\naF1.0\naF1.0\naF3.0\naF1.0\naF1.0\naF3.0\naF1.0\naF1.0\naF3.0\naF2.0\naF0.0\naF0.0\naF0.0\naF2.0\naF2.0\naF0.0\naF3.0\naF0.0\naF2.0\naF1.0\naF0.0\naF0.0\naF2.0\naF0.0\naF3.0\naF0.0\naF3.0\naF0.0\naF4.0\naF0.0\naF2.0\naF0.0\naF2.0\naF2.0\naF3.0\naF2.0\naF2.0\naF0.0\naF2.0\naF2.0\naF3.0\naF1.0\naF1.0\naF1.0\naF3.0\naF1.0\naF4.0\naF3.0\naF0.0\naF3.0\naF1.0\naF1.0\naF2.0\naF2.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF1.0\naF2.0\naF0.0\naF0.0\naF2.0\naF2.0\naF4.0\naF0.0\naF2.0\naF1.0\naF6.0\naF3.0\naF1.0\naF0.0\naF0.0\naF3.0\naF3.0\naF1.0\naF2.0\naF1.0\naF1.0\naF4.0\naF0.0\naF0.0\naF2.0\naF0.0\naF1.0\naF3.0\naF1.0\naF1.0\naF3.0\naF2.0\naF1.0\naF3.0\naF0.0\naF0.0\naF0.0\naF3.0\naF2.0\naF3.0\naF1.0\naF3.0\naF1.0\naF4.0\naF0.0\naF4.0\naF3.0\naF3.0\naF1.0\naF2.0\naF2.0\naF2.0\naF0.0\naF0.0\naF2.0\naF3.0\naF0.0\naF2.0\naF3.0\naF0.0\naF0.0\naF0.0\naF2.0\naF2.0\naF1.0\naF0.0\naF2.0\naF1.0\naF2.0\naF0.0\naF3.0\naF0.0\naF1.0\naF3.0\naF0.0\naF2.0\naF0.0\naF0.0\naF2.0\naF0.0\naF2.0\naF0.0\naF2.0\naF2.0\naF1.0\naF0.0\naF0.0\naF0.0\naF5.0\naF1.0\naF0.0\naF0.0\naF3.0\naF7.0\naF0.0\naF3.0\naF1.0\naF2.0\naF0.0\naF0.0\naF8.0\naF2.0\naF2.0\naF2.0\naF0.0\naF2.0\naF1.0\naF2.0\naF0.0\naF1.0\naF1.0\naF0.0\naF1.0\naF4.0\naF2.0\naF0.0\naF2.0\naF2.0\naF4.0\naF0.0\naF3.0\naF1.0\naF3.0\naF2.0\naF1.0\naF1.0\naF2.0\naF2.0\naF1.0\naF2.0\naF0.0\naF1.0\naF2.0\naF2.0\naF0.0\naF1.0\naF2.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF1.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF3.0\naF2.0\naF1.0\naF6.0\naF1.0\naF0.0\naF3.0\naF3.0\naF2.0\naF0.0\naF3.0\naF0.0\naF0.0\naF3.0\naF0.0\naF2.0\naF3.0\naF1.0\naF4.0\naF2.0\naF1.0\naF2.0\naF0.0\naF2.0\naF4.0\naF1.0\naF1.0\naF3.0\naF4.0\naF2.0\naF0.0\naF1.0\naF2.0\naF0.0\naF4.0\naF3.0\naF4.0\naF3.0\naF3.0\naF2.0\naF0.0\naF2.0\naF3.0\naF0.0\naF1.0\naF2.0\naF7.0\naF4.0\naF3.0\naF2.0\naF1.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF4.0\naF1.0\naF4.0\naF1.0\naF1.0\naF2.0\naF0.0\naF0.0\naF0.0\naF3.0\naF2.0\naF1.0\naF1.0\naF3.0\naF0.0\naF1.0\naF2.0\naF1.0\naF1.0\naF1.0\naF2.0\naF0.0\naF1.0\naF5.0\naF1.0\naF2.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF2.0\naF2.0\naF2.0\naF3.0\naF2.0\naF1.0\naF3.0\naF2.0\naF3.0\naF1.0\naF4.0\naF0.0\naF0.0\naF1.0\naF1.0\naF0.0\naF1.0\naF0.0\naF2.0\naF3.0\naF3.0\naF0.0\naF2.0\naF3.0\naF1.0\naF1.0\naF2.0\naF3.0\naF2.0\naF0.0\naF1.0\naF5.0\naF1.0\naF4.0\naF4.0\naF1.0\naF0.0\naF2.0\naF0.0\naF3.0\naF2.0\naF4.0\naF1.0\naF5.0\naF3.0\naF2.0\naF6.0\naF0.0\naF3.0\naF1.0\naF1.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF3.0\naF1.0\naF2.0\naF2.0\naF1.0\naF1.0\naF2.0\naF3.0\naF2.0\naF2.0\naF2.0\naF2.0\naF3.0\naF4.0\naF1.0\naF3.0\naF0.0\naF3.0\naF0.0\naF5.0\naF0.0\naF0.0\naF0.0\naF1.0\naF2.0\naF3.0\naF1.0\naF0.0\naF2.0\naF2.0\naF1.0\naF2.0\naF1.0\naF0.0\naF1.0\naF4.0\naF2.0\naF0.0\naF0.0\naF4.0\naF2.0\naF3.0\naF1.0\naF1.0\naF0.0\naF4.0\naF3.0\naF0.0\naF0.0\naF1.0\naF3.0\naF2.0\naF1.0\naF0.0\naF3.0\naF3.0\naF2.0\naF2.0\naF0.0\naF0.0\naF2.0\naF1.0\naF0.0\naF3.0\naF2.0\naF2.0\naF2.0\naF0.0\naF2.0\naF0.0\naF2.0\naF1.0\naF2.0\naF3.0\naF1.0\naF2.0\naF0.0\naF3.0\naF0.0\naF2.0\naF3.0\naF3.0\naF2.0\naF3.0\naF3.0\naF0.0\naF0.0\naF8.0\naF0.0\naF1.0\naF2.0\naF8.0\naF2.0\naF0.0\naF5.0\naF3.0\naF0.0\naF4.0\naF1.0\naF2.0\naF3.0\naF2.0\naF9.0\naF2.0\naF0.0\naF4.0\naF3.0\naF2.0\naF1.0\naF1.0\naF4.0\naF0.0\naF4.0\naF2.0\naF2.0\naF1.0\naF0.0\naF2.0\naF0.0\naF2.0\naF1.0\naF0.0\naF2.0\naF2.0\naF0.0\naF0.0\naF1.0\naF3.0\naF4.0\naF3.0\naF2.0\naF0.0\naF1.0\naF3.0\naF1.0\naF1.0\naF1.0\naF2.0\naF1.0\naF1.0\naF0.0\naF4.0\naF2.0\naF0.0\naF0.0\naF2.0\naF0.0\naF2.0\naF2.0\naF3.0\naF6.0\naF4.0\naF2.0\naF4.0\naF4.0\naF1.0\naF0.0\naF1.0\naF1.0\naF1.0\naF0.0\naF3.0\naF0.0\naF0.0\naF0.0\naF2.0\naF1.0\naF1.0\naF0.0\naF1.0\naF0.0\naF3.0\naF2.0\naF3.0\naF3.0\naF3.0\naF0.0\naF2.0\naF2.0\naF3.0\naF1.0\naF2.0\naF5.0\naF2.0\naF0.0\naF2.0\naF0.0\naF1.0\naF1.0\naF2.0\naF2.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF1.0\naF1.0\naF2.0\naF0.0\naF3.0\naF2.0\naF1.0\naF3.0\naF2.0\naF2.0\naF0.0\naF2.0\naF3.0\naF1.0\naF1.0\naF0.0\naF0.0\naF4.0\naF2.0\naF1.0\naF1.0\naF2.0\naF2.0\naF2.0\naF2.0\naF3.0\naF2.0\naF2.0\naF0.0\naF4.0\naF2.0\naF1.0\naF1.0\naF0.0\naF1.0\naF1.0\naF0.0\naF0.0\naF1.0\naF2.0\naF2.0\naF2.0\naF3.0\naF0.0\naF2.0\naF1.0\naF0.0\naF1.0\naF8.0\naF0.0\naF1.0\naF3.0\naF1.0\naF2.0\naF2.0\naF0.0\naF0.0\naF3.0\naF0.0\naF2.0\naF2.0\naF0.0\naF0.0\naF2.0\naF0.0\naF1.0\naF1.0\naF1.0\naF0.0\naF2.0\naF2.0\naF0.0\naF1.0\naF1.0\naF0.0\naF3.0\naF2.0\naF2.0\naF0.0\naF1.0\naF0.0\naF3.0\naF2.0\naF0.0\naF2.0\naF0.0\naF2.0\naF2.0\naF0.0\naF3.0\naF0.0\naF1.0\naF2.0\naF1.0\naF1.0\naF2.0\naF1.0\naF2.0\naF1.0\naF2.0\naF0.0\naF1.0\naF6.0\naF0.0\naF2.0\naF1.0\naF1.0\naF1.0\naF0.0\naF0.0\naF0.0\naF3.0\naF0.0\naF2.0\naF3.0\naF4.0\naF0.0\naF1.0\naF1.0\naF1.0\naF2.0\naF1.0\naF1.0\naF3.0\naF1.0\naF4.0\naF1.0\naF4.0\naF0.0\naF1.0\naF0.0\naF5.0\naF4.0\naF3.0\naF2.0\naF4.0\naF0.0\naF1.0\naF1.0\naF0.0\naF2.0\naF0.0\naF3.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF3.0\naF3.0\naF2.0\naF0.0\naF2.0\naF1.0\naF0.0\naF2.0\naF0.0\naF3.0\naF0.0\naF0.0\naF0.0\naF2.0\naF2.0\naF4.0\naF2.0\naF2.0\naF1.0\naF0.0\naF0.0\naF1.0\naF0.0\naF1.0\naF1.0\naF0.0\naF2.0\naF1.0\naF4.0\naF3.0\naF0.0\naF1.0\naF3.0\naF2.0\naF0.0\naF0.0\naF4.0\naF5.0\naF2.0\naF3.0\naF3.0\naF1.0\naF2.0\naF2.0\naF2.0\naF1.0\naF1.0\naF1.0\naF2.0\naF2.0\naF2.0\naF0.0\naF3.0\naF1.0\naF0.0\naF2.0\naF0.0\naF1.0\naF2.0\naF2.0\naF0.0\naF5.0\naF1.0\naF2.0\naF1.0\naF2.0\naF2.0\naF4.0\naF2.0\naF1.0\naF1.0\naF0.0\naF2.0\naF2.0\naF4.0\naF4.0\naF0.0\naF0.0\naF2.0\naF3.0\naF3.0\naF1.0\naF3.0\naF2.0\naF5.0\naF1.0\naF2.0\naF2.0\naF3.0\naF2.0\naF4.0\naF1.0\naF0.0\naF1.0\naF0.0\naF4.0\naF4.0\naF1.0\naF3.0\naF3.0\naF0.0\naF4.0\naF1.0\naF4.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF4.0\naF3.0\naF4.0\naF1.0\naF2.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF3.0\naF1.0\naF3.0\naF0.0\naF0.0\naF0.0\naF3.0\naF1.0\naF0.0\naF4.0\naF2.0\naF1.0\naF1.0\naF6.0\naF0.0\naF1.0\naF0.0\naF3.0\naF2.0\naF1.0\naF4.0\naF4.0\naF4.0\naF1.0\naF3.0\naF2.0\naF5.0\naF0.0\naF0.0\naF3.0\naF5.0\naF0.0\naF2.0\naF2.0\naF2.0\naF3.0\naF0.0\naF2.0\naF0.0\naF0.0\naF3.0\naF1.0\naF0.0\naF0.0\naF3.0\naF2.0\naF2.0\naF4.0\naF2.0\naF0.0\naF3.0\naF2.0\naF0.0\naF0.0\naF1.0\naF3.0\naF2.0\naF2.0\naF0.0\naF2.0\naF3.0\naF2.0\naF2.0\naF3.0\naF6.0\naF3.0\naF0.0\naF2.0\naF3.0\naF3.0\naF3.0\naF0.0\naF5.0\naF1.0\naF7.0\naF2.0\naF3.0\naF1.0\naF4.0\naF6.0\naF1.0\naF0.0\naF0.0\naF1.0\naF4.0\naF3.0\naF3.0\naF3.0\naF3.0\naF5.0\naF6.0\naF3.0\naF2.0\naF5.0\naF5.0\naF3.0\naF10.0\naF3.0\naF1.0\naF3.0\naF2.0\naF2.0\naF1.0\naF2.0\naF0.0\naF0.0\naF5.0\naF8.0\naF3.0\naF3.0\naF2.0\naF0.0\naF2.0\naF0.0\naF2.0\naF1.0\naF0.0\naF3.0\naF2.0\naF4.0\naF1.0\naF1.0\naF4.0\naF2.0\naF6.0\naF2.0\naF3.0\naF2.0\naF3.0\naF4.0\naF0.0\naF4.0\naF1.0\naF2.0\naF3.0\naF4.0\naF2.0\naF0.0\naF2.0\naF0.0\naF0.0\naF4.0\naF1.0\naF2.0\naF5.0\naF1.0\naF2.0\naF4.0\naF2.0\naF4.0\naF7.0\naF0.0\naF1.0\naF1.0\naF3.0\naF1.0\naF6.0\naF0.0\naF3.0\naF3.0\naF5.0\naF1.0\naF5.0\naF0.0\naF4.0\naF2.0\naF3.0\naF4.0\naF5.0\naF1.0\naF3.0\naF1.0\naF2.0\naF1.0\naF3.0\naF0.0\naF10.0\naF1.0\naF2.0\naF2.0\naF2.0\naF1.0\naF0.0\naF2.0\naF5.0\naF3.0\naF2.0\naF2.0\naF2.0\naF2.0\naF3.0\naF10.0\naF3.0\naF5.0\naF6.0\naF4.0\naF2.0\naF2.0\naF1.0\naF3.0\naF3.0\naF8.0\naF0.0\naF4.0\naF1.0\naF3.0\naF1.0\naF1.0\naF2.0\naF4.0\naF0.0\naF2.0\naF4.0\naF2.0\naF2.0\naF1.0\naF3.0\naF3.0\naF0.0\naF4.0\naF2.0\naF1.0\naF0.0\naF2.0\naF1.0\naF3.0\naF0.0\naF2.0\naF4.0\naF4.0\naF2.0\naF2.0\naF2.0\naF3.0\naF1.0\naF0.0\naF3.0\naF4.0\naF3.0\naF3.0\naF3.0\naF5.0\naF1.0\naF1.0\naF0.0\naF3.0\naF9.0\naF3.0\naF1.0\naF2.0\naF4.0\naF3.0\naF7.0\naF5.0\naF2.0\naF2.0\naF2.0\naF6.0\naF4.0\naF2.0\naF6.0\naF3.0\naF1.0\naF2.0\naF5.0\naF2.0\naF4.0\naF5.0\naF4.0\naF6.0\naF4.0\naF2.0\naF3.0\naF3.0\naF3.0\naF5.0\naF4.0\naF4.0\naF1.0\naF4.0\naF2.0\naF2.0\naF2.0\naF2.0\naF1.0\naF8.0\naF5.0\naF1.0\naF0.0\naF4.0\naF0.0\naF3.0\naF6.0\naF3.0\naF4.0\naF1.0\naF4.0\naF4.0\naF5.0\naF7.0\naF3.0\naF13.0\naF0.0\naF6.0\naF4.0\naF5.0\naF4.0\naF3.0\naF2.0\naF3.0\naF3.0\naF0.0\naF2.0\naF2.0\naF2.0\naF2.0\naF1.0\naF1.0\naF2.0\naF12.0\naF3.0\naF1.0\naF3.0\naF5.0\naF4.0\naF0.0\naF5.0\naF0.0\naF4.0\naF7.0\naF3.0\naF4.0\naF9.0\naF0.0\naF3.0\naF4.0\naF4.0\naF4.0\naF7.0\naF3.0\naF0.0\naF4.0\naF2.0\naF10.0\naF4.0\naF2.0\naF1.0\naF6.0\naF1.0\naF2.0\naF1.0\naF5.0\naF3.0\naF1.0\naF1.0\naF5.0\naF7.0\naF2.0\naF6.0\naF6.0\naF4.0\naF5.0\naF0.0\naF4.0\naF3.0\naF10.0\naF1.0\naF0.0\naF6.0\naF1.0\naF2.0\naF2.0\naF2.0\naF3.0\naF1.0\naF2.0\naF7.0\naF2.0\naF2.0\naF5.0\naF7.0\naF0.0\naF3.0\naF0.0\naF1.0\naF1.0\naF5.0\naF7.0\naF4.0\naF4.0\naF4.0\naF1.0\naF4.0\naF1.0\naF0.0\naF2.0\naF1.0\naF4.0\naF2.0\naF7.0\naF3.0\naF1.0\naF1.0\naF4.0\naF5.0\naF1.0\naF3.0\naF5.0\naF5.0\naF2.0\naF1.0\naF8.0\naF2.0\naF20.0\naF7.0\naF1.0\naF5.0\naF5.0\naF1.0\naF1.0\naF3.0\naF6.0\naF4.0\naF2.0\naF5.0\naF6.0\naF2.0\naF6.0\naF6.0\naF4.0\naF6.0\naF4.0\naF11.0\naF3.0\naF9.0\naF5.0\naF5.0\naF2.0\naF3.0\naF12.0\naF1.0\naF5.0\naF11.0\naF2.0\naF4.0\naF1.0\naF6.0\naF2.0\naF11.0\naF7.0\naF2.0\naF4.0\naF3.0\naF4.0\naF4.0\naF1.0\naF4.0\naF1.0\naF6.0\naF3.0\naF6.0\naF6.0\naF1.0\naF3.0\naF8.0\naF2.0\naF5.0\naF3.0\naF6.0\naF5.0\naF7.0\naF6.0\naF3.0\naF0.0\naF6.0\naF3.0\naF7.0\naF5.0\naF2.0\naF6.0\naF3.0\naF4.0\naF3.0\naF5.0\naF4.0\naF4.0\naF2.0\naF12.0\naF6.0\naF7.0\naF5.0\naF6.0\naF3.0\naF3.0\naF4.0\naF6.0\naF4.0\naF3.0\naF3.0\naF1.0\naF4.0\naF3.0\naF6.0\naF6.0\naF9.0\naF5.0\naF1.0\naF5.0\naF4.0\naF2.0\naF7.0\naF5.0\naF7.0\naF5.0\naF2.0\naF0.0\naF4.0\naF8.0\naF3.0\naF20.0\naF0.0\naF6.0\naF5.0\naF10.0\naF5.0\naF6.0\naF2.0\naF5.0\naF4.0\naF1.0\naF3.0\naF5.0\naF3.0\naF3.0\naF7.0\naF5.0\naF4.0\naF2.0\naF3.0\naF4.0\naF5.0\naF3.0\naF8.0\naF4.0\naF0.0\naF5.0\naF3.0\naF2.0\naF2.0\naF12.0\naF9.0\naF2.0\naF6.0\naF3.0\naF6.0\naF8.0\naF14.0\naF6.0\naF2.0\naF5.0\naF4.0\naF0.0\naF3.0\naF5.0\naF4.0\naF4.0\naF2.0\naF5.0\naF6.0\naF5.0\naF1.0\naF11.0\naF4.0\naF1.0\naF14.0\naF5.0\naF6.0\naF12.0\naF4.0\naF8.0\naF6.0\naF4.0\naF1.0\naF13.0\naF4.0\naF5.0\naF5.0\naF3.0\naF3.0\naF4.0\naF6.0\naF10.0\naF5.0\naF4.0\naF7.0\naF2.0\naF5.0\naF1.0\naF12.0\naF10.0\naF5.0\naF3.0\naF4.0\naF8.0\naF2.0\naF4.0\naF5.0\naF7.0\naF4.0\naF4.0\naF2.0\naF2.0\naF2.0\naF0.0\naF9.0\naF2.0\naF6.0\naF4.0\naF0.0\naF3.0\naF5.0\naF4.0\naF4.0\naF3.0\naF7.0\naF1.0\naF7.0\naF3.0\naF6.0\naF4.0\naF5.0\naF6.0\naF7.0\naF7.0\naF6.0\naF2.0\naF4.0\naF1.0\naF1.0\naF11.0\naF5.0\naF0.0\naF3.0\naF3.0\naF6.0\naF3.0\naF3.0\naF9.0\naF4.0\naF5.0\naF3.0\naF6.0\naF2.0\naF5.0\naF4.0\naF9.0\naF6.0\naF8.0\naF7.0\naF0.0\naF9.0\naF3.0\naF4.0\naF3.0\naF4.0\naF6.0\naF3.0\naF5.0\naF3.0\naF4.0\naF2.0\naF2.0\naF7.0\naF4.0\naF6.0\naF5.0\naF3.0\naF8.0\naF4.0\naF1.0\naF4.0\naF8.0\naF6.0\naF5.0\naF8.0\naF6.0\naF3.0\naF2.0\naF6.0\naF4.0\naF3.0\naF6.0\naF2.0\naF3.0\naF6.0\naF4.0\naF1.0\naF2.0\naF5.0\naF4.0\naF4.0\naF3.0\naF4.0\naF2.0\naF6.0\naF2.0\naF1.0\naF1.0\naF5.0\naF1.0\naF6.0\naF3.0\naF4.0\naF4.0\naF6.0\naF7.0\naF6.0\naF4.0\naF6.0\naF8.0\naF8.0\naF5.0\naF3.0\naF3.0\naF3.0\naF3.0\naF11.0\naF0.0\naF0.0\naF3.0\naF3.0\naF4.0\naF10.0\naF4.0\naF1.0\naF4.0\naF7.0\naF4.0\naF6.0\naF3.0\naF5.0\naF4.0\naF2.0\naF10.0\naF3.0\naF7.0\naF3.0\naF0.0\naF3.0\naF1.0\naF7.0\naF3.0\naF12.0\naF6.0\naF2.0\naF9.0\naF1.0\naF6.0\naF5.0\naF7.0\naF3.0\naF4.0\naF2.0\naF3.0\naF7.0\naF4.0\naF3.0\naF4.0\naF9.0\naF0.0\naF2.0\naF6.0\naF2.0\naF6.0\naF4.0\naF8.0\naF2.0\naF5.0\naF1.0\naF3.0\naF9.0\naF5.0\naF2.0\naF5.0\naF3.0\naF5.0\naF6.0\naF5.0\naF7.0\naF6.0\naF7.0\naF2.0\naF5.0\naF9.0\naF7.0\naF8.0\naF0.0\naF25.0\naF3.0\naF11.0\naF3.0\naF5.0\naF12.0\naF2.0\naF8.0\naF2.0\naF3.0\naF6.0\naF9.0\naF6.0\naF3.0\naF9.0\naF2.0\naF1.0\naF5.0\naF4.0\naF7.0\naF3.0\naF0.0\naF2.0\naF12.0\naF3.0\naF4.0\naF5.0\naF7.0\naF4.0\naF5.0\naF4.0\naF3.0\naF9.0\naF5.0\naF7.0\naF4.0\naF11.0\naF5.0\naF7.0\naF7.0\naF7.0\naF1.0\naF6.0\naF4.0\naF7.0\naF11.0\naF2.0\naF4.0\naF3.0\naF5.0\naF1.0\naF3.0\naF1.0\naF5.0\naF3.0\naF3.0\naF3.0\naF9.0\naF6.0\naF11.0\naF1.0\naF3.0\naF9.0\naF9.0\naF4.0\naF4.0\naF5.0\naF6.0\naF1.0\naF6.0\naF7.0\naF8.0\naF6.0\naF13.0\naF7.0\naF7.0\naF7.0\naF3.0\naF7.0\naF6.0\naF6.0\naF1.0\naF4.0\naF0.0\naF8.0\naF10.0\naF2.0\naF4.0\naF4.0\naF8.0\naF2.0\naF4.0\naF11.0\naF4.0\naF15.0\naF6.0\naF3.0\naF4.0\naF4.0\naF4.0\naF5.0\naF12.0\naF3.0\naF6.0\naF12.0\naF8.0\naF7.0\naF7.0\naF8.0\naF5.0\naF0.0\naF6.0\naF13.0\naF7.0\naF3.0\naF4.0\naF3.0\naF5.0\naF9.0\naF4.0\naF9.0\naF4.0\naF6.0\naF7.0\naF10.0\naF7.0\naF7.0\naF10.0\naF4.0\naF1.0\naF24.0\naF5.0\naF8.0\naF4.0\naF8.0\naF4.0\naF5.0\naF2.0\naF7.0\naF11.0\naF6.0\naF5.0\naF5.0\naF2.0\naF4.0\naF7.0\naF7.0\naF9.0\naF4.0\naF3.0\naF7.0\naF13.0\naF11.0\naF6.0\naF7.0\naF13.0\naF8.0\naF5.0\naF11.0\naF4.0\naF9.0\naF6.0\naF6.0\naF14.0\naF5.0\naF5.0\naF3.0\naF3.0\naF3.0\naF2.0\naF3.0\naF4.0\naF7.0\naF8.0\naF7.0\naF11.0\naF6.0\naF5.0\naF4.0\naF6.0\naF9.0\naF3.0\naF10.0\naF8.0\naF5.0\naF8.0\naF8.0\naF9.0\naF5.0\naF8.0\naF6.0\naF4.0\naF8.0\naF5.0\naF2.0\naF5.0\naF4.0\naF7.0\naF3.0\naF16.0\naF7.0\naF5.0\naF11.0\naF8.0\naF8.0\naF5.0\naF5.0\naF5.0\naF8.0\naF5.0\naF7.0\naF5.0\naF4.0\naF23.0\naF4.0\naF2.0\naF6.0\naF9.0\naF16.0\naF3.0\naF21.0\naF10.0\naF6.0\naF0.0\naF5.0\naF3.0\naF6.0\naF10.0\naF3.0\naF7.0\naF8.0\naF4.0\naF2.0\naF4.0\naF6.0\naF6.0\naF8.0\naF9.0\naF6.0\naF2.0\naF8.0\naF6.0\naF8.0\naF9.0\naF5.0\naF2.0\naF5.0\naF8.0\naF12.0\naF6.0\naF3.0\naF3.0\naF7.0\naF6.0\naF9.0\naF6.0\naF8.0\naF5.0\naF3.0\naF10.0\naF7.0\naF10.0\naF5.0\naF7.0\naF4.0\naF18.0\naF5.0\naF6.0\naF8.0\naF9.0\naF10.0\naF1.0\naF12.0\naF9.0\naF5.0\naF6.0\naF6.0\naF4.0\naF5.0\naF9.0\naF4.0\naF7.0\naF3.0\naF9.0\naF11.0\naF1.0\naF7.0\naF4.0\naF8.0\naF3.0\naF14.0\naF9.0\naF11.0\naF3.0\naF9.0\naF5.0\naF6.0\naF7.0\naF6.0\naF5.0\naF11.0\naF16.0\naF5.0\naF3.0\naF7.0\naF3.0\naF3.0\naF5.0\naF13.0\naF0.0\naF7.0\naF4.0\naF8.0\naF4.0\naF15.0\naF7.0\naF5.0\naF2.0\naF5.0\naF9.0\naF10.0\naF8.0\naF3.0\naF2.0\naF4.0\naF6.0\naF6.0\naF3.0\naF3.0\naF8.0\naF9.0\naF7.0\naF1.0\naF17.0\naF7.0\naF5.0\naF5.0\naF15.0\naF8.0\naF11.0\naF3.0\naF3.0\naF6.0\naF14.0\naF0.0\naF7.0\naF3.0\naF5.0\naF7.0\naF10.0\naF3.0\naF11.0\naF5.0\naF8.0\naF10.0\naF5.0\naF2.0\naF4.0\naF8.0\naF8.0\naF3.0\naF3.0\naF2.0\naF3.0\naF5.0\naF5.0\naF4.0\naF10.0\naF11.0\naF3.0\naF8.0\naF8.0\naF6.0\naF6.0\naF6.0\naF6.0\naF7.0\naF9.0\naF16.0\naF10.0\naF5.0\naF4.0\naF5.0\naF9.0\naF9.0\naF15.0\naF3.0\naF3.0\naF4.0\naF11.0\naF5.0\naF11.0\naF8.0\naF11.0\naF6.0\naF4.0\naF13.0\naF2.0\naF4.0\naF7.0\naF4.0\naF2.0\naF7.0\naF12.0\naF10.0\naF3.0\naF5.0\naF3.0\naF11.0\naF7.0\naF5.0\naF6.0\naF11.0\naF14.0\naF9.0\naF3.0\naF13.0\naF14.0\naF9.0\naF8.0\naF7.0\naF7.0\naF9.0\naF5.0\naF5.0\naF9.0\naF4.0\naF5.0\naF7.0\naF6.0\naF13.0\naF4.0\naF3.0\naF4.0\naF6.0\naF5.0\naF4.0\naF16.0\naF9.0\naF9.0\naF2.0\naF5.0\naF18.0\naF10.0\naF9.0\naF8.0\naF8.0\naF4.0\naF3.0\naF3.0\naF15.0\naF6.0\naF5.0\naF12.0\naF7.0\naF7.0\naF4.0\naF2.0\naF10.0\naF20.0\naF10.0\naF10.0\naF14.0\naF14.0\naF11.0\naF6.0\naF9.0\naF10.0\naF6.0\naF5.0\naF7.0\naF16.0\naF3.0\naF7.0\naF10.0\naF10.0\naF5.0\naF6.0\naF9.0\naF9.0\naF2.0\naF10.0\naF11.0\naF6.0\naF19.0\naF4.0\naF6.0\naF7.0\naF6.0\naF9.0\naF8.0\naF12.0\naF4.0\naF6.0\naF6.0\naF10.0\naF7.0\naF10.0\naF7.0\naF3.0\naF10.0\naF7.0\naF6.0\naF9.0\naF19.0\naF12.0\naF13.0\naF10.0\naF5.0\naF9.0\naF7.0\naF15.0\naF8.0\naF12.0\naF4.0\naF2.0\naF7.0\naF6.0\naF1.0\naF3.0\naF7.0\naF10.0\naF6.0\naF4.0\naF9.0\naF5.0\naF8.0\naF5.0\naF7.0\naF4.0\naF14.0\naF6.0\naF15.0\naF8.0\naF5.0\naF4.0\naF7.0\naF10.0\naF12.0\naF15.0\naF12.0\naF11.0\naF7.0\naF8.0\naF6.0\naF12.0\naF15.0\naF14.0\naF5.0\naF10.0\naF7.0\naF7.0\naF12.0\naF9.0\naF22.0\naF6.0\naF3.0\naF12.0\naF6.0\naF10.0\naF10.0\naF9.0\naF4.0\naF9.0\naF12.0\naF19.0\naF8.0\naF9.0\naF5.0\naF6.0\naF19.0\naF8.0\naF7.0\naF14.0\naF10.0\naF3.0\naF8.0\naF3.0\naF8.0\naF10.0\naF9.0\naF10.0\naF2.0\naF7.0\naF16.0\naF11.0\naF3.0\naF14.0\naF18.0\naF10.0\naF8.0\naF10.0\naF6.0\naF8.0\naF10.0\naF4.0\naF8.0\naF12.0\naF2.0\naF4.0\naF9.0\naF11.0\naF6.0\naF5.0\naF14.0\naF4.0\naF11.0\naF11.0\naF4.0\naF3.0\naF12.0\naF9.0\naF9.0\naF2.0\naF17.0\naF17.0\naF13.0\naF6.0\naF12.0\naF16.0\naF4.0\naF10.0\naF9.0\naF3.0\naF13.0\naF8.0\naF6.0\naF6.0\naF12.0\naF10.0\naF3.0\naF9.0\naF6.0\naF18.0\naF14.0\naF8.0\naF9.0\naF17.0\naF15.0\naF8.0\naF6.0\naF3.0\naF2.0\naF8.0\naF7.0\naF7.0\naF11.0\naF15.0\naF16.0\naF8.0\naF11.0\naF10.0\naF9.0\naF6.0\naF5.0\naF8.0\naF7.0\naF6.0\naF26.0\naF5.0\naF5.0\naF6.0\naF9.0\naF10.0\naF15.0\naF9.0\naF8.0\naF19.0\naF9.0\naF7.0\naF15.0\naF9.0\naF4.0\naF10.0\naF5.0\naF5.0\naF5.0\naF10.0\naF5.0\naF10.0\naF3.0\naF6.0\naF7.0\naF10.0\naF5.0\naF15.0\naF14.0\naF11.0\naF10.0\naF5.0\naF10.0\naF9.0\naF11.0\naF4.0\naF10.0\naF2.0\naF4.0\naF5.0\naF11.0\naF12.0\naF16.0\naF11.0\naF6.0\naF7.0\naF10.0\naF7.0\naF14.0\naF11.0\naF10.0\naF10.0\naF4.0\naF13.0\naF7.0\naF7.0\naF10.0\naF6.0\naF10.0\naF12.0\naF10.0\naF14.0\naF4.0\naF11.0\naF5.0\naF13.0\naF7.0\naF9.0\naF2.0\naF10.0\naF5.0\naF8.0\naF12.0\naF19.0\naF16.0\naF9.0\naF7.0\naF11.0\naF5.0\naF12.0\naF16.0\naF7.0\naF14.0\naF5.0\naF4.0\naF6.0\naF18.0\naF6.0\naF8.0\naF12.0\naF10.0\naF17.0\naF12.0\naF16.0\naF14.0\naF8.0\naF16.0\naF6.0\naF13.0\naF18.0\naF9.0\naF10.0\naF10.0\naF2.0\naF15.0\naF13.0\naF6.0\naF10.0\naF17.0\naF14.0\naF11.0\naF9.0\naF7.0\naF10.0\naF5.0\naF10.0\naF17.0\naF18.0\naF8.0\naF6.0\naF19.0\naF19.0\naF10.0\naF9.0\naF6.0\naF11.0\naF8.0\naF9.0\naF19.0\naF9.0\naF14.0\naF7.0\naF8.0\naF12.0\naF15.0\naF7.0\naF15.0\naF11.0\naF2.0\naF7.0\naF15.0\naF7.0\naF9.0\naF10.0\naF16.0\naF15.0\naF2.0\naF19.0\naF14.0\naF10.0\naF13.0\naF4.0\naF20.0\naF16.0\naF14.0\naF15.0\naF9.0\naF10.0\naF6.0\naF12.0\naF11.0\naF12.0\naF11.0\naF22.0\naF9.0\naF15.0\naF7.0\naF11.0\naF7.0\naF11.0\naF17.0\naF16.0\naF15.0\naF15.0\naF18.0\naF12.0\naF10.0\naF6.0\naF6.0\naF15.0\naF21.0\naF20.0\naF9.0\naF12.0\naF14.0\naF14.0\naF14.0\naF15.0\naF11.0\naF14.0\naF12.0\naF20.0\naF12.0\naF22.0\naF16.0\naF16.0\naF12.0\naF26.0\naF13.0\naF25.0\naF11.0\naF8.0\naF20.0\naF19.0\naF18.0\naF13.0\naF9.0\naF18.0\naF11.0\naF12.0\naF12.0\naF9.0\naF7.0\naF20.0\naF14.0\naF13.0\naF16.0\naF18.0\naF6.0\naF12.0\naF20.0\naF22.0\naF12.0\naF12.0\naF10.0\naF7.0\naF14.0\naF11.0\naF10.0\naF10.0\naF11.0\naF13.0\naF28.0\naF12.0\naF9.0\naF13.0\naF30.0\naF14.0\naF9.0\naF14.0\naF12.0\naF16.0\naF17.0\naF14.0\naF11.0\naF24.0\naF17.0\naF17.0\naF20.0\naF21.0\naF14.0\naF3.0\naF17.0\naF18.0\naF7.0\naF17.0\naF13.0\naF11.0\naF7.0\naF21.0\naF13.0\naF24.0\naF15.0\naF11.0\naF9.0\naF11.0\naF23.0\naF15.0\naF13.0\naF21.0\naF10.0\naF13.0\naF23.0\naF11.0\naF16.0\naF17.0\naF17.0\naF10.0\naF10.0\naF26.0\naF17.0\naF7.0\naF6.0\naF12.0\naF22.0\naF11.0\naF12.0\naF12.0\naF6.0\naF14.0\naF12.0\naF21.0\naF38.0\naF25.0\naF12.0\naF20.0\naF5.0\naF20.0\naF28.0\naF12.0\naF15.0\naF13.0\naF9.0\naF9.0\naF27.0\naF10.0\naF28.0\naF15.0\naF18.0\naF16.0\naF19.0\naF23.0\naF9.0\naF8.0\naF12.0\naF14.0\naF23.0\naF21.0\naF20.0\naF21.0\naF16.0\naF13.0\naF32.0\naF12.0\naF21.0\naF9.0\naF7.0\naF9.0\naF18.0\naF21.0\naF13.0\naF39.0\naF18.0\naF30.0\naF19.0\naF12.0\naF14.0\naF22.0\naF10.0\naF20.0\naF16.0\naF18.0\naF8.0\naF36.0\naF19.0\naF12.0\naF29.0\naF9.0\naF19.0\naF11.0\naF9.0\naF14.0\naF18.0\naF10.0\naF15.0\naF12.0\naF16.0\naF16.0\naF20.0\naF17.0\naF19.0\naF31.0\naF19.0\naF9.0\naF20.0\naF27.0\naF20.0\naF23.0\naF22.0\naF12.0\naF23.0\naF24.0\naF18.0\naF20.0\naF12.0\naF21.0\naF25.0\naF19.0\naF21.0\naF18.0\naF9.0\naF30.0\naF26.0\naF36.0\naF32.0\naF23.0\naF15.0\naF18.0\naF28.0\naF16.0\naF12.0\naF28.0\naF24.0\naF14.0\naF12.0\naF15.0\naF26.0\naF19.0\naF14.0\naF19.0\naF17.0\naF21.0\naF10.0\naF13.0\naF17.0\naF10.0\naF21.0\naF21.0\naF10.0\naF10.0\naF24.0\naF24.0\naF21.0\naF7.0\naF17.0\naF30.0\naF30.0\naF20.0\naF9.0\naF24.0\naF27.0\naF21.0\naF16.0\naF15.0\naF22.0\naF18.0\naF9.0\naF12.0\naF21.0\naF29.0\naF34.0\naF27.0\naF12.0\naF26.0\naF24.0\naF30.0\naF8.0\naF24.0\naF21.0\naF37.0\naF25.0\naF13.0\naF28.0\naF11.0\naF22.0\naF17.0\naF19.0\naF26.0\naF29.0\naF21.0\naF15.0\naF34.0\naF16.0\naF24.0\naF28.0\naF22.0\naF6.0\naF38.0\naF33.0\naF31.0\naF25.0\naF25.0\naF21.0\naF7.0\naF35.0\naF42.0\naF8.0\naF29.0\naF33.0\naF18.0\naF30.0\naF17.0\naF24.0\naF31.0\naF30.0\naF10.0\naF22.0\naF29.0\naF18.0\naF33.0\naF18.0\naF39.0\naF60.0\naF14.0\naF33.0\naF26.0\naF18.0\naF35.0\naF19.0\naF27.0\naF15.0\naF17.0\naF33.0\naF20.0\naF23.0\naF26.0\naF36.0\naF44.0\naF36.0\naF21.0\naF56.0\naF16.0\naF31.0\naF26.0\naF39.0\naF46.0\naF43.0\naF53.0\naF27.0\naF23.0\naF17.0\naF33.0\naF22.0\naF60.0\naF24.0\naF26.0\naF17.0\naF17.0\naF62.0\naF34.0\naF54.0\naF19.0\naF35.0\naF22.0\naF77.0\naF16.0\naF14.0\naF17.0\naF31.0\naF23.0\naF21.0\naF47.0\naF31.0\naF44.0\naF28.0\naF23.0\naF27.0\naF23.0\naF17.0\naF43.0\naF18.0\naF34.0\naF16.0\naF37.0\naF25.0\naF39.0\naF39.0\naF23.0\naF43.0\naF30.0\naF32.0\naF54.0\naF33.0\naF27.0\naF50.0\naF65.0\naF42.0\naF45.0\naF33.0\naF43.0\naF39.0\naF34.0\naF32.0\naF20.0\naF41.0\naF43.0\naF37.0\naF34.0\naF23.0\naF44.0\naF34.0\naF33.0\naF61.0\naF33.0\naF34.0\naF38.0\naF20.0\naF53.0\naF29.0\naF24.0\naF50.0\naF18.0\naF27.0\naF42.0\naF49.0\naF37.0\naF48.0\naF54.0\naF26.0\naF45.0\naF35.0\naF40.0\naF56.0\naF19.0\naF35.0\naF58.0\naF37.0\naF55.0\naF41.0\naF42.0\naF62.0\naF20.0\naF49.0\naF52.0\naF34.0\naF40.0\naF25.0\naF54.0\naF22.0\naF27.0\naF40.0\naF53.0\naF33.0\naF24.0\naF36.0\naF60.0\naF44.0\naF38.0\naF49.0\naF41.0\naF54.0\naF51.0\naF52.0\naF25.0\naF53.0\naF78.0\naF35.0\naF23.0\naF59.0\naF57.0\naF26.0\naF23.0\naF18.0\naF82.0\naF37.0\naF53.0\naF66.0\naF31.0\naF60.0\naF36.0\naF40.0\naF47.0\naF28.0\naF31.0\naF42.0\naF39.0\naF38.0\naF34.0\naF48.0\naF60.0\naF29.0\naF42.0\naF44.0\naF52.0\naF60.0\naF74.0\naF38.0\naF46.0\naF26.0\naF15.0\naF35.0\naF97.0\naF26.0\naF39.0\naF58.0\naF46.0\naF54.0\naF41.0\naF54.0\naF45.0\naF43.0\naF32.0\naF72.0\naF57.0\naF57.0\naF68.0\naF30.0\naF32.0\naF58.0\naF50.0\naF57.0\naF46.0\naF68.0\naF23.0\naF46.0\naF41.0\naF57.0\naF33.0\naF66.0\naF68.0\naF49.0\naF49.0\naF69.0\naF37.0\naF50.0\naF14.0\naF39.0\naF68.0\naF25.0\naF30.0\naF39.0\naF45.0\naF54.0\naF49.0\naF52.0\naF45.0\naF48.0\naF37.0\naF30.0\naF56.0\naF37.0\naF35.0\naF49.0\naF49.0\naF82.0\naF48.0\naF59.0\naF83.0\naF68.0\naF69.0\naF43.0\naF64.0\naF57.0\naF52.0\naF63.0\naF16.0\naF64.0\naF33.0\naF61.0\naF38.0\naF61.0\naF48.0\naF33.0\naF54.0\naF32.0\naF43.0\naF59.0\naF46.0\naF46.0\naF83.0\naF34.0\naF40.0\naF52.0\naF41.0\naF79.0\naF35.0\naF65.0\naF18.0\naF57.0\naF48.0\naF49.0\naF63.0\naF80.0\naF47.0\naF92.0\naF47.0\naF64.0\naF40.0\naF40.0\naF69.0\naF49.0\naF36.0\naF67.0\naF89.0\naF49.0\naF24.0\naF45.0\naF33.0\naF82.0\naF52.0\naF44.0\naF21.0\naF41.0\naF56.0\naF57.0\naF32.0\naF40.0\naF55.0\naF34.0\naF59.0\naF50.0\naF41.0\naF33.0\naF32.0\naF22.0\naF77.0\naF41.0\naF37.0\naF60.0\naF37.0\naF64.0\naF23.0\naF32.0\naF67.0\naF71.0\naF48.0\naF32.0\naF75.0\naF56.0\naF64.0\naF84.0\naF82.0\naF84.0\naF33.0\naF66.0\naF51.0\naF44.0\naF60.0\naF62.0\naF30.0\naF82.0\naF30.0\naF18.0\naF18.0\naF52.0\naF35.0\naF68.0\naF50.0\naF67.0\naF36.0\naF60.0\naF62.0\naF44.0\naF52.0\naF81.0\naF55.0\naF81.0\naF59.0\naF21.0\naF39.0\naF101.0\naF44.0\naF56.0\naF60.0\naF57.0\naF62.0\naF37.0\naF43.0\naF33.0\naF67.0\naF26.0\naF52.0\naF72.0\naF50.0\naF29.0\naF28.0\naF68.0\naF59.0\naF41.0\naF57.0\naF65.0\naF58.0\naF56.0\naF72.0\naF61.0\naF71.0\naF33.0\naF51.0\naF68.0\naF43.0\naF37.0\naF57.0\naF59.0\naF47.0\naF88.0\naF63.0\naF98.0\naF54.0\naF50.0\naF55.0\naF41.0\naF48.0\naF56.0\naF52.0\naF62.0\naF21.0\naF46.0\naF55.0\naF46.0\naF39.0\naF64.0\naF58.0\naF87.0\naF71.0\naF71.0\naF74.0\naF63.0\naF53.0\naF73.0\naF33.0\naF47.0\naF64.0\naF60.0\naF94.0\naF50.0\naF65.0\naF86.0\naF60.0\naF64.0\naF74.0\naF79.0\naF100.0\naF90.0\naF53.0\naF75.0\naF71.0\naF72.0\naF76.0\naF85.0\naF79.0\naF47.0\naF40.0\naF52.0\naF14.0\naF87.0\naF71.0\naF61.0\naF25.0\naF57.0\naF57.0\naF38.0\naF71.0\naF56.0\naF50.0\naF67.0\naF60.0\naF86.0\naF60.0\naF75.0\naF41.0\naF57.0\naF22.0\naF57.0\naF74.0\naF71.0\naF81.0\naF71.0\naF61.0\naF49.0\naF40.0\naF53.0\naF32.0\naF106.0\naF71.0\naF16.0\naF60.0\naF75.0\naF77.0\naF70.0\naF74.0\naF55.0\naF72.0\naF86.0\naF61.0\naF64.0\naF47.0\naF69.0\naF78.0\naF61.0\naF90.0\naF68.0\naF40.0\naF82.0\naF84.0\naF48.0\naF46.0\naF119.0\naF78.0\naF43.0\naF76.0\naF34.0\naF75.0\naF108.0\naF99.0\naF74.0\naF50.0\naF36.0\naF41.0\naF77.0\naF56.0\naF70.0\naF59.0\naF52.0\naF83.0\naF158.0\naF39.0\naF237.0\naF81.0\naF52.0\naF91.0\naF44.0\naF64.0\naF30.0\naF76.0\naF18.0\naF81.0\naF36.0\naF35.0\naF58.0\naF73.0\naF67.0\naF64.0\naF65.0\naF84.0\naF23.0\naF4.0\naF4.0\naF2.0\naF2.0\naF4.0\naF3.0\naF2.0\naF4.0\naF7.0\naF6.0\naF6.0\naF2.0\naF4.0\naF6.0\naF6.0\naF17.0\naF8.0\naF10.0\naF3.0\naF25.0\naF15.0\naF7.0\naF36.0\naF11.0\naF21.0\naF41.0\naF85.0\naF39.0\naF63.0\naF64.0\naF95.0\naF106.0\naF59.0\naF85.0\naF61.0\naF56.0\naF41.0\naF30.0\naF76.0\naF65.0\naF29.0\naF83.0\naF36.0\naF66.0\naF56.0\naF71.0\naF79.0\naF65.0\naF88.0\naF71.0\naF96.0\naF45.0\naF62.0\naF62.0\naF72.0\naF67.0\naF63.0\naF91.0\naF45.0\naF63.0\naF74.0\naF26.0\naF17.0\naF1.0\naF0.0\naF1.0\naF1.0\naF0.0\naF4.0\naF5.0\naF1.0\naF5.0\naF4.0\naF10.0\naF57.0\naF64.0\naF60.0\naF42.0\naF6.0\naF8.0\naF88.0\naF45.0\naF65.0\naF57.0\naF28.0\naF55.0\naF111.0\naF59.0\naF93.0\naF35.0\naF11.0\naF0.0\naF6.0\naF1.0\naF0.0\naF10.0\naF7.0\naF6.0\naF3.0\naF5.0\naF2.0\naF5.0\naF8.0\naF0.0\naF2.0\naF13.0\naF3.0\naF7.0\naF52.0\naF53.0\naF48.0\naF37.0\naF70.0\naF72.0\naF61.0\naF59.0\naF83.0\naF58.0\naF106.0\naF51.0\naF31.0\naF8.0\naF4.0\naF5.0\naF0.0\naF4.0\naF5.0\naF2.0\naF41.0\naF84.0\naF85.0\naF78.0\naF51.0\naF70.0\naF26.0\naF59.0\naF20.0\naF53.0\naF54.0\naF50.0\naF105.0\naF73.0\naF47.0\naF14.0\naF55.0\naF97.0\naF104.0\naF47.0\naF39.0\naF1.0\naF4.0\naF3.0\naF1.0\naF1.0\naF1.0\naF5.0\naF3.0\naF2.0\naF1.0\naF3.0\naF1.0\naF4.0\naF2.0\naF0.0\naF0.0\naF1.0\naF3.0\naF2.0\naF6.0\naF2.0\naF1.0\naF0.0\naF2.0\naF1.0\naF3.0\naF2.0\naF1.0\naF4.0\naF2.0\naF2.0\naF1.0\naF4.0\naF0.0\naF1.0\naF2.0\naF2.0\naF3.0\naF2.0\naF2.0\naF0.0\naF1.0\naF4.0\naF2.0\naF2.0\naF1.0\naF2.0\naF4.0\naF5.0\naF5.0\naF11.0\naF3.0\naF3.0\naF2.0\naF2.0\naF1.0\naF4.0\naF0.0\naF1.0\naF0.0\naF3.0\naF2.0\naF1.0\naF1.0\naF3.0\naF2.0\naF6.0\naF7.0\naF8.0\naF4.0\naF11.0\naF8.0\naF12.0\naF13.0\naF8.0\naF8.0\naF3.0\naF2.0\naF3.0\naF3.0\naF3.0\naF11.0\naF14.0\naF28.0\naF4.0\naF27.0\naF37.0\naF65.0\naF49.0\naF69.0\naF31.0\naF54.0\naF52.0\naF63.0\naF75.0\naF68.0\naF76.0\naF85.0\naF112.0\naF69.0\naF0.0\naF52.0\naF78.0\naF38.0\naF32.0\naF1.0\naF1.0\naF2.0\naF3.0\naF3.0\naF2.0\naF3.0\naF0.0\naF1.0\naF3.0\naF4.0\naF3.0\naF2.0\naF1.0\naF4.0\naF7.0\naF4.0\naF80.0\naF73.0\naF70.0\naF27.0\naF69.0\naF120.0\naF35.0\naF64.0\naF67.0\naF5.0\naF5.0\naF5.0\naF3.0\naF1.0\naF1.0\naF5.0\naF1.0\naF2.0\naF4.0\naF4.0\naF6.0\naF3.0\naF1.0\naF14.0\naF24.0\naF35.0\naF43.0\naF67.0\naF82.0\naF100.0\naF52.0\naF59.0\naF52.0\naF86.0\naF83.0\naF69.0\naF57.0\naF61.0\naF39.0\naF42.0\naF84.0\naF60.0\naF87.0\naF47.0\naF94.0\naF61.0\naF57.0\naF40.0\naF57.0\naF103.0\naF78.0\naF47.0\naF88.0\naF45.0\naF62.0\naF87.0\naF51.0\naF42.0\naF71.0\naF84.0\naF62.0\naF19.0\naF85.0\naF32.0\naF54.0\naF39.0\naF0.0\naF0.0\naF2.0\naF1.0\naF1.0\naF1.0\naF3.0\naF0.0\naF8.0\naF1.0\naF2.0\naF3.0\naF1.0\naF4.0\naF7.0\naF5.0\naF14.0\naF5.0\naF1.0\naF10.0\naF30.0\naF59.0\naF35.0\naF59.0\naF58.0\naF67.0\naF56.0\naF28.0\naF38.0\naF49.0\naF59.0\naF66.0\naF59.0\naF89.0\naF54.0\naF67.0\naF64.0\naF43.0\naF71.0\naF44.0\naF82.0\naF105.0\naF12.0\naF30.0\naF60.0\naF6.0\naF0.0\naF1.0\naF1.0\naF2.0\naF1.0\naF2.0\naF3.0\naF1.0\naF1.0\naF0.0\naF2.0\naF2.0\naF0.0\naF0.0\naF3.0\naF1.0\naF0.0\naF1.0\naF0.0\naF2.0\naF2.0\naF1.0\naF2.0\naF5.0\naF1.0\naF1.0\naF2.0\naF0.0\naF1.0\naF4.0\naF1.0\naF4.0\naF1.0\naF5.0\naF7.0\naF9.0\naF3.0\naF17.0\naF6.0\naF13.0\naF20.0\naF16.0\naF26.0\naF28.0\naF46.0\naF41.0\naF26.0\naF94.0\naF288.0\naF81.0\naF81.0\naF43.0\naF52.0\naF87.0\naF42.0\naF79.0\naF9.0\naF2.0\naF4.0\naF2.0\naF6.0\naF9.0\naF40.0\naF51.0\naF70.0\naF52.0\naF81.0\naF62.0\naF44.0\naF1.0\naF9.0\naF96.0\naF58.0\naF104.0\naF62.0\naF64.0\naF12.0\naF10.0\naF8.0\naF13.0\naF73.0\naF26.0\naF19.0\naF68.0\naF73.0\naF96.0\naF75.0\naF41.0\naF44.0\naF43.0\naF39.0\naF56.0\naF104.0\naF47.0\naF70.0\naF85.0\naF63.0\naF37.0\naF2.0\naF1.0\naF3.0\naF6.0\naF0.0\naF0.0\naF5.0\naF8.0\naF8.0\naF5.0\naF20.0\naF51.0\naF61.0\naF32.0\naF80.0\naF53.0\naF56.0\naF79.0\naF89.0\naF60.0\naF60.0\naF109.0\naF49.0\naF72.0\naF81.0\naF55.0\naF61.0\naF92.0\naF81.0\naF73.0\naF77.0\naF87.0\naF48.0\naF87.0\naF53.0\naF61.0\naF50.0\naF79.0\naF65.0\naF49.0\naF55.0\naF41.0\naF95.0\naF51.0\naF114.0\naF107.0\naF52.0\naF25.0\naF51.0\naF76.0\naF104.0\naF66.0\naF35.0\naF50.0\naF86.0\naF40.0\naF5.0\naF1.0\naF0.0\naF5.0\naF50.0\naF51.0\naF43.0\naF118.0\naF54.0\naF70.0\naF110.0\naF93.0\naF16.0\naF5.0\naF61.0\naF172.0\naF34.0\naF287.0\naF29.0\naF78.0\naF67.0\naF120.0\naF74.0\naF62.0\naF42.0\naF59.0\naF101.0\naF46.0\naF13.0\naF0.0\naF4.0\naF4.0\naF4.0\naF5.0\naF1.0\naF21.0\naF13.0\naF13.0\naF73.0\naF31.0\naF58.0\naF18.0\naF6.0\naF1.0\naF1.0\naF2.0\naF3.0\naF2.0\naF8.0\naF5.0\naF9.0\naF10.0\naF18.0\naF19.0\naF39.0\naF40.0\naF58.0\naF52.0\naF42.0\naF71.0\naF86.0\naF104.0\naF1.0\naF1.0\naF2.0\naF7.0\naF8.0\naF6.0\naF50.0\naF63.0\naF67.0\naF49.0\naF54.0\naF49.0\naF27.0\naF29.0\naF18.0\naF49.0\naF66.0\naF108.0\naF110.0\naF23.0\naF85.0\naF85.0\naF48.0\naF16.0\naF64.0\naF20.0\naF50.0\naF58.0\naF51.0\naF37.0\naF3.0\naF20.0\naF31.0\naF74.0\naF45.0\naF7.0\naF49.0\naF91.0\naF103.0\naF8.0\naF66.0\naF59.0\naF62.0\naF66.0\naF50.0\naF23.0\naF42.0\naF63.0\naF93.0\naF61.0\naF94.0\naF53.0\naF66.0\naF31.0\naF90.0\naF56.0\naF10.0\naF33.0\naF79.0\naF20.0\naF11.0\naF52.0\naF67.0\naF48.0\naF87.0\naF79.0\naF126.0\naF43.0\naF69.0\naF21.0\naF86.0\naF73.0\naF68.0\naF42.0\naF75.0\naF49.0\naF15.0\naF32.0\naF60.0\naF64.0\naF60.0\naF22.0\naF1.0\naF219.0\naF62.0\naF27.0\naF69.0\naF32.0\naF30.0\naF27.0\naF49.0\naF3.0\naF4.0\naF5.0\naF6.0\naF3.0\naF0.0\naF7.0\naF13.0\naF19.0\naF3.0\naF3.0\naF1.0\naF1.0\naF5.0\naF4.0\naF8.0\naF7.0\naF15.0\naF3.0\naF8.0\naF22.0\naF3.0\naF25.0\naF28.0\naF38.0\naF36.0\naF41.0\naF77.0\naF25.0\naF74.0\naF44.0\naF41.0\naF66.0\naF38.0\naF96.0\naF96.0\naF44.0\naF128.0\naF61.0\naF75.0\naF134.0\naF77.0\naF59.0\naF50.0\naF55.0\naF89.0\naF50.0\naF90.0\naF53.0\naF47.0\naF88.0\naF23.0\naF11.0\naF84.0\naF21.0\naF13.0\naF4.0\naF84.0\naF48.0\naF28.0\naF95.0\naF41.0\naF82.0\naF33.0\naF101.0\naF85.0\naF51.0\naF77.0\naF64.0\naF94.0\naF13.0\naF5.0\naF11.0\naF27.0\naF35.0\naF45.0\naF45.0\naF41.0\naF126.0\naF27.0\naF45.0\naF3.0\naF7.0\naF12.0\naF12.0\naF2.0\naF27.0\naF53.0\naF32.0\naF66.0\naF80.0\naF63.0\naF68.0\naF45.0\naF80.0\naF72.0\naF77.0\naF59.0\naF18.0\naF56.0\naF80.0\naF73.0\naF34.0\naF23.0\naF86.0\naF83.0\naF35.0\naF77.0\naF101.0\naF87.0\naF259.0\naF48.0\naF45.0\naF69.0\naF31.0\naF8.0\naF50.0\naF89.0\naF74.0\naF52.0\naF52.0\naF81.0\naF12.0\naF25.0\naF94.0\naF60.0\naF60.0\naF16.0\naF18.0\naF67.0\naF86.0\naF66.0\naF47.0\naF53.0\naF62.0\naF60.0\naF35.0\naF103.0\naF30.0\naF154.0\naF52.0\naF47.0\naF42.0\naF48.0\naF62.0\naF57.0\naF31.0\naF45.0\naF66.0\naF24.0\naF26.0\naF62.0\naF21.0\naF83.0\naF6.0\naF7.0\naF54.0\naF86.0\naF39.0\naF56.0\naF73.0\naF57.0\naF3.0\naF15.0\naF21.0\naF72.0\naF68.0\naF62.0\naF69.0\naF83.0\naF98.0\naF70.0\naF62.0\naF50.0\naF23.0\naF10.0\naF80.0\naF38.0\naF53.0\naF69.0\naF50.0\naF115.0\naF98.0\naF46.0\naF3.0\naF12.0\naF0.0\naF41.0\naF62.0\naF85.0\naF98.0\naF54.0\naF19.0\naF95.0\naF103.0\naF88.0\naF74.0\naF129.0\naF1.0\naF1.0\naF6.0\naF5.0\naF7.0\naF2.0\naF9.0\naF1.0\naF9.0\naF42.0\naF91.0\naF60.0\naF74.0\naF47.0\naF29.0\naF58.0\naF43.0\naF70.0\naF100.0\naF13.0\naF1.0\naF6.0\naF47.0\naF94.0\naF84.0\naF37.0\naF74.0\naF89.0\naF68.0\naF50.0\naF73.0\naF127.0\naF135.0\naF70.0\naF60.0\naF39.0\naF100.0\naF71.0\naF71.0\naF254.0\naF81.0\naF65.0\naF105.0\naF71.0\naF82.0\naF48.0\naF54.0\naF153.0\naF101.0\naF42.0\naF22.0\naF90.0\naF270.0\naF100.0\naF67.0\naF86.0\naF70.0\naF47.0\naF89.0\naF29.0\naF69.0\naF73.0\naF280.0\naF75.0\naF85.0\naF55.0\naF41.0\naF57.0\naF65.0\naF26.0\naF76.0\naF72.0\naF75.0\naF58.0\naF62.0\naF9.0\naF19.0\naF3.0\naF2.0\naF81.0\naF88.0\naF45.0\naF37.0\naF35.0\naF62.0\naF75.0\naF51.0\naF56.0\naF43.0\naF7.0\naF66.0\naF89.0\naF93.0\naF33.0\naF102.0\naF85.0\naF57.0\naF91.0\naF66.0\naF52.0\naF24.0\naF90.0\naF68.0\naF64.0\naF43.0\naF34.0\naF96.0\naF60.0\naF51.0\naF102.0\naF115.0\naF98.0\naF68.0\naF11.0\naF3.0\naF12.0\naF27.0\naF78.0\naF51.0\naF38.0\naF34.0\naF52.0\naF85.0\naF68.0\naF49.0\naF100.0\naF63.0\naF51.0\naF65.0\naF120.0\naF283.0\naF69.0\naF77.0\naF60.0\naF68.0\naF36.0\naF140.0\naF56.0\naF102.0\naF66.0\naF78.0\naF45.0\naF79.0\naF119.0\naF49.0\naF68.0\naF117.0\naF87.0\naF79.0\naF42.0\naF85.0\naF72.0\naF64.0\naF101.0\naF49.0\naF138.0\naF69.0\naF45.0\naF100.0\naF42.0\naF50.0\naF25.0\naF8.0\naF2.0\naF17.0\naF28.0\naF40.0\naF83.0\naF58.0\naF33.0\naF82.0\naF198.0\naF66.0\naF69.0\naF20.0\naF83.0\naF79.0\naF59.0\naF267.0\naF79.0\naF67.0\naF114.0\naF231.0\naF110.0\naF51.0\naF101.0\naF53.0\naF114.0\naF44.0\naF147.0\naF6.0\naF117.0\naF101.0\naF131.0\naF35.0\naF26.0\naF88.0\naF92.0\naF180.0\naF78.0\naF18.0\naF82.0\naF75.0\naF65.0\naF48.0\naF39.0\naF65.0\naF74.0\naF28.0\naF66.0\naF110.0\naF100.0\naF49.0\naF65.0\naF96.0\naF64.0\naF110.0\naF67.0\naF54.0\naF87.0\naF50.0\naF91.0\naF41.0\naF70.0\naF88.0\naF86.0\naF71.0\naF43.0\naF90.0\naF111.0\naF60.0\naF120.0\naF48.0\naF79.0\naF30.0\naF36.0\naF109.0\naF34.0\naF0.0\naF69.0\naF103.0\naF68.0\naF2.0\naF15.0\naF49.0\naF65.0\naF183.0\naF61.0\naF54.0\naF60.0\naF86.0\naF26.0\naF18.0\naF104.0\naF40.0\naF53.0\naF121.0\naF122.0\naF84.0\naF79.0\naF62.0\naF74.0\naF70.0\naF140.0\naF24.0\naF71.0\naF70.0\naF87.0\naF100.0\naF105.0\naF86.0\naF110.0\naF234.0\naF47.0\naF65.0\naF82.0\naF51.0\naF99.0\naF27.0\naF129.0\naF57.0\naF78.0\naF66.0\naF111.0\naF272.0\naF46.0\naF52.0\naF61.0\naF87.0\naF44.0\naF43.0\naF35.0\naF121.0\naF62.0\naF41.0\naF72.0\naF91.0\naF80.0\naF44.0\naF41.0\naF48.0\naF55.0\naF65.0\naF57.0\naF53.0\naF71.0\naF165.0\naF48.0\naF35.0\naF34.0\naF74.0\naF81.0\naF17.0\naF23.0\naF39.0\naF59.0\naF91.0\naF90.0\naF112.0\naF73.0\naF152.0\naF107.0\naF111.0\naF137.0\naF192.0\naF105.0\naF152.0\naF68.0\naF329.0\naF82.0\naF115.0\naF111.0\naF13.0\naF77.0\naF20.0\naF27.0\naF28.0\naF104.0\naF258.0\naF37.0\naF78.0\naF158.0\naF84.0\naF45.0\naF78.0\naF113.0\naF95.0\naF54.0\naF103.0\naF80.0\naF86.0\naF101.0\naF58.0\naF6.0\naF93.0\naF45.0\naF30.0\naF202.0\naF45.0\naF57.0\naF40.0\naF140.0\naF72.0\naF160.0\naF141.0\naF76.0\naF59.0\naF194.0\naF34.0\naF104.0\naF124.0\naF70.0\naF46.0\naF76.0\naF64.0\naF97.0\naF71.0\naF126.0\naF66.0\naF109.0\naF238.0\naF107.0\naF70.0\naF80.0\naF91.0\naF58.0\naF46.0\naF62.0\naF94.0\naF256.0\naF52.0\naF190.0\naF122.0\naF29.0\naF100.0\naF62.0\naF162.0\naF26.0\naF1.0\naF99.0\naF51.0\naF82.0\naF128.0\naF71.0\naF95.0\naF68.0\naF71.0\naF75.0\naF120.0\naF140.0\naF97.0\naF51.0\naF188.0\naF37.0\naF111.0\naF86.0\naF90.0\naF53.0\naF125.0\naF134.0\naF138.0\naF78.0\naF137.0\naF66.0\naF218.0\naF100.0\naF71.0\naF77.0\naF43.0\naF227.0\naF249.0\naF51.0\naF72.0\naF53.0\naF13.0\naF2.0\naF21.0\naF87.0\naF30.0\naF35.0\naF77.0\naF80.0\naF39.0\naF12.0\naF58.0\naF68.0\naF73.0\naF89.0\naF115.0\naF94.0\naF130.0\naF88.0\naF84.0\naF38.0\naF174.0\naF177.0\naF83.0\naF18.0\naF13.0\naF77.0\naF119.0\naF69.0\naF235.0\naF118.0\naF151.0\naF240.0\naF43.0\naF13.0\naF8.0\naF3.0\naF3.0\naF55.0\naF63.0\naF30.0\naF57.0\naF53.0\naF252.0\naF81.0\naF73.0\naF125.0\naF110.0\naF280.0\naF83.0\naF4.0\naF4.0\naF13.0\naF10.0\naF2.0\naF12.0\naF22.0\naF4.0\naF68.0\naF63.0\naF72.0\naF90.0\naF60.0\naF98.0\naF73.0\naF197.0\naF66.0\naF80.0\naF98.0\naF57.0\naF69.0\naF325.0\naF131.0\naF254.0\naF139.0\naF55.0\naF97.0\naF227.0\naF69.0\naF82.0\naF104.0\naF81.0\naF64.0\naF26.0\naF113.0\naF78.0\naF145.0\naF77.0\naF113.0\naF133.0\naF87.0\naF157.0\naF217.0\naF132.0\naF100.0\naF95.0\naF89.0\naF70.0\naF66.0\naF72.0\naF104.0\naF116.0\naF105.0\naF84.0\naF179.0\naF31.0\naF99.0\naF52.0\naF98.0\naF177.0\naF51.0\naF135.0\naF67.0\naF113.0\naF115.0\naF68.0\naF88.0\naF169.0\naF105.0\naF93.0\naF114.0\naF96.0\naF30.0\naF8.0\naF116.0\naF17.0\naF62.0\naF93.0\naF44.0\naF70.0\naF112.0\naF148.0\naF181.0\naF107.0\naF87.0\naF82.0\naF72.0\naF68.0\naF38.0\naF157.0\naF120.0\naF80.0\naF11.0\naF32.0\naF86.0\naF233.0\naF73.0\naF87.0\naF114.0\naF108.0\naF63.0\naF70.0\naF93.0\naF132.0\naF45.0\naF15.0\naF21.0\naF105.0\naF77.0\naF146.0\naF100.0\naF33.0\naF49.0\naF213.0\naF102.0\naF166.0\naF80.0\naF110.0\naF112.0\naF81.0\naF224.0\naF151.0\naF115.0\naF175.0\naF256.0\naF18.0\naF3.0\naF4.0\naF10.0\naF206.0\naF121.0\naF43.0\naF97.0\naF128.0\naF58.0\naF89.0\naF67.0\naF100.0\naF139.0\naF74.0\naF13.0\naF62.0\naF163.0\naF135.0\naF101.0\naF121.0\naF110.0\naF73.0\naF107.0\naF23.0\naF9.0\naF117.0\naF235.0\naF140.0\naF218.0\naF85.0\naF153.0\naF153.0\naF280.0\naF161.0\naF125.0\naF54.0\naF118.0\naF122.0\naF111.0\naF159.0\naF79.0\naF100.0\naF98.0\naF199.0\naF283.0\naF221.0\naF224.0\naF107.0\naF78.0\naF83.0\naF58.0\naF83.0\naF85.0\naF82.0\naF93.0\naF19.0\naF72.0\naF268.0\naF119.0\naF61.0\naF277.0\naF129.0\naF176.0\naF105.0\naF132.0\naF133.0\naF45.0\naF119.0\naF155.0\naF36.0\naF94.0\naF115.0\naF97.0\naF82.0\naF103.0\naF142.0\naF142.0\naF82.0\naF159.0\naF187.0\naF181.0\naF76.0\naF79.0\naF399.0\naF97.0\naF118.0\naF174.0\naF128.0\naF129.0\naF141.0\naF123.0\naF302.0\naF109.0\naF314.0\naF98.0\naF97.0\naF124.0\naF199.0\naF192.0\naF128.0\naF21.0\naF105.0\naF85.0\naF1.0\naF1.0\naF116.0\naF97.0\naF117.0\naF29.0\naF16.0\naF94.0\naF125.0\naF68.0\naF71.0\naF122.0\naF120.0\naF88.0\naF77.0\naF42.0\naF88.0\naF83.0\naF150.0\naF82.0\naF126.0\naF192.0\naF79.0\naF240.0\naF47.0\naF328.0\naF148.0\naF143.0\naF153.0\naF303.0\naF53.0\naF135.0\naF47.0\naF124.0\naF236.0\naF55.0\naF89.0\naF140.0\naF54.0\naF93.0\naF79.0\naF193.0\naF68.0\naF133.0\naF126.0\naF64.0\naF114.0\naF160.0\naF63.0\naF183.0\naF84.0\naF182.0\naF107.0\naF100.0\naF89.0\naF70.0\naF82.0\naF175.0\naF142.0\naF113.0\naF177.0\naF204.0\naF59.0\naF269.0\naF164.0\naF60.0\naF61.0\naF177.0\naF67.0\naF103.0\naF254.0\naF122.0\naF86.0\naF106.0\naF77.0\naF118.0\naF3.0\naF28.0\naF51.0\naF69.0\naF59.0\naF37.0\naF78.0\naF111.0\naF131.0\naF189.0\naF100.0\naF84.0\naF79.0\naF121.0\naF113.0\naF168.0\naF183.0\naF72.0\naF238.0\naF353.0\naF92.0\naF54.0\naF297.0\naF43.0\naF127.0\naF129.0\naF53.0\naF206.0\naF125.0\naF124.0\naF248.0\naF139.0\naF184.0\naF72.0\naF274.0\naF128.0\naF38.0\naF175.0\naF112.0\naF202.0\naF232.0\naF70.0\naF244.0\naF83.0\naF43.0\naF250.0\naF160.0\naF93.0\naF180.0\naF81.0\naF39.0\naF287.0\naF191.0\naF94.0\naF178.0\naF131.0\naF267.0\naF79.0\naF187.0\naF111.0\naF205.0\naF321.0\naF87.0\naF268.0\naF178.0\naF187.0\naF83.0\naF107.0\naF54.0\naF135.0\naF264.0\naF167.0\naF106.0\naF154.0\naF203.0\naF93.0\naF279.0\naF348.0\naF64.0\naF76.0\naF154.0\naF73.0\naF40.0\naF260.0\naF224.0\naF157.0\naF110.0\naF17.0\naF5.0\naF51.0\naF220.0\naF106.0\naF183.0\naF113.0\naF145.0\naF89.0\naF124.0\naF140.0\naF327.0\naF245.0\naF162.0\naF228.0\naF72.0\naF261.0\naF96.0\naF105.0\naF126.0\naF179.0\naF302.0\naF168.0\naF46.0\naF20.0\naF136.0\naF66.0\naF42.0\naF273.0\naF81.0\naF49.0\naF110.0\naF97.0\naF117.0\naF74.0\naF117.0\naF155.0\naF78.0\naF203.0\naF66.0\naF82.0\naF90.0\naF210.0\naF77.0\naF112.0\naF100.0\naF65.0\naF271.0\naF97.0\naF48.0\naF45.0\naF65.0\naF259.0\naF92.0\naF103.0\naF140.0\naF87.0\naF279.0\naF117.0\naF113.0\naF32.0\naF132.0\naF44.0\naF78.0\naF79.0\naF84.0\naF62.0\naF76.0\naF73.0\naF156.0\naF85.0\naF272.0\naF94.0\naF139.0\naF280.0\naF143.0\naF160.0\naF160.0\naF50.0\naF175.0\naF230.0\naF87.0\naF148.0\naF139.0\naF34.0\naF128.0\naF121.0\naF109.0\naF60.0\naF73.0\naF57.0\naF364.0\naF203.0\naF52.0\naF20.0\naF120.0\naF129.0\naF54.0\naF17.0\naF21.0\naF28.0\naF11.0\naF84.0\naF75.0\naF104.0\naF81.0\naF45.0\naF220.0\naF107.0\naF41.0\naF8.0\naF34.0\naF23.0\naF89.0\naF59.0\naF7.0\naF66.0\naF12.0\naF64.0\naF68.0\naF98.0\naF105.0\naF75.0\naF206.0\naF36.0\naF52.0\naF55.0\naF196.0\naF279.0\naF16.0\naF34.0\naF61.0\naF68.0\naF69.0\naF23.0\naF59.0\naF45.0\naF79.0\naF112.0\naF83.0\naF69.0\naF172.0\naF77.0\naF87.0\naF83.0\naF79.0\naF38.0\naF97.0\naF177.0\naF240.0\naF139.0\naF77.0\naF14.0\naF6.0\naF18.0\naF39.0\naF231.0\naF22.0\naF26.0\naF10.0\naF16.0\naF0.0\naF8.0\naF4.0\naF3.0\naF17.0\naF31.0\naF9.0\naF4.0\naF2.0\naF5.0\naF8.0\naF38.0\naF50.0\naF30.0\naF26.0\naF86.0\naF184.0\naF111.0\naF106.0\naF46.0\naF47.0\naF28.0\naF30.0\naF13.0\naF85.0\naF48.0\naF28.0\naF80.0\naF150.0\naF22.0\naF34.0\naF89.0\naF23.0\naF5.0\naF13.0\naF9.0\naF7.0\naF8.0\naF19.0\naF22.0\naF21.0\naF21.0\naF19.0\naF3.0\naF15.0\naF10.0\naF29.0\naF26.0\naF23.0\naF50.0\naF19.0\naF8.0\naF7.0\naF9.0\naF3.0\naF9.0\naF3.0\naF16.0\naF13.0\naF12.0\naF14.0\naF4.0\naF1.0\naF3.0\naF6.0\naF2.0\naF10.0\naF14.0\naF14.0\naF20.0\naF9.0\naF19.0\naF22.0\naF31.0\naF26.0\naF13.0\naF9.0\naF3.0\naF10.0\naF18.0\naF48.0\naF5.0\naF9.0\naF9.0\naF12.0\naF31.0\naF5.0\naF9.0\naF5.0\naF7.0\naF24.0\naF3.0\naF9.0\naF5.0\naF7.0\naF2.0\naF5.0\naF7.0\naF11.0\naF10.0\naF1.0\naF5.0\naF11.0\naF11.0\naF11.0\naF10.0\naF10.0\naF7.0\naF25.0\naF10.0\naF9.0\naF11.0\naF8.0\naF1.0\naF8.0\naF9.0\naF7.0\naF4.0\naF8.0\naF13.0\naF6.0\naF9.0\naF4.0\naF4.0\naF4.0\naF5.0\naF4.0\naF5.0\naF3.0\naF1.0\naF2.0\naF3.0\naF5.0\naF1.0\naF13.0\naF7.0\naF3.0\naF13.0\naF6.0\naF1.0\naF8.0\naF9.0\naF3.0\naF8.0\naF3.0\naF6.0\naF5.0\naF5.0\naF10.0\naF6.0\naF11.0\naF8.0\naF3.0\naF6.0\naF10.0\naF5.0\naF4.0\naF9.0\naF3.0\naF9.0\naF3.0\naF2.0\naF13.0\naF5.0\naF3.0\naF3.0\naF3.0\naF14.0\naF8.0\naF10.0\naF5.0\naF2.0\naF4.0\naF6.0\naF6.0\naF1.0\naF6.0\naF9.0\naF4.0\naF5.0\naF2.0\naF9.0\naF5.0\naF5.0\naF2.0\naF3.0\naF7.0\naF5.0\naF2.0\naF7.0\naF7.0\naF3.0\naF3.0\naF5.0\naF5.0\naF4.0\naF3.0\naF2.0\naF0.0\naF7.0\naF6.0\naF5.0\naF10.0\naF8.0\naF7.0\naF7.0\naF10.0\naF7.0\naF7.0\naF6.0\naF2.0\naF5.0\naF3.0\naF5.0\naF1.0\naF3.0\naF2.0\naF2.0\naF0.0\naF3.0\naF4.0\naF1.0\naF1.0\naF2.0\naF4.0\naF0.0\naF2.0\naF4.0\naF6.0\naF4.0\naF3.0\naF4.0\naF2.0\naF3.0\naF1.0\naF2.0\naF8.0\naF1.0\naF5.0\naF4.0\naF2.0\naF2.0\naF2.0\naF0.0\naF3.0\naF4.0\naF2.0\naF6.0\naF0.0\naF2.0\naF4.0\naF1.0\naF1.0\naF3.0\naF1.0\naF3.0\naF2.0\naF3.0\naF2.0\naF7.0\naF2.0\naF1.0\naF1.0\naF2.0\naF4.0\naF1.0\naF2.0\naF1.0\naF6.0\naF2.0\naF2.0\naF5.0\naF6.0\naF4.0\naF5.0\naF2.0\naF0.0\naF0.0\naF1.0\naF2.0\naF9.0\naF4.0\naF2.0\naF5.0\naF4.0\naF4.0\naF1.0\naF3.0\naF2.0\naF1.0\naF1.0\naF2.0\naF6.0\naF0.0\naF2.0\naF2.0\naF3.0\naF1.0\naF3.0\naF2.0\naF4.0\naF2.0\naF4.0\naF3.0\naF5.0\naF1.0\naF1.0\naF1.0\naF2.0\naF3.0\naF3.0\naF3.0\naF2.0\naF2.0\naF0.0\naF4.0\naF4.0\naF2.0\naF2.0\naF1.0\naF2.0\naF0.0\naF0.0\naF3.0\naF8.0\naF1.0\naF1.0\naF4.0\naF1.0\naF0.0\naF1.0\naF0.0\naF2.0\naF1.0\naF1.0\naF3.0\naF1.0\naF2.0\naF5.0\naF2.0\naF3.0\naF4.0\naF5.0\naF2.0\naF1.0\naF2.0\naF2.0\naF3.0\naF1.0\naF3.0\naF1.0\naF0.0\naF1.0\naF1.0\naF2.0\naF2.0\naF3.0\naF3.0\naF5.0\naF1.0\naF3.0\naF2.0\naF2.0\naF4.0\naF0.0\naF2.0\naF1.0\naF1.0\naF2.0\naF5.0\naF2.0\naF0.0\naF0.0\naF3.0\naF0.0\naF1.0\naF1.0\naF4.0\naF3.0\naF3.0\naF4.0\naF1.0\naF0.0\naF1.0\naF2.0\naF2.0\naF0.0\naF0.0\naF0.0\naF6.0\naF1.0\naF3.0\naF3.0\naF0.0\naF0.0\naF1.0\naF0.0\naF3.0\naF2.0\naF1.0\naF3.0\naF6.0\naF3.0\naF1.0\naF2.0\naF0.0\naF0.0\naF4.0\naF0.0\naF1.0\naF3.0\naF1.0\naF3.0\naF2.0\naF3.0\naF2.0\naF0.0\naF1.0\naF2.0\naF2.0\naF1.0\naF1.0\naF2.0\naF1.0\naF0.0\naF3.0\naF0.0\naF1.0\naF1.0\naF2.0\naF4.0\naF1.0\naF4.0\naF3.0\naF2.0\naF2.0\naF6.0\naF1.0\naF4.0\naF0.0\naF1.0\naF0.0\naF2.0\naF1.0\naF1.0\naF1.0\naF0.0\naF1.0\naF2.0\naF2.0\naF1.0\naF4.0\naF0.0\naF1.0\naF1.0\naF0.0\naF0.0\naF0.0\naF1.0\naF2.0\naF3.0\naF0.0\naF2.0\naF3.0\naF4.0\naF1.0\naF0.0\naF3.0\naF0.0\naF0.0\naF6.0\naF2.0\naF0.0\naF1.0\naF1.0\naF1.0\naF0.0\naF1.0\naF0.0\naF2.0\naF1.0\naF1.0\naF1.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF6.0\naF0.0\naF2.0\naF1.0\naF1.0\naF1.0\naF1.0\naF5.0\naF7.0\naF0.0\naF5.0\naF2.0\naF4.0\naF2.0\naF2.0\naF2.0\naF5.0\naF1.0\naF1.0\naF4.0\naF1.0\naF1.0\naF2.0\naF1.0\naF2.0\naF3.0\naF3.0\naF2.0\naF1.0\naF3.0\naF3.0\naF1.0\naF1.0\naF3.0\naF1.0\naF1.0\naF4.0\naF1.0\naF3.0\naF1.0\naF0.0\naF1.0\naF2.0\naF4.0\naF4.0\naF3.0\naF4.0\naF0.0\naF0.0\naF2.0\naF2.0\naF1.0\naF2.0\naF3.0\naF2.0\naF1.0\naF2.0\naF0.0\naF1.0\naF1.0\naF2.0\naF1.0\naF1.0\naF4.0\naF1.0\naF0.0\naF0.0\naF1.0\naF1.0\naF0.0\naF0.0\naF1.0\naF1.0\naF3.0\naF1.0\naF0.0\naF3.0\naF5.0\naF0.0\naF0.0\naF2.0\naF2.0\naF0.0\naF1.0\naF3.0\naF0.0\naF1.0\naF0.0\naF1.0\naF3.0\naF2.0\naF0.0\naF1.0\naF2.0\naF0.0\naF5.0\naF1.0\naF2.0\naF1.0\naF4.0\naF1.0\naF1.0\naF4.0\naF1.0\naF1.0\naF2.0\naF3.0\naF0.0\naF1.0\naF2.0\naF3.0\naF0.0\naF0.0\naF0.0\naF1.0\naF3.0\naF1.0\naF1.0\naF1.0\naF2.0\naF2.0\naF0.0\naF0.0\naF1.0\naF1.0\naF1.0\naF2.0\naF0.0\naF1.0\naF3.0\naF3.0\naF1.0\naF0.0\naF3.0\naF1.0\naF4.0\naF0.0\naF2.0\naF3.0\naF0.0\naF1.0\naF1.0\naF5.0\naF3.0\naF1.0\naF3.0\naF2.0\naF0.0\naF2.0\naF2.0\naF3.0\naF1.0\naF2.0\naF2.0\naF5.0\naF2.0\naF3.0\naF3.0\naF2.0\naF1.0\naF2.0\naF1.0\naF1.0\naF2.0\naF3.0\naF3.0\naF3.0\naF4.0\naF2.0\naF4.0\naF0.0\naF0.0\naF2.0\naF3.0\naF1.0\naF2.0\naF5.0\naF1.0\naF1.0\naF3.0\naF3.0\naF1.0\naF2.0\naF4.0\naF4.0\naF1.0\naF0.0\naF0.0\naF1.0\naF3.0\naF1.0\naF3.0\naF0.0\naF0.0\naF2.0\naF2.0\naF1.0\naF2.0\naF0.0\naF4.0\naF3.0\naF4.0\naF0.0\naF1.0\naF1.0\naF1.0\naF1.0\naF1.0\naF2.0\naF3.0\naF3.0\naF3.0\naF3.0\naF3.0\naF2.0\naF1.0\naF2.0\naF2.0\naF2.0\naF2.0\naF4.0\naF0.0\naF2.0\naF1.0\naF0.0\naF1.0\naF1.0\naF1.0\naF1.0\naF1.0\naF2.0\naF1.0\naF0.0\naF1.0\naF1.0\naF1.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF1.0\naF1.0\naF4.0\naF2.0\naF1.0\naF0.0\naF1.0\naF1.0\naF1.0\naF0.0\naF3.0\naF1.0\naF1.0\naF2.0\naF2.0\naF1.0\naF1.0\naF1.0\naF2.0\naF2.0\naF2.0\naF1.0\naF0.0\naF1.0\naF7.0\naF9.0\naF1.0\naF1.0\naF0.0\naF1.0\naF0.0\naF3.0\naF2.0\naF1.0\naF2.0\naF1.0\naF0.0\naF0.0\naF4.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF3.0\naF1.0\naF1.0\naF1.0\naF1.0\naF2.0\naF1.0\naF3.0\naF2.0\naF1.0\naF2.0\naF3.0\naF2.0\naF1.0\naF0.0\naF9.0\naF3.0\naF1.0\naF1.0\naF1.0\naF4.0\naF2.0\naF2.0\naF0.0\naF0.0\naF3.0\naF3.0\naF2.0\naF5.0\naF3.0\naF3.0\naF1.0\naF1.0\naF3.0\naF3.0\naF0.0\naF3.0\naF2.0\naF0.0\naF2.0\naF2.0\naF1.0\naF1.0\naF2.0\naF2.0\naF1.0\naF0.0\naF1.0\naF5.0\naF1.0\naF0.0\naF1.0\naF1.0\naF0.0\naF0.0\naF1.0\naF0.0\naF1.0\naF0.0\naF2.0\naF2.0\naF2.0\naF4.0\naF3.0\naF4.0\naF1.0\naF2.0\naF3.0\naF8.0\naF2.0\naF4.0\naF2.0\naF2.0\naF2.0\naF1.0\naF3.0\naF1.0\naF4.0\naF1.0\naF0.0\naF3.0\naF2.0\naF2.0\naF2.0\naF1.0\naF2.0\naF4.0\naF0.0\naF0.0\naF2.0\naF1.0\naF2.0\naF3.0\naF2.0\naF2.0\naF2.0\naF5.0\naF2.0\naF1.0\naF0.0\naF2.0\naF1.0\naF3.0\naF1.0\naF3.0\naF3.0\naF1.0\naF6.0\naF1.0\naF1.0\naF1.0\naF3.0\naF1.0\naF3.0\naF1.0\naF3.0\naF2.0\naF3.0\naF0.0\naF1.0\naF0.0\naF2.0\naF3.0\naF1.0\naF2.0\naF4.0\naF3.0\naF2.0\naF3.0\naF1.0\naF5.0\naF0.0\naF1.0\naF1.0\naF2.0\naF1.0\naF1.0\naF0.0\naF1.0\naF2.0\naF0.0\naF0.0\naF0.0\naF3.0\naF0.0\naF4.0\naF8.0\naF0.0\naF2.0\naF2.0\naF2.0\naF0.0\naF3.0\naF1.0\naF3.0\naF5.0\naF1.0\naF0.0\naF5.0\naF6.0\naF1.0\naF0.0\naF3.0\naF2.0\naF3.0\naF1.0\naF2.0\naF2.0\naF2.0\naF4.0\naF2.0\naF2.0\naF1.0\naF3.0\naF2.0\naF3.0\naF4.0\naF1.0\naF0.0\naF1.0\naF3.0\naF4.0\naF0.0\naF2.0\naF4.0\naF3.0\naF2.0\naF3.0\naF1.0\naF2.0\naF1.0\naF1.0\naF1.0\naF2.0\naF1.0\naF2.0\naF1.0\naF1.0\naF2.0\naF1.0\naF3.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF2.0\naF4.0\naF2.0\naF2.0\naF3.0\naF5.0\naF1.0\naF2.0\naF4.0\naF3.0\naF2.0\naF0.0\naF0.0\naF1.0\naF0.0\naF2.0\naF2.0\naF2.0\naF2.0\naF3.0\naF1.0\naF3.0\naF0.0\naF2.0\naF1.0\naF2.0\naF2.0\naF5.0\naF0.0\naF4.0\naF1.0\naF2.0\naF5.0\naF1.0\naF4.0\naF0.0\naF1.0\naF1.0\naF2.0\naF2.0\naF1.0\naF0.0\naF1.0\naF0.0\naF1.0\naF0.0\naF3.0\naF4.0\naF1.0\naF2.0\naF2.0\naF2.0\naF2.0\naF5.0\naF1.0\naF0.0\naF2.0\naF1.0\naF1.0\naF0.0\naF5.0\naF2.0\naF1.0\naF2.0\naF0.0\naF1.0\naF0.0\naF4.0\naF2.0\naF0.0\naF3.0\naF3.0\naF2.0\naF0.0\naF1.0\naF0.0\naF2.0\naF0.0\naF1.0\naF0.0\naF2.0\naF3.0\naF1.0\naF2.0\naF2.0\naF1.0\naF1.0\naF2.0\naF0.0\naF1.0\naF2.0\naF2.0\naF1.0\naF1.0\naF0.0\naF1.0\naF0.0\naF1.0\naF3.0\naF2.0\naF2.0\naF1.0\naF0.0\naF0.0\naF1.0\naF4.0\naF2.0\naF3.0\naF0.0\naF4.0\naF3.0\naF2.0\naF1.0\naF3.0\naF0.0\naF0.0\naF3.0\naF0.0\naF1.0\naF1.0\naF0.0\naF1.0\naF0.0\naF0.0\naF4.0\naF2.0\naF2.0\naF1.0\naF4.0\naF2.0\naF0.0\naF0.0\naF1.0\naF3.0\naF3.0\naF0.0\naF2.0\naF6.0\naF4.0\naF2.0\naF0.0\naF2.0\naF2.0\naF0.0\naF0.0\naF1.0\naF2.0\naF0.0\naF1.0\naF1.0\naF2.0\naF1.0\naF2.0\naF1.0\naF2.0\naF1.0\naF0.0\naF0.0\naF5.0\naF3.0\naF2.0\naF0.0\naF2.0\naF2.0\naF3.0\naF5.0\naF7.0\naF4.0\naF3.0\naF7.0\naF0.0\naF1.0\naF0.0\naF0.0\naF3.0\naF0.0\naF1.0\naF1.0\naF0.0\naF1.0\naF0.0\naF2.0\naF3.0\naF0.0\naF0.0\naF3.0\naF2.0\naF1.0\naF3.0\naF0.0\naF2.0\naF0.0\naF1.0\naF1.0\naF2.0\naF3.0\naF1.0\naF2.0\naF3.0\naF0.0\naF2.0\naF9.0\naF2.0\naF1.0\naF1.0\naF6.0\naF1.0\naF1.0\naF1.0\naF2.0\naF0.0\naF2.0\naF3.0\naF0.0\naF3.0\naF1.0\naF0.0\naF6.0\naF2.0\naF1.0\naF1.0\naF2.0\naF1.0\naF1.0\naF2.0\naF1.0\naF2.0\naF2.0\naF0.0\naF3.0\naF2.0\naF1.0\naF0.0\naF3.0\naF0.0\naF2.0\naF1.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF1.0\naF1.0\naF0.0\naF0.0\naF1.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF3.0\naF4.0\naF2.0\naF1.0\naF0.0\naF2.0\naF2.0\naF0.0\naF1.0\naF0.0\naF1.0\naF3.0\naF1.0\naF1.0\naF2.0\naF1.0\naF1.0\naF1.0\naF0.0\naF0.0\naF0.0\naF1.0\naF4.0\naF0.0\naF3.0\naF3.0\naF2.0\naF3.0\naF1.0\naF0.0\naF1.0\naF1.0\naF1.0\naF2.0\naF0.0\naF1.0\naF3.0\naF3.0\naF1.0\naF0.0\naF0.0\naF3.0\naF1.0\naF0.0\naF2.0\naF0.0\naF3.0\naF2.0\naF0.0\naF2.0\naF0.0\naF2.0\naF2.0\naF0.0\naF0.0\naF1.0\naF2.0\naF0.0\naF2.0\naF1.0\naF0.0\naF1.0\naF2.0\naF1.0\naF1.0\naF0.0\naF2.0\naF3.0\naF1.0\naF0.0\naF4.0\naF3.0\naF0.0\naF0.0\naF4.0\naF0.0\naF2.0\naF1.0\naF1.0\naF3.0\naF2.0\naF0.0\naF1.0\naF0.0\naF3.0\naF0.0\naF0.0\naF1.0\naF1.0\naF1.0\naF1.0\naF0.0\naF0.0\naF3.0\naF0.0\naF0.0\naF3.0\naF0.0\naF2.0\naF0.0\naF2.0\naF2.0\naF2.0\naF1.0\naF0.0\naF2.0\naF1.0\naF4.0\naF0.0\naF1.0\naF2.0\naF3.0\naF4.0\naF0.0\naF0.0\naF0.0\naF3.0\naF1.0\naF2.0\naF1.0\naF3.0\naF1.0\naF0.0\naF2.0\naF4.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF3.0\naF2.0\naF0.0\naF0.0\naF3.0\naF2.0\naF1.0\naF1.0\naF1.0\naF1.0\naF0.0\naF2.0\naF3.0\naF1.0\naF1.0\naF2.0\naF3.0\naF2.0\naF0.0\naF4.0\naF1.0\naF2.0\naF3.0\naF2.0\naF1.0\naF1.0\naF3.0\naF2.0\naF3.0\naF1.0\naF1.0\naF2.0\naF0.0\naF0.0\naF4.0\naF1.0\naF2.0\naF2.0\naF0.0\naF1.0\naF0.0\naF6.0\naF1.0\naF2.0\naF3.0\naF2.0\naF1.0\naF2.0\naF3.0\naF0.0\naF4.0\naF2.0\naF1.0\naF3.0\naF2.0\naF3.0\naF3.0\naF3.0\naF3.0\naF5.0\naF1.0\naF4.0\naF1.0\naF4.0\naF1.0\naF1.0\naF3.0\naF1.0\naF3.0\naF1.0\naF3.0\naF4.0\naF1.0\naF0.0\naF1.0\naF3.0\naF4.0\naF1.0\naF4.0\naF4.0\naF3.0\naF0.0\naF7.0\naF1.0\naF1.0\naF1.0\naF2.0\naF1.0\naF3.0\naF1.0\naF1.0\naF4.0\naF1.0\naF1.0\naF6.0\naF1.0\naF2.0\naF5.0\naF3.0\naF3.0\naF1.0\naF3.0\naF1.0\naF1.0\naF5.0\naF1.0\naF0.0\naF2.0\naF4.0\naF3.0\naF2.0\naF2.0\naF4.0\naF2.0\naF2.0\naF1.0\naF3.0\naF1.0\naF5.0\naF1.0\naF5.0\naF0.0\naF3.0\naF1.0\naF2.0\naF3.0\naF0.0\naF0.0\naF1.0\naF2.0\naF2.0\naF3.0\naF0.0\naF1.0\naF1.0\naF3.0\naF2.0\naF4.0\naF3.0\naF3.0\naF0.0\naF0.0\naF3.0\naF1.0\naF3.0\naF4.0\naF0.0\naF6.0\naF0.0\naF2.0\naF1.0\naF3.0\naF3.0\naF2.0\naF0.0\naF3.0\naF4.0\naF2.0\naF4.0\naF2.0\naF1.0\naF1.0\naF4.0\naF0.0\naF1.0\naF6.0\naF0.0\naF2.0\naF7.0\naF1.0\naF0.0\naF0.0\naF2.0\naF2.0\naF1.0\naF0.0\naF1.0\naF1.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF3.0\naF3.0\naF0.0\naF0.0\naF1.0\naF0.0\naF1.0\naF0.0\naF1.0\naF4.0\naF4.0\naF3.0\naF3.0\naF3.0\naF3.0\naF2.0\naF4.0\naF5.0\naF0.0\naF0.0\naF4.0\naF2.0\naF4.0\naF3.0\naF4.0\naF1.0\naF3.0\naF0.0\naF0.0\naF0.0\naF4.0\naF4.0\naF2.0\naF0.0\naF4.0\naF5.0\naF2.0\naF4.0\naF1.0\naF3.0\naF4.0\naF0.0\naF2.0\naF0.0\naF3.0\naF0.0\naF2.0\naF3.0\naF5.0\naF5.0\naF3.0\naF3.0\naF1.0\naF4.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF2.0\naF2.0\naF1.0\naF5.0\naF2.0\naF0.0\naF3.0\naF5.0\naF2.0\naF2.0\naF1.0\naF3.0\naF5.0\naF0.0\naF0.0\naF1.0\naF1.0\naF1.0\naF0.0\naF1.0\naF1.0\naF1.0\naF1.0\naF2.0\naF4.0\naF3.0\naF0.0\naF3.0\naF0.0\naF2.0\naF2.0\naF4.0\naF1.0\naF0.0\naF0.0\naF2.0\naF3.0\naF2.0\naF0.0\naF1.0\naF2.0\naF4.0\naF1.0\naF2.0\naF2.0\naF1.0\naF2.0\naF4.0\naF2.0\naF3.0\naF4.0\naF3.0\naF3.0\naF1.0\naF2.0\naF3.0\naF1.0\naF4.0\naF3.0\naF1.0\naF4.0\naF3.0\naF3.0\naF3.0\naF1.0\naF3.0\naF1.0\naF4.0\naF3.0\naF3.0\naF5.0\naF4.0\naF5.0\naF1.0\naF3.0\naF3.0\naF2.0\naF1.0\naF4.0\naF0.0\naF3.0\naF5.0\naF1.0\naF1.0\naF3.0\naF3.0\naF2.0\naF0.0\naF3.0\naF0.0\naF4.0\naF0.0\naF1.0\naF2.0\naF3.0\naF1.0\naF4.0\naF2.0\naF6.0\naF4.0\naF2.0\naF2.0\naF0.0\naF2.0\naF3.0\naF2.0\naF0.0\naF3.0\naF0.0\naF2.0\naF3.0\naF1.0\naF2.0\naF1.0\naF5.0\naF4.0\naF4.0\naF1.0\naF3.0\naF3.0\naF2.0\naF5.0\naF0.0\naF1.0\naF3.0\naF2.0\naF3.0\naF2.0\naF1.0\naF6.0\naF2.0\naF6.0\naF1.0\naF2.0\naF1.0\naF3.0\naF2.0\naF1.0\naF2.0\naF3.0\naF1.0\naF0.0\naF3.0\naF1.0\naF2.0\naF4.0\naF4.0\naF3.0\naF2.0\naF1.0\naF1.0\naF0.0\naF2.0\naF2.0\naF5.0\naF4.0\naF3.0\naF2.0\naF5.0\naF0.0\naF1.0\naF0.0\naF3.0\naF2.0\naF5.0\naF2.0\naF0.0\naF3.0\naF4.0\naF0.0\naF3.0\naF0.0\naF0.0\naF8.0\naF1.0\naF2.0\naF6.0\naF0.0\naF2.0\naF1.0\naF1.0\naF1.0\naF2.0\naF0.0\naF4.0\naF0.0\naF2.0\naF1.0\naF4.0\naF2.0\naF1.0\naF2.0\naF3.0\naF7.0\naF0.0\naF0.0\naF6.0\naF0.0\naF1.0\naF2.0\naF1.0\naF3.0\naF0.0\naF2.0\naF2.0\naF0.0\naF2.0\naF0.0\naF2.0\naF3.0\naF4.0\naF2.0\naF0.0\naF3.0\naF0.0\naF3.0\naF4.0\naF3.0\naF1.0\naF2.0\naF7.0\naF3.0\naF4.0\naF2.0\naF2.0\naF4.0\naF0.0\naF3.0\naF1.0\naF0.0\naF4.0\naF4.0\naF4.0\naF5.0\naF0.0\naF1.0\naF0.0\naF3.0\naF1.0\naF1.0\naF5.0\naF5.0\naF0.0\naF2.0\naF1.0\naF2.0\naF1.0\naF0.0\naF2.0\naF2.0\naF4.0\naF2.0\naF1.0\naF1.0\naF2.0\naF3.0\naF3.0\naF3.0\naF1.0\naF3.0\naF2.0\naF2.0\naF2.0\naF2.0\naF4.0\naF6.0\naF4.0\naF1.0\naF2.0\naF4.0\naF1.0\naF5.0\naF0.0\naF3.0\naF0.0\naF0.0\naF3.0\naF3.0\naF2.0\naF2.0\naF3.0\naF5.0\naF4.0\naF3.0\naF3.0\naF3.0\naF2.0\naF4.0\naF2.0\naF2.0\naF2.0\naF0.0\naF3.0\naF3.0\naF1.0\naF1.0\naF2.0\naF3.0\naF2.0\naF0.0\naF1.0\naF3.0\naF0.0\naF2.0\naF2.0\naF1.0\naF0.0\naF2.0\naF2.0\naF2.0\naF1.0\naF3.0\naF0.0\naF2.0\naF2.0\naF1.0\naF2.0\naF2.0\naF4.0\naF1.0\naF2.0\naF4.0\naF4.0\naF2.0\naF0.0\naF0.0\naF1.0\naF1.0\naF3.0\naF1.0\naF3.0\naF0.0\naF1.0\naF2.0\naF0.0\naF4.0\naF3.0\naF0.0\naF2.0\naF3.0\naF1.0\naF6.0\naF3.0\naF1.0\naF1.0\naF0.0\naF6.0\naF1.0\naF4.0\naF2.0\naF0.0\naF1.0\naF4.0\naF5.0\naF2.0\naF5.0\naF0.0\naF1.0\naF2.0\naF1.0\naF2.0\naF1.0\naF2.0\naF3.0\naF3.0\naF2.0\naF1.0\naF3.0\naF1.0\naF2.0\naF1.0\naF2.0\naF3.0\naF0.0\naF0.0\naF3.0\naF1.0\naF5.0\naF1.0\naF0.0\naF1.0\naF1.0\naF1.0\naF2.0\naF1.0\naF5.0\naF4.0\naF2.0\naF2.0\naF2.0\naF2.0\naF3.0\naF4.0\naF0.0\naF2.0\naF2.0\naF2.0\naF3.0\naF4.0\naF3.0\naF7.0\naF3.0\naF2.0\naF4.0\naF0.0\naF3.0\naF3.0\naF3.0\naF1.0\naF2.0\naF2.0\naF1.0\naF1.0\naF7.0\naF1.0\naF3.0\naF2.0\naF1.0\naF2.0\naF1.0\naF1.0\naF0.0\naF0.0\naF3.0\naF0.0\naF1.0\naF3.0\naF0.0\naF2.0\naF1.0\naF2.0\naF2.0\naF3.0\naF2.0\naF7.0\naF0.0\naF2.0\naF2.0\naF3.0\naF1.0\naF1.0\naF0.0\naF0.0\naF1.0\naF0.0\naF3.0\naF0.0\naF3.0\naF3.0\naF2.0\naF3.0\naF2.0\naF2.0\naF3.0\naF2.0\naF2.0\naF2.0\naF0.0\naF2.0\naF3.0\naF4.0\naF3.0\naF3.0\naF2.0\naF4.0\naF4.0\naF2.0\naF0.0\naF1.0\naF2.0\naF1.0\naF2.0\naF4.0\naF1.0\naF0.0\naF4.0\naF7.0\naF1.0\naF2.0\naF3.0\naF1.0\naF5.0\naF2.0\naF3.0\naF2.0\naF2.0\naF2.0\naF7.0\naF0.0\naF3.0\naF1.0\naF0.0\naF3.0\naF2.0\naF2.0\naF1.0\naF3.0\naF3.0\naF3.0\naF4.0\naF1.0\naF1.0\naF2.0\naF0.0\naF6.0\naF6.0\naF2.0\naF5.0\naF1.0\naF1.0\naF3.0\naF1.0\naF3.0\naF0.0\naF5.0\naF2.0\naF0.0\naF3.0\naF3.0\naF2.0\naF0.0\naF1.0\naF2.0\naF2.0\naF4.0\naF3.0\naF1.0\naF3.0\naF1.0\naF5.0\naF3.0\naF3.0\naF3.0\naF0.0\naF2.0\naF1.0\naF2.0\naF3.0\naF2.0\naF1.0\naF2.0\naF4.0\naF6.0\naF3.0\naF5.0\naF4.0\naF5.0\naF3.0\naF2.0\naF3.0\naF1.0\naF3.0\naF2.0\naF2.0\naF9.0\naF2.0\naF0.0\naF1.0\naF1.0\naF2.0\naF2.0\naF4.0\naF8.0\naF4.0\naF2.0\naF1.0\naF0.0\naF1.0\naF1.0\naF4.0\naF2.0\naF0.0\naF1.0\naF4.0\naF5.0\naF3.0\naF5.0\naF0.0\naF1.0\naF2.0\naF1.0\naF2.0\naF5.0\naF2.0\naF5.0\naF2.0\naF8.0\naF1.0\naF4.0\naF1.0\naF7.0\naF2.0\naF0.0\naF2.0\naF3.0\naF0.0\naF1.0\naF3.0\naF5.0\naF4.0\naF5.0\naF3.0\naF7.0\naF3.0\naF0.0\naF3.0\naF0.0\naF0.0\naF5.0\naF2.0\naF2.0\naF4.0\naF4.0\naF3.0\naF1.0\naF2.0\naF5.0\naF1.0\naF0.0\naF4.0\naF5.0\naF3.0\naF1.0\naF4.0\naF1.0\naF2.0\naF5.0\naF0.0\naF6.0\naF2.0\naF2.0\naF2.0\naF2.0\naF4.0\naF2.0\naF2.0\naF3.0\naF2.0\naF7.0\naF1.0\naF1.0\naF6.0\naF1.0\naF5.0\naF1.0\naF3.0\naF7.0\naF3.0\naF1.0\naF0.0\naF2.0\naF2.0\naF5.0\naF1.0\naF0.0\naF5.0\naF3.0\naF5.0\naF2.0\naF0.0\naF9.0\naF4.0\naF1.0\naF3.0\naF6.0\naF6.0\naF0.0\naF6.0\naF8.0\naF6.0\naF4.0\naF2.0\naF5.0\naF0.0\naF3.0\naF6.0\naF1.0\naF2.0\naF3.0\naF5.0\naF7.0\naF6.0\naF2.0\naF6.0\naF2.0\naF8.0\naF4.0\naF7.0\naF3.0\naF4.0\naF4.0\naF4.0\naF9.0\naF2.0\naF4.0\naF4.0\naF6.0\naF8.0\naF4.0\naF7.0\naF4.0\naF3.0\naF6.0\naF5.0\naF11.0\naF5.0\naF6.0\naF1.0\naF4.0\naF2.0\naF1.0\naF1.0\naF3.0\naF1.0\naF3.0\naF4.0\naF8.0\naF6.0\naF2.0\naF4.0\naF7.0\naF6.0\naF4.0\naF5.0\naF4.0\naF0.0\naF1.0\naF4.0\naF6.0\naF5.0\naF7.0\naF6.0\naF5.0\naF6.0\naF5.0\naF9.0\naF4.0\naF3.0\naF2.0\naF2.0\naF4.0\naF3.0\naF1.0\naF4.0\naF2.0\naF4.0\naF2.0\naF2.0\naF6.0\naF4.0\naF4.0\naF2.0\naF14.0\naF3.0\naF2.0\naF4.0\naF5.0\naF4.0\naF4.0\naF4.0\naF2.0\naF4.0\naF6.0\naF3.0\naF1.0\naF3.0\naF3.0\naF2.0\naF14.0\naF7.0\naF5.0\naF10.0\naF9.0\naF5.0\naF4.0\naF8.0\naF3.0\naF2.0\naF3.0\naF4.0\naF5.0\naF5.0\naF7.0\naF9.0\naF5.0\naF4.0\naF4.0\naF8.0\naF1.0\naF5.0\naF4.0\naF6.0\naF6.0\naF3.0\naF11.0\naF4.0\naF10.0\naF4.0\naF5.0\naF4.0\naF8.0\naF5.0\naF7.0\naF2.0\naF3.0\naF6.0\naF4.0\naF4.0\naF7.0\naF3.0\naF2.0\naF5.0\naF7.0\naF6.0\naF2.0\naF8.0\naF5.0\naF0.0\naF4.0\naF6.0\naF3.0\naF3.0\naF3.0\naF7.0\naF5.0\naF6.0\naF6.0\naF4.0\naF8.0\naF4.0\naF7.0\naF6.0\naF10.0\naF6.0\naF4.0\naF4.0\naF3.0\naF3.0\naF6.0\naF2.0\naF3.0\naF6.0\naF5.0\naF9.0\naF9.0\naF3.0\naF4.0\naF4.0\naF3.0\naF6.0\naF3.0\naF14.0\naF5.0\naF4.0\naF6.0\naF4.0\naF7.0\naF8.0\naF0.0\naF3.0\naF6.0\naF3.0\naF3.0\naF3.0\naF6.0\naF5.0\naF3.0\naF5.0\naF3.0\naF5.0\naF6.0\naF4.0\naF3.0\naF1.0\naF8.0\naF14.0\naF4.0\naF8.0\naF2.0\naF4.0\naF5.0\naF5.0\naF7.0\naF8.0\naF7.0\naF5.0\naF3.0\naF8.0\naF2.0\naF1.0\naF5.0\naF4.0\naF6.0\naF2.0\naF6.0\naF5.0\naF6.0\naF7.0\naF8.0\naF11.0\naF6.0\naF5.0\naF1.0\naF5.0\naF2.0\naF6.0\naF5.0\naF1.0\naF0.0\naF5.0\naF6.0\naF5.0\naF6.0\naF7.0\naF6.0\naF7.0\naF6.0\naF2.0\naF5.0\naF9.0\naF6.0\naF4.0\naF6.0\naF1.0\naF6.0\naF4.0\naF3.0\naF9.0\naF5.0\naF6.0\naF8.0\naF4.0\naF5.0\naF4.0\naF9.0\naF5.0\naF2.0\naF4.0\naF6.0\naF1.0\naF5.0\naF7.0\naF5.0\naF8.0\naF7.0\naF3.0\naF6.0\naF5.0\naF5.0\naF5.0\naF14.0\naF7.0\naF7.0\naF4.0\naF6.0\naF8.0\naF4.0\naF7.0\naF6.0\naF6.0\naF9.0\naF10.0\naF8.0\naF7.0\naF11.0\naF4.0\naF6.0\naF7.0\naF5.0\naF7.0\naF7.0\naF4.0\naF7.0\naF6.0\naF3.0\naF13.0\naF7.0\naF3.0\naF3.0\naF12.0\naF7.0\naF8.0\naF7.0\naF9.0\naF7.0\naF7.0\naF5.0\naF5.0\naF4.0\naF9.0\naF11.0\naF9.0\naF5.0\naF7.0\naF3.0\naF7.0\naF2.0\naF15.0\naF3.0\naF7.0\naF10.0\naF9.0\naF6.0\naF3.0\naF3.0\naF5.0\naF6.0\naF9.0\naF6.0\naF9.0\naF5.0\naF8.0\naF8.0\naF16.0\naF3.0\naF10.0\naF13.0\naF8.0\naF7.0\naF7.0\naF9.0\naF10.0\naF11.0\naF8.0\naF11.0\naF6.0\naF12.0\naF9.0\naF13.0\naF8.0\naF9.0\naF3.0\naF9.0\naF7.0\naF9.0\naF6.0\naF8.0\naF7.0\naF10.0\naF14.0\naF12.0\naF8.0\naF5.0\naF4.0\naF9.0\naF10.0\naF10.0\naF8.0\naF14.0\naF5.0\naF11.0\naF8.0\naF8.0\naF8.0\naF10.0\naF7.0\naF9.0\naF6.0\naF9.0\naF8.0\naF6.0\naF17.0\naF12.0\naF7.0\naF10.0\naF9.0\naF10.0\naF7.0\naF7.0\naF12.0\naF8.0\naF12.0\naF8.0\naF6.0\naF6.0\naF6.0\naF12.0\naF11.0\naF10.0\naF8.0\naF10.0\naF6.0\naF8.0\naF3.0\naF9.0\naF11.0\naF16.0\naF14.0\naF16.0\naF15.0\naF6.0\naF7.0\naF5.0\naF9.0\naF9.0\naF8.0\naF10.0\naF9.0\naF8.0\naF6.0\naF14.0\naF16.0\naF11.0\naF10.0\naF4.0\naF12.0\naF8.0\naF4.0\naF8.0\naF11.0\naF10.0\naF5.0\naF10.0\naF7.0\naF9.0\naF6.0\naF6.0\naF8.0\naF11.0\naF6.0\naF13.0\naF8.0\naF9.0\naF19.0\naF17.0\naF6.0\naF6.0\naF17.0\naF7.0\naF5.0\naF7.0\naF9.0\naF15.0\naF14.0\naF7.0\naF4.0\naF19.0\naF10.0\naF8.0\naF14.0\naF9.0\naF13.0\naF9.0\naF7.0\naF12.0\naF9.0\naF18.0\naF14.0\naF10.0\naF9.0\naF11.0\naF10.0\naF11.0\naF18.0\naF9.0\naF13.0\naF10.0\naF15.0\naF9.0\naF11.0\naF8.0\naF10.0\naF9.0\naF17.0\naF7.0\naF8.0\naF14.0\naF4.0\naF7.0\naF11.0\naF24.0\naF17.0\naF11.0\naF13.0\naF8.0\naF13.0\naF17.0\naF9.0\naF11.0\naF11.0\naF13.0\naF7.0\naF0.0\naF3.0\naF8.0\naF14.0\naF10.0\naF10.0\naF8.0\naF15.0\naF12.0\naF10.0\naF8.0\naF9.0\naF6.0\naF10.0\naF24.0\naF11.0\naF11.0\naF10.0\naF10.0\naF18.0\naF12.0\naF7.0\naF16.0\naF8.0\naF14.0\naF10.0\naF3.0\naF5.0\naF8.0\naF23.0\naF10.0\naF13.0\naF14.0\naF12.0\naF15.0\naF16.0\naF8.0\naF23.0\naF12.0\naF18.0\naF13.0\naF9.0\naF9.0\naF12.0\naF12.0\naF12.0\naF12.0\naF12.0\naF7.0\naF17.0\naF9.0\naF19.0\naF15.0\naF13.0\naF11.0\naF14.0\naF9.0\naF9.0\naF12.0\naF9.0\naF11.0\naF12.0\naF23.0\naF17.0\naF13.0\naF17.0\naF9.0\naF8.0\naF12.0\naF13.0\naF11.0\naF17.0\naF11.0\naF12.0\naF13.0\naF9.0\naF12.0\naF9.0\naF11.0\naF22.0\naF19.0\naF14.0\naF25.0\naF15.0\naF10.0\naF24.0\naF8.0\naF20.0\naF11.0\naF17.0\naF13.0\naF25.0\naF11.0\naF20.0\naF10.0\naF11.0\naF10.0\naF23.0\naF21.0\naF10.0\naF8.0\naF5.0\naF12.0\naF19.0\naF18.0\naF23.0\naF17.0\naF29.0\naF17.0\naF8.0\naF13.0\naF19.0\naF16.0\naF15.0\naF22.0\naF34.0\naF8.0\naF12.0\naF13.0\naF18.0\naF27.0\naF15.0\naF18.0\naF8.0\naF15.0\naF20.0\naF10.0\naF15.0\naF14.0\naF11.0\naF10.0\naF9.0\naF20.0\naF29.0\naF15.0\naF13.0\naF9.0\naF16.0\naF10.0\naF13.0\naF10.0\naF47.0\naF11.0\naF9.0\naF27.0\naF12.0\naF11.0\naF21.0\naF16.0\naF20.0\naF11.0\naF10.0\naF19.0\naF37.0\naF12.0\naF17.0\naF21.0\naF17.0\naF17.0\naF19.0\naF10.0\naF14.0\naF18.0\naF15.0\naF8.0\naF22.0\naF13.0\naF13.0\naF20.0\naF18.0\naF28.0\naF29.0\naF10.0\naF11.0\naF12.0\naF17.0\naF7.0\naF13.0\naF19.0\naF7.0\naF18.0\naF16.0\naF16.0\naF23.0\naF11.0\naF17.0\naF13.0\naF16.0\naF12.0\naF11.0\naF19.0\naF12.0\naF4.0\naF10.0\naF12.0\naF7.0\naF18.0\naF12.0\naF14.0\naF15.0\naF10.0\naF14.0\naF8.0\naF12.0\naF10.0\naF19.0\naF12.0\naF21.0\naF16.0\naF13.0\naF11.0\naF11.0\naF12.0\naF16.0\naF17.0\naF35.0\naF18.0\naF9.0\naF13.0\naF7.0\naF11.0\naF13.0\naF11.0\naF26.0\naF18.0\naF11.0\naF11.0\naF22.0\naF18.0\naF28.0\naF20.0\naF12.0\naF12.0\naF17.0\naF13.0\naF32.0\naF18.0\naF21.0\naF28.0\naF11.0\naF15.0\naF24.0\naF13.0\naF20.0\naF15.0\naF20.0\naF16.0\naF16.0\naF16.0\naF14.0\naF9.0\naF21.0\naF29.0\naF14.0\naF7.0\naF12.0\naF9.0\naF19.0\naF7.0\naF20.0\naF14.0\naF19.0\naF20.0\naF11.0\naF19.0\naF17.0\naF25.0\naF14.0\naF16.0\naF14.0\naF11.0\naF27.0\naF14.0\naF13.0\naF17.0\naF11.0\naF14.0\naF14.0\naF16.0\naF8.0\naF13.0\naF20.0\naF7.0\naF14.0\naF11.0\naF13.0\naF22.0\naF9.0\naF11.0\naF15.0\naF13.0\naF25.0\naF25.0\naF24.0\naF13.0\naF22.0\naF13.0\naF14.0\naF18.0\naF10.0\naF23.0\naF12.0\naF14.0\naF22.0\naF26.0\naF12.0\naF9.0\naF13.0\naF43.0\naF15.0\naF9.0\naF14.0\naF14.0\naF14.0\naF11.0\naF16.0\naF17.0\naF15.0\naF18.0\naF21.0\naF13.0\naF17.0\naF13.0\naF15.0\naF14.0\naF18.0\naF21.0\naF29.0\naF16.0\naF9.0\naF12.0\naF19.0\naF23.0\naF24.0\naF14.0\naF12.0\naF18.0\naF21.0\naF19.0\naF11.0\naF16.0\naF11.0\naF26.0\naF9.0\naF18.0\naF19.0\naF10.0\naF12.0\naF21.0\naF28.0\naF21.0\naF27.0\naF16.0\naF20.0\naF16.0\naF9.0\naF26.0\naF14.0\naF17.0\naF15.0\naF16.0\naF15.0\naF17.0\naF22.0\naF26.0\naF16.0\naF26.0\naF13.0\naF17.0\naF23.0\naF21.0\naF27.0\naF18.0\naF30.0\naF31.0\naF27.0\naF22.0\naF22.0\naF20.0\naF19.0\naF6.0\naF12.0\naF15.0\naF31.0\naF34.0\naF32.0\naF16.0\naF25.0\naF17.0\naF11.0\naF18.0\naF17.0\naF30.0\naF17.0\naF13.0\naF33.0\naF25.0\naF37.0\naF27.0\naF24.0\naF17.0\naF35.0\naF17.0\naF19.0\naF29.0\naF41.0\naF33.0\naF33.0\naF17.0\naF18.0\naF24.0\naF12.0\naF24.0\naF25.0\naF27.0\naF26.0\naF25.0\naF26.0\naF23.0\naF25.0\naF29.0\naF32.0\naF39.0\naF15.0\naF20.0\naF23.0\naF20.0\naF26.0\naF36.0\naF26.0\naF22.0\naF30.0\naF40.0\naF27.0\naF19.0\naF29.0\naF22.0\naF33.0\naF32.0\naF21.0\naF22.0\naF28.0\naF15.0\naF18.0\naF21.0\naF29.0\naF18.0\naF29.0\naF28.0\naF34.0\naF40.0\naF32.0\naF18.0\naF28.0\naF20.0\naF44.0\naF37.0\naF25.0\naF49.0\naF22.0\naF26.0\naF36.0\naF33.0\naF21.0\naF38.0\naF28.0\naF38.0\naF18.0\naF25.0\naF36.0\naF21.0\naF22.0\naF24.0\naF20.0\naF22.0\naF14.0\naF2.0\naF30.0\naF18.0\naF31.0\naF35.0\naF26.0\naF19.0\naF18.0\naF18.0\naF26.0\naF12.0\naF21.0\naF32.0\naF30.0\naF20.0\naF20.0\naF31.0\naF35.0\naF17.0\naF27.0\naF39.0\naF40.0\naF26.0\naF22.0\naF30.0\naF21.0\naF30.0\naF42.0\naF41.0\naF65.0\naF35.0\naF19.0\naF18.0\naF24.0\naF20.0\naF29.0\naF24.0\naF29.0\naF24.0\naF30.0\naF29.0\naF19.0\naF25.0\naF32.0\naF38.0\naF18.0\naF34.0\naF31.0\naF35.0\naF55.0\naF24.0\naF36.0\naF13.0\naF27.0\naF20.0\naF32.0\naF46.0\naF30.0\naF32.0\naF42.0\naF35.0\naF34.0\naF50.0\naF56.0\naF47.0\naF24.0\naF29.0\naF47.0\naF30.0\naF44.0\naF14.0\naF34.0\naF51.0\naF34.0\naF31.0\naF54.0\naF35.0\naF40.0\naF53.0\naF67.0\naF59.0\naF50.0\naF57.0\naF34.0\naF50.0\naF26.0\naF27.0\naF40.0\naF44.0\naF57.0\naF46.0\naF26.0\naF28.0\naF38.0\naF32.0\naF66.0\naF38.0\naF49.0\naF39.0\naF27.0\naF35.0\naF28.0\naF40.0\naF47.0\naF62.0\naF40.0\naF56.0\naF20.0\naF57.0\naF68.0\naF40.0\naF31.0\naF41.0\naF39.0\naF62.0\naF28.0\naF18.0\naF41.0\naF44.0\naF33.0\naF53.0\naF26.0\naF50.0\naF28.0\naF32.0\naF53.0\naF65.0\naF38.0\naF50.0\naF25.0\naF25.0\naF70.0\naF56.0\naF56.0\naF62.0\naF57.0\naF47.0\naF64.0\naF62.0\naF44.0\naF58.0\naF63.0\naF59.0\naF40.0\naF51.0\naF46.0\naF39.0\naF46.0\naF45.0\naF53.0\naF67.0\naF38.0\naF46.0\naF42.0\naF55.0\naF56.0\naF66.0\naF76.0\naF31.0\naF49.0\naF72.0\naF65.0\naF67.0\naF24.0\naF63.0\naF68.0\naF16.0\naF54.0\naF32.0\naF34.0\naF64.0\naF47.0\naF47.0\naF56.0\naF55.0\naF49.0\naF48.0\naF50.0\naF23.0\naF50.0\naF44.0\naF60.0\naF54.0\naF59.0\naF63.0\naF68.0\naF75.0\naF45.0\naF48.0\naF76.0\naF59.0\naF38.0\naF48.0\naF35.0\naF40.0\naF88.0\naF65.0\naF55.0\naF56.0\naF57.0\naF28.0\naF67.0\naF53.0\naF78.0\naF57.0\naF69.0\naF59.0\naF72.0\naF44.0\naF71.0\naF59.0\naF59.0\naF22.0\naF63.0\naF43.0\naF84.0\naF41.0\naF40.0\naF81.0\naF75.0\naF61.0\naF67.0\naF48.0\naF65.0\naF41.0\naF30.0\naF72.0\naF47.0\naF37.0\naF68.0\naF64.0\naF44.0\naF35.0\naF45.0\naF38.0\naF71.0\naF63.0\naF57.0\naF53.0\naF57.0\naF44.0\naF35.0\naF30.0\naF70.0\naF33.0\naF73.0\naF81.0\naF69.0\naF93.0\naF70.0\naF54.0\naF25.0\naF67.0\naF43.0\naF60.0\naF66.0\naF52.0\naF44.0\naF45.0\naF41.0\naF43.0\naF77.0\naF58.0\naF51.0\naF90.0\naF62.0\naF84.0\naF42.0\naF55.0\naF72.0\naF42.0\naF76.0\naF60.0\naF71.0\naF78.0\naF33.0\naF49.0\naF63.0\naF56.0\naF59.0\naF64.0\naF41.0\naF58.0\naF74.0\naF77.0\naF54.0\naF61.0\naF60.0\naF63.0\naF86.0\naF68.0\naF80.0\naF90.0\naF84.0\naF64.0\naF70.0\naF64.0\naF84.0\naF87.0\naF32.0\naF88.0\naF54.0\naF60.0\naF60.0\naF71.0\naF49.0\naF86.0\naF54.0\naF59.0\naF85.0\naF99.0\naF94.0\naF50.0\naF73.0\naF91.0\naF93.0\naF74.0\naF47.0\naF71.0\naF59.0\naF110.0\naF104.0\naF94.0\naF71.0\naF99.0\naF51.0\naF69.0\naF72.0\naF51.0\naF67.0\naF115.0\naF87.0\naF70.0\naF91.0\naF74.0\naF93.0\naF87.0\naF159.0\naF69.0\naF71.0\naF108.0\naF61.0\naF68.0\naF42.0\naF80.0\naF75.0\naF65.0\naF62.0\naF83.0\naF61.0\naF68.0\naF48.0\naF64.0\naF84.0\naF55.0\naF75.0\naF82.0\naF76.0\naF80.0\naF76.0\naF99.0\naF94.0\naF61.0\naF53.0\naF82.0\naF76.0\naF100.0\naF248.0\naF82.0\naF80.0\naF69.0\naF107.0\naF71.0\naF254.0\naF57.0\naF90.0\naF67.0\naF109.0\naF93.0\naF73.0\naF55.0\naF91.0\naF93.0\naF62.0\naF93.0\naF93.0\naF75.0\naF76.0\naF40.0\naF58.0\naF39.0\naF82.0\naF48.0\naF63.0\naF68.0\naF47.0\naF96.0\naF78.0\naF84.0\naF51.0\naF40.0\naF55.0\naF58.0\naF46.0\naF71.0\naF69.0\naF54.0\naF37.0\naF80.0\naF77.0\naF81.0\naF80.0\naF75.0\naF90.0\naF49.0\naF80.0\naF117.0\naF87.0\naF86.0\naF99.0\naF68.0\naF65.0\naF80.0\naF88.0\naF55.0\naF99.0\naF80.0\naF77.0\naF67.0\naF95.0\naF129.0\naF61.0\naF51.0\naF98.0\naF72.0\naF66.0\naF305.0\naF66.0\naF67.0\naF89.0\naF269.0\naF94.0\naF156.0\naF120.0\naF111.0\naF62.0\naF97.0\naF21.0\naF56.0\naF87.0\naF45.0\naF82.0\naF119.0\naF84.0\naF96.0\naF80.0\naF74.0\naF110.0\naF97.0\naF61.0\naF65.0\naF91.0\naF103.0\naF90.0\naF132.0\naF72.0\naF88.0\naF75.0\naF61.0\naF69.0\naF106.0\naF59.0\naF94.0\naF115.0\naF98.0\naF87.0\naF104.0\naF102.0\naF208.0\naF96.0\naF90.0\naF71.0\naF139.0\naF71.0\naF68.0\naF106.0\naF72.0\naF66.0\naF106.0\naF58.0\naF71.0\naF68.0\naF73.0\naF71.0\naF77.0\naF153.0\naF89.0\naF81.0\naF61.0\naF87.0\naF99.0\naF132.0\naF121.0\naF116.0\naF83.0\naF131.0\naF101.0\naF86.0\naF73.0\naF117.0\naF51.0\naF78.0\naF99.0\naF88.0\naF103.0\naF94.0\naF73.0\naF88.0\naF105.0\naF81.0\naF55.0\naF80.0\naF122.0\naF80.0\naF235.0\naF94.0\naF97.0\naF68.0\naF89.0\naF112.0\naF69.0\naF52.0\naF90.0\naF82.0\naF114.0\naF325.0\naF235.0\naF69.0\naF107.0\naF66.0\naF71.0\naF90.0\naF69.0\naF52.0\naF45.0\naF58.0\naF82.0\naF77.0\naF189.0\naF73.0\naF82.0\naF75.0\naF78.0\naF87.0\naF73.0\naF107.0\naF49.0\naF125.0\naF69.0\naF76.0\naF57.0\naF218.0\naF191.0\naF252.0\naF80.0\naF73.0\naF180.0\naF254.0\naF103.0\naF93.0\naF91.0\naF93.0\naF93.0\naF76.0\naF90.0\naF105.0\naF87.0\naF204.0\naF90.0\naF130.0\naF87.0\naF80.0\naF79.0\naF244.0\naF100.0\naF109.0\naF96.0\naF126.0\naF127.0\naF240.0\naF117.0\naF137.0\naF76.0\naF171.0\naF164.0\naF146.0\naF106.0\naF104.0\naF114.0\naF103.0\naF81.0\naF126.0\naF151.0\naF75.0\naF56.0\naF117.0\naF96.0\naF94.0\naF107.0\naF204.0\naF60.0\naF118.0\naF259.0\naF109.0\naF60.0\naF46.0\naF85.0\naF84.0\naF64.0\naF104.0\naF67.0\naF67.0\naF77.0\naF59.0\naF86.0\naF175.0\naF57.0\naF118.0\naF55.0\naF91.0\naF101.0\naF77.0\naF107.0\naF157.0\naF58.0\naF192.0\naF71.0\naF124.0\naF86.0\naF84.0\naF104.0\naF109.0\naF109.0\naF91.0\naF66.0\naF77.0\naF105.0\naF158.0\naF109.0\naF113.0\naF116.0\naF126.0\naF98.0\naF142.0\naF108.0\naF69.0\naF51.0\naF22.0\naF62.0\naF86.0\naF109.0\naF119.0\naF71.0\naF112.0\naF104.0\naF92.0\naF113.0\naF76.0\naF156.0\naF83.0\naF119.0\naF72.0\naF69.0\naF73.0\naF188.0\naF139.0\naF104.0\naF185.0\naF78.0\naF135.0\naF75.0\naF227.0\naF71.0\naF154.0\naF115.0\naF141.0\naF118.0\naF87.0\naF149.0\naF121.0\naF75.0\naF292.0\naF96.0\naF177.0\naF118.0\naF86.0\naF52.0\naF117.0\naF113.0\naF98.0\naF102.0\naF96.0\naF181.0\naF129.0\naF109.0\naF107.0\naF104.0\naF172.0\naF77.0\naF206.0\naF207.0\naF163.0\naF241.0\naF142.0\naF205.0\naF107.0\naF252.0\naF152.0\naF117.0\naF189.0\naF72.0\naF112.0\naF79.0\naF103.0\naF238.0\naF166.0\naF111.0\naF103.0\naF137.0\naF168.0\naF143.0\naF124.0\naF90.0\naF260.0\naF304.0\naF109.0\naF208.0\naF316.0\naF128.0\naF89.0\naF172.0\naF27.0\naF218.0\naF200.0\naF238.0\naF147.0\naF122.0\naF91.0\naF118.0\naF107.0\naF97.0\naF63.0\naF74.0\naF42.0\naF266.0\naF89.0\naF105.0\naF108.0\naF132.0\naF258.0\naF101.0\naF151.0\naF175.0\naF111.0\naF118.0\naF137.0\naF97.0\naF138.0\naF121.0\naF105.0\naF128.0\naF93.0\naF78.0\naF62.0\naF141.0\naF69.0\naF167.0\naF122.0\naF132.0\naF94.0\naF301.0\naF112.0\naF62.0\naF103.0\naF89.0\naF111.0\naF86.0\naF95.0\naF153.0\naF184.0\naF177.0\naF229.0\naF384.0\naF124.0\naF224.0\naF127.0\naF160.0\naF144.0\naF84.0\naF150.0\naF129.0\naF141.0\naF72.0\naF20.0\naF10.0\naF44.0\naF63.0\naF82.0\naF107.0\naF82.0\naF111.0\naF117.0\naF81.0\naF87.0\naF99.0\naF122.0\naF168.0\naF204.0\naF277.0\naF70.0\naF236.0\naF153.0\naF64.0\naF252.0\naF184.0\naF223.0\naF126.0\naF172.0\naF130.0\naF92.0\naF100.0\naF51.0\naF69.0\naF148.0\naF112.0\naF147.0\naF112.0\naF100.0\naF145.0\naF271.0\naF263.0\naF69.0\naF165.0\naF149.0\naF218.0\naF215.0\naF118.0\naF77.0\naF186.0\naF125.0\naF68.0\naF229.0\naF85.0\naF288.0\naF267.0\naF168.0\naF135.0\naF133.0\naF80.0\naF271.0\naF122.0\naF100.0\naF97.0\naF97.0\naF78.0\naF90.0\naF73.0\naF135.0\naF144.0\naF151.0\naF114.0\naF96.0\naF232.0\naF103.0\naF210.0\naF153.0\naF197.0\naF159.0\naF115.0\naF291.0\naF106.0\naF212.0\naF61.0\naF167.0\naF175.0\naF83.0\naF196.0\naF187.0\naF148.0\naF263.0\naF128.0\naF55.0\naF124.0\naF63.0\naF118.0\naF197.0\naF307.0\naF163.0\naF293.0\naF227.0\naF95.0\naF269.0\naF95.0\naF98.0\naF108.0\naF54.0\naF119.0\naF40.0\naF176.0\naF125.0\naF71.0\naF104.0\naF107.0\naF148.0\naF94.0\naF136.0\naF131.0\naF104.0\naF161.0\naF73.0\naF237.0\naF246.0\naF125.0\naF226.0\naF138.0\naF222.0\naF260.0\naF271.0\naF120.0\naF277.0\naF122.0\naF322.0\naF59.0\naF59.0\naF324.0\naF90.0\naF270.0\naF120.0\naF129.0\naF138.0\naF307.0\naF103.0\naF228.0\naF95.0\naF128.0\naF144.0\naF260.0\naF307.0\naF68.0\naF154.0\naF155.0\naF14.0\naF56.0\naF226.0\naF66.0\naF259.0\naF198.0\naF263.0\naF241.0\naF80.0\naF285.0\naF90.0\naF102.0\naF192.0\naF89.0\naF205.0\naF226.0\naF128.0\naF123.0\naF61.0\naF171.0\naF87.0\naF92.0\naF271.0\naF307.0\naF198.0\naF95.0\naF73.0\naF81.0\naF34.0\naF81.0\naF171.0\naF74.0\naF174.0\naF104.0\naF203.0\naF145.0\naF140.0\naF152.0\naF204.0\naF302.0\naF45.0\naF338.0\naF64.0\naF194.0\naF267.0\naF142.0\naF195.0\naF275.0\naF229.0\naF234.0\naF305.0\naF186.0\naF159.0\naF276.0\naF201.0\naF327.0\naF219.0\naF331.0\naF187.0\naF256.0\naF303.0\naF127.0\naF300.0\naF243.0\naF228.0\naF116.0\naF106.0\naF29.0\naF24.0\naF74.0\naF303.0\naF200.0\naF68.0\naF168.0\naF217.0\naF209.0\naF131.0\naF101.0\naF118.0\naF57.0\naF281.0\naF286.0\naF278.0\naF312.0\naF162.0\naF213.0\naF247.0\naF224.0\naF231.0\naF174.0\naF255.0\naF250.0\naF255.0\naF79.0\naF254.0\naF180.0\naF152.0\naF187.0\naF42.0\naF251.0\naF231.0\naF343.0\naF190.0\naF278.0\naF321.0\naF99.0\naF99.0\naF193.0\naF227.0\naF184.0\naF130.0\naF257.0\naF226.0\naF84.0\naF324.0\naF128.0\naF309.0\naF72.0\naF331.0\naF200.0\naF270.0\naF189.0\naF105.0\naF280.0\naF365.0\naF179.0\naF274.0\naF16.0\naF266.0\naF147.0\naF87.0\naF67.0\naF55.0\naF236.0\naF331.0\naF342.0\naF264.0\naF248.0\naF132.0\naF69.0\naF147.0\naF276.0\naF315.0\naF248.0\naF244.0\naF273.0\naF215.0\naF195.0\naF202.0\naF275.0\naF169.0\naF191.0\naF326.0\naF191.0\naF352.0\naF297.0\naF79.0\naF191.0\naF349.0\naF288.0\naF180.0\naF162.0\naF228.0\naF164.0\naF220.0\naF224.0\naF239.0\naF94.0\naF180.0\naF294.0\naF268.0\naF206.0\naF206.0\naF315.0\naF350.0\naF130.0\naF242.0\naF258.0\naF360.0\naF319.0\naF352.0\naF259.0\naF104.0\naF78.0\naF189.0\naF157.0\naF177.0\naF257.0\naF337.0\naF58.0\naF265.0\naF273.0\naF241.0\naF192.0\naF327.0\naF290.0\naF101.0\naF300.0\naF185.0\naF236.0\naF78.0\naF279.0\naF300.0\naF296.0\naF200.0\naF68.0\naF329.0\naF219.0\naF300.0\naF331.0\naF233.0\naF328.0\naF381.0\naF279.0\naF344.0\naF280.0\naF319.0\naF312.0\naF99.0\naF243.0\naF79.0\naF342.0\naF232.0\naF299.0\naF366.0\naF203.0\naF90.0\naF237.0\naF47.0\naF180.0\naF82.0\naF319.0\naF239.0\naF313.0\naF246.0\naF245.0\naF229.0\naF280.0\naF309.0\naF97.0\naF374.0\naF159.0\naF310.0\naF81.0\naF334.0\naF291.0\naF315.0\naF195.0\naF243.0\naF331.0\naF214.0\naF325.0\naF280.0\naF227.0\naF195.0\naF133.0\naF282.0\naF236.0\naF307.0\naF351.0\naF370.0\naF296.0\naF265.0\naF382.0\naF382.0\naF242.0\naF193.0\naF365.0\naF253.0\naF245.0\naF289.0\naF112.0\naF235.0\naF242.0\naF264.0\naF113.0\naF214.0\naF280.0\naF305.0\naF389.0\naF316.0\naF264.0\naF362.0\naF257.0\naF200.0\naF285.0\naF46.0\naF98.0\naF351.0\naF299.0\naF317.0\naF229.0\naF385.0\naF218.0\naF306.0\naF240.0\naF73.0\naF231.0\naF237.0\naF395.0\naF338.0\naF96.0\naF126.0\naF294.0\naF164.0\naF192.0\naF343.0\naF325.0\naF127.0\naF336.0\naF312.0\naF318.0\naF239.0\naF161.0\naF119.0\naF316.0\naF340.0\naF295.0\naF371.0\naF254.0\naF320.0\naF339.0\naF229.0\naF313.0\naF199.0\naF271.0\naF275.0\naF255.0\naF228.0\naF259.0\naF339.0\naF334.0\naF336.0\naF372.0\naF308.0\naF237.0\naF280.0\naF327.0\naF372.0\naF132.0\naF289.0\naF308.0\naF296.0\naF241.0\naF277.0\naF153.0\naF257.0\naF267.0\naF306.0\naF254.0\naF370.0\naF234.0\naF360.0\naF295.0\naF214.0\naF204.0\naF346.0\naF393.0\naF245.0\naF278.0\naF213.0\naF47.0\naF349.0\naF358.0\naF318.0\naF286.0\naF367.0\naF411.0\naF230.0\naF324.0\naF389.0\naF369.0\naF95.0\naF272.0\naF313.0\naF344.0\naF237.0\naF44.0\naF354.0\naF351.0\naF348.0\naF348.0\naF251.0\naF73.0\naF371.0\naF360.0\naF203.0\naF205.0\naF366.0\naF283.0\naF74.0\naF219.0\naF334.0\naF214.0\naF331.0\naF337.0\naF274.0\naF255.0\naF262.0\naF356.0\naF364.0\naF262.0\naF227.0\naF357.0\naF256.0\naF431.0\naF269.0\naF335.0\naF258.0\naF92.0\naF332.0\naF317.0\naF312.0\naF136.0\naF360.0\naF273.0\naF276.0\naF128.0\naF348.0\naF211.0\naF367.0\naF268.0\naF250.0\naF254.0\naF224.0\naF315.0\naF258.0\naF285.0\naF314.0\naF208.0\naF346.0\naF394.0\naF259.0\naF336.0\naF255.0\naF204.0\naF384.0\naF329.0\naF275.0\naF265.0\naF374.0\naF262.0\naF401.0\naF318.0\naF213.0\naF192.0\naF338.0\naF315.0\naF151.0\naF315.0\naF374.0\naF321.0\naF316.0\naF338.0\naF292.0\naF320.0\naF342.0\naF306.0\naF389.0\naF116.0\naF358.0\naF269.0\naF325.0\naF329.0\naF165.0\naF243.0\naF299.0\naF315.0\naF78.0\naF358.0\naF361.0\naF152.0\naF353.0\naF394.0\naF315.0\naF394.0\naF337.0\naF198.0\naF297.0\naF238.0\naF338.0\naF321.0\naF289.0\naF269.0\naF388.0\naF315.0\naF271.0\naF176.0\naF331.0\naF264.0\naF40.0\naF337.0\naF372.0\naF328.0\naF404.0\naF277.0\naF204.0\naF306.0\naF323.0\naF289.0\naF407.0\naF213.0\naF303.0\naF240.0\naF372.0\naF301.0\naF291.0\naF338.0\naF246.0\naF350.0\naF277.0\naF359.0\naF197.0\naF338.0\naF380.0\naF335.0\naF277.0\naF62.0\naF247.0\naF313.0\naF250.0\naF275.0\naF292.0\naF272.0\naF336.0\naF339.0\naF269.0\naF219.0\naF317.0\naF370.0\naF388.0\naF379.0\naF359.0\naF319.0\naF236.0\naF233.0\naF206.0\naF334.0\naF324.0\naF287.0\naF243.0\naF254.0\naF350.0\naF289.0\naF357.0\naF365.0\naF233.0\naF321.0\naF322.0\naF402.0\naF300.0\naF229.0\naF398.0\naF186.0\naF314.0\naF377.0\naF345.0\naF388.0\naF240.0\naF342.0\naF319.0\naF380.0\naF298.0\naF155.0\naF316.0\naF375.0\naF289.0\naF292.0\naF299.0\naF412.0\naF410.0\naF393.0\naF315.0\naF129.0\naF249.0\naF308.0\naF369.0\naF351.0\naF205.0\naF222.0\naF362.0\naF333.0\naF262.0\naF222.0\naF388.0\naF258.0\naF366.0\naF208.0\naF380.0\naF366.0\naF386.0\naF349.0\naF369.0\naF374.0\naF400.0\naF256.0\naF208.0\naF220.0\naF355.0\naF374.0\naF355.0\naF204.0\naF235.0\naF369.0\naF232.0\naF277.0\naF346.0\naF368.0\naF324.0\naF264.0\naF241.0\naF205.0\naF206.0\naF343.0\naF254.0\naF296.0\naF234.0\naF287.0\naF404.0\naF390.0\naF256.0\naF276.0\naF365.0\naF252.0\naF324.0\naF354.0\naF264.0\naF389.0\naF289.0\naF417.0\naF313.0\naF289.0\naF376.0\naF399.0\naF229.0\naF386.0\naF389.0\naF346.0\naF372.0\naF192.0\naF317.0\naF228.0\naF304.0\naF275.0\naF387.0\naF335.0\naF388.0\naF375.0\naF227.0\naF304.0\naF419.0\naF287.0\naF107.0\naF285.0\naF380.0\naF196.0\naF288.0\naF268.0\naF298.0\naF401.0\naF350.0\naF306.0\naF333.0\naF378.0\naF320.0\naF252.0\naF423.0\naF308.0\naF405.0\naF350.0\naF142.0\naF40.0\naF1.0\naF333.0\naF378.0\naF281.0\naF376.0\naF412.0\naF274.0\naF428.0\naF411.0\naF413.0\naF374.0\naF400.0\naF420.0\naF381.0\naF411.0\naF367.0\naF400.0\naF405.0\naF377.0\naF327.0\naF239.0\naF346.0\naF274.0\naF423.0\naF231.0\naF363.0\naF173.0\naF371.0\naF362.0\naF309.0\naF391.0\naF404.0\naF410.0\naF212.0\naF375.0\naF406.0\naF294.0\naF334.0\naF393.0\naF311.0\naF379.0\naF362.0\naF386.0\naF324.0\naF306.0\naF393.0\naF373.0\naF345.0\naF363.0\naF377.0\naF382.0\naF334.0\naF386.0\naF411.0\naF345.0\naF333.0\naF373.0\naF347.0\naF385.0\naF370.0\naF372.0\naF406.0\naF367.0\naF406.0\naF388.0\naF139.0\naF389.0\naF307.0\naF352.0\naF330.0\naF399.0\naF347.0\naF328.0\naF356.0\naF390.0\naF381.0\naF409.0\naF363.0\naF396.0\naF366.0\naF290.0\naF415.0\naF397.0\naF364.0\naF402.0\naF390.0\naF432.0\naF306.0\naF275.0\naF406.0\naF230.0\naF387.0\naF425.0\naF373.0\naF402.0\naF369.0\naF313.0\naF345.0\naF388.0\naF370.0\naF393.0\naF359.0\naF241.0\naF361.0\naF361.0\naF366.0\naF410.0\naF348.0\naF409.0\naF413.0\naF332.0\naF424.0\naF396.0\naF373.0\naF388.0\naF414.0\naF306.0\naF338.0\naF412.0\naF418.0\naF395.0\naF416.0\naF400.0\naF411.0\naF319.0\naF260.0\naF389.0\naF302.0\naF365.0\naF409.0\naF412.0\naF427.0\naF412.0\naF66.0\naF378.0\naF404.0\naF407.0\naF411.0\naF376.0\naF302.0\naF389.0\naF412.0\naF316.0\naF418.0\naF421.0\naF370.0\naF275.0\naF297.0\naF375.0\naF392.0\naF374.0\naF407.0\naF416.0\naF342.0\naF345.0\naF427.0\naF423.0\naF462.0\naF413.0\naF433.0\naF380.0\naF413.0\naF424.0\naF333.0\naF408.0\naF324.0\naF277.0\naF420.0\naF338.0\naF406.0\naF254.0\naF392.0\naF283.0\naF417.0\naF416.0\naF381.0\naF328.0\naF403.0\naF373.0\naF384.0\naF391.0\naF395.0\naF303.0\naF321.0\naF377.0\naF427.0\naF408.0\naF403.0\naF173.0\naF392.0\naF330.0\naF428.0\naF108.0\naF116.0\naF346.0\naF381.0\naF420.0\naF280.0\naF165.0\naF396.0\naF421.0\naF380.0\naF322.0\naF421.0\naF423.0\naF260.0\naF404.0\naF396.0\naF416.0\naF438.0\naF402.0\naF341.0\naF265.0\naF410.0\naF409.0\naF311.0\naF330.0\naF367.0\naF74.0\naF421.0\naF374.0\naF257.0\naF396.0\naF401.0\naF388.0\naF330.0\naF364.0\naF343.0\naF380.0\naF400.0\naF283.0\naF359.0\naF348.0\naF385.0\naF382.0\naF288.0\naF417.0\naF424.0\naF395.0\naF382.0\naF378.0\naF265.0\naF374.0\naF186.0\naF428.0\naF393.0\naF397.0\naF421.0\naF366.0\naF381.0\naF374.0\naF405.0\naF410.0\naF419.0\naF199.0\naF407.0\naF256.0\naF306.0\naF245.0\naF390.0\naF424.0\naF359.0\naF376.0\naF389.0\naF343.0\naF395.0\naF417.0\naF119.0\naF378.0\naF313.0\naF391.0\naF421.0\naF287.0\naF374.0\naF413.0\naF296.0\naF426.0\naF400.0\naF386.0\naF403.0\naF385.0\naF403.0\naF367.0\naF346.0\naF353.0\naF345.0\naF313.0\naF431.0\naF405.0\naF431.0\naF381.0\naF426.0\naF411.0\naF414.0\naF820.0\naF385.0\naF361.0\naF419.0\naF391.0\naF418.0\naF430.0\naF428.0\naF345.0\naF297.0\naF413.0\naF406.0\naF402.0\naF349.0\naF347.0\naF356.0\naF231.0\naF424.0\naF230.0\naF368.0\naF370.0\naF337.0\naF366.0\naF411.0\naF382.0\naF417.0\naF401.0\naF400.0\naF386.0\naF53.0\naF191.0\naF63.0\naF400.0\naF406.0\naF202.0\naF431.0\naF377.0\naF365.0\naF272.0\naF393.0\naF369.0\naF376.0\naF421.0\naF314.0\naF389.0\naF277.0\naF424.0\naF405.0\naF302.0\naF378.0\naF388.0\naF385.0\naF96.0\naF411.0\naF415.0\naF373.0\naF374.0\naF423.0\naF413.0\naF396.0\naF409.0\naF410.0\naF367.0\naF386.0\naF367.0\naF352.0\naF350.0\naF93.0\naF218.0\naF420.0\naF383.0\naF349.0\naF390.0\naF362.0\naF384.0\naF394.0\naF428.0\naF390.0\naF377.0\naF335.0\naF325.0\naF292.0\naF289.0\naF418.0\naF168.0\naF441.0\naF402.0\naF424.0\naF412.0\naF425.0\naF410.0\naF291.0\naF406.0\naF362.0\naF413.0\naF388.0\naF384.0\naF379.0\naF386.0\naF405.0\naF357.0\naF321.0\naF383.0\naF413.0\naF421.0\naF349.0\naF291.0\naF377.0\naF398.0\naF436.0\naF319.0\naF361.0\naF175.0\naF414.0\naF264.0\naF388.0\naF398.0\naF419.0\naF420.0\naF314.0\naF365.0\naF381.0\naF336.0\naF428.0\naF398.0\naF351.0\naF301.0\naF413.0\naF403.0\naF377.0\naF376.0\naF115.0\naF423.0\naF348.0\naF419.0\naF160.0\naF424.0\naF414.0\naF351.0\naF215.0\naF374.0\naF59.0\naF345.0\naF279.0\naF394.0\naF241.0\naF406.0\naF325.0\naF220.0\naF367.0\naF358.0\naF389.0\naF304.0\naF409.0\naF377.0\naF390.0\naF428.0\naF404.0\naF351.0\naF168.0\naF155.0\naF346.0\naF402.0\naF389.0\naF176.0\naF328.0\naF416.0\naF55.0\naF261.0\naF406.0\naF372.0\naF415.0\naF390.0\naF413.0\naF368.0\naF433.0\naF397.0\naF334.0\naF292.0\naF360.0\naF315.0\naF395.0\naF418.0\naF202.0\naF350.0\naF397.0\naF388.0\naF388.0\naF401.0\naF316.0\naF381.0\naF393.0\naF391.0\naF387.0\naF323.0\naF373.0\naF416.0\naF358.0\naF351.0\naF347.0\naF364.0\naF409.0\naF360.0\naF410.0\naF411.0\naF218.0\naF71.0\naF288.0\naF343.0\naF277.0\naF225.0\naF396.0\naF130.0\naF342.0\naF236.0\naF424.0\naF384.0\naF314.0\naF406.0\naF371.0\naF337.0\naF422.0\naF370.0\naF53.0\naF243.0\naF370.0\naF421.0\naF38.0\naF332.0\naF51.0\naF409.0\naF336.0\naF355.0\naF407.0\naF424.0\naF382.0\naF407.0\naF431.0\naF520.0\naF402.0\naF215.0\naF420.0\naF208.0\naF367.0\naF407.0\naF358.0\naF328.0\naF125.0\naF398.0\naF327.0\naF215.0\naF374.0\naF392.0\naF405.0\naF308.0\naF413.0\naF415.0\naF381.0\naF830.0\naF385.0\naF384.0\naF428.0\naF414.0\naF408.0\naF322.0\naF389.0\naF415.0\naF385.0\naF420.0\naF411.0\naF365.0\naF416.0\naF414.0\naF419.0\naF359.0\naF418.0\naF415.0\naF387.0\naF438.0\naF404.0\naF320.0\naF424.0\naF235.0\naF420.0\naF392.0\naF392.0\naF435.0\naF396.0\naF431.0\naF189.0\naF415.0\naF370.0\naF418.0\naF407.0\naF400.0\naF320.0\naF404.0\naF397.0\naF414.0\naF403.0\naF333.0\naF405.0\naF371.0\naF380.0\naF401.0\naF61.0\naF201.0\naF362.0\naF424.0\naF394.0\naF410.0\naF795.0\naF380.0\naF303.0\naF145.0\naF421.0\naF394.0\naF413.0\naF399.0\naF384.0\naF403.0\naF304.0\naF402.0\naF423.0\naF416.0\naF362.0\naF441.0\naF320.0\naF396.0\naF404.0\naF298.0\naF399.0\naF424.0\naF381.0\naF424.0\naF397.0\naF334.0\naF417.0\naF448.0\naF414.0\naF122.0\naF344.0\naF785.0\naF433.0\naF388.0\naF397.0\naF377.0\naF262.0\naF368.0\naF200.0\naF387.0\naF395.0\naF177.0\naF406.0\naF394.0\naF412.0\naF415.0\naF391.0\naF416.0\naF221.0\naF311.0\naF417.0\naF411.0\naF424.0\naF382.0\naF301.0\naF235.0\naF283.0\naF424.0\naF389.0\naF408.0\naF398.0\naF437.0\naF388.0\naF400.0\naF396.0\naF428.0\naF388.0\naF297.0\naF314.0\naF408.0\naF418.0\naF417.0\naF410.0\naF420.0\naF400.0\naF364.0\naF388.0\naF441.0\naF413.0\naF364.0\naF323.0\naF378.0\naF343.0\naF390.0\naF383.0\naF419.0\naF412.0\naF431.0\naF414.0\naF382.0\naF416.0\naF380.0\naF371.0\naF293.0\naF395.0\naF212.0\naF403.0\naF374.0\naF311.0\naF424.0\naF428.0\naF357.0\naF413.0\naF391.0\naF361.0\naF427.0\naF427.0\naF369.0\naF434.0\naF300.0\naF399.0\naF355.0\naF397.0\naF416.0\naF150.0\naF428.0\naF361.0\naF424.0\naF120.0\naF420.0\naF332.0\naF428.0\naF359.0\naF168.0\naF315.0\naF402.0\naF280.0\naF428.0\naF412.0\naF425.0\naF419.0\naF349.0\naF390.0\naF345.0\naF377.0\naF391.0\naF411.0\naF385.0\naF277.0\naF413.0\naF383.0\naF360.0\naF421.0\naF337.0\naF399.0\naF675.0\naF403.0\naF416.0\naF316.0\naF414.0\naF394.0\naF364.0\naF345.0\naF402.0\naF424.0\naF399.0\naF412.0\naF428.0\naF396.0\naF390.0\naF382.0\naF343.0\naF392.0\naF398.0\naF422.0\naF399.0\naF428.0\naF406.0\naF539.0\naF412.0\naF417.0\naF367.0\naF380.0\naF383.0\naF427.0\naF397.0\naF329.0\naF256.0\naF369.0\naF409.0\naF383.0\naF416.0\naF270.0\naF404.0\naF376.0\naF395.0\naF414.0\naF411.0\naF424.0\naF399.0\naF412.0\naF394.0\naF393.0\naF359.0\naF371.0\naF377.0\naF370.0\naF419.0\naF505.0\naF377.0\naF351.0\naF399.0\naF390.0\naF171.0\naF409.0\naF420.0\naF391.0\naF247.0\naF378.0\naF411.0\naF426.0\naF303.0\naF436.0\naF431.0\naF435.0\naF384.0\naF424.0\naF348.0\naF418.0\naF385.0\naF71.0\naF294.0\naF287.0\naF675.0\naF293.0\naF433.0\naF410.0\naF162.0\naF415.0\naF101.0\naF379.0\naF421.0\naF417.0\naF428.0\naF428.0\naF328.0\naF412.0\naF366.0\naF511.0\naF320.0\naF334.0\naF413.0\naF412.0\naF303.0\naF424.0\naF391.0\naF363.0\naF417.0\naF425.0\naF411.0\naF432.0\naF374.0\naF370.0\naF393.0\naF260.0\naF385.0\naF414.0\naF412.0\naF402.0\naF146.0\naF301.0\naF428.0\naF400.0\naF120.0\naF334.0\naF387.0\naF391.0\naF417.0\naF416.0\naF376.0\naF393.0\naF358.0\naF421.0\naF386.0\naF381.0\naF345.0\naF398.0\naF304.0\naF157.0\naF342.0\naF378.0\naF423.0\naF374.0\naF421.0\naF384.0\naF428.0\naF417.0\naF399.0\naF414.0\naF369.0\naF374.0\naF428.0\naF96.0\naF418.0\naF383.0\naF458.0\naF396.0\naF291.0\naF382.0\naF370.0\naF412.0\naF390.0\naF386.0\naF341.0\naF428.0\naF403.0\naF406.0\naF463.0\naF399.0\naF266.0\naF390.0\naF369.0\naF400.0\naF318.0\naF84.0\naF414.0\naF417.0\naF379.0\naF422.0\naF428.0\naF419.0\naF413.0\naF379.0\naF214.0\naF380.0\naF393.0\naF408.0\naF340.0\naF416.0\naF416.0\naF406.0\naF390.0\naF381.0\naF415.0\naF423.0\naF385.0\naF342.0\naF425.0\naF391.0\naF393.0\naF224.0\naF406.0\naF378.0\naF355.0\naF406.0\naF424.0\naF411.0\naF400.0\naF378.0\naF364.0\naF406.0\naF398.0\naF416.0\naF409.0\naF232.0\naF413.0\naF378.0\naF382.0\naF418.0\naF367.0\naF346.0\naF398.0\naF416.0\naF421.0\naF367.0\naF431.0\naF410.0\naF348.0\naF395.0\naF288.0\naF399.0\naF393.0\naF421.0\naF414.0\naF404.0\naF407.0\naF433.0\naF346.0\naF433.0\naF328.0\naF246.0\naF382.0\naF375.0\naF389.0\naF334.0\naF421.0\naF37.0\naF404.0\naF410.0\naF309.0\naF428.0\naF401.0\naF397.0\naF422.0\naF398.0\naF354.0\naF463.0\naF408.0\naF424.0\naF319.0\naF409.0\naF424.0\naF424.0\naF305.0\naF346.0\naF413.0\naF416.0\naF264.0\naF113.0\naF381.0\naF428.0\naF385.0\naF424.0\naF410.0\naF369.0\naF413.0\naF432.0\naF363.0\naF393.0\naF350.0\naF421.0\naF414.0\naF423.0\naF410.0\naF346.0\naF382.0\naF180.0\naF404.0\naF343.0\na."
  },
  {
    "path": "dqn/logs_pkls/Enduro_s001.pkl",
    "content": "(lp0\n(I60000\ncnumpy.core.multiarray\nscalar\np1\n(cnumpy\ndtype\np2\n(S'f8'\np3\nI0\nI1\ntp4\nRp5\n(I3\nS'<'\np6\nNNNI-1\nI-1\nI0\ntp7\nbS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np8\ntp9\nRp10\nF-inf\nF0.0\ntp11\na(I70000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np12\ntp13\nRp14\nF-inf\nF0.0\ntp15\na(I80000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np16\ntp17\nRp18\nF-inf\nF0.0\ntp19\na(I90000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np20\ntp21\nRp22\nF-inf\nF0.0\ntp23\na(I100000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np24\ntp25\nRp26\nF-inf\nF0.0\ntp27\na(I110000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np28\ntp29\nRp30\nF-inf\nF0.0\ntp31\na(I120000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np32\ntp33\nRp34\nF-inf\nF0.0\ntp35\na(I130000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np36\ntp37\nRp38\nF-inf\nF0.0\ntp39\na(I140000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np40\ntp41\nRp42\nF-inf\nF0.0\ntp43\na(I150000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np44\ntp45\nRp46\nF-inf\nF0.0\ntp47\na(I160000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np48\ntp49\nRp50\nF-inf\nF0.0\ntp51\na(I170000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np52\ntp53\nRp54\nF-inf\nF0.0\ntp55\na(I180000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np56\ntp57\nRp58\nF-inf\nF0.0\ntp59\na(I190000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np60\ntp61\nRp62\nF-inf\nF0.0\ntp63\na(I200000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np64\ntp65\nRp66\nF-inf\nF0.0\ntp67\na(I210000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np68\ntp69\nRp70\nF-inf\nF0.0\ntp71\na(I220000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np72\ntp73\nRp74\nF-inf\nF0.0\ntp75\na(I230000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np76\ntp77\nRp78\nF-inf\nF0.0\ntp79\na(I240000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np80\ntp81\nRp82\nF-inf\nF0.0\ntp83\na(I250000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np84\ntp85\nRp86\nF-inf\nF0.0\ntp87\na(I260000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np88\ntp89\nRp90\nF-inf\nF0.0\ntp91\na(I270000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np92\ntp93\nRp94\nF-inf\nF0.0\ntp95\na(I280000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np96\ntp97\nRp98\nF-inf\nF0.0\ntp99\na(I290000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np100\ntp101\nRp102\nF-inf\nF0.0\ntp103\na(I300000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np104\ntp105\nRp106\nF-inf\nF0.0\ntp107\na(I310000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np108\ntp109\nRp110\nF-inf\nF0.0\ntp111\na(I320000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np112\ntp113\nRp114\nF-inf\nF0.0\ntp115\na(I330000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np116\ntp117\nRp118\nF-inf\nF0.0\ntp119\na(I340000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np120\ntp121\nRp122\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np123\ntp124\nRp125\nF0.0\ntp126\na(I350000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np127\ntp128\nRp129\ng125\nF0.0\ntp130\na(I360000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np131\ntp132\nRp133\ng125\nF0.0\ntp134\na(I370000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np135\ntp136\nRp137\ng125\nF0.0\ntp138\na(I380000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np139\ntp140\nRp141\ng125\nF0.0\ntp142\na(I390000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np143\ntp144\nRp145\ng125\nF0.0\ntp146\na(I400000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np147\ntp148\nRp149\ng125\nF0.0\ntp150\na(I410000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np151\ntp152\nRp153\ng125\nF0.0\ntp154\na(I420000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np155\ntp156\nRp157\ng125\nF0.0\ntp158\na(I430000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np159\ntp160\nRp161\ng125\nF0.0\ntp162\na(I440000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np163\ntp164\nRp165\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np166\ntp167\nRp168\nF0.0\ntp169\na(I450000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np170\ntp171\nRp172\ng168\nF0.0\ntp173\na(I460000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np174\ntp175\nRp176\ng168\nF0.0\ntp177\na(I470000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np178\ntp179\nRp180\ng168\nF0.0\ntp181\na(I480000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np182\ntp183\nRp184\ng168\nF0.0\ntp185\na(I490000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np186\ntp187\nRp188\ng168\nF0.0\ntp189\na(I500000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np190\ntp191\nRp192\ng168\nF0.0\ntp193\na(I510000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np194\ntp195\nRp196\ng168\nF0.0\ntp197\na(I520000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np198\ntp199\nRp200\ng168\nF0.0\ntp201\na(I530000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np202\ntp203\nRp204\ng168\nF0.0\ntp205\na(I540000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np206\ntp207\nRp208\ng168\nF0.0\ntp209\na(I550000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np210\ntp211\nRp212\ng168\nF0.0\ntp213\na(I560000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np214\ntp215\nRp216\ng168\nF0.0\ntp217\na(I570000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np218\ntp219\nRp220\ng168\nF0.0\ntp221\na(I580000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np222\ntp223\nRp224\ng168\nF0.0\ntp225\na(I590000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np226\ntp227\nRp228\ng168\nF0.0\ntp229\na(I600000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np230\ntp231\nRp232\ng168\nF0.0\ntp233\na(I610000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np234\ntp235\nRp236\ng168\nF0.0\ntp237\na(I620000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np238\ntp239\nRp240\ng168\nF0.0\ntp241\na(I630000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np242\ntp243\nRp244\ng168\nF0.0\ntp245\na(I640000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np246\ntp247\nRp248\ng168\nF0.0\ntp249\na(I650000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np250\ntp251\nRp252\ng168\nF0.0\ntp253\na(I660000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np254\ntp255\nRp256\ng168\nF0.0\ntp257\na(I670000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np258\ntp259\nRp260\ng168\nF0.0\ntp261\na(I680000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np262\ntp263\nRp264\ng168\nF0.0\ntp265\na(I690000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np266\ntp267\nRp268\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np269\ntp270\nRp271\nF0.0\ntp272\na(I700000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np273\ntp274\nRp275\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np276\ntp277\nRp278\nF1.0\ntp279\na(I710000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np280\ntp281\nRp282\ng278\nF0.0\ntp283\na(I720000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np284\ntp285\nRp286\ng278\nF0.0\ntp287\na(I730000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np288\ntp289\nRp290\ng278\nF0.0\ntp291\na(I740000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np292\ntp293\nRp294\ng278\nF0.0\ntp295\na(I750000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np296\ntp297\nRp298\ng278\nF0.0\ntp299\na(I760000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np300\ntp301\nRp302\ng278\nF0.0\ntp303\na(I770000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np304\ntp305\nRp306\ng278\nF0.0\ntp307\na(I780000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np308\ntp309\nRp310\ng278\nF0.0\ntp311\na(I790000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np312\ntp313\nRp314\ng278\nF0.0\ntp315\na(I800000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np316\ntp317\nRp318\ng278\nF0.0\ntp319\na(I810000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np320\ntp321\nRp322\ng278\nF0.0\ntp323\na(I820000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np324\ntp325\nRp326\ng278\nF0.0\ntp327\na(I830000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np328\ntp329\nRp330\ng278\nF0.0\ntp331\na(I840000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np332\ntp333\nRp334\ng278\nF0.0\ntp335\na(I850000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np336\ntp337\nRp338\ng278\nF1.0\ntp339\na(I860000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np340\ntp341\nRp342\ng278\nF0.0\ntp343\na(I870000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np344\ntp345\nRp346\ng278\nF0.0\ntp347\na(I880000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np348\ntp349\nRp350\ng278\nF0.0\ntp351\na(I890000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np352\ntp353\nRp354\ng278\nF0.0\ntp355\na(I900000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np356\ntp357\nRp358\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np359\ntp360\nRp361\nF0.0\ntp362\na(I910000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np363\ntp364\nRp365\ng361\nF0.0\ntp366\na(I920000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np367\ntp368\nRp369\ng361\nF0.0\ntp370\na(I930000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np371\ntp372\nRp373\ng361\nF0.0\ntp374\na(I940000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np375\ntp376\nRp377\ng361\nF0.0\ntp378\na(I950000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np379\ntp380\nRp381\ng361\nF0.0\ntp382\na(I960000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np383\ntp384\nRp385\ng361\nF0.0\ntp386\na(I970000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np387\ntp388\nRp389\ng361\nF0.0\ntp390\na(I980000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np391\ntp392\nRp393\ng361\nF0.0\ntp394\na(I990000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np395\ntp396\nRp397\ng361\nF0.0\ntp398\na(I1000000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np399\ntp400\nRp401\ng361\nF0.0\ntp402\na(I1010000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np403\ntp404\nRp405\ng361\nF0.0\ntp406\na(I1020000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np407\ntp408\nRp409\ng361\nF0.0\ntp410\na(I1030000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np411\ntp412\nRp413\ng361\nF0.0\ntp414\na(I1040000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np415\ntp416\nRp417\ng361\nF0.0\ntp418\na(I1050000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np419\ntp420\nRp421\ng361\nF0.0\ntp422\na(I1060000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np423\ntp424\nRp425\ng361\nF0.0\ntp426\na(I1070000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np427\ntp428\nRp429\ng361\nF0.0\ntp430\na(I1080000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np431\ntp432\nRp433\ng361\nF0.0\ntp434\na(I1090000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np435\ntp436\nRp437\ng361\nF0.0\ntp438\na(I1100000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np439\ntp440\nRp441\ng361\nF0.0\ntp442\na(I1110000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np443\ntp444\nRp445\ng361\nF0.0\ntp446\na(I1120000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np447\ntp448\nRp449\ng361\nF0.0\ntp450\na(I1130000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np451\ntp452\nRp453\ng361\nF0.0\ntp454\na(I1140000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np455\ntp456\nRp457\ng361\nF0.0\ntp458\na(I1150000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np459\ntp460\nRp461\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np462\ntp463\nRp464\nF0.0\ntp465\na(I1160000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np466\ntp467\nRp468\ng464\nF0.0\ntp469\na(I1170000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np470\ntp471\nRp472\ng464\nF0.0\ntp473\na(I1180000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np474\ntp475\nRp476\ng464\nF0.0\ntp477\na(I1190000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np478\ntp479\nRp480\ng464\nF0.0\ntp481\na(I1200000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np482\ntp483\nRp484\ng464\nF0.0\ntp485\na(I1210000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np486\ntp487\nRp488\ng464\nF0.0\ntp489\na(I1220000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np490\ntp491\nRp492\ng464\nF1.0\ntp493\na(I1230000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np494\ntp495\nRp496\ng464\nF0.0\ntp497\na(I1240000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np498\ntp499\nRp500\ng464\nF0.0\ntp501\na(I1250000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np502\ntp503\nRp504\ng464\nF0.0\ntp505\na(I1260000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np506\ntp507\nRp508\ng464\nF0.0\ntp509\na(I1270000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np510\ntp511\nRp512\ng464\nF0.0\ntp513\na(I1280000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np514\ntp515\nRp516\ng464\nF0.0\ntp517\na(I1290000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np518\ntp519\nRp520\ng464\nF0.0\ntp521\na(I1300000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np522\ntp523\nRp524\ng464\nF0.0\ntp525\na(I1310000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np526\ntp527\nRp528\ng464\nF0.0\ntp529\na(I1320000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np530\ntp531\nRp532\ng464\nF0.0\ntp533\na(I1330000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np534\ntp535\nRp536\ng464\nF0.0\ntp537\na(I1340000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np538\ntp539\nRp540\ng464\nF0.0\ntp541\na(I1350000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np542\ntp543\nRp544\ng464\nF0.0\ntp545\na(I1360000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np546\ntp547\nRp548\ng464\nF0.0\ntp549\na(I1370000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np550\ntp551\nRp552\ng464\nF0.0\ntp553\na(I1380000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np554\ntp555\nRp556\ng464\nF0.0\ntp557\na(I1390000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np558\ntp559\nRp560\ng464\nF0.0\ntp561\na(I1400000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np562\ntp563\nRp564\ng464\nF0.0\ntp565\na(I1410000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np566\ntp567\nRp568\ng464\nF0.0\ntp569\na(I1420000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np570\ntp571\nRp572\ng464\nF1.0\ntp573\na(I1430000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np574\ntp575\nRp576\ng464\nF0.0\ntp577\na(I1440000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np578\ntp579\nRp580\ng464\nF0.0\ntp581\na(I1450000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np582\ntp583\nRp584\ng464\nF0.0\ntp585\na(I1460000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np586\ntp587\nRp588\ng464\nF0.0\ntp589\na(I1470000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np590\ntp591\nRp592\ng464\nF0.0\ntp593\na(I1480000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np594\ntp595\nRp596\ng464\nF0.0\ntp597\na(I1490000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np598\ntp599\nRp600\ng464\nF0.0\ntp601\na(I1500000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np602\ntp603\nRp604\ng464\nF0.0\ntp605\na(I1510000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np606\ntp607\nRp608\ng464\nF0.0\ntp609\na(I1520000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np610\ntp611\nRp612\ng464\nF0.0\ntp613\na(I1530000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np614\ntp615\nRp616\ng464\nF0.0\ntp617\na(I1540000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np618\ntp619\nRp620\ng464\nF0.0\ntp621\na(I1550000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np622\ntp623\nRp624\ng464\nF0.0\ntp625\na(I1560000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np626\ntp627\nRp628\ng464\nF0.0\ntp629\na(I1570000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np630\ntp631\nRp632\ng464\nF0.0\ntp633\na(I1580000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np634\ntp635\nRp636\ng464\nF0.0\ntp637\na(I1590000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np638\ntp639\nRp640\ng464\nF0.0\ntp641\na(I1600000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np642\ntp643\nRp644\ng464\nF0.0\ntp645\na(I1610000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np646\ntp647\nRp648\ng464\nF0.0\ntp649\na(I1620000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np650\ntp651\nRp652\ng464\nF0.0\ntp653\na(I1630000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np654\ntp655\nRp656\ng464\nF0.0\ntp657\na(I1640000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np658\ntp659\nRp660\ng464\nF0.0\ntp661\na(I1650000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np662\ntp663\nRp664\ng464\nF0.0\ntp665\na(I1660000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np666\ntp667\nRp668\ng464\nF0.0\ntp669\na(I1670000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np670\ntp671\nRp672\ng464\nF0.0\ntp673\na(I1680000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np674\ntp675\nRp676\ng464\nF0.0\ntp677\na(I1690000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np678\ntp679\nRp680\ng464\nF0.0\ntp681\na(I1700000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np682\ntp683\nRp684\ng464\nF0.0\ntp685\na(I1710000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np686\ntp687\nRp688\ng464\nF0.0\ntp689\na(I1720000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np690\ntp691\nRp692\ng464\nF0.0\ntp693\na(I1730000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np694\ntp695\nRp696\ng464\nF0.0\ntp697\na(I1740000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np698\ntp699\nRp700\ng464\nF0.0\ntp701\na(I1750000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np702\ntp703\nRp704\ng464\nF0.0\ntp705\na(I1760000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np706\ntp707\nRp708\ng464\nF0.0\ntp709\na(I1770000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np710\ntp711\nRp712\ng464\nF0.0\ntp713\na(I1780000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np714\ntp715\nRp716\ng464\nF0.0\ntp717\na(I1790000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np718\ntp719\nRp720\ng464\nF0.0\ntp721\na(I1800000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np722\ntp723\nRp724\ng464\nF0.0\ntp725\na(I1810000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np726\ntp727\nRp728\ng464\nF0.0\ntp729\na(I1820000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np730\ntp731\nRp732\ng464\nF0.0\ntp733\na(I1830000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np734\ntp735\nRp736\ng464\nF0.0\ntp737\na(I1840000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np738\ntp739\nRp740\ng464\nF0.0\ntp741\na(I1850000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np742\ntp743\nRp744\ng464\nF0.0\ntp745\na(I1860000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np746\ntp747\nRp748\ng464\nF0.0\ntp749\na(I1870000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np750\ntp751\nRp752\ng464\nF0.0\ntp753\na(I1880000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np754\ntp755\nRp756\ng464\nF0.0\ntp757\na(I1890000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np758\ntp759\nRp760\ng464\nF0.0\ntp761\na(I1900000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np762\ntp763\nRp764\ng464\nF0.0\ntp765\na(I1910000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np766\ntp767\nRp768\ng464\nF0.0\ntp769\na(I1920000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np770\ntp771\nRp772\ng464\nF0.0\ntp773\na(I1930000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np774\ntp775\nRp776\ng464\nF0.0\ntp777\na(I1940000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np778\ntp779\nRp780\ng464\nF0.0\ntp781\na(I1950000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np782\ntp783\nRp784\ng464\nF0.0\ntp785\na(I1960000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np786\ntp787\nRp788\ng464\nF0.0\ntp789\na(I1970000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np790\ntp791\nRp792\ng464\nF0.0\ntp793\na(I1980000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np794\ntp795\nRp796\ng464\nF0.0\ntp797\na(I1990000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np798\ntp799\nRp800\ng464\nF0.0\ntp801\na(I2000000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np802\ntp803\nRp804\ng464\nF0.0\ntp805\na(I2010000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np806\ntp807\nRp808\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np809\ntp810\nRp811\nF2.0\ntp812\na(I2020000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np813\ntp814\nRp815\ng811\nF0.0\ntp816\na(I2030000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np817\ntp818\nRp819\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np820\ntp821\nRp822\nF1.0\ntp823\na(I2040000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np824\ntp825\nRp826\ng822\nF0.0\ntp827\na(I2050000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np828\ntp829\nRp830\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np831\ntp832\nRp833\nF1.0\ntp834\na(I2060000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np835\ntp836\nRp837\ng833\nF0.0\ntp838\na(I2070000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np839\ntp840\nRp841\ng833\nF0.0\ntp842\na(I2080000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np843\ntp844\nRp845\ng833\nF0.0\ntp846\na(I2090000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np847\ntp848\nRp849\ng833\nF0.0\ntp850\na(I2100000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np851\ntp852\nRp853\ng833\nF0.0\ntp854\na(I2110000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np855\ntp856\nRp857\ng833\nF0.0\ntp858\na(I2120000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np859\ntp860\nRp861\ng833\nF0.0\ntp862\na(I2130000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np863\ntp864\nRp865\ng833\nF0.0\ntp866\na(I2140000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np867\ntp868\nRp869\ng833\nF0.0\ntp870\na(I2150000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np871\ntp872\nRp873\ng833\nF1.0\ntp874\na(I2160000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np875\ntp876\nRp877\ng833\nF0.0\ntp878\na(I2170000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np879\ntp880\nRp881\ng833\nF0.0\ntp882\na(I2180000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np883\ntp884\nRp885\ng833\nF0.0\ntp886\na(I2190000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np887\ntp888\nRp889\ng833\nF0.0\ntp890\na(I2200000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np891\ntp892\nRp893\ng833\nF0.0\ntp894\na(I2210000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np895\ntp896\nRp897\ng833\nF0.0\ntp898\na(I2220000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np899\ntp900\nRp901\ng833\nF0.0\ntp902\na(I2230000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np903\ntp904\nRp905\ng833\nF0.0\ntp906\na(I2240000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np907\ntp908\nRp909\ng833\nF0.0\ntp910\na(I2250000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np911\ntp912\nRp913\ng833\nF0.0\ntp914\na(I2260000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np915\ntp916\nRp917\ng833\nF0.0\ntp918\na(I2270000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np919\ntp920\nRp921\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np922\ntp923\nRp924\nF0.0\ntp925\na(I2280000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np926\ntp927\nRp928\ng924\nF0.0\ntp929\na(I2290000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np930\ntp931\nRp932\ng924\nF0.0\ntp933\na(I2300000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np934\ntp935\nRp936\ng924\nF0.0\ntp937\na(I2310000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np938\ntp939\nRp940\ng924\nF0.0\ntp941\na(I2320000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np942\ntp943\nRp944\ng924\nF0.0\ntp945\na(I2330000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np946\ntp947\nRp948\ng924\nF1.0\ntp949\na(I2340000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np950\ntp951\nRp952\ng924\nF0.0\ntp953\na(I2350000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np954\ntp955\nRp956\ng924\nF0.0\ntp957\na(I2360000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np958\ntp959\nRp960\ng924\nF0.0\ntp961\na(I2370000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np962\ntp963\nRp964\ng924\nF0.0\ntp965\na(I2380000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np966\ntp967\nRp968\ng924\nF0.0\ntp969\na(I2390000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np970\ntp971\nRp972\ng924\nF0.0\ntp973\na(I2400000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np974\ntp975\nRp976\ng924\nF0.0\ntp977\na(I2410000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np978\ntp979\nRp980\ng924\nF0.0\ntp981\na(I2420000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np982\ntp983\nRp984\ng924\nF0.0\ntp985\na(I2430000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np986\ntp987\nRp988\ng924\nF0.0\ntp989\na(I2440000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np990\ntp991\nRp992\ng924\nF0.0\ntp993\na(I2450000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np994\ntp995\nRp996\ng924\nF0.0\ntp997\na(I2460000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np998\ntp999\nRp1000\ng924\nF0.0\ntp1001\na(I2470000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1002\ntp1003\nRp1004\ng924\nF0.0\ntp1005\na(I2480000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1006\ntp1007\nRp1008\ng924\nF0.0\ntp1009\na(I2490000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1010\ntp1011\nRp1012\ng924\nF1.0\ntp1013\na(I2500000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1014\ntp1015\nRp1016\ng924\nF0.0\ntp1017\na(I2510000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1018\ntp1019\nRp1020\ng924\nF0.0\ntp1021\na(I2520000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1022\ntp1023\nRp1024\ng924\nF0.0\ntp1025\na(I2530000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1026\ntp1027\nRp1028\ng924\nF0.0\ntp1029\na(I2540000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1030\ntp1031\nRp1032\ng924\nF0.0\ntp1033\na(I2550000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1034\ntp1035\nRp1036\ng924\nF0.0\ntp1037\na(I2560000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1038\ntp1039\nRp1040\ng924\nF0.0\ntp1041\na(I2570000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1042\ntp1043\nRp1044\ng924\nF0.0\ntp1045\na(I2580000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1046\ntp1047\nRp1048\ng924\nF0.0\ntp1049\na(I2590000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1050\ntp1051\nRp1052\ng924\nF0.0\ntp1053\na(I2600000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1054\ntp1055\nRp1056\ng924\nF0.0\ntp1057\na(I2610000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1058\ntp1059\nRp1060\ng924\nF0.0\ntp1061\na(I2620000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1062\ntp1063\nRp1064\ng924\nF0.0\ntp1065\na(I2630000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1066\ntp1067\nRp1068\ng924\nF0.0\ntp1069\na(I2640000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1070\ntp1071\nRp1072\ng924\nF0.0\ntp1073\na(I2650000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1074\ntp1075\nRp1076\ng924\nF2.0\ntp1077\na(I2660000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1078\ntp1079\nRp1080\ng924\nF0.0\ntp1081\na(I2670000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1082\ntp1083\nRp1084\ng924\nF1.0\ntp1085\na(I2680000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1086\ntp1087\nRp1088\ng924\nF0.0\ntp1089\na(I2690000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1090\ntp1091\nRp1092\ng924\nF0.0\ntp1093\na(I2700000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1094\ntp1095\nRp1096\ng924\nF0.0\ntp1097\na(I2710000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1098\ntp1099\nRp1100\ng924\nF0.0\ntp1101\na(I2720000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1102\ntp1103\nRp1104\ng924\nF0.0\ntp1105\na(I2730000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1106\ntp1107\nRp1108\ng924\nF0.0\ntp1109\na(I2740000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np1110\ntp1111\nRp1112\ng924\nF0.0\ntp1113\na(I2750000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1114\ntp1115\nRp1116\ng924\nF0.0\ntp1117\na(I2760000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1118\ntp1119\nRp1120\ng924\nF0.0\ntp1121\na(I2770000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1122\ntp1123\nRp1124\ng924\nF0.0\ntp1125\na(I2780000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1126\ntp1127\nRp1128\ng924\nF0.0\ntp1129\na(I2790000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1130\ntp1131\nRp1132\ng924\nF0.0\ntp1133\na(I2800000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1134\ntp1135\nRp1136\ng924\nF0.0\ntp1137\na(I2810000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1138\ntp1139\nRp1140\ng924\nF0.0\ntp1141\na(I2820000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np1142\ntp1143\nRp1144\ng924\nF3.0\ntp1145\na(I2830000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np1146\ntp1147\nRp1148\ng924\nF0.0\ntp1149\na(I2840000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np1150\ntp1151\nRp1152\ng924\nF0.0\ntp1153\na(I2850000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np1154\ntp1155\nRp1156\ng924\nF0.0\ntp1157\na(I2860000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np1158\ntp1159\nRp1160\ng924\nF0.0\ntp1161\na(I2870000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np1162\ntp1163\nRp1164\ng924\nF0.0\ntp1165\na(I2880000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np1166\ntp1167\nRp1168\ng924\nF0.0\ntp1169\na(I2890000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np1170\ntp1171\nRp1172\ng924\nF0.0\ntp1173\na(I2900000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np1174\ntp1175\nRp1176\ng924\nF0.0\ntp1177\na(I2910000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np1178\ntp1179\nRp1180\ng924\nF0.0\ntp1181\na(I2920000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xbe?'\np1182\ntp1183\nRp1184\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xbe?'\np1185\ntp1186\nRp1187\nF0.0\ntp1188\na(I2930000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xbe?'\np1189\ntp1190\nRp1191\ng1187\nF0.0\ntp1192\na(I2940000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xc0?'\np1193\ntp1194\nRp1195\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xc0?'\np1196\ntp1197\nRp1198\nF1.0\ntp1199\na(I2950000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xc0?'\np1200\ntp1201\nRp1202\ng1198\nF0.0\ntp1203\na(I2960000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xc0?'\np1204\ntp1205\nRp1206\ng1198\nF0.0\ntp1207\na(I2970000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xc0?'\np1208\ntp1209\nRp1210\ng1198\nF0.0\ntp1211\na(I2980000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xc0?'\np1212\ntp1213\nRp1214\ng1198\nF0.0\ntp1215\na(I2990000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xc0?'\np1216\ntp1217\nRp1218\ng1198\nF1.0\ntp1219\na(I3000000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xbe?'\np1220\ntp1221\nRp1222\ng1198\nF0.0\ntp1223\na(I3010000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np1224\ntp1225\nRp1226\ng1198\nF0.0\ntp1227\na(I3020000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np1228\ntp1229\nRp1230\ng1198\nF0.0\ntp1231\na(I3030000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np1232\ntp1233\nRp1234\ng1198\nF0.0\ntp1235\na(I3040000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np1236\ntp1237\nRp1238\ng1198\nF0.0\ntp1239\na(I3050000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np1240\ntp1241\nRp1242\ng1198\nF0.0\ntp1243\na(I3060000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np1244\ntp1245\nRp1246\ng1198\nF0.0\ntp1247\na(I3070000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np1248\ntp1249\nRp1250\ng1198\nF0.0\ntp1251\na(I3080000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xbe?'\np1252\ntp1253\nRp1254\ng1198\nF1.0\ntp1255\na(I3090000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xbe?'\np1256\ntp1257\nRp1258\ng1198\nF0.0\ntp1259\na(I3100000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xbe?'\np1260\ntp1261\nRp1262\ng1198\nF0.0\ntp1263\na(I3110000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xbe?'\np1264\ntp1265\nRp1266\ng1198\nF0.0\ntp1267\na(I3120000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xbe?'\np1268\ntp1269\nRp1270\ng1198\nF0.0\ntp1271\na(I3130000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xbe?'\np1272\ntp1273\nRp1274\ng1198\nF0.0\ntp1275\na(I3140000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xbe?'\np1276\ntp1277\nRp1278\ng1198\nF0.0\ntp1279\na(I3150000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np1280\ntp1281\nRp1282\ng1198\nF0.0\ntp1283\na(I3160000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np1284\ntp1285\nRp1286\ng1198\nF1.0\ntp1287\na(I3170000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np1288\ntp1289\nRp1290\ng1198\nF0.0\ntp1291\na(I3180000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xbe?'\np1292\ntp1293\nRp1294\ng1198\nF0.0\ntp1295\na(I3190000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xbe?'\np1296\ntp1297\nRp1298\ng1198\nF0.0\ntp1299\na(I3200000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np1300\ntp1301\nRp1302\ng1198\nF0.0\ntp1303\na(I3210000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np1304\ntp1305\nRp1306\ng1198\nF0.0\ntp1307\na(I3220000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np1308\ntp1309\nRp1310\ng1198\nF0.0\ntp1311\na(I3230000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np1312\ntp1313\nRp1314\ng1198\nF0.0\ntp1315\na(I3240000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np1316\ntp1317\nRp1318\ng1198\nF0.0\ntp1319\na(I3250000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np1320\ntp1321\nRp1322\ng1198\nF0.0\ntp1323\na(I3260000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np1324\ntp1325\nRp1326\ng1198\nF0.0\ntp1327\na(I3270000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1328\ntp1329\nRp1330\ng1198\nF0.0\ntp1331\na(I3280000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1332\ntp1333\nRp1334\ng1198\nF0.0\ntp1335\na(I3290000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1336\ntp1337\nRp1338\ng1198\nF0.0\ntp1339\na(I3300000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1340\ntp1341\nRp1342\ng1198\nF0.0\ntp1343\na(I3310000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1344\ntp1345\nRp1346\ng1198\nF0.0\ntp1347\na(I3320000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1348\ntp1349\nRp1350\ng1198\nF0.0\ntp1351\na(I3330000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1352\ntp1353\nRp1354\ng1198\nF0.0\ntp1355\na(I3340000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1356\ntp1357\nRp1358\ng1198\nF0.0\ntp1359\na(I3350000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1360\ntp1361\nRp1362\ng1198\nF0.0\ntp1363\na(I3360000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1364\ntp1365\nRp1366\ng1198\nF0.0\ntp1367\na(I3370000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1368\ntp1369\nRp1370\ng1198\nF0.0\ntp1371\na(I3380000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1372\ntp1373\nRp1374\ng1198\nF1.0\ntp1375\na(I3390000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1376\ntp1377\nRp1378\ng1198\nF0.0\ntp1379\na(I3400000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1380\ntp1381\nRp1382\ng1198\nF0.0\ntp1383\na(I3410000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1384\ntp1385\nRp1386\ng1198\nF0.0\ntp1387\na(I3420000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1388\ntp1389\nRp1390\ng1198\nF0.0\ntp1391\na(I3430000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1392\ntp1393\nRp1394\ng1198\nF0.0\ntp1395\na(I3440000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1396\ntp1397\nRp1398\ng1198\nF1.0\ntp1399\na(I3450000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1400\ntp1401\nRp1402\ng1198\nF0.0\ntp1403\na(I3460000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np1404\ntp1405\nRp1406\ng1198\nF0.0\ntp1407\na(I3470000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np1408\ntp1409\nRp1410\ng1198\nF0.0\ntp1411\na(I3480000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np1412\ntp1413\nRp1414\ng1198\nF0.0\ntp1415\na(I3490000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xc1?'\np1416\ntp1417\nRp1418\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xc1?'\np1419\ntp1420\nRp1421\nF0.0\ntp1422\na(I3500000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xc0?'\np1423\ntp1424\nRp1425\ng1421\nF0.0\ntp1426\na(I3510000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xbe?'\np1427\ntp1428\nRp1429\ng1421\nF0.0\ntp1430\na(I3520000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xbe?'\np1431\ntp1432\nRp1433\ng1421\nF0.0\ntp1434\na(I3530000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xc4?'\np1435\ntp1436\nRp1437\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xc4?'\np1438\ntp1439\nRp1440\nF0.0\ntp1441\na(I3540000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xc4?'\np1442\ntp1443\nRp1444\ng1440\nF0.0\ntp1445\na(I3550000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xc4?'\np1446\ntp1447\nRp1448\ng1440\nF0.0\ntp1449\na(I3560000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xc4?'\np1450\ntp1451\nRp1452\ng1440\nF0.0\ntp1453\na(I3570000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xc9?'\np1454\ntp1455\nRp1456\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xc9?'\np1457\ntp1458\nRp1459\nF2.0\ntp1460\na(I3580000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xc9?'\np1461\ntp1462\nRp1463\ng1459\nF0.0\ntp1464\na(I3590000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xc9?'\np1465\ntp1466\nRp1467\ng1459\nF0.0\ntp1468\na(I3600000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xc9?'\np1469\ntp1470\nRp1471\ng1459\nF0.0\ntp1472\na(I3610000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\xca?'\np1473\ntp1474\nRp1475\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\xca?'\np1476\ntp1477\nRp1478\nF0.0\ntp1479\na(I3620000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\xca?'\np1480\ntp1481\nRp1482\ng1478\nF0.0\ntp1483\na(I3630000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\xca?'\np1484\ntp1485\nRp1486\ng1478\nF0.0\ntp1487\na(I3640000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\xca?'\np1488\ntp1489\nRp1490\ng1478\nF0.0\ntp1491\na(I3650000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\xca?'\np1492\ntp1493\nRp1494\ng1478\nF0.0\ntp1495\na(I3660000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\xca?'\np1496\ntp1497\nRp1498\ng1478\nF0.0\ntp1499\na(I3670000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xcd?'\np1500\ntp1501\nRp1502\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xcd?'\np1503\ntp1504\nRp1505\nF0.0\ntp1506\na(I3680000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xcd?'\np1507\ntp1508\nRp1509\ng1505\nF0.0\ntp1510\na(I3690000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np1511\ntp1512\nRp1513\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np1514\ntp1515\nRp1516\nF1.0\ntp1517\na(I3700000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np1518\ntp1519\nRp1520\ng1516\nF0.0\ntp1521\na(I3710000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np1522\ntp1523\nRp1524\ng1516\nF0.0\ntp1525\na(I3720000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xcd?'\np1526\ntp1527\nRp1528\ng1516\nF0.0\ntp1529\na(I3730000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xcd?'\np1530\ntp1531\nRp1532\ng1516\nF0.0\ntp1533\na(I3740000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xcd?'\np1534\ntp1535\nRp1536\ng1516\nF0.0\ntp1537\na(I3750000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xd0?'\np1538\ntp1539\nRp1540\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xd0?'\np1541\ntp1542\nRp1543\nF3.0\ntp1544\na(I3760000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xd0?'\np1545\ntp1546\nRp1547\ng1543\nF0.0\ntp1548\na(I3770000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xd0?'\np1549\ntp1550\nRp1551\ng1543\nF0.0\ntp1552\na(I3780000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np1553\ntp1554\nRp1555\ng1543\nF0.0\ntp1556\na(I3790000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xcc?'\np1557\ntp1558\nRp1559\ng1543\nF0.0\ntp1560\na(I3800000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\xc8?'\np1561\ntp1562\nRp1563\ng1543\nF0.0\ntp1564\na(I3810000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\xca?'\np1565\ntp1566\nRp1567\ng1543\nF2.0\ntp1568\na(I3820000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xc7?'\np1569\ntp1570\nRp1571\ng1543\nF0.0\ntp1572\na(I3830000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\xca?'\np1573\ntp1574\nRp1575\ng1543\nF3.0\ntp1576\na(I3840000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\xca?'\np1577\ntp1578\nRp1579\ng1543\nF0.0\ntp1580\na(I3850000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np1581\ntp1582\nRp1583\ng1543\nF0.0\ntp1584\na(I3860000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xc9?'\np1585\ntp1586\nRp1587\ng1543\nF0.0\ntp1588\na(I3870000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\xca?'\np1589\ntp1590\nRp1591\ng1543\nF0.0\ntp1592\na(I3880000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xcc?'\np1593\ntp1594\nRp1595\ng1543\nF0.0\ntp1596\na(I3890000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xcd?'\np1597\ntp1598\nRp1599\ng1543\nF1.0\ntp1600\na(I3900000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xcc?'\np1601\ntp1602\nRp1603\ng1543\nF1.0\ntp1604\na(I3910000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xc9?'\np1605\ntp1606\nRp1607\ng1543\nF0.0\ntp1608\na(I3920000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\xca?'\np1609\ntp1610\nRp1611\ng1543\nF1.0\ntp1612\na(I3930000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\xca?'\np1613\ntp1614\nRp1615\ng1543\nF0.0\ntp1616\na(I3940000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xcc?'\np1617\ntp1618\nRp1619\ng1543\nF2.0\ntp1620\na(I3950000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xcd?'\np1621\ntp1622\nRp1623\ng1543\nF1.0\ntp1624\na(I3960000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xcd?'\np1625\ntp1626\nRp1627\ng1543\nF0.0\ntp1628\na(I3970000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\xd0?'\np1629\ntp1630\nRp1631\ng1543\nF2.0\ntp1632\na(I3980000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\xd0?'\np1633\ntp1634\nRp1635\ng1543\nF0.0\ntp1636\na(I3990000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\xd0?'\np1637\ntp1638\nRp1639\ng1543\nF0.0\ntp1640\na(I4000000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xcd?'\np1641\ntp1642\nRp1643\ng1543\nF0.0\ntp1644\na(I4010000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xcd?'\np1645\ntp1646\nRp1647\ng1543\nF0.0\ntp1648\na(I4020000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xcd?'\np1649\ntp1650\nRp1651\ng1543\nF0.0\ntp1652\na(I4030000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np1653\ntp1654\nRp1655\ng1543\nF0.0\ntp1656\na(I4040000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np1657\ntp1658\nRp1659\ng1543\nF0.0\ntp1660\na(I4050000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np1661\ntp1662\nRp1663\ng1543\nF0.0\ntp1664\na(I4060000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np1665\ntp1666\nRp1667\ng1543\nF0.0\ntp1668\na(I4070000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np1669\ntp1670\nRp1671\ng1543\nF0.0\ntp1672\na(I4080000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np1673\ntp1674\nRp1675\ng1543\nF0.0\ntp1676\na(I4090000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\xd0?'\np1677\ntp1678\nRp1679\ng1543\nF4.0\ntp1680\na(I4100000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\xd1?'\np1681\ntp1682\nRp1683\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\xd1?'\np1684\ntp1685\nRp1686\nF0.0\ntp1687\na(I4110000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\xd1?'\np1688\ntp1689\nRp1690\ng1686\nF0.0\ntp1691\na(I4120000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\xd2?'\np1692\ntp1693\nRp1694\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\xd2?'\np1695\ntp1696\nRp1697\nF2.0\ntp1698\na(I4130000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\xd2?'\np1699\ntp1700\nRp1701\ng1697\nF0.0\ntp1702\na(I4140000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\xd1?'\np1703\ntp1704\nRp1705\ng1697\nF0.0\ntp1706\na(I4150000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xd1?'\np1707\ntp1708\nRp1709\ng1697\nF0.0\ntp1710\na(I4160000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\xd0?'\np1711\ntp1712\nRp1713\ng1697\nF0.0\ntp1714\na(I4170000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xd1?'\np1715\ntp1716\nRp1717\ng1697\nF4.0\ntp1718\na(I4180000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\xd0?'\np1719\ntp1720\nRp1721\ng1697\nF0.0\ntp1722\na(I4190000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\xd0?'\np1723\ntp1724\nRp1725\ng1697\nF0.0\ntp1726\na(I4200000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np1727\ntp1728\nRp1729\ng1697\nF0.0\ntp1730\na(I4210000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xcd?'\np1731\ntp1732\nRp1733\ng1697\nF0.0\ntp1734\na(I4220000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xcc?'\np1735\ntp1736\nRp1737\ng1697\nF0.0\ntp1738\na(I4230000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xcd?'\np1739\ntp1740\nRp1741\ng1697\nF0.0\ntp1742\na(I4240000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\xd1?'\np1743\ntp1744\nRp1745\ng1697\nF4.0\ntp1746\na(I4250000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xd0?'\np1747\ntp1748\nRp1749\ng1697\nF0.0\ntp1750\na(I4260000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xd1?'\np1751\ntp1752\nRp1753\ng1697\nF0.0\ntp1754\na(I4270000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xd0?'\np1755\ntp1756\nRp1757\ng1697\nF0.0\ntp1758\na(I4280000\ng1\n(g5\nS'333333\\xd3?'\np1759\ntp1760\nRp1761\ng1\n(g5\nS'333333\\xd3?'\np1762\ntp1763\nRp1764\nF3.0\ntp1765\na(I4290000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xe1?'\np1766\ntp1767\nRp1768\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xe1?'\np1769\ntp1770\nRp1771\nF3.0\ntp1772\na(I4300000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\xe0?'\np1773\ntp1774\nRp1775\ng1771\nF0.0\ntp1776\na(I4310000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\xe0?'\np1777\ntp1778\nRp1779\ng1771\nF0.0\ntp1780\na(I4320000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\xe1?'\np1781\ntp1782\nRp1783\ng1771\nF0.0\ntp1784\na(I4330000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\xe1?'\np1785\ntp1786\nRp1787\ng1771\nF0.0\ntp1788\na(I4340000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7\\xe3?'\np1789\ntp1790\nRp1791\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7\\xe3?'\np1792\ntp1793\nRp1794\nF3.0\ntp1795\na(I4350000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\xe4?'\np1796\ntp1797\nRp1798\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\xe4?'\np1799\ntp1800\nRp1801\nF3.0\ntp1802\na(I4360000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xe4?'\np1803\ntp1804\nRp1805\ng1801\nF1.0\ntp1806\na(I4370000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xe5?'\np1807\ntp1808\nRp1809\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xe5?'\np1810\ntp1811\nRp1812\nF0.0\ntp1813\na(I4380000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\xf0?'\np1814\ntp1815\nRp1816\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\xf0?'\np1817\ntp1818\nRp1819\nF21.0\ntp1820\na(I4390000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xf1?'\np1821\ntp1822\nRp1823\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xf1?'\np1824\ntp1825\nRp1826\nF0.0\ntp1827\na(I4400000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xf1?'\np1828\ntp1829\nRp1830\ng1826\nF0.0\ntp1831\na(I4410000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xf3?'\np1832\ntp1833\nRp1834\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xf3?'\np1835\ntp1836\nRp1837\nF3.0\ntp1838\na(I4420000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\xf2?'\np1839\ntp1840\nRp1841\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\xf3?'\np1842\ntp1843\nRp1844\nF0.0\ntp1845\na(I4430000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\xf4?'\np1846\ntp1847\nRp1848\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\xf4?'\np1849\ntp1850\nRp1851\nF5.0\ntp1852\na(I4440000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xf5?'\np1853\ntp1854\nRp1855\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xf5?'\np1856\ntp1857\nRp1858\nF0.0\ntp1859\na(I4450000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xf5?'\np1860\ntp1861\nRp1862\ng1858\nF0.0\ntp1863\na(I4460000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xf5?'\np1864\ntp1865\nRp1866\ng1858\nF1.0\ntp1867\na(I4470000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\xf6?'\np1868\ntp1869\nRp1870\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\xf6?'\np1871\ntp1872\nRp1873\nF1.0\ntp1874\na(I4480000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xf7?'\np1875\ntp1876\nRp1877\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xf7?'\np1878\ntp1879\nRp1880\nF1.0\ntp1881\na(I4490000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\xfa?'\np1882\ntp1883\nRp1884\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\xfa?'\np1885\ntp1886\nRp1887\nF3.0\ntp1888\na(I4500000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\xfa?'\np1889\ntp1890\nRp1891\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\xfa?'\np1892\ntp1893\nRp1894\nF0.0\ntp1895\na(I4510000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\\xfa?'\np1896\ntp1897\nRp1898\ng1894\nF1.0\ntp1899\na(I4520000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\xfb?'\np1900\ntp1901\nRp1902\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\xfb?'\np1903\ntp1904\nRp1905\nF7.0\ntp1906\na(I4530000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xfe?'\np1907\ntp1908\nRp1909\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xfe?'\np1910\ntp1911\nRp1912\nF0.0\ntp1913\na(I4540000\ng1\n(g5\nS'333333\\xff?'\np1914\ntp1915\nRp1916\ng1\n(g5\nS'333333\\xff?'\np1917\ntp1918\nRp1919\nF2.0\ntp1920\na(I4550000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\x01@'\np1921\ntp1922\nRp1923\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\x01@'\np1924\ntp1925\nRp1926\nF9.0\ntp1927\na(I4560000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x02@'\np1928\ntp1929\nRp1930\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x02@'\np1931\ntp1932\nRp1933\nF3.0\ntp1934\na(I4570000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\x02@'\np1935\ntp1936\nRp1937\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\x02@'\np1938\ntp1939\nRp1940\nF0.0\ntp1941\na(I4580000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e\\x03@'\np1942\ntp1943\nRp1944\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e\\x03@'\np1945\ntp1946\nRp1947\nF0.0\ntp1948\na(I4590000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e\\x03@'\np1949\ntp1950\nRp1951\ng1\n(g5\nS'333333\\x03@'\np1952\ntp1953\nRp1954\nF1.0\ntp1955\na(I4600000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x03@'\np1956\ntp1957\nRp1958\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x03@'\np1959\ntp1960\nRp1961\nF0.0\ntp1962\na(I4610000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\x03@'\np1963\ntp1964\nRp1965\ng1961\nF0.0\ntp1966\na(I4620000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x01@'\np1967\ntp1968\nRp1969\ng1961\nF1.0\ntp1970\na(I4630000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x01@'\np1971\ntp1972\nRp1973\ng1961\nF3.0\ntp1974\na(I4640000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\x02@'\np1975\ntp1976\nRp1977\ng1961\nF1.0\ntp1978\na(I4650000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\x02@'\np1979\ntp1980\nRp1981\ng1961\nF0.0\ntp1982\na(I4660000\ng1\n(g5\nS'ffffff\\x02@'\np1983\ntp1984\nRp1985\ng1961\nF0.0\ntp1986\na(I4670000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x02@'\np1987\ntp1988\nRp1989\ng1961\nF0.0\ntp1990\na(I4680000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\x02@'\np1991\ntp1992\nRp1993\ng1961\nF0.0\ntp1994\na(I4690000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\\x02@'\np1995\ntp1996\nRp1997\ng1961\nF4.0\ntp1998\na(I4700000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\x01@'\np1999\ntp2000\nRp2001\ng1961\nF0.0\ntp2002\na(I4710000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x01@'\np2003\ntp2004\nRp2005\ng1961\nF0.0\ntp2006\na(I4720000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xfd?'\np2007\ntp2008\nRp2009\ng1961\nF0.0\ntp2010\na(I4730000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00@'\np2011\ntp2012\nRp2013\ng1961\nF14.0\ntp2014\na(I4740000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x01@'\np2015\ntp2016\nRp2017\ng1961\nF6.0\ntp2018\na(I4750000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\x02@'\np2019\ntp2020\nRp2021\ng1961\nF0.0\ntp2022\na(I4760000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\x02@'\np2023\ntp2024\nRp2025\ng1961\nF7.0\ntp2026\na(I4770000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\x02@'\np2027\ntp2028\nRp2029\ng1961\nF1.0\ntp2030\na(I4780000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\x04@'\np2031\ntp2032\nRp2033\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\x04@'\np2034\ntp2035\nRp2036\nF5.0\ntp2037\na(I4790000\ng1\n(g5\nS'ffffff\\x06@'\np2038\ntp2039\nRp2040\ng1\n(g5\nS'ffffff\\x06@'\np2041\ntp2042\nRp2043\nF23.0\ntp2044\na(I4800000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x07@'\np2045\ntp2046\nRp2047\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x07@'\np2048\ntp2049\nRp2050\nF12.0\ntp2051\na(I4810000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x07@'\np2052\ntp2053\nRp2054\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x07@'\np2055\ntp2056\nRp2057\nF1.0\ntp2058\na(I4820000\ng1\n(g5\nS'ffffff\\x06@'\np2059\ntp2060\nRp2061\ng2057\nF0.0\ntp2062\na(I4830000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\x08@'\np2063\ntp2064\nRp2065\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\x08@'\np2066\ntp2067\nRp2068\nF0.0\ntp2069\na(I4840000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x0c@'\np2070\ntp2071\nRp2072\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x0c@'\np2073\ntp2074\nRp2075\nF0.0\ntp2076\na(I4850000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\x0f@'\np2077\ntp2078\nRp2079\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\x0f@'\np2080\ntp2081\nRp2082\nF15.0\ntp2083\na(I4860000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\x0e@'\np2084\ntp2085\nRp2086\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x0f@'\np2087\ntp2088\nRp2089\nF0.0\ntp2090\na(I4870000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\x0e@'\np2091\ntp2092\nRp2093\ng2089\nF0.0\ntp2094\na(I4880000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\r@'\np2095\ntp2096\nRp2097\ng2089\nF2.0\ntp2098\na(I4890000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x0e@'\np2099\ntp2100\nRp2101\ng2089\nF17.0\ntp2102\na(I4900000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\x0e@'\np2103\ntp2104\nRp2105\ng2089\nF0.0\ntp2106\na(I4910000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x0f@'\np2107\ntp2108\nRp2109\ng2089\nF8.0\ntp2110\na(I4920000\ng1\n(g5\nS'333333\\x0f@'\np2111\ntp2112\nRp2113\ng2089\nF0.0\ntp2114\na(I4930000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\x0e@'\np2115\ntp2116\nRp2117\ng2089\nF4.0\ntp2118\na(I4940000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\x0f@'\np2119\ntp2120\nRp2121\ng2089\nF0.0\ntp2122\na(I4950000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x11@'\np2123\ntp2124\nRp2125\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x11@'\np2126\ntp2127\nRp2128\nF0.0\ntp2129\na(I4960000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x13@'\np2130\ntp2131\nRp2132\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x13@'\np2133\ntp2134\nRp2135\nF9.0\ntp2136\na(I4970000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\x14@'\np2137\ntp2138\nRp2139\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\x14@'\np2140\ntp2141\nRp2142\nF13.0\ntp2143\na(I4980000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\x15@'\np2144\ntp2145\nRp2146\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\x15@'\np2147\ntp2148\nRp2149\nF0.0\ntp2150\na(I4990000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x16@'\np2151\ntp2152\nRp2153\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x16@'\np2154\ntp2155\nRp2156\nF13.0\ntp2157\na(I5000000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\x1a@'\np2158\ntp2159\nRp2160\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\x1a@'\np2161\ntp2162\nRp2163\nF67.0\ntp2164\na(I5010000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\x1e@'\np2165\ntp2166\nRp2167\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\x1e@'\np2168\ntp2169\nRp2170\nF28.0\ntp2171\na(I5020000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1 @'\np2172\ntp2173\nRp2174\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1 @'\np2175\ntp2176\nRp2177\nF33.0\ntp2178\na(I5030000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k!@'\np2179\ntp2180\nRp2181\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k!@'\np2182\ntp2183\nRp2184\nF0.0\ntp2185\na(I5040000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n#@'\np2186\ntp2187\nRp2188\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n#@'\np2189\ntp2190\nRp2191\nF2.0\ntp2192\na(I5050000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1$@'\np2193\ntp2194\nRp2195\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1$@'\np2196\ntp2197\nRp2198\nF59.0\ntp2199\na(I5060000\ng1\n(g5\nS'33333\\xb3&@'\np2200\ntp2201\nRp2202\ng1\n(g5\nS'33333\\xb3&@'\np2203\ntp2204\nRp2205\nF13.0\ntp2206\na(I5070000\ng1\n(g5\nS\"\\xa4p=\\n\\xd7\\xa3'@\"\np2207\ntp2208\nRp2209\ng1\n(g5\nS\"\\xa4p=\\n\\xd7\\xa3'@\"\np2210\ntp2211\nRp2212\nF15.0\ntp2213\na(I5080000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8*@'\np2214\ntp2215\nRp2216\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8*@'\np2217\ntp2218\nRp2219\nF40.0\ntp2220\na(I5090000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa+@'\np2221\ntp2222\nRp2223\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa+@'\np2224\ntp2225\nRp2226\nF34.0\ntp2227\na(I5100000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2-@'\np2228\ntp2229\nRp2230\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2-@'\np2231\ntp2232\nRp2233\nF72.0\ntp2234\na(I5110000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x140@'\np2235\ntp2236\nRp2237\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x140@'\np2238\ntp2239\nRp2240\nF42.0\ntp2241\na(I5120000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\1@'\np2242\ntp2243\nRp2244\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\1@'\np2245\ntp2246\nRp2247\nF87.0\ntp2248\na(I5130000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(3@'\np2249\ntp2250\nRp2251\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(3@'\np2252\ntp2253\nRp2254\nF63.0\ntp2255\na(I5140000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc3@'\np2256\ntp2257\nRp2258\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc3@'\np2259\ntp2260\nRp2261\nF30.0\ntp2262\na(I5150000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=6@'\np2263\ntp2264\nRp2265\ng1\n(g5\nS'=\\n\\xd7\\xa3p=6@'\np2266\ntp2267\nRp2268\nF77.0\ntp2269\na(I5160000\ng1\n(g5\nS'fffff\\xa67@'\np2270\ntp2271\nRp2272\ng1\n(g5\nS'fffff\\xa67@'\np2273\ntp2274\nRp2275\nF44.0\ntp2276\na(I5170000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\9@'\np2277\ntp2278\nRp2279\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\9@'\np2280\ntp2281\nRp2282\nF51.0\ntp2283\na(I5180000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf:@'\np2284\ntp2285\nRp2286\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf:@'\np2287\ntp2288\nRp2289\nF115.0\ntp2290\na(I5190000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0c<@'\np2291\ntp2292\nRp2293\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0c<@'\np2294\ntp2295\nRp2296\nF33.0\ntp2297\na(I5200000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde=@'\np2298\ntp2299\nRp2300\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde=@'\np2301\ntp2302\nRp2303\nF27.0\ntp2304\na(I5210000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf0?@'\np2305\ntp2306\nRp2307\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf0?@'\np2308\ntp2309\nRp2310\nF84.0\ntp2311\na(I5220000\ng1\n(g5\nS'fffff\\xc6@@'\np2312\ntp2313\nRp2314\ng1\n(g5\nS'fffff\\xc6@@'\np2315\ntp2316\nRp2317\nF76.0\ntp2318\na(I5230000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdcA@'\np2319\ntp2320\nRp2321\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdcA@'\np2322\ntp2323\nRp2324\nF75.0\ntp2325\na(I5240000\ng1\n(g5\nS'q=\\n\\xd7\\xa3PB@'\np2326\ntp2327\nRp2328\ng1\n(g5\nS'q=\\n\\xd7\\xa3PB@'\np2329\ntp2330\nRp2331\nF30.0\ntp2332\na(I5250000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@C@'\np2333\ntp2334\nRp2335\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@C@'\np2336\ntp2337\nRp2338\nF93.0\ntp2339\na(I5260000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xd9C@'\np2340\ntp2341\nRp2342\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xd9C@'\np2343\ntp2344\nRp2345\nF48.0\ntp2346\na(I5270000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eeD@'\np2347\ntp2348\nRp2349\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eeD@'\np2350\ntp2351\nRp2352\nF51.0\ntp2353\na(I5280000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5HE@'\np2354\ntp2355\nRp2356\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5HE@'\np2357\ntp2358\nRp2359\nF66.0\ntp2360\na(I5290000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x1aF@'\np2361\ntp2362\nRp2363\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x1aF@'\np2364\ntp2365\nRp2366\nF82.0\ntp2367\na(I5300000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x02G@'\np2368\ntp2369\nRp2370\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x02G@'\np2371\ntp2372\nRp2373\nF111.0\ntp2374\na(I5310000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x95G@'\np2375\ntp2376\nRp2377\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x95G@'\np2378\ntp2379\nRp2380\nF39.0\ntp2381\na(I5320000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xd5H@'\np2382\ntp2383\nRp2384\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xd5H@'\np2385\ntp2386\nRp2387\nF74.0\ntp2388\na(I5330000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85kI@'\np2389\ntp2390\nRp2391\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85kI@'\np2392\ntp2393\nRp2394\nF106.0\ntp2395\na(I5340000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGAJ@'\np2396\ntp2397\nRp2398\ng1\n(g5\nS'\\xe1z\\x14\\xaeGAJ@'\np2399\ntp2400\nRp2401\nF80.0\ntp2402\na(I5350000\ng1\n(g5\nS'fffff\\xe6J@'\np2403\ntp2404\nRp2405\ng1\n(g5\nS'fffff\\xe6J@'\np2406\ntp2407\nRp2408\nF68.0\ntp2409\na(I5360000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xdaK@'\np2410\ntp2411\nRp2412\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xdaK@'\np2413\ntp2414\nRp2415\nF47.0\ntp2416\na(I5370000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x8eL@'\np2417\ntp2418\nRp2419\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x8eL@'\np2420\ntp2421\nRp2422\nF48.0\ntp2423\na(I5380000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8aM@'\np2424\ntp2425\nRp2426\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8aM@'\np2427\ntp2428\nRp2429\nF108.0\ntp2430\na(I5390000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGaN@'\np2431\ntp2432\nRp2433\ng1\n(g5\nS'\\xe1z\\x14\\xaeGaN@'\np2434\ntp2435\nRp2436\nF103.0\ntp2437\na(I5400000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xceN@'\np2438\ntp2439\nRp2440\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xceN@'\np2441\ntp2442\nRp2443\nF58.0\ntp2444\na(I5410000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2UO@'\np2445\ntp2446\nRp2447\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2UO@'\np2448\ntp2449\nRp2450\nF90.0\ntp2451\na(I5420000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8P@'\np2452\ntp2453\nRp2454\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8P@'\np2455\ntp2456\nRp2457\nF93.0\ntp2458\na(I5430000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14NP@'\np2459\ntp2460\nRp2461\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00PP@'\np2462\ntp2463\nRp2464\nF92.0\ntp2465\na(I5440000\ng1\n(g5\nS'q=\\n\\xd7\\xa3 P@'\np2466\ntp2467\nRp2468\ng1\n(g5\nS'H\\xe1z\\x14\\xaeWP@'\np2469\ntp2470\nRp2471\nF2.0\ntp2472\na(I5450000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG1P@'\np2473\ntp2474\nRp2475\ng2471\nF102.0\ntp2476\na(I5460000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00 P@'\np2477\ntp2478\nRp2479\ng2471\nF28.0\ntp2480\na(I5470000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zTP@'\np2481\ntp2482\nRp2483\ng2471\nF29.0\ntp2484\na(I5480000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x90P@'\np2485\ntp2486\nRp2487\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x90P@'\np2488\ntp2489\nRp2490\nF93.0\ntp2491\na(I5490000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1euP@'\np2492\ntp2493\nRp2494\ng2490\nF83.0\ntp2495\na(I5500000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x7fP@'\np2496\ntp2497\nRp2498\ng2490\nF72.0\ntp2499\na(I5510000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc0P@'\np2500\ntp2501\nRp2502\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc0P@'\np2503\ntp2504\nRp2505\nF132.0\ntp2506\na(I5520000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xc7P@'\np2507\ntp2508\nRp2509\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xc7P@'\np2510\ntp2511\nRp2512\nF94.0\ntp2513\na(I5530000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf8P@'\np2514\ntp2515\nRp2516\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf8P@'\np2517\ntp2518\nRp2519\nF111.0\ntp2520\na(I5540000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0cQ@'\np2521\ntp2522\nRp2523\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x11Q@'\np2524\ntp2525\nRp2526\nF51.0\ntp2527\na(I5550000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x15Q@'\np2528\ntp2529\nRp2530\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x15Q@'\np2531\ntp2532\nRp2533\nF91.0\ntp2534\na(I5560000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebqQ@'\np2535\ntp2536\nRp2537\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebqQ@'\np2538\ntp2539\nRp2540\nF105.0\ntp2541\na(I5570000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xc4Q@'\np2542\ntp2543\nRp2544\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xc4Q@'\np2545\ntp2546\nRp2547\nF81.0\ntp2548\na(I5580000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#R@'\np2549\ntp2550\nRp2551\ng1\n(g5\nS'\\xa4p=\\n\\xd7#R@'\np2552\ntp2553\nRp2554\nF73.0\ntp2555\na(I5590000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14^R@'\np2556\ntp2557\nRp2558\ng1\n(g5\nS'\\xaeG\\xe1z\\x14^R@'\np2559\ntp2560\nRp2561\nF50.0\ntp2562\na(I5600000\ng1\n(g5\nS'fffff\\xb6R@'\np2563\ntp2564\nRp2565\ng1\n(g5\nS'fffff\\xb6R@'\np2566\ntp2567\nRp2568\nF88.0\ntp2569\na(I5610000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x15S@'\np2570\ntp2571\nRp2572\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x15S@'\np2573\ntp2574\nRp2575\nF115.0\ntp2576\na(I5620000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00`S@'\np2577\ntp2578\nRp2579\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00`S@'\np2580\ntp2581\nRp2582\nF105.0\ntp2583\na(I5630000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xa7S@'\np2584\ntp2585\nRp2586\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xa7S@'\np2587\ntp2588\nRp2589\nF111.0\ntp2590\na(I5640000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xc3S@'\np2591\ntp2592\nRp2593\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xc3S@'\np2594\ntp2595\nRp2596\nF103.0\ntp2597\na(I5650000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xd8S@'\np2598\ntp2599\nRp2600\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5S@'\np2601\ntp2602\nRp2603\nF104.0\ntp2604\na(I5660000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc25T@'\np2605\ntp2606\nRp2607\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc25T@'\np2608\ntp2609\nRp2610\nF116.0\ntp2611\na(I5670000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xfcS@'\np2612\ntp2613\nRp2614\ng2610\nF41.0\ntp2615\na(I5680000\ng1\n(g5\nS'=\\n\\xd7\\xa3p]T@'\np2616\ntp2617\nRp2618\ng1\n(g5\nS'=\\n\\xd7\\xa3p]T@'\np2619\ntp2620\nRp2621\nF97.0\ntp2622\na(I5690000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85{T@'\np2623\ntp2624\nRp2625\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x80T@'\np2626\ntp2627\nRp2628\nF94.0\ntp2629\na(I5700000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8~T@'\np2630\ntp2631\nRp2632\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x9aT@'\np2633\ntp2634\nRp2635\nF30.0\ntp2636\na(I5710000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xa0T@'\np2637\ntp2638\nRp2639\ng1\n(g5\nS'33333\\xa3T@'\np2640\ntp2641\nRp2642\nF116.0\ntp2643\na(I5720000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x8dT@'\np2644\ntp2645\nRp2646\ng2642\nF126.0\ntp2647\na(I5730000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x84T@'\np2648\ntp2649\nRp2650\ng2642\nF8.0\ntp2651\na(I5740000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x8cT@'\np2652\ntp2653\nRp2654\ng2642\nF100.0\ntp2655\na(I5750000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1euT@'\np2656\ntp2657\nRp2658\ng2642\nF98.0\ntp2659\na(I5760000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xa2T@'\np2660\ntp2661\nRp2662\ng2642\nF117.0\ntp2663\na(I5770000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xd1T@'\np2664\ntp2665\nRp2666\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xd1T@'\np2667\ntp2668\nRp2669\nF90.0\ntp2670\na(I5780000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\?U@'\np2671\ntp2672\nRp2673\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\?U@'\np2674\ntp2675\nRp2676\nF56.0\ntp2677\na(I5790000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14^U@'\np2678\ntp2679\nRp2680\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x8eU@'\np2681\ntp2682\nRp2683\nF28.0\ntp2684\na(I5800000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1U@'\np2685\ntp2686\nRp2687\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1U@'\np2688\ntp2689\nRp2690\nF105.0\ntp2691\na(I5810000\ng1\n(g5\nS\"\\xd7\\xa3p=\\n'V@\"\np2692\ntp2693\nRp2694\ng1\n(g5\nS\"\\xd7\\xa3p=\\n'V@\"\np2695\ntp2696\nRp2697\nF132.0\ntp2698\na(I5820000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.V@'\np2699\ntp2700\nRp2701\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2UV@'\np2702\ntp2703\nRp2704\nF0.0\ntp2705\na(I5830000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x1dV@'\np2706\ntp2707\nRp2708\ng2704\nF32.0\ntp2709\na(I5840000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.V@'\np2710\ntp2711\nRp2712\ng2704\nF23.0\ntp2713\na(I5850000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e%V@'\np2714\ntp2715\nRp2716\ng2704\nF23.0\ntp2717\na(I5860000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf58V@'\np2718\ntp2719\nRp2720\ng2704\nF83.0\ntp2721\na(I5870000\ng1\n(g5\nS'\\xa4p=\\n\\xd7SV@'\np2722\ntp2723\nRp2724\ng2704\nF92.0\ntp2725\na(I5880000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8V@'\np2726\ntp2727\nRp2728\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8V@'\np2729\ntp2730\nRp2731\nF106.0\ntp2732\na(I5890000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xadV@'\np2733\ntp2734\nRp2735\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xbfV@'\np2736\ntp2737\nRp2738\nF106.0\ntp2739\na(I5900000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xa1V@'\np2740\ntp2741\nRp2742\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xc4V@'\np2743\ntp2744\nRp2745\nF52.0\ntp2746\na(I5910000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xe1V@'\np2747\ntp2748\nRp2749\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xe1V@'\np2750\ntp2751\nRp2752\nF140.0\ntp2753\na(I5920000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfaV@'\np2754\ntp2755\nRp2756\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x11W@'\np2757\ntp2758\nRp2759\nF128.0\ntp2760\na(I5930000\ng1\n(g5\nS'H\\xe1z\\x14\\xaegW@'\np2761\ntp2762\nRp2763\ng1\n(g5\nS'H\\xe1z\\x14\\xaegW@'\np2764\ntp2765\nRp2766\nF116.0\ntp2767\na(I5940000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xa0W@'\np2768\ntp2769\nRp2770\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xa0W@'\np2771\ntp2772\nRp2773\nF138.0\ntp2774\na(I5950000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x95W@'\np2775\ntp2776\nRp2777\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xaeW@'\np2778\ntp2779\nRp2780\nF75.0\ntp2781\na(I5960000\ng1\n(g5\nS'fffff\\x96W@'\np2782\ntp2783\nRp2784\ng2780\nF77.0\ntp2785\na(I5970000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xe0W@'\np2786\ntp2787\nRp2788\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xe0W@'\np2789\ntp2790\nRp2791\nF189.0\ntp2792\na(I5980000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x13X@'\np2793\ntp2794\nRp2795\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\x13X@'\np2796\ntp2797\nRp2798\nF104.0\ntp2799\na(I5990000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fBX@'\np2800\ntp2801\nRp2802\ng1\n(g5\nS'\\xa4p=\\n\\xd7CX@'\np2803\ntp2804\nRp2805\nF109.0\ntp2806\na(I6000000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14>X@'\np2807\ntp2808\nRp2809\ng2805\nF108.0\ntp2810\na(I6010000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x1eX@'\np2811\ntp2812\nRp2813\ng1\n(g5\nS'\\xaeG\\xe1z\\x14nX@'\np2814\ntp2815\nRp2816\nF49.0\ntp2817\na(I6020000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb0W@'\np2818\ntp2819\nRp2820\ng2816\nF39.0\ntp2821\na(I6030000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xb7W@'\np2822\ntp2823\nRp2824\ng2816\nF129.0\ntp2825\na(I6040000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xc1W@'\np2826\ntp2827\nRp2828\ng2816\nF2.0\ntp2829\na(I6050000\ng1\n(g5\nS'fffff\\xe6W@'\np2830\ntp2831\nRp2832\ng2816\nF158.0\ntp2833\na(I6060000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xdaW@'\np2834\ntp2835\nRp2836\ng2816\nF135.0\ntp2837\na(I6070000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8NX@'\np2838\ntp2839\nRp2840\ng2816\nF103.0\ntp2841\na(I6080000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGaX@'\np2842\ntp2843\nRp2844\ng2816\nF106.0\ntp2845\na(I6090000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xa4X@'\np2846\ntp2847\nRp2848\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xa4X@'\np2849\ntp2850\nRp2851\nF82.0\ntp2852\na(I6100000\ng1\n(g5\nS'33333\\x93X@'\np2853\ntp2854\nRp2855\ng2851\nF79.0\ntp2856\na(I6110000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xc1X@'\np2857\ntp2858\nRp2859\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xc1X@'\np2860\ntp2861\nRp2862\nF107.0\ntp2863\na(I6120000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99X@'\np2864\ntp2865\nRp2866\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xc9X@'\np2867\ntp2868\nRp2869\nF66.0\ntp2870\na(I6130000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9cX@'\np2871\ntp2872\nRp2873\ng2869\nF93.0\ntp2874\na(I6140000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xa2X@'\np2875\ntp2876\nRp2877\ng2869\nF62.0\ntp2878\na(I6150000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xccX@'\np2879\ntp2880\nRp2881\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xccX@'\np2882\ntp2883\nRp2884\nF56.0\ntp2885\na(I6160000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xd0X@'\np2886\ntp2887\nRp2888\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xd0X@'\np2889\ntp2890\nRp2891\nF149.0\ntp2892\na(I6170000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQXY@'\np2893\ntp2894\nRp2895\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQXY@'\np2896\ntp2897\nRp2898\nF111.0\ntp2899\na(I6180000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x9dY@'\np2900\ntp2901\nRp2902\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x9dY@'\np2903\ntp2904\nRp2905\nF129.0\ntp2906\na(I6190000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xc0Y@'\np2907\ntp2908\nRp2909\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xc0Y@'\np2910\ntp2911\nRp2912\nF130.0\ntp2913\na(I6200000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x02Z@'\np2914\ntp2915\nRp2916\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x02Z@'\np2917\ntp2918\nRp2919\nF160.0\ntp2920\na(I6210000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xe2Y@'\np2921\ntp2922\nRp2923\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\nZ@'\np2924\ntp2925\nRp2926\nF99.0\ntp2927\na(I6220000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xf4Y@'\np2928\ntp2929\nRp2930\ng2926\nF96.0\ntp2931\na(I6230000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8>Y@'\np2932\ntp2933\nRp2934\ng2926\nF7.0\ntp2935\na(I6240000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xdaX@'\np2936\ntp2937\nRp2938\ng2926\nF104.0\ntp2939\na(I6250000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xe2X@'\np2940\ntp2941\nRp2942\ng2926\nF131.0\ntp2943\na(I6260000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcfX@'\np2944\ntp2945\nRp2946\ng2926\nF102.0\ntp2947\na(I6270000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xbaX@'\np2948\ntp2949\nRp2950\ng2926\nF94.0\ntp2951\na(I6280000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xcbX@'\np2952\ntp2953\nRp2954\ng2926\nF99.0\ntp2955\na(I6290000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99X@'\np2956\ntp2957\nRp2958\ng2926\nF63.0\ntp2959\na(I6300000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xf7X@'\np2960\ntp2961\nRp2962\ng2926\nF173.0\ntp2963\na(I6310000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0cY@'\np2964\ntp2965\nRp2966\ng2926\nF111.0\ntp2967\na(I6320000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xfeX@'\np2968\ntp2969\nRp2970\ng2926\nF113.0\ntp2971\na(I6330000\ng1\n(g5\nS'fffff\\x16Y@'\np2972\ntp2973\nRp2974\ng2926\nF118.0\ntp2975\na(I6340000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z4Y@'\np2976\ntp2977\nRp2978\ng2926\nF119.0\ntp2979\na(I6350000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xdaY@'\np2980\ntp2981\nRp2982\ng2926\nF82.0\ntp2983\na(I6360000\ng1\n(g5\nS'fffff\\xf6Y@'\np2984\ntp2985\nRp2986\ng2926\nF166.0\ntp2987\na(I6370000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x81Z@'\np2988\ntp2989\nRp2990\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x81Z@'\np2991\ntp2992\nRp2993\nF132.0\ntp2994\na(I6380000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xfcZ@'\np2995\ntp2996\nRp2997\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xfcZ@'\np2998\ntp2999\nRp3000\nF174.0\ntp3001\na(I6390000\ng1\n(g5\nS'\\n\\xd7\\xa3p=J[@'\np3002\ntp3003\nRp3004\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O[@'\np3005\ntp3006\nRp3007\nF127.0\ntp3008\na(I6400000\ng1\n(g5\nS'=\\n\\xd7\\xa3pM[@'\np3009\ntp3010\nRp3011\ng3007\nF129.0\ntp3012\na(I6410000\ng1\n(g5\nS'fffff\\xa6[@'\np3013\ntp3014\nRp3015\ng1\n(g5\nS'fffff\\xa6[@'\np3016\ntp3017\nRp3018\nF110.0\ntp3019\na(I6420000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x08\\\\@'\np3020\ntp3021\nRp3022\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x08\\\\@'\np3023\ntp3024\nRp3025\nF172.0\ntp3026\na(I6430000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00`\\\\@'\np3027\ntp3028\nRp3029\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00`\\\\@'\np3030\ntp3031\nRp3032\nF123.0\ntp3033\na(I6440000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xaa\\\\@'\np3034\ntp3035\nRp3036\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xaa\\\\@'\np3037\ntp3038\nRp3039\nF175.0\ntp3040\na(I6450000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb!]@'\np3041\ntp3042\nRp3043\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb!]@'\np3044\ntp3045\nRp3046\nF140.0\ntp3047\na(I6460000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h]@'\np3048\ntp3049\nRp3050\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h]@'\np3051\ntp3052\nRp3053\nF109.0\ntp3054\na(I6470000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xd8]@'\np3055\ntp3056\nRp3057\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xd8]@'\np3058\ntp3059\nRp3060\nF185.0\ntp3061\na(I6480000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x1d^@'\np3062\ntp3063\nRp3064\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x1d^@'\np3065\ntp3066\nRp3067\nF175.0\ntp3068\na(I6490000\ng1\n(g5\nS'fffff\\xf6^@'\np3069\ntp3070\nRp3071\ng1\n(g5\nS'fffff\\xf6^@'\np3072\ntp3073\nRp3074\nF174.0\ntp3075\na(I6500000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xf2^@'\np3076\ntp3077\nRp3078\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xf9^@'\np3079\ntp3080\nRp3081\nF139.0\ntp3082\na(I6510000\ng1\n(g5\nS'q=\\n\\xd7\\xa30_@'\np3083\ntp3084\nRp3085\ng1\n(g5\nS'q=\\n\\xd7\\xa30_@'\np3086\ntp3087\nRp3088\nF165.0\ntp3089\na(I6520000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8_@'\np3090\ntp3091\nRp3092\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8_@'\np3093\ntp3094\nRp3095\nF166.0\ntp3096\na(I6530000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x08`@'\np3097\ntp3098\nRp3099\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x08`@'\np3100\ntp3101\nRp3102\nF272.0\ntp3103\na(I6540000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eU`@'\np3104\ntp3105\nRp3106\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\\\`@'\np3107\ntp3108\nRp3109\nF137.0\ntp3110\na(I6550000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xbd`@'\np3111\ntp3112\nRp3113\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xbd`@'\np3114\ntp3115\nRp3116\nF351.0\ntp3117\na(I6560000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xdc`@'\np3118\ntp3119\nRp3120\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xdc`@'\np3121\ntp3122\nRp3123\nF153.0\ntp3124\na(I6570000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\a@'\np3125\ntp3126\nRp3127\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\a@'\np3128\ntp3129\nRp3130\nF180.0\ntp3131\na(I6580000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xf0a@'\np3132\ntp3133\nRp3134\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xf0a@'\np3135\ntp3136\nRp3137\nF196.0\ntp3138\na(I6590000\ng1\n(g5\nS'H\\xe1z\\x14\\xae?b@'\np3139\ntp3140\nRp3141\ng1\n(g5\nS'H\\xe1z\\x14\\xae?b@'\np3142\ntp3143\nRp3144\nF199.0\ntp3145\na(I6600000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x12b@'\np3146\ntp3147\nRp3148\ng3144\nF153.0\ntp3149\na(I6610000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85Kb@'\np3150\ntp3151\nRp3152\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85Kb@'\np3153\ntp3154\nRp3155\nF136.0\ntp3156\na(I6620000\ng1\n(g5\nS'\\n\\xd7\\xa3p=zb@'\np3157\ntp3158\nRp3159\ng1\n(g5\nS'\\xa4p=\\n\\xd7{b@'\np3160\ntp3161\nRp3162\nF174.0\ntp3163\na(I6630000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x9eb@'\np3164\ntp3165\nRp3166\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x9eb@'\np3167\ntp3168\nRp3169\nF157.0\ntp3170\na(I6640000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xf2b@'\np3171\ntp3172\nRp3173\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xf2b@'\np3174\ntp3175\nRp3176\nF364.0\ntp3177\na(I6650000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x81c@'\np3178\ntp3179\nRp3180\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x81c@'\np3181\ntp3182\nRp3183\nF313.0\ntp3184\na(I6660000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xe1c@'\np3185\ntp3186\nRp3187\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xe1c@'\np3188\ntp3189\nRp3190\nF187.0\ntp3191\na(I6670000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xc5c@'\np3192\ntp3193\nRp3194\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xe2c@'\np3195\ntp3196\nRp3197\nF83.0\ntp3198\na(I6680000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00d@'\np3199\ntp3200\nRp3201\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00d@'\np3202\ntp3203\nRp3204\nF171.0\ntp3205\na(I6690000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1Rd@'\np3206\ntp3207\nRp3208\ng1\n(g5\nS'{\\x14\\xaeG\\xe1Rd@'\np3209\ntp3210\nRp3211\nF120.0\ntp3212\na(I6700000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb5d@'\np3213\ntp3214\nRp3215\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb5d@'\np3216\ntp3217\nRp3218\nF325.0\ntp3219\na(I6710000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x16e@'\np3220\ntp3221\nRp3222\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x16e@'\np3223\ntp3224\nRp3225\nF407.0\ntp3226\na(I6720000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x92e@'\np3227\ntp3228\nRp3229\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x92e@'\np3230\ntp3231\nRp3232\nF385.0\ntp3233\na(I6730000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xb0e@'\np3234\ntp3235\nRp3236\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xb0e@'\np3237\ntp3238\nRp3239\nF150.0\ntp3240\na(I6740000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf0e@'\np3241\ntp3242\nRp3243\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf0e@'\np3244\ntp3245\nRp3246\nF179.0\ntp3247\na(I6750000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xe7e@'\np3248\ntp3249\nRp3250\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2%f@'\np3251\ntp3252\nRp3253\nF84.0\ntp3254\na(I6760000\ng1\n(g5\nS'fffff\\xdee@'\np3255\ntp3256\nRp3257\ng3253\nF165.0\ntp3258\na(I6770000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5($f@'\np3259\ntp3260\nRp3261\ng3253\nF356.0\ntp3262\na(I6780000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85cf@'\np3263\ntp3264\nRp3265\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85cf@'\np3266\ntp3267\nRp3268\nF405.0\ntp3269\na(I6790000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xc0f@'\np3270\ntp3271\nRp3272\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xc0f@'\np3273\ntp3274\nRp3275\nF172.0\ntp3276\na(I6800000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xfff@'\np3277\ntp3278\nRp3279\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xfff@'\np3280\ntp3281\nRp3282\nF270.0\ntp3283\na(I6810000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\Og@'\np3284\ntp3285\nRp3286\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\Og@'\np3287\ntp3288\nRp3289\nF181.0\ntp3290\na(I6820000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x90g@'\np3291\ntp3292\nRp3293\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x90g@'\np3294\ntp3295\nRp3296\nF128.0\ntp3297\na(I6830000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xb8g@'\np3298\ntp3299\nRp3300\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xcag@'\np3301\ntp3302\nRp3303\nF120.0\ntp3304\na(I6840000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xcdg@'\np3305\ntp3306\nRp3307\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xcdg@'\np3308\ntp3309\nRp3310\nF170.0\ntp3311\na(I6850000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x19h@'\np3312\ntp3313\nRp3314\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x19h@'\np3315\ntp3316\nRp3317\nF197.0\ntp3318\na(I6860000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1emh@'\np3319\ntp3320\nRp3321\ng1\n(g5\nS'H\\xe1z\\x14\\xaeoh@'\np3322\ntp3323\nRp3324\nF167.0\ntp3325\na(I6870000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xa0h@'\np3326\ntp3327\nRp3328\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xa0h@'\np3329\ntp3330\nRp3331\nF345.0\ntp3332\na(I6880000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf8h@'\np3333\ntp3334\nRp3335\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf8h@'\np3336\ntp3337\nRp3338\nF174.0\ntp3339\na(I6890000\ng1\n(g5\nS'\\n\\xd7\\xa3p=Zi@'\np3340\ntp3341\nRp3342\ng1\n(g5\nS'\\n\\xd7\\xa3p=Zi@'\np3343\ntp3344\nRp3345\nF150.0\ntp3346\na(I6900000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x8ei@'\np3347\ntp3348\nRp3349\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x8ei@'\np3350\ntp3351\nRp3352\nF164.0\ntp3353\na(I6910000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3i@'\np3354\ntp3355\nRp3356\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3i@'\np3357\ntp3358\nRp3359\nF251.0\ntp3360\na(I6920000\ng1\n(g5\nS'=\\n\\xd7\\xa3p-j@'\np3361\ntp3362\nRp3363\ng1\n(g5\nS'=\\n\\xd7\\xa3p-j@'\np3364\ntp3365\nRp3366\nF270.0\ntp3367\na(I6930000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14~j@'\np3368\ntp3369\nRp3370\ng1\n(g5\nS'\\xaeG\\xe1z\\x14~j@'\np3371\ntp3372\nRp3373\nF155.0\ntp3374\na(I6940000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x92j@'\np3375\ntp3376\nRp3377\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x92j@'\np3378\ntp3379\nRp3380\nF175.0\ntp3381\na(I6950000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xe2j@'\np3382\ntp3383\nRp3384\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xe2j@'\np3385\ntp3386\nRp3387\nF368.0\ntp3388\na(I6960000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x18k@'\np3389\ntp3390\nRp3391\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x18k@'\np3392\ntp3393\nRp3394\nF159.0\ntp3395\na(I6970000\ng1\n(g5\nS'fffff\\x0ek@'\np3396\ntp3397\nRp3398\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85#k@'\np3399\ntp3400\nRp3401\nF177.0\ntp3402\na(I6980000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xffj@'\np3403\ntp3404\nRp3405\ng3401\nF134.0\ntp3406\na(I6990000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xc9j@'\np3407\ntp3408\nRp3409\ng3401\nF114.0\ntp3410\na(I7000000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xcbj@'\np3411\ntp3412\nRp3413\ng3401\nF160.0\ntp3414\na(I7010000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8k@'\np3415\ntp3416\nRp3417\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8k@'\np3418\ntp3419\nRp3420\nF477.0\ntp3421\na(I7020000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Ik@'\np3422\ntp3423\nRp3424\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x82k@'\np3425\ntp3426\nRp3427\nF168.0\ntp3428\na(I7030000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:k@'\np3429\ntp3430\nRp3431\ng3427\nF188.0\ntp3432\na(I7040000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xa7k@'\np3433\ntp3434\nRp3435\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xa7k@'\np3436\ntp3437\nRp3438\nF330.0\ntp3439\na(I7050000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xe2k@'\np3440\ntp3441\nRp3442\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xe2k@'\np3443\ntp3444\nRp3445\nF353.0\ntp3446\na(I7060000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x92l@'\np3447\ntp3448\nRp3449\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x92l@'\np3450\ntp3451\nRp3452\nF424.0\ntp3453\na(I7070000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x02m@'\np3454\ntp3455\nRp3456\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x02m@'\np3457\ntp3458\nRp3459\nF376.0\ntp3460\na(I7080000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fbm@'\np3461\ntp3462\nRp3463\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fbm@'\np3464\ntp3465\nRp3466\nF180.0\ntp3467\na(I7090000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(|m@'\np3468\ntp3469\nRp3470\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x91m@'\np3471\ntp3472\nRp3473\nF191.0\ntp3474\na(I7100000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xc1m@'\np3475\ntp3476\nRp3477\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xc1m@'\np3478\ntp3479\nRp3480\nF381.0\ntp3481\na(I7110000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x11n@'\np3482\ntp3483\nRp3484\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x11n@'\np3485\ntp3486\nRp3487\nF358.0\ntp3488\na(I7120000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99yn@'\np3489\ntp3490\nRp3491\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99yn@'\np3492\ntp3493\nRp3494\nF450.0\ntp3495\na(I7130000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\\\n@'\np3496\ntp3497\nRp3498\ng3494\nF360.0\ntp3499\na(I7140000\ng1\n(g5\nS'\\x14\\xaeG\\xe1ztn@'\np3500\ntp3501\nRp3502\ng1\n(g5\nS'\\n\\xd7\\xa3p=zn@'\np3503\ntp3504\nRp3505\nF169.0\ntp3506\na(I7150000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8nn@'\np3507\ntp3508\nRp3509\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8cn@'\np3510\ntp3511\nRp3512\nF184.0\ntp3513\na(I7160000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x9dn@'\np3514\ntp3515\nRp3516\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x9dn@'\np3517\ntp3518\nRp3519\nF318.0\ntp3520\na(I7170000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xacn@'\np3521\ntp3522\nRp3523\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xacn@'\np3524\ntp3525\nRp3526\nF193.0\ntp3527\na(I7180000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xfen@'\np3528\ntp3529\nRp3530\ng1\n(g5\nS'33333\\x03o@'\np3531\ntp3532\nRp3533\nF158.0\ntp3534\na(I7190000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99)o@'\np3535\ntp3536\nRp3537\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99)o@'\np3538\ntp3539\nRp3540\nF175.0\ntp3541\na(I7200000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00xo@'\np3542\ntp3543\nRp3544\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00xo@'\np3545\ntp3546\nRp3547\nF465.0\ntp3548\na(I7210000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x8co@'\np3549\ntp3550\nRp3551\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x8do@'\np3552\ntp3553\nRp3554\nF179.0\ntp3555\na(I7220000\ng1\n(g5\nS'33333\\xb3o@'\np3556\ntp3557\nRp3558\ng1\n(g5\nS'33333\\xb3o@'\np3559\ntp3560\nRp3561\nF388.0\ntp3562\na(I7230000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xd7o@'\np3563\ntp3564\nRp3565\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xd7o@'\np3566\ntp3567\nRp3568\nF292.0\ntp3569\na(I7240000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc0p@'\np3570\ntp3571\nRp3572\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc0p@'\np3573\ntp3574\nRp3575\nF287.0\ntp3576\na(I7250000\ng1\n(g5\nS'=\\n\\xd7\\xa3pqp@'\np3577\ntp3578\nRp3579\ng1\n(g5\nS'=\\n\\xd7\\xa3pqp@'\np3580\ntp3581\nRp3582\nF428.0\ntp3583\na(I7260000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x9dp@'\np3584\ntp3585\nRp3586\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x9dp@'\np3587\ntp3588\nRp3589\nF387.0\ntp3590\na(I7270000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xecp@'\np3591\ntp3592\nRp3593\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xecp@'\np3594\ntp3595\nRp3596\nF383.0\ntp3597\na(I7280000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xf3p@'\np3598\ntp3599\nRp3600\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xf3p@'\np3601\ntp3602\nRp3603\nF186.0\ntp3604\na(I7290000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf8p@'\np3605\ntp3606\nRp3607\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf8p@'\np3608\ntp3609\nRp3610\nF437.0\ntp3611\na(I7300000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x1bq@'\np3612\ntp3613\nRp3614\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x1bq@'\np3615\ntp3616\nRp3617\nF356.0\ntp3618\na(I7310000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x1dq@'\np3619\ntp3620\nRp3621\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x1dq@'\np3622\ntp3623\nRp3624\nF457.0\ntp3625\na(I7320000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ<q@'\np3626\ntp3627\nRp3628\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ<q@'\np3629\ntp3630\nRp3631\nF375.0\ntp3632\na(I7330000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8q@'\np3633\ntp3634\nRp3635\ng3631\nF139.0\ntp3636\na(I7340000\ng1\n(g5\nS'=\\n\\xd7\\xa3pmq@'\np3637\ntp3638\nRp3639\ng1\n(g5\nS'=\\n\\xd7\\xa3pmq@'\np3640\ntp3641\nRp3642\nF377.0\ntp3643\na(I7350000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x96q@'\np3644\ntp3645\nRp3646\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x96q@'\np3647\ntp3648\nRp3649\nF374.0\ntp3650\na(I7360000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xb0q@'\np3651\ntp3652\nRp3653\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xb3q@'\np3654\ntp3655\nRp3656\nF151.0\ntp3657\na(I7370000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xdbq@'\np3658\ntp3659\nRp3660\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xdbq@'\np3661\ntp3662\nRp3663\nF355.0\ntp3664\na(I7380000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xc8q@'\np3665\ntp3666\nRp3667\ng3663\nF289.0\ntp3668\na(I7390000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xf0q@'\np3669\ntp3670\nRp3671\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xf0q@'\np3672\ntp3673\nRp3674\nF373.0\ntp3675\na(I7400000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xf7q@'\np3676\ntp3677\nRp3678\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xf7q@'\np3679\ntp3680\nRp3681\nF407.0\ntp3682\na(I7410000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x03r@'\np3683\ntp3684\nRp3685\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x1fr@'\np3686\ntp3687\nRp3688\nF185.0\ntp3689\na(I7420000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGIr@'\np3690\ntp3691\nRp3692\ng1\n(g5\nS'\\xe1z\\x14\\xaeGIr@'\np3693\ntp3694\nRp3695\nF382.0\ntp3696\na(I7430000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1ear@'\np3697\ntp3698\nRp3699\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1ear@'\np3700\ntp3701\nRp3702\nF450.0\ntp3703\na(I7440000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQlr@'\np3704\ntp3705\nRp3706\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQlr@'\np3707\ntp3708\nRp3709\nF321.0\ntp3710\na(I7450000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2er@'\np3711\ntp3712\nRp3713\ng1\n(g5\nS'\\xd7\\xa3p=\\nsr@'\np3714\ntp3715\nRp3716\nF187.0\ntp3717\na(I7460000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00`r@'\np3718\ntp3719\nRp3720\ng3716\nF108.0\ntp3721\na(I7470000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xa8r@'\np3722\ntp3723\nRp3724\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xa8r@'\np3725\ntp3726\nRp3727\nF443.0\ntp3728\na(I7480000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xcfr@'\np3729\ntp3730\nRp3731\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xcfr@'\np3732\ntp3733\nRp3734\nF417.0\ntp3735\na(I7490000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xf2r@'\np3736\ntp3737\nRp3738\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xf6r@'\np3739\ntp3740\nRp3741\nF341.0\ntp3742\na(I7500000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xe6r@'\np3743\ntp3744\nRp3745\ng3741\nF185.0\ntp3746\na(I7510000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x1cs@'\np3747\ntp3748\nRp3749\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x1cs@'\np3750\ntp3751\nRp3752\nF199.0\ntp3753\na(I7520000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zps@'\np3754\ntp3755\nRp3756\ng1\n(g5\nS'\\x14\\xaeG\\xe1zps@'\np3757\ntp3758\nRp3759\nF447.0\ntp3760\na(I7530000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x94s@'\np3761\ntp3762\nRp3763\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x94s@'\np3764\ntp3765\nRp3766\nF362.0\ntp3767\na(I7540000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8s@'\np3768\ntp3769\nRp3770\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8s@'\np3771\ntp3772\nRp3773\nF195.0\ntp3774\na(I7550000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xc8s@'\np3775\ntp3776\nRp3777\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xe1s@'\np3778\ntp3779\nRp3780\nF194.0\ntp3781\na(I7560000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xd4s@'\np3782\ntp3783\nRp3784\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xecs@'\np3785\ntp3786\nRp3787\nF323.0\ntp3788\na(I7570000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xd3s@'\np3789\ntp3790\nRp3791\ng3787\nF146.0\ntp3792\na(I7580000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\tt@'\np3793\ntp3794\nRp3795\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\tt@'\np3796\ntp3797\nRp3798\nF432.0\ntp3799\na(I7590000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xecs@'\np3800\ntp3801\nRp3802\ng1\n(g5\nS'33333\\x0bt@'\np3803\ntp3804\nRp3805\nF148.0\ntp3806\na(I7600000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x9cs@'\np3807\ntp3808\nRp3809\ng3805\nF169.0\ntp3810\na(I7610000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14zs@'\np3811\ntp3812\nRp3813\ng3805\nF185.0\ntp3814\na(I7620000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x81s@'\np3815\ntp3816\nRp3817\ng3805\nF392.0\ntp3818\na(I7630000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xa4s@'\np3819\ntp3820\nRp3821\ng3805\nF414.0\ntp3822\na(I7640000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xd8s@'\np3823\ntp3824\nRp3825\ng3805\nF483.0\ntp3826\na(I7650000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x05t@'\np3827\ntp3828\nRp3829\ng3805\nF474.0\ntp3830\na(I7660000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f2t@'\np3831\ntp3832\nRp3833\ng1\n(g5\nS'=\\n\\xd7\\xa3pUt@'\np3834\ntp3835\nRp3836\nF163.0\ntp3837\na(I7670000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Et@'\np3838\ntp3839\nRp3840\ng3836\nF438.0\ntp3841\na(I7680000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xe4s@'\np3842\ntp3843\nRp3844\ng3836\nF183.0\ntp3845\na(I7690000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xdbs@'\np3846\ntp3847\nRp3848\ng3836\nF391.0\ntp3849\na(I7700000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xf2s@'\np3850\ntp3851\nRp3852\ng3836\nF188.0\ntp3853\na(I7710000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x00t@'\np3854\ntp3855\nRp3856\ng3836\nF195.0\ntp3857\na(I7720000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x03t@'\np3858\ntp3859\nRp3860\ng3836\nF380.0\ntp3861\na(I7730000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x04t@'\np3862\ntp3863\nRp3864\ng3836\nF176.0\ntp3865\na(I7740000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xfcs@'\np3866\ntp3867\nRp3868\ng3836\nF368.0\ntp3869\na(I7750000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2-t@'\np3870\ntp3871\nRp3872\ng3836\nF397.0\ntp3873\na(I7760000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f&t@'\np3874\ntp3875\nRp3876\ng3836\nF420.0\ntp3877\na(I7770000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f>t@'\np3878\ntp3879\nRp3880\ng3836\nF385.0\ntp3881\na(I7780000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99At@'\np3882\ntp3883\nRp3884\ng3836\nF185.0\ntp3885\na(I7790000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x81t@'\np3886\ntp3887\nRp3888\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x81t@'\np3889\ntp3890\nRp3891\nF396.0\ntp3892\na(I7800000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5Lt@'\np3893\ntp3894\nRp3895\ng3891\nF161.0\ntp3896\na(I7810000\ng1\n(g5\nS'=\\n\\xd7\\xa3pMt@'\np3897\ntp3898\nRp3899\ng3891\nF431.0\ntp3900\na(I7820000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQPt@'\np3901\ntp3902\nRp3903\ng3891\nF411.0\ntp3904\na(I7830000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\\\t@'\np3905\ntp3906\nRp3907\ng3891\nF456.0\ntp3908\na(I7840000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fJt@'\np3909\ntp3910\nRp3911\ng3891\nF170.0\ntp3912\na(I7850000\ng1\n(g5\nS'\\xa4p=\\n\\xd7Gt@'\np3913\ntp3914\nRp3915\ng3891\nF325.0\ntp3916\na(I7860000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xe7s@'\np3917\ntp3918\nRp3919\ng3891\nF153.0\ntp3920\na(I7870000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xb6s@'\np3921\ntp3922\nRp3923\ng3891\nF128.0\ntp3924\na(I7880000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xb1s@'\np3925\ntp3926\nRp3927\ng3891\nF359.0\ntp3928\na(I7890000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x97s@'\np3929\ntp3930\nRp3931\ng3891\nF189.0\ntp3932\na(I7900000\ng1\n(g5\nS'33333\\xc7s@'\np3933\ntp3934\nRp3935\ng3891\nF424.0\ntp3936\na(I7910000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebqs@'\np3937\ntp3938\nRp3939\ng3891\nF193.0\ntp3940\na(I7920000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\x82s@'\np3941\ntp3942\nRp3943\ng3891\nF495.0\ntp3944\na(I7930000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xabs@'\np3945\ntp3946\nRp3947\ng3891\nF627.0\ntp3948\na(I7940000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb1s@'\np3949\ntp3950\nRp3951\ng3891\nF413.0\ntp3952\na(I7950000\ng1\n(g5\nS'33333\\xabs@'\np3953\ntp3954\nRp3955\ng3891\nF348.0\ntp3956\na(I7960000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00|s@'\np3957\ntp3958\nRp3959\ng3891\nF111.0\ntp3960\na(I7970000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x8cs@'\np3961\ntp3962\nRp3963\ng3891\nF403.0\ntp3964\na(I7980000\ng1\n(g5\nS'\\xa4p=\\n\\xd7{s@'\np3965\ntp3966\nRp3967\ng3891\nF351.0\ntp3968\na(I7990000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xa9s@'\np3969\ntp3970\nRp3971\ng3891\nF461.0\ntp3972\na(I8000000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xd3s@'\np3973\ntp3974\nRp3975\ng3891\nF370.0\ntp3976\na(I8010000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xccs@'\np3977\ntp3978\nRp3979\ng3891\nF401.0\ntp3980\na(I8020000\ng1\n(g5\nS'fffff\\xces@'\np3981\ntp3982\nRp3983\ng3891\nF430.0\ntp3984\na(I8030000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xd1s@'\np3985\ntp3986\nRp3987\ng3891\nF341.0\ntp3988\na(I8040000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xf6s@'\np3989\ntp3990\nRp3991\ng3891\nF408.0\ntp3992\na(I8050000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x14t@'\np3993\ntp3994\nRp3995\ng3891\nF436.0\ntp3996\na(I8060000\ng1\n(g5\nS'\\xd7\\xa3p=\\n_t@'\np3997\ntp3998\nRp3999\ng3891\nF667.0\ntp4000\na(I8070000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb]t@'\np4001\ntp4002\nRp4003\ng3891\nF387.0\ntp4004\na(I8080000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00lt@'\np4005\ntp4006\nRp4007\ng3891\nF407.0\ntp4008\na(I8090000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(Lt@'\np4009\ntp4010\nRp4011\ng3891\nF192.0\ntp4012\na(I8100000\ng1\n(g5\nS'fffff\\x96t@'\np4013\ntp4014\nRp4015\ng1\n(g5\nS'fffff\\x96t@'\np4016\ntp4017\nRp4018\nF481.0\ntp4019\na(I8110000\ng1\n(g5\nS'fffff\\xc6t@'\np4020\ntp4021\nRp4022\ng1\n(g5\nS'fffff\\xc6t@'\np4023\ntp4024\nRp4025\nF494.0\ntp4026\na(I8120000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xb3t@'\np4027\ntp4028\nRp4029\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xc8t@'\np4030\ntp4031\nRp4032\nF195.0\ntp4033\na(I8130000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xe4t@'\np4034\ntp4035\nRp4036\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xe4t@'\np4037\ntp4038\nRp4039\nF353.0\ntp4040\na(I8140000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xe3t@'\np4041\ntp4042\nRp4043\ng4039\nF441.0\ntp4044\na(I8150000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x0bu@'\np4045\ntp4046\nRp4047\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x0bu@'\np4048\ntp4049\nRp4050\nF449.0\ntp4051\na(I8160000\ng1\n(g5\nS'fffffJu@'\np4052\ntp4053\nRp4054\ng1\n(g5\nS'fffffJu@'\np4055\ntp4056\nRp4057\nF394.0\ntp4058\na(I8170000\ng1\n(g5\nS'q=\\n\\xd7\\xa3pu@'\np4059\ntp4060\nRp4061\ng1\n(g5\nS'q=\\n\\xd7\\xa3pu@'\np4062\ntp4063\nRp4064\nF409.0\ntp4065\na(I8180000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x80u@'\np4066\ntp4067\nRp4068\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xa4u@'\np4069\ntp4070\nRp4071\nF155.0\ntp4072\na(I8190000\ng1\n(g5\nS'\\xd7\\xa3p=\\ncu@'\np4073\ntp4074\nRp4075\ng4071\nF196.0\ntp4076\na(I8200000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\ru@'\np4077\ntp4078\nRp4079\ng4071\nF177.0\ntp4080\na(I8210000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xd2t@'\np4081\ntp4082\nRp4083\ng4071\nF383.0\ntp4084\na(I8220000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2%u@'\np4085\ntp4086\nRp4087\ng4071\nF683.0\ntp4088\na(I8230000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85Su@'\np4089\ntp4090\nRp4091\ng4071\nF721.0\ntp4092\na(I8240000\ng1\n(g5\nS'fffffbu@'\np4093\ntp4094\nRp4095\ng4071\nF410.0\ntp4096\na(I8250000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x96u@'\np4097\ntp4098\nRp4099\ng4071\nF446.0\ntp4100\na(I8260000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xf2u@'\np4101\ntp4102\nRp4103\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xf2u@'\np4104\ntp4105\nRp4106\nF453.0\ntp4107\na(I8270000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfau@'\np4108\ntp4109\nRp4110\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfau@'\np4111\ntp4112\nRp4113\nF445.0\ntp4114\na(I8280000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\3v@'\np4115\ntp4116\nRp4117\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\3v@'\np4118\ntp4119\nRp4120\nF384.0\ntp4121\na(I8290000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x000v@'\np4122\ntp4123\nRp4124\ng4120\nF374.0\ntp4125\na(I8300000\ng1\n(g5\nS'H\\xe1z\\x14\\xaecv@'\np4126\ntp4127\nRp4128\ng1\n(g5\nS'H\\xe1z\\x14\\xaecv@'\np4129\ntp4130\nRp4131\nF490.0\ntp4132\na(I8310000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5dv@'\np4133\ntp4134\nRp4135\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5dv@'\np4136\ntp4137\nRp4138\nF194.0\ntp4139\na(I8320000\ng1\n(g5\nS'fffffJv@'\np4140\ntp4141\nRp4142\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\ov@'\np4143\ntp4144\nRp4145\nF137.0\ntp4146\na(I8330000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x18v@'\np4147\ntp4148\nRp4149\ng4145\nF377.0\ntp4150\na(I8340000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xcdu@'\np4151\ntp4152\nRp4153\ng4145\nF197.0\ntp4154\na(I8350000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xd0u@'\np4155\ntp4156\nRp4157\ng4145\nF166.0\ntp4158\na(I8360000\ng1\n(g5\nS'33333\\x83u@'\np4159\ntp4160\nRp4161\ng4145\nF161.0\ntp4162\na(I8370000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xc1u@'\np4163\ntp4164\nRp4165\ng4145\nF377.0\ntp4166\na(I8380000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xe8u@'\np4167\ntp4168\nRp4169\ng4145\nF401.0\ntp4170\na(I8390000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa4u@'\np4171\ntp4172\nRp4173\ng4145\nF197.0\ntp4174\na(I8400000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xaau@'\np4175\ntp4176\nRp4177\ng4145\nF443.0\ntp4178\na(I8410000\ng1\n(g5\nS'33333\\xcfu@'\np4179\ntp4180\nRp4181\ng4145\nF490.0\ntp4182\na(I8420000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xf0u@'\np4183\ntp4184\nRp4185\ng4145\nF404.0\ntp4186\na(I8430000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x000v@'\np4187\ntp4188\nRp4189\ng4145\nF164.0\ntp4190\na(I8440000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGiv@'\np4191\ntp4192\nRp4193\ng4145\nF683.0\ntp4194\na(I8450000\ng1\n(g5\nS'fffff\\xa6v@'\np4195\ntp4196\nRp4197\ng1\n(g5\nS'fffff\\xa6v@'\np4198\ntp4199\nRp4200\nF164.0\ntp4201\na(I8460000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xa0v@'\np4202\ntp4203\nRp4204\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xaav@'\np4205\ntp4206\nRp4207\nF186.0\ntp4208\na(I8470000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xc3v@'\np4209\ntp4210\nRp4211\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xc3v@'\np4212\ntp4213\nRp4214\nF348.0\ntp4215\na(I8480000\ng1\n(g5\nS'33333\\xcfv@'\np4216\ntp4217\nRp4218\ng1\n(g5\nS'33333\\xcfv@'\np4219\ntp4220\nRp4221\nF406.0\ntp4222\na(I8490000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xefv@'\np4223\ntp4224\nRp4225\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xefv@'\np4226\ntp4227\nRp4228\nF390.0\ntp4229\na(I8500000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x17w@'\np4230\ntp4231\nRp4232\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x17w@'\np4233\ntp4234\nRp4235\nF650.0\ntp4236\na(I8510000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00<w@'\np4237\ntp4238\nRp4239\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00<w@'\np4240\ntp4241\nRp4242\nF349.0\ntp4243\na(I8520000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQdw@'\np4244\ntp4245\nRp4246\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQdw@'\np4247\ntp4248\nRp4249\nF446.0\ntp4250\na(I8530000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e}w@'\np4251\ntp4252\nRp4253\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\x91w@'\np4254\ntp4255\nRp4256\nF368.0\ntp4257\na(I8540000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG9w@'\np4258\ntp4259\nRp4260\ng4256\nF469.0\ntp4261\na(I8550000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(Dw@'\np4262\ntp4263\nRp4264\ng4256\nF470.0\ntp4265\na(I8560000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85Ow@'\np4266\ntp4267\nRp4268\ng4256\nF419.0\ntp4269\na(I8570000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xbaw@'\np4270\ntp4271\nRp4272\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xbaw@'\np4273\ntp4274\nRp4275\nF438.0\ntp4276\na(I8580000\ng1\n(g5\nS'fffff~w@'\np4277\ntp4278\nRp4279\ng4275\nF158.0\ntp4280\na(I8590000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\x8fw@'\np4281\ntp4282\nRp4283\ng4275\nF458.0\ntp4284\na(I8600000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xc9w@'\np4285\ntp4286\nRp4287\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xc9w@'\np4288\ntp4289\nRp4290\nF786.0\ntp4291\na(I8610000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xa8w@'\np4292\ntp4293\nRp4294\ng4290\nF197.0\ntp4295\na(I8620000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xb1w@'\np4296\ntp4297\nRp4298\ng4290\nF367.0\ntp4299\na(I8630000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xdcw@'\np4300\ntp4301\nRp4302\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xdcw@'\np4303\ntp4304\nRp4305\nF697.0\ntp4306\na(I8640000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1w@'\np4307\ntp4308\nRp4309\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1w@'\np4310\ntp4311\nRp4312\nF470.0\ntp4313\na(I8650000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf8w@'\np4314\ntp4315\nRp4316\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\x1cx@'\np4317\ntp4318\nRp4319\nF183.0\ntp4320\na(I8660000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xcfw@'\np4321\ntp4322\nRp4323\ng4319\nF192.0\ntp4324\na(I8670000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xc3w@'\np4325\ntp4326\nRp4327\ng4319\nF591.0\ntp4328\na(I8680000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xbew@'\np4329\ntp4330\nRp4331\ng4319\nF411.0\ntp4332\na(I8690000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xc4w@'\np4333\ntp4334\nRp4335\ng4319\nF444.0\ntp4336\na(I8700000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcbw@'\np4337\ntp4338\nRp4339\ng4319\nF413.0\ntp4340\na(I8710000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x87w@'\np4341\ntp4342\nRp4343\ng4319\nF185.0\ntp4344\na(I8720000\ng1\n(g5\nS'33333/w@'\np4345\ntp4346\nRp4347\ng4319\nF146.0\ntp4348\na(I8730000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85Cw@'\np4349\ntp4350\nRp4351\ng4319\nF475.0\ntp4352\na(I8740000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x1fw@'\np4353\ntp4354\nRp4355\ng4319\nF479.0\ntp4356\na(I8750000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x1ew@'\np4357\ntp4358\nRp4359\ng4319\nF434.0\ntp4360\na(I8760000\ng1\n(g5\nS'33333\\xcbv@'\np4361\ntp4362\nRp4363\ng4319\nF186.0\ntp4364\na(I8770000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xf0v@'\np4365\ntp4366\nRp4367\ng4319\nF435.0\ntp4368\na(I8780000\ng1\n(g5\nS'H\\xe1z\\x14\\xae/w@'\np4369\ntp4370\nRp4371\ng4319\nF471.0\ntp4372\na(I8790000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x80w@'\np4373\ntp4374\nRp4375\ng4319\nF699.0\ntp4376\na(I8800000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xa2w@'\np4377\ntp4378\nRp4379\ng4319\nF404.0\ntp4380\na(I8810000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xcbw@'\np4381\ntp4382\nRp4383\ng4319\nF373.0\ntp4384\na(I8820000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xd0w@'\np4385\ntp4386\nRp4387\ng4319\nF409.0\ntp4388\na(I8830000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xd6w@'\np4389\ntp4390\nRp4391\ng4319\nF726.0\ntp4392\na(I8840000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xd7w@'\np4393\ntp4394\nRp4395\ng4319\nF477.0\ntp4396\na(I8850000\ng1\n(g5\nS'33333\\xe3w@'\np4397\ntp4398\nRp4399\ng4319\nF482.0\ntp4400\na(I8860000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xb5w@'\np4401\ntp4402\nRp4403\ng4319\nF162.0\ntp4404\na(I8870000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x91w@'\np4405\ntp4406\nRp4407\ng4319\nF192.0\ntp4408\na(I8880000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xb0w@'\np4409\ntp4410\nRp4411\ng4319\nF653.0\ntp4412\na(I8890000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xcbw@'\np4413\ntp4414\nRp4415\ng4319\nF495.0\ntp4416\na(I8900000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9aw@'\np4417\ntp4418\nRp4419\ng4319\nF187.0\ntp4420\na(I8910000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa9w@'\np4421\ntp4422\nRp4423\ng4319\nF480.0\ntp4424\na(I8920000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xe8w@'\np4425\ntp4426\nRp4427\ng4319\nF408.0\ntp4428\na(I8930000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2!x@'\np4429\ntp4430\nRp4431\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2!x@'\np4432\ntp4433\nRp4434\nF479.0\ntp4435\na(I8940000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb1x@'\np4436\ntp4437\nRp4438\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb1x@'\np4439\ntp4440\nRp4441\nF195.0\ntp4442\na(I8950000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2Yx@'\np4443\ntp4444\nRp4445\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2Yx@'\np4446\ntp4447\nRp4448\nF446.0\ntp4449\na(I8960000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x91x@'\np4450\ntp4451\nRp4452\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\x91x@'\np4453\ntp4454\nRp4455\nF479.0\ntp4456\na(I8970000\ng1\n(g5\nS'33333\\x8bx@'\np4457\ntp4458\nRp4459\ng4455\nF397.0\ntp4460\na(I8980000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xc5x@'\np4461\ntp4462\nRp4463\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xc5x@'\np4464\ntp4465\nRp4466\nF490.0\ntp4467\na(I8990000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb5x@'\np4468\ntp4469\nRp4470\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xd7x@'\np4471\ntp4472\nRp4473\nF191.0\ntp4474\na(I9000000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xd4x@'\np4475\ntp4476\nRp4477\ng4473\nF435.0\ntp4478\na(I9010000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xf7x@'\np4479\ntp4480\nRp4481\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xf7x@'\np4482\ntp4483\nRp4484\nF446.0\ntp4485\na(I9020000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xd8x@'\np4486\ntp4487\nRp4488\ng4484\nF499.0\ntp4489\na(I9030000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xd2x@'\np4490\ntp4491\nRp4492\ng4484\nF424.0\ntp4493\na(I9040000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xe4x@'\np4494\ntp4495\nRp4496\ng4484\nF709.0\ntp4497\na(I9050000\ng1\n(g5\nS'fffff\\xc6x@'\np4498\ntp4499\nRp4500\ng1\n(g5\nS'fffff\\x16y@'\np4501\ntp4502\nRp4503\nF183.0\ntp4504\na(I9060000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xcax@'\np4505\ntp4506\nRp4507\ng4503\nF466.0\ntp4508\na(I9070000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z$y@'\np4509\ntp4510\nRp4511\ng1\n(g5\nS'\\x14\\xaeG\\xe1z$y@'\np4512\ntp4513\nRp4514\nF417.0\ntp4515\na(I9080000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5Ty@'\np4516\ntp4517\nRp4518\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5Ty@'\np4519\ntp4520\nRp4521\nF440.0\ntp4522\na(I9090000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x9dy@'\np4523\ntp4524\nRp4525\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x9dy@'\np4526\ntp4527\nRp4528\nF640.0\ntp4529\na(I9100000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xa0y@'\np4530\ntp4531\nRp4532\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xa8y@'\np4533\ntp4534\nRp4535\nF374.0\ntp4536\na(I9110000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xacy@'\np4537\ntp4538\nRp4539\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xacy@'\np4540\ntp4541\nRp4542\nF484.0\ntp4543\na(I9120000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x89y@'\np4544\ntp4545\nRp4546\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd3y@'\np4547\ntp4548\nRp4549\nF193.0\ntp4550\na(I9130000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x82y@'\np4551\ntp4552\nRp4553\ng4549\nF397.0\ntp4554\na(I9140000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebay@'\np4555\ntp4556\nRp4557\ng4549\nF189.0\ntp4558\na(I9150000\ng1\n(g5\nS'=\\n\\xd7\\xa3puy@'\np4559\ntp4560\nRp4561\ng4549\nF482.0\ntp4562\na(I9160000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8y@'\np4563\ntp4564\nRp4565\ng4549\nF610.0\ntp4566\na(I9170000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xbay@'\np4567\ntp4568\nRp4569\ng4549\nF189.0\ntp4570\na(I9180000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xafy@'\np4571\ntp4572\nRp4573\ng4549\nF403.0\ntp4574\na(I9190000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xb1y@'\np4575\ntp4576\nRp4577\ng4549\nF473.0\ntp4578\na(I9200000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xbay@'\np4579\ntp4580\nRp4581\ng4549\nF496.0\ntp4582\na(I9210000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xcfy@'\np4583\ntp4584\nRp4585\ng4549\nF188.0\ntp4586\na(I9220000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa1y@'\np4587\ntp4588\nRp4589\ng4549\nF478.0\ntp4590\na(I9230000\ng1\n(g5\nS'33333\\xb7y@'\np4591\ntp4592\nRp4593\ng4549\nF563.0\ntp4594\na(I9240000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xacy@'\np4595\ntp4596\nRp4597\ng4549\nF416.0\ntp4598\na(I9250000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x11y@'\np4599\ntp4600\nRp4601\ng4549\nF187.0\ntp4602\na(I9260000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xecx@'\np4603\ntp4604\nRp4605\ng4549\nF479.0\ntp4606\na(I9270000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f6y@'\np4607\ntp4608\nRp4609\ng4549\nF646.0\ntp4610\na(I9280000\ng1\n(g5\nS'33333Cy@'\np4611\ntp4612\nRp4613\ng4549\nF193.0\ntp4614\na(I9290000\ng1\n(g5\nS'\\xa4p=\\n\\xd7+y@'\np4615\ntp4616\nRp4617\ng4549\nF493.0\ntp4618\na(I9300000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x0cy@'\np4619\ntp4620\nRp4621\ng4549\nF486.0\ntp4622\na(I9310000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\ty@'\np4623\ntp4624\nRp4625\ng4549\nF449.0\ntp4626\na(I9320000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x1cy@'\np4627\ntp4628\nRp4629\ng4549\nF478.0\ntp4630\na(I9330000\ng1\n(g5\nS'\\xd7\\xa3p=\\n?y@'\np4631\ntp4632\nRp4633\ng4549\nF402.0\ntp4634\na(I9340000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x94y@'\np4635\ntp4636\nRp4637\ng4549\nF461.0\ntp4638\na(I9350000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xc2y@'\np4639\ntp4640\nRp4641\ng4549\nF429.0\ntp4642\na(I9360000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xf0y@'\np4643\ntp4644\nRp4645\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xf0y@'\np4646\ntp4647\nRp4648\nF472.0\ntp4649\na(I9370000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Ez@'\np4650\ntp4651\nRp4652\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Ez@'\np4653\ntp4654\nRp4655\nF464.0\ntp4656\na(I9380000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2Az@'\np4657\ntp4658\nRp4659\ng4655\nF455.0\ntp4660\na(I9390000\ng1\n(g5\nS'33333kz@'\np4661\ntp4662\nRp4663\ng1\n(g5\nS'33333kz@'\np4664\ntp4665\nRp4666\nF693.0\ntp4667\na(I9400000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x96z@'\np4668\ntp4669\nRp4670\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\x96z@'\np4671\ntp4672\nRp4673\nF671.0\ntp4674\na(I9410000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xdfz@'\np4675\ntp4676\nRp4677\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xdfz@'\np4678\ntp4679\nRp4680\nF407.0\ntp4681\na(I9420000\ng1\n(g5\nS'fffff\\xe6z@'\np4682\ntp4683\nRp4684\ng1\n(g5\nS'fffff\\xe6z@'\np4685\ntp4686\nRp4687\nF476.0\ntp4688\na(I9430000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xdcz@'\np4689\ntp4690\nRp4691\ng4687\nF420.0\ntp4692\na(I9440000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xb3z@'\np4693\ntp4694\nRp4695\ng4687\nF443.0\ntp4696\na(I9450000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe5z@'\np4697\ntp4698\nRp4699\ng4687\nF716.0\ntp4700\na(I9460000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xf9z@'\np4701\ntp4702\nRp4703\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x16{@'\np4704\ntp4705\nRp4706\nF191.0\ntp4707\na(I9470000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x04{@'\np4708\ntp4709\nRp4710\ng4706\nF482.0\ntp4711\na(I9480000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xd7z@'\np4712\ntp4713\nRp4714\ng4706\nF450.0\ntp4715\na(I9490000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x8dz@'\np4716\ntp4717\nRp4718\ng4706\nF174.0\ntp4719\na(I9500000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\x91z@'\np4720\ntp4721\nRp4722\ng4706\nF492.0\ntp4723\na(I9510000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xeaz@'\np4724\ntp4725\nRp4726\ng4706\nF714.0\ntp4727\na(I9520000\ng1\n(g5\nS'fffff\\x0e{@'\np4728\ntp4729\nRp4730\ng4706\nF491.0\ntp4731\na(I9530000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xb1z@'\np4732\ntp4733\nRp4734\ng4706\nF60.0\ntp4735\na(I9540000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xaaz@'\np4736\ntp4737\nRp4738\ng4706\nF451.0\ntp4739\na(I9550000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xacz@'\np4740\ntp4741\nRp4742\ng4706\nF415.0\ntp4743\na(I9560000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xc6z@'\np4744\ntp4745\nRp4746\ng4706\nF191.0\ntp4747\na(I9570000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xcez@'\np4748\ntp4749\nRp4750\ng4706\nF427.0\ntp4751\na(I9580000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xccz@'\np4752\ntp4753\nRp4754\ng4706\nF466.0\ntp4755\na(I9590000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xccz@'\np4756\ntp4757\nRp4758\ng4706\nF466.0\ntp4759\na(I9600000\ng1\n(g5\nS'\\n\\xd7\\xa3p=>{@'\np4760\ntp4761\nRp4762\ng1\n(g5\nS'\\n\\xd7\\xa3p=>{@'\np4763\ntp4764\nRp4765\nF450.0\ntp4766\na(I9610000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x14{@'\np4767\ntp4768\nRp4769\ng4765\nF491.0\ntp4770\na(I9620000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xe5z@'\np4771\ntp4772\nRp4773\ng4765\nF183.0\ntp4774\na(I9630000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xf1z@'\np4775\ntp4776\nRp4777\ng4765\nF174.0\ntp4778\na(I9640000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ {@'\np4779\ntp4780\nRp4781\ng4765\nF782.0\ntp4782\na(I9650000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xcdz@'\np4783\ntp4784\nRp4785\ng4765\nF31.0\ntp4786\na(I9660000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99qz@'\np4787\ntp4788\nRp4789\ng4765\nF197.0\ntp4790\na(I9670000\ng1\n(g5\nS'=\\n\\xd7\\xa3pqz@'\np4791\ntp4792\nRp4793\ng4765\nF447.0\ntp4794\na(I9680000\ng1\n(g5\nS'fffff\\xe6y@'\np4795\ntp4796\nRp4797\ng4765\nF64.0\ntp4798\na(I9690000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2yy@'\np4799\ntp4800\nRp4801\ng4765\nF173.0\ntp4802\na(I9700000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\"y@'\np4803\ntp4804\nRp4805\ng4765\nF173.0\ntp4806\na(I9710000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xaex@'\np4807\ntp4808\nRp4809\ng4765\nF64.0\ntp4810\na(I9720000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xb2x@'\np4811\ntp4812\nRp4813\ng4765\nF428.0\ntp4814\na(I9730000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eIx@'\np4815\ntp4816\nRp4817\ng4765\nF290.0\ntp4818\na(I9740000\ng1\n(g5\nS'\\xa4p=\\n\\xd7Gx@'\np4819\ntp4820\nRp4821\ng4765\nF189.0\ntp4822\na(I9750000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1Nx@'\np4823\ntp4824\nRp4825\ng4765\nF445.0\ntp4826\na(I9760000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\x04x@'\np4827\ntp4828\nRp4829\ng4765\nF195.0\ntp4830\na(I9770000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xc1w@'\np4831\ntp4832\nRp4833\ng4765\nF190.0\ntp4834\na(I9780000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x0bx@'\np4835\ntp4836\nRp4837\ng4765\nF414.0\ntp4838\na(I9790000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x18x@'\np4839\ntp4840\nRp4841\ng4765\nF484.0\ntp4842\na(I9800000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x1cx@'\np4843\ntp4844\nRp4845\ng4765\nF454.0\ntp4846\na(I9810000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14x@'\np4847\ntp4848\nRp4849\ng4765\nF447.0\ntp4850\na(I9820000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85Gx@'\np4851\ntp4852\nRp4853\ng4765\nF489.0\ntp4854\na(I9830000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x94w@'\np4855\ntp4856\nRp4857\ng4765\nF30.0\ntp4858\na(I9840000\ng1\n(g5\nS'fffff^w@'\np4859\ntp4860\nRp4861\ng4765\nF192.0\ntp4862\na(I9850000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x80w@'\np4863\ntp4864\nRp4865\ng4765\nF396.0\ntp4866\na(I9860000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\+w@'\np4867\ntp4868\nRp4869\ng4765\nF157.0\ntp4870\na(I9870000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\"w@'\np4871\ntp4872\nRp4873\ng4765\nF188.0\ntp4874\na(I9880000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xcev@'\np4875\ntp4876\nRp4877\ng4765\nF160.0\ntp4878\na(I9890000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xffv@'\np4879\ntp4880\nRp4881\ng4765\nF793.0\ntp4882\na(I9900000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc(w@'\np4883\ntp4884\nRp4885\ng4765\nF708.0\ntp4886\na(I9910000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\x04w@'\np4887\ntp4888\nRp4889\ng4765\nF187.0\ntp4890\na(I9920000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ4w@'\np4891\ntp4892\nRp4893\ng4765\nF492.0\ntp4894\na(I9930000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x004w@'\np4895\ntp4896\nRp4897\ng4765\nF448.0\ntp4898\na(I9940000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eYw@'\np4899\ntp4900\nRp4901\ng4765\nF693.0\ntp4902\na(I9950000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e]w@'\np4903\ntp4904\nRp4905\ng4765\nF496.0\ntp4906\na(I9960000\ng1\n(g5\nS'{\\x14\\xaeG\\xe16w@'\np4907\ntp4908\nRp4909\ng4765\nF489.0\ntp4910\na(I9970000\ng1\n(g5\nS'33333/w@'\np4911\ntp4912\nRp4913\ng4765\nF197.0\ntp4914\na(I9980000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xb7v@'\np4915\ntp4916\nRp4917\ng4765\nF193.0\ntp4918\na(I9985964\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xb7v@'\np4919\ntp4920\nRp4921\ng4765\nF193.0\ntp4922\na.(lp0\nF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF3.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF3.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF3.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF1.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF3.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF3.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF4.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF1.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF3.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF3.0\naF0.0\naF1.0\naF0.0\naF0.0\naF3.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF4.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF4.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF4.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF3.0\naF22.0\naF0.0\naF3.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF5.0\naF3.0\naF0.0\naF0.0\naF3.0\naF0.0\naF0.0\naF1.0\naF3.0\naF0.0\naF0.0\naF12.0\naF0.0\naF21.0\naF6.0\naF6.0\naF0.0\naF0.0\naF0.0\naF0.0\naF3.0\naF1.0\naF3.0\naF3.0\naF0.0\naF0.0\naF2.0\naF7.0\naF5.0\naF5.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF3.0\naF1.0\naF5.0\naF1.0\naF1.0\naF0.0\naF16.0\naF3.0\naF3.0\naF0.0\naF0.0\naF0.0\naF1.0\naF1.0\naF0.0\naF2.0\naF7.0\naF13.0\naF6.0\naF0.0\naF1.0\naF0.0\naF2.0\naF18.0\naF0.0\naF9.0\naF0.0\naF2.0\naF3.0\naF2.0\naF0.0\naF0.0\naF16.0\naF0.0\naF0.0\naF1.0\naF0.0\naF1.0\naF6.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF1.0\naF0.0\naF0.0\naF3.0\naF1.0\naF6.0\naF1.0\naF1.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF5.0\naF0.0\naF0.0\naF0.0\naF4.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF5.0\naF0.0\naF0.0\naF0.0\naF1.0\naF14.0\naF9.0\naF2.0\naF6.0\naF7.0\naF23.0\naF0.0\naF1.0\naF0.0\naF7.0\naF10.0\naF0.0\naF1.0\naF15.0\naF0.0\naF5.0\naF0.0\naF0.0\naF23.0\naF0.0\naF0.0\naF12.0\naF4.0\naF10.0\naF1.0\naF1.0\naF0.0\naF0.0\naF12.0\naF16.0\naF0.0\naF49.0\naF0.0\naF0.0\naF0.0\naF32.0\naF15.0\naF9.0\naF0.0\naF0.0\naF0.0\naF9.0\naF0.0\naF2.0\naF0.0\naF2.0\naF0.0\naF9.0\naF17.0\naF0.0\naF4.0\naF0.0\naF8.0\naF5.0\naF8.0\naF0.0\naF3.0\naF0.0\naF0.0\naF0.0\naF4.0\naF4.0\naF0.0\naF0.0\naF18.0\naF20.0\naF0.0\naF30.0\naF10.0\naF9.0\naF31.0\naF4.0\naF13.0\naF21.0\naF16.0\naF0.0\naF1.0\naF1.0\naF13.0\naF10.0\naF27.0\naF67.0\naF51.0\naF26.0\naF28.0\naF2.0\naF43.0\naF33.0\naF16.0\naF15.0\naF0.0\naF59.0\naF21.0\naF2.0\naF31.0\naF7.0\naF59.0\naF31.0\naF48.0\naF13.0\naF7.0\naF50.0\naF15.0\naF93.0\naF32.0\naF40.0\naF15.0\naF10.0\naF34.0\naF26.0\naF38.0\naF72.0\naF45.0\naF49.0\naF42.0\naF33.0\naF13.0\naF87.0\naF59.0\naF81.0\naF63.0\naF29.0\naF1.0\naF31.0\naF30.0\naF104.0\naF64.0\naF77.0\naF86.0\naF39.0\naF44.0\naF76.0\naF93.0\naF51.0\naF52.0\naF25.0\naF115.0\naF62.0\naF38.0\naF33.0\naF66.0\naF98.0\naF27.0\naF75.0\naF52.0\naF84.0\naF49.0\naF62.0\naF76.0\naF92.0\naF54.0\naF75.0\naF34.0\naF48.0\naF30.0\naF57.0\naF40.0\naF93.0\naF57.0\naF19.0\naF48.0\naF51.0\naF11.0\naF51.0\naF100.0\naF50.0\naF66.0\naF50.0\naF81.0\naF82.0\naF63.0\naF55.0\naF111.0\naF78.0\naF35.0\naF39.0\naF80.0\naF111.0\naF74.0\naF62.0\naF53.0\naF106.0\naF74.0\naF118.0\naF80.0\naF97.0\naF42.0\naF68.0\naF73.0\naF102.0\naF47.0\naF120.0\naF54.0\naF48.0\naF76.0\naF110.0\naF108.0\naF109.0\naF48.0\naF103.0\naF91.0\naF8.0\naF58.0\naF89.0\naF92.0\naF90.0\naF95.0\naF92.0\naF93.0\naF63.0\naF15.0\naF92.0\naF60.0\naF3.0\naF2.0\naF50.0\naF7.0\naF102.0\naF44.0\naF104.0\naF28.0\naF55.0\naF59.0\naF29.0\naF88.0\naF111.0\naF93.0\naF14.0\naF62.0\naF83.0\naF38.0\naF119.0\naF72.0\naF74.0\naF23.0\naF132.0\naF72.0\naF60.0\naF94.0\naF55.0\naF108.0\naF111.0\naF67.0\naF68.0\naF51.0\naF63.0\naF54.0\naF91.0\naF129.0\naF133.0\naF105.0\naF99.0\naF106.0\naF81.0\naF109.0\naF94.0\naF73.0\naF102.0\naF108.0\naF50.0\naF46.0\naF114.0\naF88.0\naF102.0\naF133.0\naF115.0\naF113.0\naF95.0\naF105.0\naF110.0\naF90.0\naF111.0\naF64.0\naF102.0\naF103.0\naF117.0\naF42.0\naF104.0\naF107.0\naF111.0\naF116.0\naF102.0\naF66.0\naF41.0\naF131.0\naF142.0\naF97.0\naF111.0\naF85.0\naF94.0\naF96.0\naF100.0\naF30.0\naF105.0\naF66.0\naF116.0\naF41.0\naF68.0\naF126.0\naF99.0\naF81.0\naF8.0\naF42.0\naF109.0\naF100.0\naF119.0\naF24.0\naF98.0\naF71.0\naF54.0\naF117.0\naF84.0\naF54.0\naF90.0\naF96.0\naF79.0\naF56.0\naF129.0\naF141.0\naF28.0\naF126.0\naF116.0\naF105.0\naF121.0\naF84.0\naF132.0\naF146.0\naF34.0\naF0.0\naF82.0\naF100.0\naF32.0\naF90.0\naF82.0\naF23.0\naF114.0\naF113.0\naF23.0\naF110.0\naF95.0\naF83.0\naF85.0\naF111.0\naF92.0\naF105.0\naF114.0\naF106.0\naF102.0\naF128.0\naF106.0\naF135.0\naF105.0\naF52.0\naF116.0\naF128.0\naF140.0\naF148.0\naF46.0\naF128.0\naF145.0\naF119.0\naF116.0\naF126.0\naF147.0\naF138.0\naF137.0\naF95.0\naF75.0\naF131.0\naF98.0\naF77.0\naF119.0\naF84.0\naF189.0\naF102.0\naF137.0\naF104.0\naF159.0\naF127.0\naF109.0\naF105.0\naF64.0\naF108.0\naF116.0\naF99.0\naF49.0\naF45.0\naF38.0\naF39.0\naF55.0\naF116.0\naF129.0\naF92.0\naF124.0\naF2.0\naF89.0\naF35.0\naF158.0\naF116.0\naF36.0\naF135.0\naF129.0\naF109.0\naF103.0\naF43.0\naF123.0\naF106.0\naF126.0\naF120.0\naF82.0\naF27.0\naF122.0\naF79.0\naF105.0\naF125.0\naF107.0\naF49.0\naF149.0\naF66.0\naF72.0\naF109.0\naF93.0\naF130.0\naF128.0\naF62.0\naF130.0\naF104.0\naF88.0\naF56.0\naF23.0\naF48.0\naF149.0\naF153.0\naF143.0\naF111.0\naF119.0\naF110.0\naF129.0\naF162.0\naF51.0\naF130.0\naF161.0\naF70.0\naF160.0\naF117.0\naF59.0\naF99.0\naF93.0\naF175.0\naF96.0\naF0.0\naF1.0\naF7.0\naF38.0\naF85.0\naF104.0\naF48.0\naF156.0\naF131.0\naF106.0\naF142.0\naF102.0\naF106.0\naF179.0\naF94.0\naF134.0\naF100.0\naF99.0\naF156.0\naF9.0\naF63.0\naF171.0\naF194.0\naF173.0\naF120.0\naF146.0\naF111.0\naF149.0\naF110.0\naF113.0\naF77.0\naF120.0\naF118.0\naF124.0\naF68.0\naF119.0\naF123.0\naF177.0\naF82.0\naF34.0\naF143.0\naF166.0\naF177.0\naF126.0\naF132.0\naF123.0\naF177.0\naF174.0\naF167.0\naF115.0\naF127.0\naF113.0\naF104.0\naF129.0\naF143.0\naF158.0\naF110.0\naF135.0\naF175.0\naF172.0\naF105.0\naF136.0\naF123.0\naF143.0\naF135.0\naF175.0\naF185.0\naF126.0\naF140.0\naF152.0\naF124.0\naF109.0\naF183.0\naF127.0\naF185.0\naF115.0\naF139.0\naF175.0\naF125.0\naF167.0\naF174.0\naF154.0\naF146.0\naF139.0\naF155.0\naF117.0\naF165.0\naF192.0\naF196.0\naF166.0\naF156.0\naF272.0\naF334.0\naF137.0\naF150.0\naF351.0\naF138.0\naF153.0\naF367.0\naF122.0\naF180.0\naF179.0\naF136.0\naF196.0\naF166.0\naF118.0\naF199.0\naF28.0\naF72.0\naF153.0\naF285.0\naF136.0\naF257.0\naF174.0\naF174.0\naF109.0\naF157.0\naF364.0\naF297.0\naF313.0\naF349.0\naF187.0\naF195.0\naF83.0\naF278.0\naF171.0\naF325.0\naF184.0\naF120.0\naF174.0\naF325.0\naF134.0\naF407.0\naF195.0\naF385.0\naF183.0\naF150.0\naF282.0\naF179.0\naF200.0\naF29.0\naF84.0\naF134.0\naF109.0\naF165.0\naF162.0\naF356.0\naF134.0\naF405.0\naF362.0\naF172.0\naF142.0\naF270.0\naF341.0\naF181.0\naF343.0\naF128.0\naF317.0\naF120.0\naF116.0\naF192.0\naF170.0\naF306.0\naF197.0\naF404.0\naF167.0\naF345.0\naF367.0\naF174.0\naF359.0\naF182.0\naF150.0\naF310.0\naF164.0\naF251.0\naF414.0\naF270.0\naF397.0\naF155.0\naF196.0\naF187.0\naF175.0\naF169.0\naF368.0\naF281.0\naF159.0\naF199.0\naF145.0\naF177.0\naF141.0\naF134.0\naF282.0\naF179.0\naF114.0\naF348.0\naF160.0\naF477.0\naF385.0\naF143.0\naF168.0\naF125.0\naF188.0\naF340.0\naF330.0\naF353.0\naF443.0\naF424.0\naF376.0\naF346.0\naF180.0\naF411.0\naF156.0\naF191.0\naF185.0\naF381.0\naF358.0\naF396.0\naF450.0\naF159.0\naF360.0\naF442.0\naF169.0\naF194.0\naF160.0\naF184.0\naF318.0\naF362.0\naF193.0\naF391.0\naF158.0\naF420.0\naF175.0\naF382.0\naF465.0\naF452.0\naF179.0\naF166.0\naF388.0\naF292.0\naF374.0\naF287.0\naF194.0\naF428.0\naF387.0\naF438.0\naF383.0\naF345.0\naF186.0\naF437.0\naF369.0\naF170.0\naF356.0\naF164.0\naF457.0\naF375.0\naF307.0\naF139.0\naF392.0\naF377.0\naF374.0\naF374.0\naF151.0\naF414.0\naF355.0\naF289.0\naF389.0\naF373.0\naF407.0\naF425.0\naF185.0\naF385.0\naF382.0\naF173.0\naF450.0\naF321.0\naF456.0\naF187.0\naF408.0\naF108.0\naF392.0\naF443.0\naF417.0\naF418.0\naF341.0\naF181.0\naF185.0\naF483.0\naF199.0\naF394.0\naF447.0\naF362.0\naF391.0\naF195.0\naF465.0\naF194.0\naF387.0\naF323.0\naF377.0\naF146.0\naF199.0\naF432.0\naF199.0\naF148.0\naF289.0\naF170.0\naF169.0\naF398.0\naF185.0\naF392.0\naF395.0\naF414.0\naF483.0\naF474.0\naF682.0\naF163.0\naF435.0\naF438.0\naF61.0\naF119.0\naF183.0\naF164.0\naF391.0\naF306.0\naF188.0\naF395.0\naF195.0\naF380.0\naF390.0\naF185.0\naF176.0\naF368.0\naF470.0\naF397.0\naF420.0\naF396.0\naF385.0\naF185.0\naF684.0\naF396.0\naF185.0\naF180.0\naF161.0\naF431.0\naF432.0\naF411.0\naF456.0\naF496.0\naF193.0\naF170.0\naF197.0\naF325.0\naF78.0\naF144.0\naF153.0\naF191.0\naF198.0\naF128.0\naF359.0\naF398.0\naF189.0\naF400.0\naF424.0\naF138.0\naF194.0\naF193.0\naF495.0\naF627.0\naF458.0\naF413.0\naF181.0\naF348.0\naF149.0\naF111.0\naF472.0\naF403.0\naF351.0\naF422.0\naF461.0\naF370.0\naF387.0\naF401.0\naF430.0\naF439.0\naF341.0\naF408.0\naF420.0\naF436.0\naF667.0\naF387.0\naF490.0\naF407.0\naF192.0\naF643.0\naF481.0\naF494.0\naF399.0\naF195.0\naF476.0\naF353.0\naF179.0\naF441.0\naF449.0\naF439.0\naF394.0\naF409.0\naF495.0\naF199.0\naF155.0\naF409.0\naF196.0\naF187.0\naF177.0\naF403.0\naF383.0\naF683.0\naF721.0\naF182.0\naF410.0\naF446.0\naF466.0\naF453.0\naF445.0\naF463.0\naF384.0\naF374.0\naF408.0\naF490.0\naF389.0\naF194.0\naF241.0\naF137.0\naF178.0\naF377.0\naF150.0\naF197.0\naF424.0\naF166.0\naF435.0\naF161.0\naF379.0\naF377.0\naF401.0\naF246.0\naF197.0\naF443.0\naF694.0\naF490.0\naF404.0\naF597.0\naF164.0\naF683.0\naF440.0\naF164.0\naF181.0\naF137.0\naF186.0\naF348.0\naF424.0\naF406.0\naF390.0\naF650.0\naF442.0\naF349.0\naF446.0\naF475.0\naF368.0\naF192.0\naF469.0\naF192.0\naF470.0\naF419.0\naF491.0\naF438.0\naF341.0\naF158.0\naF458.0\naF786.0\naF426.0\naF197.0\naF478.0\naF367.0\naF697.0\naF470.0\naF712.0\naF183.0\naF408.0\naF192.0\naF591.0\naF433.0\naF411.0\naF444.0\naF467.0\naF413.0\naF363.0\naF185.0\naF194.0\naF181.0\naF146.0\naF184.0\naF475.0\naF183.0\naF479.0\naF434.0\naF403.0\naF190.0\naF186.0\naF435.0\naF485.0\naF471.0\naF699.0\naF404.0\naF463.0\naF373.0\naF409.0\naF726.0\naF431.0\naF477.0\naF482.0\naF463.0\naF162.0\naF484.0\naF192.0\naF653.0\naF436.0\naF495.0\naF404.0\naF187.0\naF480.0\naF421.0\naF408.0\naF195.0\naF479.0\naF433.0\naF195.0\naF446.0\naF458.0\naF479.0\naF397.0\naF414.0\naF490.0\naF489.0\naF191.0\naF435.0\naF415.0\naF446.0\naF499.0\naF436.0\naF424.0\naF709.0\naF475.0\naF183.0\naF466.0\naF490.0\naF417.0\naF440.0\naF640.0\naF414.0\naF374.0\naF484.0\naF630.0\naF193.0\naF397.0\naF401.0\naF189.0\naF483.0\naF482.0\naF610.0\naF484.0\naF189.0\naF403.0\naF450.0\naF473.0\naF496.0\naF442.0\naF188.0\naF475.0\naF478.0\naF563.0\naF191.0\naF416.0\naF194.0\naF187.0\naF187.0\naF479.0\naF646.0\naF486.0\naF193.0\naF385.0\naF493.0\naF173.0\naF486.0\naF449.0\naF415.0\naF478.0\naF402.0\naF450.0\naF461.0\naF429.0\naF472.0\naF728.0\naF464.0\naF455.0\naF693.0\naF671.0\naF430.0\naF407.0\naF476.0\naF473.0\naF420.0\naF443.0\naF716.0\naF769.0\naF191.0\naF482.0\naF425.0\naF450.0\naF319.0\naF174.0\naF492.0\naF714.0\naF412.0\naF491.0\naF447.0\naF60.0\naF451.0\naF415.0\naF639.0\naF191.0\naF453.0\naF427.0\naF197.0\naF466.0\naF889.0\naF450.0\naF154.0\naF491.0\naF183.0\naF713.0\naF174.0\naF782.0\naF441.0\naF128.0\naF31.0\naF87.0\naF197.0\naF487.0\naF447.0\naF200.0\naF64.0\naF126.0\naF146.0\naF173.0\naF190.0\naF173.0\naF291.0\naF64.0\naF384.0\naF428.0\naF165.0\naF290.0\naF393.0\naF189.0\naF445.0\naF314.0\naF183.0\naF195.0\naF190.0\naF717.0\naF414.0\naF484.0\naF496.0\naF454.0\naF447.0\naF460.0\naF489.0\naF192.0\naF173.0\naF30.0\naF97.0\naF176.0\naF192.0\naF193.0\naF396.0\naF434.0\naF157.0\naF433.0\naF188.0\naF197.0\naF170.0\naF160.0\naF793.0\naF708.0\naF187.0\naF688.0\naF492.0\naF448.0\naF693.0\naF430.0\naF496.0\naF489.0\naF674.0\naF197.0\naF425.0\naF193.0\na."
  },
  {
    "path": "dqn/logs_pkls/Enduro_s002.pkl",
    "content": "(lp0\n(I60000\ncnumpy.core.multiarray\nscalar\np1\n(cnumpy\ndtype\np2\n(S'f8'\np3\nI0\nI1\ntp4\nRp5\n(I3\nS'<'\np6\nNNNI-1\nI-1\nI0\ntp7\nbS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np8\ntp9\nRp10\nF-inf\nF0.0\ntp11\na(I70000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np12\ntp13\nRp14\nF-inf\nF0.0\ntp15\na(I80000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np16\ntp17\nRp18\nF-inf\nF0.0\ntp19\na(I90000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np20\ntp21\nRp22\nF-inf\nF0.0\ntp23\na(I100000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np24\ntp25\nRp26\nF-inf\nF0.0\ntp27\na(I110000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np28\ntp29\nRp30\nF-inf\nF0.0\ntp31\na(I120000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np32\ntp33\nRp34\nF-inf\nF0.0\ntp35\na(I130000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np36\ntp37\nRp38\nF-inf\nF0.0\ntp39\na(I140000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np40\ntp41\nRp42\nF-inf\nF0.0\ntp43\na(I150000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np44\ntp45\nRp46\nF-inf\nF0.0\ntp47\na(I160000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np48\ntp49\nRp50\nF-inf\nF0.0\ntp51\na(I170000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np52\ntp53\nRp54\nF-inf\nF0.0\ntp55\na(I180000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np56\ntp57\nRp58\nF-inf\nF0.0\ntp59\na(I190000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np60\ntp61\nRp62\nF-inf\nF0.0\ntp63\na(I200000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np64\ntp65\nRp66\nF-inf\nF0.0\ntp67\na(I210000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np68\ntp69\nRp70\nF-inf\nF0.0\ntp71\na(I220000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np72\ntp73\nRp74\nF-inf\nF0.0\ntp75\na(I230000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np76\ntp77\nRp78\nF-inf\nF0.0\ntp79\na(I240000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np80\ntp81\nRp82\nF-inf\nF0.0\ntp83\na(I250000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np84\ntp85\nRp86\nF-inf\nF0.0\ntp87\na(I260000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np88\ntp89\nRp90\nF-inf\nF0.0\ntp91\na(I270000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np92\ntp93\nRp94\nF-inf\nF0.0\ntp95\na(I280000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np96\ntp97\nRp98\nF-inf\nF0.0\ntp99\na(I290000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np100\ntp101\nRp102\nF-inf\nF0.0\ntp103\na(I300000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np104\ntp105\nRp106\nF-inf\nF0.0\ntp107\na(I310000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np108\ntp109\nRp110\nF-inf\nF0.0\ntp111\na(I320000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np112\ntp113\nRp114\nF-inf\nF0.0\ntp115\na(I330000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np116\ntp117\nRp118\nF-inf\nF0.0\ntp119\na(I340000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np120\ntp121\nRp122\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np123\ntp124\nRp125\nF0.0\ntp126\na(I350000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np127\ntp128\nRp129\ng125\nF0.0\ntp130\na(I360000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np131\ntp132\nRp133\ng125\nF0.0\ntp134\na(I370000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np135\ntp136\nRp137\ng125\nF0.0\ntp138\na(I380000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np139\ntp140\nRp141\ng125\nF0.0\ntp142\na(I390000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np143\ntp144\nRp145\ng125\nF0.0\ntp146\na(I400000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np147\ntp148\nRp149\ng125\nF0.0\ntp150\na(I410000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np151\ntp152\nRp153\ng125\nF0.0\ntp154\na(I420000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np155\ntp156\nRp157\ng125\nF0.0\ntp158\na(I430000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np159\ntp160\nRp161\ng125\nF0.0\ntp162\na(I440000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np163\ntp164\nRp165\ng125\nF0.0\ntp166\na(I450000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np167\ntp168\nRp169\ng125\nF0.0\ntp170\na(I460000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np171\ntp172\nRp173\ng125\nF0.0\ntp174\na(I470000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np175\ntp176\nRp177\ng125\nF0.0\ntp178\na(I480000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np179\ntp180\nRp181\ng125\nF0.0\ntp182\na(I490000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np183\ntp184\nRp185\ng125\nF0.0\ntp186\na(I500000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np187\ntp188\nRp189\ng125\nF0.0\ntp190\na(I510000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np191\ntp192\nRp193\ng125\nF0.0\ntp194\na(I520000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np195\ntp196\nRp197\ng125\nF0.0\ntp198\na(I530000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np199\ntp200\nRp201\ng125\nF0.0\ntp202\na(I540000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np203\ntp204\nRp205\ng125\nF0.0\ntp206\na(I550000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np207\ntp208\nRp209\ng125\nF0.0\ntp210\na(I560000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np211\ntp212\nRp213\ng125\nF0.0\ntp214\na(I570000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np215\ntp216\nRp217\ng125\nF0.0\ntp218\na(I580000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np219\ntp220\nRp221\ng125\nF0.0\ntp222\na(I590000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np223\ntp224\nRp225\ng125\nF0.0\ntp226\na(I600000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np227\ntp228\nRp229\ng125\nF0.0\ntp230\na(I610000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np231\ntp232\nRp233\ng125\nF0.0\ntp234\na(I620000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np235\ntp236\nRp237\ng125\nF0.0\ntp238\na(I630000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np239\ntp240\nRp241\ng125\nF0.0\ntp242\na(I640000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np243\ntp244\nRp245\ng125\nF0.0\ntp246\na(I650000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np247\ntp248\nRp249\ng125\nF0.0\ntp250\na(I660000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np251\ntp252\nRp253\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np254\ntp255\nRp256\nF0.0\ntp257\na(I670000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np258\ntp259\nRp260\ng256\nF0.0\ntp261\na(I680000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np262\ntp263\nRp264\ng256\nF0.0\ntp265\na(I690000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np266\ntp267\nRp268\ng256\nF0.0\ntp269\na(I700000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np270\ntp271\nRp272\ng256\nF0.0\ntp273\na(I710000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np274\ntp275\nRp276\ng256\nF0.0\ntp277\na(I720000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np278\ntp279\nRp280\ng256\nF0.0\ntp281\na(I730000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np282\ntp283\nRp284\ng256\nF0.0\ntp285\na(I740000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np286\ntp287\nRp288\ng256\nF0.0\ntp289\na(I750000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np290\ntp291\nRp292\ng256\nF0.0\ntp293\na(I760000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np294\ntp295\nRp296\ng256\nF0.0\ntp297\na(I770000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np298\ntp299\nRp300\ng256\nF0.0\ntp301\na(I780000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np302\ntp303\nRp304\ng256\nF0.0\ntp305\na(I790000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np306\ntp307\nRp308\ng256\nF0.0\ntp309\na(I800000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np310\ntp311\nRp312\ng256\nF0.0\ntp313\na(I810000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np314\ntp315\nRp316\ng256\nF0.0\ntp317\na(I820000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np318\ntp319\nRp320\ng256\nF0.0\ntp321\na(I830000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np322\ntp323\nRp324\ng256\nF0.0\ntp325\na(I840000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np326\ntp327\nRp328\ng256\nF0.0\ntp329\na(I850000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np330\ntp331\nRp332\ng256\nF0.0\ntp333\na(I860000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np334\ntp335\nRp336\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np337\ntp338\nRp339\nF4.0\ntp340\na(I870000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np341\ntp342\nRp343\ng339\nF0.0\ntp344\na(I880000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np345\ntp346\nRp347\ng339\nF0.0\ntp348\na(I890000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np349\ntp350\nRp351\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np352\ntp353\nRp354\nF0.0\ntp355\na(I900000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np356\ntp357\nRp358\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np359\ntp360\nRp361\nF0.0\ntp362\na(I910000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np363\ntp364\nRp365\ng361\nF0.0\ntp366\na(I920000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np367\ntp368\nRp369\ng361\nF0.0\ntp370\na(I930000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np371\ntp372\nRp373\ng361\nF0.0\ntp374\na(I940000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np375\ntp376\nRp377\ng361\nF0.0\ntp378\na(I950000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np379\ntp380\nRp381\ng361\nF0.0\ntp382\na(I960000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np383\ntp384\nRp385\ng361\nF0.0\ntp386\na(I970000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np387\ntp388\nRp389\ng361\nF0.0\ntp390\na(I980000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xc1?'\np391\ntp392\nRp393\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xc1?'\np394\ntp395\nRp396\nF0.0\ntp397\na(I990000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xc1?'\np398\ntp399\nRp400\ng1\n(g5\nS'333333\\xc3?'\np401\ntp402\nRp403\nF0.0\ntp404\na(I1000000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xc1?'\np405\ntp406\nRp407\ng403\nF0.0\ntp408\na(I1010000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xc1?'\np409\ntp410\nRp411\ng403\nF0.0\ntp412\na(I1020000\ng1\n(g5\nS'333333\\xc3?'\np413\ntp414\nRp415\ng403\nF0.0\ntp416\na(I1030000\ng1\n(g5\nS'333333\\xc3?'\np417\ntp418\nRp419\ng403\nF0.0\ntp420\na(I1040000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\xc8?'\np421\ntp422\nRp423\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\xc8?'\np424\ntp425\nRp426\nF0.0\ntp427\na(I1050000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np428\ntp429\nRp430\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np431\ntp432\nRp433\nF0.0\ntp434\na(I1060000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np435\ntp436\nRp437\ng433\nF0.0\ntp438\na(I1070000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np439\ntp440\nRp441\ng433\nF0.0\ntp442\na(I1080000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np443\ntp444\nRp445\ng433\nF0.0\ntp446\na(I1090000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np447\ntp448\nRp449\ng433\nF0.0\ntp450\na(I1100000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np451\ntp452\nRp453\ng433\nF0.0\ntp454\na(I1110000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np455\ntp456\nRp457\ng433\nF0.0\ntp458\na(I1120000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np459\ntp460\nRp461\ng433\nF0.0\ntp462\na(I1130000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np463\ntp464\nRp465\ng433\nF0.0\ntp466\na(I1140000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np467\ntp468\nRp469\ng433\nF0.0\ntp470\na(I1150000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np471\ntp472\nRp473\ng433\nF0.0\ntp474\na(I1160000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xce?'\np475\ntp476\nRp477\ng433\nF0.0\ntp478\na(I1170000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xd0?'\np479\ntp480\nRp481\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xd0?'\np482\ntp483\nRp484\nF0.0\ntp485\na(I1180000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xd0?'\np486\ntp487\nRp488\ng484\nF0.0\ntp489\na(I1190000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xcc?'\np490\ntp491\nRp492\ng484\nF0.0\ntp493\na(I1200000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xcc?'\np494\ntp495\nRp496\ng484\nF0.0\ntp497\na(I1210000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xcc?'\np498\ntp499\nRp500\ng484\nF0.0\ntp501\na(I1220000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\xc5?'\np502\ntp503\nRp504\ng484\nF0.0\ntp505\na(I1230000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xc4?'\np506\ntp507\nRp508\ng484\nF0.0\ntp509\na(I1240000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xc4?'\np510\ntp511\nRp512\ng484\nF0.0\ntp513\na(I1250000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xc4?'\np514\ntp515\nRp516\ng484\nF0.0\ntp517\na(I1260000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\xc5?'\np518\ntp519\nRp520\ng484\nF0.0\ntp521\na(I1270000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\xc5?'\np522\ntp523\nRp524\ng484\nF0.0\ntp525\na(I1280000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\xc5?'\np526\ntp527\nRp528\ng484\nF0.0\ntp529\na(I1290000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\xc5?'\np530\ntp531\nRp532\ng484\nF0.0\ntp533\na(I1300000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\xc5?'\np534\ntp535\nRp536\ng484\nF0.0\ntp537\na(I1310000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xc1?'\np538\ntp539\nRp540\ng484\nF0.0\ntp541\na(I1320000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xc0?'\np542\ntp543\nRp544\ng484\nF0.0\ntp545\na(I1330000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xc1?'\np546\ntp547\nRp548\ng484\nF0.0\ntp549\na(I1340000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xc1?'\np550\ntp551\nRp552\ng484\nF0.0\ntp553\na(I1350000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xc0?'\np554\ntp555\nRp556\ng484\nF0.0\ntp557\na(I1360000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xc0?'\np558\ntp559\nRp560\ng484\nF0.0\ntp561\na(I1370000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np562\ntp563\nRp564\ng484\nF0.0\ntp565\na(I1380000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np566\ntp567\nRp568\ng484\nF0.0\ntp569\na(I1390000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np570\ntp571\nRp572\ng484\nF0.0\ntp573\na(I1400000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np574\ntp575\nRp576\ng484\nF0.0\ntp577\na(I1410000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np578\ntp579\nRp580\ng484\nF0.0\ntp581\na(I1420000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np582\ntp583\nRp584\ng484\nF0.0\ntp585\na(I1430000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np586\ntp587\nRp588\ng484\nF0.0\ntp589\na(I1440000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np590\ntp591\nRp592\ng484\nF0.0\ntp593\na(I1450000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np594\ntp595\nRp596\ng484\nF0.0\ntp597\na(I1460000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np598\ntp599\nRp600\ng484\nF1.0\ntp601\na(I1470000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np602\ntp603\nRp604\ng484\nF0.0\ntp605\na(I1480000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np606\ntp607\nRp608\ng484\nF0.0\ntp609\na(I1490000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np610\ntp611\nRp612\ng484\nF0.0\ntp613\na(I1500000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np614\ntp615\nRp616\ng484\nF0.0\ntp617\na(I1510000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np618\ntp619\nRp620\ng484\nF0.0\ntp621\na(I1520000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np622\ntp623\nRp624\ng484\nF0.0\ntp625\na(I1530000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np626\ntp627\nRp628\ng484\nF0.0\ntp629\na(I1540000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np630\ntp631\nRp632\ng484\nF0.0\ntp633\na(I1550000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np634\ntp635\nRp636\ng484\nF0.0\ntp637\na(I1560000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np638\ntp639\nRp640\ng484\nF0.0\ntp641\na(I1570000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np642\ntp643\nRp644\ng484\nF0.0\ntp645\na(I1580000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np646\ntp647\nRp648\ng484\nF0.0\ntp649\na(I1590000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np650\ntp651\nRp652\ng484\nF0.0\ntp653\na(I1600000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np654\ntp655\nRp656\ng484\nF0.0\ntp657\na(I1610000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np658\ntp659\nRp660\ng484\nF0.0\ntp661\na(I1620000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np662\ntp663\nRp664\ng484\nF0.0\ntp665\na(I1630000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np666\ntp667\nRp668\ng484\nF0.0\ntp669\na(I1640000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np670\ntp671\nRp672\ng484\nF0.0\ntp673\na(I1650000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np674\ntp675\nRp676\ng484\nF0.0\ntp677\na(I1660000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np678\ntp679\nRp680\ng484\nF0.0\ntp681\na(I1670000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np682\ntp683\nRp684\ng484\nF0.0\ntp685\na(I1680000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np686\ntp687\nRp688\ng484\nF0.0\ntp689\na(I1690000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np690\ntp691\nRp692\ng484\nF0.0\ntp693\na(I1700000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np694\ntp695\nRp696\ng484\nF0.0\ntp697\na(I1710000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np698\ntp699\nRp700\ng484\nF0.0\ntp701\na(I1720000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np702\ntp703\nRp704\ng484\nF0.0\ntp705\na(I1730000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np706\ntp707\nRp708\ng484\nF0.0\ntp709\na(I1740000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np710\ntp711\nRp712\ng484\nF0.0\ntp713\na(I1750000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np714\ntp715\nRp716\ng484\nF0.0\ntp717\na(I1760000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np718\ntp719\nRp720\ng484\nF0.0\ntp721\na(I1770000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np722\ntp723\nRp724\ng484\nF0.0\ntp725\na(I1780000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np726\ntp727\nRp728\ng484\nF0.0\ntp729\na(I1790000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np730\ntp731\nRp732\ng484\nF0.0\ntp733\na(I1800000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np734\ntp735\nRp736\ng484\nF0.0\ntp737\na(I1810000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np738\ntp739\nRp740\ng484\nF0.0\ntp741\na(I1820000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np742\ntp743\nRp744\ng484\nF0.0\ntp745\na(I1830000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np746\ntp747\nRp748\ng484\nF0.0\ntp749\na(I1840000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np750\ntp751\nRp752\ng484\nF0.0\ntp753\na(I1850000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np754\ntp755\nRp756\ng484\nF0.0\ntp757\na(I1860000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np758\ntp759\nRp760\ng484\nF0.0\ntp761\na(I1870000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np762\ntp763\nRp764\ng484\nF0.0\ntp765\na(I1880000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np766\ntp767\nRp768\ng484\nF0.0\ntp769\na(I1890000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np770\ntp771\nRp772\ng484\nF0.0\ntp773\na(I1900000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np774\ntp775\nRp776\ng484\nF0.0\ntp777\na(I1910000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np778\ntp779\nRp780\ng484\nF1.0\ntp781\na(I1920000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np782\ntp783\nRp784\ng484\nF0.0\ntp785\na(I1930000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np786\ntp787\nRp788\ng484\nF0.0\ntp789\na(I1940000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np790\ntp791\nRp792\ng484\nF0.0\ntp793\na(I1950000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np794\ntp795\nRp796\ng484\nF0.0\ntp797\na(I1960000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np798\ntp799\nRp800\ng484\nF0.0\ntp801\na(I1970000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np802\ntp803\nRp804\ng484\nF0.0\ntp805\na(I1980000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np806\ntp807\nRp808\ng484\nF0.0\ntp809\na(I1990000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np810\ntp811\nRp812\ng484\nF0.0\ntp813\na(I2000000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np814\ntp815\nRp816\ng484\nF0.0\ntp817\na(I2010000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np818\ntp819\nRp820\ng484\nF0.0\ntp821\na(I2020000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np822\ntp823\nRp824\ng484\nF1.0\ntp825\na(I2030000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np826\ntp827\nRp828\ng484\nF0.0\ntp829\na(I2040000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np830\ntp831\nRp832\ng484\nF0.0\ntp833\na(I2050000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np834\ntp835\nRp836\ng484\nF1.0\ntp837\na(I2060000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np838\ntp839\nRp840\ng484\nF0.0\ntp841\na(I2070000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np842\ntp843\nRp844\ng484\nF0.0\ntp845\na(I2080000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np846\ntp847\nRp848\ng484\nF0.0\ntp849\na(I2090000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np850\ntp851\nRp852\ng484\nF0.0\ntp853\na(I2100000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np854\ntp855\nRp856\ng484\nF0.0\ntp857\na(I2110000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np858\ntp859\nRp860\ng484\nF0.0\ntp861\na(I2120000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np862\ntp863\nRp864\ng484\nF0.0\ntp865\na(I2130000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xbe?'\np866\ntp867\nRp868\ng484\nF0.0\ntp869\na(I2140000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xbe?'\np870\ntp871\nRp872\ng484\nF0.0\ntp873\na(I2150000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xbe?'\np874\ntp875\nRp876\ng484\nF0.0\ntp877\na(I2160000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np878\ntp879\nRp880\ng484\nF1.0\ntp881\na(I2170000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np882\ntp883\nRp884\ng484\nF0.0\ntp885\na(I2180000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np886\ntp887\nRp888\ng484\nF0.0\ntp889\na(I2190000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np890\ntp891\nRp892\ng484\nF0.0\ntp893\na(I2200000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np894\ntp895\nRp896\ng484\nF0.0\ntp897\na(I2210000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np898\ntp899\nRp900\ng484\nF0.0\ntp901\na(I2220000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np902\ntp903\nRp904\ng484\nF0.0\ntp905\na(I2230000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np906\ntp907\nRp908\ng484\nF0.0\ntp909\na(I2240000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np910\ntp911\nRp912\ng484\nF0.0\ntp913\na(I2250000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np914\ntp915\nRp916\ng484\nF0.0\ntp917\na(I2260000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np918\ntp919\nRp920\ng484\nF0.0\ntp921\na(I2270000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np922\ntp923\nRp924\ng484\nF0.0\ntp925\na(I2280000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np926\ntp927\nRp928\ng484\nF0.0\ntp929\na(I2290000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xbc?'\np930\ntp931\nRp932\ng484\nF0.0\ntp933\na(I2300000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np934\ntp935\nRp936\ng484\nF0.0\ntp937\na(I2310000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np938\ntp939\nRp940\ng484\nF0.0\ntp941\na(I2320000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np942\ntp943\nRp944\ng484\nF0.0\ntp945\na(I2330000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np946\ntp947\nRp948\ng484\nF0.0\ntp949\na(I2340000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np950\ntp951\nRp952\ng484\nF0.0\ntp953\na(I2350000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np954\ntp955\nRp956\ng484\nF0.0\ntp957\na(I2360000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np958\ntp959\nRp960\ng484\nF1.0\ntp961\na(I2370000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np962\ntp963\nRp964\ng484\nF0.0\ntp965\na(I2380000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np966\ntp967\nRp968\ng484\nF0.0\ntp969\na(I2390000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np970\ntp971\nRp972\ng484\nF0.0\ntp973\na(I2400000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xb7?'\np974\ntp975\nRp976\ng484\nF0.0\ntp977\na(I2410000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np978\ntp979\nRp980\ng484\nF0.0\ntp981\na(I2420000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np982\ntp983\nRp984\ng484\nF0.0\ntp985\na(I2430000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np986\ntp987\nRp988\ng484\nF0.0\ntp989\na(I2440000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np990\ntp991\nRp992\ng484\nF0.0\ntp993\na(I2450000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9?'\np994\ntp995\nRp996\ng484\nF0.0\ntp997\na(I2460000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np998\ntp999\nRp1000\ng484\nF0.0\ntp1001\na(I2470000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1002\ntp1003\nRp1004\ng484\nF0.0\ntp1005\na(I2480000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1006\ntp1007\nRp1008\ng484\nF0.0\ntp1009\na(I2490000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1010\ntp1011\nRp1012\ng484\nF0.0\ntp1013\na(I2500000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1014\ntp1015\nRp1016\ng484\nF0.0\ntp1017\na(I2510000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1018\ntp1019\nRp1020\ng484\nF0.0\ntp1021\na(I2520000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1022\ntp1023\nRp1024\ng484\nF0.0\ntp1025\na(I2530000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1026\ntp1027\nRp1028\ng484\nF0.0\ntp1029\na(I2540000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1030\ntp1031\nRp1032\ng484\nF0.0\ntp1033\na(I2550000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1034\ntp1035\nRp1036\ng484\nF0.0\ntp1037\na(I2560000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1038\ntp1039\nRp1040\ng484\nF0.0\ntp1041\na(I2570000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1042\ntp1043\nRp1044\ng484\nF0.0\ntp1045\na(I2580000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1046\ntp1047\nRp1048\ng484\nF0.0\ntp1049\na(I2590000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1050\ntp1051\nRp1052\ng484\nF1.0\ntp1053\na(I2600000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1054\ntp1055\nRp1056\ng484\nF0.0\ntp1057\na(I2610000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1058\ntp1059\nRp1060\ng484\nF0.0\ntp1061\na(I2620000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1062\ntp1063\nRp1064\ng484\nF0.0\ntp1065\na(I2630000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1066\ntp1067\nRp1068\ng484\nF0.0\ntp1069\na(I2640000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1070\ntp1071\nRp1072\ng484\nF0.0\ntp1073\na(I2650000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1074\ntp1075\nRp1076\ng484\nF0.0\ntp1077\na(I2660000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1078\ntp1079\nRp1080\ng484\nF0.0\ntp1081\na(I2670000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1082\ntp1083\nRp1084\ng484\nF0.0\ntp1085\na(I2680000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1086\ntp1087\nRp1088\ng484\nF0.0\ntp1089\na(I2690000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1090\ntp1091\nRp1092\ng484\nF0.0\ntp1093\na(I2700000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1094\ntp1095\nRp1096\ng484\nF0.0\ntp1097\na(I2710000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1098\ntp1099\nRp1100\ng484\nF0.0\ntp1101\na(I2720000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1102\ntp1103\nRp1104\ng484\nF0.0\ntp1105\na(I2730000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1106\ntp1107\nRp1108\ng484\nF0.0\ntp1109\na(I2740000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1110\ntp1111\nRp1112\ng484\nF0.0\ntp1113\na(I2750000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1114\ntp1115\nRp1116\ng484\nF0.0\ntp1117\na(I2760000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1118\ntp1119\nRp1120\ng484\nF0.0\ntp1121\na(I2770000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1122\ntp1123\nRp1124\ng484\nF0.0\ntp1125\na(I2780000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1126\ntp1127\nRp1128\ng484\nF0.0\ntp1129\na(I2790000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1130\ntp1131\nRp1132\ng484\nF0.0\ntp1133\na(I2800000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1134\ntp1135\nRp1136\ng484\nF1.0\ntp1137\na(I2810000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1138\ntp1139\nRp1140\ng484\nF0.0\ntp1141\na(I2820000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1142\ntp1143\nRp1144\ng484\nF0.0\ntp1145\na(I2830000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1146\ntp1147\nRp1148\ng484\nF0.0\ntp1149\na(I2840000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1150\ntp1151\nRp1152\ng484\nF0.0\ntp1153\na(I2850000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1154\ntp1155\nRp1156\ng484\nF0.0\ntp1157\na(I2860000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1158\ntp1159\nRp1160\ng484\nF0.0\ntp1161\na(I2870000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1162\ntp1163\nRp1164\ng484\nF0.0\ntp1165\na(I2880000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1166\ntp1167\nRp1168\ng484\nF0.0\ntp1169\na(I2890000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1170\ntp1171\nRp1172\ng484\nF0.0\ntp1173\na(I2900000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1174\ntp1175\nRp1176\ng484\nF1.0\ntp1177\na(I2910000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1178\ntp1179\nRp1180\ng484\nF0.0\ntp1181\na(I2920000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1182\ntp1183\nRp1184\ng484\nF0.0\ntp1185\na(I2930000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1186\ntp1187\nRp1188\ng484\nF0.0\ntp1189\na(I2940000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1190\ntp1191\nRp1192\ng484\nF0.0\ntp1193\na(I2950000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1194\ntp1195\nRp1196\ng484\nF1.0\ntp1197\na(I2960000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1198\ntp1199\nRp1200\ng484\nF0.0\ntp1201\na(I2970000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1202\ntp1203\nRp1204\ng484\nF0.0\ntp1205\na(I2980000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1206\ntp1207\nRp1208\ng484\nF0.0\ntp1209\na(I2990000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1210\ntp1211\nRp1212\ng484\nF0.0\ntp1213\na(I3000000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1214\ntp1215\nRp1216\ng484\nF0.0\ntp1217\na(I3010000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1218\ntp1219\nRp1220\ng484\nF0.0\ntp1221\na(I3020000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1222\ntp1223\nRp1224\ng484\nF0.0\ntp1225\na(I3030000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1226\ntp1227\nRp1228\ng484\nF0.0\ntp1229\na(I3040000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1230\ntp1231\nRp1232\ng484\nF0.0\ntp1233\na(I3050000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1234\ntp1235\nRp1236\ng484\nF0.0\ntp1237\na(I3060000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1238\ntp1239\nRp1240\ng484\nF0.0\ntp1241\na(I3070000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1242\ntp1243\nRp1244\ng484\nF0.0\ntp1245\na(I3080000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1246\ntp1247\nRp1248\ng484\nF0.0\ntp1249\na(I3090000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1250\ntp1251\nRp1252\ng484\nF0.0\ntp1253\na(I3100000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1254\ntp1255\nRp1256\ng484\nF0.0\ntp1257\na(I3110000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1258\ntp1259\nRp1260\ng484\nF2.0\ntp1261\na(I3120000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1262\ntp1263\nRp1264\ng484\nF0.0\ntp1265\na(I3130000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1266\ntp1267\nRp1268\ng484\nF0.0\ntp1269\na(I3140000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1270\ntp1271\nRp1272\ng484\nF0.0\ntp1273\na(I3150000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1274\ntp1275\nRp1276\ng484\nF0.0\ntp1277\na(I3160000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1278\ntp1279\nRp1280\ng484\nF0.0\ntp1281\na(I3170000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1282\ntp1283\nRp1284\ng484\nF0.0\ntp1285\na(I3180000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1286\ntp1287\nRp1288\ng484\nF0.0\ntp1289\na(I3190000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1290\ntp1291\nRp1292\ng484\nF0.0\ntp1293\na(I3200000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1294\ntp1295\nRp1296\ng484\nF0.0\ntp1297\na(I3210000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1298\ntp1299\nRp1300\ng484\nF0.0\ntp1301\na(I3220000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xb1?'\np1302\ntp1303\nRp1304\ng484\nF0.0\ntp1305\na(I3230000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1306\ntp1307\nRp1308\ng484\nF0.0\ntp1309\na(I3240000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1310\ntp1311\nRp1312\ng484\nF0.0\ntp1313\na(I3250000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1314\ntp1315\nRp1316\ng484\nF0.0\ntp1317\na(I3260000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xae?'\np1318\ntp1319\nRp1320\ng484\nF0.0\ntp1321\na(I3270000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1322\ntp1323\nRp1324\ng484\nF0.0\ntp1325\na(I3280000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1326\ntp1327\nRp1328\ng484\nF0.0\ntp1329\na(I3290000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xa4?'\np1330\ntp1331\nRp1332\ng484\nF0.0\ntp1333\na(I3300000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1334\ntp1335\nRp1336\ng484\nF1.0\ntp1337\na(I3310000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1338\ntp1339\nRp1340\ng484\nF0.0\ntp1341\na(I3320000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1342\ntp1343\nRp1344\ng484\nF0.0\ntp1345\na(I3330000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1346\ntp1347\nRp1348\ng484\nF0.0\ntp1349\na(I3340000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1350\ntp1351\nRp1352\ng484\nF0.0\ntp1353\na(I3350000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1354\ntp1355\nRp1356\ng484\nF0.0\ntp1357\na(I3360000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1358\ntp1359\nRp1360\ng484\nF0.0\ntp1361\na(I3370000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1362\ntp1363\nRp1364\ng484\nF0.0\ntp1365\na(I3380000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1366\ntp1367\nRp1368\ng484\nF0.0\ntp1369\na(I3390000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1370\ntp1371\nRp1372\ng484\nF0.0\ntp1373\na(I3400000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1374\ntp1375\nRp1376\ng484\nF0.0\ntp1377\na(I3410000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1378\ntp1379\nRp1380\ng484\nF0.0\ntp1381\na(I3420000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1382\ntp1383\nRp1384\ng484\nF0.0\ntp1385\na(I3430000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1386\ntp1387\nRp1388\ng484\nF0.0\ntp1389\na(I3440000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xa9?'\np1390\ntp1391\nRp1392\ng484\nF0.0\ntp1393\na(I3450000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1394\ntp1395\nRp1396\ng484\nF0.0\ntp1397\na(I3460000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1398\ntp1399\nRp1400\ng484\nF0.0\ntp1401\na(I3470000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1402\ntp1403\nRp1404\ng484\nF0.0\ntp1405\na(I3480000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1406\ntp1407\nRp1408\ng484\nF0.0\ntp1409\na(I3490000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1410\ntp1411\nRp1412\ng484\nF0.0\ntp1413\na(I3500000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1414\ntp1415\nRp1416\ng484\nF0.0\ntp1417\na(I3510000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1418\ntp1419\nRp1420\ng484\nF0.0\ntp1421\na(I3520000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1422\ntp1423\nRp1424\ng484\nF0.0\ntp1425\na(I3530000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1426\ntp1427\nRp1428\ng484\nF0.0\ntp1429\na(I3540000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1430\ntp1431\nRp1432\ng484\nF0.0\ntp1433\na(I3550000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np1434\ntp1435\nRp1436\ng484\nF0.0\ntp1437\na(I3560000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np1438\ntp1439\nRp1440\ng484\nF0.0\ntp1441\na(I3570000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np1442\ntp1443\nRp1444\ng484\nF0.0\ntp1445\na(I3580000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np1446\ntp1447\nRp1448\ng484\nF0.0\ntp1449\na(I3590000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np1450\ntp1451\nRp1452\ng484\nF0.0\ntp1453\na(I3600000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np1454\ntp1455\nRp1456\ng484\nF0.0\ntp1457\na(I3610000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1458\ntp1459\nRp1460\ng484\nF0.0\ntp1461\na(I3620000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1462\ntp1463\nRp1464\ng484\nF0.0\ntp1465\na(I3630000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1466\ntp1467\nRp1468\ng484\nF0.0\ntp1469\na(I3640000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1470\ntp1471\nRp1472\ng484\nF0.0\ntp1473\na(I3650000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1474\ntp1475\nRp1476\ng484\nF0.0\ntp1477\na(I3660000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1478\ntp1479\nRp1480\ng484\nF0.0\ntp1481\na(I3670000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1482\ntp1483\nRp1484\ng484\nF0.0\ntp1485\na(I3680000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1486\ntp1487\nRp1488\ng484\nF0.0\ntp1489\na(I3690000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1490\ntp1491\nRp1492\ng484\nF0.0\ntp1493\na(I3700000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1494\ntp1495\nRp1496\ng484\nF0.0\ntp1497\na(I3710000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1498\ntp1499\nRp1500\ng484\nF0.0\ntp1501\na(I3720000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1502\ntp1503\nRp1504\ng484\nF0.0\ntp1505\na(I3730000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1506\ntp1507\nRp1508\ng484\nF0.0\ntp1509\na(I3740000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1510\ntp1511\nRp1512\ng484\nF0.0\ntp1513\na(I3750000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1514\ntp1515\nRp1516\ng484\nF0.0\ntp1517\na(I3760000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1518\ntp1519\nRp1520\ng484\nF0.0\ntp1521\na(I3770000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1522\ntp1523\nRp1524\ng484\nF0.0\ntp1525\na(I3780000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1526\ntp1527\nRp1528\ng484\nF0.0\ntp1529\na(I3790000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1530\ntp1531\nRp1532\ng484\nF0.0\ntp1533\na(I3800000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1534\ntp1535\nRp1536\ng484\nF0.0\ntp1537\na(I3810000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1538\ntp1539\nRp1540\ng484\nF0.0\ntp1541\na(I3820000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1542\ntp1543\nRp1544\ng484\nF0.0\ntp1545\na(I3830000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1546\ntp1547\nRp1548\ng484\nF0.0\ntp1549\na(I3840000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1550\ntp1551\nRp1552\ng484\nF0.0\ntp1553\na(I3850000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1554\ntp1555\nRp1556\ng484\nF0.0\ntp1557\na(I3860000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1558\ntp1559\nRp1560\ng484\nF0.0\ntp1561\na(I3870000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1562\ntp1563\nRp1564\ng484\nF0.0\ntp1565\na(I3880000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1566\ntp1567\nRp1568\ng484\nF0.0\ntp1569\na(I3890000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1570\ntp1571\nRp1572\ng484\nF0.0\ntp1573\na(I3900000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1574\ntp1575\nRp1576\ng484\nF0.0\ntp1577\na(I3910000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1578\ntp1579\nRp1580\ng484\nF0.0\ntp1581\na(I3920000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1582\ntp1583\nRp1584\ng484\nF0.0\ntp1585\na(I3930000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1586\ntp1587\nRp1588\ng484\nF0.0\ntp1589\na(I3940000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1590\ntp1591\nRp1592\ng484\nF2.0\ntp1593\na(I3950000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1594\ntp1595\nRp1596\ng484\nF0.0\ntp1597\na(I3960000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1598\ntp1599\nRp1600\ng484\nF0.0\ntp1601\na(I3970000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x94?'\np1602\ntp1603\nRp1604\ng484\nF0.0\ntp1605\na(I3980000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1606\ntp1607\nRp1608\ng484\nF0.0\ntp1609\na(I3990000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1610\ntp1611\nRp1612\ng484\nF0.0\ntp1613\na(I4000000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1614\ntp1615\nRp1616\ng484\nF0.0\ntp1617\na(I4010000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1618\ntp1619\nRp1620\ng484\nF0.0\ntp1621\na(I4020000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1622\ntp1623\nRp1624\ng484\nF0.0\ntp1625\na(I4030000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1626\ntp1627\nRp1628\ng484\nF0.0\ntp1629\na(I4040000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1630\ntp1631\nRp1632\ng484\nF0.0\ntp1633\na(I4050000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1634\ntp1635\nRp1636\ng484\nF0.0\ntp1637\na(I4060000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1638\ntp1639\nRp1640\ng484\nF0.0\ntp1641\na(I4070000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1642\ntp1643\nRp1644\ng484\nF0.0\ntp1645\na(I4080000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1646\ntp1647\nRp1648\ng484\nF0.0\ntp1649\na(I4090000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1650\ntp1651\nRp1652\ng484\nF0.0\ntp1653\na(I4100000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1654\ntp1655\nRp1656\ng484\nF0.0\ntp1657\na(I4110000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1658\ntp1659\nRp1660\ng484\nF0.0\ntp1661\na(I4120000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1662\ntp1663\nRp1664\ng484\nF0.0\ntp1665\na(I4130000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1666\ntp1667\nRp1668\ng484\nF0.0\ntp1669\na(I4140000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1670\ntp1671\nRp1672\ng484\nF0.0\ntp1673\na(I4150000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1674\ntp1675\nRp1676\ng484\nF0.0\ntp1677\na(I4160000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1678\ntp1679\nRp1680\ng484\nF0.0\ntp1681\na(I4170000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1682\ntp1683\nRp1684\ng484\nF0.0\ntp1685\na(I4180000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1686\ntp1687\nRp1688\ng484\nF0.0\ntp1689\na(I4190000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1690\ntp1691\nRp1692\ng484\nF0.0\ntp1693\na(I4200000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1694\ntp1695\nRp1696\ng484\nF0.0\ntp1697\na(I4210000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1698\ntp1699\nRp1700\ng484\nF0.0\ntp1701\na(I4220000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1702\ntp1703\nRp1704\ng484\nF0.0\ntp1705\na(I4230000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1706\ntp1707\nRp1708\ng484\nF0.0\ntp1709\na(I4240000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1710\ntp1711\nRp1712\ng484\nF0.0\ntp1713\na(I4250000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1714\ntp1715\nRp1716\ng484\nF0.0\ntp1717\na(I4260000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x9e?'\np1718\ntp1719\nRp1720\ng484\nF0.0\ntp1721\na(I4270000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np1722\ntp1723\nRp1724\ng484\nF0.0\ntp1725\na(I4280000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np1726\ntp1727\nRp1728\ng484\nF0.0\ntp1729\na(I4290000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np1730\ntp1731\nRp1732\ng484\nF0.0\ntp1733\na(I4300000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np1734\ntp1735\nRp1736\ng484\nF0.0\ntp1737\na(I4310000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1738\ntp1739\nRp1740\ng484\nF0.0\ntp1741\na(I4320000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1742\ntp1743\nRp1744\ng484\nF0.0\ntp1745\na(I4330000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1746\ntp1747\nRp1748\ng484\nF0.0\ntp1749\na(I4340000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1750\ntp1751\nRp1752\ng484\nF0.0\ntp1753\na(I4350000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1754\ntp1755\nRp1756\ng484\nF0.0\ntp1757\na(I4360000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1758\ntp1759\nRp1760\ng484\nF0.0\ntp1761\na(I4370000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1762\ntp1763\nRp1764\ng484\nF0.0\ntp1765\na(I4380000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1766\ntp1767\nRp1768\ng484\nF0.0\ntp1769\na(I4390000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1770\ntp1771\nRp1772\ng484\nF0.0\ntp1773\na(I4400000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1774\ntp1775\nRp1776\ng484\nF0.0\ntp1777\na(I4410000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1778\ntp1779\nRp1780\ng484\nF0.0\ntp1781\na(I4420000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1782\ntp1783\nRp1784\ng484\nF0.0\ntp1785\na(I4430000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1786\ntp1787\nRp1788\ng484\nF0.0\ntp1789\na(I4440000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1790\ntp1791\nRp1792\ng484\nF0.0\ntp1793\na(I4450000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1794\ntp1795\nRp1796\ng484\nF0.0\ntp1797\na(I4460000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1798\ntp1799\nRp1800\ng484\nF0.0\ntp1801\na(I4470000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1802\ntp1803\nRp1804\ng484\nF0.0\ntp1805\na(I4480000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1806\ntp1807\nRp1808\ng484\nF0.0\ntp1809\na(I4490000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1810\ntp1811\nRp1812\ng484\nF0.0\ntp1813\na(I4500000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1814\ntp1815\nRp1816\ng484\nF0.0\ntp1817\na(I4510000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1818\ntp1819\nRp1820\ng484\nF0.0\ntp1821\na(I4520000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1822\ntp1823\nRp1824\ng484\nF0.0\ntp1825\na(I4530000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1826\ntp1827\nRp1828\ng484\nF0.0\ntp1829\na(I4540000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1830\ntp1831\nRp1832\ng484\nF0.0\ntp1833\na(I4550000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1834\ntp1835\nRp1836\ng484\nF0.0\ntp1837\na(I4560000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1838\ntp1839\nRp1840\ng484\nF0.0\ntp1841\na(I4570000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1842\ntp1843\nRp1844\ng484\nF0.0\ntp1845\na(I4580000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1846\ntp1847\nRp1848\ng484\nF0.0\ntp1849\na(I4590000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1850\ntp1851\nRp1852\ng484\nF0.0\ntp1853\na(I4600000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1854\ntp1855\nRp1856\ng484\nF0.0\ntp1857\na(I4610000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1858\ntp1859\nRp1860\ng484\nF0.0\ntp1861\na(I4620000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00'\np1862\ntp1863\nRp1864\ng484\nF0.0\ntp1865\na(I4630000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np1866\ntp1867\nRp1868\ng484\nF0.0\ntp1869\na(I4640000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np1870\ntp1871\nRp1872\ng484\nF0.0\ntp1873\na(I4650000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x84?'\np1874\ntp1875\nRp1876\ng484\nF0.0\ntp1877\na(I4660000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np1878\ntp1879\nRp1880\ng484\nF5.0\ntp1881\na(I4670000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np1882\ntp1883\nRp1884\ng484\nF0.0\ntp1885\na(I4680000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np1886\ntp1887\nRp1888\ng484\nF0.0\ntp1889\na(I4690000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xb4?'\np1890\ntp1891\nRp1892\ng484\nF0.0\ntp1893\na(I4700000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\xe5?'\np1894\ntp1895\nRp1896\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\xe5?'\np1897\ntp1898\nRp1899\nF42.0\ntp1900\na(I4710000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\xf7?'\np1901\ntp1902\nRp1903\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\xf7?'\np1904\ntp1905\nRp1906\nF25.0\ntp1907\na(I4720000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\\xfe?'\np1908\ntp1909\nRp1910\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\\xfe?'\np1911\ntp1912\nRp1913\nF21.0\ntp1914\na(I4730000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x05@'\np1915\ntp1916\nRp1917\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x05@'\np1918\ntp1919\nRp1920\nF29.0\ntp1921\na(I4740000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7\\r@'\np1922\ntp1923\nRp1924\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7\\r@'\np1925\ntp1926\nRp1927\nF30.0\ntp1928\na(I4750000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\x11@'\np1929\ntp1930\nRp1931\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\x11@'\np1932\ntp1933\nRp1934\nF26.0\ntp1935\na(I4760000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x15@'\np1936\ntp1937\nRp1938\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x15@'\np1939\ntp1940\nRp1941\nF31.0\ntp1942\na(I4770000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x18@'\np1943\ntp1944\nRp1945\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x18@'\np1946\ntp1947\nRp1948\nF12.0\ntp1949\na(I4780000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\x1c@'\np1950\ntp1951\nRp1952\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\x1c@'\np1953\ntp1954\nRp1955\nF38.0\ntp1956\na(I4790000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5( @'\np1957\ntp1958\nRp1959\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5( @'\np1960\ntp1961\nRp1962\nF39.0\ntp1963\na(I4800000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf0 @'\np1964\ntp1965\nRp1966\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf0 @'\np1967\ntp1968\nRp1969\nF18.0\ntp1970\na(I4810000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00#@'\np1971\ntp1972\nRp1973\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00#@'\np1974\ntp1975\nRp1976\nF41.0\ntp1977\na(I4820000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8$@'\np1978\ntp1979\nRp1980\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8$@'\np1981\ntp1982\nRp1983\nF5.0\ntp1984\na(I4830000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e%@'\np1985\ntp1986\nRp1987\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e%@'\np1988\ntp1989\nRp1990\nF32.0\ntp1991\na(I4840000\ng1\n(g5\nS\"\\xd7\\xa3p=\\n\\xd7'@\"\np1992\ntp1993\nRp1994\ng1\n(g5\nS\"\\xd7\\xa3p=\\n\\xd7'@\"\np1995\ntp1996\nRp1997\nF26.0\ntp1998\na(I4850000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05+@'\np1999\ntp2000\nRp2001\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05+@'\np2002\ntp2003\nRp2004\nF41.0\ntp2005\na(I4860000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB-@'\np2006\ntp2007\nRp2008\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB-@'\np2009\ntp2010\nRp2011\nF30.0\ntp2012\na(I4870000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8.@'\np2013\ntp2014\nRp2015\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8.@'\np2016\ntp2017\nRp2018\nF26.0\ntp2019\na(I4880000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x80/@'\np2020\ntp2021\nRp2022\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x80/@'\np2023\ntp2024\nRp2025\nF19.0\ntp2026\na(I4890000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f0@'\np2027\ntp2028\nRp2029\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f0@'\np2030\ntp2031\nRp2032\nF21.0\ntp2033\na(I4900000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW1@'\np2034\ntp2035\nRp2036\ng1\n(g5\nS'\\xd7\\xa3p=\\nW1@'\np2037\ntp2038\nRp2039\nF45.0\ntp2040\na(I4910000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde1@'\np2041\ntp2042\nRp2043\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde1@'\np2044\ntp2045\nRp2046\nF10.0\ntp2047\na(I4920000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc52@'\np2048\ntp2049\nRp2050\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc52@'\np2051\ntp2052\nRp2053\nF18.0\ntp2054\na(I4930000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\3@'\np2055\ntp2056\nRp2057\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\3@'\np2058\ntp2059\nRp2060\nF36.0\ntp2061\na(I4940000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x004@'\np2062\ntp2063\nRp2064\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x004@'\np2065\ntp2066\nRp2067\nF25.0\ntp2068\na(I4950000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np2069\ntp2070\nRp2071\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np2072\ntp2073\nRp2074\nF7.0\ntp2075\na(I4960000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O5@'\np2076\ntp2077\nRp2078\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ5@'\np2079\ntp2080\nRp2081\nF0.0\ntp2082\na(I4970000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e6@'\np2083\ntp2084\nRp2085\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e6@'\np2086\ntp2087\nRp2088\nF26.0\ntp2089\na(I4980000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc06@'\np2090\ntp2091\nRp2092\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc06@'\np2093\ntp2094\nRp2095\nF34.0\ntp2096\na(I4990000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^7@'\np2097\ntp2098\nRp2099\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^7@'\np2100\ntp2101\nRp2102\nF32.0\ntp2103\na(I5000000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca7@'\np2104\ntp2105\nRp2106\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca7@'\np2107\ntp2108\nRp2109\nF6.0\ntp2110\na(I5010000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x978@'\np2111\ntp2112\nRp2113\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x978@'\np2114\ntp2115\nRp2116\nF29.0\ntp2117\na(I5020000\ng1\n(g5\nS'\\xa4p=\\n\\xd7c9@'\np2118\ntp2119\nRp2120\ng1\n(g5\nS'\\xa4p=\\n\\xd7c9@'\np2121\ntp2122\nRp2123\nF27.0\ntp2124\na(I5030000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba9@'\np2125\ntp2126\nRp2127\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba9@'\np2128\ntp2129\nRp2130\nF25.0\ntp2131\na(I5040000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca9@'\np2132\ntp2133\nRp2134\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca9@'\np2135\ntp2136\nRp2137\nF31.0\ntp2138\na(I5050000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x19:@'\np2139\ntp2140\nRp2141\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x19:@'\np2142\ntp2143\nRp2144\nF43.0\ntp2145\na(I5060000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14:@'\np2146\ntp2147\nRp2148\ng2144\nF18.0\ntp2149\na(I5070000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xe39@'\np2150\ntp2151\nRp2152\ng1\n(g5\nS'333333:@'\np2153\ntp2154\nRp2155\nF6.0\ntp2156\na(I5080000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1c:@'\np2157\ntp2158\nRp2159\ng2155\nF35.0\ntp2160\na(I5090000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f:@'\np2161\ntp2162\nRp2163\ng2155\nF22.0\ntp2164\na(I5100000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc09@'\np2165\ntp2166\nRp2167\ng2155\nF10.0\ntp2168\na(I5110000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c9@'\np2169\ntp2170\nRp2171\ng2155\nF31.0\ntp2172\na(I5120000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#9@'\np2173\ntp2174\nRp2175\ng2155\nF23.0\ntp2176\na(I5130000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x829@'\np2177\ntp2178\nRp2179\ng2155\nF25.0\ntp2180\na(I5140000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf8@'\np2181\ntp2182\nRp2183\ng2155\nF1.0\ntp2184\na(I5150000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf8@'\np2185\ntp2186\nRp2187\ng2155\nF13.0\ntp2188\na(I5160000\ng1\n(g5\nS'33333\\xb38@'\np2189\ntp2190\nRp2191\ng2155\nF18.0\ntp2192\na(I5170000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^8@'\np2193\ntp2194\nRp2195\ng2155\nF37.0\ntp2196\na(I5180000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xd97@'\np2197\ntp2198\nRp2199\ng2155\nF36.0\ntp2200\na(I5190000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB7@'\np2201\ntp2202\nRp2203\ng2155\nF13.0\ntp2204\na(I5200000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc77@'\np2205\ntp2206\nRp2207\ng2155\nF34.0\ntp2208\na(I5210000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x078@'\np2209\ntp2210\nRp2211\ng2155\nF33.0\ntp2212\na(I5220000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x198@'\np2213\ntp2214\nRp2215\ng2155\nF27.0\ntp2216\na(I5230000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc77@'\np2217\ntp2218\nRp2219\ng2155\nF22.0\ntp2220\na(I5240000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xee7@'\np2221\ntp2222\nRp2223\ng2155\nF19.0\ntp2224\na(I5250000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc7@'\np2225\ntp2226\nRp2227\ng2155\nF33.0\ntp2228\na(I5260000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=8@'\np2229\ntp2230\nRp2231\ng2155\nF11.0\ntp2232\na(I5270000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf07@'\np2233\ntp2234\nRp2235\ng2155\nF34.0\ntp2236\na(I5280000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe17@'\np2237\ntp2238\nRp2239\ng2155\nF13.0\ntp2240\na(I5290000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ8@'\np2241\ntp2242\nRp2243\ng2155\nF36.0\ntp2244\na(I5300000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^8@'\np2245\ntp2246\nRp2247\ng2155\nF29.0\ntp2248\na(I5310000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c8@'\np2249\ntp2250\nRp2251\ng2155\nF22.0\ntp2252\na(I5320000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n8@'\np2253\ntp2254\nRp2255\ng2155\nF4.0\ntp2256\na(I5330000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc258@'\np2257\ntp2258\nRp2259\ng2155\nF20.0\ntp2260\na(I5340000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf57@'\np2261\ntp2262\nRp2263\ng2155\nF26.0\ntp2264\na(I5350000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde7@'\np2265\ntp2266\nRp2267\ng2155\nF2.0\ntp2268\na(I5360000\ng1\n(g5\nS'3333338@'\np2269\ntp2270\nRp2271\ng2155\nF25.0\ntp2272\na(I5370000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG!8@'\np2273\ntp2274\nRp2275\ng2155\nF36.0\ntp2276\na(I5380000\ng1\n(g5\nS'3333338@'\np2277\ntp2278\nRp2279\ng2155\nF11.0\ntp2280\na(I5390000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=8@'\np2281\ntp2282\nRp2283\ng2155\nF34.0\ntp2284\na(I5400000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85+8@'\np2285\ntp2286\nRp2287\ng2155\nF41.0\ntp2288\na(I5410000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc7@'\np2289\ntp2290\nRp2291\ng2155\nF32.0\ntp2292\na(I5420000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f7@'\np2293\ntp2294\nRp2295\ng2155\nF34.0\ntp2296\na(I5430000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x197@'\np2297\ntp2298\nRp2299\ng2155\nF3.0\ntp2300\na(I5440000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfd6@'\np2301\ntp2302\nRp2303\ng2155\nF28.0\ntp2304\na(I5450000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde6@'\np2305\ntp2306\nRp2307\ng2155\nF42.0\ntp2308\na(I5460000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x057@'\np2309\ntp2310\nRp2311\ng2155\nF32.0\ntp2312\na(I5470000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde6@'\np2313\ntp2314\nRp2315\ng2155\nF7.0\ntp2316\na(I5480000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x197@'\np2317\ntp2318\nRp2319\ng2155\nF38.0\ntp2320\na(I5490000\ng1\n(g5\nS'33333s7@'\np2321\ntp2322\nRp2323\ng2155\nF28.0\ntp2324\na(I5500000\ng1\n(g5\nS'ffffff7@'\np2325\ntp2326\nRp2327\ng2155\nF33.0\ntp2328\na(I5510000\ng1\n(g5\nS'fffff&7@'\np2329\ntp2330\nRp2331\ng2155\nF32.0\ntp2332\na(I5520000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=7@'\np2333\ntp2334\nRp2335\ng2155\nF44.0\ntp2336\na(I5530000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f6@'\np2337\ntp2338\nRp2339\ng2155\nF6.0\ntp2340\na(I5540000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa6@'\np2341\ntp2342\nRp2343\ng2155\nF21.0\ntp2344\na(I5550000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n6@'\np2345\ntp2346\nRp2347\ng2155\nF25.0\ntp2348\na(I5560000\ng1\n(g5\nS'33333s6@'\np2349\ntp2350\nRp2351\ng2155\nF38.0\ntp2352\na(I5570000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc56@'\np2353\ntp2354\nRp2355\ng2155\nF37.0\ntp2356\na(I5580000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z6@'\np2357\ntp2358\nRp2359\ng2155\nF28.0\ntp2360\na(I5590000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xe35@'\np2361\ntp2362\nRp2363\ng2155\nF33.0\ntp2364\na(I5600000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x826@'\np2365\ntp2366\nRp2367\ng2155\nF31.0\ntp2368\na(I5610000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xee5@'\np2369\ntp2370\nRp2371\ng2155\nF3.0\ntp2372\na(I5620000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n6@'\np2373\ntp2374\nRp2375\ng2155\nF23.0\ntp2376\na(I5630000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1c5@'\np2377\ntp2378\nRp2379\ng2155\nF0.0\ntp2380\na(I5640000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x974@'\np2381\ntp2382\nRp2383\ng2155\nF11.0\ntp2384\na(I5650000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfd4@'\np2385\ntp2386\nRp2387\ng2155\nF33.0\ntp2388\na(I5660000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c4@'\np2389\ntp2390\nRp2391\ng2155\nF0.0\ntp2392\na(I5670000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f4@'\np2393\ntp2394\nRp2395\ng2155\nF0.0\ntp2396\na(I5680000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1c3@'\np2397\ntp2398\nRp2399\ng2155\nF0.0\ntp2400\na(I5690000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^3@'\np2401\ntp2402\nRp2403\ng2155\nF35.0\ntp2404\na(I5700000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#3@'\np2405\ntp2406\nRp2407\ng2155\nF21.0\ntp2408\na(I5710000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}2@'\np2409\ntp2410\nRp2411\ng2155\nF9.0\ntp2412\na(I5720000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O2@'\np2413\ntp2414\nRp2415\ng2155\nF23.0\ntp2416\na(I5730000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc02@'\np2417\ntp2418\nRp2419\ng2155\nF35.0\ntp2420\na(I5740000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb82@'\np2421\ntp2422\nRp2423\ng2155\nF31.0\ntp2424\na(I5750000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x822@'\np2425\ntp2426\nRp2427\ng2155\nF0.0\ntp2428\na(I5760000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x112@'\np2429\ntp2430\nRp2431\ng2155\nF4.0\ntp2432\na(I5770000\ng1\n(g5\nS'\\xa4p=\\n\\xd7c2@'\np2433\ntp2434\nRp2435\ng2155\nF14.0\ntp2436\na(I5780000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf82@'\np2437\ntp2438\nRp2439\ng2155\nF16.0\ntp2440\na(I5790000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE3@'\np2441\ntp2442\nRp2443\ng2155\nF39.0\ntp2444\na(I5800000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c3@'\np2445\ntp2446\nRp2447\ng2155\nF24.0\ntp2448\na(I5810000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zT4@'\np2449\ntp2450\nRp2451\ng2155\nF35.0\ntp2452\na(I5820000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=4@'\np2453\ntp2454\nRp2455\ng2155\nF36.0\ntp2456\na(I5830000\ng1\n(g5\nS'\\xa4p=\\n\\xd7c4@'\np2457\ntp2458\nRp2459\ng2155\nF32.0\ntp2460\na(I5840000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y4@'\np2461\ntp2462\nRp2463\ng2155\nF42.0\ntp2464\na(I5850000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa14@'\np2465\ntp2466\nRp2467\ng2155\nF45.0\ntp2468\na(I5860000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd14@'\np2469\ntp2470\nRp2471\ng2155\nF19.0\ntp2472\na(I5870000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x005@'\np2473\ntp2474\nRp2475\ng2155\nF36.0\ntp2476\na(I5880000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x195@'\np2477\ntp2478\nRp2479\ng2155\nF33.0\ntp2480\na(I5890000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np2481\ntp2482\nRp2483\ng2155\nF0.0\ntp2484\na(I5900000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x994@'\np2485\ntp2486\nRp2487\ng2155\nF36.0\ntp2488\na(I5910000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x005@'\np2489\ntp2490\nRp2491\ng2155\nF30.0\ntp2492\na(I5920000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc255@'\np2493\ntp2494\nRp2495\ng2155\nF41.0\ntp2496\na(I5930000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ5@'\np2497\ntp2498\nRp2499\ng2155\nF46.0\ntp2500\na(I5940000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h5@'\np2501\ntp2502\nRp2503\ng2155\nF24.0\ntp2504\na(I5950000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zT5@'\np2505\ntp2506\nRp2507\ng2155\nF26.0\ntp2508\na(I5960000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ6@'\np2509\ntp2510\nRp2511\ng2155\nF30.0\ntp2512\na(I5970000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x996@'\np2513\ntp2514\nRp2515\ng2155\nF30.0\ntp2516\na(I5980000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e7@'\np2517\ntp2518\nRp2519\ng2155\nF40.0\ntp2520\na(I5990000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@7@'\np2521\ntp2522\nRp2523\ng2155\nF8.0\ntp2524\na(I6000000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0c8@'\np2525\ntp2526\nRp2527\ng2155\nF26.0\ntp2528\na(I6010000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfd8@'\np2529\ntp2530\nRp2531\ng2155\nF22.0\ntp2532\na(I6020000\ng1\n(g5\nS'q=\\n\\xd7\\xa309@'\np2533\ntp2534\nRp2535\ng2155\nF27.0\ntp2536\na(I6030000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE9@'\np2537\ntp2538\nRp2539\ng2155\nF32.0\ntp2540\na(I6040000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG9@'\np2541\ntp2542\nRp2543\ng2155\nF19.0\ntp2544\na(I6050000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1c:@'\np2545\ntp2546\nRp2547\ng2155\nF28.0\ntp2548\na(I6060000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc59@'\np2549\ntp2550\nRp2551\ng2155\nF17.0\ntp2552\na(I6070000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc29@'\np2553\ntp2554\nRp2555\ng2155\nF24.0\ntp2556\na(I6080000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb59@'\np2557\ntp2558\nRp2559\ng2155\nF8.0\ntp2560\na(I6090000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c:@'\np2561\ntp2562\nRp2563\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c:@'\np2564\ntp2565\nRp2566\nF24.0\ntp2567\na(I6100000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99:@'\np2568\ntp2569\nRp2570\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99:@'\np2571\ntp2572\nRp2573\nF21.0\ntp2574\na(I6110000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x97:@'\np2575\ntp2576\nRp2577\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c:@'\np2578\ntp2579\nRp2580\nF43.0\ntp2581\na(I6120000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#:@'\np2582\ntp2583\nRp2584\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8:@'\np2585\ntp2586\nRp2587\nF13.0\ntp2588\na(I6130000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c9@'\np2589\ntp2590\nRp2591\ng2587\nF16.0\ntp2592\na(I6140000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e9@'\np2593\ntp2594\nRp2595\ng2587\nF29.0\ntp2596\na(I6150000\ng1\n(g5\nS'3333339@'\np2597\ntp2598\nRp2599\ng2587\nF25.0\ntp2600\na(I6160000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc259@'\np2601\ntp2602\nRp2603\ng2587\nF22.0\ntp2604\na(I6170000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n9@'\np2605\ntp2606\nRp2607\ng2587\nF23.0\ntp2608\na(I6180000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^9@'\np2609\ntp2610\nRp2611\ng2587\nF30.0\ntp2612\na(I6190000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG9@'\np2613\ntp2614\nRp2615\ng2587\nF17.0\ntp2616\na(I6200000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba9@'\np2617\ntp2618\nRp2619\ng2587\nF33.0\ntp2620\na(I6210000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd49@'\np2621\ntp2622\nRp2623\ng2587\nF17.0\ntp2624\na(I6220000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x07:@'\np2625\ntp2626\nRp2627\ng2587\nF6.0\ntp2628\na(I6230000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n:@'\np2629\ntp2630\nRp2631\ng2587\nF29.0\ntp2632\na(I6240000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0c:@'\np2633\ntp2634\nRp2635\ng2587\nF19.0\ntp2636\na(I6250000\ng1\n(g5\nS'fffff&:@'\np2637\ntp2638\nRp2639\ng2587\nF33.0\ntp2640\na(I6260000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xd99@'\np2641\ntp2642\nRp2643\ng2587\nF12.0\ntp2644\na(I6270000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xe39@'\np2645\ntp2646\nRp2647\ng2587\nF9.0\ntp2648\na(I6280000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf9@'\np2649\ntp2650\nRp2651\ng2587\nF25.0\ntp2652\na(I6290000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z9@'\np2653\ntp2654\nRp2655\ng2587\nF64.0\ntp2656\na(I6300000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x11:@'\np2657\ntp2658\nRp2659\ng2587\nF41.0\ntp2660\na(I6310000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa89@'\np2661\ntp2662\nRp2663\ng2587\nF29.0\ntp2664\na(I6320000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL:@'\np2665\ntp2666\nRp2667\ng2587\nF71.0\ntp2668\na(I6330000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb0:@'\np2669\ntp2670\nRp2671\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb0:@'\np2672\ntp2673\nRp2674\nF42.0\ntp2675\na(I6340000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z:@'\np2676\ntp2677\nRp2678\ng2674\nF17.0\ntp2679\na(I6350000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#:@'\np2680\ntp2681\nRp2682\ng2674\nF25.0\ntp2683\na(I6360000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x11:@'\np2684\ntp2685\nRp2686\ng2674\nF27.0\ntp2687\na(I6370000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x91:@'\np2688\ntp2689\nRp2690\ng2674\nF48.0\ntp2691\na(I6380000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG:@'\np2692\ntp2693\nRp2694\ng2674\nF31.0\ntp2695\na(I6390000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab:@'\np2696\ntp2697\nRp2698\ng2674\nF53.0\ntp2699\na(I6400000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2:@'\np2700\ntp2701\nRp2702\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd4:@'\np2703\ntp2704\nRp2705\nF28.0\ntp2706\na(I6410000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE;@'\np2707\ntp2708\nRp2709\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE;@'\np2710\ntp2711\nRp2712\nF51.0\ntp2713\na(I6420000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca;@'\np2714\ntp2715\nRp2716\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca;@'\np2717\ntp2718\nRp2719\nF26.0\ntp2720\na(I6430000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8;@'\np2721\ntp2722\nRp2723\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xee;@'\np2724\ntp2725\nRp2726\nF22.0\ntp2727\na(I6440000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u;@'\np2728\ntp2729\nRp2730\ng2726\nF19.0\ntp2731\na(I6450000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa1;@'\np2732\ntp2733\nRp2734\ng2726\nF24.0\ntp2735\na(I6460000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae;@'\np2736\ntp2737\nRp2738\ng2726\nF16.0\ntp2739\na(I6470000\ng1\n(g5\nS'=\\n\\xd7\\xa3p};@'\np2740\ntp2741\nRp2742\ng2726\nF33.0\ntp2743\na(I6480000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc5;@'\np2744\ntp2745\nRp2746\ng2726\nF32.0\ntp2747\na(I6490000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfd;@'\np2748\ntp2749\nRp2750\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05<@'\np2751\ntp2752\nRp2753\nF40.0\ntp2754\na(I6500000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e;@'\np2755\ntp2756\nRp2757\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f<@'\np2758\ntp2759\nRp2760\nF21.0\ntp2761\na(I6510000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e;@'\np2762\ntp2763\nRp2764\ng2760\nF36.0\ntp2765\na(I6520000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f;@'\np2766\ntp2767\nRp2768\ng2760\nF37.0\ntp2769\na(I6530000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c:@'\np2770\ntp2771\nRp2772\ng2760\nF5.0\ntp2773\na(I6540000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW:@'\np2774\ntp2775\nRp2776\ng2760\nF45.0\ntp2777\na(I6550000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8:@'\np2778\ntp2779\nRp2780\ng2760\nF31.0\ntp2781\na(I6560000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc9@'\np2782\ntp2783\nRp2784\ng2760\nF23.0\ntp2785\na(I6570000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x17:@'\np2786\ntp2787\nRp2788\ng2760\nF43.0\ntp2789\na(I6580000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#:@'\np2790\ntp2791\nRp2792\ng2760\nF30.0\ntp2793\na(I6590000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#:@'\np2794\ntp2795\nRp2796\ng2760\nF24.0\ntp2797\na(I6600000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb9@'\np2798\ntp2799\nRp2800\ng2760\nF31.0\ntp2801\na(I6610000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zT:@'\np2802\ntp2803\nRp2804\ng2760\nF22.0\ntp2805\na(I6620000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ:@'\np2806\ntp2807\nRp2808\ng2760\nF2.0\ntp2809\na(I6630000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa89@'\np2810\ntp2811\nRp2812\ng2760\nF3.0\ntp2813\na(I6640000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x829@'\np2814\ntp2815\nRp2816\ng2760\nF48.0\ntp2817\na(I6650000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc09@'\np2818\ntp2819\nRp2820\ng2760\nF6.0\ntp2821\na(I6660000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf08@'\np2822\ntp2823\nRp2824\ng2760\nF27.0\ntp2825\na(I6670000\ng1\n(g5\nS'33333\\xb38@'\np2826\ntp2827\nRp2828\ng2760\nF27.0\ntp2829\na(I6680000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx8@'\np2830\ntp2831\nRp2832\ng2760\nF0.0\ntp2833\na(I6690000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xd97@'\np2834\ntp2835\nRp2836\ng2760\nF11.0\ntp2837\na(I6700000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c7@'\np2838\ntp2839\nRp2840\ng2760\nF25.0\ntp2841\na(I6710000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@7@'\np2842\ntp2843\nRp2844\ng2760\nF27.0\ntp2845\na(I6720000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx7@'\np2846\ntp2847\nRp2848\ng2760\nF27.0\ntp2849\na(I6730000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfa6@'\np2850\ntp2851\nRp2852\ng2760\nF10.0\ntp2853\na(I6740000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O6@'\np2854\ntp2855\nRp2856\ng2760\nF15.0\ntp2857\na(I6750000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc5@'\np2858\ntp2859\nRp2860\ng2760\nF54.0\ntp2861\na(I6760000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd5@'\np2862\ntp2863\nRp2864\ng2760\nF0.0\ntp2865\na(I6770000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@5@'\np2866\ntp2867\nRp2868\ng2760\nF11.0\ntp2869\na(I6780000\ng1\n(g5\nS'fffff&5@'\np2870\ntp2871\nRp2872\ng2760\nF33.0\ntp2873\na(I6790000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc4@'\np2874\ntp2875\nRp2876\ng2760\nF0.0\ntp2877\na(I6800000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np2878\ntp2879\nRp2880\ng2760\nF18.0\ntp2881\na(I6810000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x145@'\np2882\ntp2883\nRp2884\ng2760\nF13.0\ntp2885\na(I6820000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW5@'\np2886\ntp2887\nRp2888\ng2760\nF28.0\ntp2889\na(I6830000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x025@'\np2890\ntp2891\nRp2892\ng2760\nF2.0\ntp2893\na(I6840000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1c5@'\np2894\ntp2895\nRp2896\ng2760\nF29.0\ntp2897\na(I6850000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O5@'\np2898\ntp2899\nRp2900\ng2760\nF33.0\ntp2901\na(I6860000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb05@'\np2902\ntp2903\nRp2904\ng2760\nF39.0\ntp2905\na(I6870000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85+6@'\np2906\ntp2907\nRp2908\ng2760\nF28.0\ntp2909\na(I6880000\ng1\n(g5\nS'\\n\\xd7\\xa3p=J6@'\np2910\ntp2911\nRp2912\ng2760\nF41.0\ntp2913\na(I6890000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1c6@'\np2914\ntp2915\nRp2916\ng2760\nF34.0\ntp2917\na(I6900000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c6@'\np2918\ntp2919\nRp2920\ng2760\nF44.0\ntp2921\na(I6910000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb56@'\np2922\ntp2923\nRp2924\ng2760\nF36.0\ntp2925\na(I6920000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd6@'\np2926\ntp2927\nRp2928\ng2760\nF30.0\ntp2929\na(I6930000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc257@'\np2930\ntp2931\nRp2932\ng2760\nF27.0\ntp2933\na(I6940000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p7@'\np2934\ntp2935\nRp2936\ng2760\nF34.0\ntp2937\na(I6950000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y7@'\np2938\ntp2939\nRp2940\ng2760\nF31.0\ntp2941\na(I6960000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf7@'\np2942\ntp2943\nRp2944\ng2760\nF49.0\ntp2945\na(I6970000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n8@'\np2946\ntp2947\nRp2948\ng2760\nF29.0\ntp2949\na(I6980000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc77@'\np2950\ntp2951\nRp2952\ng2760\nF28.0\ntp2953\na(I6990000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xee7@'\np2954\ntp2955\nRp2956\ng2760\nF13.0\ntp2957\na(I7000000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.8@'\np2958\ntp2959\nRp2960\ng2760\nF23.0\ntp2961\na(I7010000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\8@'\np2962\ntp2963\nRp2964\ng2760\nF17.0\ntp2965\na(I7020000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x119@'\np2966\ntp2967\nRp2968\ng2760\nF34.0\ntp2969\na(I7030000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x949@'\np2970\ntp2971\nRp2972\ng2760\nF19.0\ntp2973\na(I7040000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa39@'\np2974\ntp2975\nRp2976\ng2760\nF6.0\ntp2977\na(I7050000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc259@'\np2978\ntp2979\nRp2980\ng2760\nF9.0\ntp2981\na(I7060000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW9@'\np2982\ntp2983\nRp2984\ng2760\nF46.0\ntp2985\na(I7070000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^9@'\np2986\ntp2987\nRp2988\ng2760\nF7.0\ntp2989\na(I7080000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(9@'\np2990\ntp2991\nRp2992\ng2760\nF29.0\ntp2993\na(I7090000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca8@'\np2994\ntp2995\nRp2996\ng2760\nF16.0\ntp2997\na(I7100000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.9@'\np2998\ntp2999\nRp3000\ng2760\nF1.0\ntp3001\na(I7110000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x979@'\np3002\ntp3003\nRp3004\ng2760\nF35.0\ntp3005\na(I7120000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x919@'\np3006\ntp3007\nRp3008\ng2760\nF22.0\ntp3009\na(I7130000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb59@'\np3010\ntp3011\nRp3012\ng2760\nF9.0\ntp3013\na(I7140000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW9@'\np3014\ntp3015\nRp3016\ng2760\nF12.0\ntp3017\na(I7150000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc58@'\np3018\ntp3019\nRp3020\ng2760\nF7.0\ntp3021\na(I7160000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=9@'\np3022\ntp3023\nRp3024\ng2760\nF32.0\ntp3025\na(I7170000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE9@'\np3026\ntp3027\nRp3028\ng2760\nF37.0\ntp3029\na(I7180000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc259@'\np3030\ntp3031\nRp3032\ng2760\nF36.0\ntp3033\na(I7190000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL9@'\np3034\ntp3035\nRp3036\ng2760\nF28.0\ntp3037\na(I7200000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ9@'\np3038\ntp3039\nRp3040\ng2760\nF29.0\ntp3041\na(I7210000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x119@'\np3042\ntp3043\nRp3044\ng2760\nF20.0\ntp3045\na(I7220000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ89@'\np3046\ntp3047\nRp3048\ng2760\nF13.0\ntp3049\na(I7230000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb8@'\np3050\ntp3051\nRp3052\ng2760\nF26.0\ntp3053\na(I7240000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB8@'\np3054\ntp3055\nRp3056\ng2760\nF15.0\ntp3057\na(I7250000\ng1\n(g5\nS'q=\\n\\xd7\\xa308@'\np3058\ntp3059\nRp3060\ng2760\nF6.0\ntp3061\na(I7260000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x877@'\np3062\ntp3063\nRp3064\ng2760\nF1.0\ntp3065\na(I7270000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f7@'\np3066\ntp3067\nRp3068\ng2760\nF15.0\ntp3069\na(I7280000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p7@'\np3070\ntp3071\nRp3072\ng2760\nF32.0\ntp3073\na(I7290000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}6@'\np3074\ntp3075\nRp3076\ng2760\nF13.0\ntp3077\na(I7300000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u6@'\np3078\ntp3079\nRp3080\ng2760\nF27.0\ntp3081\na(I7310000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x856@'\np3082\ntp3083\nRp3084\ng2760\nF31.0\ntp3085\na(I7320000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc256@'\np3086\ntp3087\nRp3088\ng2760\nF13.0\ntp3089\na(I7330000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n6@'\np3090\ntp3091\nRp3092\ng2760\nF31.0\ntp3093\na(I7340000\ng1\n(g5\nS'3333336@'\np3094\ntp3095\nRp3096\ng2760\nF11.0\ntp3097\na(I7350000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f6@'\np3098\ntp3099\nRp3100\ng2760\nF23.0\ntp3101\na(I7360000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}5@'\np3102\ntp3103\nRp3104\ng2760\nF12.0\ntp3105\na(I7370000\ng1\n(g5\nS'\\xa4p=\\n\\xd7c5@'\np3106\ntp3107\nRp3108\ng2760\nF25.0\ntp3109\na(I7380000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a5@'\np3110\ntp3111\nRp3112\ng2760\nF11.0\ntp3113\na(I7390000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x825@'\np3114\ntp3115\nRp3116\ng2760\nF2.0\ntp3117\na(I7400000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG!6@'\np3118\ntp3119\nRp3120\ng2760\nF31.0\ntp3121\na(I7410000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:6@'\np3122\ntp3123\nRp3124\ng2760\nF14.0\ntp3125\na(I7420000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc6@'\np3126\ntp3127\nRp3128\ng2760\nF30.0\ntp3129\na(I7430000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb86@'\np3130\ntp3131\nRp3132\ng2760\nF26.0\ntp3133\na(I7440000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(6@'\np3134\ntp3135\nRp3136\ng2760\nF0.0\ntp3137\na(I7450000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc5@'\np3138\ntp3139\nRp3140\ng2760\nF32.0\ntp3141\na(I7460000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=6@'\np3142\ntp3143\nRp3144\ng2760\nF26.0\ntp3145\na(I7470000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^6@'\np3146\ntp3147\nRp3148\ng2760\nF28.0\ntp3149\na(I7480000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba6@'\np3150\ntp3151\nRp3152\ng2760\nF46.0\ntp3153\na(I7490000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xe36@'\np3154\ntp3155\nRp3156\ng2760\nF22.0\ntp3157\na(I7500000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca6@'\np3158\ntp3159\nRp3160\ng2760\nF19.0\ntp3161\na(I7510000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb06@'\np3162\ntp3163\nRp3164\ng2760\nF36.0\ntp3165\na(I7520000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a6@'\np3166\ntp3167\nRp3168\ng2760\nF20.0\ntp3169\na(I7530000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa6@'\np3170\ntp3171\nRp3172\ng2760\nF39.0\ntp3173\na(I7540000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xe36@'\np3174\ntp3175\nRp3176\ng2760\nF77.0\ntp3177\na(I7550000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd6@'\np3178\ntp3179\nRp3180\ng2760\nF8.0\ntp3181\na(I7560000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf6@'\np3182\ntp3183\nRp3184\ng2760\nF36.0\ntp3185\na(I7570000\ng1\n(g5\nS'q=\\n\\xd7\\xa307@'\np3186\ntp3187\nRp3188\ng2760\nF34.0\ntp3189\na(I7580000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG!7@'\np3190\ntp3191\nRp3192\ng2760\nF23.0\ntp3193\na(I7590000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x877@'\np3194\ntp3195\nRp3196\ng2760\nF12.0\ntp3197\na(I7600000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe87@'\np3198\ntp3199\nRp3200\ng2760\nF48.0\ntp3201\na(I7610000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb87@'\np3202\ntp3203\nRp3204\ng2760\nF13.0\ntp3205\na(I7620000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd77@'\np3206\ntp3207\nRp3208\ng2760\nF16.0\ntp3209\na(I7630000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb87@'\np3210\ntp3211\nRp3212\ng2760\nF3.0\ntp3213\na(I7640000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c7@'\np3214\ntp3215\nRp3216\ng2760\nF25.0\ntp3217\na(I7650000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc27@'\np3218\ntp3219\nRp3220\ng2760\nF15.0\ntp3221\na(I7660000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb7@'\np3222\ntp3223\nRp3224\ng2760\nF18.0\ntp3225\na(I7670000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfa7@'\np3226\ntp3227\nRp3228\ng2760\nF34.0\ntp3229\na(I7680000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf88@'\np3230\ntp3231\nRp3232\ng2760\nF10.0\ntp3233\na(I7690000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z9@'\np3234\ntp3235\nRp3236\ng2760\nF26.0\ntp3237\na(I7700000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xee9@'\np3238\ntp3239\nRp3240\ng2760\nF29.0\ntp3241\na(I7710000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf09@'\np3242\ntp3243\nRp3244\ng2760\nF24.0\ntp3245\na(I7720000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf89@'\np3246\ntp3247\nRp3248\ng2760\nF27.0\ntp3249\na(I7730000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc25:@'\np3250\ntp3251\nRp3252\ng2760\nF25.0\ntp3253\na(I7740000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k:@'\np3254\ntp3255\nRp3256\ng2760\nF30.0\ntp3257\na(I7750000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85+:@'\np3258\ntp3259\nRp3260\ng2760\nF31.0\ntp3261\na(I7760000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd4:@'\np3262\ntp3263\nRp3264\ng2760\nF29.0\ntp3265\na(I7770000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc5:@'\np3266\ntp3267\nRp3268\ng2760\nF31.0\ntp3269\na(I7780000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB;@'\np3270\ntp3271\nRp3272\ng2760\nF3.0\ntp3273\na(I7790000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x02;@'\np3274\ntp3275\nRp3276\ng2760\nF22.0\ntp3277\na(I7800000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:;@'\np3278\ntp3279\nRp3280\ng2760\nF35.0\ntp3281\na(I7810000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x11;@'\np3282\ntp3283\nRp3284\ng2760\nF14.0\ntp3285\na(I7820000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00;@'\np3286\ntp3287\nRp3288\ng2760\nF44.0\ntp3289\na(I7830000\ng1\n(g5\nS'333333;@'\np3290\ntp3291\nRp3292\ng2760\nF5.0\ntp3293\na(I7840000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z;@'\np3294\ntp3295\nRp3296\ng2760\nF8.0\ntp3297\na(I7850000\ng1\n(g5\nS'33333\\xb3;@'\np3298\ntp3299\nRp3300\ng2760\nF32.0\ntp3301\na(I7860000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc25<@'\np3302\ntp3303\nRp3304\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc25<@'\np3305\ntp3306\nRp3307\nF23.0\ntp3308\na(I7870000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfa;@'\np3309\ntp3310\nRp3311\ng3307\nF14.0\ntp3312\na(I7880000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zT;@'\np3313\ntp3314\nRp3315\ng3307\nF14.0\ntp3316\na(I7890000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1;@'\np3317\ntp3318\nRp3319\ng3307\nF29.0\ntp3320\na(I7900000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xee;@'\np3321\ntp3322\nRp3323\ng3307\nF40.0\ntp3324\na(I7910000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf8;@'\np3325\ntp3326\nRp3327\ng3307\nF17.0\ntp3328\na(I7920000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf8;@'\np3329\ntp3330\nRp3331\ng3307\nF29.0\ntp3332\na(I7930000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf8;@'\np3333\ntp3334\nRp3335\ng3307\nF5.0\ntp3336\na(I7940000\ng1\n(g5\nS'333333;@'\np3337\ntp3338\nRp3339\ng3307\nF12.0\ntp3340\na(I7950000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd1;@'\np3341\ntp3342\nRp3343\ng3307\nF39.0\ntp3344\na(I7960000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xd9;@'\np3345\ntp3346\nRp3347\ng3307\nF3.0\ntp3348\na(I7970000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde<@'\np3349\ntp3350\nRp3351\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde<@'\np3352\ntp3353\nRp3354\nF93.0\ntp3355\na(I7980000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x02=@'\np3356\ntp3357\nRp3358\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x02=@'\np3359\ntp3360\nRp3361\nF35.0\ntp3362\na(I7990000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x17=@'\np3363\ntp3364\nRp3365\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x17=@'\np3366\ntp3367\nRp3368\nF36.0\ntp3369\na(I8000000\ng1\n(g5\nS'fffff&=@'\np3370\ntp3371\nRp3372\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc25=@'\np3373\ntp3374\nRp3375\nF55.0\ntp3376\na(I8010000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8;@'\np3377\ntp3378\nRp3379\ng3375\nF16.0\ntp3380\na(I8020000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba;@'\np3381\ntp3382\nRp3383\ng3375\nF45.0\ntp3384\na(I8030000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x11<@'\np3385\ntp3386\nRp3387\ng3375\nF52.0\ntp3388\na(I8040000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x80;@'\np3389\ntp3390\nRp3391\ng3375\nF11.0\ntp3392\na(I8050000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f;@'\np3393\ntp3394\nRp3395\ng3375\nF45.0\ntp3396\na(I8060000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n;@'\np3397\ntp3398\nRp3399\ng3375\nF29.0\ntp3400\na(I8070000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae;@'\np3401\ntp3402\nRp3403\ng3375\nF41.0\ntp3404\na(I8080000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x87;@'\np3405\ntp3406\nRp3407\ng3375\nF16.0\ntp3408\na(I8090000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x11;@'\np3409\ntp3410\nRp3411\ng3375\nF11.0\ntp3412\na(I8100000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x94;@'\np3413\ntp3414\nRp3415\ng3375\nF46.0\ntp3416\na(I8110000\ng1\n(g5\nS'ffffff;@'\np3417\ntp3418\nRp3419\ng3375\nF13.0\ntp3420\na(I8120000\ng1\n(g5\nS'=\\n\\xd7\\xa3p};@'\np3421\ntp3422\nRp3423\ng3375\nF29.0\ntp3424\na(I8130000\ng1\n(g5\nS'fffff&;@'\np3425\ntp3426\nRp3427\ng3375\nF38.0\ntp3428\na(I8140000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfa:@'\np3429\ntp3430\nRp3431\ng3375\nF38.0\ntp3432\na(I8150000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe8:@'\np3433\ntp3434\nRp3435\ng3375\nF32.0\ntp3436\na(I8160000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xd9:@'\np3437\ntp3438\nRp3439\ng3375\nF25.0\ntp3440\na(I8170000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8:@'\np3441\ntp3442\nRp3443\ng3375\nF29.0\ntp3444\na(I8180000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3:@'\np3445\ntp3446\nRp3447\ng3375\nF66.0\ntp3448\na(I8190000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zT:@'\np3449\ntp3450\nRp3451\ng3375\nF20.0\ntp3452\na(I8200000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f;@'\np3453\ntp3454\nRp3455\ng3375\nF40.0\ntp3456\na(I8210000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5:@'\np3457\ntp3458\nRp3459\ng3375\nF9.0\ntp3460\na(I8220000\ng1\n(g5\nS'ffffff:@'\np3461\ntp3462\nRp3463\ng3375\nF8.0\ntp3464\na(I8230000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y:@'\np3465\ntp3466\nRp3467\ng3375\nF30.0\ntp3468\na(I8240000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n:@'\np3469\ntp3470\nRp3471\ng3375\nF13.0\ntp3472\na(I8250000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85:@'\np3473\ntp3474\nRp3475\ng3375\nF84.0\ntp3476\na(I8260000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc:@'\np3477\ntp3478\nRp3479\ng3375\nF42.0\ntp3480\na(I8270000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x02;@'\np3481\ntp3482\nRp3483\ng3375\nF9.0\ntp3484\na(I8280000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae:@'\np3485\ntp3486\nRp3487\ng3375\nF24.0\ntp3488\na(I8290000\ng1\n(g5\nS'33333\\xb3:@'\np3489\ntp3490\nRp3491\ng3375\nF14.0\ntp3492\na(I8300000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf09@'\np3493\ntp3494\nRp3495\ng3375\nF31.0\ntp3496\na(I8310000\ng1\n(g5\nS'fffff&:@'\np3497\ntp3498\nRp3499\ng3375\nF52.0\ntp3500\na(I8320000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^:@'\np3501\ntp3502\nRp3503\ng3375\nF27.0\ntp3504\na(I8330000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f:@'\np3505\ntp3506\nRp3507\ng3375\nF38.0\ntp3508\na(I8340000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd1:@'\np3509\ntp3510\nRp3511\ng3375\nF14.0\ntp3512\na(I8350000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab:@'\np3513\ntp3514\nRp3515\ng3375\nF8.0\ntp3516\na(I8360000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zT:@'\np3517\ntp3518\nRp3519\ng3375\nF41.0\ntp3520\na(I8370000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c:@'\np3521\ntp3522\nRp3523\ng3375\nF18.0\ntp3524\na(I8380000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx:@'\np3525\ntp3526\nRp3527\ng3375\nF14.0\ntp3528\na(I8390000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x07:@'\np3529\ntp3530\nRp3531\ng3375\nF8.0\ntp3532\na(I8400000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c9@'\np3533\ntp3534\nRp3535\ng3375\nF3.0\ntp3536\na(I8410000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG:@'\np3537\ntp3538\nRp3539\ng3375\nF92.0\ntp3540\na(I8420000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99:@'\np3541\ntp3542\nRp3543\ng3375\nF39.0\ntp3544\na(I8430000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f:@'\np3545\ntp3546\nRp3547\ng3375\nF7.0\ntp3548\na(I8440000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfa9@'\np3549\ntp3550\nRp3551\ng3375\nF8.0\ntp3552\na(I8450000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf89@'\np3553\ntp3554\nRp3555\ng3375\nF16.0\ntp3556\na(I8460000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00:@'\np3557\ntp3558\nRp3559\ng3375\nF23.0\ntp3560\na(I8470000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae9@'\np3561\ntp3562\nRp3563\ng3375\nF21.0\ntp3564\na(I8480000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x809@'\np3565\ntp3566\nRp3567\ng3375\nF0.0\ntp3568\na(I8490000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx9@'\np3569\ntp3570\nRp3571\ng3375\nF21.0\ntp3572\na(I8500000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde9@'\np3573\ntp3574\nRp3575\ng3375\nF43.0\ntp3576\na(I8510000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc79@'\np3577\ntp3578\nRp3579\ng3375\nF20.0\ntp3580\na(I8520000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd49@'\np3581\ntp3582\nRp3583\ng3375\nF55.0\ntp3584\na(I8530000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb9@'\np3585\ntp3586\nRp3587\ng3375\nF37.0\ntp3588\na(I8540000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab9@'\np3589\ntp3590\nRp3591\ng3375\nF16.0\ntp3592\na(I8550000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u:@'\np3593\ntp3594\nRp3595\ng3375\nF1.0\ntp3596\na(I8560000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd49@'\np3597\ntp3598\nRp3599\ng3375\nF5.0\ntp3600\na(I8570000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O:@'\np3601\ntp3602\nRp3603\ng3375\nF76.0\ntp3604\na(I8580000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.:@'\np3605\ntp3606\nRp3607\ng3375\nF37.0\ntp3608\na(I8590000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x999@'\np3609\ntp3610\nRp3611\ng3375\nF22.0\ntp3612\na(I8600000\ng1\n(g5\nS'fffff\\xa69@'\np3613\ntp3614\nRp3615\ng3375\nF23.0\ntp3616\na(I8610000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf09@'\np3617\ntp3618\nRp3619\ng3375\nF25.0\ntp3620\na(I8620000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa:@'\np3621\ntp3622\nRp3623\ng3375\nF42.0\ntp3624\na(I8630000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb:@'\np3625\ntp3626\nRp3627\ng3375\nF25.0\ntp3628\na(I8640000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd4:@'\np3629\ntp3630\nRp3631\ng3375\nF10.0\ntp3632\na(I8650000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85:@'\np3633\ntp3634\nRp3635\ng3375\nF38.0\ntp3636\na(I8660000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y:@'\np3637\ntp3638\nRp3639\ng3375\nF29.0\ntp3640\na(I8670000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8:@'\np3641\ntp3642\nRp3643\ng3375\nF48.0\ntp3644\na(I8680000\ng1\n(g5\nS'33333s:@'\np3645\ntp3646\nRp3647\ng3375\nF9.0\ntp3648\na(I8690000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3:@'\np3649\ntp3650\nRp3651\ng3375\nF1.0\ntp3652\na(I8700000\ng1\n(g5\nS'33333\\xb3:@'\np3653\ntp3654\nRp3655\ng3375\nF22.0\ntp3656\na(I8710000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfd9@'\np3657\ntp3658\nRp3659\ng3375\nF10.0\ntp3660\na(I8720000\ng1\n(g5\nS'fffff\\xa6:@'\np3661\ntp3662\nRp3663\ng3375\nF24.0\ntp3664\na(I8730000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde:@'\np3665\ntp3666\nRp3667\ng3375\nF30.0\ntp3668\na(I8740000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc0;@'\np3669\ntp3670\nRp3671\ng3375\nF24.0\ntp3672\na(I8750000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xee:@'\np3673\ntp3674\nRp3675\ng3375\nF20.0\ntp3676\na(I8760000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x19;@'\np3677\ntp3678\nRp3679\ng3375\nF27.0\ntp3680\na(I8770000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc:@'\np3681\ntp3682\nRp3683\ng3375\nF37.0\ntp3684\na(I8780000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB;@'\np3685\ntp3686\nRp3687\ng3375\nF39.0\ntp3688\na(I8790000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL;@'\np3689\ntp3690\nRp3691\ng3375\nF25.0\ntp3692\na(I8800000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba;@'\np3693\ntp3694\nRp3695\ng3375\nF29.0\ntp3696\na(I8810000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2;@'\np3697\ntp3698\nRp3699\ng3375\nF7.0\ntp3700\na(I8820000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x02<@'\np3701\ntp3702\nRp3703\ng3375\nF15.0\ntp3704\na(I8830000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc5;@'\np3705\ntp3706\nRp3707\ng3375\nF26.0\ntp3708\na(I8840000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG;@'\np3709\ntp3710\nRp3711\ng3375\nF21.0\ntp3712\na(I8850000\ng1\n(g5\nS'ffffff;@'\np3713\ntp3714\nRp3715\ng3375\nF43.0\ntp3716\na(I8860000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb5:@'\np3717\ntp3718\nRp3719\ng3375\nF16.0\ntp3720\na(I8870000\ng1\n(g5\nS'ffffff:@'\np3721\ntp3722\nRp3723\ng3375\nF28.0\ntp3724\na(I8880000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb89@'\np3725\ntp3726\nRp3727\ng3375\nF12.0\ntp3728\na(I8890000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x91:@'\np3729\ntp3730\nRp3731\ng3375\nF17.0\ntp3732\na(I8900000\ng1\n(g5\nS'fffff\\xa6:@'\np3733\ntp3734\nRp3735\ng3375\nF18.0\ntp3736\na(I8910000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x97:@'\np3737\ntp3738\nRp3739\ng3375\nF30.0\ntp3740\na(I8920000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7:@'\np3741\ntp3742\nRp3743\ng3375\nF14.0\ntp3744\na(I8930000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14;@'\np3745\ntp3746\nRp3747\ng3375\nF38.0\ntp3748\na(I8940000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG!;@'\np3749\ntp3750\nRp3751\ng3375\nF30.0\ntp3752\na(I8950000\ng1\n(g5\nS'\\n\\xd7\\xa3p=J;@'\np3753\ntp3754\nRp3755\ng3375\nF41.0\ntp3756\na(I8960000\ng1\n(g5\nS'q=\\n\\xd7\\xa30;@'\np3757\ntp3758\nRp3759\ng3375\nF38.0\ntp3760\na(I8970000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z;@'\np3761\ntp3762\nRp3763\ng3375\nF43.0\ntp3764\na(I8980000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O;@'\np3765\ntp3766\nRp3767\ng3375\nF26.0\ntp3768\na(I8990000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfd:@'\np3769\ntp3770\nRp3771\ng3375\nF18.0\ntp3772\na(I9000000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x07;@'\np3773\ntp3774\nRp3775\ng3375\nF36.0\ntp3776\na(I9010000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf:@'\np3777\ntp3778\nRp3779\ng3375\nF36.0\ntp3780\na(I9020000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xee:@'\np3781\ntp3782\nRp3783\ng3375\nF18.0\ntp3784\na(I9030000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e;@'\np3785\ntp3786\nRp3787\ng3375\nF21.0\ntp3788\na(I9040000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8;@'\np3789\ntp3790\nRp3791\ng3375\nF17.0\ntp3792\na(I9050000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\;@'\np3793\ntp3794\nRp3795\ng3375\nF44.0\ntp3796\na(I9060000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=;@'\np3797\ntp3798\nRp3799\ng3375\nF33.0\ntp3800\na(I9070000\ng1\n(g5\nS'ffffff:@'\np3801\ntp3802\nRp3803\ng3375\nF28.0\ntp3804\na(I9080000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8:@'\np3805\ntp3806\nRp3807\ng3375\nF16.0\ntp3808\na(I9090000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u:@'\np3809\ntp3810\nRp3811\ng3375\nF18.0\ntp3812\na(I9100000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5:@'\np3813\ntp3814\nRp3815\ng3375\nF33.0\ntp3816\na(I9110000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb0:@'\np3817\ntp3818\nRp3819\ng3375\nF29.0\ntp3820\na(I9120000\ng1\n(g5\nS'ffffff:@'\np3821\ntp3822\nRp3823\ng3375\nF23.0\ntp3824\na(I9130000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx:@'\np3825\ntp3826\nRp3827\ng3375\nF30.0\ntp3828\na(I9140000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x02:@'\np3829\ntp3830\nRp3831\ng3375\nF28.0\ntp3832\na(I9150000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf89@'\np3833\ntp3834\nRp3835\ng3375\nF26.0\ntp3836\na(I9160000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe89@'\np3837\ntp3838\nRp3839\ng3375\nF3.0\ntp3840\na(I9170000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb0:@'\np3841\ntp3842\nRp3843\ng3375\nF54.0\ntp3844\na(I9180000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab:@'\np3845\ntp3846\nRp3847\ng3375\nF20.0\ntp3848\na(I9190000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde:@'\np3849\ntp3850\nRp3851\ng3375\nF30.0\ntp3852\na(I9200000\ng1\n(g5\nS'33333\\xf3:@'\np3853\ntp3854\nRp3855\ng3375\nF28.0\ntp3856\na(I9210000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe8:@'\np3857\ntp3858\nRp3859\ng3375\nF27.0\ntp3860\na(I9220000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc7:@'\np3861\ntp3862\nRp3863\ng3375\nF33.0\ntp3864\na(I9230000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae:@'\np3865\ntp3866\nRp3867\ng3375\nF17.0\ntp3868\na(I9240000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k:@'\np3869\ntp3870\nRp3871\ng3375\nF30.0\ntp3872\na(I9250000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85+:@'\np3873\ntp3874\nRp3875\ng3375\nF29.0\ntp3876\na(I9260000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca9@'\np3877\ntp3878\nRp3879\ng3375\nF6.0\ntp3880\na(I9270000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}9@'\np3881\ntp3882\nRp3883\ng3375\nF15.0\ntp3884\na(I9280000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG!9@'\np3885\ntp3886\nRp3887\ng3375\nF9.0\ntp3888\na(I9290000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x828@'\np3889\ntp3890\nRp3891\ng3375\nF9.0\ntp3892\na(I9300000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x008@'\np3893\ntp3894\nRp3895\ng3375\nF23.0\ntp3896\na(I9310000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc258@'\np3897\ntp3898\nRp3899\ng3375\nF19.0\ntp3900\na(I9320000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW8@'\np3901\ntp3902\nRp3903\ng3375\nF1.0\ntp3904\na(I9330000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x178@'\np3905\ntp3906\nRp3907\ng3375\nF26.0\ntp3908\na(I9340000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfd7@'\np3909\ntp3910\nRp3911\ng3375\nF14.0\ntp3912\na(I9350000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^7@'\np3913\ntp3914\nRp3915\ng3375\nF6.0\ntp3916\na(I9360000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ7@'\np3917\ntp3918\nRp3919\ng3375\nF29.0\ntp3920\na(I9370000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc57@'\np3921\ntp3922\nRp3923\ng3375\nF50.0\ntp3924\na(I9380000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc7@'\np3925\ntp3926\nRp3927\ng3375\nF3.0\ntp3928\na(I9390000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb07@'\np3929\ntp3930\nRp3931\ng3375\nF34.0\ntp3932\na(I9400000\ng1\n(g5\nS'33333\\xf37@'\np3933\ntp3934\nRp3935\ng3375\nF31.0\ntp3936\na(I9410000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc27@'\np3937\ntp3938\nRp3939\ng3375\nF25.0\ntp3940\na(I9420000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f8@'\np3941\ntp3942\nRp3943\ng3375\nF33.0\ntp3944\na(I9430000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f8@'\np3945\ntp3946\nRp3947\ng3375\nF27.0\ntp3948\na(I9440000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde7@'\np3949\ntp3950\nRp3951\ng3375\nF26.0\ntp3952\na(I9450000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85+8@'\np3953\ntp3954\nRp3955\ng3375\nF12.0\ntp3956\na(I9460000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zT8@'\np3957\ntp3958\nRp3959\ng3375\nF35.0\ntp3960\na(I9470000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x828@'\np3961\ntp3962\nRp3963\ng3375\nF32.0\ntp3964\na(I9480000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x948@'\np3965\ntp3966\nRp3967\ng3375\nF23.0\ntp3968\na(I9490000\ng1\n(g5\nS'33333\\xb38@'\np3969\ntp3970\nRp3971\ng3375\nF35.0\ntp3972\na(I9500000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xe38@'\np3973\ntp3974\nRp3975\ng3375\nF31.0\ntp3976\na(I9510000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x198@'\np3977\ntp3978\nRp3979\ng3375\nF0.0\ntp3980\na(I9520000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:8@'\np3981\ntp3982\nRp3983\ng3375\nF46.0\ntp3984\na(I9530000\ng1\n(g5\nS'q=\\n\\xd7\\xa308@'\np3985\ntp3986\nRp3987\ng3375\nF15.0\ntp3988\na(I9540000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd77@'\np3989\ntp3990\nRp3991\ng3375\nF8.0\ntp3992\na(I9550000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xe37@'\np3993\ntp3994\nRp3995\ng3375\nF31.0\ntp3996\na(I9560000\ng1\n(g5\nS'\\xa4p=\\n\\xd7c8@'\np3997\ntp3998\nRp3999\ng3375\nF37.0\ntp4000\na(I9570000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a8@'\np4001\ntp4002\nRp4003\ng3375\nF4.0\ntp4004\na(I9580000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa18@'\np4005\ntp4006\nRp4007\ng3375\nF38.0\ntp4008\na(I9590000\ng1\n(g5\nS'fffff\\xa68@'\np4009\ntp4010\nRp4011\ng3375\nF26.0\ntp4012\na(I9600000\ng1\n(g5\nS'33333\\xf38@'\np4013\ntp4014\nRp4015\ng3375\nF20.0\ntp4016\na(I9610000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x878@'\np4017\ntp4018\nRp4019\ng3375\nF24.0\ntp4020\na(I9620000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}8@'\np4021\ntp4022\nRp4023\ng3375\nF0.0\ntp4024\na(I9630000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x878@'\np4025\ntp4026\nRp4027\ng3375\nF0.0\ntp4028\na(I9640000\ng1\n(g5\nS'33333s8@'\np4029\ntp4030\nRp4031\ng3375\nF50.0\ntp4032\na(I9650000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h8@'\np4033\ntp4034\nRp4035\ng3375\nF24.0\ntp4036\na(I9660000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW8@'\np4037\ntp4038\nRp4039\ng3375\nF9.0\ntp4040\na(I9670000\ng1\n(g5\nS'fffff\\xe67@'\np4041\ntp4042\nRp4043\ng3375\nF24.0\ntp4044\na(I9680000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u8@'\np4045\ntp4046\nRp4047\ng3375\nF40.0\ntp4048\na(I9690000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde8@'\np4049\ntp4050\nRp4051\ng3375\nF33.0\ntp4052\na(I9700000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf8@'\np4053\ntp4054\nRp4055\ng3375\nF32.0\ntp4056\na(I9710000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc08@'\np4057\ntp4058\nRp4059\ng3375\nF32.0\ntp4060\na(I9720000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}8@'\np4061\ntp4062\nRp4063\ng3375\nF23.0\ntp4064\na(I9730000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ88@'\np4065\ntp4066\nRp4067\ng3375\nF14.0\ntp4068\na(I9740000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc258@'\np4069\ntp4070\nRp4071\ng3375\nF21.0\ntp4072\na(I9750000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h8@'\np4073\ntp4074\nRp4075\ng3375\nF36.0\ntp4076\na(I9760000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd77@'\np4077\ntp4078\nRp4079\ng3375\nF7.0\ntp4080\na(I9770000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb57@'\np4081\ntp4082\nRp4083\ng3375\nF22.0\ntp4084\na(I9780000\ng1\n(g5\nS'33333s7@'\np4085\ntp4086\nRp4087\ng3375\nF14.0\ntp4088\na(I9790000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ87@'\np4089\ntp4090\nRp4091\ng3375\nF1.0\ntp4092\na(I9800000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n7@'\np4093\ntp4094\nRp4095\ng3375\nF17.0\ntp4096\na(I9810000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca6@'\np4097\ntp4098\nRp4099\ng3375\nF24.0\ntp4100\na(I9820000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^7@'\np4101\ntp4102\nRp4103\ng3375\nF40.0\ntp4104\na(I9830000\ng1\n(g5\nS'fffff&7@'\np4105\ntp4106\nRp4107\ng3375\nF26.0\ntp4108\na(I9840000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c6@'\np4109\ntp4110\nRp4111\ng3375\nF0.0\ntp4112\na(I9850000\ng1\n(g5\nS'ffffff6@'\np4113\ntp4114\nRp4115\ng3375\nF18.0\ntp4116\na(I9860000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc55@'\np4117\ntp4118\nRp4119\ng3375\nF0.0\ntp4120\na(I9870000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd5@'\np4121\ntp4122\nRp4123\ng3375\nF22.0\ntp4124\na(I9880000\ng1\n(g5\nS'ffffff6@'\np4125\ntp4126\nRp4127\ng3375\nF26.0\ntp4128\na(I9890000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe15@'\np4129\ntp4130\nRp4131\ng3375\nF24.0\ntp4132\na(I9900000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x115@'\np4133\ntp4134\nRp4135\ng3375\nF14.0\ntp4136\na(I9910000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O5@'\np4137\ntp4138\nRp4139\ng3375\nF18.0\ntp4140\na(I9920000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xd94@'\np4141\ntp4142\nRp4143\ng3375\nF18.0\ntp4144\na(I9930000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u4@'\np4145\ntp4146\nRp4147\ng3375\nF19.0\ntp4148\na(I9940000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np4149\ntp4150\nRp4151\ng3375\nF29.0\ntp4152\na(I9950000\ng1\n(g5\nS'fffff\\xe64@'\np4153\ntp4154\nRp4155\ng3375\nF36.0\ntp4156\na(I9960000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x195@'\np4157\ntp4158\nRp4159\ng3375\nF38.0\ntp4160\na(I9970000\ng1\n(g5\nS'33333s5@'\np4161\ntp4162\nRp4163\ng3375\nF5.0\ntp4164\na(I9980000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np4165\ntp4166\nRp4167\ng3375\nF5.0\ntp4168\na(I9983323\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n4@'\np4169\ntp4170\nRp4171\ng3375\nF0.0\ntp4172\na.(lp0\nF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF4.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF5.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF3.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF4.0\naF0.0\naF0.0\naF5.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF5.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF1.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF2.0\naF0.0\naF5.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF18.0\naF42.0\naF26.0\naF28.0\naF25.0\naF6.0\naF15.0\naF21.0\naF34.0\naF19.0\naF29.0\naF35.0\naF37.0\naF30.0\naF7.0\naF38.0\naF26.0\naF41.0\naF24.0\naF31.0\naF24.0\naF39.0\naF12.0\naF31.0\naF38.0\naF38.0\naF19.0\naF28.0\naF39.0\naF20.0\naF1.0\naF18.0\naF34.0\naF28.0\naF41.0\naF23.0\naF33.0\naF5.0\naF14.0\naF24.0\naF32.0\naF45.0\naF40.0\naF26.0\naF88.0\naF30.0\naF41.0\naF49.0\naF33.0\naF30.0\naF15.0\naF7.0\naF26.0\naF25.0\naF20.0\naF19.0\naF23.0\naF37.0\naF21.0\naF32.0\naF1.0\naF45.0\naF20.0\naF23.0\naF10.0\naF29.0\naF43.0\naF18.0\naF0.0\naF23.0\naF36.0\naF33.0\naF6.0\naF25.0\naF40.0\naF33.0\naF7.0\naF32.0\naF20.0\naF0.0\naF27.0\naF28.0\naF26.0\naF14.0\naF15.0\naF34.0\naF4.0\naF28.0\naF32.0\naF10.0\naF31.0\naF6.0\naF38.0\naF13.0\naF29.0\naF15.0\naF38.0\naF27.0\naF5.0\naF22.0\naF25.0\naF43.0\naF28.0\naF31.0\naF11.0\naF23.0\naF43.0\naF14.0\naF40.0\naF18.0\naF30.0\naF46.0\naF6.0\naF25.0\naF37.0\naF35.0\naF16.0\naF48.0\naF22.0\naF39.0\naF14.0\naF10.0\naF7.0\naF29.0\naF31.0\naF19.0\naF12.0\naF23.0\naF23.0\naF3.0\naF48.0\naF25.0\naF28.0\naF4.0\naF1.0\naF28.0\naF20.0\naF13.0\naF6.0\naF35.0\naF18.0\naF11.0\naF30.0\naF37.0\naF34.0\naF37.0\naF36.0\naF27.0\naF13.0\naF13.0\naF14.0\naF52.0\naF34.0\naF29.0\naF27.0\naF33.0\naF27.0\naF34.0\naF27.0\naF8.0\naF16.0\naF22.0\naF21.0\naF28.0\naF19.0\naF9.0\naF41.0\naF33.0\naF34.0\naF52.0\naF11.0\naF0.0\naF0.0\naF34.0\naF25.0\naF36.0\naF13.0\naF35.0\naF25.0\naF36.0\naF26.0\naF31.0\naF29.0\naF38.0\naF21.0\naF22.0\naF9.0\naF0.0\naF4.0\naF17.0\naF27.0\naF20.0\naF12.0\naF17.0\naF26.0\naF29.0\naF40.0\naF2.0\naF27.0\naF33.0\naF25.0\naF21.0\naF38.0\naF36.0\naF41.0\naF32.0\naF11.0\naF4.0\naF38.0\naF34.0\naF6.0\naF28.0\naF41.0\naF10.0\naF18.0\naF32.0\naF15.0\naF13.0\naF34.0\naF14.0\naF0.0\naF3.0\naF10.0\naF18.0\naF28.0\naF0.0\naF0.0\naF42.0\naF37.0\naF20.0\naF32.0\naF27.0\naF8.0\naF7.0\naF23.0\naF11.0\naF38.0\naF30.0\naF31.0\naF28.0\naF15.0\naF6.0\naF33.0\naF40.0\naF11.0\naF32.0\naF14.0\naF27.0\naF44.0\naF5.0\naF0.0\naF6.0\naF19.0\naF32.0\naF21.0\naF10.0\naF25.0\naF25.0\naF51.0\naF3.0\naF38.0\naF27.0\naF39.0\naF37.0\naF2.0\naF10.0\naF28.0\naF15.0\naF12.0\naF33.0\naF1.0\naF41.0\naF31.0\naF6.0\naF28.0\naF3.0\naF39.0\naF22.0\naF23.0\naF0.0\naF0.0\naF0.0\naF7.0\naF18.0\naF11.0\naF33.0\naF5.0\naF33.0\naF4.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF0.0\naF15.0\naF38.0\naF35.0\naF36.0\naF4.0\naF21.0\naF8.0\naF27.0\naF9.0\naF0.0\naF12.0\naF23.0\naF47.0\naF30.0\naF35.0\naF18.0\naF17.0\naF31.0\naF35.0\naF4.0\naF0.0\naF0.0\naF0.0\naF4.0\naF34.0\naF15.0\naF14.0\naF30.0\naF40.0\naF16.0\naF40.0\naF50.0\naF39.0\naF49.0\naF28.0\naF24.0\naF31.0\naF47.0\naF35.0\naF18.0\naF36.0\naF36.0\naF32.0\naF0.0\naF32.0\naF13.0\naF25.0\naF42.0\naF28.0\naF28.0\naF45.0\naF28.0\naF21.0\naF19.0\naF24.0\naF15.0\naF36.0\naF7.0\naF26.0\naF33.0\naF10.0\naF26.0\naF0.0\naF27.0\naF34.0\naF36.0\naF35.0\naF24.0\naF30.0\naF14.0\naF21.0\naF41.0\naF37.0\naF3.0\naF46.0\naF31.0\naF19.0\naF24.0\naF7.0\naF23.0\naF26.0\naF48.0\naF44.0\naF30.0\naF10.0\naF13.0\naF30.0\naF16.0\naF45.0\naF40.0\naF29.0\naF13.0\naF8.0\naF29.0\naF25.0\naF26.0\naF46.0\naF26.0\naF22.0\naF14.0\naF32.0\naF27.0\naF4.0\naF47.0\naF32.0\naF33.0\naF5.0\naF19.0\naF37.0\naF39.0\naF28.0\naF17.0\naF32.0\naF17.0\naF25.0\naF20.0\naF24.0\naF28.0\naF29.0\naF8.0\naF27.0\naF33.0\naF24.0\naF7.0\naF30.0\naF21.0\naF15.0\naF25.0\naF43.0\naF23.0\naF25.0\naF13.0\naF7.0\naF40.0\naF16.0\naF49.0\naF33.0\naF27.0\naF29.0\naF3.0\naF20.0\naF25.0\naF0.0\naF43.0\naF22.0\naF44.0\naF35.0\naF23.0\naF22.0\naF43.0\naF30.0\naF24.0\naF18.0\naF17.0\naF41.0\naF46.0\naF33.0\naF25.0\naF34.0\naF17.0\naF24.0\naF26.0\naF6.0\naF45.0\naF63.0\naF29.0\naF0.0\naF32.0\naF19.0\naF21.0\naF32.0\naF33.0\naF24.0\naF20.0\naF12.0\naF44.0\naF25.0\naF9.0\naF16.0\naF7.0\naF25.0\naF17.0\naF8.0\naF64.0\naF40.0\naF31.0\naF41.0\naF22.0\naF9.0\naF29.0\naF18.0\naF25.0\naF71.0\naF28.0\naF49.0\naF42.0\naF22.0\naF34.0\naF17.0\naF14.0\naF0.0\naF25.0\naF35.0\naF14.0\naF27.0\naF34.0\naF25.0\naF48.0\naF16.0\naF28.0\naF31.0\naF47.0\naF5.0\naF53.0\naF41.0\naF9.0\naF28.0\naF49.0\naF16.0\naF51.0\naF32.0\naF78.0\naF26.0\naF21.0\naF8.0\naF22.0\naF21.0\naF17.0\naF19.0\naF29.0\naF25.0\naF24.0\naF25.0\naF27.0\naF16.0\naF30.0\naF27.0\naF33.0\naF18.0\naF30.0\naF32.0\naF22.0\naF28.0\naF40.0\naF29.0\naF14.0\naF21.0\naF31.0\naF21.0\naF36.0\naF12.0\naF17.0\naF37.0\naF0.0\naF4.0\naF5.0\naF12.0\naF8.0\naF45.0\naF22.0\naF2.0\naF31.0\naF30.0\naF25.0\naF23.0\naF18.0\naF23.0\naF43.0\naF34.0\naF13.0\naF30.0\naF20.0\naF33.0\naF24.0\naF9.0\naF19.0\naF31.0\naF28.0\naF23.0\naF22.0\naF26.0\naF21.0\naF2.0\naF42.0\naF24.0\naF3.0\naF4.0\naF5.0\naF48.0\naF40.0\naF50.0\naF6.0\naF11.0\naF29.0\naF27.0\naF33.0\naF14.0\naF27.0\naF1.0\naF7.0\naF0.0\naF1.0\naF0.0\naF11.0\naF25.0\naF6.0\naF25.0\naF17.0\naF18.0\naF27.0\naF33.0\naF45.0\naF27.0\naF18.0\naF26.0\naF10.0\naF5.0\naF6.0\naF15.0\naF13.0\naF49.0\naF54.0\naF2.0\naF41.0\naF0.0\naF0.0\naF0.0\naF11.0\naF25.0\naF5.0\naF33.0\naF38.0\naF9.0\naF0.0\naF17.0\naF29.0\naF18.0\naF56.0\naF43.0\naF13.0\naF45.0\naF35.0\naF28.0\naF21.0\naF27.0\naF2.0\naF21.0\naF33.0\naF29.0\naF32.0\naF20.0\naF33.0\naF7.0\naF33.0\naF39.0\naF28.0\naF17.0\naF28.0\naF7.0\naF33.0\naF41.0\naF20.0\naF14.0\naF34.0\naF22.0\naF42.0\naF44.0\naF45.0\naF25.0\naF36.0\naF36.0\naF20.0\naF30.0\naF33.0\naF39.0\naF27.0\naF47.0\naF24.0\naF34.0\naF28.0\naF1.0\naF31.0\naF33.0\naF32.0\naF49.0\naF11.0\naF34.0\naF29.0\naF28.0\naF17.0\naF28.0\naF14.0\naF34.0\naF13.0\naF26.0\naF50.0\naF23.0\naF22.0\naF14.0\naF17.0\naF16.0\naF22.0\naF34.0\naF38.0\naF36.0\naF19.0\naF27.0\naF33.0\naF6.0\naF35.0\naF18.0\naF9.0\naF19.0\naF19.0\naF46.0\naF4.0\naF13.0\naF7.0\naF18.0\naF9.0\naF29.0\naF21.0\naF23.0\naF16.0\naF6.0\naF32.0\naF1.0\naF16.0\naF31.0\naF35.0\naF32.0\naF24.0\naF22.0\naF30.0\naF21.0\naF9.0\naF20.0\naF17.0\naF44.0\naF12.0\naF8.0\naF36.0\naF7.0\naF31.0\naF34.0\naF32.0\naF12.0\naF37.0\naF37.0\naF42.0\naF1.0\naF36.0\naF21.0\naF39.0\naF28.0\naF32.0\naF14.0\naF29.0\naF9.0\naF27.0\naF20.0\naF21.0\naF49.0\naF13.0\naF37.0\naF15.0\naF26.0\naF13.0\naF12.0\naF15.0\naF33.0\naF40.0\naF6.0\naF29.0\naF3.0\naF1.0\naF16.0\naF27.0\naF15.0\naF35.0\naF31.0\naF32.0\naF2.0\naF4.0\naF13.0\naF23.0\naF21.0\naF27.0\naF20.0\naF28.0\naF31.0\naF2.0\naF15.0\naF13.0\naF28.0\naF23.0\naF31.0\naF26.0\naF32.0\naF11.0\naF2.0\naF33.0\naF23.0\naF8.0\naF16.0\naF12.0\naF12.0\naF19.0\naF25.0\naF33.0\naF33.0\naF11.0\naF35.0\naF44.0\naF2.0\naF25.0\naF30.0\naF31.0\naF21.0\naF31.0\naF14.0\naF55.0\naF32.0\naF30.0\naF0.0\naF5.0\naF26.0\naF0.0\naF26.0\naF0.0\naF4.0\naF12.0\naF32.0\naF38.0\naF34.0\naF26.0\naF33.0\naF33.0\naF28.0\naF13.0\naF33.0\naF46.0\naF34.0\naF32.0\naF22.0\naF22.0\naF30.0\naF19.0\naF12.0\naF22.0\naF36.0\naF27.0\naF34.0\naF20.0\naF9.0\naF10.0\naF39.0\naF10.0\naF29.0\naF77.0\naF30.0\naF37.0\naF8.0\naF26.0\naF10.0\naF36.0\naF32.0\naF23.0\naF34.0\naF28.0\naF31.0\naF23.0\naF36.0\naF30.0\naF12.0\naF30.0\naF4.0\naF48.0\naF30.0\naF19.0\naF13.0\naF13.0\naF21.0\naF16.0\naF16.0\naF26.0\naF3.0\naF15.0\naF24.0\naF25.0\naF43.0\naF5.0\naF15.0\naF45.0\naF17.0\naF18.0\naF38.0\naF23.0\naF34.0\naF89.0\naF46.0\naF10.0\naF33.0\naF39.0\naF26.0\naF27.0\naF32.0\naF29.0\naF37.0\naF31.0\naF24.0\naF38.0\naF28.0\naF27.0\naF17.0\naF39.0\naF25.0\naF32.0\naF42.0\naF30.0\naF18.0\naF27.0\naF31.0\naF27.0\naF45.0\naF29.0\naF13.0\naF2.0\naF31.0\naF30.0\naF32.0\naF3.0\naF23.0\naF34.0\naF22.0\naF45.0\naF34.0\naF35.0\naF29.0\naF15.0\naF14.0\naF47.0\naF14.0\naF44.0\naF72.0\naF17.0\naF5.0\naF26.0\naF47.0\naF8.0\naF49.0\naF38.0\naF32.0\naF37.0\naF30.0\naF23.0\naF15.0\naF26.0\naF14.0\naF34.0\naF31.0\naF14.0\naF35.0\naF35.0\naF29.0\naF28.0\naF28.0\naF40.0\naF49.0\naF31.0\naF17.0\naF43.0\naF17.0\naF29.0\naF18.0\naF23.0\naF5.0\naF4.0\naF4.0\naF12.0\naF44.0\naF26.0\naF39.0\naF48.0\naF10.0\naF3.0\naF21.0\naF30.0\naF93.0\naF29.0\naF23.0\naF35.0\naF17.0\naF32.0\naF36.0\naF30.0\naF0.0\naF55.0\naF4.0\naF6.0\naF16.0\naF13.0\naF25.0\naF45.0\naF36.0\naF31.0\naF52.0\naF21.0\naF8.0\naF11.0\naF25.0\naF26.0\naF45.0\naF14.0\naF27.0\naF29.0\naF30.0\naF53.0\naF41.0\naF29.0\naF15.0\naF16.0\naF13.0\naF33.0\naF11.0\naF13.0\naF36.0\naF46.0\naF19.0\naF43.0\naF13.0\naF19.0\naF21.0\naF29.0\naF0.0\naF29.0\naF38.0\naF10.0\naF14.0\naF38.0\naF15.0\naF35.0\naF30.0\naF32.0\naF32.0\naF31.0\naF25.0\naF9.0\naF30.0\naF29.0\naF42.0\naF3.0\naF66.0\naF4.0\naF35.0\naF20.0\naF44.0\naF44.0\naF40.0\naF32.0\naF28.0\naF9.0\naF8.0\naF27.0\naF8.0\naF28.0\naF33.0\naF30.0\naF32.0\naF21.0\naF13.0\naF41.0\naF12.0\naF84.0\naF6.0\naF26.0\naF42.0\naF11.0\naF21.0\naF9.0\naF20.0\naF32.0\naF24.0\naF17.0\naF32.0\naF14.0\naF30.0\naF7.0\naF31.0\naF21.0\naF35.0\naF52.0\naF49.0\naF31.0\naF27.0\naF35.0\naF31.0\naF38.0\naF14.0\naF24.0\naF14.0\naF30.0\naF30.0\naF8.0\naF25.0\naF19.0\naF41.0\naF0.0\naF44.0\naF18.0\naF36.0\naF38.0\naF14.0\naF11.0\naF7.0\naF8.0\naF45.0\naF34.0\naF3.0\naF34.0\naF1.0\naF92.0\naF29.0\naF21.0\naF39.0\naF21.0\naF13.0\naF7.0\naF28.0\naF31.0\naF8.0\naF33.0\naF19.0\naF16.0\naF42.0\naF5.0\naF23.0\naF6.0\naF3.0\naF21.0\naF30.0\naF32.0\naF0.0\naF38.0\naF33.0\naF21.0\naF29.0\naF32.0\naF43.0\naF35.0\naF10.0\naF20.0\naF28.0\naF27.0\naF55.0\naF47.0\naF33.0\naF37.0\naF25.0\naF34.0\naF16.0\naF90.0\naF32.0\naF1.0\naF0.0\naF1.0\naF5.0\naF7.0\naF48.0\naF76.0\naF0.0\naF16.0\naF37.0\naF0.0\naF36.0\naF22.0\naF29.0\naF27.0\naF23.0\naF30.0\naF35.0\naF25.0\naF37.0\naF38.0\naF42.0\naF16.0\naF64.0\naF25.0\naF34.0\naF34.0\naF10.0\naF32.0\naF31.0\naF38.0\naF40.0\naF7.0\naF29.0\naF26.0\naF33.0\naF48.0\naF21.0\naF23.0\naF9.0\naF35.0\naF35.0\naF1.0\naF34.0\naF35.0\naF22.0\naF10.0\naF1.0\naF10.0\naF30.0\naF44.0\naF24.0\naF49.0\naF30.0\naF30.0\naF7.0\naF95.0\naF24.0\naF31.0\naF9.0\naF20.0\naF27.0\naF36.0\naF27.0\naF0.0\naF5.0\naF37.0\naF31.0\naF30.0\naF39.0\naF9.0\naF33.0\naF25.0\naF36.0\naF10.0\naF29.0\naF38.0\naF41.0\naF7.0\naF42.0\naF39.0\naF15.0\naF23.0\naF9.0\naF26.0\naF0.0\naF18.0\naF21.0\naF13.0\naF31.0\naF43.0\naF31.0\naF19.0\naF16.0\naF29.0\naF8.0\naF28.0\naF24.0\naF34.0\naF12.0\naF32.0\naF38.0\naF17.0\naF25.0\naF25.0\naF18.0\naF29.0\naF27.0\naF30.0\naF57.0\naF27.0\naF14.0\naF44.0\naF20.0\naF38.0\naF18.0\naF45.0\naF30.0\naF36.0\naF39.0\naF41.0\naF36.0\naF38.0\naF38.0\naF47.0\naF32.0\naF43.0\naF20.0\naF10.0\naF26.0\naF35.0\naF0.0\naF18.0\naF20.0\naF36.0\naF36.0\naF18.0\naF16.0\naF36.0\naF44.0\naF29.0\naF18.0\naF33.0\naF35.0\naF21.0\naF34.0\naF36.0\naF17.0\naF1.0\naF9.0\naF44.0\naF31.0\naF27.0\naF33.0\naF1.0\naF19.0\naF28.0\naF30.0\naF44.0\naF16.0\naF12.0\naF33.0\naF18.0\naF29.0\naF20.0\naF33.0\naF37.0\naF5.0\naF29.0\naF29.0\naF0.0\naF23.0\naF27.0\naF21.0\naF30.0\naF33.0\naF1.0\naF28.0\naF32.0\naF26.0\naF26.0\naF36.0\naF24.0\naF4.0\naF3.0\naF20.0\naF43.0\naF54.0\naF38.0\naF27.0\naF20.0\naF20.0\naF36.0\naF30.0\naF15.0\naF30.0\naF28.0\naF9.0\naF30.0\naF27.0\naF28.0\naF13.0\naF33.0\naF36.0\naF5.0\naF17.0\naF9.0\naF21.0\naF30.0\naF17.0\naF27.0\naF29.0\naF40.0\naF18.0\naF6.0\naF19.0\naF29.0\naF15.0\naF37.0\naF34.0\naF9.0\naF36.0\naF5.0\naF9.0\naF32.0\naF16.0\naF23.0\naF17.0\naF41.0\naF19.0\naF39.0\naF26.0\naF1.0\naF13.0\naF28.0\naF26.0\naF11.0\naF35.0\naF14.0\naF17.0\naF6.0\naF6.0\naF28.0\naF27.0\naF29.0\naF49.0\naF33.0\naF50.0\naF22.0\naF32.0\naF3.0\naF28.0\naF18.0\naF34.0\naF37.0\naF6.0\naF31.0\naF35.0\naF11.0\naF25.0\naF39.0\naF21.0\naF33.0\naF31.0\naF24.0\naF27.0\naF13.0\naF13.0\naF26.0\naF26.0\naF44.0\naF12.0\naF28.0\naF31.0\naF35.0\naF19.0\naF29.0\naF32.0\naF31.0\naF37.0\naF23.0\naF14.0\naF27.0\naF35.0\naF26.0\naF28.0\naF31.0\naF25.0\naF15.0\naF0.0\naF21.0\naF22.0\naF46.0\naF34.0\naF22.0\naF15.0\naF16.0\naF8.0\naF8.0\naF30.0\naF12.0\naF31.0\naF37.0\naF50.0\naF37.0\naF25.0\naF33.0\naF4.0\naF22.0\naF23.0\naF38.0\naF34.0\naF29.0\naF26.0\naF25.0\naF39.0\naF20.0\naF11.0\naF9.0\naF24.0\naF11.0\naF35.0\naF0.0\naF39.0\naF22.0\naF0.0\naF7.0\naF16.0\naF50.0\naF45.0\naF11.0\naF24.0\naF0.0\naF26.0\naF9.0\naF0.0\naF4.0\naF24.0\naF30.0\naF23.0\naF40.0\naF35.0\naF34.0\naF33.0\naF43.0\naF30.0\naF32.0\naF36.0\naF30.0\naF32.0\naF0.0\naF0.0\naF23.0\naF12.0\naF24.0\naF14.0\naF26.0\naF29.0\naF21.0\naF30.0\naF39.0\naF36.0\naF13.0\naF11.0\naF7.0\naF0.0\naF18.0\naF22.0\naF21.0\naF35.0\naF14.0\naF3.0\naF44.0\naF1.0\naF20.0\naF28.0\naF17.0\naF39.0\naF12.0\naF24.0\naF31.0\naF51.0\naF40.0\naF8.0\naF33.0\naF26.0\naF9.0\naF8.0\naF0.0\naF0.0\naF4.0\naF18.0\naF26.0\naF13.0\naF0.0\naF5.0\naF9.0\naF22.0\naF69.0\naF21.0\naF26.0\naF29.0\naF13.0\naF24.0\naF0.0\naF0.0\naF14.0\naF32.0\naF23.0\naF18.0\naF8.0\naF29.0\naF18.0\naF29.0\naF3.0\naF19.0\naF13.0\naF31.0\naF29.0\naF18.0\naF27.0\naF36.0\naF10.0\naF33.0\naF38.0\naF30.0\naF23.0\naF5.0\naF9.0\naF14.0\naF5.0\naF0.0\na."
  },
  {
    "path": "dqn/logs_pkls/Pong_s001.pkl",
    "content": "(lp0\n(I60000\ncnumpy.core.multiarray\nscalar\np1\n(cnumpy\ndtype\np2\n(S'f8'\np3\nI0\nI1\ntp4\nRp5\n(I3\nS'<'\np6\nNNNI-1\nI-1\nI0\ntp7\nbS'/\\xf4B/\\xf4B4\\xc0'\np8\ntp9\nRp10\nF-inf\nF-20.0\ntp11\na(I70000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=4\\xc0'\np12\ntp13\nRp14\nF-inf\nF-21.0\ntp15\na(I80000\ng1\n(g5\nS'\\xd0\\x17\\xf4\\x05}A4\\xc0'\np16\ntp17\nRp18\nF-inf\nF-20.0\ntp19\na(I90000\ng1\n(g5\nS'\\xab\\xaa\\xaa\\xaa\\xaa:4\\xc0'\np20\ntp21\nRp22\nF-inf\nF-20.0\ntp23\na(I100000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ84\\xc0'\np24\ntp25\nRp26\ng1\n(g5\nS'q=\\n\\xd7\\xa304\\xc0'\np27\ntp28\nRp29\nF-21.0\ntp30\na(I110000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@4\\xc0'\np31\ntp32\nRp33\ng29\nF-21.0\ntp34\na(I120000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ84\\xc0'\np35\ntp36\nRp37\ng29\nF-21.0\ntp38\na(I130000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG4\\xc0'\np39\ntp40\nRp41\ng29\nF-20.0\ntp42\na(I140000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE4\\xc0'\np43\ntp44\nRp45\ng29\nF-20.0\ntp46\na(I150000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE4\\xc0'\np47\ntp48\nRp49\ng29\nF-19.0\ntp50\na(I160000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW4\\xc0'\np51\ntp52\nRp53\ng29\nF-20.0\ntp54\na(I170000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@4\\xc0'\np55\ntp56\nRp57\ng29\nF-20.0\ntp58\na(I180000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL4\\xc0'\np59\ntp60\nRp61\ng29\nF-21.0\ntp62\na(I190000\ng1\n(g5\nS'\\n\\xd7\\xa3p=J4\\xc0'\np63\ntp64\nRp65\ng29\nF-19.0\ntp66\na(I200000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE4\\xc0'\np67\ntp68\nRp69\ng29\nF-21.0\ntp70\na(I210000\ng1\n(g5\nS'3333334\\xc0'\np71\ntp72\nRp73\ng29\nF-21.0\ntp74\na(I220000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.4\\xc0'\np75\ntp76\nRp77\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.4\\xc0'\np78\ntp79\nRp80\nF-21.0\ntp81\na(I230000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(4\\xc0'\np82\ntp83\nRp84\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(4\\xc0'\np85\ntp86\nRp87\nF-21.0\ntp88\na(I240000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85+4\\xc0'\np89\ntp90\nRp91\ng1\n(g5\nS'\\xa4p=\\n\\xd7#4\\xc0'\np92\ntp93\nRp94\nF-20.0\ntp95\na(I250000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.4\\xc0'\np96\ntp97\nRp98\ng94\nF-21.0\ntp99\na(I260000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85+4\\xc0'\np100\ntp101\nRp102\ng94\nF-21.0\ntp103\na(I270000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:4\\xc0'\np104\ntp105\nRp106\ng94\nF-21.0\ntp107\na(I280000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ84\\xc0'\np108\ntp109\nRp110\ng94\nF-20.0\ntp111\na(I290000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE4\\xc0'\np112\ntp113\nRp114\ng94\nF-21.0\ntp115\na(I300000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG4\\xc0'\np116\ntp117\nRp118\ng94\nF-20.0\ntp119\na(I310000\ng1\n(g5\nS'\\n\\xd7\\xa3p=J4\\xc0'\np120\ntp121\nRp122\ng94\nF-20.0\ntp123\na(I320000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zT4\\xc0'\np124\ntp125\nRp126\ng94\nF-21.0\ntp127\na(I330000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG4\\xc0'\np128\ntp129\nRp130\ng94\nF-17.0\ntp131\na(I340000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL4\\xc0'\np132\ntp133\nRp134\ng94\nF-21.0\ntp135\na(I350000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^4\\xc0'\np136\ntp137\nRp138\ng94\nF-21.0\ntp139\na(I360000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y4\\xc0'\np140\ntp141\nRp142\ng94\nF-21.0\ntp143\na(I370000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ4\\xc0'\np144\ntp145\nRp146\ng94\nF-20.0\ntp147\na(I380000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW4\\xc0'\np148\ntp149\nRp150\ng94\nF-21.0\ntp151\na(I390000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW4\\xc0'\np152\ntp153\nRp154\ng94\nF-19.0\ntp155\na(I400000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zT4\\xc0'\np156\ntp157\nRp158\ng94\nF-20.0\ntp159\na(I410000\ng1\n(g5\nS'\\n\\xd7\\xa3p=J4\\xc0'\np160\ntp161\nRp162\ng94\nF-20.0\ntp163\na(I420000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@4\\xc0'\np164\ntp165\nRp166\ng94\nF-21.0\ntp167\na(I430000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x194\\xc0'\np168\ntp169\nRp170\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x194\\xc0'\np171\ntp172\nRp173\nF-16.0\ntp174\na(I440000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf83\\xc0'\np175\ntp176\nRp177\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf83\\xc0'\np178\ntp179\nRp180\nF-18.0\ntp181\na(I450000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde3\\xc0'\np182\ntp183\nRp184\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde3\\xc0'\np185\ntp186\nRp187\nF-20.0\ntp188\na(I460000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e3\\xc0'\np189\ntp190\nRp191\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e3\\xc0'\np192\ntp193\nRp194\nF-20.0\ntp195\na(I470000\ng1\n(g5\nS'33333s3\\xc0'\np196\ntp197\nRp198\ng1\n(g5\nS'33333s3\\xc0'\np199\ntp200\nRp201\nF-18.0\ntp202\na(I480000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O3\\xc0'\np203\ntp204\nRp205\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O3\\xc0'\np206\ntp207\nRp208\nF-20.0\ntp209\na(I490000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ83\\xc0'\np210\ntp211\nRp212\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ83\\xc0'\np213\ntp214\nRp215\nF-18.0\ntp216\na(I500000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x073\\xc0'\np217\ntp218\nRp219\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x073\\xc0'\np220\ntp221\nRp222\nF-16.0\ntp223\na(I510000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb2\\xc0'\np224\ntp225\nRp226\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb2\\xc0'\np227\ntp228\nRp229\nF-16.0\ntp230\na(I520000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc02\\xc0'\np231\ntp232\nRp233\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc02\\xc0'\np234\ntp235\nRp236\nF-15.0\ntp237\na(I530000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f2\\xc0'\np238\ntp239\nRp240\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f2\\xc0'\np241\ntp242\nRp243\nF-18.0\ntp244\na(I540000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h2\\xc0'\np245\ntp246\nRp247\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h2\\xc0'\np248\ntp249\nRp250\nF-15.0\ntp251\na(I550000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@2\\xc0'\np252\ntp253\nRp254\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@2\\xc0'\np255\ntp256\nRp257\nF-18.0\ntp258\na(I560000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x172\\xc0'\np259\ntp260\nRp261\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x172\\xc0'\np262\ntp263\nRp264\nF-18.0\ntp265\na(I570000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f2\\xc0'\np266\ntp267\nRp268\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f2\\xc0'\np269\ntp270\nRp271\nF-15.0\ntp272\na(I580000\ng1\n(g5\nS'fffff\\xe61\\xc0'\np273\ntp274\nRp275\ng1\n(g5\nS'fffff\\xe61\\xc0'\np276\ntp277\nRp278\nF-15.0\ntp279\na(I590000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd41\\xc0'\np280\ntp281\nRp282\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc1\\xc0'\np283\ntp284\nRp285\nF-20.0\ntp286\na(I600000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab1\\xc0'\np287\ntp288\nRp289\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab1\\xc0'\np290\ntp291\nRp292\nF-17.0\ntp293\na(I610000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba1\\xc0'\np294\ntp295\nRp296\ng1\n(g5\nS'fffff\\xa61\\xc0'\np297\ntp298\nRp299\nF-21.0\ntp300\na(I620000\ng1\n(g5\nS'33333\\xb31\\xc0'\np301\ntp302\nRp303\ng299\nF-19.0\ntp304\na(I630000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa31\\xc0'\np305\ntp306\nRp307\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa11\\xc0'\np308\ntp309\nRp310\nF-19.0\ntp311\na(I640000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x801\\xc0'\np312\ntp313\nRp314\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x801\\xc0'\np315\ntp316\nRp317\nF-16.0\ntp318\na(I650000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k1\\xc0'\np319\ntp320\nRp321\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h1\\xc0'\np322\ntp323\nRp324\nF-19.0\ntp325\na(I660000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa1\\xc0'\np326\ntp327\nRp328\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\1\\xc0'\np329\ntp330\nRp331\nF-20.0\ntp332\na(I670000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW1\\xc0'\np333\ntp334\nRp335\ng1\n(g5\nS'\\xd7\\xa3p=\\nW1\\xc0'\np336\ntp337\nRp338\nF-18.0\ntp339\na(I680000\ng1\n(g5\nS'\\n\\xd7\\xa3p=J1\\xc0'\np340\ntp341\nRp342\ng1\n(g5\nS'\\n\\xd7\\xa3p=J1\\xc0'\np343\ntp344\nRp345\nF-18.0\ntp346\na(I690000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zT1\\xc0'\np347\ntp348\nRp349\ng345\nF-17.0\ntp350\na(I700000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB1\\xc0'\np351\ntp352\nRp353\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB1\\xc0'\np354\ntp355\nRp356\nF-15.0\ntp357\na(I710000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ81\\xc0'\np358\ntp359\nRp360\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ81\\xc0'\np361\ntp362\nRp363\nF-19.0\ntp364\na(I720000\ng1\n(g5\nS'q=\\n\\xd7\\xa301\\xc0'\np365\ntp366\nRp367\ng1\n(g5\nS'q=\\n\\xd7\\xa301\\xc0'\np368\ntp369\nRp370\nF-16.0\ntp371\na(I730000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f1\\xc0'\np372\ntp373\nRp374\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f1\\xc0'\np375\ntp376\nRp377\nF-14.0\ntp378\na(I740000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f1\\xc0'\np379\ntp380\nRp381\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n1\\xc0'\np382\ntp383\nRp384\nF-16.0\ntp385\na(I750000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x001\\xc0'\np386\ntp387\nRp388\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfa0\\xc0'\np389\ntp390\nRp391\nF-14.0\ntp392\na(I760000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe80\\xc0'\np393\ntp394\nRp395\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe80\\xc0'\np396\ntp397\nRp398\nF-14.0\ntp399\na(I770000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc20\\xc0'\np400\ntp401\nRp402\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc00\\xc0'\np403\ntp404\nRp405\nF-19.0\ntp406\na(I780000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e0\\xc0'\np407\ntp408\nRp409\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e0\\xc0'\np410\ntp411\nRp412\nF-11.0\ntp413\na(I790000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x970\\xc0'\np414\ntp415\nRp416\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x970\\xc0'\np417\ntp418\nRp419\nF-13.0\ntp420\na(I800000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z0\\xc0'\np421\ntp422\nRp423\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z0\\xc0'\np424\ntp425\nRp426\nF-18.0\ntp427\na(I810000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^0\\xc0'\np428\ntp429\nRp430\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\0\\xc0'\np431\ntp432\nRp433\nF-17.0\ntp434\na(I820000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa0\\xc0'\np435\ntp436\nRp437\ng433\nF-18.0\ntp438\na(I830000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O0\\xc0'\np439\ntp440\nRp441\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O0\\xc0'\np442\ntp443\nRp444\nF-14.0\ntp445\na(I840000\ng1\n(g5\nS'q=\\n\\xd7\\xa300\\xc0'\np446\ntp447\nRp448\ng1\n(g5\nS'q=\\n\\xd7\\xa300\\xc0'\np449\ntp450\nRp451\nF-16.0\ntp452\na(I850000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x170\\xc0'\np453\ntp454\nRp455\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x170\\xc0'\np456\ntp457\nRp458\nF-15.0\ntp459\na(I860000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7/\\xc0'\np460\ntp461\nRp462\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7/\\xc0'\np463\ntp464\nRp465\nF-11.0\ntp466\na(I870000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z/\\xc0'\np467\ntp468\nRp469\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z/\\xc0'\np470\ntp471\nRp472\nF-13.0\ntp473\na(I880000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB/\\xc0'\np474\ntp475\nRp476\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB/\\xc0'\np477\ntp478\nRp479\nF-13.0\ntp480\na(I890000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05/\\xc0'\np481\ntp482\nRp483\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05/\\xc0'\np484\ntp485\nRp486\nF-18.0\ntp487\na(I900000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e.\\xc0'\np488\ntp489\nRp490\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e.\\xc0'\np491\ntp492\nRp493\nF-11.0\ntp494\na(I910000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8.\\xc0'\np495\ntp496\nRp497\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8.\\xc0'\np498\ntp499\nRp500\nF-12.0\ntp501\na(I920000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n.\\xc0'\np502\ntp503\nRp504\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n.\\xc0'\np505\ntp506\nRp507\nF-13.0\ntp508\na(I930000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc7-\\xc0'\np509\ntp510\nRp511\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc7-\\xc0'\np512\ntp513\nRp514\nF-15.0\ntp515\na(I940000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.-\\xc0'\np516\ntp517\nRp518\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.-\\xc0'\np519\ntp520\nRp521\nF-15.0\ntp522\na(I950000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5,\\xc0'\np523\ntp524\nRp525\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5,\\xc0'\np526\ntp527\nRp528\nF-14.0\ntp529\na(I960000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd1,\\xc0'\np530\ntp531\nRp532\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd1,\\xc0'\np533\ntp534\nRp535\nF-12.0\ntp536\na(I970000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85,\\xc0'\np537\ntp538\nRp539\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85,\\xc0'\np540\ntp541\nRp542\nF-7.0\ntp543\na(I980000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB,\\xc0'\np544\ntp545\nRp546\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8,\\xc0'\np547\ntp548\nRp549\nF-18.0\ntp550\na(I990000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae+\\xc0'\np551\ntp552\nRp553\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae+\\xc0'\np554\ntp555\nRp556\nF-6.0\ntp557\na(I1000000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=+\\xc0'\np558\ntp559\nRp560\ng1\n(g5\nS'=\\n\\xd7\\xa3p=+\\xc0'\np561\ntp562\nRp563\nF-8.0\ntp564\na(I1010000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x19+\\xc0'\np565\ntp566\nRp567\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x19+\\xc0'\np568\ntp569\nRp570\nF-8.0\ntp571\na(I1020000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5*\\xc0'\np572\ntp573\nRp574\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd1*\\xc0'\np575\ntp576\nRp577\nF-16.0\ntp578\na(I1030000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x80*\\xc0'\np579\ntp580\nRp581\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x80*\\xc0'\np582\ntp583\nRp584\nF-13.0\ntp585\na(I1040000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW*\\xc0'\np586\ntp587\nRp588\ng1\n(g5\nS'\\xd7\\xa3p=\\nW*\\xc0'\np589\ntp590\nRp591\nF-10.0\ntp592\na(I1050000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2)\\xc0'\np593\ntp594\nRp595\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2)\\xc0'\np596\ntp597\nRp598\nF-7.0\ntp599\na(I1060000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x80)\\xc0'\np600\ntp601\nRp602\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x80)\\xc0'\np603\ntp604\nRp605\nF-7.0\ntp606\na(I1070000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e)\\xc0'\np607\ntp608\nRp609\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e)\\xc0'\np610\ntp611\nRp612\nF-10.0\ntp613\na(I1080000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc7(\\xc0'\np614\ntp615\nRp616\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc7(\\xc0'\np617\ntp618\nRp619\nF-5.0\ntp620\na(I1090000\ng1\n(g5\nS'333333(\\xc0'\np621\ntp622\nRp623\ng1\n(g5\nS'333333(\\xc0'\np624\ntp625\nRp626\nF-7.0\ntp627\na(I1100000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8(\\xc0'\np628\ntp629\nRp630\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n(\\xc0'\np631\ntp632\nRp633\nF-17.0\ntp634\na(I1110000\ng1\n(g5\nS\"fffff\\xe6'\\xc0\"\np635\ntp636\nRp637\ng1\n(g5\nS\"fffff\\xe6'\\xc0\"\np638\ntp639\nRp640\nF-15.0\ntp641\na(I1120000\ng1\n(g5\nS\"\\\\\\x8f\\xc2\\xf5(\\\\'\\xc0\"\np642\ntp643\nRp644\ng1\n(g5\nS\"\\\\\\x8f\\xc2\\xf5(\\\\'\\xc0\"\np645\ntp646\nRp647\nF-13.0\ntp648\na(I1130000\ng1\n(g5\nS\"\\n\\xd7\\xa3p=\\n'\\xc0\"\np649\ntp650\nRp651\ng1\n(g5\nS\"\\n\\xd7\\xa3p=\\n'\\xc0\"\np652\ntp653\nRp654\nF-9.0\ntp655\na(I1140000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7&\\xc0'\np656\ntp657\nRp658\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd1&\\xc0'\np659\ntp660\nRp661\nF-12.0\ntp662\na(I1150000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a&\\xc0'\np663\ntp664\nRp665\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u&\\xc0'\np666\ntp667\nRp668\nF-13.0\ntp669\na(I1160000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb%\\xc0'\np670\ntp671\nRp672\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb%\\xc0'\np673\ntp674\nRp675\nF-14.0\ntp676\na(I1170000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85%\\xc0'\np677\ntp678\nRp679\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85%\\xc0'\np680\ntp681\nRp682\nF-10.0\ntp683\na(I1180000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8$\\xc0'\np684\ntp685\nRp686\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8$\\xc0'\np687\ntp688\nRp689\nF-6.0\ntp690\na(I1190000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u$\\xc0'\np691\ntp692\nRp693\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u$\\xc0'\np694\ntp695\nRp696\nF-9.0\ntp697\na(I1200000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x19$\\xc0'\np698\ntp699\nRp700\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x19$\\xc0'\np701\ntp702\nRp703\nF-10.0\ntp704\na(I1210000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa#\\xc0'\np705\ntp706\nRp707\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa#\\xc0'\np708\ntp709\nRp710\nF-6.0\ntp711\na(I1220000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05#\\xc0'\np712\ntp713\nRp714\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05#\\xc0'\np715\ntp716\nRp717\nF-8.0\ntp718\na(I1230000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\"\\xc0'\np719\ntp720\nRp721\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\"\\xc0'\np722\ntp723\nRp724\nF-4.0\ntp725\na(I1240000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#\"\\xc0'\np726\ntp727\nRp728\ng1\n(g5\nS'\\xa4p=\\n\\xd7#\"\\xc0'\np729\ntp730\nRp731\nF-9.0\ntp732\na(I1250000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3!\\xc0'\np733\ntp734\nRp735\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3!\\xc0'\np736\ntp737\nRp738\nF-4.0\ntp739\na(I1260000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05!\\xc0'\np740\ntp741\nRp742\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x05!\\xc0'\np743\ntp744\nRp745\nF-4.0\ntp746\na(I1270000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8 \\xc0'\np747\ntp748\nRp749\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8 \\xc0'\np750\ntp751\nRp752\nF-4.0\ntp753\na(I1280000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n \\xc0'\np754\ntp755\nRp756\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\x1f\\xc0'\np757\ntp758\nRp759\nF-8.0\ntp760\na(I1290000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x1e\\xc0'\np761\ntp762\nRp763\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x1e\\xc0'\np764\ntp765\nRp766\nF-9.0\ntp767\na(I1300000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x1e\\xc0'\np768\ntp769\nRp770\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x1e\\xc0'\np771\ntp772\nRp773\nF-1.0\ntp774\na(I1310000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\x1c\\xc0'\np775\ntp776\nRp777\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\x1c\\xc0'\np778\ntp779\nRp780\nF2.0\ntp781\na(I1320000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x1b\\xc0'\np782\ntp783\nRp784\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x1b\\xc0'\np785\ntp786\nRp787\nF-8.0\ntp788\na(I1330000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\x1a\\xc0'\np789\ntp790\nRp791\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\x1a\\xc0'\np792\ntp793\nRp794\nF2.0\ntp795\na(I1340000\ng1\n(g5\nS'ffffff\\x19\\xc0'\np796\ntp797\nRp798\ng1\n(g5\nS'ffffff\\x19\\xc0'\np799\ntp800\nRp801\nF3.0\ntp802\na(I1350000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\x17\\xc0'\np803\ntp804\nRp805\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\x17\\xc0'\np806\ntp807\nRp808\nF-6.0\ntp809\na(I1360000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x16\\xc0'\np810\ntp811\nRp812\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\x16\\xc0'\np813\ntp814\nRp815\nF-1.0\ntp816\na(I1370000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x16\\xc0'\np817\ntp818\nRp819\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x16\\xc0'\np820\ntp821\nRp822\nF-3.0\ntp823\na(I1380000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x14\\xc0'\np824\ntp825\nRp826\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x14\\xc0'\np827\ntp828\nRp829\nF3.0\ntp830\na(I1390000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\x13\\xc0'\np831\ntp832\nRp833\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\x13\\xc0'\np834\ntp835\nRp836\nF2.0\ntp837\na(I1400000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\x12\\xc0'\np838\ntp839\nRp840\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\x12\\xc0'\np841\ntp842\nRp843\nF-6.0\ntp844\na(I1410000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x11\\xc0'\np845\ntp846\nRp847\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x11\\xc0'\np848\ntp849\nRp850\nF5.0\ntp851\na(I1420000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\x0f\\xc0'\np852\ntp853\nRp854\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\x0f\\xc0'\np855\ntp856\nRp857\nF4.0\ntp858\na(I1430000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\n\\xc0'\np859\ntp860\nRp861\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\n\\xc0'\np862\ntp863\nRp864\nF2.0\ntp865\na(I1440000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x08\\xc0'\np866\ntp867\nRp868\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x08\\xc0'\np869\ntp870\nRp871\nF4.0\ntp872\na(I1450000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x07\\xc0'\np873\ntp874\nRp875\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x07\\xc0'\np876\ntp877\nRp878\nF-5.0\ntp879\na(I1460000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x04\\xc0'\np880\ntp881\nRp882\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x04\\xc0'\np883\ntp884\nRp885\nF1.0\ntp886\na(I1470000\ng1\n(g5\nS'ffffff\\x00\\xc0'\np887\ntp888\nRp889\ng1\n(g5\nS'ffffff\\x00\\xc0'\np890\ntp891\nRp892\nF2.0\ntp893\na(I1480000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xf9\\xbf'\np894\ntp895\nRp896\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\xf9\\xbf'\np897\ntp898\nRp899\nF4.0\ntp900\na(I1490000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\xf2\\xbf'\np901\ntp902\nRp903\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\xf2\\xbf'\np904\ntp905\nRp906\nF5.0\ntp907\na(I1500000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xe7\\xbf'\np908\ntp909\nRp910\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\xe7\\xbf'\np911\ntp912\nRp913\nF8.0\ntp914\na(I1510000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9\\xbf'\np915\ntp916\nRp917\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9\\xbf'\np918\ntp919\nRp920\nF8.0\ntp921\na(I1520000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\xd8?'\np922\ntp923\nRp924\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\xd8?'\np925\ntp926\nRp927\nF8.0\ntp928\na(I1530000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xe9?'\np929\ntp930\nRp931\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xe9?'\np932\ntp933\nRp934\nF9.0\ntp935\na(I1540000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xf0?'\np936\ntp937\nRp938\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\xf0?'\np939\ntp940\nRp941\nF8.0\ntp942\na(I1550000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xf5?'\np943\ntp944\nRp945\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xf5?'\np946\ntp947\nRp948\nF6.0\ntp949\na(I1560000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xfa?'\np950\ntp951\nRp952\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\\xfa?'\np953\ntp954\nRp955\nF8.0\ntp956\na(I1570000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\x00@'\np957\ntp958\nRp959\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\x00@'\np960\ntp961\nRp962\nF9.0\ntp963\na(I1580000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\x05@'\np964\ntp965\nRp966\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\x05@'\np967\ntp968\nRp969\nF9.0\ntp970\na(I1590000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\t@'\np971\ntp972\nRp973\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\t@'\np974\ntp975\nRp976\nF12.0\ntp977\na(I1600000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\r@'\np978\ntp979\nRp980\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\r@'\np981\ntp982\nRp983\nF15.0\ntp984\na(I1610000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x12@'\np985\ntp986\nRp987\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x12@'\np988\ntp989\nRp990\nF18.0\ntp991\na(I1620000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\x14@'\np992\ntp993\nRp994\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\x14@'\np995\ntp996\nRp997\nF19.0\ntp998\na(I1630000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x16@'\np999\ntp1000\nRp1001\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x16@'\np1002\ntp1003\nRp1004\nF12.0\ntp1005\na(I1640000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\x18@'\np1006\ntp1007\nRp1008\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\x18@'\np1009\ntp1010\nRp1011\nF13.0\ntp1012\na(I1650000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x1a@'\np1013\ntp1014\nRp1015\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\x1a@'\np1016\ntp1017\nRp1018\nF13.0\ntp1019\na(I1660000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x1d@'\np1020\ntp1021\nRp1022\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x1d@'\np1023\ntp1024\nRp1025\nF14.0\ntp1026\na(I1670000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p @'\np1027\ntp1028\nRp1029\ng1\n(g5\nS'q=\\n\\xd7\\xa3p @'\np1030\ntp1031\nRp1032\nF19.0\ntp1033\na(I1680000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u!@'\np1034\ntp1035\nRp1036\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u!@'\np1037\ntp1038\nRp1039\nF16.0\ntp1040\na(I1690000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\"@'\np1041\ntp1042\nRp1043\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\"@'\np1044\ntp1045\nRp1046\nF15.0\ntp1047\na(I1700000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc#@'\np1048\ntp1049\nRp1050\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc#@'\np1051\ntp1052\nRp1053\nF17.0\ntp1054\na(I1710000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb$@'\np1055\ntp1056\nRp1057\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb$@'\np1058\ntp1059\nRp1060\nF16.0\ntp1061\na(I1720000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.&@'\np1062\ntp1063\nRp1064\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.&@'\np1065\ntp1066\nRp1067\nF16.0\ntp1068\na(I1730000\ng1\n(g5\nS\"q=\\n\\xd7\\xa3p'@\"\np1069\ntp1070\nRp1071\ng1\n(g5\nS\"q=\\n\\xd7\\xa3p'@\"\np1072\ntp1073\nRp1074\nF21.0\ntp1075\na(I1740000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z(@'\np1076\ntp1077\nRp1078\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z(@'\np1079\ntp1080\nRp1081\nF18.0\ntp1082\na(I1750000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG)@'\np1083\ntp1084\nRp1085\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG)@'\np1086\ntp1087\nRp1088\nF17.0\ntp1089\na(I1760000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#*@'\np1090\ntp1091\nRp1092\ng1\n(g5\nS'\\xa4p=\\n\\xd7#*@'\np1093\ntp1094\nRp1095\nF18.0\ntp1096\na(I1770000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc*@'\np1097\ntp1098\nRp1099\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc*@'\np1100\ntp1101\nRp1102\nF20.0\ntp1103\na(I1780000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n,@'\np1104\ntp1105\nRp1106\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n,@'\np1107\ntp1108\nRp1109\nF17.0\ntp1110\na(I1790000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf0,@'\np1111\ntp1112\nRp1113\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf0,@'\np1114\ntp1115\nRp1116\nF17.0\ntp1117\na(I1800000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5-@'\np1118\ntp1119\nRp1120\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5-@'\np1121\ntp1122\nRp1123\nF17.0\ntp1124\na(I1810000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\.@'\np1125\ntp1126\nRp1127\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\.@'\np1128\ntp1129\nRp1130\nF18.0\ntp1131\na(I1820000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#/@'\np1132\ntp1133\nRp1134\ng1\n(g5\nS'\\xa4p=\\n\\xd7#/@'\np1135\ntp1136\nRp1137\nF19.0\ntp1138\na(I1830000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z/@'\np1139\ntp1140\nRp1141\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z/@'\np1142\ntp1143\nRp1144\nF19.0\ntp1145\na(I1840000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf0/@'\np1146\ntp1147\nRp1148\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf0/@'\np1149\ntp1150\nRp1151\nF14.0\ntp1152\na(I1850000\ng1\n(g5\nS'q=\\n\\xd7\\xa300@'\np1153\ntp1154\nRp1155\ng1\n(g5\nS'q=\\n\\xd7\\xa300@'\np1156\ntp1157\nRp1158\nF18.0\ntp1159\na(I1860000\ng1\n(g5\nS'ffffff0@'\np1160\ntp1161\nRp1162\ng1\n(g5\nS'ffffff0@'\np1163\ntp1164\nRp1165\nF18.0\ntp1166\na(I1870000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x800@'\np1167\ntp1168\nRp1169\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x870@'\np1170\ntp1171\nRp1172\nF14.0\ntp1173\na(I1880000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}0@'\np1174\ntp1175\nRp1176\ng1172\nF17.0\ntp1177\na(I1890000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx0@'\np1178\ntp1179\nRp1180\ng1172\nF19.0\ntp1181\na(I1900000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x970@'\np1182\ntp1183\nRp1184\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x970@'\np1185\ntp1186\nRp1187\nF19.0\ntp1188\na(I1910000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab0@'\np1189\ntp1190\nRp1191\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab0@'\np1192\ntp1193\nRp1194\nF15.0\ntp1195\na(I1920000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa10@'\np1196\ntp1197\nRp1198\ng1194\nF16.0\ntp1199\na(I1930000\ng1\n(g5\nS'fffff\\xa60@'\np1200\ntp1201\nRp1202\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd0@'\np1203\ntp1204\nRp1205\nF18.0\ntp1206\na(I1940000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0c0@'\np1207\ntp1208\nRp1209\ng1205\nF-9.0\ntp1210\na(I1950000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x190@'\np1211\ntp1212\nRp1213\ng1205\nF17.0\ntp1214\na(I1960000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1c0@'\np1215\ntp1216\nRp1217\ng1205\nF14.0\ntp1218\na(I1970000\ng1\n(g5\nS'fffff&0@'\np1219\ntp1220\nRp1221\ng1205\nF19.0\ntp1222\na(I1980000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f0@'\np1223\ntp1224\nRp1225\ng1205\nF17.0\ntp1226\na(I1990000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ80@'\np1227\ntp1228\nRp1229\ng1205\nF19.0\ntp1230\na(I2000000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O0@'\np1231\ntp1232\nRp1233\ng1205\nF18.0\ntp1234\na(I2010000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h0@'\np1235\ntp1236\nRp1237\ng1205\nF18.0\ntp1238\na(I2020000\ng1\n(g5\nS'33333s0@'\np1239\ntp1240\nRp1241\ng1205\nF18.0\ntp1242\na(I2030000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\0@'\np1243\ntp1244\nRp1245\ng1205\nF11.0\ntp1246\na(I2040000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u0@'\np1247\ntp1248\nRp1249\ng1205\nF20.0\ntp1250\na(I2050000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx0@'\np1251\ntp1252\nRp1253\ng1205\nF16.0\ntp1254\na(I2060000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n0@'\np1255\ntp1256\nRp1257\ng1205\nF15.0\ntp1258\na(I2070000\ng1\n(g5\nS'\\xa4p=\\n\\xd7c0@'\np1259\ntp1260\nRp1261\ng1205\nF19.0\ntp1262\na(I2080000\ng1\n(g5\nS'33333s0@'\np1263\ntp1264\nRp1265\ng1205\nF17.0\ntp1266\na(I2090000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ/@'\np1267\ntp1268\nRp1269\ng1205\nF20.0\ntp1270\na(I2100000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85/@'\np1271\ntp1272\nRp1273\ng1205\nF18.0\ntp1274\na(I2110000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e/@'\np1275\ntp1276\nRp1277\ng1205\nF20.0\ntp1278\na(I2120000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2/@'\np1279\ntp1280\nRp1281\ng1205\nF18.0\ntp1282\na(I2130000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99/@'\np1283\ntp1284\nRp1285\ng1205\nF20.0\ntp1286\na(I2140000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.0@'\np1287\ntp1288\nRp1289\ng1205\nF19.0\ntp1290\na(I2150000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x850@'\np1291\ntp1292\nRp1293\ng1205\nF18.0\ntp1294\na(I2160000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z0@'\np1295\ntp1296\nRp1297\ng1205\nF17.0\ntp1298\na(I2170000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x870@'\np1299\ntp1300\nRp1301\ng1205\nF16.0\ntp1302\na(I2180000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x940@'\np1303\ntp1304\nRp1305\ng1205\nF18.0\ntp1306\na(I2190000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx0@'\np1307\ntp1308\nRp1309\ng1205\nF14.0\ntp1310\na(I2200000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y0@'\np1311\ntp1312\nRp1313\ng1205\nF5.0\ntp1314\na(I2210000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zT0@'\np1315\ntp1316\nRp1317\ng1205\nF20.0\ntp1318\na(I2220000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ0@'\np1319\ntp1320\nRp1321\ng1205\nF18.0\ntp1322\na(I2230000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^0@'\np1323\ntp1324\nRp1325\ng1205\nF17.0\ntp1326\na(I2240000\ng1\n(g5\nS'\\xa4p=\\n\\xd7c0@'\np1327\ntp1328\nRp1329\ng1205\nF17.0\ntp1330\na(I2250000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^0@'\np1331\ntp1332\nRp1333\ng1205\nF19.0\ntp1334\na(I2260000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n0@'\np1335\ntp1336\nRp1337\ng1205\nF18.0\ntp1338\na(I2270000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a0@'\np1339\ntp1340\nRp1341\ng1205\nF18.0\ntp1342\na(I2280000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x870@'\np1343\ntp1344\nRp1345\ng1205\nF17.0\ntp1346\na(I2290000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf0@'\np1347\ntp1348\nRp1349\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf0@'\np1350\ntp1351\nRp1352\nF18.0\ntp1353\na(I2300000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa1@'\np1354\ntp1355\nRp1356\ng1\n(g5\nS'33333s1@'\np1357\ntp1358\nRp1359\nF13.0\ntp1360\na(I2310000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O1@'\np1361\ntp1362\nRp1363\ng1359\nF19.0\ntp1364\na(I2320000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL1@'\np1365\ntp1366\nRp1367\ng1359\nF18.0\ntp1368\na(I2330000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW1@'\np1369\ntp1370\nRp1371\ng1359\nF18.0\ntp1372\na(I2340000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^1@'\np1373\ntp1374\nRp1375\ng1359\nF18.0\ntp1376\na(I2350000\ng1\n(g5\nS'\\xa4p=\\n\\xd7c1@'\np1377\ntp1378\nRp1379\ng1359\nF18.0\ntp1380\na(I2360000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}1@'\np1381\ntp1382\nRp1383\ng1\n(g5\nS'=\\n\\xd7\\xa3p}1@'\np1384\ntp1385\nRp1386\nF19.0\ntp1387\na(I2370000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x911@'\np1388\ntp1389\nRp1390\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x911@'\np1391\ntp1392\nRp1393\nF20.0\ntp1394\na(I2380000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb01@'\np1395\ntp1396\nRp1397\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb01@'\np1398\ntp1399\nRp1400\nF18.0\ntp1401\na(I2390000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc01@'\np1402\ntp1403\nRp1404\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc1@'\np1405\ntp1406\nRp1407\nF16.0\ntp1408\na(I2400000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc51@'\np1409\ntp1410\nRp1411\ng1407\nF18.0\ntp1412\na(I2410000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb1@'\np1413\ntp1414\nRp1415\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb1@'\np1416\ntp1417\nRp1418\nF19.0\ntp1419\na(I2420000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd11@'\np1420\ntp1421\nRp1422\ng1418\nF15.0\ntp1423\na(I2430000\ng1\n(g5\nS'fffff\\xe61@'\np1424\ntp1425\nRp1426\ng1418\nF21.0\ntp1427\na(I2440000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb1@'\np1428\ntp1429\nRp1430\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf01@'\np1431\ntp1432\nRp1433\nF17.0\ntp1434\na(I2450000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde1@'\np1435\ntp1436\nRp1437\ng1433\nF20.0\ntp1438\na(I2460000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc1@'\np1439\ntp1440\nRp1441\ng1433\nF18.0\ntp1442\na(I2470000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe81@'\np1443\ntp1444\nRp1445\ng1433\nF18.0\ntp1446\na(I2480000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfa1@'\np1447\ntp1448\nRp1449\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfa1@'\np1450\ntp1451\nRp1452\nF20.0\ntp1453\na(I2490000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf81@'\np1454\ntp1455\nRp1456\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x002@'\np1457\ntp1458\nRp1459\nF18.0\ntp1460\na(I2500000\ng1\n(g5\nS'33333\\xf31@'\np1461\ntp1462\nRp1463\ng1459\nF18.0\ntp1464\na(I2510000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f2@'\np1465\ntp1466\nRp1467\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e2@'\np1468\ntp1469\nRp1470\nF17.0\ntp1471\na(I2520000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x072@'\np1472\ntp1473\nRp1474\ng1470\nF20.0\ntp1475\na(I2530000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x112@'\np1476\ntp1477\nRp1478\ng1470\nF20.0\ntp1479\na(I2540000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb51@'\np1480\ntp1481\nRp1482\ng1470\nF19.0\ntp1483\na(I2550000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\1@'\np1484\ntp1485\nRp1486\ng1470\nF-18.0\ntp1487\na(I2560000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x191@'\np1488\ntp1489\nRp1490\ng1470\nF20.0\ntp1491\na(I2570000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f1@'\np1492\ntp1493\nRp1494\ng1470\nF19.0\ntp1495\na(I2580000\ng1\n(g5\nS'33333\\xf30@'\np1496\ntp1497\nRp1498\ng1470\nF16.0\ntp1499\na(I2590000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf80@'\np1500\ntp1501\nRp1502\ng1470\nF19.0\ntp1503\na(I2600000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x071@'\np1504\ntp1505\nRp1506\ng1470\nF14.0\ntp1507\na(I2610000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x111@'\np1508\ntp1509\nRp1510\ng1470\nF19.0\ntp1511\na(I2620000\ng1\n(g5\nS'q=\\n\\xd7\\xa301@'\np1512\ntp1513\nRp1514\ng1470\nF20.0\ntp1515\na(I2630000\ng1\n(g5\nS'fffff&1@'\np1516\ntp1517\nRp1518\ng1470\nF18.0\ntp1519\na(I2640000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(1@'\np1520\ntp1521\nRp1522\ng1470\nF17.0\ntp1523\na(I2650000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#1@'\np1524\ntp1525\nRp1526\ng1470\nF17.0\ntp1527\na(I2660000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#1@'\np1528\ntp1529\nRp1530\ng1470\nF19.0\ntp1531\na(I2670000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e1@'\np1532\ntp1533\nRp1534\ng1470\nF21.0\ntp1535\na(I2680000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x071@'\np1536\ntp1537\nRp1538\ng1470\nF21.0\ntp1539\na(I2690000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n1@'\np1540\ntp1541\nRp1542\ng1470\nF20.0\ntp1543\na(I2700000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG!1@'\np1544\ntp1545\nRp1546\ng1470\nF19.0\ntp1547\na(I2710000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.1@'\np1548\ntp1549\nRp1550\ng1470\nF18.0\ntp1551\na(I2720000\ng1\n(g5\nS'3333331@'\np1552\ntp1553\nRp1554\ng1470\nF20.0\ntp1555\na(I2730000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ1@'\np1556\ntp1557\nRp1558\ng1470\nF20.0\ntp1559\na(I2740000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb51@'\np1560\ntp1561\nRp1562\ng1470\nF18.0\ntp1563\na(I2750000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x142@'\np1564\ntp1565\nRp1566\ng1470\nF18.0\ntp1567\na(I2760000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y2@'\np1568\ntp1569\nRp1570\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa2@'\np1571\ntp1572\nRp1573\nF19.0\ntp1574\na(I2770000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k2@'\np1575\ntp1576\nRp1577\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k2@'\np1578\ntp1579\nRp1580\nF20.0\ntp1581\na(I2780000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k2@'\np1582\ntp1583\nRp1584\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n2@'\np1585\ntp1586\nRp1587\nF17.0\ntp1588\na(I2790000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa2@'\np1589\ntp1590\nRp1591\ng1587\nF19.0\ntp1592\na(I2800000\ng1\n(g5\nS'ffffff2@'\np1593\ntp1594\nRp1595\ng1\n(g5\nS'q=\\n\\xd7\\xa3p2@'\np1596\ntp1597\nRp1598\nF17.0\ntp1599\na(I2810000\ng1\n(g5\nS'33333s2@'\np1600\ntp1601\nRp1602\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx2@'\np1603\ntp1604\nRp1605\nF18.0\ntp1606\na(I2820000\ng1\n(g5\nS'33333s2@'\np1607\ntp1608\nRp1609\ng1605\nF19.0\ntp1610\na(I2830000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z2@'\np1611\ntp1612\nRp1613\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z2@'\np1614\ntp1615\nRp1616\nF20.0\ntp1617\na(I2840000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e2@'\np1618\ntp1619\nRp1620\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa12@'\np1621\ntp1622\nRp1623\nF18.0\ntp1624\na(I2850000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab2@'\np1625\ntp1626\nRp1627\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb02@'\np1628\ntp1629\nRp1630\nF17.0\ntp1631\na(I2860000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa32@'\np1632\ntp1633\nRp1634\ng1630\nF19.0\ntp1635\na(I2870000\ng1\n(g5\nS'fffff\\xa62@'\np1636\ntp1637\nRp1638\ng1630\nF15.0\ntp1639\na(I2880000\ng1\n(g5\nS'33333\\xb32@'\np1640\ntp1641\nRp1642\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba2@'\np1643\ntp1644\nRp1645\nF16.0\ntp1646\na(I2890000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba2@'\np1647\ntp1648\nRp1649\ng1645\nF19.0\ntp1650\na(I2900000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb82@'\np1651\ntp1652\nRp1653\ng1645\nF19.0\ntp1654\na(I2910000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd2@'\np1655\ntp1656\nRp1657\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc02@'\np1658\ntp1659\nRp1660\nF18.0\ntp1661\na(I2920000\ng1\n(g5\nS'fffff\\xa62@'\np1662\ntp1663\nRp1664\ng1660\nF21.0\ntp1665\na(I2930000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x992@'\np1666\ntp1667\nRp1668\ng1660\nF19.0\ntp1669\na(I2940000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab2@'\np1670\ntp1671\nRp1672\ng1660\nF19.0\ntp1673\na(I2950000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa12@'\np1674\ntp1675\nRp1676\ng1660\nF18.0\ntp1677\na(I2960000\ng1\n(g5\nS'33333\\xb32@'\np1678\ntp1679\nRp1680\ng1660\nF20.0\ntp1681\na(I2970000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb52@'\np1682\ntp1683\nRp1684\ng1660\nF21.0\ntp1685\na(I2980000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd2@'\np1686\ntp1687\nRp1688\ng1660\nF18.0\ntp1689\na(I2990000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc52@'\np1690\ntp1691\nRp1692\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc72@'\np1693\ntp1694\nRp1695\nF20.0\ntp1696\na(I3000000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba2@'\np1697\ntp1698\nRp1699\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf2@'\np1700\ntp1701\nRp1702\nF19.0\ntp1703\na(I3010000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb52@'\np1704\ntp1705\nRp1706\ng1702\nF21.0\ntp1707\na(I3020000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd2@'\np1708\ntp1709\nRp1710\ng1702\nF19.0\ntp1711\na(I3030000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab2@'\np1712\ntp1713\nRp1714\ng1702\nF19.0\ntp1715\na(I3040000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc02@'\np1716\ntp1717\nRp1718\ng1702\nF20.0\ntp1719\na(I3050000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd2@'\np1720\ntp1721\nRp1722\ng1702\nF16.0\ntp1723\na(I3060000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc22@'\np1724\ntp1725\nRp1726\ng1702\nF20.0\ntp1727\na(I3070000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xe32@'\np1728\ntp1729\nRp1730\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xe32@'\np1731\ntp1732\nRp1733\nF21.0\ntp1734\na(I3080000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf52@'\np1735\ntp1736\nRp1737\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf52@'\np1738\ntp1739\nRp1740\nF20.0\ntp1741\na(I3090000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf82@'\np1742\ntp1743\nRp1744\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x003@'\np1745\ntp1746\nRp1747\nF20.0\ntp1748\na(I3100000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x003@'\np1749\ntp1750\nRp1751\ng1747\nF18.0\ntp1752\na(I3110000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x113@'\np1753\ntp1754\nRp1755\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e3@'\np1756\ntp1757\nRp1758\nF21.0\ntp1759\na(I3120000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf52@'\np1760\ntp1761\nRp1762\ng1758\nF4.0\ntp1763\na(I3130000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfd2@'\np1764\ntp1765\nRp1766\ng1758\nF17.0\ntp1767\na(I3140000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfa2@'\np1768\ntp1769\nRp1770\ng1758\nF18.0\ntp1771\na(I3150000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfd2@'\np1772\ntp1773\nRp1774\ng1758\nF19.0\ntp1775\na(I3160000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x113@'\np1776\ntp1777\nRp1778\ng1758\nF20.0\ntp1779\na(I3170000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1c3@'\np1780\ntp1781\nRp1782\ng1758\nF20.0\ntp1783\na(I3180000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1c3@'\np1784\ntp1785\nRp1786\ng1\n(g5\nS'fffff&3@'\np1787\ntp1788\nRp1789\nF18.0\ntp1790\na(I3190000\ng1\n(g5\nS'q=\\n\\xd7\\xa303@'\np1791\ntp1792\nRp1793\ng1\n(g5\nS'q=\\n\\xd7\\xa303@'\np1794\ntp1795\nRp1796\nF20.0\ntp1797\na(I3200000\ng1\n(g5\nS'q=\\n\\xd7\\xa303@'\np1798\ntp1799\nRp1800\ng1\n(g5\nS'=\\n\\xd7\\xa3p=3@'\np1801\ntp1802\nRp1803\nF18.0\ntp1804\na(I3210000\ng1\n(g5\nS'fffff&3@'\np1805\ntp1806\nRp1807\ng1803\nF19.0\ntp1808\na(I3220000\ng1\n(g5\nS'q=\\n\\xd7\\xa303@'\np1809\ntp1810\nRp1811\ng1803\nF18.0\ntp1812\na(I3230000\ng1\n(g5\nS'q=\\n\\xd7\\xa303@'\np1813\ntp1814\nRp1815\ng1803\nF21.0\ntp1816\na(I3240000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL3@'\np1817\ntp1818\nRp1819\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL3@'\np1820\ntp1821\nRp1822\nF20.0\ntp1823\na(I3250000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O3@'\np1824\ntp1825\nRp1826\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\3@'\np1827\ntp1828\nRp1829\nF18.0\ntp1830\na(I3260000\ng1\n(g5\nS'\\n\\xd7\\xa3p=J3@'\np1831\ntp1832\nRp1833\ng1829\nF20.0\ntp1834\na(I3270000\ng1\n(g5\nS'\\n\\xd7\\xa3p=J3@'\np1835\ntp1836\nRp1837\ng1829\nF21.0\ntp1838\na(I3280000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE3@'\np1839\ntp1840\nRp1841\ng1829\nF19.0\ntp1842\na(I3290000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa3@'\np1843\ntp1844\nRp1845\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa3@'\np1846\ntp1847\nRp1848\nF20.0\ntp1849\na(I3300000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y3@'\np1850\ntp1851\nRp1852\ng1848\nF18.0\ntp1853\na(I3310000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x823@'\np1854\ntp1855\nRp1856\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x873@'\np1857\ntp1858\nRp1859\nF20.0\ntp1860\na(I3320000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c3@'\np1861\ntp1862\nRp1863\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c3@'\np1864\ntp1865\nRp1866\nF21.0\ntp1867\na(I3330000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x993@'\np1868\ntp1869\nRp1870\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa33@'\np1871\ntp1872\nRp1873\nF21.0\ntp1874\na(I3340000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e3@'\np1875\ntp1876\nRp1877\ng1873\nF21.0\ntp1878\na(I3350000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x993@'\np1879\ntp1880\nRp1881\ng1873\nF20.0\ntp1882\na(I3360000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x913@'\np1883\ntp1884\nRp1885\ng1873\nF19.0\ntp1886\na(I3370000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c3@'\np1887\ntp1888\nRp1889\ng1873\nF21.0\ntp1890\na(I3380000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c3@'\np1891\ntp1892\nRp1893\ng1873\nF20.0\ntp1894\na(I3390000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc23@'\np1895\ntp1896\nRp1897\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc23@'\np1898\ntp1899\nRp1900\nF21.0\ntp1901\na(I3400000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc23@'\np1902\ntp1903\nRp1904\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc53@'\np1905\ntp1906\nRp1907\nF19.0\ntp1908\na(I3410000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc73@'\np1909\ntp1910\nRp1911\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc3@'\np1912\ntp1913\nRp1914\nF19.0\ntp1915\na(I3420000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc23@'\np1916\ntp1917\nRp1918\ng1914\nF21.0\ntp1919\na(I3430000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb83@'\np1920\ntp1921\nRp1922\ng1914\nF15.0\ntp1923\na(I3440000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc53@'\np1924\ntp1925\nRp1926\ng1914\nF19.0\ntp1927\na(I3450000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc03@'\np1928\ntp1929\nRp1930\ng1914\nF21.0\ntp1931\na(I3460000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c3@'\np1932\ntp1933\nRp1934\ng1914\nF15.0\ntp1935\na(I3470000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x993@'\np1936\ntp1937\nRp1938\ng1914\nF21.0\ntp1939\na(I3480000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x913@'\np1940\ntp1941\nRp1942\ng1914\nF21.0\ntp1943\na(I3490000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f3@'\np1944\ntp1945\nRp1946\ng1914\nF21.0\ntp1947\na(I3500000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x973@'\np1948\ntp1949\nRp1950\ng1914\nF21.0\ntp1951\na(I3510000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa33@'\np1952\ntp1953\nRp1954\ng1914\nF19.0\ntp1955\na(I3520000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c3@'\np1956\ntp1957\nRp1958\ng1914\nF18.0\ntp1959\na(I3530000\ng1\n(g5\nS'fffff\\xa63@'\np1960\ntp1961\nRp1962\ng1914\nF20.0\ntp1963\na(I3540000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa13@'\np1964\ntp1965\nRp1966\ng1914\nF21.0\ntp1967\na(I3550000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa83@'\np1968\ntp1969\nRp1970\ng1914\nF21.0\ntp1971\na(I3560000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba3@'\np1972\ntp1973\nRp1974\ng1914\nF21.0\ntp1975\na(I3570000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc03@'\np1976\ntp1977\nRp1978\ng1914\nF20.0\ntp1979\na(I3580000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc53@'\np1980\ntp1981\nRp1982\ng1914\nF21.0\ntp1983\na(I3590000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc3@'\np1984\ntp1985\nRp1986\ng1914\nF20.0\ntp1987\na(I3600000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd73@'\np1988\ntp1989\nRp1990\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd73@'\np1991\ntp1992\nRp1993\nF21.0\ntp1994\na(I3610000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde3@'\np1995\ntp1996\nRp1997\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde3@'\np1998\ntp1999\nRp2000\nF17.0\ntp2001\na(I3620000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf53@'\np2002\ntp2003\nRp2004\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf53@'\np2005\ntp2006\nRp2007\nF20.0\ntp2008\na(I3630000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfd3@'\np2009\ntp2010\nRp2011\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfd3@'\np2012\ntp2013\nRp2014\nF21.0\ntp2015\na(I3640000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=4@'\np2016\ntp2017\nRp2018\ng1\n(g5\nS'=\\n\\xd7\\xa3p=4@'\np2019\ntp2020\nRp2021\nF21.0\ntp2022\na(I3650000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@4@'\np2023\ntp2024\nRp2025\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@4@'\np2026\ntp2027\nRp2028\nF21.0\ntp2029\na(I3660000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=4@'\np2030\ntp2031\nRp2032\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE4@'\np2033\ntp2034\nRp2035\nF20.0\ntp2036\na(I3670000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB4@'\np2037\ntp2038\nRp2039\ng2035\nF21.0\ntp2040\na(I3680000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG4@'\np2041\ntp2042\nRp2043\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG4@'\np2044\ntp2045\nRp2046\nF21.0\ntp2047\na(I3690000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG4@'\np2048\ntp2049\nRp2050\ng2046\nF21.0\ntp2051\na(I3700000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y4@'\np2052\ntp2053\nRp2054\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y4@'\np2055\ntp2056\nRp2057\nF21.0\ntp2058\na(I3710000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa4@'\np2059\ntp2060\nRp2061\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa4@'\np2062\ntp2063\nRp2064\nF21.0\ntp2065\na(I3720000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p4@'\np2066\ntp2067\nRp2068\ng1\n(g5\nS'q=\\n\\xd7\\xa3p4@'\np2069\ntp2070\nRp2071\nF21.0\ntp2072\na(I3730000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa4@'\np2073\ntp2074\nRp2075\ng2071\nF18.0\ntp2076\na(I3740000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zT4@'\np2077\ntp2078\nRp2079\ng2071\nF21.0\ntp2080\na(I3750000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^4@'\np2081\ntp2082\nRp2083\ng2071\nF21.0\ntp2084\na(I3760000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa4@'\np2085\ntp2086\nRp2087\ng2071\nF20.0\ntp2088\na(I3770000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h4@'\np2089\ntp2090\nRp2091\ng2071\nF21.0\ntp2092\na(I3780000\ng1\n(g5\nS'\\xa4p=\\n\\xd7c4@'\np2093\ntp2094\nRp2095\ng2071\nF21.0\ntp2096\na(I3790000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k4@'\np2097\ntp2098\nRp2099\ng2071\nF21.0\ntp2100\na(I3800000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k4@'\np2101\ntp2102\nRp2103\ng2071\nF21.0\ntp2104\na(I3810000\ng1\n(g5\nS'ffffff4@'\np2105\ntp2106\nRp2107\ng2071\nF20.0\ntp2108\na(I3820000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k4@'\np2109\ntp2110\nRp2111\ng2071\nF21.0\ntp2112\na(I3830000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p4@'\np2113\ntp2114\nRp2115\ng2071\nF19.0\ntp2116\na(I3840000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx4@'\np2117\ntp2118\nRp2119\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z4@'\np2120\ntp2121\nRp2122\nF21.0\ntp2123\na(I3850000\ng1\n(g5\nS'33333s4@'\np2124\ntp2125\nRp2126\ng2122\nF21.0\ntp2127\na(I3860000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx4@'\np2128\ntp2129\nRp2130\ng2122\nF20.0\ntp2131\na(I3870000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p4@'\np2132\ntp2133\nRp2134\ng2122\nF19.0\ntp2135\na(I3880000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u4@'\np2136\ntp2137\nRp2138\ng2122\nF21.0\ntp2139\na(I3890000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n4@'\np2140\ntp2141\nRp2142\ng2122\nF20.0\ntp2143\na(I3900000\ng1\n(g5\nS'33333s4@'\np2144\ntp2145\nRp2146\ng2122\nF21.0\ntp2147\na(I3910000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2148\ntp2149\nRp2150\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2151\ntp2152\nRp2153\nF21.0\ntp2154\na(I3920000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x804@'\np2155\ntp2156\nRp2157\ng2153\nF19.0\ntp2158\na(I3930000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h4@'\np2159\ntp2160\nRp2161\ng2153\nF19.0\ntp2162\na(I3940000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h4@'\np2163\ntp2164\nRp2165\ng2153\nF20.0\ntp2166\na(I3950000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h4@'\np2167\ntp2168\nRp2169\ng2153\nF21.0\ntp2170\na(I3960000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p4@'\np2171\ntp2172\nRp2173\ng2153\nF21.0\ntp2174\na(I3970000\ng1\n(g5\nS'ffffff4@'\np2175\ntp2176\nRp2177\ng2153\nF19.0\ntp2178\na(I3980000\ng1\n(g5\nS'\\xa4p=\\n\\xd7c4@'\np2179\ntp2180\nRp2181\ng2153\nF21.0\ntp2182\na(I3990000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n4@'\np2183\ntp2184\nRp2185\ng2153\nF21.0\ntp2186\na(I4000000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa4@'\np2187\ntp2188\nRp2189\ng2153\nF20.0\ntp2190\na(I4010000\ng1\n(g5\nS'\\xa4p=\\n\\xd7c4@'\np2191\ntp2192\nRp2193\ng2153\nF20.0\ntp2194\na(I4020000\ng1\n(g5\nS'\\xa4p=\\n\\xd7c4@'\np2195\ntp2196\nRp2197\ng2153\nF21.0\ntp2198\na(I4030000\ng1\n(g5\nS'\\xa4p=\\n\\xd7c4@'\np2199\ntp2200\nRp2201\ng2153\nF21.0\ntp2202\na(I4040000\ng1\n(g5\nS'ffffff4@'\np2203\ntp2204\nRp2205\ng2153\nF20.0\ntp2206\na(I4050000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n4@'\np2207\ntp2208\nRp2209\ng2153\nF21.0\ntp2210\na(I4060000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n4@'\np2211\ntp2212\nRp2213\ng2153\nF21.0\ntp2214\na(I4070000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h4@'\np2215\ntp2216\nRp2217\ng2153\nF21.0\ntp2218\na(I4080000\ng1\n(g5\nS'ffffff4@'\np2219\ntp2220\nRp2221\ng2153\nF20.0\ntp2222\na(I4090000\ng1\n(g5\nS'\\xa4p=\\n\\xd7c4@'\np2223\ntp2224\nRp2225\ng2153\nF21.0\ntp2226\na(I4100000\ng1\n(g5\nS'33333s4@'\np2227\ntp2228\nRp2229\ng2153\nF20.0\ntp2230\na(I4110000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx4@'\np2231\ntp2232\nRp2233\ng2153\nF21.0\ntp2234\na(I4120000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z4@'\np2235\ntp2236\nRp2237\ng2153\nF21.0\ntp2238\na(I4130000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u4@'\np2239\ntp2240\nRp2241\ng2153\nF20.0\ntp2242\na(I4140000\ng1\n(g5\nS'33333s4@'\np2243\ntp2244\nRp2245\ng2153\nF21.0\ntp2246\na(I4150000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z4@'\np2247\ntp2248\nRp2249\ng2153\nF21.0\ntp2250\na(I4160000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx4@'\np2251\ntp2252\nRp2253\ng2153\nF21.0\ntp2254\na(I4170000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2255\ntp2256\nRp2257\ng2153\nF21.0\ntp2258\na(I4180000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a4@'\np2259\ntp2260\nRp2261\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a4@'\np2262\ntp2263\nRp2264\nF21.0\ntp2265\na(I4190000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x944@'\np2266\ntp2267\nRp2268\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x944@'\np2269\ntp2270\nRp2271\nF21.0\ntp2272\na(I4200000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x944@'\np2273\ntp2274\nRp2275\ng2271\nF21.0\ntp2276\na(I4210000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x974@'\np2277\ntp2278\nRp2279\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x974@'\np2280\ntp2281\nRp2282\nF21.0\ntp2283\na(I4220000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x974@'\np2284\ntp2285\nRp2286\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x994@'\np2287\ntp2288\nRp2289\nF20.0\ntp2290\na(I4230000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c4@'\np2291\ntp2292\nRp2293\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c4@'\np2294\ntp2295\nRp2296\nF21.0\ntp2297\na(I4240000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa34@'\np2298\ntp2299\nRp2300\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa34@'\np2301\ntp2302\nRp2303\nF21.0\ntp2304\na(I4250000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np2305\ntp2306\nRp2307\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np2308\ntp2309\nRp2310\nF21.0\ntp2311\na(I4260000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np2312\ntp2313\nRp2314\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np2315\ntp2316\nRp2317\nF21.0\ntp2318\na(I4270000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np2319\ntp2320\nRp2321\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np2322\ntp2323\nRp2324\nF21.0\ntp2325\na(I4280000\ng1\n(g5\nS'33333\\xb34@'\np2326\ntp2327\nRp2328\ng2324\nF21.0\ntp2329\na(I4290000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np2330\ntp2331\nRp2332\ng2324\nF21.0\ntp2333\na(I4300000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np2334\ntp2335\nRp2336\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np2337\ntp2338\nRp2339\nF21.0\ntp2340\na(I4310000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np2341\ntp2342\nRp2343\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np2344\ntp2345\nRp2346\nF20.0\ntp2347\na(I4320000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np2348\ntp2349\nRp2350\ng2346\nF20.0\ntp2351\na(I4330000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np2352\ntp2353\nRp2354\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np2355\ntp2356\nRp2357\nF20.0\ntp2358\na(I4340000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np2359\ntp2360\nRp2361\ng2357\nF21.0\ntp2362\na(I4350000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np2363\ntp2364\nRp2365\ng2357\nF21.0\ntp2366\na(I4360000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np2367\ntp2368\nRp2369\ng2357\nF21.0\ntp2370\na(I4370000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np2371\ntp2372\nRp2373\ng2357\nF20.0\ntp2374\na(I4380000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np2375\ntp2376\nRp2377\ng2357\nF21.0\ntp2378\na(I4390000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np2379\ntp2380\nRp2381\ng2357\nF21.0\ntp2382\na(I4400000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np2383\ntp2384\nRp2385\ng2357\nF21.0\ntp2386\na(I4410000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np2387\ntp2388\nRp2389\ng2357\nF21.0\ntp2390\na(I4420000\ng1\n(g5\nS'33333\\xb34@'\np2391\ntp2392\nRp2393\ng2357\nF21.0\ntp2394\na(I4430000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np2395\ntp2396\nRp2397\ng2357\nF21.0\ntp2398\na(I4440000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np2399\ntp2400\nRp2401\ng2357\nF21.0\ntp2402\na(I4450000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np2403\ntp2404\nRp2405\ng2357\nF21.0\ntp2406\na(I4460000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np2407\ntp2408\nRp2409\ng2357\nF20.0\ntp2410\na(I4470000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa34@'\np2411\ntp2412\nRp2413\ng2357\nF21.0\ntp2414\na(I4480000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np2415\ntp2416\nRp2417\ng2357\nF21.0\ntp2418\na(I4490000\ng1\n(g5\nS'fffff\\xa64@'\np2419\ntp2420\nRp2421\ng2357\nF20.0\ntp2422\na(I4500000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e4@'\np2423\ntp2424\nRp2425\ng2357\nF21.0\ntp2426\na(I4510000\ng1\n(g5\nS'fffff\\xa64@'\np2427\ntp2428\nRp2429\ng2357\nF21.0\ntp2430\na(I4520000\ng1\n(g5\nS'fffff\\xa64@'\np2431\ntp2432\nRp2433\ng2357\nF21.0\ntp2434\na(I4530000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa14@'\np2435\ntp2436\nRp2437\ng2357\nF21.0\ntp2438\na(I4540000\ng1\n(g5\nS'fffff\\xa64@'\np2439\ntp2440\nRp2441\ng2357\nF21.0\ntp2442\na(I4550000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e4@'\np2443\ntp2444\nRp2445\ng2357\nF21.0\ntp2446\na(I4560000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e4@'\np2447\ntp2448\nRp2449\ng2357\nF21.0\ntp2450\na(I4570000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e4@'\np2451\ntp2452\nRp2453\ng2357\nF20.0\ntp2454\na(I4580000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e4@'\np2455\ntp2456\nRp2457\ng2357\nF20.0\ntp2458\na(I4590000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np2459\ntp2460\nRp2461\ng2357\nF21.0\ntp2462\na(I4600000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa14@'\np2463\ntp2464\nRp2465\ng2357\nF21.0\ntp2466\na(I4610000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c4@'\np2467\ntp2468\nRp2469\ng2357\nF21.0\ntp2470\na(I4620000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c4@'\np2471\ntp2472\nRp2473\ng2357\nF21.0\ntp2474\na(I4630000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c4@'\np2475\ntp2476\nRp2477\ng2357\nF21.0\ntp2478\na(I4640000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x994@'\np2479\ntp2480\nRp2481\ng2357\nF21.0\ntp2482\na(I4650000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x944@'\np2483\ntp2484\nRp2485\ng2357\nF20.0\ntp2486\na(I4660000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x994@'\np2487\ntp2488\nRp2489\ng2357\nF21.0\ntp2490\na(I4670000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e4@'\np2491\ntp2492\nRp2493\ng2357\nF21.0\ntp2494\na(I4680000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x944@'\np2495\ntp2496\nRp2497\ng2357\nF20.0\ntp2498\na(I4690000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x944@'\np2499\ntp2500\nRp2501\ng2357\nF20.0\ntp2502\na(I4700000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x914@'\np2503\ntp2504\nRp2505\ng2357\nF21.0\ntp2506\na(I4710000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c4@'\np2507\ntp2508\nRp2509\ng2357\nF21.0\ntp2510\na(I4720000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x914@'\np2511\ntp2512\nRp2513\ng2357\nF21.0\ntp2514\na(I4730000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c4@'\np2515\ntp2516\nRp2517\ng2357\nF21.0\ntp2518\na(I4740000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x914@'\np2519\ntp2520\nRp2521\ng2357\nF21.0\ntp2522\na(I4750000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x944@'\np2523\ntp2524\nRp2525\ng2357\nF21.0\ntp2526\na(I4760000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x944@'\np2527\ntp2528\nRp2529\ng2357\nF21.0\ntp2530\na(I4770000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x994@'\np2531\ntp2532\nRp2533\ng2357\nF21.0\ntp2534\na(I4780000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e4@'\np2535\ntp2536\nRp2537\ng2357\nF21.0\ntp2538\na(I4790000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa14@'\np2539\ntp2540\nRp2541\ng2357\nF21.0\ntp2542\na(I4800000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa34@'\np2543\ntp2544\nRp2545\ng2357\nF21.0\ntp2546\na(I4810000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np2547\ntp2548\nRp2549\ng2357\nF21.0\ntp2550\na(I4820000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np2551\ntp2552\nRp2553\ng2357\nF21.0\ntp2554\na(I4830000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np2555\ntp2556\nRp2557\ng2357\nF21.0\ntp2558\na(I4840000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np2559\ntp2560\nRp2561\ng2357\nF21.0\ntp2562\na(I4850000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np2563\ntp2564\nRp2565\ng2357\nF21.0\ntp2566\na(I4860000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np2567\ntp2568\nRp2569\ng2357\nF20.0\ntp2570\na(I4870000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np2571\ntp2572\nRp2573\ng2357\nF20.0\ntp2574\na(I4880000\ng1\n(g5\nS'33333\\xb34@'\np2575\ntp2576\nRp2577\ng2357\nF21.0\ntp2578\na(I4890000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np2579\ntp2580\nRp2581\ng2357\nF21.0\ntp2582\na(I4900000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa34@'\np2583\ntp2584\nRp2585\ng2357\nF13.0\ntp2586\na(I4910000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa14@'\np2587\ntp2588\nRp2589\ng2357\nF20.0\ntp2590\na(I4920000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e4@'\np2591\ntp2592\nRp2593\ng2357\nF20.0\ntp2594\na(I4930000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c4@'\np2595\ntp2596\nRp2597\ng2357\nF21.0\ntp2598\na(I4940000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa14@'\np2599\ntp2600\nRp2601\ng2357\nF21.0\ntp2602\na(I4950000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e4@'\np2603\ntp2604\nRp2605\ng2357\nF20.0\ntp2606\na(I4960000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e4@'\np2607\ntp2608\nRp2609\ng2357\nF21.0\ntp2610\na(I4970000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c4@'\np2611\ntp2612\nRp2613\ng2357\nF21.0\ntp2614\na(I4980000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c4@'\np2615\ntp2616\nRp2617\ng2357\nF21.0\ntp2618\na(I4990000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e4@'\np2619\ntp2620\nRp2621\ng2357\nF21.0\ntp2622\na(I5000000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x914@'\np2623\ntp2624\nRp2625\ng2357\nF19.0\ntp2626\na(I5010000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x974@'\np2627\ntp2628\nRp2629\ng2357\nF21.0\ntp2630\na(I5020000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x994@'\np2631\ntp2632\nRp2633\ng2357\nF21.0\ntp2634\na(I5030000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x974@'\np2635\ntp2636\nRp2637\ng2357\nF21.0\ntp2638\na(I5040000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x974@'\np2639\ntp2640\nRp2641\ng2357\nF20.0\ntp2642\na(I5050000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x994@'\np2643\ntp2644\nRp2645\ng2357\nF20.0\ntp2646\na(I5060000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x944@'\np2647\ntp2648\nRp2649\ng2357\nF21.0\ntp2650\na(I5070000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x974@'\np2651\ntp2652\nRp2653\ng2357\nF21.0\ntp2654\na(I5080000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np2655\ntp2656\nRp2657\ng2357\nF21.0\ntp2658\na(I5090000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa34@'\np2659\ntp2660\nRp2661\ng2357\nF21.0\ntp2662\na(I5100000\ng1\n(g5\nS'fffff\\xa64@'\np2663\ntp2664\nRp2665\ng2357\nF21.0\ntp2666\na(I5110000\ng1\n(g5\nS'fffff\\xa64@'\np2667\ntp2668\nRp2669\ng2357\nF21.0\ntp2670\na(I5120000\ng1\n(g5\nS'fffff\\xa64@'\np2671\ntp2672\nRp2673\ng2357\nF21.0\ntp2674\na(I5130000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np2675\ntp2676\nRp2677\ng2357\nF21.0\ntp2678\na(I5140000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np2679\ntp2680\nRp2681\ng2357\nF21.0\ntp2682\na(I5150000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np2683\ntp2684\nRp2685\ng2357\nF21.0\ntp2686\na(I5160000\ng1\n(g5\nS'33333\\xb34@'\np2687\ntp2688\nRp2689\ng2357\nF21.0\ntp2690\na(I5170000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np2691\ntp2692\nRp2693\ng2357\nF21.0\ntp2694\na(I5180000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np2695\ntp2696\nRp2697\ng2357\nF21.0\ntp2698\na(I5190000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np2699\ntp2700\nRp2701\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np2702\ntp2703\nRp2704\nF20.0\ntp2705\na(I5200000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np2706\ntp2707\nRp2708\ng2704\nF21.0\ntp2709\na(I5210000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np2710\ntp2711\nRp2712\ng2704\nF21.0\ntp2713\na(I5220000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np2714\ntp2715\nRp2716\ng2704\nF21.0\ntp2717\na(I5230000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np2718\ntp2719\nRp2720\ng2704\nF21.0\ntp2721\na(I5240000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np2722\ntp2723\nRp2724\ng2704\nF21.0\ntp2725\na(I5250000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np2726\ntp2727\nRp2728\ng2704\nF20.0\ntp2729\na(I5260000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np2730\ntp2731\nRp2732\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np2733\ntp2734\nRp2735\nF20.0\ntp2736\na(I5270000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np2737\ntp2738\nRp2739\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf4@'\np2740\ntp2741\nRp2742\nF20.0\ntp2743\na(I5280000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np2744\ntp2745\nRp2746\ng2742\nF21.0\ntp2747\na(I5290000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np2748\ntp2749\nRp2750\ng2742\nF21.0\ntp2751\na(I5300000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np2752\ntp2753\nRp2754\ng2742\nF21.0\ntp2755\na(I5310000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np2756\ntp2757\nRp2758\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd14@'\np2759\ntp2760\nRp2761\nF20.0\ntp2762\na(I5320000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np2763\ntp2764\nRp2765\ng2761\nF21.0\ntp2766\na(I5330000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np2767\ntp2768\nRp2769\ng2761\nF20.0\ntp2770\na(I5340000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np2771\ntp2772\nRp2773\ng2761\nF21.0\ntp2774\na(I5350000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np2775\ntp2776\nRp2777\ng2761\nF20.0\ntp2778\na(I5360000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np2779\ntp2780\nRp2781\ng2761\nF21.0\ntp2782\na(I5370000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np2783\ntp2784\nRp2785\ng2761\nF21.0\ntp2786\na(I5380000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np2787\ntp2788\nRp2789\ng2761\nF21.0\ntp2790\na(I5390000\ng1\n(g5\nS'33333\\xb34@'\np2791\ntp2792\nRp2793\ng2761\nF19.0\ntp2794\na(I5400000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np2795\ntp2796\nRp2797\ng2761\nF20.0\ntp2798\na(I5410000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np2799\ntp2800\nRp2801\ng2761\nF21.0\ntp2802\na(I5420000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np2803\ntp2804\nRp2805\ng2761\nF20.0\ntp2806\na(I5430000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np2807\ntp2808\nRp2809\ng2761\nF21.0\ntp2810\na(I5440000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np2811\ntp2812\nRp2813\ng2761\nF21.0\ntp2814\na(I5450000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np2815\ntp2816\nRp2817\ng2761\nF21.0\ntp2818\na(I5460000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np2819\ntp2820\nRp2821\ng2761\nF21.0\ntp2822\na(I5470000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np2823\ntp2824\nRp2825\ng2761\nF21.0\ntp2826\na(I5480000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np2827\ntp2828\nRp2829\ng2761\nF20.0\ntp2830\na(I5490000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np2831\ntp2832\nRp2833\ng2761\nF21.0\ntp2834\na(I5500000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np2835\ntp2836\nRp2837\ng2761\nF18.0\ntp2838\na(I5510000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np2839\ntp2840\nRp2841\ng2761\nF20.0\ntp2842\na(I5520000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np2843\ntp2844\nRp2845\ng2761\nF21.0\ntp2846\na(I5530000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np2847\ntp2848\nRp2849\ng2761\nF20.0\ntp2850\na(I5540000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np2851\ntp2852\nRp2853\ng2761\nF21.0\ntp2854\na(I5550000\ng1\n(g5\nS'33333\\xb34@'\np2855\ntp2856\nRp2857\ng2761\nF21.0\ntp2858\na(I5560000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np2859\ntp2860\nRp2861\ng2761\nF21.0\ntp2862\na(I5570000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np2863\ntp2864\nRp2865\ng2761\nF20.0\ntp2866\na(I5580000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np2867\ntp2868\nRp2869\ng2761\nF20.0\ntp2870\na(I5590000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np2871\ntp2872\nRp2873\ng2761\nF21.0\ntp2874\na(I5600000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np2875\ntp2876\nRp2877\ng2761\nF20.0\ntp2878\na(I5610000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np2879\ntp2880\nRp2881\ng2761\nF21.0\ntp2882\na(I5620000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np2883\ntp2884\nRp2885\ng2761\nF20.0\ntp2886\na(I5630000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np2887\ntp2888\nRp2889\ng2761\nF21.0\ntp2890\na(I5640000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np2891\ntp2892\nRp2893\ng2761\nF21.0\ntp2894\na(I5650000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np2895\ntp2896\nRp2897\ng2761\nF21.0\ntp2898\na(I5660000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np2899\ntp2900\nRp2901\ng2761\nF21.0\ntp2902\na(I5670000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np2903\ntp2904\nRp2905\ng2761\nF21.0\ntp2906\na(I5680000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np2907\ntp2908\nRp2909\ng2761\nF21.0\ntp2910\na(I5690000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np2911\ntp2912\nRp2913\ng2761\nF20.0\ntp2914\na(I5700000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np2915\ntp2916\nRp2917\ng2761\nF21.0\ntp2918\na(I5710000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np2919\ntp2920\nRp2921\ng2761\nF21.0\ntp2922\na(I5720000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np2923\ntp2924\nRp2925\ng2761\nF20.0\ntp2926\na(I5730000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np2927\ntp2928\nRp2929\ng2761\nF20.0\ntp2930\na(I5740000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np2931\ntp2932\nRp2933\ng2761\nF20.0\ntp2934\na(I5750000\ng1\n(g5\nS'33333\\xb34@'\np2935\ntp2936\nRp2937\ng2761\nF21.0\ntp2938\na(I5760000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np2939\ntp2940\nRp2941\ng2761\nF21.0\ntp2942\na(I5770000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np2943\ntp2944\nRp2945\ng2761\nF21.0\ntp2946\na(I5780000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np2947\ntp2948\nRp2949\ng2761\nF21.0\ntp2950\na(I5790000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np2951\ntp2952\nRp2953\ng2761\nF21.0\ntp2954\na(I5800000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np2955\ntp2956\nRp2957\ng2761\nF21.0\ntp2958\na(I5810000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np2959\ntp2960\nRp2961\ng2761\nF20.0\ntp2962\na(I5820000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa14@'\np2963\ntp2964\nRp2965\ng2761\nF21.0\ntp2966\na(I5830000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa14@'\np2967\ntp2968\nRp2969\ng2761\nF21.0\ntp2970\na(I5840000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c4@'\np2971\ntp2972\nRp2973\ng2761\nF18.0\ntp2974\na(I5850000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e4@'\np2975\ntp2976\nRp2977\ng2761\nF21.0\ntp2978\na(I5860000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e4@'\np2979\ntp2980\nRp2981\ng2761\nF20.0\ntp2982\na(I5870000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa14@'\np2983\ntp2984\nRp2985\ng2761\nF20.0\ntp2986\na(I5880000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e4@'\np2987\ntp2988\nRp2989\ng2761\nF21.0\ntp2990\na(I5890000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa14@'\np2991\ntp2992\nRp2993\ng2761\nF21.0\ntp2994\na(I5900000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa14@'\np2995\ntp2996\nRp2997\ng2761\nF20.0\ntp2998\na(I5910000\ng1\n(g5\nS'fffff\\xa64@'\np2999\ntp3000\nRp3001\ng2761\nF21.0\ntp3002\na(I5920000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3003\ntp3004\nRp3005\ng2761\nF21.0\ntp3006\na(I5930000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np3007\ntp3008\nRp3009\ng2761\nF21.0\ntp3010\na(I5940000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np3011\ntp3012\nRp3013\ng2761\nF21.0\ntp3014\na(I5950000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np3015\ntp3016\nRp3017\ng2761\nF20.0\ntp3018\na(I5960000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np3019\ntp3020\nRp3021\ng2761\nF20.0\ntp3022\na(I5970000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np3023\ntp3024\nRp3025\ng2761\nF21.0\ntp3026\na(I5980000\ng1\n(g5\nS'33333\\xb34@'\np3027\ntp3028\nRp3029\ng2761\nF21.0\ntp3030\na(I5990000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np3031\ntp3032\nRp3033\ng2761\nF21.0\ntp3034\na(I6000000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np3035\ntp3036\nRp3037\ng2761\nF21.0\ntp3038\na(I6010000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np3039\ntp3040\nRp3041\ng2761\nF21.0\ntp3042\na(I6020000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3043\ntp3044\nRp3045\ng2761\nF20.0\ntp3046\na(I6030000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np3047\ntp3048\nRp3049\ng2761\nF21.0\ntp3050\na(I6040000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np3051\ntp3052\nRp3053\ng2761\nF21.0\ntp3054\na(I6050000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np3055\ntp3056\nRp3057\ng2761\nF21.0\ntp3058\na(I6060000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3059\ntp3060\nRp3061\ng2761\nF21.0\ntp3062\na(I6070000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3063\ntp3064\nRp3065\ng2761\nF21.0\ntp3066\na(I6080000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3067\ntp3068\nRp3069\ng2761\nF21.0\ntp3070\na(I6090000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np3071\ntp3072\nRp3073\ng2761\nF20.0\ntp3074\na(I6100000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3075\ntp3076\nRp3077\ng2761\nF21.0\ntp3078\na(I6110000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3079\ntp3080\nRp3081\ng2761\nF21.0\ntp3082\na(I6120000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3083\ntp3084\nRp3085\ng2761\nF21.0\ntp3086\na(I6130000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3087\ntp3088\nRp3089\ng2761\nF20.0\ntp3090\na(I6140000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np3091\ntp3092\nRp3093\ng2761\nF21.0\ntp3094\na(I6150000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3095\ntp3096\nRp3097\ng2761\nF19.0\ntp3098\na(I6160000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3099\ntp3100\nRp3101\ng2761\nF20.0\ntp3102\na(I6170000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np3103\ntp3104\nRp3105\ng2761\nF21.0\ntp3106\na(I6180000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np3107\ntp3108\nRp3109\ng2761\nF21.0\ntp3110\na(I6190000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3111\ntp3112\nRp3113\ng2761\nF21.0\ntp3114\na(I6200000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3115\ntp3116\nRp3117\ng2761\nF21.0\ntp3118\na(I6210000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np3119\ntp3120\nRp3121\ng2761\nF20.0\ntp3122\na(I6220000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd14@'\np3123\ntp3124\nRp3125\ng2761\nF21.0\ntp3126\na(I6230000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd44@'\np3127\ntp3128\nRp3129\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd44@'\np3130\ntp3131\nRp3132\nF21.0\ntp3133\na(I6240000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd14@'\np3134\ntp3135\nRp3136\ng3132\nF21.0\ntp3137\na(I6250000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd14@'\np3138\ntp3139\nRp3140\ng3132\nF21.0\ntp3141\na(I6260000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd74@'\np3142\ntp3143\nRp3144\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd74@'\np3145\ntp3146\nRp3147\nF21.0\ntp3148\na(I6270000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd74@'\np3149\ntp3150\nRp3151\ng3147\nF21.0\ntp3152\na(I6280000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd14@'\np3153\ntp3154\nRp3155\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xd94@'\np3156\ntp3157\nRp3158\nF20.0\ntp3159\na(I6290000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xd94@'\np3160\ntp3161\nRp3162\ng3158\nF21.0\ntp3163\na(I6300000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc4@'\np3164\ntp3165\nRp3166\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc4@'\np3167\ntp3168\nRp3169\nF21.0\ntp3170\na(I6310000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xd94@'\np3171\ntp3172\nRp3173\ng3169\nF20.0\ntp3174\na(I6320000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc4@'\np3175\ntp3176\nRp3177\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde4@'\np3178\ntp3179\nRp3180\nF21.0\ntp3181\na(I6330000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd74@'\np3182\ntp3183\nRp3184\ng3180\nF21.0\ntp3185\na(I6340000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd44@'\np3186\ntp3187\nRp3188\ng3180\nF21.0\ntp3189\na(I6350000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf4@'\np3190\ntp3191\nRp3192\ng3180\nF21.0\ntp3193\na(I6360000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf4@'\np3194\ntp3195\nRp3196\ng3180\nF20.0\ntp3197\na(I6370000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np3198\ntp3199\nRp3200\ng3180\nF21.0\ntp3201\na(I6380000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3202\ntp3203\nRp3204\ng3180\nF20.0\ntp3205\na(I6390000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np3206\ntp3207\nRp3208\ng3180\nF21.0\ntp3209\na(I6400000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np3210\ntp3211\nRp3212\ng3180\nF21.0\ntp3213\na(I6410000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np3214\ntp3215\nRp3216\ng3180\nF21.0\ntp3217\na(I6420000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np3218\ntp3219\nRp3220\ng3180\nF21.0\ntp3221\na(I6430000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np3222\ntp3223\nRp3224\ng3180\nF21.0\ntp3225\na(I6440000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np3226\ntp3227\nRp3228\ng3180\nF21.0\ntp3229\na(I6450000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np3230\ntp3231\nRp3232\ng3180\nF21.0\ntp3233\na(I6460000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np3234\ntp3235\nRp3236\ng3180\nF21.0\ntp3237\na(I6470000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np3238\ntp3239\nRp3240\ng3180\nF21.0\ntp3241\na(I6480000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3242\ntp3243\nRp3244\ng3180\nF21.0\ntp3245\na(I6490000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np3246\ntp3247\nRp3248\ng3180\nF21.0\ntp3249\na(I6500000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np3250\ntp3251\nRp3252\ng3180\nF21.0\ntp3253\na(I6510000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3254\ntp3255\nRp3256\ng3180\nF21.0\ntp3257\na(I6520000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3258\ntp3259\nRp3260\ng3180\nF21.0\ntp3261\na(I6530000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3262\ntp3263\nRp3264\ng3180\nF21.0\ntp3265\na(I6540000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3266\ntp3267\nRp3268\ng3180\nF20.0\ntp3269\na(I6550000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np3270\ntp3271\nRp3272\ng3180\nF21.0\ntp3273\na(I6560000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np3274\ntp3275\nRp3276\ng3180\nF21.0\ntp3277\na(I6570000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3278\ntp3279\nRp3280\ng3180\nF21.0\ntp3281\na(I6580000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np3282\ntp3283\nRp3284\ng3180\nF21.0\ntp3285\na(I6590000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np3286\ntp3287\nRp3288\ng3180\nF20.0\ntp3289\na(I6600000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3290\ntp3291\nRp3292\ng3180\nF21.0\ntp3293\na(I6610000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3294\ntp3295\nRp3296\ng3180\nF21.0\ntp3297\na(I6620000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3298\ntp3299\nRp3300\ng3180\nF21.0\ntp3301\na(I6630000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3302\ntp3303\nRp3304\ng3180\nF21.0\ntp3305\na(I6640000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3306\ntp3307\nRp3308\ng3180\nF21.0\ntp3309\na(I6650000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3310\ntp3311\nRp3312\ng3180\nF21.0\ntp3313\na(I6660000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3314\ntp3315\nRp3316\ng3180\nF21.0\ntp3317\na(I6670000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf4@'\np3318\ntp3319\nRp3320\ng3180\nF21.0\ntp3321\na(I6680000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np3322\ntp3323\nRp3324\ng3180\nF20.0\ntp3325\na(I6690000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np3326\ntp3327\nRp3328\ng3180\nF20.0\ntp3329\na(I6700000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3330\ntp3331\nRp3332\ng3180\nF21.0\ntp3333\na(I6710000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np3334\ntp3335\nRp3336\ng3180\nF21.0\ntp3337\na(I6720000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3338\ntp3339\nRp3340\ng3180\nF20.0\ntp3341\na(I6730000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3342\ntp3343\nRp3344\ng3180\nF21.0\ntp3345\na(I6740000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3346\ntp3347\nRp3348\ng3180\nF21.0\ntp3349\na(I6750000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np3350\ntp3351\nRp3352\ng3180\nF21.0\ntp3353\na(I6760000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd14@'\np3354\ntp3355\nRp3356\ng3180\nF21.0\ntp3357\na(I6770000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd14@'\np3358\ntp3359\nRp3360\ng3180\nF20.0\ntp3361\na(I6780000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf4@'\np3362\ntp3363\nRp3364\ng3180\nF20.0\ntp3365\na(I6790000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd14@'\np3366\ntp3367\nRp3368\ng3180\nF20.0\ntp3369\na(I6800000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf4@'\np3370\ntp3371\nRp3372\ng3180\nF21.0\ntp3373\na(I6810000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf4@'\np3374\ntp3375\nRp3376\ng3180\nF20.0\ntp3377\na(I6820000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf4@'\np3378\ntp3379\nRp3380\ng3180\nF21.0\ntp3381\na(I6830000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np3382\ntp3383\nRp3384\ng3180\nF21.0\ntp3385\na(I6840000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np3386\ntp3387\nRp3388\ng3180\nF21.0\ntp3389\na(I6850000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np3390\ntp3391\nRp3392\ng3180\nF21.0\ntp3393\na(I6860000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np3394\ntp3395\nRp3396\ng3180\nF20.0\ntp3397\na(I6870000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np3398\ntp3399\nRp3400\ng3180\nF21.0\ntp3401\na(I6880000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np3402\ntp3403\nRp3404\ng3180\nF21.0\ntp3405\na(I6890000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd14@'\np3406\ntp3407\nRp3408\ng3180\nF21.0\ntp3409\na(I6900000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd14@'\np3410\ntp3411\nRp3412\ng3180\nF21.0\ntp3413\na(I6910000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np3414\ntp3415\nRp3416\ng3180\nF21.0\ntp3417\na(I6920000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np3418\ntp3419\nRp3420\ng3180\nF21.0\ntp3421\na(I6930000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3422\ntp3423\nRp3424\ng3180\nF20.0\ntp3425\na(I6940000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3426\ntp3427\nRp3428\ng3180\nF21.0\ntp3429\na(I6950000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np3430\ntp3431\nRp3432\ng3180\nF21.0\ntp3433\na(I6960000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np3434\ntp3435\nRp3436\ng3180\nF21.0\ntp3437\na(I6970000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np3438\ntp3439\nRp3440\ng3180\nF21.0\ntp3441\na(I6980000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np3442\ntp3443\nRp3444\ng3180\nF21.0\ntp3445\na(I6990000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3446\ntp3447\nRp3448\ng3180\nF21.0\ntp3449\na(I7000000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3450\ntp3451\nRp3452\ng3180\nF21.0\ntp3453\na(I7010000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3454\ntp3455\nRp3456\ng3180\nF21.0\ntp3457\na(I7020000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3458\ntp3459\nRp3460\ng3180\nF21.0\ntp3461\na(I7030000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np3462\ntp3463\nRp3464\ng3180\nF20.0\ntp3465\na(I7040000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np3466\ntp3467\nRp3468\ng3180\nF21.0\ntp3469\na(I7050000\ng1\n(g5\nS'33333\\xb34@'\np3470\ntp3471\nRp3472\ng3180\nF20.0\ntp3473\na(I7060000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np3474\ntp3475\nRp3476\ng3180\nF21.0\ntp3477\na(I7070000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np3478\ntp3479\nRp3480\ng3180\nF21.0\ntp3481\na(I7080000\ng1\n(g5\nS'fffff\\xa64@'\np3482\ntp3483\nRp3484\ng3180\nF20.0\ntp3485\na(I7090000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np3486\ntp3487\nRp3488\ng3180\nF21.0\ntp3489\na(I7100000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3490\ntp3491\nRp3492\ng3180\nF21.0\ntp3493\na(I7110000\ng1\n(g5\nS'33333\\xb34@'\np3494\ntp3495\nRp3496\ng3180\nF20.0\ntp3497\na(I7120000\ng1\n(g5\nS'33333\\xb34@'\np3498\ntp3499\nRp3500\ng3180\nF21.0\ntp3501\na(I7130000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np3502\ntp3503\nRp3504\ng3180\nF21.0\ntp3505\na(I7140000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3506\ntp3507\nRp3508\ng3180\nF21.0\ntp3509\na(I7150000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3510\ntp3511\nRp3512\ng3180\nF21.0\ntp3513\na(I7160000\ng1\n(g5\nS'33333\\xb34@'\np3514\ntp3515\nRp3516\ng3180\nF21.0\ntp3517\na(I7170000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3518\ntp3519\nRp3520\ng3180\nF20.0\ntp3521\na(I7180000\ng1\n(g5\nS'33333\\xb34@'\np3522\ntp3523\nRp3524\ng3180\nF20.0\ntp3525\na(I7190000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np3526\ntp3527\nRp3528\ng3180\nF21.0\ntp3529\na(I7200000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np3530\ntp3531\nRp3532\ng3180\nF21.0\ntp3533\na(I7210000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3534\ntp3535\nRp3536\ng3180\nF21.0\ntp3537\na(I7220000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np3538\ntp3539\nRp3540\ng3180\nF21.0\ntp3541\na(I7230000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np3542\ntp3543\nRp3544\ng3180\nF21.0\ntp3545\na(I7240000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np3546\ntp3547\nRp3548\ng3180\nF20.0\ntp3549\na(I7250000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np3550\ntp3551\nRp3552\ng3180\nF21.0\ntp3553\na(I7260000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3554\ntp3555\nRp3556\ng3180\nF21.0\ntp3557\na(I7270000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np3558\ntp3559\nRp3560\ng3180\nF21.0\ntp3561\na(I7280000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np3562\ntp3563\nRp3564\ng3180\nF21.0\ntp3565\na(I7290000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np3566\ntp3567\nRp3568\ng3180\nF21.0\ntp3569\na(I7300000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3570\ntp3571\nRp3572\ng3180\nF21.0\ntp3573\na(I7310000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np3574\ntp3575\nRp3576\ng3180\nF21.0\ntp3577\na(I7320000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np3578\ntp3579\nRp3580\ng3180\nF21.0\ntp3581\na(I7330000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np3582\ntp3583\nRp3584\ng3180\nF21.0\ntp3585\na(I7340000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np3586\ntp3587\nRp3588\ng3180\nF21.0\ntp3589\na(I7350000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3590\ntp3591\nRp3592\ng3180\nF21.0\ntp3593\na(I7360000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np3594\ntp3595\nRp3596\ng3180\nF21.0\ntp3597\na(I7370000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3598\ntp3599\nRp3600\ng3180\nF21.0\ntp3601\na(I7380000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3602\ntp3603\nRp3604\ng3180\nF21.0\ntp3605\na(I7390000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3606\ntp3607\nRp3608\ng3180\nF21.0\ntp3609\na(I7400000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3610\ntp3611\nRp3612\ng3180\nF21.0\ntp3613\na(I7410000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np3614\ntp3615\nRp3616\ng3180\nF21.0\ntp3617\na(I7420000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf4@'\np3618\ntp3619\nRp3620\ng3180\nF21.0\ntp3621\na(I7430000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd74@'\np3622\ntp3623\nRp3624\ng3180\nF21.0\ntp3625\na(I7440000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xd94@'\np3626\ntp3627\nRp3628\ng3180\nF21.0\ntp3629\na(I7450000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd74@'\np3630\ntp3631\nRp3632\ng3180\nF21.0\ntp3633\na(I7460000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd14@'\np3634\ntp3635\nRp3636\ng3180\nF21.0\ntp3637\na(I7470000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np3638\ntp3639\nRp3640\ng3180\nF21.0\ntp3641\na(I7476493\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np3642\ntp3643\nRp3644\ng3180\nF21.0\ntp3645\na.(lp0\nF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-18.0\naF-19.0\naF-20.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-19.0\naF-21.0\naF-20.0\naF-19.0\naF-19.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-18.0\naF-20.0\naF-21.0\naF-19.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-19.0\naF-20.0\naF-18.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-19.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-17.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-18.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-19.0\naF-19.0\naF-21.0\naF-20.0\naF-21.0\naF-19.0\naF-20.0\naF-21.0\naF-20.0\naF-20.0\naF-19.0\naF-21.0\naF-20.0\naF-19.0\naF-21.0\naF-19.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-21.0\naF-20.0\naF-19.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-19.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-19.0\naF-21.0\naF-19.0\naF-21.0\naF-21.0\naF-21.0\naF-19.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-19.0\naF-20.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-20.0\naF-21.0\naF-19.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-19.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-20.0\naF-19.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-19.0\naF-20.0\naF-18.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-19.0\naF-19.0\naF-20.0\naF-18.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-19.0\naF-21.0\naF-19.0\naF-19.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-21.0\naF-19.0\naF-20.0\naF-21.0\naF-20.0\naF-19.0\naF-19.0\naF-20.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-18.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-18.0\naF-19.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-19.0\naF-19.0\naF-21.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-19.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-19.0\naF-21.0\naF-21.0\naF-20.0\naF-18.0\naF-20.0\naF-20.0\naF-21.0\naF-19.0\naF-21.0\naF-19.0\naF-19.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-19.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-19.0\naF-21.0\naF-18.0\naF-20.0\naF-20.0\naF-17.0\naF-21.0\naF-21.0\naF-21.0\naF-19.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-18.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-19.0\naF-20.0\naF-19.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-19.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-20.0\naF-19.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-19.0\naF-20.0\naF-20.0\naF-20.0\naF-21.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-19.0\naF-21.0\naF-20.0\naF-20.0\naF-19.0\naF-20.0\naF-19.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-17.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-19.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-19.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-19.0\naF-20.0\naF-21.0\naF-20.0\naF-19.0\naF-20.0\naF-20.0\naF-21.0\naF-18.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-18.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-19.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-19.0\naF-20.0\naF-19.0\naF-20.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-20.0\naF-21.0\naF-18.0\naF-21.0\naF-19.0\naF-20.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-19.0\naF-19.0\naF-16.0\naF-20.0\naF-20.0\naF-20.0\naF-21.0\naF-19.0\naF-20.0\naF-18.0\naF-19.0\naF-19.0\naF-17.0\naF-18.0\naF-16.0\naF-18.0\naF-20.0\naF-20.0\naF-19.0\naF-20.0\naF-20.0\naF-19.0\naF-20.0\naF-18.0\naF-19.0\naF-21.0\naF-17.0\naF-16.0\naF-19.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-18.0\naF-17.0\naF-14.0\naF-14.0\naF-16.0\naF-19.0\naF-20.0\naF-19.0\naF-20.0\naF-15.0\naF-18.0\naF-16.0\naF-19.0\naF-18.0\naF-18.0\naF-17.0\naF-18.0\naF-18.0\naF-17.0\naF-18.0\naF-20.0\naF-20.0\naF-19.0\naF-18.0\naF-20.0\naF-19.0\naF-18.0\naF-18.0\naF-19.0\naF-17.0\naF-18.0\naF-18.0\naF-20.0\naF-18.0\naF-16.0\naF-18.0\naF-19.0\naF-20.0\naF-19.0\naF-19.0\naF-20.0\naF-16.0\naF-21.0\naF-18.0\naF-17.0\naF-18.0\naF-15.0\naF-19.0\naF-15.0\naF-17.0\naF-19.0\naF-19.0\naF-17.0\naF-16.0\naF-19.0\naF-18.0\naF-19.0\naF-16.0\naF-19.0\naF-18.0\naF-18.0\naF-20.0\naF-15.0\naF-18.0\naF-16.0\naF-19.0\naF-17.0\naF-15.0\naF-18.0\naF-18.0\naF-18.0\naF-14.0\naF-19.0\naF-16.0\naF-17.0\naF-18.0\naF-17.0\naF-21.0\naF-17.0\naF-17.0\naF-17.0\naF-15.0\naF-18.0\naF-16.0\naF-16.0\naF-19.0\naF-17.0\naF-15.0\naF-16.0\naF-19.0\naF-18.0\naF-17.0\naF-17.0\naF-20.0\naF-15.0\naF-16.0\naF-18.0\naF-17.0\naF-18.0\naF-17.0\naF-16.0\naF-18.0\naF-16.0\naF-17.0\naF-18.0\naF-18.0\naF-21.0\naF-14.0\naF-18.0\naF-16.0\naF-19.0\naF-18.0\naF-19.0\naF-15.0\naF-19.0\naF-14.0\naF-16.0\naF-19.0\naF-14.0\naF-17.0\naF-17.0\naF-16.0\naF-16.0\naF-19.0\naF-20.0\naF-9.0\naF-18.0\naF-19.0\naF-17.0\naF-16.0\naF-18.0\naF-17.0\naF-18.0\naF-20.0\naF-14.0\naF-18.0\naF-18.0\naF-20.0\naF-19.0\naF-18.0\naF-15.0\naF-20.0\naF-18.0\naF-19.0\naF-15.0\naF-18.0\naF-18.0\naF-17.0\naF-18.0\naF-19.0\naF-17.0\naF-18.0\naF-17.0\naF-17.0\naF-16.0\naF-18.0\naF-15.0\naF-17.0\naF-15.0\naF-20.0\naF-16.0\naF-19.0\naF-20.0\naF-15.0\naF-14.0\naF-16.0\naF-10.0\naF-15.0\naF-15.0\naF-19.0\naF-14.0\naF-12.0\naF-20.0\naF-16.0\naF-18.0\naF-19.0\naF-16.0\naF-13.0\naF-19.0\naF-15.0\naF-20.0\naF-14.0\naF-15.0\naF-17.0\naF-14.0\naF-14.0\naF-9.0\naF-16.0\naF-17.0\naF-9.0\naF-19.0\naF-14.0\naF-16.0\naF-13.0\naF-17.0\naF-11.0\naF-18.0\naF-15.0\naF-20.0\naF-17.0\naF-13.0\naF-13.0\naF-11.0\naF-16.0\naF-18.0\naF-14.0\naF-16.0\naF-17.0\naF-12.0\naF-17.0\naF-18.0\naF-19.0\naF-18.0\naF-18.0\naF-18.0\naF-11.0\naF-13.0\naF-18.0\naF-14.0\naF-16.0\naF-14.0\naF-8.0\naF-16.0\naF-14.0\naF-18.0\naF-15.0\naF-13.0\naF-15.0\naF-7.0\naF-16.0\naF-11.0\naF-17.0\naF-13.0\naF-9.0\naF-17.0\naF-13.0\naF-17.0\naF-16.0\naF-13.0\naF-14.0\naF-15.0\naF-15.0\naF-16.0\naF-18.0\naF-11.0\naF-9.0\naF-11.0\naF-14.0\naF-11.0\naF-18.0\naF-14.0\naF-12.0\naF-14.0\naF-14.0\naF-13.0\naF-10.0\naF-17.0\naF-10.0\naF-15.0\naF2.0\naF-12.0\naF-15.0\naF-13.0\naF-15.0\naF-12.0\naF-14.0\naF-8.0\naF-13.0\naF-12.0\naF-16.0\naF-14.0\naF-13.0\naF-7.0\naF-12.0\naF-15.0\naF-11.0\naF-18.0\naF-15.0\naF3.0\naF-6.0\naF-14.0\naF-5.0\naF-8.0\naF-16.0\naF-10.0\naF-13.0\naF-8.0\naF-5.0\naF-14.0\naF-16.0\naF-7.0\naF-10.0\naF-9.0\naF-13.0\naF-14.0\naF-14.0\naF-10.0\naF-8.0\naF-8.0\naF-7.0\naF-13.0\naF-12.0\naF-8.0\naF-7.0\naF-12.0\naF-7.0\naF-10.0\naF-7.0\naF-19.0\naF-16.0\naF-5.0\naF-1.0\naF-7.0\naF-12.0\naF-16.0\naF-16.0\naF-17.0\naF-10.0\naF-7.0\naF-15.0\naF5.0\naF-7.0\naF-10.0\naF-13.0\naF-13.0\naF-8.0\naF-9.0\naF-13.0\naF-12.0\naF-2.0\naF-12.0\naF-6.0\naF-5.0\naF-13.0\naF-10.0\naF-6.0\naF-2.0\naF-14.0\naF-2.0\naF-10.0\naF-10.0\naF-4.0\naF1.0\naF-6.0\naF-13.0\naF4.0\naF-9.0\naF-16.0\naF1.0\naF-10.0\naF1.0\naF1.0\naF-6.0\naF-5.0\naF-6.0\naF-8.0\naF6.0\naF-5.0\naF-4.0\naF-3.0\naF-8.0\naF-9.0\naF-4.0\naF-7.0\naF-4.0\naF3.0\naF-3.0\naF-4.0\naF-5.0\naF7.0\naF-4.0\naF-1.0\naF-14.0\naF-8.0\naF1.0\naF-12.0\naF-5.0\naF-9.0\naF4.0\naF-2.0\naF-1.0\naF-2.0\naF-3.0\naF2.0\naF2.0\naF7.0\naF-8.0\naF7.0\naF2.0\naF-6.0\naF-1.0\naF3.0\naF4.0\naF2.0\naF-6.0\naF2.0\naF-2.0\naF-1.0\naF-2.0\naF-6.0\naF-3.0\naF3.0\naF9.0\naF3.0\naF-1.0\naF2.0\naF2.0\naF-6.0\naF-6.0\naF4.0\naF-10.0\naF5.0\naF7.0\naF2.0\naF4.0\naF-1.0\naF16.0\naF2.0\naF7.0\naF4.0\naF2.0\naF-3.0\naF-5.0\naF3.0\naF6.0\naF1.0\naF3.0\naF7.0\naF2.0\naF9.0\naF13.0\naF4.0\naF4.0\naF6.0\naF5.0\naF5.0\naF9.0\naF8.0\naF10.0\naF8.0\naF10.0\naF8.0\naF11.0\naF11.0\naF8.0\naF8.0\naF14.0\naF-9.0\naF9.0\naF6.0\naF2.0\naF8.0\naF-4.0\naF12.0\naF6.0\naF8.0\naF7.0\naF-2.0\naF8.0\naF1.0\naF15.0\naF9.0\naF12.0\naF8.0\naF15.0\naF9.0\naF5.0\naF16.0\naF12.0\naF9.0\naF11.0\naF14.0\naF15.0\naF17.0\naF9.0\naF9.0\naF18.0\naF18.0\naF8.0\naF9.0\naF19.0\naF13.0\naF19.0\naF7.0\naF12.0\naF9.0\naF14.0\naF14.0\naF13.0\naF14.0\naF12.0\naF19.0\naF13.0\naF10.0\naF17.0\naF17.0\naF14.0\naF15.0\naF17.0\naF20.0\naF15.0\naF19.0\naF12.0\naF17.0\naF19.0\naF16.0\naF14.0\naF10.0\naF18.0\naF15.0\naF15.0\naF17.0\naF12.0\naF17.0\naF18.0\naF17.0\naF15.0\naF15.0\naF16.0\naF14.0\naF14.0\naF17.0\naF16.0\naF15.0\naF15.0\naF17.0\naF15.0\naF21.0\naF17.0\naF16.0\naF16.0\naF17.0\naF18.0\naF19.0\naF17.0\naF12.0\naF17.0\naF20.0\naF18.0\naF14.0\naF17.0\naF18.0\naF13.0\naF20.0\naF18.0\naF14.0\naF20.0\naF12.0\naF18.0\naF17.0\naF14.0\naF17.0\naF16.0\naF15.0\naF19.0\naF17.0\naF14.0\naF18.0\naF16.0\naF17.0\naF18.0\naF12.0\naF13.0\naF18.0\naF18.0\naF18.0\naF18.0\naF15.0\naF20.0\naF19.0\naF18.0\naF16.0\naF16.0\naF14.0\naF19.0\naF18.0\naF19.0\naF15.0\naF19.0\naF14.0\naF19.0\naF20.0\naF19.0\naF16.0\naF18.0\naF17.0\naF16.0\naF15.0\naF19.0\naF18.0\naF17.0\naF19.0\naF17.0\naF14.0\naF14.0\naF17.0\naF15.0\naF13.0\naF17.0\naF17.0\naF18.0\naF17.0\naF10.0\naF19.0\naF18.0\naF14.0\naF20.0\naF18.0\naF19.0\naF17.0\naF17.0\naF18.0\naF15.0\naF17.0\naF15.0\naF15.0\naF15.0\naF16.0\naF19.0\naF19.0\naF17.0\naF6.0\naF18.0\naF15.0\naF18.0\naF-7.0\naF6.0\naF-9.0\naF18.0\naF18.0\naF18.0\naF18.0\naF17.0\naF19.0\naF15.0\naF18.0\naF20.0\naF14.0\naF16.0\naF16.0\naF20.0\naF19.0\naF14.0\naF15.0\naF17.0\naF13.0\naF17.0\naF18.0\naF18.0\naF21.0\naF18.0\naF19.0\naF18.0\naF14.0\naF20.0\naF20.0\naF18.0\naF19.0\naF18.0\naF17.0\naF19.0\naF18.0\naF20.0\naF18.0\naF13.0\naF20.0\naF18.0\naF13.0\naF19.0\naF18.0\naF18.0\naF11.0\naF18.0\naF20.0\naF20.0\naF18.0\naF20.0\naF16.0\naF17.0\naF19.0\naF16.0\naF15.0\naF19.0\naF19.0\naF18.0\naF15.0\naF12.0\naF16.0\naF16.0\naF18.0\naF19.0\naF18.0\naF16.0\naF16.0\naF20.0\naF17.0\naF16.0\naF-8.0\naF-15.0\naF-12.0\naF20.0\naF16.0\naF14.0\naF20.0\naF20.0\naF20.0\naF18.0\naF19.0\naF19.0\naF17.0\naF19.0\naF20.0\naF20.0\naF13.0\naF18.0\naF18.0\naF16.0\naF18.0\naF13.0\naF11.0\naF20.0\naF16.0\naF20.0\naF18.0\naF15.0\naF19.0\naF17.0\naF16.0\naF16.0\naF18.0\naF16.0\naF17.0\naF16.0\naF17.0\naF17.0\naF20.0\naF18.0\naF21.0\naF14.0\naF16.0\naF19.0\naF16.0\naF18.0\naF19.0\naF18.0\naF6.0\naF21.0\naF14.0\naF21.0\naF14.0\naF15.0\naF19.0\naF18.0\naF5.0\naF20.0\naF19.0\naF17.0\naF17.0\naF20.0\naF20.0\naF19.0\naF16.0\naF18.0\naF18.0\naF18.0\naF18.0\naF16.0\naF17.0\naF19.0\naF12.0\naF19.0\naF19.0\naF17.0\naF19.0\naF19.0\naF17.0\naF18.0\naF19.0\naF21.0\naF19.0\naF15.0\naF19.0\naF18.0\naF18.0\naF18.0\naF18.0\naF19.0\naF18.0\naF18.0\naF19.0\naF13.0\naF19.0\naF17.0\naF20.0\naF14.0\naF21.0\naF16.0\naF18.0\naF20.0\naF17.0\naF16.0\naF13.0\naF8.0\naF21.0\naF20.0\naF17.0\naF19.0\naF20.0\naF18.0\naF17.0\naF20.0\naF18.0\naF17.0\naF19.0\naF18.0\naF17.0\naF18.0\naF19.0\naF20.0\naF5.0\naF19.0\naF18.0\naF17.0\naF20.0\naF18.0\naF18.0\naF18.0\naF20.0\naF21.0\naF16.0\naF17.0\naF19.0\naF17.0\naF20.0\naF19.0\naF20.0\naF20.0\naF19.0\naF19.0\naF19.0\naF20.0\naF21.0\naF18.0\naF18.0\naF17.0\naF19.0\naF16.0\naF17.0\naF17.0\naF15.0\naF18.0\naF18.0\naF18.0\naF20.0\naF18.0\naF19.0\naF19.0\naF17.0\naF17.0\naF17.0\naF16.0\naF15.0\naF18.0\naF18.0\naF20.0\naF19.0\naF21.0\naF20.0\naF16.0\naF16.0\naF17.0\naF16.0\naF15.0\naF15.0\naF20.0\naF20.0\naF19.0\naF18.0\naF18.0\naF18.0\naF18.0\naF20.0\naF20.0\naF19.0\naF19.0\naF18.0\naF20.0\naF19.0\naF15.0\naF20.0\naF20.0\naF17.0\naF18.0\naF19.0\naF18.0\naF18.0\naF17.0\naF20.0\naF20.0\naF10.0\naF18.0\naF18.0\naF20.0\naF17.0\naF18.0\naF17.0\naF16.0\naF19.0\naF17.0\naF19.0\naF20.0\naF16.0\naF19.0\naF20.0\naF18.0\naF20.0\naF9.0\naF20.0\naF-11.0\naF8.0\naF19.0\naF18.0\naF17.0\naF18.0\naF20.0\naF19.0\naF-18.0\naF-4.0\naF12.0\naF20.0\naF19.0\naF20.0\naF16.0\naF19.0\naF18.0\naF19.0\naF13.0\naF17.0\naF21.0\naF19.0\naF16.0\naF18.0\naF20.0\naF20.0\naF18.0\naF19.0\naF18.0\naF20.0\naF17.0\naF20.0\naF14.0\naF21.0\naF17.0\naF20.0\naF20.0\naF19.0\naF16.0\naF20.0\naF18.0\naF20.0\naF19.0\naF20.0\naF18.0\naF18.0\naF19.0\naF19.0\naF18.0\naF18.0\naF21.0\naF14.0\naF17.0\naF12.0\naF19.0\naF17.0\naF19.0\naF17.0\naF16.0\naF18.0\naF19.0\naF19.0\naF20.0\naF19.0\naF19.0\naF20.0\naF17.0\naF17.0\naF21.0\naF17.0\naF18.0\naF20.0\naF6.0\naF21.0\naF16.0\naF18.0\naF18.0\naF19.0\naF20.0\naF16.0\naF21.0\naF19.0\naF20.0\naF19.0\naF16.0\naF20.0\naF19.0\naF20.0\naF18.0\naF16.0\naF19.0\naF19.0\naF19.0\naF20.0\naF20.0\naF18.0\naF20.0\naF20.0\naF20.0\naF20.0\naF20.0\naF19.0\naF16.0\naF18.0\naF17.0\naF21.0\naF18.0\naF19.0\naF18.0\naF19.0\naF19.0\naF18.0\naF19.0\naF19.0\naF16.0\naF18.0\naF20.0\naF18.0\naF20.0\naF18.0\naF17.0\naF19.0\naF20.0\naF17.0\naF19.0\naF20.0\naF18.0\naF15.0\naF19.0\naF19.0\naF18.0\naF19.0\naF21.0\naF17.0\naF20.0\naF18.0\naF19.0\naF21.0\naF21.0\naF18.0\naF20.0\naF20.0\naF18.0\naF18.0\naF19.0\naF19.0\naF20.0\naF19.0\naF17.0\naF20.0\naF21.0\naF19.0\naF19.0\naF20.0\naF18.0\naF14.0\naF19.0\naF20.0\naF21.0\naF20.0\naF17.0\naF18.0\naF18.0\naF21.0\naF18.0\naF19.0\naF20.0\naF15.0\naF20.0\naF21.0\naF15.0\naF19.0\naF15.0\naF17.0\naF19.0\naF16.0\naF20.0\naF17.0\naF20.0\naF19.0\naF17.0\naF20.0\naF18.0\naF19.0\naF21.0\naF19.0\naF20.0\naF20.0\naF20.0\naF16.0\naF18.0\naF8.0\naF19.0\naF19.0\naF20.0\naF21.0\naF16.0\naF21.0\naF19.0\naF20.0\naF19.0\naF19.0\naF20.0\naF19.0\naF19.0\naF20.0\naF19.0\naF20.0\naF19.0\naF14.0\naF18.0\naF19.0\naF19.0\naF20.0\naF20.0\naF19.0\naF20.0\naF19.0\naF16.0\naF21.0\naF16.0\naF21.0\naF20.0\naF18.0\naF20.0\naF21.0\naF18.0\naF18.0\naF18.0\naF17.0\naF20.0\naF21.0\naF20.0\naF21.0\naF15.0\naF19.0\naF17.0\naF19.0\naF19.0\naF17.0\naF19.0\naF19.0\naF21.0\naF20.0\naF21.0\naF18.0\naF19.0\naF18.0\naF19.0\naF19.0\naF18.0\naF18.0\naF18.0\naF19.0\naF19.0\naF20.0\naF21.0\naF20.0\naF20.0\naF18.0\naF21.0\naF17.0\naF21.0\naF16.0\naF19.0\naF18.0\naF16.0\naF21.0\naF20.0\naF18.0\naF19.0\naF20.0\naF21.0\naF20.0\naF21.0\naF18.0\naF21.0\naF19.0\naF21.0\naF20.0\naF21.0\naF18.0\naF16.0\naF21.0\naF20.0\naF20.0\naF19.0\naF20.0\naF19.0\naF20.0\naF18.0\naF20.0\naF12.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF19.0\naF21.0\naF4.0\naF19.0\naF21.0\naF21.0\naF20.0\naF21.0\naF17.0\naF19.0\naF19.0\naF20.0\naF13.0\naF18.0\naF20.0\naF21.0\naF20.0\naF19.0\naF19.0\naF19.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF19.0\naF20.0\naF19.0\naF21.0\naF20.0\naF20.0\naF19.0\naF19.0\naF21.0\naF20.0\naF18.0\naF20.0\naF20.0\naF18.0\naF19.0\naF20.0\naF19.0\naF21.0\naF20.0\naF18.0\naF18.0\naF17.0\naF18.0\naF16.0\naF20.0\naF20.0\naF19.0\naF21.0\naF19.0\naF18.0\naF20.0\naF18.0\naF21.0\naF19.0\naF20.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF19.0\naF21.0\naF20.0\naF21.0\naF16.0\naF18.0\naF18.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF17.0\naF20.0\naF21.0\naF21.0\naF20.0\naF16.0\naF19.0\naF21.0\naF19.0\naF19.0\naF21.0\naF19.0\naF21.0\naF19.0\naF20.0\naF20.0\naF20.0\naF20.0\naF21.0\naF19.0\naF18.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF20.0\naF18.0\naF21.0\naF20.0\naF20.0\naF21.0\naF19.0\naF21.0\naF15.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF18.0\naF21.0\naF19.0\naF18.0\naF19.0\naF21.0\naF20.0\naF19.0\naF20.0\naF20.0\naF19.0\naF20.0\naF19.0\naF20.0\naF21.0\naF19.0\naF19.0\naF21.0\naF20.0\naF19.0\naF20.0\naF20.0\naF20.0\naF19.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF18.0\naF19.0\naF20.0\naF20.0\naF21.0\naF21.0\naF18.0\naF19.0\naF21.0\naF21.0\naF20.0\naF17.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF15.0\naF19.0\naF18.0\naF21.0\naF20.0\naF19.0\naF16.0\naF20.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF3.0\naF20.0\naF18.0\naF15.0\naF21.0\naF20.0\naF19.0\naF21.0\naF21.0\naF21.0\naF18.0\naF19.0\naF19.0\naF21.0\naF21.0\naF19.0\naF19.0\naF20.0\naF19.0\naF21.0\naF20.0\naF20.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF19.0\naF21.0\naF20.0\naF20.0\naF20.0\naF18.0\naF21.0\naF21.0\naF17.0\naF21.0\naF20.0\naF20.0\naF17.0\naF20.0\naF19.0\naF21.0\naF19.0\naF19.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF19.0\naF20.0\naF21.0\naF19.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF19.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF17.0\naF20.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF18.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF20.0\naF18.0\naF20.0\naF20.0\naF18.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF18.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF19.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF19.0\naF21.0\naF21.0\naF18.0\naF18.0\naF19.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF18.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF20.0\naF21.0\naF19.0\naF20.0\naF20.0\naF19.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF20.0\naF19.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF20.0\naF21.0\naF19.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF20.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF13.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF19.0\naF19.0\naF20.0\naF21.0\naF20.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF17.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF18.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF18.0\naF21.0\naF21.0\naF21.0\naF20.0\naF19.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF18.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF19.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF19.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF18.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF19.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF18.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF19.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF18.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF18.0\naF21.0\naF21.0\naF13.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF19.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF19.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF18.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF19.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF19.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF19.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF18.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF18.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF18.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF19.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF18.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF18.0\naF21.0\naF20.0\naF21.0\na."
  },
  {
    "path": "dqn/logs_pkls/Pong_s002.pkl",
    "content": "(lp0\n(I60000\ncnumpy.core.multiarray\nscalar\np1\n(cnumpy\ndtype\np2\n(S'f8'\np3\nI0\nI1\ntp4\nRp5\n(I3\nS'<'\np6\nNNNI-1\nI-1\nI0\ntp7\nbS'Q\\x14EQ\\x14E4\\xc0'\np8\ntp9\nRp10\nF-inf\nF-19.0\ntp11\na(I70000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ4\\xc0'\np12\ntp13\nRp14\nF-inf\nF-20.0\ntp15\na(I80000\ng1\n(g5\nS'6eMYSV4\\xc0'\np16\ntp17\nRp18\nF-inf\nF-20.0\ntp19\na(I90000\ng1\n(g5\nS'\\xab\\xaa\\xaa\\xaa\\xaaJ4\\xc0'\np20\ntp21\nRp22\nF-inf\nF-19.0\ntp23\na(I100000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE4\\xc0'\np24\ntp25\nRp26\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@4\\xc0'\np27\ntp28\nRp29\nF-21.0\ntp30\na(I110000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:4\\xc0'\np31\ntp32\nRp33\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:4\\xc0'\np34\ntp35\nRp36\nF-21.0\ntp37\na(I120000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB4\\xc0'\np38\ntp39\nRp40\ng36\nF-19.0\ntp41\na(I130000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:4\\xc0'\np42\ntp43\nRp44\ng36\nF-19.0\ntp45\na(I140000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB4\\xc0'\np46\ntp47\nRp48\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ84\\xc0'\np49\ntp50\nRp51\nF-21.0\ntp52\na(I150000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG4\\xc0'\np53\ntp54\nRp55\ng51\nF-21.0\ntp56\na(I160000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ4\\xc0'\np57\ntp58\nRp59\ng51\nF-20.0\ntp60\na(I170000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@4\\xc0'\np61\ntp62\nRp63\ng51\nF-20.0\ntp64\na(I180000\ng1\n(g5\nS'\\n\\xd7\\xa3p=J4\\xc0'\np65\ntp66\nRp67\ng51\nF-21.0\ntp68\na(I190000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW4\\xc0'\np69\ntp70\nRp71\ng51\nF-21.0\ntp72\na(I200000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ4\\xc0'\np73\ntp74\nRp75\ng51\nF-21.0\ntp76\na(I210000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zT4\\xc0'\np77\ntp78\nRp79\ng51\nF-19.0\ntp80\na(I220000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW4\\xc0'\np81\ntp82\nRp83\ng51\nF-20.0\ntp84\na(I230000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zT4\\xc0'\np85\ntp86\nRp87\ng51\nF-20.0\ntp88\na(I240000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O4\\xc0'\np89\ntp90\nRp91\ng51\nF-20.0\ntp92\na(I250000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB4\\xc0'\np93\ntp94\nRp95\ng51\nF-18.0\ntp96\na(I260000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE4\\xc0'\np97\ntp98\nRp99\ng51\nF-21.0\ntp100\na(I270000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=4\\xc0'\np101\ntp102\nRp103\ng51\nF-20.0\ntp104\na(I280000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@4\\xc0'\np105\ntp106\nRp107\ng51\nF-20.0\ntp108\na(I290000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc254\\xc0'\np109\ntp110\nRp111\ng1\n(g5\nS'3333334\\xc0'\np112\ntp113\nRp114\nF-20.0\ntp115\na(I300000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(4\\xc0'\np116\ntp117\nRp118\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(4\\xc0'\np119\ntp120\nRp121\nF-17.0\ntp122\na(I310000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ84\\xc0'\np123\ntp124\nRp125\ng121\nF-21.0\ntp126\na(I320000\ng1\n(g5\nS'q=\\n\\xd7\\xa304\\xc0'\np127\ntp128\nRp129\ng121\nF-20.0\ntp130\na(I330000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB4\\xc0'\np131\ntp132\nRp133\ng121\nF-20.0\ntp134\na(I340000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc254\\xc0'\np135\ntp136\nRp137\ng121\nF-21.0\ntp138\na(I350000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB4\\xc0'\np139\ntp140\nRp141\ng121\nF-21.0\ntp142\na(I360000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85+4\\xc0'\np143\ntp144\nRp145\ng121\nF-19.0\ntp146\na(I370000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x114\\xc0'\np147\ntp148\nRp149\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x114\\xc0'\np150\ntp151\nRp152\nF-19.0\ntp153\na(I380000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0c4\\xc0'\np154\ntp155\nRp156\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n4\\xc0'\np157\ntp158\nRp159\nF-19.0\ntp160\na(I390000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x024\\xc0'\np161\ntp162\nRp163\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x024\\xc0'\np164\ntp165\nRp166\nF-19.0\ntp167\na(I400000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe83\\xc0'\np168\ntp169\nRp170\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe83\\xc0'\np171\ntp172\nRp173\nF-18.0\ntp174\na(I410000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd13\\xc0'\np175\ntp176\nRp177\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd13\\xc0'\np178\ntp179\nRp180\nF-19.0\ntp181\na(I420000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa83\\xc0'\np182\ntp183\nRp184\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa83\\xc0'\np185\ntp186\nRp187\nF-20.0\ntp188\na(I430000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f3\\xc0'\np189\ntp190\nRp191\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f3\\xc0'\np192\ntp193\nRp194\nF-15.0\ntp195\na(I440000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^3\\xc0'\np196\ntp197\nRp198\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^3\\xc0'\np199\ntp200\nRp201\nF-17.0\ntp202\na(I450000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.3\\xc0'\np203\ntp204\nRp205\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.3\\xc0'\np206\ntp207\nRp208\nF-19.0\ntp209\na(I460000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x173\\xc0'\np210\ntp211\nRp212\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x173\\xc0'\np213\ntp214\nRp215\nF-19.0\ntp216\na(I470000\ng1\n(g5\nS'fffff\\xe62\\xc0'\np217\ntp218\nRp219\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xe32\\xc0'\np220\ntp221\nRp222\nF-20.0\ntp223\na(I480000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc72\\xc0'\np224\ntp225\nRp226\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc72\\xc0'\np227\ntp228\nRp229\nF-18.0\ntp230\na(I490000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb82\\xc0'\np231\ntp232\nRp233\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb52\\xc0'\np234\ntp235\nRp236\nF-19.0\ntp237\na(I500000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x822\\xc0'\np238\ntp239\nRp240\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x822\\xc0'\np241\ntp242\nRp243\nF-17.0\ntp244\na(I510000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p2\\xc0'\np245\ntp246\nRp247\ng1\n(g5\nS'q=\\n\\xd7\\xa3p2\\xc0'\np248\ntp249\nRp250\nF-21.0\ntp251\na(I520000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.2\\xc0'\np252\ntp253\nRp254\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.2\\xc0'\np255\ntp256\nRp257\nF-14.0\ntp258\na(I530000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0c2\\xc0'\np259\ntp260\nRp261\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0c2\\xc0'\np262\ntp263\nRp264\nF-19.0\ntp265\na(I540000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf01\\xc0'\np266\ntp267\nRp268\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf01\\xc0'\np269\ntp270\nRp271\nF-18.0\ntp272\na(I550000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe11\\xc0'\np273\ntp274\nRp275\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe11\\xc0'\np276\ntp277\nRp278\nF-17.0\ntp279\na(I560000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\xde1\\xc0'\np280\ntp281\nRp282\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc1\\xc0'\np283\ntp284\nRp285\nF-18.0\ntp286\na(I570000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc71\\xc0'\np287\ntp288\nRp289\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc71\\xc0'\np290\ntp291\nRp292\nF-16.0\ntp293\na(I580000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa11\\xc0'\np294\ntp295\nRp296\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa11\\xc0'\np297\ntp298\nRp299\nF-18.0\ntp300\na(I590000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba1\\xc0'\np301\ntp302\nRp303\ng299\nF-18.0\ntp304\na(I600000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa81\\xc0'\np305\ntp306\nRp307\ng299\nF-17.0\ntp308\na(I610000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x971\\xc0'\np309\ntp310\nRp311\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x971\\xc0'\np312\ntp313\nRp314\nF-16.0\ntp315\na(I620000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}1\\xc0'\np316\ntp317\nRp318\ng1\n(g5\nS'=\\n\\xd7\\xa3p}1\\xc0'\np319\ntp320\nRp321\nF-15.0\ntp322\na(I630000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx1\\xc0'\np323\ntp324\nRp325\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n1\\xc0'\np326\ntp327\nRp328\nF-17.0\ntp329\na(I640000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y1\\xc0'\np330\ntp331\nRp332\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y1\\xc0'\np333\ntp334\nRp335\nF-16.0\ntp336\na(I650000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG1\\xc0'\np337\ntp338\nRp339\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG1\\xc0'\np340\ntp341\nRp342\nF-16.0\ntp343\na(I660000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.1\\xc0'\np344\ntp345\nRp346\ng1\n(g5\nS'\\xa4p=\\n\\xd7#1\\xc0'\np347\ntp348\nRp349\nF-15.0\ntp350\na(I670000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1c1\\xc0'\np351\ntp352\nRp353\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1c1\\xc0'\np354\ntp355\nRp356\nF-18.0\ntp357\na(I680000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfd0\\xc0'\np358\ntp359\nRp360\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfd0\\xc0'\np361\ntp362\nRp363\nF-16.0\ntp364\na(I690000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f1\\xc0'\np365\ntp366\nRp367\ng363\nF-18.0\ntp368\na(I700000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf00\\xc0'\np369\ntp370\nRp371\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf00\\xc0'\np372\ntp373\nRp374\nF-15.0\ntp375\na(I710000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd70\\xc0'\np376\ntp377\nRp378\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd70\\xc0'\np379\ntp380\nRp381\nF-14.0\ntp382\na(I720000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc70\\xc0'\np383\ntp384\nRp385\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc70\\xc0'\np386\ntp387\nRp388\nF-14.0\ntp389\na(I730000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd0\\xc0'\np390\ntp391\nRp392\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb80\\xc0'\np393\ntp394\nRp395\nF-19.0\ntp396\na(I740000\ng1\n(g5\nS'fffff\\xa60\\xc0'\np397\ntp398\nRp399\ng1\n(g5\nS'fffff\\xa60\\xc0'\np400\ntp401\nRp402\nF-15.0\ntp403\na(I750000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c0\\xc0'\np404\ntp405\nRp406\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c0\\xc0'\np407\ntp408\nRp409\nF-14.0\ntp410\na(I760000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x820\\xc0'\np411\ntp412\nRp413\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x820\\xc0'\np414\ntp415\nRp416\nF-15.0\ntp417\na(I770000\ng1\n(g5\nS'\\x14\\xaeG\\xe1zT0\\xc0'\np418\ntp419\nRp420\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL0\\xc0'\np421\ntp422\nRp423\nF-20.0\ntp424\na(I780000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^0\\xc0'\np425\ntp426\nRp427\ng423\nF-17.0\ntp428\na(I790000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O0\\xc0'\np429\ntp430\nRp431\ng423\nF-12.0\ntp432\na(I800000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85+0\\xc0'\np433\ntp434\nRp435\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85+0\\xc0'\np436\ntp437\nRp438\nF-14.0\ntp439\na(I810000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x050\\xc0'\np440\ntp441\nRp442\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x050\\xc0'\np443\ntp444\nRp445\nF-10.0\ntp446\na(I820000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x000\\xc0'\np447\ntp448\nRp449\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc/\\xc0'\np450\ntp451\nRp452\nF-19.0\ntp453\na(I830000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8/\\xc0'\np454\ntp455\nRp456\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8/\\xc0'\np457\ntp458\nRp459\nF-7.0\ntp460\na(I840000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a/\\xc0'\np461\ntp462\nRp463\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a/\\xc0'\np464\ntp465\nRp466\nF-17.0\ntp467\na(I850000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8/\\xc0'\np468\ntp469\nRp470\ng1\n(g5\nS'\\xa4p=\\n\\xd7#/\\xc0'\np471\ntp472\nRp473\nF-17.0\ntp474\na(I860000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#/\\xc0'\np475\ntp476\nRp477\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x19/\\xc0'\np478\ntp479\nRp480\nF-17.0\ntp481\na(I870000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc.\\xc0'\np482\ntp483\nRp484\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc.\\xc0'\np485\ntp486\nRp487\nF-18.0\ntp488\na(I880000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2.\\xc0'\np489\ntp490\nRp491\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2.\\xc0'\np492\ntp493\nRp494\nF-16.0\ntp495\na(I890000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x19.\\xc0'\np496\ntp497\nRp498\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x19.\\xc0'\np499\ntp500\nRp501\nF-11.0\ntp502\na(I900000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb-\\xc0'\np503\ntp504\nRp505\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb-\\xc0'\np506\ntp507\nRp508\nF-11.0\ntp509\na(I910000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8-\\xc0'\np510\ntp511\nRp512\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8-\\xc0'\np513\ntp514\nRp515\nF-15.0\ntp516\na(I920000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW-\\xc0'\np517\ntp518\nRp519\ng1\n(g5\nS'\\xd7\\xa3p=\\nW-\\xc0'\np520\ntp521\nRp522\nF-12.0\ntp523\na(I930000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1,\\xc0'\np524\ntp525\nRp526\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7,\\xc0'\np527\ntp528\nRp529\nF-17.0\ntp530\na(I940000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a,\\xc0'\np531\ntp532\nRp533\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a,\\xc0'\np534\ntp535\nRp536\nF-17.0\ntp537\na(I950000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00,\\xc0'\np538\ntp539\nRp540\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00,\\xc0'\np541\ntp542\nRp543\nF-7.0\ntp544\na(I960000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3+\\xc0'\np545\ntp546\nRp547\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3+\\xc0'\np548\ntp549\nRp550\nF-11.0\ntp551\na(I970000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfa*\\xc0'\np552\ntp553\nRp554\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfa*\\xc0'\np555\ntp556\nRp557\nF-8.0\ntp558\na(I980000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.*\\xc0'\np559\ntp560\nRp561\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.*\\xc0'\np562\ntp563\nRp564\nF-9.0\ntp565\na(I990000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd)\\xc0'\np566\ntp567\nRp568\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd)\\xc0'\np569\ntp570\nRp571\nF-6.0\ntp572\na(I1000000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG)\\xc0'\np573\ntp574\nRp575\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG)\\xc0'\np576\ntp577\nRp578\nF-13.0\ntp579\na(I1010000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2(\\xc0'\np580\ntp581\nRp582\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2(\\xc0'\np583\ntp584\nRp585\nF-11.0\ntp586\na(I1020000\ng1\n(g5\nS'333333(\\xc0'\np587\ntp588\nRp589\ng1\n(g5\nS'333333(\\xc0'\np590\ntp591\nRp592\nF-1.0\ntp593\na(I1030000\ng1\n(g5\nS\"q=\\n\\xd7\\xa3p'\\xc0\"\np594\ntp595\nRp596\ng1\n(g5\nS\"q=\\n\\xd7\\xa3p'\\xc0\"\np597\ntp598\nRp599\nF5.0\ntp600\na(I1040000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1&\\xc0'\np601\ntp602\nRp603\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1&\\xc0'\np604\ntp605\nRp606\nF-8.0\ntp607\na(I1050000\ng1\n(g5\nS'ffffff&\\xc0'\np608\ntp609\nRp610\ng1\n(g5\nS'ffffff&\\xc0'\np611\ntp612\nRp613\nF2.0\ntp614\na(I1060000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#&\\xc0'\np615\ntp616\nRp617\ng1\n(g5\nS'\\xa4p=\\n\\xd7#&\\xc0'\np618\ntp619\nRp620\nF-8.0\ntp621\na(I1070000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8%\\xc0'\np622\ntp623\nRp624\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa8%\\xc0'\np625\ntp626\nRp627\nF-11.0\ntp628\na(I1080000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL%\\xc0'\np629\ntp630\nRp631\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL%\\xc0'\np632\ntp633\nRp634\nF-2.0\ntp635\na(I1090000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB$\\xc0'\np636\ntp637\nRp638\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB$\\xc0'\np639\ntp640\nRp641\nF-5.0\ntp642\na(I1100000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x80#\\xc0'\np643\ntp644\nRp645\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x80#\\xc0'\np646\ntp647\nRp648\nF-5.0\ntp649\na(I1110000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8#\\xc0'\np650\ntp651\nRp652\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ8#\\xc0'\np653\ntp654\nRp655\nF4.0\ntp656\na(I1120000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x94\"\\xc0'\np657\ntp658\nRp659\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x94\"\\xc0'\np660\ntp661\nRp662\nF-9.0\ntp663\na(I1130000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\"\\xc0'\np664\ntp665\nRp666\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\"\\xc0'\np667\ntp668\nRp669\nF-2.0\ntp670\na(I1140000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW\"\\xc0'\np671\ntp672\nRp673\ng1\n(g5\nS'\\xd7\\xa3p=\\nW\"\\xc0'\np674\ntp675\nRp676\nF-10.0\ntp677\na(I1150000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f!\\xc0'\np678\ntp679\nRp680\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f!\\xc0'\np681\ntp682\nRp683\nF4.0\ntp684\na(I1160000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e!\\xc0'\np685\ntp686\nRp687\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e!\\xc0'\np688\ntp689\nRp690\nF-12.0\ntp691\na(I1170000\ng1\n(g5\nS'333333 \\xc0'\np692\ntp693\nRp694\ng1\n(g5\nS'333333 \\xc0'\np695\ntp696\nRp697\nF2.0\ntp698\na(I1180000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x1e\\xc0'\np699\ntp700\nRp701\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae\\x1e\\xc0'\np702\ntp703\nRp704\nF7.0\ntp705\na(I1190000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\x1d\\xc0'\np706\ntp707\nRp708\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\x1d\\xc0'\np709\ntp710\nRp711\nF3.0\ntp712\na(I1200000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x1c\\xc0'\np713\ntp714\nRp715\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x1c\\xc0'\np716\ntp717\nRp718\nF4.0\ntp719\na(I1210000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\x1a\\xc0'\np720\ntp721\nRp722\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\x1a\\xc0'\np723\ntp724\nRp725\nF5.0\ntp726\na(I1220000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\x19\\xc0'\np727\ntp728\nRp729\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\x19\\xc0'\np730\ntp731\nRp732\nF-6.0\ntp733\na(I1230000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x18\\xc0'\np734\ntp735\nRp736\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x18\\xc0'\np737\ntp738\nRp739\nF8.0\ntp740\na(I1240000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x16\\xc0'\np741\ntp742\nRp743\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x16\\xc0'\np744\ntp745\nRp746\nF1.0\ntp747\na(I1250000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x15\\xc0'\np748\ntp749\nRp750\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x15\\xc0'\np751\ntp752\nRp753\nF-3.0\ntp754\na(I1260000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\x13\\xc0'\np755\ntp756\nRp757\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\x13\\xc0'\np758\ntp759\nRp760\nF1.0\ntp761\na(I1270000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\x12\\xc0'\np762\ntp763\nRp764\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\x12\\xc0'\np765\ntp766\nRp767\nF-7.0\ntp768\na(I1280000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x11\\xc0'\np769\ntp770\nRp771\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x11\\xc0'\np772\ntp773\nRp774\nF1.0\ntp775\na(I1290000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f\\x10\\xc0'\np776\ntp777\nRp778\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\x10\\xc0'\np779\ntp780\nRp781\nF-10.0\ntp782\na(I1300000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\x0e\\xc0'\np783\ntp784\nRp785\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf5\\x0e\\xc0'\np786\ntp787\nRp788\nF9.0\ntp789\na(I1310000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\r\\xc0'\np790\ntp791\nRp792\ng1\n(g5\nS'q=\\n\\xd7\\xa3p\\r\\xc0'\np793\ntp794\nRp795\nF4.0\ntp796\na(I1320000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e\\x0b\\xc0'\np797\ntp798\nRp799\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e\\x0b\\xc0'\np800\ntp801\nRp802\nF4.0\ntp803\na(I1330000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\x08\\xc0'\np804\ntp805\nRp806\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\x08\\xc0'\np807\ntp808\nRp809\nF-5.0\ntp810\na(I1340000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x08\\xc0'\np811\ntp812\nRp813\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\x07\\xc0'\np814\ntp815\nRp816\nF-6.0\ntp817\na(I1350000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x06\\xc0'\np818\ntp819\nRp820\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x14\\x06\\xc0'\np821\ntp822\nRp823\nF7.0\ntp824\na(I1360000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\x03\\xc0'\np825\ntp826\nRp827\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x85\\x03\\xc0'\np828\ntp829\nRp830\nF7.0\ntp831\na(I1370000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\xc0'\np832\ntp833\nRp834\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\xc0'\np835\ntp836\nRp837\nF7.0\ntp838\na(I1380000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\xfc\\xbf'\np839\ntp840\nRp841\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\xfc\\xbf'\np842\ntp843\nRp844\nF3.0\ntp845\na(I1390000\ng1\n(g5\nS'333333\\xf7\\xbf'\np846\ntp847\nRp848\ng1\n(g5\nS'333333\\xf7\\xbf'\np849\ntp850\nRp851\nF6.0\ntp852\na(I1400000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\xf5\\xbf'\np853\ntp854\nRp855\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\xf5\\xbf'\np856\ntp857\nRp858\nF-2.0\ntp859\na(I1410000\ng1\n(g5\nS'ffffff\\xf2\\xbf'\np860\ntp861\nRp862\ng1\n(g5\nS'ffffff\\xf2\\xbf'\np863\ntp864\nRp865\nF5.0\ntp866\na(I1420000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\xe8\\xbf'\np867\ntp868\nRp869\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ\\xe8\\xbf'\np870\ntp871\nRp872\nF2.0\ntp873\na(I1430000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xe4\\xbf'\np874\ntp875\nRp876\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\xe4\\xbf'\np877\ntp878\nRp879\nF3.0\ntp880\na(I1440000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xd9\\xbf'\np881\ntp882\nRp883\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xd9\\xbf'\np884\ntp885\nRp886\nF9.0\ntp887\na(I1450000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\\xda\\xbf'\np888\ntp889\nRp890\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc2\\xd5\\xbf'\np891\ntp892\nRp893\nF-4.0\ntp894\na(I1460000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9\\xbf'\np895\ntp896\nRp897\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xb9\\xbf'\np898\ntp899\nRp900\nF5.0\ntp901\na(I1470000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xc9?'\np902\ntp903\nRp904\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x99\\xc9?'\np905\ntp906\nRp907\nF5.0\ntp908\na(I1480000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\\xda?'\np909\ntp910\nRp911\ng1\n(g5\nS'=\\n\\xd7\\xa3p=\\xda?'\np912\ntp913\nRp914\nF6.0\ntp915\na(I1490000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xf1?'\np916\ntp917\nRp918\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xeb\\xf1?'\np919\ntp920\nRp921\nF12.0\ntp922\na(I1500000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xf8?'\np923\ntp924\nRp925\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\xf8?'\np926\ntp927\nRp928\nF-5.0\ntp929\na(I1510000\ng1\n(g5\nS'ffffff\\xfe?'\np930\ntp931\nRp932\ng1\n(g5\nS'ffffff\\xfe?'\np933\ntp934\nRp935\nF-2.0\ntp936\na(I1520000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7\\x01@'\np937\ntp938\nRp939\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x02@'\np940\ntp941\nRp942\nF2.0\ntp943\na(I1530000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x04@'\np944\ntp945\nRp946\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z\\x04@'\np947\ntp948\nRp949\nF5.0\ntp950\na(I1540000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\x06@'\np951\ntp952\nRp953\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(\\x06@'\np954\ntp955\nRp956\nF10.0\ntp957\na(I1550000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\x08@'\np958\ntp959\nRp960\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\x08@'\np961\ntp962\nRp963\nF16.0\ntp964\na(I1560000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\x0c@'\np965\ntp966\nRp967\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa3\\x0c@'\np968\ntp969\nRp970\nF6.0\ntp971\na(I1570000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\x0e@'\np972\ntp973\nRp974\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc\\x0e@'\np975\ntp976\nRp977\nF14.0\ntp978\na(I1580000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\x10@'\np979\ntp980\nRp981\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\x10@'\np982\ntp983\nRp984\nF9.0\ntp985\na(I1590000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x13@'\np986\ntp987\nRp988\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x00\\x13@'\np989\ntp990\nRp991\nF12.0\ntp992\na(I1600000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\x14@'\np993\ntp994\nRp995\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG\\x14@'\np996\ntp997\nRp998\nF12.0\ntp999\na(I1610000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7\\x16@'\np1000\ntp1001\nRp1002\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd7\\x16@'\np1003\ntp1004\nRp1005\nF14.0\ntp1006\na(I1620000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\x17@'\np1007\ntp1008\nRp1009\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1\\x17@'\np1010\ntp1011\nRp1012\nF10.0\ntp1013\na(I1630000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x19@'\np1014\ntp1015\nRp1016\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x19@'\np1017\ntp1018\nRp1019\nF10.0\ntp1020\na(I1640000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x1c@'\np1021\ntp1022\nRp1023\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n\\x1c@'\np1024\ntp1025\nRp1026\nF15.0\ntp1027\na(I1650000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x1e@'\np1028\ntp1029\nRp1030\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\\\x1e@'\np1031\ntp1032\nRp1033\nF17.0\ntp1034\na(I1660000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa @'\np1035\ntp1036\nRp1037\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa @'\np1038\ntp1039\nRp1040\nF17.0\ntp1041\na(I1670000\ng1\n(g5\nS'fffff\\xe6!@'\np1042\ntp1043\nRp1044\ng1\n(g5\nS'fffff\\xe6!@'\np1045\ntp1046\nRp1047\nF14.0\ntp1048\na(I1680000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\"@'\np1049\ntp1050\nRp1051\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb8\"@'\np1052\ntp1053\nRp1054\nF19.0\ntp1055\na(I1690000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1#@'\np1056\ntp1057\nRp1058\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe1#@'\np1059\ntp1060\nRp1061\nF14.0\ntp1062\na(I1700000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf0$@'\np1063\ntp1064\nRp1065\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf0$@'\np1066\ntp1067\nRp1068\nF17.0\ntp1069\na(I1710000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG&@'\np1070\ntp1071\nRp1072\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG&@'\np1073\ntp1074\nRp1075\nF20.0\ntp1076\na(I1720000\ng1\n(g5\nS\")\\\\\\x8f\\xc2\\xf5('@\"\np1077\ntp1078\nRp1079\ng1\n(g5\nS\")\\\\\\x8f\\xc2\\xf5('@\"\np1080\ntp1081\nRp1082\nF16.0\ntp1083\na(I1730000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW(@'\np1084\ntp1085\nRp1086\ng1\n(g5\nS'\\xd7\\xa3p=\\nW(@'\np1087\ntp1088\nRp1089\nF16.0\ntp1090\na(I1740000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5()@'\np1091\ntp1092\nRp1093\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5()@'\np1094\ntp1095\nRp1096\nF16.0\ntp1097\na(I1750000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL*@'\np1098\ntp1099\nRp1100\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL*@'\np1101\ntp1102\nRp1103\nF18.0\ntp1104\na(I1760000\ng1\n(g5\nS'333333+@'\np1105\ntp1106\nRp1107\ng1\n(g5\nS'333333+@'\np1108\ntp1109\nRp1110\nF18.0\ntp1111\na(I1770000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p,@'\np1112\ntp1113\nRp1114\ng1\n(g5\nS'q=\\n\\xd7\\xa3p,@'\np1115\ntp1116\nRp1117\nF14.0\ntp1118\na(I1780000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(-@'\np1119\ntp1120\nRp1121\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(-@'\np1122\ntp1123\nRp1124\nF17.0\ntp1125\na(I1790000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k-@'\np1126\ntp1127\nRp1128\ng1\n(g5\nS'q=\\n\\xd7\\xa3p-@'\np1129\ntp1130\nRp1131\nF15.0\ntp1132\na(I1800000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG.@'\np1133\ntp1134\nRp1135\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG.@'\np1136\ntp1137\nRp1138\nF18.0\ntp1139\na(I1810000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa.@'\np1140\ntp1141\nRp1142\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa.@'\np1143\ntp1144\nRp1145\nF20.0\ntp1146\na(I1820000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd.@'\np1147\ntp1148\nRp1149\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd.@'\np1150\ntp1151\nRp1152\nF17.0\ntp1153\na(I1830000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ/@'\np1154\ntp1155\nRp1156\ng1\n(g5\nS'\\xd7\\xa3p=\\nW/@'\np1157\ntp1158\nRp1159\nF13.0\ntp1160\na(I1840000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x94/@'\np1161\ntp1162\nRp1163\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x94/@'\np1164\ntp1165\nRp1166\nF15.0\ntp1167\na(I1850000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n0@'\np1168\ntp1169\nRp1170\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n0@'\np1171\ntp1172\nRp1173\nF18.0\ntp1174\na(I1860000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=0@'\np1175\ntp1176\nRp1177\ng1\n(g5\nS'=\\n\\xd7\\xa3p=0@'\np1178\ntp1179\nRp1180\nF16.0\ntp1181\na(I1870000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85+0@'\np1182\ntp1183\nRp1184\ng1180\nF15.0\ntp1185\na(I1880000\ng1\n(g5\nS'3333330@'\np1186\ntp1187\nRp1188\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@0@'\np1189\ntp1190\nRp1191\nF12.0\ntp1192\na(I1890000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=0@'\np1193\ntp1194\nRp1195\ng1191\nF16.0\ntp1196\na(I1900000\ng1\n(g5\nS'\\n\\xd7\\xa3p=J0@'\np1197\ntp1198\nRp1199\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y0@'\np1200\ntp1201\nRp1202\nF13.0\ntp1203\na(I1910000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL0@'\np1204\ntp1205\nRp1206\ng1202\nF12.0\ntp1207\na(I1920000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@0@'\np1208\ntp1209\nRp1210\ng1202\nF14.0\ntp1211\na(I1930000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL0@'\np1212\ntp1213\nRp1214\ng1202\nF19.0\ntp1215\na(I1940000\ng1\n(g5\nS'ffffff0@'\np1216\ntp1217\nRp1218\ng1\n(g5\nS'ffffff0@'\np1219\ntp1220\nRp1221\nF18.0\ntp1222\na(I1950000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k0@'\np1223\ntp1224\nRp1225\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k0@'\np1226\ntp1227\nRp1228\nF19.0\ntp1229\na(I1960000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x800@'\np1230\ntp1231\nRp1232\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x800@'\np1233\ntp1234\nRp1235\nF18.0\ntp1236\na(I1970000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx0@'\np1237\ntp1238\nRp1239\ng1235\nF18.0\ntp1240\na(I1980000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u0@'\np1241\ntp1242\nRp1243\ng1235\nF20.0\ntp1244\na(I1990000\ng1\n(g5\nS'33333s0@'\np1245\ntp1246\nRp1247\ng1235\nF20.0\ntp1248\na(I2000000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u0@'\np1249\ntp1250\nRp1251\ng1235\nF14.0\ntp1252\na(I2010000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x820@'\np1253\ntp1254\nRp1255\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x820@'\np1256\ntp1257\nRp1258\nF17.0\ntp1259\na(I2020000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f0@'\np1260\ntp1261\nRp1262\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x910@'\np1263\ntp1264\nRp1265\nF16.0\ntp1266\na(I2030000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e0@'\np1267\ntp1268\nRp1269\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa10@'\np1270\ntp1271\nRp1272\nF17.0\ntp1273\na(I2040000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa30@'\np1274\ntp1275\nRp1276\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa80@'\np1277\ntp1278\nRp1279\nF20.0\ntp1280\na(I2050000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae0@'\np1281\ntp1282\nRp1283\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae0@'\np1284\ntp1285\nRp1286\nF17.0\ntp1287\na(I2060000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc50@'\np1288\ntp1289\nRp1290\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc50@'\np1291\ntp1292\nRp1293\nF18.0\ntp1294\na(I2070000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc20@'\np1295\ntp1296\nRp1297\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf0@'\np1298\ntp1299\nRp1300\nF17.0\ntp1301\na(I2080000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc50@'\np1302\ntp1303\nRp1304\ng1300\nF17.0\ntp1305\na(I2090000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca0@'\np1306\ntp1307\nRp1308\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd40@'\np1309\ntp1310\nRp1311\nF20.0\ntp1312\na(I2100000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xee0@'\np1313\ntp1314\nRp1315\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xee0@'\np1316\ntp1317\nRp1318\nF18.0\ntp1319\na(I2110000\ng1\n(g5\nS'33333\\xf30@'\np1320\ntp1321\nRp1322\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf50@'\np1323\ntp1324\nRp1325\nF16.0\ntp1326\na(I2120000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfd0@'\np1327\ntp1328\nRp1329\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfd0@'\np1330\ntp1331\nRp1332\nF17.0\ntp1333\na(I2130000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x171@'\np1334\ntp1335\nRp1336\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x171@'\np1337\ntp1338\nRp1339\nF18.0\ntp1340\na(I2140000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:1@'\np1341\ntp1342\nRp1343\ng1\n(g5\nS'{\\x14\\xaeG\\xe1:1@'\np1344\ntp1345\nRp1346\nF18.0\ntp1347\na(I2150000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG!1@'\np1348\ntp1349\nRp1350\ng1346\nF18.0\ntp1351\na(I2160000\ng1\n(g5\nS'q=\\n\\xd7\\xa301@'\np1352\ntp1353\nRp1354\ng1346\nF16.0\ntp1355\na(I2170000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc251@'\np1356\ntp1357\nRp1358\ng1346\nF20.0\ntp1359\na(I2180000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=1@'\np1360\ntp1361\nRp1362\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE1@'\np1363\ntp1364\nRp1365\nF13.0\ntp1366\na(I2190000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG1@'\np1367\ntp1368\nRp1369\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL1@'\np1370\ntp1371\nRp1372\nF19.0\ntp1373\na(I2200000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O1@'\np1374\ntp1375\nRp1376\ng1\n(g5\nS'\\x14\\xaeG\\xe1zT1@'\np1377\ntp1378\nRp1379\nF16.0\ntp1380\na(I2210000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\1@'\np1381\ntp1382\nRp1383\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\1@'\np1384\ntp1385\nRp1386\nF19.0\ntp1387\na(I2220000\ng1\n(g5\nS'\\xa4p=\\n\\xd7c1@'\np1388\ntp1389\nRp1390\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h1@'\np1391\ntp1392\nRp1393\nF17.0\ntp1394\na(I2230000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h1@'\np1395\ntp1396\nRp1397\ng1393\nF19.0\ntp1398\na(I2240000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00@1@'\np1399\ntp1400\nRp1401\ng1393\nF16.0\ntp1402\na(I2250000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL1@'\np1403\ntp1404\nRp1405\ng1393\nF20.0\ntp1406\na(I2260000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL1@'\np1407\ntp1408\nRp1409\ng1393\nF18.0\ntp1410\na(I2270000\ng1\n(g5\nS'\\xd7\\xa3p=\\nW1@'\np1411\ntp1412\nRp1413\ng1393\nF14.0\ntp1414\na(I2280000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\1@'\np1415\ntp1416\nRp1417\ng1393\nF19.0\ntp1418\na(I2290000\ng1\n(g5\nS'ffffff1@'\np1419\ntp1420\nRp1421\ng1393\nF20.0\ntp1422\na(I2300000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa1@'\np1423\ntp1424\nRp1425\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx1@'\np1426\ntp1427\nRp1428\nF18.0\ntp1429\na(I2310000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k1@'\np1430\ntp1431\nRp1432\ng1428\nF16.0\ntp1433\na(I2320000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x851@'\np1434\ntp1435\nRp1436\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x851@'\np1437\ntp1438\nRp1439\nF20.0\ntp1440\na(I2330000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e1@'\np1441\ntp1442\nRp1443\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x9e1@'\np1444\ntp1445\nRp1446\nF19.0\ntp1447\na(I2340000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c1@'\np1448\ntp1449\nRp1450\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa11@'\np1451\ntp1452\nRp1453\nF21.0\ntp1454\na(I2350000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba1@'\np1455\ntp1456\nRp1457\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba1@'\np1458\ntp1459\nRp1460\nF19.0\ntp1461\na(I2360000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc51@'\np1462\ntp1463\nRp1464\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc51@'\np1465\ntp1466\nRp1467\nF20.0\ntp1468\na(I2370000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd11@'\np1469\ntp1470\nRp1471\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd11@'\np1472\ntp1473\nRp1474\nF18.0\ntp1475\na(I2380000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb51@'\np1476\ntp1477\nRp1478\ng1474\nF11.0\ntp1479\na(I2390000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc21@'\np1480\ntp1481\nRp1482\ng1474\nF19.0\ntp1483\na(I2400000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa81@'\np1484\ntp1485\nRp1486\ng1474\nF19.0\ntp1487\na(I2410000\ng1\n(g5\nS'33333\\xb31@'\np1488\ntp1489\nRp1490\ng1474\nF17.0\ntp1491\na(I2420000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba1@'\np1492\ntp1493\nRp1494\ng1474\nF17.0\ntp1495\na(I2430000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc1@'\np1496\ntp1497\nRp1498\ng1474\nF20.0\ntp1499\na(I2440000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc1@'\np1500\ntp1501\nRp1502\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\xdc1@'\np1503\ntp1504\nRp1505\nF20.0\ntp1506\na(I2450000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x022@'\np1507\ntp1508\nRp1509\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x022@'\np1510\ntp1511\nRp1512\nF21.0\ntp1513\na(I2460000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfa1@'\np1514\ntp1515\nRp1516\ng1512\nF19.0\ntp1517\na(I2470000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xee1@'\np1518\ntp1519\nRp1520\ng1512\nF18.0\ntp1521\na(I2480000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x112@'\np1522\ntp1523\nRp1524\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x112@'\np1525\ntp1526\nRp1527\nF19.0\ntp1528\na(I2490000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f2@'\np1529\ntp1530\nRp1531\ng1527\nF19.0\ntp1532\na(I2500000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x172@'\np1533\ntp1534\nRp1535\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x172@'\np1536\ntp1537\nRp1538\nF19.0\ntp1539\na(I2510000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e2@'\np1540\ntp1541\nRp1542\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e2@'\np1543\ntp1544\nRp1545\nF18.0\ntp1546\na(I2520000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e2@'\np1547\ntp1548\nRp1549\ng1\n(g5\nS'\\xa4p=\\n\\xd7#2@'\np1550\ntp1551\nRp1552\nF17.0\ntp1553\na(I2530000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x112@'\np1554\ntp1555\nRp1556\ng1552\nF19.0\ntp1557\na(I2540000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x142@'\np1558\ntp1559\nRp1560\ng1552\nF20.0\ntp1561\na(I2550000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xee1@'\np1562\ntp1563\nRp1564\ng1552\nF13.0\ntp1565\na(I2560000\ng1\n(g5\nS'33333\\xf31@'\np1566\ntp1567\nRp1568\ng1552\nF19.0\ntp1569\na(I2570000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf51@'\np1570\ntp1571\nRp1572\ng1552\nF19.0\ntp1573\na(I2580000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe81@'\np1574\ntp1575\nRp1576\ng1552\nF17.0\ntp1577\na(I2590000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf81@'\np1578\ntp1579\nRp1580\ng1552\nF19.0\ntp1581\na(I2600000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x052@'\np1582\ntp1583\nRp1584\ng1552\nF19.0\ntp1585\na(I2610000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfa1@'\np1586\ntp1587\nRp1588\ng1552\nF16.0\ntp1589\na(I2620000\ng1\n(g5\nS'33333\\xf31@'\np1590\ntp1591\nRp1592\ng1552\nF18.0\ntp1593\na(I2630000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf81@'\np1594\ntp1595\nRp1596\ng1552\nF18.0\ntp1597\na(I2640000\ng1\n(g5\nS'33333\\xf31@'\np1598\ntp1599\nRp1600\ng1552\nF19.0\ntp1601\na(I2650000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf51@'\np1602\ntp1603\nRp1604\ng1552\nF20.0\ntp1605\na(I2660000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x112@'\np1606\ntp1607\nRp1608\ng1552\nF18.0\ntp1609\na(I2670000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x172@'\np1610\ntp1611\nRp1612\ng1552\nF20.0\ntp1613\na(I2680000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e2@'\np1614\ntp1615\nRp1616\ng1552\nF19.0\ntp1617\na(I2690000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE2@'\np1618\ntp1619\nRp1620\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE2@'\np1621\ntp1622\nRp1623\nF21.0\ntp1624\na(I2700000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL2@'\np1625\ntp1626\nRp1627\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL2@'\np1628\ntp1629\nRp1630\nF20.0\ntp1631\na(I2710000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=2@'\np1632\ntp1633\nRp1634\ng1630\nF15.0\ntp1635\na(I2720000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE2@'\np1636\ntp1637\nRp1638\ng1630\nF19.0\ntp1639\na(I2730000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O2@'\np1640\ntp1641\nRp1642\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O2@'\np1643\ntp1644\nRp1645\nF21.0\ntp1646\na(I2740000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y2@'\np1647\ntp1648\nRp1649\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y2@'\np1650\ntp1651\nRp1652\nF19.0\ntp1653\na(I2750000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^2@'\np1654\ntp1655\nRp1656\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^2@'\np1657\ntp1658\nRp1659\nF20.0\ntp1660\na(I2760000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xebQ2@'\np1661\ntp1662\nRp1663\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa2@'\np1664\ntp1665\nRp1666\nF20.0\ntp1667\na(I2770000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\\\2@'\np1668\ntp1669\nRp1670\ng1666\nF18.0\ntp1671\na(I2780000\ng1\n(g5\nS'33333s2@'\np1672\ntp1673\nRp1674\ng1\n(g5\nS'33333s2@'\np1675\ntp1676\nRp1677\nF19.0\ntp1678\na(I2790000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x872@'\np1679\ntp1680\nRp1681\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c2@'\np1682\ntp1683\nRp1684\nF18.0\ntp1685\na(I2800000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x942@'\np1686\ntp1687\nRp1688\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x992@'\np1689\ntp1690\nRp1691\nF19.0\ntp1692\na(I2810000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae2@'\np1693\ntp1694\nRp1695\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae2@'\np1696\ntp1697\nRp1698\nF19.0\ntp1699\na(I2820000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae2@'\np1700\ntp1701\nRp1702\ng1698\nF19.0\ntp1703\na(I2830000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc52@'\np1704\ntp1705\nRp1706\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc52@'\np1707\ntp1708\nRp1709\nF20.0\ntp1710\na(I2840000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc22@'\np1711\ntp1712\nRp1713\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd72@'\np1714\ntp1715\nRp1716\nF19.0\ntp1717\na(I2850000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca2@'\np1718\ntp1719\nRp1720\ng1716\nF19.0\ntp1721\na(I2860000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe12@'\np1722\ntp1723\nRp1724\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xe12@'\np1725\ntp1726\nRp1727\nF19.0\ntp1728\na(I2870000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd42@'\np1729\ntp1730\nRp1731\ng1727\nF16.0\ntp1732\na(I2880000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca2@'\np1733\ntp1734\nRp1735\ng1727\nF18.0\ntp1736\na(I2890000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae2@'\np1737\ntp1738\nRp1739\ng1727\nF17.0\ntp1740\na(I2900000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb82@'\np1741\ntp1742\nRp1743\ng1727\nF19.0\ntp1744\na(I2910000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc72@'\np1745\ntp1746\nRp1747\ng1727\nF20.0\ntp1748\na(I2920000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc72@'\np1749\ntp1750\nRp1751\ng1727\nF19.0\ntp1752\na(I2930000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd42@'\np1753\ntp1754\nRp1755\ng1727\nF21.0\ntp1756\na(I2940000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe82@'\np1757\ntp1758\nRp1759\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xf02@'\np1760\ntp1761\nRp1762\nF17.0\ntp1763\na(I2950000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfd2@'\np1764\ntp1765\nRp1766\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x003@'\np1767\ntp1768\nRp1769\nF19.0\ntp1770\na(I2960000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x143@'\np1771\ntp1772\nRp1773\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x143@'\np1774\ntp1775\nRp1776\nF20.0\ntp1777\na(I2970000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e3@'\np1778\ntp1779\nRp1780\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e3@'\np1781\ntp1782\nRp1783\nF20.0\ntp1784\na(I2980000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x193@'\np1785\ntp1786\nRp1787\ng1\n(g5\nS'\\xa4p=\\n\\xd7#3@'\np1788\ntp1789\nRp1790\nF15.0\ntp1791\na(I2990000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG!3@'\np1792\ntp1793\nRp1794\ng1\n(g5\nS'fffff&3@'\np1795\ntp1796\nRp1797\nF19.0\ntp1798\na(I3000000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x173@'\np1799\ntp1800\nRp1801\ng1797\nF19.0\ntp1802\na(I3010000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x193@'\np1803\ntp1804\nRp1805\ng1797\nF19.0\ntp1806\na(I3020000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1c3@'\np1807\ntp1808\nRp1809\ng1797\nF20.0\ntp1810\na(I3030000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#3@'\np1811\ntp1812\nRp1813\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(3@'\np1814\ntp1815\nRp1816\nF19.0\ntp1817\na(I3040000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x073@'\np1818\ntp1819\nRp1820\ng1816\nF17.0\ntp1821\na(I3050000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xfd2@'\np1822\ntp1823\nRp1824\ng1816\nF19.0\ntp1825\na(I3060000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x023@'\np1826\ntp1827\nRp1828\ng1816\nF19.0\ntp1829\na(I3070000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f3@'\np1830\ntp1831\nRp1832\ng1816\nF20.0\ntp1833\na(I3080000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f3@'\np1834\ntp1835\nRp1836\ng1816\nF17.0\ntp1837\na(I3090000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x193@'\np1838\ntp1839\nRp1840\ng1816\nF19.0\ntp1841\na(I3100000\ng1\n(g5\nS'fffff&3@'\np1842\ntp1843\nRp1844\ng1816\nF20.0\ntp1845\na(I3110000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85+3@'\np1846\ntp1847\nRp1848\ng1\n(g5\nS'\\xaeG\\xe1z\\x14.3@'\np1849\ntp1850\nRp1851\nF20.0\ntp1852\na(I3120000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e3@'\np1853\ntp1854\nRp1855\ng1851\nF19.0\ntp1856\na(I3130000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1c3@'\np1857\ntp1858\nRp1859\ng1851\nF20.0\ntp1860\na(I3140000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x143@'\np1861\ntp1862\nRp1863\ng1851\nF21.0\ntp1864\na(I3150000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x193@'\np1865\ntp1866\nRp1867\ng1851\nF21.0\ntp1868\na(I3160000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x113@'\np1869\ntp1870\nRp1871\ng1851\nF18.0\ntp1872\na(I3170000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f3@'\np1873\ntp1874\nRp1875\ng1851\nF20.0\ntp1876\na(I3180000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x173@'\np1877\ntp1878\nRp1879\ng1851\nF20.0\ntp1880\na(I3190000\ng1\n(g5\nS'fffff&3@'\np1881\ntp1882\nRp1883\ng1851\nF20.0\ntp1884\na(I3200000\ng1\n(g5\nS'fffff&3@'\np1885\ntp1886\nRp1887\ng1\n(g5\nS'q=\\n\\xd7\\xa303@'\np1888\ntp1889\nRp1890\nF18.0\ntp1891\na(I3210000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#3@'\np1892\ntp1893\nRp1894\ng1890\nF19.0\ntp1895\na(I3220000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc253@'\np1896\ntp1897\nRp1898\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc253@'\np1899\ntp1900\nRp1901\nF20.0\ntp1902\na(I3230000\ng1\n(g5\nS'\\n\\xd7\\xa3p=J3@'\np1903\ntp1904\nRp1905\ng1\n(g5\nS'\\n\\xd7\\xa3p=J3@'\np1906\ntp1907\nRp1908\nF20.0\ntp1909\na(I3240000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG3@'\np1910\ntp1911\nRp1912\ng1908\nF18.0\ntp1913\na(I3250000\ng1\n(g5\nS'=\\n\\xd7\\xa3p=3@'\np1914\ntp1915\nRp1916\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL3@'\np1917\ntp1918\nRp1919\nF20.0\ntp1920\na(I3260000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8fB3@'\np1921\ntp1922\nRp1923\ng1919\nF20.0\ntp1924\na(I3270000\ng1\n(g5\nS'\\n\\xd7\\xa3p=J3@'\np1925\ntp1926\nRp1927\ng1919\nF18.0\ntp1928\na(I3280000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc253@'\np1929\ntp1930\nRp1931\ng1919\nF19.0\ntp1932\na(I3290000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc253@'\np1933\ntp1934\nRp1935\ng1919\nF19.0\ntp1936\na(I3300000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ83@'\np1937\ntp1938\nRp1939\ng1919\nF20.0\ntp1940\na(I3310000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG3@'\np1941\ntp1942\nRp1943\ng1919\nF19.0\ntp1944\na(I3320000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y3@'\np1945\ntp1946\nRp1947\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y3@'\np1948\ntp1949\nRp1950\nF19.0\ntp1951\na(I3330000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xccL3@'\np1952\ntp1953\nRp1954\ng1950\nF21.0\ntp1955\na(I3340000\ng1\n(g5\nS'\\n\\xd7\\xa3p=J3@'\np1956\ntp1957\nRp1958\ng1950\nF20.0\ntp1959\na(I3350000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^3@'\np1960\ntp1961\nRp1962\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^3@'\np1963\ntp1964\nRp1965\nF20.0\ntp1966\na(I3360000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h3@'\np1967\ntp1968\nRp1969\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h3@'\np1970\ntp1971\nRp1972\nF21.0\ntp1973\na(I3370000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u3@'\np1974\ntp1975\nRp1976\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx3@'\np1977\ntp1978\nRp1979\nF20.0\ntp1980\na(I3380000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n3@'\np1981\ntp1982\nRp1983\ng1979\nF19.0\ntp1984\na(I3390000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x803@'\np1985\ntp1986\nRp1987\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x803@'\np1988\ntp1989\nRp1990\nF21.0\ntp1991\na(I3400000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x873@'\np1992\ntp1993\nRp1994\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a3@'\np1995\ntp1996\nRp1997\nF20.0\ntp1998\na(I3410000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x913@'\np1999\ntp2000\nRp2001\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x913@'\np2002\ntp2003\nRp2004\nF20.0\ntp2005\na(I3420000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x973@'\np2006\ntp2007\nRp2008\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x973@'\np2009\ntp2010\nRp2011\nF20.0\ntp2012\na(I3430000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb03@'\np2013\ntp2014\nRp2015\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb03@'\np2016\ntp2017\nRp2018\nF20.0\ntp2019\na(I3440000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba3@'\np2020\ntp2021\nRp2022\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba3@'\np2023\ntp2024\nRp2025\nF20.0\ntp2026\na(I3450000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd43@'\np2027\ntp2028\nRp2029\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd43@'\np2030\ntp2031\nRp2032\nF21.0\ntp2033\na(I3460000\ng1\n(g5\nS'fffff\\xe63@'\np2034\ntp2035\nRp2036\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xe83@'\np2037\ntp2038\nRp2039\nF20.0\ntp2040\na(I3470000\ng1\n(g5\nS'33333\\xf33@'\np2041\ntp2042\nRp2043\ng1\n(g5\nS'33333\\xf33@'\np2044\ntp2045\nRp2046\nF20.0\ntp2047\na(I3480000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf53@'\np2048\ntp2049\nRp2050\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf53@'\np2051\ntp2052\nRp2053\nF19.0\ntp2054\na(I3490000\ng1\n(g5\nS'33333\\xf33@'\np2055\ntp2056\nRp2057\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf83@'\np2058\ntp2059\nRp2060\nF21.0\ntp2061\na(I3500000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xf83@'\np2062\ntp2063\nRp2064\ng2060\nF20.0\ntp2065\na(I3510000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xf53@'\np2066\ntp2067\nRp2068\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x004@'\np2069\ntp2070\nRp2071\nF18.0\ntp2072\na(I3520000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xfa3@'\np2073\ntp2074\nRp2075\ng2071\nF19.0\ntp2076\na(I3530000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x054@'\np2077\ntp2078\nRp2079\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x054@'\np2080\ntp2081\nRp2082\nF21.0\ntp2083\na(I3540000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x054@'\np2084\ntp2085\nRp2086\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x074@'\np2087\ntp2088\nRp2089\nF21.0\ntp2090\na(I3550000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0c4@'\np2091\ntp2092\nRp2093\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x0c4@'\np2094\ntp2095\nRp2096\nF20.0\ntp2097\na(I3560000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x144@'\np2098\ntp2099\nRp2100\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x144@'\np2101\ntp2102\nRp2103\nF21.0\ntp2104\na(I3570000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x174@'\np2105\ntp2106\nRp2107\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x174@'\np2108\ntp2109\nRp2110\nF21.0\ntp2111\na(I3580000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1c4@'\np2112\ntp2113\nRp2114\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8\\x1e4@'\np2115\ntp2116\nRp2117\nF20.0\ntp2118\na(I3590000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x174@'\np2119\ntp2120\nRp2121\ng2117\nF21.0\ntp2122\na(I3600000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x1c4@'\np2123\ntp2124\nRp2125\ng2117\nF20.0\ntp2126\na(I3610000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x144@'\np2127\ntp2128\nRp2129\ng2117\nF18.0\ntp2130\na(I3620000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f4@'\np2131\ntp2132\nRp2133\ng2117\nF20.0\ntp2134\na(I3630000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x004@'\np2135\ntp2136\nRp2137\ng2117\nF19.0\ntp2138\na(I3640000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x074@'\np2139\ntp2140\nRp2141\ng2117\nF21.0\ntp2142\na(I3650000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\n4@'\np2143\ntp2144\nRp2145\ng2117\nF20.0\ntp2146\na(I3660000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x0f4@'\np2147\ntp2148\nRp2149\ng2117\nF21.0\ntp2150\na(I3670000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x194@'\np2151\ntp2152\nRp2153\ng2117\nF20.0\ntp2154\na(I3680000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG!4@'\np2155\ntp2156\nRp2157\ng1\n(g5\nS'\\xe1z\\x14\\xaeG!4@'\np2158\ntp2159\nRp2160\nF20.0\ntp2161\na(I3690000\ng1\n(g5\nS'fffff&4@'\np2162\ntp2163\nRp2164\ng1\n(g5\nS'fffff&4@'\np2165\ntp2166\nRp2167\nF21.0\ntp2168\na(I3700000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(4@'\np2169\ntp2170\nRp2171\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5(4@'\np2172\ntp2173\nRp2174\nF21.0\ntp2175\na(I3710000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#4@'\np2176\ntp2177\nRp2178\ng2174\nF20.0\ntp2179\na(I3720000\ng1\n(g5\nS'\\xa4p=\\n\\xd7#4@'\np2180\ntp2181\nRp2182\ng2174\nF20.0\ntp2183\na(I3730000\ng1\n(g5\nS'q=\\n\\xd7\\xa304@'\np2184\ntp2185\nRp2186\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc254@'\np2187\ntp2188\nRp2189\nF19.0\ntp2190\na(I3740000\ng1\n(g5\nS'3333334@'\np2191\ntp2192\nRp2193\ng2189\nF20.0\ntp2194\na(I3750000\ng1\n(g5\nS'q=\\n\\xd7\\xa304@'\np2195\ntp2196\nRp2197\ng2189\nF20.0\ntp2198\na(I3760000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc254@'\np2199\ntp2200\nRp2201\ng2189\nF21.0\ntp2202\na(I3770000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE4@'\np2203\ntp2204\nRp2205\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1eE4@'\np2206\ntp2207\nRp2208\nF20.0\ntp2209\na(I3780000\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG4@'\np2210\ntp2211\nRp2212\ng1\n(g5\nS'H\\xe1z\\x14\\xaeG4@'\np2213\ntp2214\nRp2215\nF21.0\ntp2216\na(I3790000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O4@'\np2217\ntp2218\nRp2219\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\O4@'\np2220\ntp2221\nRp2222\nF21.0\ntp2223\na(I3800000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^4@'\np2224\ntp2225\nRp2226\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^4@'\np2227\ntp2228\nRp2229\nF21.0\ntp2230\na(I3810000\ng1\n(g5\nS'\\xa4p=\\n\\xd7c4@'\np2231\ntp2232\nRp2233\ng1\n(g5\nS'\\xa4p=\\n\\xd7c4@'\np2234\ntp2235\nRp2236\nF19.0\ntp2237\na(I3820000\ng1\n(g5\nS'\\xe1z\\x14\\xaeGa4@'\np2238\ntp2239\nRp2240\ng1\n(g5\nS'ffffff4@'\np2241\ntp2242\nRp2243\nF19.0\ntp2244\na(I3830000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h4@'\np2245\ntp2246\nRp2247\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h4@'\np2248\ntp2249\nRp2250\nF20.0\ntp2251\na(I3840000\ng1\n(g5\nS'\\x1f\\x85\\xebQ\\xb8^4@'\np2252\ntp2253\nRp2254\ng2250\nF20.0\ntp2255\na(I3850000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99Y4@'\np2256\ntp2257\nRp2258\ng2250\nF19.0\ntp2259\na(I3860000\ng1\n(g5\nS'ffffff4@'\np2260\ntp2261\nRp2262\ng2250\nF20.0\ntp2263\na(I3870000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k4@'\np2264\ntp2265\nRp2266\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k4@'\np2267\ntp2268\nRp2269\nF21.0\ntp2270\na(I3880000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx4@'\np2271\ntp2272\nRp2273\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx4@'\np2274\ntp2275\nRp2276\nF21.0\ntp2277\na(I3890000\ng1\n(g5\nS'33333s4@'\np2278\ntp2279\nRp2280\ng2276\nF20.0\ntp2281\na(I3900000\ng1\n(g5\nS'33333s4@'\np2282\ntp2283\nRp2284\ng2276\nF20.0\ntp2285\na(I3910000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p4@'\np2286\ntp2287\nRp2288\ng2276\nF20.0\ntp2289\na(I3920000\ng1\n(g5\nS'33333s4@'\np2290\ntp2291\nRp2292\ng2276\nF21.0\ntp2293\na(I3930000\ng1\n(g5\nS'33333s4@'\np2294\ntp2295\nRp2296\ng2276\nF21.0\ntp2297\na(I3940000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u4@'\np2298\ntp2299\nRp2300\ng2276\nF21.0\ntp2301\na(I3950000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u4@'\np2302\ntp2303\nRp2304\ng2276\nF21.0\ntp2305\na(I3960000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx4@'\np2306\ntp2307\nRp2308\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z4@'\np2309\ntp2310\nRp2311\nF20.0\ntp2312\na(I3970000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n4@'\np2313\ntp2314\nRp2315\ng2311\nF21.0\ntp2316\na(I3980000\ng1\n(g5\nS'33333s4@'\np2317\ntp2318\nRp2319\ng2311\nF21.0\ntp2320\na(I3990000\ng1\n(g5\nS'33333s4@'\np2321\ntp2322\nRp2323\ng2311\nF21.0\ntp2324\na(I4000000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p4@'\np2325\ntp2326\nRp2327\ng1\n(g5\nS'=\\n\\xd7\\xa3p}4@'\np2328\ntp2329\nRp2330\nF19.0\ntp2331\na(I4010000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u4@'\np2332\ntp2333\nRp2334\ng2330\nF21.0\ntp2335\na(I4020000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}4@'\np2336\ntp2337\nRp2338\ng2330\nF21.0\ntp2339\na(I4030000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x824@'\np2340\ntp2341\nRp2342\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2343\ntp2344\nRp2345\nF21.0\ntp2346\na(I4040000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}4@'\np2347\ntp2348\nRp2349\ng2345\nF20.0\ntp2350\na(I4050000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z4@'\np2351\ntp2352\nRp2353\ng2345\nF21.0\ntp2354\na(I4060000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2355\ntp2356\nRp2357\ng2345\nF21.0\ntp2358\na(I4070000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x804@'\np2359\ntp2360\nRp2361\ng2345\nF21.0\ntp2362\na(I4080000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x824@'\np2363\ntp2364\nRp2365\ng2345\nF21.0\ntp2366\na(I4090000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x824@'\np2367\ntp2368\nRp2369\ng2345\nF21.0\ntp2370\na(I4100000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2371\ntp2372\nRp2373\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x874@'\np2374\ntp2375\nRp2376\nF20.0\ntp2377\na(I4110000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z4@'\np2378\ntp2379\nRp2380\ng2376\nF20.0\ntp2381\na(I4120000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z4@'\np2382\ntp2383\nRp2384\ng2376\nF21.0\ntp2385\na(I4130000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}4@'\np2386\ntp2387\nRp2388\ng2376\nF21.0\ntp2389\na(I4140000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x874@'\np2390\ntp2391\nRp2392\ng2376\nF21.0\ntp2393\na(I4150000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2394\ntp2395\nRp2396\ng2376\nF21.0\ntp2397\na(I4160000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x804@'\np2398\ntp2399\nRp2400\ng2376\nF19.0\ntp2401\na(I4170000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a4@'\np2402\ntp2403\nRp2404\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a4@'\np2405\ntp2406\nRp2407\nF21.0\ntp2408\na(I4180000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x914@'\np2409\ntp2410\nRp2411\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x914@'\np2412\ntp2413\nRp2414\nF21.0\ntp2415\na(I4190000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x914@'\np2416\ntp2417\nRp2418\ng2414\nF21.0\ntp2419\na(I4200000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x874@'\np2420\ntp2421\nRp2422\ng2414\nF19.0\ntp2423\na(I4210000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a4@'\np2424\ntp2425\nRp2426\ng2414\nF21.0\ntp2427\na(I4220000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x804@'\np2428\ntp2429\nRp2430\ng2414\nF19.0\ntp2431\na(I4230000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}4@'\np2432\ntp2433\nRp2434\ng2414\nF20.0\ntp2435\na(I4240000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x824@'\np2436\ntp2437\nRp2438\ng2414\nF21.0\ntp2439\na(I4250000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x824@'\np2440\ntp2441\nRp2442\ng2414\nF20.0\ntp2443\na(I4260000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2444\ntp2445\nRp2446\ng2414\nF21.0\ntp2447\na(I4270000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x874@'\np2448\ntp2449\nRp2450\ng2414\nF21.0\ntp2451\na(I4280000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x874@'\np2452\ntp2453\nRp2454\ng2414\nF20.0\ntp2455\na(I4290000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a4@'\np2456\ntp2457\nRp2458\ng2414\nF19.0\ntp2459\na(I4300000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2460\ntp2461\nRp2462\ng2414\nF20.0\ntp2463\na(I4310000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2464\ntp2465\nRp2466\ng2414\nF21.0\ntp2467\na(I4320000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z4@'\np2468\ntp2469\nRp2470\ng2414\nF19.0\ntp2471\na(I4330000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x804@'\np2472\ntp2473\nRp2474\ng2414\nF21.0\ntp2475\na(I4340000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx4@'\np2476\ntp2477\nRp2478\ng2414\nF21.0\ntp2479\na(I4350000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx4@'\np2480\ntp2481\nRp2482\ng2414\nF21.0\ntp2483\na(I4360000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u4@'\np2484\ntp2485\nRp2486\ng2414\nF20.0\ntp2487\na(I4370000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x824@'\np2488\ntp2489\nRp2490\ng2414\nF21.0\ntp2491\na(I4380000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2492\ntp2493\nRp2494\ng2414\nF21.0\ntp2495\na(I4390000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f4@'\np2496\ntp2497\nRp2498\ng2414\nF21.0\ntp2499\na(I4400000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a4@'\np2500\ntp2501\nRp2502\ng2414\nF21.0\ntp2503\na(I4410000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2504\ntp2505\nRp2506\ng2414\nF21.0\ntp2507\na(I4420000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x874@'\np2508\ntp2509\nRp2510\ng2414\nF20.0\ntp2511\na(I4430000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2512\ntp2513\nRp2514\ng2414\nF21.0\ntp2515\na(I4440000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x824@'\np2516\ntp2517\nRp2518\ng2414\nF20.0\ntp2519\na(I4450000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x874@'\np2520\ntp2521\nRp2522\ng2414\nF21.0\ntp2523\na(I4460000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2524\ntp2525\nRp2526\ng2414\nF20.0\ntp2527\na(I4470000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x824@'\np2528\ntp2529\nRp2530\ng2414\nF21.0\ntp2531\na(I4480000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z4@'\np2532\ntp2533\nRp2534\ng2414\nF20.0\ntp2535\na(I4490000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x874@'\np2536\ntp2537\nRp2538\ng2414\nF20.0\ntp2539\na(I4500000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x874@'\np2540\ntp2541\nRp2542\ng2414\nF20.0\ntp2543\na(I4510000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c4@'\np2544\ntp2545\nRp2546\ng2414\nF20.0\ntp2547\na(I4520000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c4@'\np2548\ntp2549\nRp2550\ng2414\nF21.0\ntp2551\na(I4530000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2552\ntp2553\nRp2554\ng2414\nF20.0\ntp2555\na(I4540000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x804@'\np2556\ntp2557\nRp2558\ng2414\nF20.0\ntp2559\na(I4550000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x804@'\np2560\ntp2561\nRp2562\ng2414\nF21.0\ntp2563\na(I4560000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z4@'\np2564\ntp2565\nRp2566\ng2414\nF20.0\ntp2567\na(I4570000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}4@'\np2568\ntp2569\nRp2570\ng2414\nF21.0\ntp2571\na(I4580000\ng1\n(g5\nS'33333s4@'\np2572\ntp2573\nRp2574\ng2414\nF21.0\ntp2575\na(I4590000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n4@'\np2576\ntp2577\nRp2578\ng2414\nF21.0\ntp2579\na(I4600000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p4@'\np2580\ntp2581\nRp2582\ng2414\nF21.0\ntp2583\na(I4610000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u4@'\np2584\ntp2585\nRp2586\ng2414\nF21.0\ntp2587\na(I4620000\ng1\n(g5\nS'33333s4@'\np2588\ntp2589\nRp2590\ng2414\nF21.0\ntp2591\na(I4630000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p4@'\np2592\ntp2593\nRp2594\ng2414\nF20.0\ntp2595\na(I4640000\ng1\n(g5\nS'33333s4@'\np2596\ntp2597\nRp2598\ng2414\nF20.0\ntp2599\na(I4650000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx4@'\np2600\ntp2601\nRp2602\ng2414\nF20.0\ntp2603\na(I4660000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx4@'\np2604\ntp2605\nRp2606\ng2414\nF21.0\ntp2607\na(I4670000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x804@'\np2608\ntp2609\nRp2610\ng2414\nF20.0\ntp2611\na(I4680000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}4@'\np2612\ntp2613\nRp2614\ng2414\nF21.0\ntp2615\na(I4690000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx4@'\np2616\ntp2617\nRp2618\ng2414\nF21.0\ntp2619\na(I4700000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx4@'\np2620\ntp2621\nRp2622\ng2414\nF19.0\ntp2623\na(I4710000\ng1\n(g5\nS'33333s4@'\np2624\ntp2625\nRp2626\ng2414\nF20.0\ntp2627\na(I4720000\ng1\n(g5\nS'33333s4@'\np2628\ntp2629\nRp2630\ng2414\nF20.0\ntp2631\na(I4730000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx4@'\np2632\ntp2633\nRp2634\ng2414\nF20.0\ntp2635\na(I4740000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx4@'\np2636\ntp2637\nRp2638\ng2414\nF20.0\ntp2639\na(I4750000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x824@'\np2640\ntp2641\nRp2642\ng2414\nF20.0\ntp2643\na(I4760000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x804@'\np2644\ntp2645\nRp2646\ng2414\nF20.0\ntp2647\na(I4770000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}4@'\np2648\ntp2649\nRp2650\ng2414\nF21.0\ntp2651\na(I4780000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}4@'\np2652\ntp2653\nRp2654\ng2414\nF21.0\ntp2655\na(I4790000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x824@'\np2656\ntp2657\nRp2658\ng2414\nF21.0\ntp2659\na(I4800000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2660\ntp2661\nRp2662\ng2414\nF21.0\ntp2663\na(I4810000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2664\ntp2665\nRp2666\ng2414\nF19.0\ntp2667\na(I4820000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c4@'\np2668\ntp2669\nRp2670\ng2414\nF21.0\ntp2671\na(I4830000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f4@'\np2672\ntp2673\nRp2674\ng2414\nF21.0\ntp2675\na(I4840000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a4@'\np2676\ntp2677\nRp2678\ng2414\nF21.0\ntp2679\na(I4850000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a4@'\np2680\ntp2681\nRp2682\ng2414\nF21.0\ntp2683\na(I4860000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a4@'\np2684\ntp2685\nRp2686\ng2414\nF19.0\ntp2687\na(I4870000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c4@'\np2688\ntp2689\nRp2690\ng2414\nF19.0\ntp2691\na(I4880000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x914@'\np2692\ntp2693\nRp2694\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x944@'\np2695\ntp2696\nRp2697\nF20.0\ntp2698\na(I4890000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f4@'\np2699\ntp2700\nRp2701\ng2697\nF21.0\ntp2702\na(I4900000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x874@'\np2703\ntp2704\nRp2705\ng2697\nF20.0\ntp2706\na(I4910000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x804@'\np2707\ntp2708\nRp2709\ng2697\nF21.0\ntp2710\na(I4920000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x824@'\np2711\ntp2712\nRp2713\ng2697\nF21.0\ntp2714\na(I4930000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x874@'\np2715\ntp2716\nRp2717\ng2697\nF21.0\ntp2718\na(I4940000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c4@'\np2719\ntp2720\nRp2721\ng2697\nF21.0\ntp2722\na(I4950000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a4@'\np2723\ntp2724\nRp2725\ng2697\nF20.0\ntp2726\na(I4960000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2727\ntp2728\nRp2729\ng2697\nF19.0\ntp2730\na(I4970000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}4@'\np2731\ntp2732\nRp2733\ng2697\nF21.0\ntp2734\na(I4980000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}4@'\np2735\ntp2736\nRp2737\ng2697\nF20.0\ntp2738\na(I4990000\ng1\n(g5\nS'33333s4@'\np2739\ntp2740\nRp2741\ng2697\nF20.0\ntp2742\na(I5000000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k4@'\np2743\ntp2744\nRp2745\ng2697\nF21.0\ntp2746\na(I5010000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p4@'\np2747\ntp2748\nRp2749\ng2697\nF21.0\ntp2750\na(I5020000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u4@'\np2751\ntp2752\nRp2753\ng2697\nF21.0\ntp2754\na(I5030000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85k4@'\np2755\ntp2756\nRp2757\ng2697\nF19.0\ntp2758\na(I5040000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p4@'\np2759\ntp2760\nRp2761\ng2697\nF21.0\ntp2762\na(I5050000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u4@'\np2763\ntp2764\nRp2765\ng2697\nF21.0\ntp2766\na(I5060000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx4@'\np2767\ntp2768\nRp2769\ng2697\nF21.0\ntp2770\na(I5070000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x824@'\np2771\ntp2772\nRp2773\ng2697\nF21.0\ntp2774\na(I5080000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c4@'\np2775\ntp2776\nRp2777\ng2697\nF21.0\ntp2778\na(I5090000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a4@'\np2779\ntp2780\nRp2781\ng2697\nF21.0\ntp2782\na(I5100000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x874@'\np2783\ntp2784\nRp2785\ng2697\nF21.0\ntp2786\na(I5110000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x874@'\np2787\ntp2788\nRp2789\ng2697\nF20.0\ntp2790\na(I5120000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2791\ntp2792\nRp2793\ng2697\nF20.0\ntp2794\na(I5130000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}4@'\np2795\ntp2796\nRp2797\ng2697\nF20.0\ntp2798\na(I5140000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2799\ntp2800\nRp2801\ng2697\nF21.0\ntp2802\na(I5150000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x824@'\np2803\ntp2804\nRp2805\ng2697\nF21.0\ntp2806\na(I5160000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}4@'\np2807\ntp2808\nRp2809\ng2697\nF20.0\ntp2810\na(I5170000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x874@'\np2811\ntp2812\nRp2813\ng2697\nF21.0\ntp2814\na(I5180000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x874@'\np2815\ntp2816\nRp2817\ng2697\nF21.0\ntp2818\na(I5190000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x804@'\np2819\ntp2820\nRp2821\ng2697\nF20.0\ntp2822\na(I5200000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2823\ntp2824\nRp2825\ng2697\nF21.0\ntp2826\na(I5210000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2827\ntp2828\nRp2829\ng2697\nF21.0\ntp2830\na(I5220000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x804@'\np2831\ntp2832\nRp2833\ng2697\nF21.0\ntp2834\na(I5230000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQx4@'\np2835\ntp2836\nRp2837\ng2697\nF20.0\ntp2838\na(I5240000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u4@'\np2839\ntp2840\nRp2841\ng2697\nF21.0\ntp2842\na(I5250000\ng1\n(g5\nS'33333s4@'\np2843\ntp2844\nRp2845\ng2697\nF21.0\ntp2846\na(I5260000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n4@'\np2847\ntp2848\nRp2849\ng2697\nF21.0\ntp2850\na(I5270000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n4@'\np2851\ntp2852\nRp2853\ng2697\nF21.0\ntp2854\na(I5280000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h4@'\np2855\ntp2856\nRp2857\ng2697\nF20.0\ntp2858\na(I5290000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5h4@'\np2859\ntp2860\nRp2861\ng2697\nF21.0\ntp2862\na(I5300000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2u4@'\np2863\ntp2864\nRp2865\ng2697\nF20.0\ntp2866\na(I5310000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1z4@'\np2867\ntp2868\nRp2869\ng2697\nF21.0\ntp2870\na(I5320000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x804@'\np2871\ntp2872\nRp2873\ng2697\nF21.0\ntp2874\na(I5330000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x874@'\np2875\ntp2876\nRp2877\ng2697\nF21.0\ntp2878\na(I5340000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x824@'\np2879\ntp2880\nRp2881\ng2697\nF21.0\ntp2882\na(I5350000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}4@'\np2883\ntp2884\nRp2885\ng2697\nF21.0\ntp2886\na(I5360000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np2887\ntp2888\nRp2889\ng2697\nF21.0\ntp2890\na(I5370000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c4@'\np2891\ntp2892\nRp2893\ng2697\nF21.0\ntp2894\na(I5380000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a4@'\np2895\ntp2896\nRp2897\ng2697\nF21.0\ntp2898\na(I5390000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c4@'\np2899\ntp2900\nRp2901\ng2697\nF21.0\ntp2902\na(I5400000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x974@'\np2903\ntp2904\nRp2905\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x974@'\np2906\ntp2907\nRp2908\nF20.0\ntp2909\na(I5410000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x974@'\np2910\ntp2911\nRp2912\ng2908\nF21.0\ntp2913\na(I5420000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa14@'\np2914\ntp2915\nRp2916\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa14@'\np2917\ntp2918\nRp2919\nF21.0\ntp2920\na(I5430000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np2921\ntp2922\nRp2923\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np2924\ntp2925\nRp2926\nF21.0\ntp2927\na(I5440000\ng1\n(g5\nS'fffff\\xa64@'\np2928\ntp2929\nRp2930\ng2926\nF19.0\ntp2931\na(I5450000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa14@'\np2932\ntp2933\nRp2934\ng2926\nF21.0\ntp2935\na(I5460000\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\x994@'\np2936\ntp2937\nRp2938\ng2926\nF21.0\ntp2939\na(I5470000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c4@'\np2940\ntp2941\nRp2942\ng2926\nF21.0\ntp2943\na(I5480000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c4@'\np2944\ntp2945\nRp2946\ng2926\nF21.0\ntp2947\na(I5490000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x944@'\np2948\ntp2949\nRp2950\ng2926\nF20.0\ntp2951\na(I5500000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\x974@'\np2952\ntp2953\nRp2954\ng2926\nF21.0\ntp2955\na(I5510000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x944@'\np2956\ntp2957\nRp2958\ng2926\nF21.0\ntp2959\na(I5520000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\x914@'\np2960\ntp2961\nRp2962\ng2926\nF21.0\ntp2963\na(I5530000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c4@'\np2964\ntp2965\nRp2966\ng2926\nF21.0\ntp2967\na(I5540000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x824@'\np2968\ntp2969\nRp2970\ng2926\nF20.0\ntp2971\na(I5550000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\x874@'\np2972\ntp2973\nRp2974\ng2926\nF20.0\ntp2975\na(I5560000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a4@'\np2976\ntp2977\nRp2978\ng2926\nF21.0\ntp2979\na(I5570000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\x8f4@'\np2980\ntp2981\nRp2982\ng2926\nF20.0\ntp2983\na(I5580000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\x824@'\np2984\ntp2985\nRp2986\ng2926\nF20.0\ntp2987\na(I5590000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}4@'\np2988\ntp2989\nRp2990\ng2926\nF20.0\ntp2991\na(I5600000\ng1\n(g5\nS'q=\\n\\xd7\\xa3p4@'\np2992\ntp2993\nRp2994\ng2926\nF19.0\ntp2995\na(I5610000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14n4@'\np2996\ntp2997\nRp2998\ng2926\nF20.0\ntp2999\na(I5620000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}4@'\np3000\ntp3001\nRp3002\ng2926\nF20.0\ntp3003\na(I5630000\ng1\n(g5\nS'=\\n\\xd7\\xa3p}4@'\np3004\ntp3005\nRp3006\ng2926\nF20.0\ntp3007\na(I5640000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x804@'\np3008\ntp3009\nRp3010\ng2926\nF21.0\ntp3011\na(I5650000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\x804@'\np3012\ntp3013\nRp3014\ng2926\nF21.0\ntp3015\na(I5660000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a4@'\np3016\ntp3017\nRp3018\ng2926\nF21.0\ntp3019\na(I5670000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np3020\ntp3021\nRp3022\ng2926\nF20.0\ntp3023\na(I5680000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np3024\ntp3025\nRp3026\ng2926\nF19.0\ntp3027\na(I5690000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a4@'\np3028\ntp3029\nRp3030\ng2926\nF21.0\ntp3031\na(I5700000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np3032\ntp3033\nRp3034\ng2926\nF20.0\ntp3035\na(I5710000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\x8a4@'\np3036\ntp3037\nRp3038\ng2926\nF20.0\ntp3039\na(I5720000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c4@'\np3040\ntp3041\nRp3042\ng2926\nF20.0\ntp3043\na(I5730000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np3044\ntp3045\nRp3046\ng2926\nF21.0\ntp3047\na(I5740000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\x854@'\np3048\ntp3049\nRp3050\ng2926\nF21.0\ntp3051\na(I5750000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\x8c4@'\np3052\ntp3053\nRp3054\ng2926\nF20.0\ntp3055\na(I5760000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\x944@'\np3056\ntp3057\nRp3058\ng2926\nF21.0\ntp3059\na(I5770000\ng1\n(g5\nS'\\\\\\x8f\\xc2\\xf5(\\x9c4@'\np3060\ntp3061\nRp3062\ng2926\nF19.0\ntp3063\na(I5780000\ng1\n(g5\nS'\\xe1z\\x14\\xaeG\\xa14@'\np3064\ntp3065\nRp3066\ng2926\nF21.0\ntp3067\na(I5790000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np3068\ntp3069\nRp3070\ng2926\nF21.0\ntp3071\na(I5800000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np3072\ntp3073\nRp3074\ng2926\nF21.0\ntp3075\na(I5810000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np3076\ntp3077\nRp3078\ng2926\nF20.0\ntp3079\na(I5820000\ng1\n(g5\nS'fffff\\xa64@'\np3080\ntp3081\nRp3082\ng2926\nF21.0\ntp3083\na(I5830000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa34@'\np3084\ntp3085\nRp3086\ng2926\nF21.0\ntp3087\na(I5840000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np3088\ntp3089\nRp3090\ng2926\nF21.0\ntp3091\na(I5850000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np3092\ntp3093\nRp3094\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np3095\ntp3096\nRp3097\nF20.0\ntp3098\na(I5860000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np3099\ntp3100\nRp3101\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3102\ntp3103\nRp3104\nF21.0\ntp3105\na(I5870000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np3106\ntp3107\nRp3108\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np3109\ntp3110\nRp3111\nF21.0\ntp3112\na(I5880000\ng1\n(g5\nS'33333\\xb34@'\np3113\ntp3114\nRp3115\ng3111\nF21.0\ntp3116\na(I5890000\ng1\n(g5\nS'33333\\xb34@'\np3117\ntp3118\nRp3119\ng3111\nF21.0\ntp3120\na(I5900000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np3121\ntp3122\nRp3123\ng3111\nF21.0\ntp3124\na(I5910000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np3125\ntp3126\nRp3127\ng3111\nF21.0\ntp3128\na(I5920000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3129\ntp3130\nRp3131\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3132\ntp3133\nRp3134\nF21.0\ntp3135\na(I5930000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3136\ntp3137\nRp3138\ng3134\nF21.0\ntp3139\na(I5940000\ng1\n(g5\nS'33333\\xb34@'\np3140\ntp3141\nRp3142\ng3134\nF20.0\ntp3143\na(I5950000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np3144\ntp3145\nRp3146\ng3134\nF21.0\ntp3147\na(I5960000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np3148\ntp3149\nRp3150\ng3134\nF21.0\ntp3151\na(I5970000\ng1\n(g5\nS'33333\\xb34@'\np3152\ntp3153\nRp3154\ng3134\nF21.0\ntp3155\na(I5980000\ng1\n(g5\nS'fffff\\xa64@'\np3156\ntp3157\nRp3158\ng3134\nF21.0\ntp3159\na(I5990000\ng1\n(g5\nS'fffff\\xa64@'\np3160\ntp3161\nRp3162\ng3134\nF21.0\ntp3163\na(I6000000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa34@'\np3164\ntp3165\nRp3166\ng3134\nF20.0\ntp3167\na(I6010000\ng1\n(g5\nS'\\xa4p=\\n\\xd7\\xa34@'\np3168\ntp3169\nRp3170\ng3134\nF21.0\ntp3171\na(I6020000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np3172\ntp3173\nRp3174\ng3134\nF21.0\ntp3175\na(I6030000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np3176\ntp3177\nRp3178\ng3134\nF21.0\ntp3179\na(I6040000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np3180\ntp3181\nRp3182\ng3134\nF21.0\ntp3183\na(I6050000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3184\ntp3185\nRp3186\ng3134\nF21.0\ntp3187\na(I6060000\ng1\n(g5\nS'33333\\xb34@'\np3188\ntp3189\nRp3190\ng3134\nF19.0\ntp3191\na(I6070000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np3192\ntp3193\nRp3194\ng3134\nF20.0\ntp3195\na(I6080000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np3196\ntp3197\nRp3198\ng3134\nF21.0\ntp3199\na(I6090000\ng1\n(g5\nS'33333\\xb34@'\np3200\ntp3201\nRp3202\ng3134\nF21.0\ntp3203\na(I6100000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3204\ntp3205\nRp3206\ng3134\nF21.0\ntp3207\na(I6110000\ng1\n(g5\nS'fffff\\xa64@'\np3208\ntp3209\nRp3210\ng3134\nF21.0\ntp3211\na(I6120000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np3212\ntp3213\nRp3214\ng3134\nF21.0\ntp3215\na(I6130000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np3216\ntp3217\nRp3218\ng3134\nF21.0\ntp3219\na(I6140000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np3220\ntp3221\nRp3222\ng3134\nF21.0\ntp3223\na(I6150000\ng1\n(g5\nS'33333\\xb34@'\np3224\ntp3225\nRp3226\ng3134\nF20.0\ntp3227\na(I6160000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np3228\ntp3229\nRp3230\ng3134\nF21.0\ntp3231\na(I6170000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3232\ntp3233\nRp3234\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3235\ntp3236\nRp3237\nF21.0\ntp3238\na(I6180000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3239\ntp3240\nRp3241\ng3237\nF21.0\ntp3242\na(I6190000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3243\ntp3244\nRp3245\ng3237\nF20.0\ntp3246\na(I6200000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np3247\ntp3248\nRp3249\ng3237\nF21.0\ntp3250\na(I6210000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np3251\ntp3252\nRp3253\ng3237\nF20.0\ntp3254\na(I6220000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3255\ntp3256\nRp3257\ng3237\nF20.0\ntp3258\na(I6230000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np3259\ntp3260\nRp3261\ng3237\nF21.0\ntp3262\na(I6240000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np3263\ntp3264\nRp3265\ng3237\nF21.0\ntp3266\na(I6250000\ng1\n(g5\nS'fffff\\xa64@'\np3267\ntp3268\nRp3269\ng3237\nF21.0\ntp3270\na(I6260000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np3271\ntp3272\nRp3273\ng3237\nF21.0\ntp3274\na(I6270000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3275\ntp3276\nRp3277\ng3237\nF21.0\ntp3278\na(I6280000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np3279\ntp3280\nRp3281\ng3237\nF21.0\ntp3282\na(I6290000\ng1\n(g5\nS'33333\\xb34@'\np3283\ntp3284\nRp3285\ng3237\nF20.0\ntp3286\na(I6300000\ng1\n(g5\nS'33333\\xb34@'\np3287\ntp3288\nRp3289\ng3237\nF21.0\ntp3290\na(I6310000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3291\ntp3292\nRp3293\ng3237\nF21.0\ntp3294\na(I6320000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3295\ntp3296\nRp3297\ng3237\nF21.0\ntp3298\na(I6330000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np3299\ntp3300\nRp3301\ng3237\nF21.0\ntp3302\na(I6340000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3303\ntp3304\nRp3305\ng3237\nF21.0\ntp3306\na(I6350000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np3307\ntp3308\nRp3309\ng3237\nF20.0\ntp3310\na(I6360000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3311\ntp3312\nRp3313\ng3237\nF21.0\ntp3314\na(I6370000\ng1\n(g5\nS'33333\\xb34@'\np3315\ntp3316\nRp3317\ng3237\nF20.0\ntp3318\na(I6380000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np3319\ntp3320\nRp3321\ng3237\nF21.0\ntp3322\na(I6390000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3323\ntp3324\nRp3325\ng3237\nF21.0\ntp3326\na(I6400000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np3327\ntp3328\nRp3329\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np3330\ntp3331\nRp3332\nF21.0\ntp3333\na(I6410000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np3334\ntp3335\nRp3336\ng3332\nF20.0\ntp3337\na(I6420000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np3338\ntp3339\nRp3340\ng3332\nF21.0\ntp3341\na(I6430000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np3342\ntp3343\nRp3344\ng3332\nF21.0\ntp3345\na(I6440000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3346\ntp3347\nRp3348\ng3332\nF20.0\ntp3349\na(I6450000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3350\ntp3351\nRp3352\ng3332\nF20.0\ntp3353\na(I6460000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3354\ntp3355\nRp3356\ng3332\nF20.0\ntp3357\na(I6470000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np3358\ntp3359\nRp3360\ng3332\nF20.0\ntp3361\na(I6480000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np3362\ntp3363\nRp3364\ng3332\nF21.0\ntp3365\na(I6490000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3366\ntp3367\nRp3368\ng3332\nF21.0\ntp3369\na(I6500000\ng1\n(g5\nS'33333\\xb34@'\np3370\ntp3371\nRp3372\ng3332\nF21.0\ntp3373\na(I6510000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np3374\ntp3375\nRp3376\ng3332\nF19.0\ntp3377\na(I6520000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np3378\ntp3379\nRp3380\ng3332\nF21.0\ntp3381\na(I6530000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np3382\ntp3383\nRp3384\ng3332\nF21.0\ntp3385\na(I6540000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np3386\ntp3387\nRp3388\ng3332\nF20.0\ntp3389\na(I6550000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np3390\ntp3391\nRp3392\ng3332\nF20.0\ntp3393\na(I6560000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np3394\ntp3395\nRp3396\ng3332\nF21.0\ntp3397\na(I6570000\ng1\n(g5\nS'33333\\xb34@'\np3398\ntp3399\nRp3400\ng3332\nF21.0\ntp3401\na(I6580000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3402\ntp3403\nRp3404\ng3332\nF20.0\ntp3405\na(I6590000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3406\ntp3407\nRp3408\ng3332\nF21.0\ntp3409\na(I6600000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3410\ntp3411\nRp3412\ng3332\nF21.0\ntp3413\na(I6610000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np3414\ntp3415\nRp3416\ng3332\nF21.0\ntp3417\na(I6620000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np3418\ntp3419\nRp3420\ng3332\nF21.0\ntp3421\na(I6630000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3422\ntp3423\nRp3424\ng3332\nF21.0\ntp3425\na(I6640000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np3426\ntp3427\nRp3428\ng3332\nF21.0\ntp3429\na(I6650000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3430\ntp3431\nRp3432\ng3332\nF21.0\ntp3433\na(I6660000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np3434\ntp3435\nRp3436\ng3332\nF21.0\ntp3437\na(I6670000\ng1\n(g5\nS'33333\\xb34@'\np3438\ntp3439\nRp3440\ng3332\nF20.0\ntp3441\na(I6680000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np3442\ntp3443\nRp3444\ng3332\nF21.0\ntp3445\na(I6690000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3446\ntp3447\nRp3448\ng3332\nF20.0\ntp3449\na(I6700000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3450\ntp3451\nRp3452\ng3332\nF21.0\ntp3453\na(I6710000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3454\ntp3455\nRp3456\ng3332\nF21.0\ntp3457\na(I6720000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np3458\ntp3459\nRp3460\ng3332\nF21.0\ntp3461\na(I6730000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3462\ntp3463\nRp3464\ng3332\nF21.0\ntp3465\na(I6740000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np3466\ntp3467\nRp3468\ng3332\nF21.0\ntp3469\na(I6750000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np3470\ntp3471\nRp3472\ng3332\nF21.0\ntp3473\na(I6760000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3474\ntp3475\nRp3476\ng3332\nF20.0\ntp3477\na(I6770000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np3478\ntp3479\nRp3480\ng3332\nF21.0\ntp3481\na(I6780000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np3482\ntp3483\nRp3484\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np3485\ntp3486\nRp3487\nF21.0\ntp3488\na(I6790000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np3489\ntp3490\nRp3491\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np3492\ntp3493\nRp3494\nF21.0\ntp3495\na(I6800000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd14@'\np3496\ntp3497\nRp3498\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd14@'\np3499\ntp3500\nRp3501\nF21.0\ntp3502\na(I6810000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd44@'\np3503\ntp3504\nRp3505\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd44@'\np3506\ntp3507\nRp3508\nF21.0\ntp3509\na(I6820000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd14@'\np3510\ntp3511\nRp3512\ng3508\nF21.0\ntp3513\na(I6830000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf4@'\np3514\ntp3515\nRp3516\ng3508\nF20.0\ntp3517\na(I6840000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf4@'\np3518\ntp3519\nRp3520\ng3508\nF21.0\ntp3521\na(I6850000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd44@'\np3522\ntp3523\nRp3524\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd74@'\np3525\ntp3526\nRp3527\nF21.0\ntp3528\na(I6860000\ng1\n(g5\nS'\\xd7\\xa3p=\\n\\xd74@'\np3529\ntp3530\nRp3531\ng3527\nF21.0\ntp3532\na(I6870000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd44@'\np3533\ntp3534\nRp3535\ng1\n(g5\nS'\\x9a\\x99\\x99\\x99\\x99\\xd94@'\np3536\ntp3537\nRp3538\nF21.0\ntp3539\na(I6880000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd44@'\np3540\ntp3541\nRp3542\ng3538\nF20.0\ntp3543\na(I6890000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd44@'\np3544\ntp3545\nRp3546\ng3538\nF21.0\ntp3547\na(I6900000\ng1\n(g5\nS'\\x14\\xaeG\\xe1z\\xd44@'\np3548\ntp3549\nRp3550\ng3538\nF21.0\ntp3551\na(I6910000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd14@'\np3552\ntp3553\nRp3554\ng3538\nF21.0\ntp3555\na(I6920000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf4@'\np3556\ntp3557\nRp3558\ng3538\nF20.0\ntp3559\na(I6930000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np3560\ntp3561\nRp3562\ng3538\nF21.0\ntp3563\na(I6940000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3564\ntp3565\nRp3566\ng3538\nF21.0\ntp3567\na(I6950000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np3568\ntp3569\nRp3570\ng3538\nF21.0\ntp3571\na(I6960000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np3572\ntp3573\nRp3574\ng3538\nF20.0\ntp3575\na(I6970000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3576\ntp3577\nRp3578\ng3538\nF20.0\ntp3579\na(I6980000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np3580\ntp3581\nRp3582\ng3538\nF20.0\ntp3583\na(I6990000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3584\ntp3585\nRp3586\ng3538\nF21.0\ntp3587\na(I7000000\ng1\n(g5\nS'33333\\xb34@'\np3588\ntp3589\nRp3590\ng3538\nF21.0\ntp3591\na(I7010000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np3592\ntp3593\nRp3594\ng3538\nF21.0\ntp3595\na(I7020000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np3596\ntp3597\nRp3598\ng3538\nF21.0\ntp3599\na(I7030000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3600\ntp3601\nRp3602\ng3538\nF20.0\ntp3603\na(I7040000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3604\ntp3605\nRp3606\ng3538\nF20.0\ntp3607\na(I7050000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3608\ntp3609\nRp3610\ng3538\nF21.0\ntp3611\na(I7060000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np3612\ntp3613\nRp3614\ng3538\nF21.0\ntp3615\na(I7070000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3616\ntp3617\nRp3618\ng3538\nF21.0\ntp3619\na(I7080000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np3620\ntp3621\nRp3622\ng3538\nF21.0\ntp3623\na(I7090000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np3624\ntp3625\nRp3626\ng3538\nF18.0\ntp3627\na(I7100000\ng1\n(g5\nS')\\\\\\x8f\\xc2\\xf5\\xa84@'\np3628\ntp3629\nRp3630\ng3538\nF21.0\ntp3631\na(I7110000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np3632\ntp3633\nRp3634\ng3538\nF20.0\ntp3635\na(I7120000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np3636\ntp3637\nRp3638\ng3538\nF21.0\ntp3639\na(I7130000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np3640\ntp3641\nRp3642\ng3538\nF21.0\ntp3643\na(I7140000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3644\ntp3645\nRp3646\ng3538\nF20.0\ntp3647\na(I7150000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np3648\ntp3649\nRp3650\ng3538\nF21.0\ntp3651\na(I7160000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np3652\ntp3653\nRp3654\ng3538\nF21.0\ntp3655\na(I7170000\ng1\n(g5\nS'33333\\xb34@'\np3656\ntp3657\nRp3658\ng3538\nF19.0\ntp3659\na(I7180000\ng1\n(g5\nS'\\xecQ\\xb8\\x1e\\x85\\xab4@'\np3660\ntp3661\nRp3662\ng3538\nF20.0\ntp3663\na(I7190000\ng1\n(g5\nS'q=\\n\\xd7\\xa3\\xb04@'\np3664\ntp3665\nRp3666\ng3538\nF21.0\ntp3667\na(I7200000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np3668\ntp3669\nRp3670\ng3538\nF21.0\ntp3671\na(I7210000\ng1\n(g5\nS'\\xf6(\\\\\\x8f\\xc2\\xb54@'\np3672\ntp3673\nRp3674\ng3538\nF21.0\ntp3675\na(I7220000\ng1\n(g5\nS'\\xb8\\x1e\\x85\\xebQ\\xb84@'\np3676\ntp3677\nRp3678\ng3538\nF21.0\ntp3679\na(I7230000\ng1\n(g5\nS'\\xaeG\\xe1z\\x14\\xae4@'\np3680\ntp3681\nRp3682\ng3538\nF19.0\ntp3683\na(I7240000\ng1\n(g5\nS'33333\\xb34@'\np3684\ntp3685\nRp3686\ng3538\nF21.0\ntp3687\na(I7250000\ng1\n(g5\nS'33333\\xb34@'\np3688\ntp3689\nRp3690\ng3538\nF21.0\ntp3691\na(I7260000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3692\ntp3693\nRp3694\ng3538\nF21.0\ntp3695\na(I7270000\ng1\n(g5\nS'{\\x14\\xaeG\\xe1\\xba4@'\np3696\ntp3697\nRp3698\ng3538\nF19.0\ntp3699\na(I7280000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np3700\ntp3701\nRp3702\ng3538\nF21.0\ntp3703\na(I7290000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np3704\ntp3705\nRp3706\ng3538\nF21.0\ntp3707\na(I7300000\ng1\n(g5\nS'\\xc3\\xf5(\\\\\\x8f\\xc24@'\np3708\ntp3709\nRp3710\ng3538\nF21.0\ntp3711\na(I7310000\ng1\n(g5\nS'=\\n\\xd7\\xa3p\\xbd4@'\np3712\ntp3713\nRp3714\ng3538\nF21.0\ntp3715\na(I7320000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np3716\ntp3717\nRp3718\ng3538\nF21.0\ntp3719\na(I7330000\ng1\n(g5\nS'\\x00\\x00\\x00\\x00\\x00\\xc04@'\np3720\ntp3721\nRp3722\ng3538\nF20.0\ntp3723\na(I7340000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np3724\ntp3725\nRp3726\ng3538\nF20.0\ntp3727\na(I7350000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np3728\ntp3729\nRp3730\ng3538\nF21.0\ntp3731\na(I7360000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np3732\ntp3733\nRp3734\ng3538\nF21.0\ntp3735\na(I7370000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np3736\ntp3737\nRp3738\ng3538\nF21.0\ntp3739\na(I7380000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np3740\ntp3741\nRp3742\ng3538\nF21.0\ntp3743\na(I7390000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf4@'\np3744\ntp3745\nRp3746\ng3538\nF21.0\ntp3747\na(I7400000\ng1\n(g5\nS'R\\xb8\\x1e\\x85\\xeb\\xd14@'\np3748\ntp3749\nRp3750\ng3538\nF21.0\ntp3751\na(I7410000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf4@'\np3752\ntp3753\nRp3754\ng3538\nF21.0\ntp3755\na(I7420000\ng1\n(g5\nS'\\x8f\\xc2\\xf5(\\\\\\xcf4@'\np3756\ntp3757\nRp3758\ng3538\nF21.0\ntp3759\na(I7430000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np3760\ntp3761\nRp3762\ng3538\nF21.0\ntp3763\na(I7440000\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np3764\ntp3765\nRp3766\ng3538\nF21.0\ntp3767\na(I7450000\ng1\n(g5\nS'\\x85\\xebQ\\xb8\\x1e\\xc54@'\np3768\ntp3769\nRp3770\ng3538\nF21.0\ntp3771\na(I7460000\ng1\n(g5\nS'H\\xe1z\\x14\\xae\\xc74@'\np3772\ntp3773\nRp3774\ng3538\nF21.0\ntp3775\na(I7470000\ng1\n(g5\nS'\\n\\xd7\\xa3p=\\xca4@'\np3776\ntp3777\nRp3778\ng3538\nF21.0\ntp3779\na(I7476547\ng1\n(g5\nS'\\xcd\\xcc\\xcc\\xcc\\xcc\\xcc4@'\np3780\ntp3781\nRp3782\ng3538\nF21.0\ntp3783\na.(lp0\nF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-19.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-19.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-18.0\naF-20.0\naF-19.0\naF-20.0\naF-18.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-19.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-20.0\naF-19.0\naF-21.0\naF-19.0\naF-20.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-19.0\naF-18.0\naF-20.0\naF-18.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-19.0\naF-19.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-19.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-19.0\naF-21.0\naF-20.0\naF-19.0\naF-21.0\naF-20.0\naF-18.0\naF-19.0\naF-20.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-20.0\naF-19.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-19.0\naF-20.0\naF-20.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-19.0\naF-20.0\naF-20.0\naF-21.0\naF-20.0\naF-19.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-19.0\naF-19.0\naF-21.0\naF-20.0\naF-19.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-21.0\naF-20.0\naF-19.0\naF-19.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-19.0\naF-20.0\naF-20.0\naF-20.0\naF-20.0\naF-19.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-17.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-19.0\naF-19.0\naF-21.0\naF-19.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-20.0\naF-19.0\naF-21.0\naF-19.0\naF-21.0\naF-21.0\naF-21.0\naF-17.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-18.0\naF-20.0\naF-21.0\naF-18.0\naF-20.0\naF-20.0\naF-20.0\naF-17.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-19.0\naF-19.0\naF-21.0\naF-20.0\naF-18.0\naF-20.0\naF-21.0\naF-21.0\naF-18.0\naF-20.0\naF-21.0\naF-19.0\naF-20.0\naF-20.0\naF-21.0\naF-20.0\naF-18.0\naF-19.0\naF-21.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-19.0\naF-21.0\naF-19.0\naF-20.0\naF-21.0\naF-21.0\naF-18.0\naF-20.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-19.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-17.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-19.0\naF-21.0\naF-20.0\naF-21.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-19.0\naF-21.0\naF-19.0\naF-21.0\naF-20.0\naF-20.0\naF-19.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-20.0\naF-20.0\naF-19.0\naF-21.0\naF-20.0\naF-20.0\naF-20.0\naF-20.0\naF-20.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-21.0\naF-20.0\naF-20.0\naF-19.0\naF-21.0\naF-21.0\naF-18.0\naF-21.0\naF-19.0\naF-18.0\naF-18.0\naF-19.0\naF-19.0\naF-20.0\naF-19.0\naF-19.0\naF-18.0\naF-18.0\naF-20.0\naF-21.0\naF-21.0\naF-21.0\naF-18.0\naF-19.0\naF-19.0\naF-18.0\naF-21.0\naF-21.0\naF-21.0\naF-21.0\naF-19.0\naF-20.0\naF-21.0\naF-21.0\naF-19.0\naF-21.0\naF-20.0\naF-19.0\naF-21.0\naF-19.0\naF-20.0\naF-18.0\naF-19.0\naF-19.0\naF-20.0\naF-20.0\naF-20.0\naF-19.0\naF-21.0\naF-16.0\naF-18.0\naF-18.0\naF-20.0\naF-20.0\naF-18.0\naF-21.0\naF-21.0\naF-17.0\naF-18.0\naF-19.0\naF-15.0\naF-18.0\naF-18.0\naF-18.0\naF-21.0\naF-18.0\naF-20.0\naF-20.0\naF-19.0\naF-19.0\naF-21.0\naF-20.0\naF-20.0\naF-17.0\naF-15.0\naF-16.0\naF-16.0\naF-16.0\naF-21.0\naF-20.0\naF-18.0\naF-18.0\naF-17.0\naF-21.0\naF-17.0\naF-17.0\naF-18.0\naF-16.0\naF-16.0\naF-19.0\naF-20.0\naF-21.0\naF-18.0\naF-19.0\naF-16.0\naF-19.0\naF-19.0\naF-20.0\naF-16.0\naF-18.0\naF-18.0\naF-17.0\naF-13.0\naF-20.0\naF-19.0\naF-18.0\naF-17.0\naF-17.0\naF-18.0\naF-17.0\naF-18.0\naF-19.0\naF-19.0\naF-13.0\naF-20.0\naF-18.0\naF-19.0\naF-18.0\naF-18.0\naF-17.0\naF-13.0\naF-18.0\naF-16.0\naF-17.0\naF-18.0\naF-20.0\naF-17.0\naF-18.0\naF-20.0\naF-21.0\naF-18.0\naF-13.0\naF-16.0\naF-19.0\naF-20.0\naF-15.0\naF-14.0\naF-16.0\naF-16.0\naF-17.0\naF-18.0\naF-17.0\naF-19.0\naF-18.0\naF-19.0\naF-18.0\naF-17.0\naF-18.0\naF-18.0\naF-21.0\naF-18.0\naF-16.0\naF-17.0\naF-19.0\naF-17.0\naF-17.0\naF-19.0\naF-18.0\naF-20.0\naF-18.0\naF-14.0\naF-18.0\naF-16.0\naF-18.0\naF-20.0\naF-18.0\naF-18.0\naF-16.0\naF-16.0\naF-17.0\naF-18.0\naF-15.0\naF-18.0\naF-18.0\naF-21.0\naF-17.0\naF-20.0\naF-17.0\naF-18.0\naF-18.0\naF-19.0\naF-16.0\naF-17.0\naF-17.0\naF-17.0\naF-17.0\naF-18.0\naF-17.0\naF-17.0\naF-18.0\naF-17.0\naF-16.0\naF-18.0\naF-15.0\naF-19.0\naF-15.0\naF-19.0\naF-15.0\naF-18.0\naF-19.0\naF-15.0\naF-11.0\naF-17.0\naF-16.0\naF-17.0\naF-14.0\naF-17.0\naF-17.0\naF-16.0\naF-16.0\naF-15.0\naF-17.0\naF-18.0\naF-17.0\naF-16.0\naF-14.0\naF-14.0\naF-16.0\naF-15.0\naF-19.0\naF-15.0\naF-16.0\naF-16.0\naF-16.0\naF-16.0\naF-18.0\naF-14.0\naF-16.0\naF-17.0\naF-19.0\naF-16.0\naF-17.0\naF-20.0\naF-16.0\naF-17.0\naF-16.0\naF-18.0\naF-13.0\naF-14.0\naF-16.0\naF-14.0\naF-15.0\naF-15.0\naF-18.0\naF-16.0\naF-19.0\naF-17.0\naF-14.0\naF-20.0\naF-17.0\naF-15.0\naF-18.0\naF-14.0\naF-15.0\naF-15.0\naF-18.0\naF-19.0\naF-19.0\naF-12.0\naF-18.0\naF-13.0\naF-19.0\naF-15.0\naF-15.0\naF-20.0\naF-19.0\naF-18.0\naF-14.0\naF-13.0\naF-15.0\naF-14.0\naF-18.0\naF-17.0\naF-15.0\naF-15.0\naF-15.0\naF-7.0\naF-20.0\naF-19.0\naF-16.0\naF-21.0\naF-15.0\naF-21.0\naF-17.0\naF-18.0\naF-17.0\naF-13.0\naF-20.0\naF-12.0\naF-13.0\naF-16.0\naF-12.0\naF-14.0\naF-15.0\naF-17.0\naF-12.0\naF-14.0\naF-10.0\naF-11.0\naF-17.0\naF-17.0\naF-14.0\naF-19.0\naF-16.0\naF-12.0\naF-15.0\naF-7.0\naF-11.0\naF-14.0\naF-17.0\naF-13.0\naF-17.0\naF-7.0\naF-13.0\naF-11.0\naF-15.0\naF-17.0\naF-11.0\naF-15.0\naF-18.0\naF-17.0\naF-8.0\naF-13.0\naF-16.0\naF-13.0\naF-18.0\naF-15.0\naF-15.0\naF-15.0\naF-16.0\naF-16.0\naF-9.0\naF-10.0\naF-7.0\naF-11.0\naF-9.0\naF-21.0\naF-11.0\naF-11.0\naF-14.0\naF-11.0\naF-10.0\naF-15.0\naF-16.0\naF-10.0\naF-13.0\naF-12.0\naF-5.0\naF-8.0\naF-13.0\naF-17.0\naF-8.0\naF-13.0\naF-15.0\naF-10.0\naF-17.0\naF-3.0\naF-13.0\naF-7.0\naF-12.0\naF-9.0\naF-11.0\naF-3.0\naF-6.0\naF-8.0\naF4.0\naF-6.0\naF-13.0\naF-9.0\naF-9.0\naF-10.0\naF-6.0\naF-9.0\naF-2.0\naF-13.0\naF-8.0\naF3.0\naF-11.0\naF-14.0\naF-13.0\naF-1.0\naF-12.0\naF-16.0\naF-10.0\naF5.0\naF-9.0\naF-5.0\naF-8.0\naF-3.0\naF2.0\naF-11.0\naF-14.0\naF-11.0\naF-8.0\naF-2.0\naF-6.0\naF-11.0\naF-1.0\naF-2.0\naF7.0\naF2.0\naF-5.0\naF-9.0\naF5.0\naF-5.0\naF-12.0\naF4.0\naF-7.0\naF6.0\naF-13.0\naF-9.0\naF-13.0\naF-17.0\naF-2.0\naF-7.0\naF-13.0\naF-17.0\naF-10.0\naF-10.0\naF-5.0\naF4.0\naF4.0\naF-7.0\naF-12.0\naF8.0\naF-10.0\naF2.0\naF6.0\naF7.0\naF-2.0\naF-2.0\naF-15.0\naF3.0\naF-2.0\naF4.0\naF1.0\naF4.0\naF5.0\naF-4.0\naF3.0\naF-6.0\naF-1.0\naF8.0\naF3.0\naF6.0\naF1.0\naF7.0\naF-5.0\naF-3.0\naF-8.0\naF-2.0\naF1.0\naF9.0\naF1.0\naF-7.0\naF7.0\naF-11.0\naF1.0\naF3.0\naF-8.0\naF-10.0\naF4.0\naF9.0\naF3.0\naF2.0\naF4.0\naF6.0\naF4.0\naF1.0\naF4.0\naF-5.0\naF-2.0\naF1.0\naF-6.0\naF-3.0\naF7.0\naF-4.0\naF7.0\naF7.0\naF7.0\naF4.0\naF7.0\naF-6.0\naF3.0\naF9.0\naF8.0\naF6.0\naF3.0\naF-2.0\naF4.0\naF5.0\naF1.0\naF3.0\naF2.0\naF1.0\naF3.0\naF3.0\naF9.0\naF4.0\naF6.0\naF-4.0\naF12.0\naF5.0\naF5.0\naF3.0\naF9.0\naF5.0\naF-8.0\naF9.0\naF6.0\naF11.0\naF9.0\naF12.0\naF13.0\naF9.0\naF-5.0\naF14.0\naF-2.0\naF9.0\naF11.0\naF2.0\naF5.0\naF8.0\naF5.0\naF9.0\naF10.0\naF9.0\naF10.0\naF12.0\naF16.0\naF13.0\naF14.0\naF6.0\naF-6.0\naF13.0\naF13.0\naF14.0\naF19.0\naF13.0\naF9.0\naF15.0\naF12.0\naF18.0\naF12.0\naF14.0\naF16.0\naF-1.0\naF12.0\naF14.0\naF9.0\naF15.0\naF14.0\naF12.0\naF7.0\naF10.0\naF14.0\naF10.0\naF10.0\naF14.0\naF10.0\naF17.0\naF15.0\naF15.0\naF17.0\naF17.0\naF16.0\naF17.0\naF14.0\naF17.0\naF16.0\naF17.0\naF16.0\naF10.0\naF17.0\naF16.0\naF14.0\naF14.0\naF14.0\naF11.0\naF19.0\naF19.0\naF16.0\naF17.0\naF9.0\naF14.0\naF20.0\naF13.0\naF18.0\naF17.0\naF18.0\naF15.0\naF12.0\naF17.0\naF20.0\naF18.0\naF8.0\naF18.0\naF16.0\naF17.0\naF12.0\naF19.0\naF18.0\naF16.0\naF12.0\naF16.0\naF19.0\naF16.0\naF17.0\naF16.0\naF19.0\naF14.0\naF18.0\naF20.0\naF12.0\naF17.0\naF21.0\naF18.0\naF18.0\naF16.0\naF21.0\naF18.0\naF14.0\naF18.0\naF15.0\naF18.0\naF17.0\naF14.0\naF18.0\naF13.0\naF15.0\naF18.0\naF14.0\naF18.0\naF15.0\naF18.0\naF14.0\naF17.0\naF13.0\naF20.0\naF19.0\naF14.0\naF18.0\naF16.0\naF17.0\naF19.0\naF18.0\naF17.0\naF17.0\naF13.0\naF17.0\naF15.0\naF16.0\naF15.0\naF13.0\naF14.0\naF15.0\naF16.0\naF18.0\naF19.0\naF18.0\naF17.0\naF21.0\naF16.0\naF13.0\naF19.0\naF13.0\naF15.0\naF19.0\naF18.0\naF18.0\naF12.0\naF14.0\naF12.0\naF18.0\naF17.0\naF16.0\naF15.0\naF19.0\naF16.0\naF13.0\naF18.0\naF17.0\naF15.0\naF12.0\naF15.0\naF17.0\naF14.0\naF17.0\naF14.0\naF16.0\naF18.0\naF17.0\naF17.0\naF19.0\naF18.0\naF17.0\naF17.0\naF18.0\naF14.0\naF17.0\naF14.0\naF20.0\naF19.0\naF16.0\naF20.0\naF16.0\naF18.0\naF18.0\naF12.0\naF18.0\naF16.0\naF18.0\naF16.0\naF16.0\naF16.0\naF19.0\naF20.0\naF17.0\naF16.0\naF17.0\naF16.0\naF20.0\naF16.0\naF17.0\naF18.0\naF18.0\naF14.0\naF17.0\naF14.0\naF18.0\naF17.0\naF17.0\naF17.0\naF21.0\naF18.0\naF15.0\naF16.0\naF18.0\naF19.0\naF19.0\naF17.0\naF17.0\naF19.0\naF18.0\naF15.0\naF20.0\naF14.0\naF16.0\naF19.0\naF17.0\naF17.0\naF18.0\naF15.0\naF16.0\naF18.0\naF19.0\naF16.0\naF14.0\naF19.0\naF17.0\naF15.0\naF18.0\naF19.0\naF18.0\naF17.0\naF16.0\naF18.0\naF16.0\naF15.0\naF20.0\naF16.0\naF20.0\naF16.0\naF18.0\naF15.0\naF19.0\naF17.0\naF18.0\naF16.0\naF16.0\naF17.0\naF17.0\naF17.0\naF16.0\naF16.0\naF17.0\naF18.0\naF18.0\naF19.0\naF21.0\naF18.0\naF20.0\naF18.0\naF15.0\naF17.0\naF19.0\naF10.0\naF18.0\naF20.0\naF16.0\naF18.0\naF20.0\naF16.0\naF17.0\naF14.0\naF21.0\naF18.0\naF20.0\naF16.0\naF20.0\naF13.0\naF21.0\naF13.0\naF19.0\naF19.0\naF16.0\naF19.0\naF19.0\naF18.0\naF19.0\naF17.0\naF18.0\naF16.0\naF18.0\naF14.0\naF20.0\naF18.0\naF19.0\naF16.0\naF19.0\naF19.0\naF15.0\naF17.0\naF19.0\naF16.0\naF17.0\naF19.0\naF19.0\naF11.0\naF19.0\naF15.0\naF14.0\naF16.0\naF17.0\naF20.0\naF15.0\naF20.0\naF18.0\naF18.0\naF17.0\naF16.0\naF18.0\naF17.0\naF19.0\naF18.0\naF20.0\naF14.0\naF15.0\naF17.0\naF15.0\naF19.0\naF19.0\naF18.0\naF17.0\naF17.0\naF20.0\naF20.0\naF18.0\naF20.0\naF16.0\naF13.0\naF18.0\naF21.0\naF20.0\naF15.0\naF16.0\naF17.0\naF17.0\naF21.0\naF18.0\naF18.0\naF20.0\naF21.0\naF18.0\naF18.0\naF18.0\naF19.0\naF19.0\naF17.0\naF18.0\naF20.0\naF21.0\naF17.0\naF21.0\naF19.0\naF15.0\naF19.0\naF17.0\naF18.0\naF20.0\naF21.0\naF20.0\naF16.0\naF19.0\naF17.0\naF21.0\naF18.0\naF14.0\naF20.0\naF17.0\naF17.0\naF11.0\naF17.0\naF19.0\naF17.0\naF19.0\naF10.0\naF17.0\naF17.0\naF19.0\naF19.0\naF17.0\naF19.0\naF17.0\naF20.0\naF17.0\naF18.0\naF19.0\naF20.0\naF20.0\naF17.0\naF15.0\naF20.0\naF16.0\naF20.0\naF20.0\naF19.0\naF14.0\naF19.0\naF17.0\naF20.0\naF19.0\naF20.0\naF18.0\naF19.0\naF21.0\naF16.0\naF17.0\naF18.0\naF19.0\naF14.0\naF20.0\naF18.0\naF18.0\naF15.0\naF18.0\naF19.0\naF15.0\naF21.0\naF20.0\naF19.0\naF19.0\naF18.0\naF17.0\naF17.0\naF19.0\naF15.0\naF18.0\naF19.0\naF19.0\naF19.0\naF19.0\naF21.0\naF19.0\naF16.0\naF18.0\naF19.0\naF17.0\naF21.0\naF17.0\naF17.0\naF18.0\naF20.0\naF18.0\naF15.0\naF19.0\naF21.0\naF18.0\naF19.0\naF16.0\naF20.0\naF14.0\naF17.0\naF19.0\naF13.0\naF18.0\naF19.0\naF19.0\naF18.0\naF19.0\naF19.0\naF20.0\naF17.0\naF17.0\naF21.0\naF19.0\naF13.0\naF18.0\naF15.0\naF18.0\naF17.0\naF18.0\naF18.0\naF15.0\naF19.0\naF18.0\naF16.0\naF20.0\naF14.0\naF19.0\naF19.0\naF16.0\naF19.0\naF18.0\naF16.0\naF19.0\naF17.0\naF18.0\naF19.0\naF18.0\naF19.0\naF18.0\naF19.0\naF16.0\naF18.0\naF17.0\naF16.0\naF18.0\naF17.0\naF19.0\naF19.0\naF21.0\naF20.0\naF20.0\naF18.0\naF20.0\naF18.0\naF20.0\naF20.0\naF19.0\naF18.0\naF19.0\naF14.0\naF19.0\naF19.0\naF20.0\naF19.0\naF20.0\naF20.0\naF19.0\naF19.0\naF19.0\naF19.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF19.0\naF18.0\naF20.0\naF19.0\naF17.0\naF16.0\naF20.0\naF15.0\naF17.0\naF19.0\naF18.0\naF20.0\naF19.0\naF19.0\naF20.0\naF18.0\naF17.0\naF20.0\naF21.0\naF17.0\naF19.0\naF18.0\naF19.0\naF16.0\naF16.0\naF17.0\naF19.0\naF20.0\naF19.0\naF19.0\naF16.0\naF16.0\naF20.0\naF15.0\naF20.0\naF20.0\naF17.0\naF19.0\naF18.0\naF21.0\naF18.0\naF18.0\naF19.0\naF19.0\naF20.0\naF21.0\naF17.0\naF20.0\naF18.0\naF21.0\naF16.0\naF17.0\naF19.0\naF19.0\naF19.0\naF20.0\naF21.0\naF19.0\naF19.0\naF16.0\naF20.0\naF19.0\naF19.0\naF19.0\naF17.0\naF18.0\naF19.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF17.0\naF17.0\naF19.0\naF21.0\naF20.0\naF18.0\naF21.0\naF19.0\naF20.0\naF19.0\naF19.0\naF20.0\naF20.0\naF19.0\naF18.0\naF18.0\naF20.0\naF21.0\naF16.0\naF18.0\naF18.0\naF18.0\naF21.0\naF18.0\naF20.0\naF21.0\naF19.0\naF13.0\naF17.0\naF21.0\naF20.0\naF17.0\naF17.0\naF19.0\naF21.0\naF19.0\naF20.0\naF21.0\naF14.0\naF20.0\naF19.0\naF19.0\naF20.0\naF16.0\naF19.0\naF21.0\naF21.0\naF17.0\naF20.0\naF21.0\naF19.0\naF21.0\naF18.0\naF19.0\naF21.0\naF17.0\naF20.0\naF20.0\naF19.0\naF20.0\naF19.0\naF20.0\naF17.0\naF21.0\naF20.0\naF20.0\naF20.0\naF20.0\naF18.0\naF21.0\naF20.0\naF20.0\naF20.0\naF19.0\naF21.0\naF19.0\naF15.0\naF20.0\naF18.0\naF21.0\naF17.0\naF19.0\naF19.0\naF19.0\naF18.0\naF17.0\naF18.0\naF19.0\naF20.0\naF18.0\naF17.0\naF21.0\naF19.0\naF18.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF19.0\naF19.0\naF20.0\naF21.0\naF19.0\naF18.0\naF14.0\naF19.0\naF19.0\naF17.0\naF19.0\naF17.0\naF20.0\naF18.0\naF19.0\naF19.0\naF19.0\naF19.0\naF16.0\naF21.0\naF19.0\naF20.0\naF20.0\naF19.0\naF21.0\naF20.0\naF19.0\naF18.0\naF18.0\naF19.0\naF17.0\naF19.0\naF19.0\naF20.0\naF19.0\naF21.0\naF19.0\naF20.0\naF20.0\naF20.0\naF19.0\naF20.0\naF20.0\naF18.0\naF20.0\naF19.0\naF20.0\naF16.0\naF20.0\naF21.0\naF20.0\naF18.0\naF19.0\naF16.0\naF19.0\naF20.0\naF19.0\naF20.0\naF17.0\naF21.0\naF17.0\naF19.0\naF21.0\naF20.0\naF21.0\naF19.0\naF19.0\naF20.0\naF21.0\naF20.0\naF20.0\naF19.0\naF19.0\naF18.0\naF18.0\naF21.0\naF16.0\naF19.0\naF17.0\naF20.0\naF20.0\naF19.0\naF20.0\naF19.0\naF20.0\naF16.0\naF21.0\naF18.0\naF21.0\naF20.0\naF20.0\naF21.0\naF18.0\naF20.0\naF18.0\naF18.0\naF20.0\naF20.0\naF20.0\naF20.0\naF19.0\naF18.0\naF20.0\naF21.0\naF20.0\naF19.0\naF20.0\naF21.0\naF18.0\naF21.0\naF19.0\naF20.0\naF18.0\naF19.0\naF20.0\naF19.0\naF18.0\naF18.0\naF19.0\naF18.0\naF16.0\naF20.0\naF21.0\naF20.0\naF21.0\naF18.0\naF19.0\naF20.0\naF19.0\naF20.0\naF19.0\naF19.0\naF18.0\naF18.0\naF19.0\naF17.0\naF18.0\naF20.0\naF19.0\naF20.0\naF19.0\naF20.0\naF19.0\naF19.0\naF18.0\naF20.0\naF21.0\naF20.0\naF18.0\naF20.0\naF19.0\naF20.0\naF19.0\naF21.0\naF19.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF19.0\naF19.0\naF17.0\naF19.0\naF19.0\naF21.0\naF19.0\naF21.0\naF18.0\naF20.0\naF20.0\naF20.0\naF20.0\naF19.0\naF21.0\naF19.0\naF20.0\naF20.0\naF21.0\naF20.0\naF19.0\naF19.0\naF21.0\naF21.0\naF20.0\naF20.0\naF18.0\naF20.0\naF18.0\naF20.0\naF20.0\naF19.0\naF21.0\naF19.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF19.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF19.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF19.0\naF19.0\naF18.0\naF19.0\naF20.0\naF21.0\naF19.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF18.0\naF20.0\naF19.0\naF20.0\naF21.0\naF20.0\naF20.0\naF20.0\naF19.0\naF21.0\naF20.0\naF20.0\naF19.0\naF19.0\naF21.0\naF17.0\naF20.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF18.0\naF19.0\naF21.0\naF19.0\naF18.0\naF20.0\naF20.0\naF21.0\naF20.0\naF19.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF19.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF17.0\naF21.0\naF20.0\naF20.0\naF19.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF19.0\naF20.0\naF19.0\naF21.0\naF18.0\naF19.0\naF21.0\naF19.0\naF21.0\naF20.0\naF20.0\naF20.0\naF20.0\naF21.0\naF18.0\naF20.0\naF21.0\naF20.0\naF20.0\naF19.0\naF20.0\naF21.0\naF19.0\naF19.0\naF20.0\naF19.0\naF20.0\naF21.0\naF20.0\naF20.0\naF19.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF19.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF19.0\naF20.0\naF19.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF19.0\naF20.0\naF20.0\naF21.0\naF21.0\naF17.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF20.0\naF21.0\naF19.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF19.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF19.0\naF20.0\naF20.0\naF21.0\naF21.0\naF19.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF19.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF19.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF19.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF19.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF19.0\naF19.0\naF21.0\naF21.0\naF21.0\naF19.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF20.0\naF19.0\naF21.0\naF20.0\naF21.0\naF20.0\naF19.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF19.0\naF20.0\naF21.0\naF20.0\naF21.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF19.0\naF21.0\naF19.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF19.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF19.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF18.0\naF20.0\naF21.0\naF21.0\naF19.0\naF20.0\naF19.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF19.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF19.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF19.0\naF19.0\naF20.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF18.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF19.0\naF21.0\naF20.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF19.0\naF20.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF19.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF19.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF20.0\naF20.0\naF20.0\naF21.0\naF19.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF19.0\naF18.0\naF21.0\naF19.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF18.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF19.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF18.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF20.0\naF18.0\naF19.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF20.0\naF19.0\naF21.0\naF21.0\naF21.0\naF19.0\naF20.0\naF20.0\naF20.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF18.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF18.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF19.0\naF20.0\naF20.0\naF20.0\naF19.0\naF21.0\naF18.0\naF21.0\naF21.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF19.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF19.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF19.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF20.0\naF19.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF18.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF19.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF20.0\naF19.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF20.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF19.0\naF19.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF19.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF19.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF19.0\naF20.0\naF21.0\naF21.0\naF19.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF18.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF18.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF18.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF19.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF19.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF19.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\naF21.0\naF21.0\naF21.0\naF21.0\naF20.0\naF21.0\na."
  },
  {
    "path": "dqn/logs_text/BeamRider_s001.text",
    "content": "('AVAILABLE GPUS: ', [u'device: 0, name: TITAN X (Pascal), pci bus id: 0000:01:00.0'])\ntask = Task<env_id=BeamRiderNoFrameskip-v3 trials=2 max_timesteps=40000000 max_seconds=None reward_floor=363.9 reward_ceiling=60000.0>\n\nTimestep: 60000\nmean reward (100 episodes): 337.6522\nbest mean reward: -inf\ncurrent episode reward: 352.0000\nepisodes: 46\nexploration: 0.94600\nlearning_rate: 0.00010\nelapsed time: 91.9 seconds (0.03 hours)\n\nTimestep: 70000\nmean reward (100 episodes): 339.6981\nbest mean reward: -inf\ncurrent episode reward: 396.0000\nepisodes: 53\nexploration: 0.93700\nlearning_rate: 0.00010\nelapsed time: 124.4 seconds (0.03 hours)\n\nTimestep: 80000\nmean reward (100 episodes): 338.9333\nbest mean reward: -inf\ncurrent episode reward: 308.0000\nepisodes: 60\nexploration: 0.92800\nlearning_rate: 0.00010\nelapsed time: 156.8 seconds (0.04 hours)\n\nTimestep: 90000\nmean reward (100 episodes): 346.2941\nbest mean reward: -inf\ncurrent episode reward: 352.0000\nepisodes: 68\nexploration: 0.91900\nlearning_rate: 0.00010\nelapsed time: 190.4 seconds (0.05 hours)\n\nTimestep: 100000\nmean reward (100 episodes): 351.7867\nbest mean reward: -inf\ncurrent episode reward: 900.0000\nepisodes: 75\nexploration: 0.91000\nlearning_rate: 0.00010\nelapsed time: 223.4 seconds (0.06 hours)\n\nTimestep: 110000\nmean reward (100 episodes): 354.5366\nbest mean reward: -inf\ncurrent episode reward: 308.0000\nepisodes: 82\nexploration: 0.90100\nlearning_rate: 0.00010\nelapsed time: 256.6 seconds (0.07 hours)\n\nTimestep: 120000\nmean reward (100 episodes): 351.8667\nbest mean reward: -inf\ncurrent episode reward: 264.0000\nepisodes: 90\nexploration: 0.89200\nlearning_rate: 0.00010\nelapsed time: 289.6 seconds (0.08 hours)\n\nTimestep: 130000\nmean reward (100 episodes): 349.1546\nbest mean reward: -inf\ncurrent episode reward: 308.0000\nepisodes: 97\nexploration: 0.88300\nlearning_rate: 0.00010\nelapsed time: 322.9 seconds (0.09 hours)\n\nTimestep: 140000\nmean reward (100 episodes): 347.0400\nbest mean reward: 348.8000\ncurrent episode reward: 264.0000\nepisodes: 105\nexploration: 0.87400\nlearning_rate: 0.00010\nelapsed time: 356.1 seconds (0.10 hours)\n\nTimestep: 150000\nmean reward (100 episodes): 343.9600\nbest mean reward: 348.8000\ncurrent episode reward: 352.0000\nepisodes: 114\nexploration: 0.86500\nlearning_rate: 0.00010\nelapsed time: 389.6 seconds (0.11 hours)\n\nTimestep: 160000\nmean reward (100 episodes): 348.8400\nbest mean reward: 351.0400\ncurrent episode reward: 352.0000\nepisodes: 122\nexploration: 0.85600\nlearning_rate: 0.00010\nelapsed time: 422.9 seconds (0.12 hours)\n\nTimestep: 170000\nmean reward (100 episodes): 358.5200\nbest mean reward: 358.5200\ncurrent episode reward: 352.0000\nepisodes: 129\nexploration: 0.84700\nlearning_rate: 0.00010\nelapsed time: 458.3 seconds (0.13 hours)\n\nTimestep: 180000\nmean reward (100 episodes): 362.4800\nbest mean reward: 363.8000\ncurrent episode reward: 440.0000\nepisodes: 136\nexploration: 0.83800\nlearning_rate: 0.00010\nelapsed time: 492.5 seconds (0.14 hours)\n\nTimestep: 190000\nmean reward (100 episodes): 358.5200\nbest mean reward: 363.8000\ncurrent episode reward: 396.0000\nepisodes: 144\nexploration: 0.82900\nlearning_rate: 0.00010\nelapsed time: 527.1 seconds (0.15 hours)\n\nTimestep: 200000\nmean reward (100 episodes): 360.6400\nbest mean reward: 365.5600\ncurrent episode reward: 264.0000\nepisodes: 151\nexploration: 0.82000\nlearning_rate: 0.00010\nelapsed time: 561.6 seconds (0.16 hours)\n\nTimestep: 210000\nmean reward (100 episodes): 356.6800\nbest mean reward: 365.5600\ncurrent episode reward: 176.0000\nepisodes: 160\nexploration: 0.81100\nlearning_rate: 0.00010\nelapsed time: 596.2 seconds (0.17 hours)\n\nTimestep: 220000\nmean reward (100 episodes): 354.0400\nbest mean reward: 365.5600\ncurrent episode reward: 176.0000\nepisodes: 167\nexploration: 0.80200\nlearning_rate: 0.00010\nelapsed time: 630.8 seconds (0.18 hours)\n\nTimestep: 230000\nmean reward (100 episodes): 358.0800\nbest mean reward: 365.5600\ncurrent episode reward: 264.0000\nepisodes: 174\nexploration: 0.79300\nlearning_rate: 0.00010\nelapsed time: 665.5 seconds (0.18 hours)\n\nTimestep: 240000\nmean reward (100 episodes): 354.4400\nbest mean reward: 365.5600\ncurrent episode reward: 440.0000\nepisodes: 181\nexploration: 0.78400\nlearning_rate: 0.00010\nelapsed time: 700.5 seconds (0.19 hours)\n\nTimestep: 250000\nmean reward (100 episodes): 356.2000\nbest mean reward: 365.5600\ncurrent episode reward: 308.0000\nepisodes: 189\nexploration: 0.77500\nlearning_rate: 0.00010\nelapsed time: 735.6 seconds (0.20 hours)\n\nTimestep: 260000\nmean reward (100 episodes): 363.2400\nbest mean reward: 365.5600\ncurrent episode reward: 440.0000\nepisodes: 196\nexploration: 0.76600\nlearning_rate: 0.00010\nelapsed time: 770.5 seconds (0.21 hours)\n\nTimestep: 270000\nmean reward (100 episodes): 363.2400\nbest mean reward: 366.7600\ncurrent episode reward: 352.0000\nepisodes: 202\nexploration: 0.75700\nlearning_rate: 0.00010\nelapsed time: 805.9 seconds (0.22 hours)\n\nTimestep: 280000\nmean reward (100 episodes): 369.8400\nbest mean reward: 369.8400\ncurrent episode reward: 176.0000\nepisodes: 210\nexploration: 0.74800\nlearning_rate: 0.00010\nelapsed time: 841.1 seconds (0.23 hours)\n\nTimestep: 290000\nmean reward (100 episodes): 361.0000\nbest mean reward: 369.8400\ncurrent episode reward: 440.0000\nepisodes: 218\nexploration: 0.73900\nlearning_rate: 0.00010\nelapsed time: 877.7 seconds (0.24 hours)\n\nTimestep: 300000\nmean reward (100 episodes): 349.5600\nbest mean reward: 369.8400\ncurrent episode reward: 132.0000\nepisodes: 226\nexploration: 0.73000\nlearning_rate: 0.00010\nelapsed time: 913.5 seconds (0.25 hours)\n\nTimestep: 310000\nmean reward (100 episodes): 350.8800\nbest mean reward: 369.8400\ncurrent episode reward: 484.0000\nepisodes: 233\nexploration: 0.72100\nlearning_rate: 0.00010\nelapsed time: 949.2 seconds (0.26 hours)\n\nTimestep: 320000\nmean reward (100 episodes): 357.9200\nbest mean reward: 369.8400\ncurrent episode reward: 176.0000\nepisodes: 241\nexploration: 0.71200\nlearning_rate: 0.00010\nelapsed time: 985.5 seconds (0.27 hours)\n\nTimestep: 330000\nmean reward (100 episodes): 351.3200\nbest mean reward: 369.8400\ncurrent episode reward: 176.0000\nepisodes: 248\nexploration: 0.70300\nlearning_rate: 0.00010\nelapsed time: 1021.9 seconds (0.28 hours)\n\nTimestep: 340000\nmean reward (100 episodes): 355.2800\nbest mean reward: 369.8400\ncurrent episode reward: 484.0000\nepisodes: 255\nexploration: 0.69400\nlearning_rate: 0.00010\nelapsed time: 1058.2 seconds (0.29 hours)\n\nTimestep: 350000\nmean reward (100 episodes): 365.4000\nbest mean reward: 369.8400\ncurrent episode reward: 220.0000\nepisodes: 261\nexploration: 0.68500\nlearning_rate: 0.00010\nelapsed time: 1094.8 seconds (0.30 hours)\n\nTimestep: 360000\nmean reward (100 episodes): 364.9600\nbest mean reward: 369.8400\ncurrent episode reward: 484.0000\nepisodes: 267\nexploration: 0.67600\nlearning_rate: 0.00010\nelapsed time: 1132.0 seconds (0.31 hours)\n\nTimestep: 370000\nmean reward (100 episodes): 361.3600\nbest mean reward: 369.8400\ncurrent episode reward: 264.0000\nepisodes: 274\nexploration: 0.66700\nlearning_rate: 0.00010\nelapsed time: 1168.9 seconds (0.32 hours)\n\nTimestep: 380000\nmean reward (100 episodes): 360.8000\nbest mean reward: 369.8400\ncurrent episode reward: 396.0000\nepisodes: 281\nexploration: 0.65800\nlearning_rate: 0.00010\nelapsed time: 1205.6 seconds (0.33 hours)\n\nTimestep: 390000\nmean reward (100 episodes): 363.4400\nbest mean reward: 369.8400\ncurrent episode reward: 352.0000\nepisodes: 288\nexploration: 0.64900\nlearning_rate: 0.00010\nelapsed time: 1242.6 seconds (0.35 hours)\n\nTimestep: 400000\nmean reward (100 episodes): 359.0400\nbest mean reward: 369.8400\ncurrent episode reward: 440.0000\nepisodes: 296\nexploration: 0.64000\nlearning_rate: 0.00010\nelapsed time: 1279.1 seconds (0.36 hours)\n\nTimestep: 410000\nmean reward (100 episodes): 358.1600\nbest mean reward: 369.8400\ncurrent episode reward: 572.0000\nepisodes: 302\nexploration: 0.63100\nlearning_rate: 0.00010\nelapsed time: 1316.2 seconds (0.37 hours)\n\nTimestep: 420000\nmean reward (100 episodes): 366.5200\nbest mean reward: 369.8400\ncurrent episode reward: 352.0000\nepisodes: 308\nexploration: 0.62200\nlearning_rate: 0.00010\nelapsed time: 1352.9 seconds (0.38 hours)\n\nTimestep: 430000\nmean reward (100 episodes): 375.3200\nbest mean reward: 375.3200\ncurrent episode reward: 440.0000\nepisodes: 316\nexploration: 0.61300\nlearning_rate: 0.00010\nelapsed time: 1390.3 seconds (0.39 hours)\n\nTimestep: 440000\nmean reward (100 episodes): 380.2400\nbest mean reward: 380.2400\ncurrent episode reward: 756.0000\nepisodes: 323\nexploration: 0.60400\nlearning_rate: 0.00010\nelapsed time: 1427.4 seconds (0.40 hours)\n\nTimestep: 450000\nmean reward (100 episodes): 388.6000\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 329\nexploration: 0.59500\nlearning_rate: 0.00010\nelapsed time: 1464.8 seconds (0.41 hours)\n\nTimestep: 460000\nmean reward (100 episodes): 372.8800\nbest mean reward: 390.3600\ncurrent episode reward: 88.0000\nepisodes: 337\nexploration: 0.58600\nlearning_rate: 0.00010\nelapsed time: 1502.6 seconds (0.42 hours)\n\nTimestep: 470000\nmean reward (100 episodes): 377.7200\nbest mean reward: 390.3600\ncurrent episode reward: 660.0000\nepisodes: 344\nexploration: 0.57700\nlearning_rate: 0.00010\nelapsed time: 1542.2 seconds (0.43 hours)\n\nTimestep: 480000\nmean reward (100 episodes): 380.8000\nbest mean reward: 390.3600\ncurrent episode reward: 352.0000\nepisodes: 351\nexploration: 0.56800\nlearning_rate: 0.00010\nelapsed time: 1581.0 seconds (0.44 hours)\n\nTimestep: 490000\nmean reward (100 episodes): 375.5200\nbest mean reward: 390.3600\ncurrent episode reward: 528.0000\nepisodes: 359\nexploration: 0.55900\nlearning_rate: 0.00010\nelapsed time: 1619.7 seconds (0.45 hours)\n\nTimestep: 500000\nmean reward (100 episodes): 374.2000\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 366\nexploration: 0.55000\nlearning_rate: 0.00010\nelapsed time: 1659.5 seconds (0.46 hours)\n\nTimestep: 510000\nmean reward (100 episodes): 375.5200\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 373\nexploration: 0.54100\nlearning_rate: 0.00010\nelapsed time: 1698.6 seconds (0.47 hours)\n\nTimestep: 520000\nmean reward (100 episodes): 375.5200\nbest mean reward: 390.3600\ncurrent episode reward: 352.0000\nepisodes: 379\nexploration: 0.53200\nlearning_rate: 0.00010\nelapsed time: 1737.7 seconds (0.48 hours)\n\nTimestep: 530000\nmean reward (100 episodes): 378.6000\nbest mean reward: 390.3600\ncurrent episode reward: 396.0000\nepisodes: 385\nexploration: 0.52300\nlearning_rate: 0.00010\nelapsed time: 1777.3 seconds (0.49 hours)\n\nTimestep: 540000\nmean reward (100 episodes): 385.7200\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 392\nexploration: 0.51400\nlearning_rate: 0.00010\nelapsed time: 1816.2 seconds (0.50 hours)\n\nTimestep: 550000\nmean reward (100 episodes): 379.1200\nbest mean reward: 390.3600\ncurrent episode reward: 176.0000\nepisodes: 400\nexploration: 0.50500\nlearning_rate: 0.00010\nelapsed time: 1855.5 seconds (0.52 hours)\n\nTimestep: 560000\nmean reward (100 episodes): 377.3600\nbest mean reward: 390.3600\ncurrent episode reward: 484.0000\nepisodes: 407\nexploration: 0.49600\nlearning_rate: 0.00010\nelapsed time: 1895.0 seconds (0.53 hours)\n\nTimestep: 570000\nmean reward (100 episodes): 370.3200\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 416\nexploration: 0.48700\nlearning_rate: 0.00010\nelapsed time: 1934.9 seconds (0.54 hours)\n\nTimestep: 580000\nmean reward (100 episodes): 355.2800\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 424\nexploration: 0.47800\nlearning_rate: 0.00010\nelapsed time: 1974.4 seconds (0.55 hours)\n\nTimestep: 590000\nmean reward (100 episodes): 355.8400\nbest mean reward: 390.3600\ncurrent episode reward: 528.0000\nepisodes: 430\nexploration: 0.46900\nlearning_rate: 0.00010\nelapsed time: 2014.1 seconds (0.56 hours)\n\nTimestep: 600000\nmean reward (100 episodes): 357.0400\nbest mean reward: 390.3600\ncurrent episode reward: 88.0000\nepisodes: 438\nexploration: 0.46000\nlearning_rate: 0.00010\nelapsed time: 2052.7 seconds (0.57 hours)\n\nTimestep: 610000\nmean reward (100 episodes): 357.9200\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 445\nexploration: 0.45100\nlearning_rate: 0.00010\nelapsed time: 2092.4 seconds (0.58 hours)\n\nTimestep: 620000\nmean reward (100 episodes): 357.9200\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 452\nexploration: 0.44200\nlearning_rate: 0.00010\nelapsed time: 2132.1 seconds (0.59 hours)\n\nTimestep: 630000\nmean reward (100 episodes): 358.3600\nbest mean reward: 390.3600\ncurrent episode reward: 396.0000\nepisodes: 459\nexploration: 0.43300\nlearning_rate: 0.00010\nelapsed time: 2172.2 seconds (0.60 hours)\n\nTimestep: 640000\nmean reward (100 episodes): 350.4400\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 467\nexploration: 0.42400\nlearning_rate: 0.00010\nelapsed time: 2212.1 seconds (0.61 hours)\n\nTimestep: 650000\nmean reward (100 episodes): 344.2800\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 475\nexploration: 0.41500\nlearning_rate: 0.00010\nelapsed time: 2252.1 seconds (0.63 hours)\n\nTimestep: 660000\nmean reward (100 episodes): 342.6000\nbest mean reward: 390.3600\ncurrent episode reward: 440.0000\nepisodes: 482\nexploration: 0.40600\nlearning_rate: 0.00010\nelapsed time: 2291.5 seconds (0.64 hours)\n\nTimestep: 670000\nmean reward (100 episodes): 332.8400\nbest mean reward: 390.3600\ncurrent episode reward: 132.0000\nepisodes: 489\nexploration: 0.39700\nlearning_rate: 0.00010\nelapsed time: 2331.7 seconds (0.65 hours)\n\nTimestep: 680000\nmean reward (100 episodes): 334.1600\nbest mean reward: 390.3600\ncurrent episode reward: 44.0000\nepisodes: 496\nexploration: 0.38800\nlearning_rate: 0.00010\nelapsed time: 2372.1 seconds (0.66 hours)\n\nTimestep: 690000\nmean reward (100 episodes): 335.4800\nbest mean reward: 390.3600\ncurrent episode reward: 352.0000\nepisodes: 502\nexploration: 0.37900\nlearning_rate: 0.00010\nelapsed time: 2412.3 seconds (0.67 hours)\n\nTimestep: 700000\nmean reward (100 episodes): 336.8000\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 509\nexploration: 0.37000\nlearning_rate: 0.00010\nelapsed time: 2452.5 seconds (0.68 hours)\n\nTimestep: 710000\nmean reward (100 episodes): 338.1200\nbest mean reward: 390.3600\ncurrent episode reward: 88.0000\nepisodes: 517\nexploration: 0.36100\nlearning_rate: 0.00010\nelapsed time: 2494.5 seconds (0.69 hours)\n\nTimestep: 720000\nmean reward (100 episodes): 343.4800\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 523\nexploration: 0.35200\nlearning_rate: 0.00010\nelapsed time: 2535.5 seconds (0.70 hours)\n\nTimestep: 730000\nmean reward (100 episodes): 342.9200\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 531\nexploration: 0.34300\nlearning_rate: 0.00010\nelapsed time: 2577.5 seconds (0.72 hours)\n\nTimestep: 740000\nmean reward (100 episodes): 344.6800\nbest mean reward: 390.3600\ncurrent episode reward: 352.0000\nepisodes: 538\nexploration: 0.33400\nlearning_rate: 0.00010\nelapsed time: 2618.5 seconds (0.73 hours)\n\nTimestep: 750000\nmean reward (100 episodes): 341.1600\nbest mean reward: 390.3600\ncurrent episode reward: 484.0000\nepisodes: 546\nexploration: 0.32500\nlearning_rate: 0.00010\nelapsed time: 2659.2 seconds (0.74 hours)\n\nTimestep: 760000\nmean reward (100 episodes): 341.6000\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 553\nexploration: 0.31600\nlearning_rate: 0.00010\nelapsed time: 2701.1 seconds (0.75 hours)\n\nTimestep: 770000\nmean reward (100 episodes): 346.0000\nbest mean reward: 390.3600\ncurrent episode reward: 440.0000\nepisodes: 560\nexploration: 0.30700\nlearning_rate: 0.00010\nelapsed time: 2742.2 seconds (0.76 hours)\n\nTimestep: 780000\nmean reward (100 episodes): 355.2400\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 567\nexploration: 0.29800\nlearning_rate: 0.00010\nelapsed time: 2784.1 seconds (0.77 hours)\n\nTimestep: 790000\nmean reward (100 episodes): 358.3200\nbest mean reward: 390.3600\ncurrent episode reward: 660.0000\nepisodes: 573\nexploration: 0.28900\nlearning_rate: 0.00010\nelapsed time: 2825.5 seconds (0.78 hours)\n\nTimestep: 800000\nmean reward (100 episodes): 357.3600\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 580\nexploration: 0.28000\nlearning_rate: 0.00010\nelapsed time: 2866.7 seconds (0.80 hours)\n\nTimestep: 810000\nmean reward (100 episodes): 356.9200\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 587\nexploration: 0.27100\nlearning_rate: 0.00010\nelapsed time: 2909.7 seconds (0.81 hours)\n\nTimestep: 820000\nmean reward (100 episodes): 349.4400\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 594\nexploration: 0.26200\nlearning_rate: 0.00010\nelapsed time: 2951.7 seconds (0.82 hours)\n\nTimestep: 830000\nmean reward (100 episodes): 357.8400\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 602\nexploration: 0.25300\nlearning_rate: 0.00010\nelapsed time: 2994.0 seconds (0.83 hours)\n\nTimestep: 840000\nmean reward (100 episodes): 363.5600\nbest mean reward: 390.3600\ncurrent episode reward: 616.0000\nepisodes: 608\nexploration: 0.24400\nlearning_rate: 0.00010\nelapsed time: 3036.4 seconds (0.84 hours)\n\nTimestep: 850000\nmean reward (100 episodes): 365.7600\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 615\nexploration: 0.23500\nlearning_rate: 0.00010\nelapsed time: 3078.6 seconds (0.86 hours)\n\nTimestep: 860000\nmean reward (100 episodes): 363.0400\nbest mean reward: 390.3600\ncurrent episode reward: 176.0000\nepisodes: 621\nexploration: 0.22600\nlearning_rate: 0.00010\nelapsed time: 3120.9 seconds (0.87 hours)\n\nTimestep: 870000\nmean reward (100 episodes): 359.9600\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 628\nexploration: 0.21700\nlearning_rate: 0.00010\nelapsed time: 3164.4 seconds (0.88 hours)\n\nTimestep: 880000\nmean reward (100 episodes): 352.9200\nbest mean reward: 390.3600\ncurrent episode reward: 352.0000\nepisodes: 636\nexploration: 0.20800\nlearning_rate: 0.00010\nelapsed time: 3207.3 seconds (0.89 hours)\n\nTimestep: 890000\nmean reward (100 episodes): 345.4400\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 643\nexploration: 0.19900\nlearning_rate: 0.00010\nelapsed time: 3251.0 seconds (0.90 hours)\n\nTimestep: 900000\nmean reward (100 episodes): 340.7200\nbest mean reward: 390.3600\ncurrent episode reward: 804.0000\nepisodes: 649\nexploration: 0.19000\nlearning_rate: 0.00010\nelapsed time: 3294.7 seconds (0.92 hours)\n\nTimestep: 910000\nmean reward (100 episodes): 349.5200\nbest mean reward: 390.3600\ncurrent episode reward: 660.0000\nepisodes: 654\nexploration: 0.18100\nlearning_rate: 0.00010\nelapsed time: 3338.6 seconds (0.93 hours)\n\nTimestep: 920000\nmean reward (100 episodes): 349.0800\nbest mean reward: 390.3600\ncurrent episode reward: 88.0000\nepisodes: 659\nexploration: 0.17200\nlearning_rate: 0.00010\nelapsed time: 3382.3 seconds (0.94 hours)\n\nTimestep: 930000\nmean reward (100 episodes): 341.1600\nbest mean reward: 390.3600\ncurrent episode reward: 176.0000\nepisodes: 666\nexploration: 0.16300\nlearning_rate: 0.00010\nelapsed time: 3425.8 seconds (0.95 hours)\n\nTimestep: 940000\nmean reward (100 episodes): 349.0800\nbest mean reward: 390.3600\ncurrent episode reward: 616.0000\nepisodes: 671\nexploration: 0.15400\nlearning_rate: 0.00010\nelapsed time: 3471.0 seconds (0.96 hours)\n\nTimestep: 950000\nmean reward (100 episodes): 341.1600\nbest mean reward: 390.3600\ncurrent episode reward: 484.0000\nepisodes: 678\nexploration: 0.14500\nlearning_rate: 0.00010\nelapsed time: 3515.3 seconds (0.98 hours)\n\nTimestep: 960000\nmean reward (100 episodes): 337.6400\nbest mean reward: 390.3600\ncurrent episode reward: 484.0000\nepisodes: 685\nexploration: 0.13600\nlearning_rate: 0.00010\nelapsed time: 3558.9 seconds (0.99 hours)\n\nTimestep: 970000\nmean reward (100 episodes): 347.7600\nbest mean reward: 390.3600\ncurrent episode reward: 660.0000\nepisodes: 689\nexploration: 0.12700\nlearning_rate: 0.00010\nelapsed time: 3603.2 seconds (1.00 hours)\n\nTimestep: 980000\nmean reward (100 episodes): 362.7200\nbest mean reward: 390.3600\ncurrent episode reward: 572.0000\nepisodes: 694\nexploration: 0.11800\nlearning_rate: 0.00010\nelapsed time: 3647.3 seconds (1.01 hours)\n\nTimestep: 990000\nmean reward (100 episodes): 356.9600\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 701\nexploration: 0.10900\nlearning_rate: 0.00010\nelapsed time: 3691.4 seconds (1.03 hours)\n\nTimestep: 1000000\nmean reward (100 episodes): 350.3600\nbest mean reward: 390.3600\ncurrent episode reward: 440.0000\nepisodes: 707\nexploration: 0.10000\nlearning_rate: 0.00010\nelapsed time: 3736.3 seconds (1.04 hours)\n\nTimestep: 1010000\nmean reward (100 episodes): 341.1200\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 715\nexploration: 0.09978\nlearning_rate: 0.00010\nelapsed time: 3781.3 seconds (1.05 hours)\n\nTimestep: 1020000\nmean reward (100 episodes): 341.1200\nbest mean reward: 390.3600\ncurrent episode reward: 440.0000\nepisodes: 722\nexploration: 0.09955\nlearning_rate: 0.00010\nelapsed time: 3826.6 seconds (1.06 hours)\n\nTimestep: 1030000\nmean reward (100 episodes): 340.2400\nbest mean reward: 390.3600\ncurrent episode reward: 616.0000\nepisodes: 729\nexploration: 0.09933\nlearning_rate: 0.00010\nelapsed time: 3871.6 seconds (1.08 hours)\n\nTimestep: 1040000\nmean reward (100 episodes): 352.2000\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 735\nexploration: 0.09910\nlearning_rate: 0.00010\nelapsed time: 3917.2 seconds (1.09 hours)\n\nTimestep: 1050000\nmean reward (100 episodes): 355.7200\nbest mean reward: 390.3600\ncurrent episode reward: 528.0000\nepisodes: 741\nexploration: 0.09888\nlearning_rate: 0.00010\nelapsed time: 3961.9 seconds (1.10 hours)\n\nTimestep: 1060000\nmean reward (100 episodes): 357.9200\nbest mean reward: 390.3600\ncurrent episode reward: 44.0000\nepisodes: 748\nexploration: 0.09865\nlearning_rate: 0.00010\nelapsed time: 4007.0 seconds (1.11 hours)\n\nTimestep: 1070000\nmean reward (100 episodes): 338.8800\nbest mean reward: 390.3600\ncurrent episode reward: 176.0000\nepisodes: 755\nexploration: 0.09842\nlearning_rate: 0.00010\nelapsed time: 4052.4 seconds (1.13 hours)\n\nTimestep: 1080000\nmean reward (100 episodes): 335.3600\nbest mean reward: 390.3600\ncurrent episode reward: 572.0000\nepisodes: 763\nexploration: 0.09820\nlearning_rate: 0.00010\nelapsed time: 4097.0 seconds (1.14 hours)\n\nTimestep: 1090000\nmean reward (100 episodes): 334.9200\nbest mean reward: 390.3600\ncurrent episode reward: 440.0000\nepisodes: 770\nexploration: 0.09798\nlearning_rate: 0.00010\nelapsed time: 4141.1 seconds (1.15 hours)\n\nTimestep: 1100000\nmean reward (100 episodes): 330.9600\nbest mean reward: 390.3600\ncurrent episode reward: 352.0000\nepisodes: 775\nexploration: 0.09775\nlearning_rate: 0.00010\nelapsed time: 4185.2 seconds (1.16 hours)\n\nTimestep: 1110000\nmean reward (100 episodes): 338.4400\nbest mean reward: 390.3600\ncurrent episode reward: 88.0000\nepisodes: 782\nexploration: 0.09753\nlearning_rate: 0.00010\nelapsed time: 4229.8 seconds (1.17 hours)\n\nTimestep: 1120000\nmean reward (100 episodes): 327.4400\nbest mean reward: 390.3600\ncurrent episode reward: 352.0000\nepisodes: 789\nexploration: 0.09730\nlearning_rate: 0.00010\nelapsed time: 4274.7 seconds (1.19 hours)\n\nTimestep: 1130000\nmean reward (100 episodes): 324.8000\nbest mean reward: 390.3600\ncurrent episode reward: 440.0000\nepisodes: 794\nexploration: 0.09708\nlearning_rate: 0.00010\nelapsed time: 4320.4 seconds (1.20 hours)\n\nTimestep: 1140000\nmean reward (100 episodes): 330.9600\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 800\nexploration: 0.09685\nlearning_rate: 0.00010\nelapsed time: 4364.9 seconds (1.21 hours)\n\nTimestep: 1150000\nmean reward (100 episodes): 341.5200\nbest mean reward: 390.3600\ncurrent episode reward: 528.0000\nepisodes: 806\nexploration: 0.09663\nlearning_rate: 0.00010\nelapsed time: 4409.6 seconds (1.22 hours)\n\nTimestep: 1160000\nmean reward (100 episodes): 342.8400\nbest mean reward: 390.3600\ncurrent episode reward: 352.0000\nepisodes: 813\nexploration: 0.09640\nlearning_rate: 0.00010\nelapsed time: 4454.8 seconds (1.24 hours)\n\nTimestep: 1170000\nmean reward (100 episodes): 345.4800\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 821\nexploration: 0.09618\nlearning_rate: 0.00010\nelapsed time: 4499.8 seconds (1.25 hours)\n\nTimestep: 1180000\nmean reward (100 episodes): 350.7600\nbest mean reward: 390.3600\ncurrent episode reward: 176.0000\nepisodes: 828\nexploration: 0.09595\nlearning_rate: 0.00010\nelapsed time: 4544.8 seconds (1.26 hours)\n\nTimestep: 1190000\nmean reward (100 episodes): 337.9200\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 835\nexploration: 0.09573\nlearning_rate: 0.00010\nelapsed time: 4589.2 seconds (1.27 hours)\n\nTimestep: 1200000\nmean reward (100 episodes): 335.2800\nbest mean reward: 390.3600\ncurrent episode reward: 484.0000\nepisodes: 843\nexploration: 0.09550\nlearning_rate: 0.00010\nelapsed time: 4634.0 seconds (1.29 hours)\n\nTimestep: 1210000\nmean reward (100 episodes): 330.0000\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 851\nexploration: 0.09527\nlearning_rate: 0.00010\nelapsed time: 4677.9 seconds (1.30 hours)\n\nTimestep: 1220000\nmean reward (100 episodes): 331.3200\nbest mean reward: 390.3600\ncurrent episode reward: 440.0000\nepisodes: 857\nexploration: 0.09505\nlearning_rate: 0.00010\nelapsed time: 4723.0 seconds (1.31 hours)\n\nTimestep: 1230000\nmean reward (100 episodes): 341.0000\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 864\nexploration: 0.09483\nlearning_rate: 0.00010\nelapsed time: 4767.4 seconds (1.32 hours)\n\nTimestep: 1240000\nmean reward (100 episodes): 341.8800\nbest mean reward: 390.3600\ncurrent episode reward: 660.0000\nepisodes: 871\nexploration: 0.09460\nlearning_rate: 0.00010\nelapsed time: 4812.3 seconds (1.34 hours)\n\nTimestep: 1250000\nmean reward (100 episodes): 337.9200\nbest mean reward: 390.3600\ncurrent episode reward: 660.0000\nepisodes: 878\nexploration: 0.09438\nlearning_rate: 0.00010\nelapsed time: 4856.7 seconds (1.35 hours)\n\nTimestep: 1260000\nmean reward (100 episodes): 340.5600\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 885\nexploration: 0.09415\nlearning_rate: 0.00010\nelapsed time: 4901.8 seconds (1.36 hours)\n\nTimestep: 1270000\nmean reward (100 episodes): 342.7600\nbest mean reward: 390.3600\ncurrent episode reward: 396.0000\nepisodes: 891\nexploration: 0.09393\nlearning_rate: 0.00010\nelapsed time: 4946.3 seconds (1.37 hours)\n\nTimestep: 1280000\nmean reward (100 episodes): 329.5600\nbest mean reward: 390.3600\ncurrent episode reward: 132.0000\nepisodes: 898\nexploration: 0.09370\nlearning_rate: 0.00010\nelapsed time: 4990.8 seconds (1.39 hours)\n\nTimestep: 1290000\nmean reward (100 episodes): 328.7200\nbest mean reward: 390.3600\ncurrent episode reward: 708.0000\nepisodes: 904\nexploration: 0.09348\nlearning_rate: 0.00010\nelapsed time: 5035.8 seconds (1.40 hours)\n\nTimestep: 1300000\nmean reward (100 episodes): 323.0000\nbest mean reward: 390.3600\ncurrent episode reward: 88.0000\nepisodes: 911\nexploration: 0.09325\nlearning_rate: 0.00010\nelapsed time: 5079.8 seconds (1.41 hours)\n\nTimestep: 1310000\nmean reward (100 episodes): 315.0800\nbest mean reward: 390.3600\ncurrent episode reward: 352.0000\nepisodes: 919\nexploration: 0.09303\nlearning_rate: 0.00010\nelapsed time: 5124.9 seconds (1.42 hours)\n\nTimestep: 1320000\nmean reward (100 episodes): 321.6800\nbest mean reward: 390.3600\ncurrent episode reward: 176.0000\nepisodes: 925\nexploration: 0.09280\nlearning_rate: 0.00010\nelapsed time: 5170.0 seconds (1.44 hours)\n\nTimestep: 1330000\nmean reward (100 episodes): 324.3200\nbest mean reward: 390.3600\ncurrent episode reward: 396.0000\nepisodes: 931\nexploration: 0.09258\nlearning_rate: 0.00010\nelapsed time: 5214.9 seconds (1.45 hours)\n\nTimestep: 1340000\nmean reward (100 episodes): 332.6800\nbest mean reward: 390.3600\ncurrent episode reward: 484.0000\nepisodes: 937\nexploration: 0.09235\nlearning_rate: 0.00010\nelapsed time: 5260.1 seconds (1.46 hours)\n\nTimestep: 1350000\nmean reward (100 episodes): 335.7600\nbest mean reward: 390.3600\ncurrent episode reward: 352.0000\nepisodes: 944\nexploration: 0.09213\nlearning_rate: 0.00010\nelapsed time: 5305.2 seconds (1.47 hours)\n\nTimestep: 1360000\nmean reward (100 episodes): 341.9200\nbest mean reward: 390.3600\ncurrent episode reward: 440.0000\nepisodes: 951\nexploration: 0.09190\nlearning_rate: 0.00010\nelapsed time: 5350.0 seconds (1.49 hours)\n\nTimestep: 1370000\nmean reward (100 episodes): 338.4000\nbest mean reward: 390.3600\ncurrent episode reward: 440.0000\nepisodes: 958\nexploration: 0.09168\nlearning_rate: 0.00010\nelapsed time: 5394.5 seconds (1.50 hours)\n\nTimestep: 1380000\nmean reward (100 episodes): 332.6800\nbest mean reward: 390.3600\ncurrent episode reward: 132.0000\nepisodes: 965\nexploration: 0.09145\nlearning_rate: 0.00010\nelapsed time: 5439.1 seconds (1.51 hours)\n\nTimestep: 1390000\nmean reward (100 episodes): 325.6400\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 973\nexploration: 0.09123\nlearning_rate: 0.00010\nelapsed time: 5483.8 seconds (1.52 hours)\n\nTimestep: 1400000\nmean reward (100 episodes): 326.0800\nbest mean reward: 390.3600\ncurrent episode reward: 396.0000\nepisodes: 980\nexploration: 0.09100\nlearning_rate: 0.00010\nelapsed time: 5528.3 seconds (1.54 hours)\n\nTimestep: 1410000\nmean reward (100 episodes): 328.2800\nbest mean reward: 390.3600\ncurrent episode reward: 132.0000\nepisodes: 987\nexploration: 0.09078\nlearning_rate: 0.00009\nelapsed time: 5573.1 seconds (1.55 hours)\n\nTimestep: 1420000\nmean reward (100 episodes): 325.2000\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 994\nexploration: 0.09055\nlearning_rate: 0.00009\nelapsed time: 5617.5 seconds (1.56 hours)\n\nTimestep: 1430000\nmean reward (100 episodes): 326.9600\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 1000\nexploration: 0.09033\nlearning_rate: 0.00009\nelapsed time: 5662.8 seconds (1.57 hours)\n\nTimestep: 1440000\nmean reward (100 episodes): 332.2000\nbest mean reward: 390.3600\ncurrent episode reward: 616.0000\nepisodes: 1005\nexploration: 0.09010\nlearning_rate: 0.00009\nelapsed time: 5707.7 seconds (1.59 hours)\n\nTimestep: 1450000\nmean reward (100 episodes): 346.2800\nbest mean reward: 390.3600\ncurrent episode reward: 660.0000\nepisodes: 1011\nexploration: 0.08988\nlearning_rate: 0.00009\nelapsed time: 5752.2 seconds (1.60 hours)\n\nTimestep: 1460000\nmean reward (100 episodes): 348.9200\nbest mean reward: 390.3600\ncurrent episode reward: 132.0000\nepisodes: 1018\nexploration: 0.08965\nlearning_rate: 0.00009\nelapsed time: 5795.9 seconds (1.61 hours)\n\nTimestep: 1470000\nmean reward (100 episodes): 339.6800\nbest mean reward: 390.3600\ncurrent episode reward: 132.0000\nepisodes: 1025\nexploration: 0.08943\nlearning_rate: 0.00009\nelapsed time: 5840.4 seconds (1.62 hours)\n\nTimestep: 1480000\nmean reward (100 episodes): 343.2000\nbest mean reward: 390.3600\ncurrent episode reward: 528.0000\nepisodes: 1031\nexploration: 0.08920\nlearning_rate: 0.00009\nelapsed time: 5885.3 seconds (1.63 hours)\n\nTimestep: 1490000\nmean reward (100 episodes): 338.3600\nbest mean reward: 390.3600\ncurrent episode reward: 352.0000\nepisodes: 1038\nexploration: 0.08897\nlearning_rate: 0.00009\nelapsed time: 5929.6 seconds (1.65 hours)\n\nTimestep: 1500000\nmean reward (100 episodes): 342.7600\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 1043\nexploration: 0.08875\nlearning_rate: 0.00009\nelapsed time: 5974.0 seconds (1.66 hours)\n\nTimestep: 1510000\nmean reward (100 episodes): 344.5200\nbest mean reward: 390.3600\ncurrent episode reward: 176.0000\nepisodes: 1049\nexploration: 0.08853\nlearning_rate: 0.00009\nelapsed time: 6017.9 seconds (1.67 hours)\n\nTimestep: 1520000\nmean reward (100 episodes): 348.4800\nbest mean reward: 390.3600\ncurrent episode reward: 352.0000\nepisodes: 1056\nexploration: 0.08830\nlearning_rate: 0.00009\nelapsed time: 6062.2 seconds (1.68 hours)\n\nTimestep: 1530000\nmean reward (100 episodes): 339.6800\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 1063\nexploration: 0.08808\nlearning_rate: 0.00009\nelapsed time: 6106.7 seconds (1.70 hours)\n\nTimestep: 1540000\nmean reward (100 episodes): 348.9200\nbest mean reward: 390.3600\ncurrent episode reward: 176.0000\nepisodes: 1070\nexploration: 0.08785\nlearning_rate: 0.00009\nelapsed time: 6150.6 seconds (1.71 hours)\n\nTimestep: 1550000\nmean reward (100 episodes): 349.8000\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 1077\nexploration: 0.08763\nlearning_rate: 0.00009\nelapsed time: 6195.3 seconds (1.72 hours)\n\nTimestep: 1560000\nmean reward (100 episodes): 341.4400\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 1083\nexploration: 0.08740\nlearning_rate: 0.00009\nelapsed time: 6240.3 seconds (1.73 hours)\n\nTimestep: 1570000\nmean reward (100 episodes): 345.4000\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 1090\nexploration: 0.08718\nlearning_rate: 0.00009\nelapsed time: 6284.5 seconds (1.75 hours)\n\nTimestep: 1580000\nmean reward (100 episodes): 343.2000\nbest mean reward: 390.3600\ncurrent episode reward: 528.0000\nepisodes: 1097\nexploration: 0.08695\nlearning_rate: 0.00009\nelapsed time: 6329.4 seconds (1.76 hours)\n\nTimestep: 1590000\nmean reward (100 episodes): 335.2800\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 1103\nexploration: 0.08673\nlearning_rate: 0.00009\nelapsed time: 6374.3 seconds (1.77 hours)\n\nTimestep: 1600000\nmean reward (100 episodes): 315.9200\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 1111\nexploration: 0.08650\nlearning_rate: 0.00009\nelapsed time: 6419.0 seconds (1.78 hours)\n\nTimestep: 1610000\nmean reward (100 episodes): 319.0000\nbest mean reward: 390.3600\ncurrent episode reward: 440.0000\nepisodes: 1118\nexploration: 0.08628\nlearning_rate: 0.00009\nelapsed time: 6463.6 seconds (1.80 hours)\n\nTimestep: 1620000\nmean reward (100 episodes): 322.5200\nbest mean reward: 390.3600\ncurrent episode reward: 396.0000\nepisodes: 1124\nexploration: 0.08605\nlearning_rate: 0.00009\nelapsed time: 6508.5 seconds (1.81 hours)\n\nTimestep: 1630000\nmean reward (100 episodes): 325.6000\nbest mean reward: 390.3600\ncurrent episode reward: 396.0000\nepisodes: 1130\nexploration: 0.08582\nlearning_rate: 0.00009\nelapsed time: 6553.6 seconds (1.82 hours)\n\nTimestep: 1640000\nmean reward (100 episodes): 321.6400\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 1136\nexploration: 0.08560\nlearning_rate: 0.00009\nelapsed time: 6598.8 seconds (1.83 hours)\n\nTimestep: 1650000\nmean reward (100 episodes): 315.4800\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 1144\nexploration: 0.08538\nlearning_rate: 0.00009\nelapsed time: 6643.9 seconds (1.85 hours)\n\nTimestep: 1660000\nmean reward (100 episodes): 311.9600\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 1150\nexploration: 0.08515\nlearning_rate: 0.00009\nelapsed time: 6688.7 seconds (1.86 hours)\n\nTimestep: 1670000\nmean reward (100 episodes): 307.1200\nbest mean reward: 390.3600\ncurrent episode reward: 176.0000\nepisodes: 1157\nexploration: 0.08493\nlearning_rate: 0.00009\nelapsed time: 6733.4 seconds (1.87 hours)\n\nTimestep: 1680000\nmean reward (100 episodes): 311.5200\nbest mean reward: 390.3600\ncurrent episode reward: 176.0000\nepisodes: 1164\nexploration: 0.08470\nlearning_rate: 0.00009\nelapsed time: 6778.4 seconds (1.88 hours)\n\nTimestep: 1690000\nmean reward (100 episodes): 312.4000\nbest mean reward: 390.3600\ncurrent episode reward: 352.0000\nepisodes: 1171\nexploration: 0.08448\nlearning_rate: 0.00009\nelapsed time: 6823.1 seconds (1.90 hours)\n\nTimestep: 1700000\nmean reward (100 episodes): 312.8400\nbest mean reward: 390.3600\ncurrent episode reward: 352.0000\nepisodes: 1177\nexploration: 0.08425\nlearning_rate: 0.00009\nelapsed time: 6868.1 seconds (1.91 hours)\n\nTimestep: 1710000\nmean reward (100 episodes): 311.5200\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 1184\nexploration: 0.08403\nlearning_rate: 0.00009\nelapsed time: 6912.6 seconds (1.92 hours)\n\nTimestep: 1720000\nmean reward (100 episodes): 315.4800\nbest mean reward: 390.3600\ncurrent episode reward: 176.0000\nepisodes: 1191\nexploration: 0.08380\nlearning_rate: 0.00009\nelapsed time: 6958.0 seconds (1.93 hours)\n\nTimestep: 1730000\nmean reward (100 episodes): 311.0800\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 1199\nexploration: 0.08358\nlearning_rate: 0.00009\nelapsed time: 7002.1 seconds (1.95 hours)\n\nTimestep: 1740000\nmean reward (100 episodes): 314.6000\nbest mean reward: 390.3600\ncurrent episode reward: 616.0000\nepisodes: 1206\nexploration: 0.08335\nlearning_rate: 0.00009\nelapsed time: 7047.0 seconds (1.96 hours)\n\nTimestep: 1750000\nmean reward (100 episodes): 306.2400\nbest mean reward: 390.3600\ncurrent episode reward: 440.0000\nepisodes: 1214\nexploration: 0.08313\nlearning_rate: 0.00009\nelapsed time: 7091.4 seconds (1.97 hours)\n\nTimestep: 1760000\nmean reward (100 episodes): 304.0400\nbest mean reward: 390.3600\ncurrent episode reward: 484.0000\nepisodes: 1221\nexploration: 0.08290\nlearning_rate: 0.00009\nelapsed time: 7135.9 seconds (1.98 hours)\n\nTimestep: 1770000\nmean reward (100 episodes): 300.0800\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 1227\nexploration: 0.08267\nlearning_rate: 0.00009\nelapsed time: 7180.4 seconds (1.99 hours)\n\nTimestep: 1780000\nmean reward (100 episodes): 303.6000\nbest mean reward: 390.3600\ncurrent episode reward: 88.0000\nepisodes: 1235\nexploration: 0.08245\nlearning_rate: 0.00009\nelapsed time: 7225.4 seconds (2.01 hours)\n\nTimestep: 1790000\nmean reward (100 episodes): 301.8400\nbest mean reward: 390.3600\ncurrent episode reward: 132.0000\nepisodes: 1242\nexploration: 0.08223\nlearning_rate: 0.00009\nelapsed time: 7269.3 seconds (2.02 hours)\n\nTimestep: 1800000\nmean reward (100 episodes): 308.8800\nbest mean reward: 390.3600\ncurrent episode reward: 572.0000\nepisodes: 1248\nexploration: 0.08200\nlearning_rate: 0.00009\nelapsed time: 7314.0 seconds (2.03 hours)\n\nTimestep: 1810000\nmean reward (100 episodes): 299.6400\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 1256\nexploration: 0.08178\nlearning_rate: 0.00009\nelapsed time: 7358.4 seconds (2.04 hours)\n\nTimestep: 1820000\nmean reward (100 episodes): 293.9200\nbest mean reward: 390.3600\ncurrent episode reward: 176.0000\nepisodes: 1264\nexploration: 0.08155\nlearning_rate: 0.00009\nelapsed time: 7403.6 seconds (2.06 hours)\n\nTimestep: 1830000\nmean reward (100 episodes): 292.6000\nbest mean reward: 390.3600\ncurrent episode reward: 572.0000\nepisodes: 1270\nexploration: 0.08133\nlearning_rate: 0.00009\nelapsed time: 7448.9 seconds (2.07 hours)\n\nTimestep: 1840000\nmean reward (100 episodes): 287.7600\nbest mean reward: 390.3600\ncurrent episode reward: 484.0000\nepisodes: 1277\nexploration: 0.08110\nlearning_rate: 0.00009\nelapsed time: 7493.4 seconds (2.08 hours)\n\nTimestep: 1850000\nmean reward (100 episodes): 288.6400\nbest mean reward: 390.3600\ncurrent episode reward: 396.0000\nepisodes: 1284\nexploration: 0.08088\nlearning_rate: 0.00009\nelapsed time: 7538.1 seconds (2.09 hours)\n\nTimestep: 1860000\nmean reward (100 episodes): 284.2400\nbest mean reward: 390.3600\ncurrent episode reward: 88.0000\nepisodes: 1291\nexploration: 0.08065\nlearning_rate: 0.00009\nelapsed time: 7581.6 seconds (2.11 hours)\n\nTimestep: 1870000\nmean reward (100 episodes): 289.5200\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 1298\nexploration: 0.08042\nlearning_rate: 0.00009\nelapsed time: 7626.3 seconds (2.12 hours)\n\nTimestep: 1880000\nmean reward (100 episodes): 289.0800\nbest mean reward: 390.3600\ncurrent episode reward: 352.0000\nepisodes: 1305\nexploration: 0.08020\nlearning_rate: 0.00009\nelapsed time: 7671.2 seconds (2.13 hours)\n\nTimestep: 1890000\nmean reward (100 episodes): 292.1600\nbest mean reward: 390.3600\ncurrent episode reward: 132.0000\nepisodes: 1312\nexploration: 0.07998\nlearning_rate: 0.00009\nelapsed time: 7716.3 seconds (2.14 hours)\n\nTimestep: 1900000\nmean reward (100 episodes): 297.4400\nbest mean reward: 390.3600\ncurrent episode reward: 660.0000\nepisodes: 1318\nexploration: 0.07975\nlearning_rate: 0.00009\nelapsed time: 7760.4 seconds (2.16 hours)\n\nTimestep: 1910000\nmean reward (100 episodes): 294.3600\nbest mean reward: 390.3600\ncurrent episode reward: 176.0000\nepisodes: 1326\nexploration: 0.07952\nlearning_rate: 0.00009\nelapsed time: 7805.7 seconds (2.17 hours)\n\nTimestep: 1920000\nmean reward (100 episodes): 291.7200\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 1332\nexploration: 0.07930\nlearning_rate: 0.00009\nelapsed time: 7850.1 seconds (2.18 hours)\n\nTimestep: 1930000\nmean reward (100 episodes): 291.2800\nbest mean reward: 390.3600\ncurrent episode reward: 484.0000\nepisodes: 1338\nexploration: 0.07908\nlearning_rate: 0.00009\nelapsed time: 7895.2 seconds (2.19 hours)\n\nTimestep: 1940000\nmean reward (100 episodes): 298.7600\nbest mean reward: 390.3600\ncurrent episode reward: 396.0000\nepisodes: 1345\nexploration: 0.07885\nlearning_rate: 0.00009\nelapsed time: 7939.5 seconds (2.21 hours)\n\nTimestep: 1950000\nmean reward (100 episodes): 291.7200\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 1353\nexploration: 0.07863\nlearning_rate: 0.00009\nelapsed time: 7983.9 seconds (2.22 hours)\n\nTimestep: 1960000\nmean reward (100 episodes): 307.1200\nbest mean reward: 390.3600\ncurrent episode reward: 484.0000\nepisodes: 1359\nexploration: 0.07840\nlearning_rate: 0.00009\nelapsed time: 8028.4 seconds (2.23 hours)\n\nTimestep: 1970000\nmean reward (100 episodes): 314.1600\nbest mean reward: 390.3600\ncurrent episode reward: 528.0000\nepisodes: 1365\nexploration: 0.07818\nlearning_rate: 0.00009\nelapsed time: 8073.9 seconds (2.24 hours)\n\nTimestep: 1980000\nmean reward (100 episodes): 310.6400\nbest mean reward: 390.3600\ncurrent episode reward: 396.0000\nepisodes: 1373\nexploration: 0.07795\nlearning_rate: 0.00009\nelapsed time: 8118.4 seconds (2.26 hours)\n\nTimestep: 1990000\nmean reward (100 episodes): 305.8000\nbest mean reward: 390.3600\ncurrent episode reward: 176.0000\nepisodes: 1380\nexploration: 0.07773\nlearning_rate: 0.00009\nelapsed time: 8163.6 seconds (2.27 hours)\n\nTimestep: 2000000\nmean reward (100 episodes): 298.3200\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 1388\nexploration: 0.07750\nlearning_rate: 0.00009\nelapsed time: 8207.6 seconds (2.28 hours)\n\nTimestep: 2010000\nmean reward (100 episodes): 295.2400\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 1395\nexploration: 0.07728\nlearning_rate: 0.00009\nelapsed time: 8252.0 seconds (2.29 hours)\n\nTimestep: 2020000\nmean reward (100 episodes): 292.6000\nbest mean reward: 390.3600\ncurrent episode reward: 176.0000\nepisodes: 1403\nexploration: 0.07705\nlearning_rate: 0.00009\nelapsed time: 8296.7 seconds (2.30 hours)\n\nTimestep: 2030000\nmean reward (100 episodes): 286.0000\nbest mean reward: 390.3600\ncurrent episode reward: 440.0000\nepisodes: 1411\nexploration: 0.07683\nlearning_rate: 0.00009\nelapsed time: 8341.3 seconds (2.32 hours)\n\nTimestep: 2040000\nmean reward (100 episodes): 282.0400\nbest mean reward: 390.3600\ncurrent episode reward: 352.0000\nepisodes: 1418\nexploration: 0.07660\nlearning_rate: 0.00009\nelapsed time: 8386.1 seconds (2.33 hours)\n\nTimestep: 2050000\nmean reward (100 episodes): 284.6800\nbest mean reward: 390.3600\ncurrent episode reward: 352.0000\nepisodes: 1425\nexploration: 0.07637\nlearning_rate: 0.00009\nelapsed time: 8429.9 seconds (2.34 hours)\n\nTimestep: 2060000\nmean reward (100 episodes): 290.8400\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 1432\nexploration: 0.07615\nlearning_rate: 0.00009\nelapsed time: 8474.2 seconds (2.35 hours)\n\nTimestep: 2070000\nmean reward (100 episodes): 290.8400\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 1438\nexploration: 0.07593\nlearning_rate: 0.00009\nelapsed time: 8518.8 seconds (2.37 hours)\n\nTimestep: 2080000\nmean reward (100 episodes): 290.4000\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 1444\nexploration: 0.07570\nlearning_rate: 0.00009\nelapsed time: 8563.0 seconds (2.38 hours)\n\nTimestep: 2090000\nmean reward (100 episodes): 291.2800\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 1451\nexploration: 0.07548\nlearning_rate: 0.00009\nelapsed time: 8607.4 seconds (2.39 hours)\n\nTimestep: 2100000\nmean reward (100 episodes): 281.6000\nbest mean reward: 390.3600\ncurrent episode reward: 132.0000\nepisodes: 1458\nexploration: 0.07525\nlearning_rate: 0.00009\nelapsed time: 8651.2 seconds (2.40 hours)\n\nTimestep: 2110000\nmean reward (100 episodes): 271.9200\nbest mean reward: 390.3600\ncurrent episode reward: 352.0000\nepisodes: 1466\nexploration: 0.07503\nlearning_rate: 0.00009\nelapsed time: 8696.0 seconds (2.42 hours)\n\nTimestep: 2120000\nmean reward (100 episodes): 276.3200\nbest mean reward: 390.3600\ncurrent episode reward: 528.0000\nepisodes: 1473\nexploration: 0.07480\nlearning_rate: 0.00009\nelapsed time: 8740.3 seconds (2.43 hours)\n\nTimestep: 2130000\nmean reward (100 episodes): 289.5200\nbest mean reward: 390.3600\ncurrent episode reward: 484.0000\nepisodes: 1479\nexploration: 0.07458\nlearning_rate: 0.00009\nelapsed time: 8784.9 seconds (2.44 hours)\n\nTimestep: 2140000\nmean reward (100 episodes): 286.0000\nbest mean reward: 390.3600\ncurrent episode reward: 88.0000\nepisodes: 1487\nexploration: 0.07435\nlearning_rate: 0.00009\nelapsed time: 8829.0 seconds (2.45 hours)\n\nTimestep: 2150000\nmean reward (100 episodes): 288.6400\nbest mean reward: 390.3600\ncurrent episode reward: 176.0000\nepisodes: 1494\nexploration: 0.07412\nlearning_rate: 0.00009\nelapsed time: 8873.0 seconds (2.46 hours)\n\nTimestep: 2160000\nmean reward (100 episodes): 289.9600\nbest mean reward: 390.3600\ncurrent episode reward: 176.0000\nepisodes: 1501\nexploration: 0.07390\nlearning_rate: 0.00009\nelapsed time: 8917.8 seconds (2.48 hours)\n\nTimestep: 2170000\nmean reward (100 episodes): 290.4000\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 1508\nexploration: 0.07368\nlearning_rate: 0.00009\nelapsed time: 8963.2 seconds (2.49 hours)\n\nTimestep: 2180000\nmean reward (100 episodes): 285.5600\nbest mean reward: 390.3600\ncurrent episode reward: 88.0000\nepisodes: 1515\nexploration: 0.07345\nlearning_rate: 0.00009\nelapsed time: 9006.8 seconds (2.50 hours)\n\nTimestep: 2190000\nmean reward (100 episodes): 285.5600\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 1522\nexploration: 0.07322\nlearning_rate: 0.00009\nelapsed time: 9052.4 seconds (2.51 hours)\n\nTimestep: 2200000\nmean reward (100 episodes): 272.8000\nbest mean reward: 390.3600\ncurrent episode reward: 88.0000\nepisodes: 1530\nexploration: 0.07300\nlearning_rate: 0.00009\nelapsed time: 9096.9 seconds (2.53 hours)\n\nTimestep: 2210000\nmean reward (100 episodes): 268.8400\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 1538\nexploration: 0.07278\nlearning_rate: 0.00008\nelapsed time: 9141.0 seconds (2.54 hours)\n\nTimestep: 2220000\nmean reward (100 episodes): 269.2800\nbest mean reward: 390.3600\ncurrent episode reward: 88.0000\nepisodes: 1545\nexploration: 0.07255\nlearning_rate: 0.00008\nelapsed time: 9185.1 seconds (2.55 hours)\n\nTimestep: 2230000\nmean reward (100 episodes): 265.3200\nbest mean reward: 390.3600\ncurrent episode reward: 396.0000\nepisodes: 1552\nexploration: 0.07233\nlearning_rate: 0.00008\nelapsed time: 9229.2 seconds (2.56 hours)\n\nTimestep: 2240000\nmean reward (100 episodes): 270.1600\nbest mean reward: 390.3600\ncurrent episode reward: 176.0000\nepisodes: 1559\nexploration: 0.07210\nlearning_rate: 0.00008\nelapsed time: 9273.9 seconds (2.58 hours)\n\nTimestep: 2250000\nmean reward (100 episodes): 276.7600\nbest mean reward: 390.3600\ncurrent episode reward: 396.0000\nepisodes: 1565\nexploration: 0.07187\nlearning_rate: 0.00008\nelapsed time: 9319.2 seconds (2.59 hours)\n\nTimestep: 2260000\nmean reward (100 episodes): 274.1200\nbest mean reward: 390.3600\ncurrent episode reward: 132.0000\nepisodes: 1572\nexploration: 0.07165\nlearning_rate: 0.00008\nelapsed time: 9364.1 seconds (2.60 hours)\n\nTimestep: 2270000\nmean reward (100 episodes): 266.6400\nbest mean reward: 390.3600\ncurrent episode reward: 132.0000\nepisodes: 1579\nexploration: 0.07143\nlearning_rate: 0.00008\nelapsed time: 9408.8 seconds (2.61 hours)\n\nTimestep: 2280000\nmean reward (100 episodes): 275.0000\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 1586\nexploration: 0.07120\nlearning_rate: 0.00008\nelapsed time: 9453.1 seconds (2.63 hours)\n\nTimestep: 2290000\nmean reward (100 episodes): 275.8800\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 1593\nexploration: 0.07097\nlearning_rate: 0.00008\nelapsed time: 9498.3 seconds (2.64 hours)\n\nTimestep: 2300000\nmean reward (100 episodes): 280.2800\nbest mean reward: 390.3600\ncurrent episode reward: 132.0000\nepisodes: 1600\nexploration: 0.07075\nlearning_rate: 0.00008\nelapsed time: 9543.3 seconds (2.65 hours)\n\nTimestep: 2310000\nmean reward (100 episodes): 281.6000\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 1607\nexploration: 0.07053\nlearning_rate: 0.00008\nelapsed time: 9587.9 seconds (2.66 hours)\n\nTimestep: 2320000\nmean reward (100 episodes): 278.9600\nbest mean reward: 390.3600\ncurrent episode reward: 44.0000\nepisodes: 1615\nexploration: 0.07030\nlearning_rate: 0.00008\nelapsed time: 9632.8 seconds (2.68 hours)\n\nTimestep: 2330000\nmean reward (100 episodes): 273.2400\nbest mean reward: 390.3600\ncurrent episode reward: 0.0000\nepisodes: 1623\nexploration: 0.07007\nlearning_rate: 0.00008\nelapsed time: 9677.1 seconds (2.69 hours)\n\nTimestep: 2340000\nmean reward (100 episodes): 262.2400\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 1632\nexploration: 0.06985\nlearning_rate: 0.00008\nelapsed time: 9721.8 seconds (2.70 hours)\n\nTimestep: 2350000\nmean reward (100 episodes): 260.9200\nbest mean reward: 390.3600\ncurrent episode reward: 88.0000\nepisodes: 1640\nexploration: 0.06962\nlearning_rate: 0.00008\nelapsed time: 9766.5 seconds (2.71 hours)\n\nTimestep: 2360000\nmean reward (100 episodes): 264.4400\nbest mean reward: 390.3600\ncurrent episode reward: 132.0000\nepisodes: 1646\nexploration: 0.06940\nlearning_rate: 0.00008\nelapsed time: 9810.1 seconds (2.73 hours)\n\nTimestep: 2370000\nmean reward (100 episodes): 275.8800\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 1654\nexploration: 0.06918\nlearning_rate: 0.00008\nelapsed time: 9854.6 seconds (2.74 hours)\n\nTimestep: 2380000\nmean reward (100 episodes): 276.7600\nbest mean reward: 390.3600\ncurrent episode reward: 484.0000\nepisodes: 1661\nexploration: 0.06895\nlearning_rate: 0.00008\nelapsed time: 9898.8 seconds (2.75 hours)\n\nTimestep: 2390000\nmean reward (100 episodes): 270.6000\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 1667\nexploration: 0.06873\nlearning_rate: 0.00008\nelapsed time: 9943.8 seconds (2.76 hours)\n\nTimestep: 2400000\nmean reward (100 episodes): 272.8000\nbest mean reward: 390.3600\ncurrent episode reward: 484.0000\nepisodes: 1674\nexploration: 0.06850\nlearning_rate: 0.00008\nelapsed time: 9987.8 seconds (2.77 hours)\n\nTimestep: 2410000\nmean reward (100 episodes): 274.1200\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 1681\nexploration: 0.06828\nlearning_rate: 0.00008\nelapsed time: 10032.5 seconds (2.79 hours)\n\nTimestep: 2420000\nmean reward (100 episodes): 270.6000\nbest mean reward: 390.3600\ncurrent episode reward: 88.0000\nepisodes: 1688\nexploration: 0.06805\nlearning_rate: 0.00008\nelapsed time: 10077.1 seconds (2.80 hours)\n\nTimestep: 2430000\nmean reward (100 episodes): 269.2800\nbest mean reward: 390.3600\ncurrent episode reward: 132.0000\nepisodes: 1695\nexploration: 0.06782\nlearning_rate: 0.00008\nelapsed time: 10122.1 seconds (2.81 hours)\n\nTimestep: 2440000\nmean reward (100 episodes): 263.5600\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 1702\nexploration: 0.06760\nlearning_rate: 0.00008\nelapsed time: 10166.5 seconds (2.82 hours)\n\nTimestep: 2450000\nmean reward (100 episodes): 265.7600\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 1710\nexploration: 0.06738\nlearning_rate: 0.00008\nelapsed time: 10211.4 seconds (2.84 hours)\n\nTimestep: 2460000\nmean reward (100 episodes): 275.0000\nbest mean reward: 390.3600\ncurrent episode reward: 528.0000\nepisodes: 1717\nexploration: 0.06715\nlearning_rate: 0.00008\nelapsed time: 10255.7 seconds (2.85 hours)\n\nTimestep: 2470000\nmean reward (100 episodes): 279.4000\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 1724\nexploration: 0.06693\nlearning_rate: 0.00008\nelapsed time: 10300.6 seconds (2.86 hours)\n\nTimestep: 2480000\nmean reward (100 episodes): 291.7200\nbest mean reward: 390.3600\ncurrent episode reward: 176.0000\nepisodes: 1731\nexploration: 0.06670\nlearning_rate: 0.00008\nelapsed time: 10345.0 seconds (2.87 hours)\n\nTimestep: 2490000\nmean reward (100 episodes): 301.8400\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 1738\nexploration: 0.06648\nlearning_rate: 0.00008\nelapsed time: 10389.5 seconds (2.89 hours)\n\nTimestep: 2500000\nmean reward (100 episodes): 310.6400\nbest mean reward: 390.3600\ncurrent episode reward: 660.0000\nepisodes: 1743\nexploration: 0.06625\nlearning_rate: 0.00008\nelapsed time: 10434.1 seconds (2.90 hours)\n\nTimestep: 2510000\nmean reward (100 episodes): 303.6000\nbest mean reward: 390.3600\ncurrent episode reward: 572.0000\nepisodes: 1750\nexploration: 0.06603\nlearning_rate: 0.00008\nelapsed time: 10478.2 seconds (2.91 hours)\n\nTimestep: 2520000\nmean reward (100 episodes): 300.0800\nbest mean reward: 390.3600\ncurrent episode reward: 220.0000\nepisodes: 1757\nexploration: 0.06580\nlearning_rate: 0.00008\nelapsed time: 10522.5 seconds (2.92 hours)\n\nTimestep: 2530000\nmean reward (100 episodes): 309.7600\nbest mean reward: 390.3600\ncurrent episode reward: 616.0000\nepisodes: 1764\nexploration: 0.06557\nlearning_rate: 0.00008\nelapsed time: 10566.9 seconds (2.94 hours)\n\nTimestep: 2540000\nmean reward (100 episodes): 314.1600\nbest mean reward: 390.3600\ncurrent episode reward: 396.0000\nepisodes: 1770\nexploration: 0.06535\nlearning_rate: 0.00008\nelapsed time: 10611.2 seconds (2.95 hours)\n\nTimestep: 2550000\nmean reward (100 episodes): 323.4000\nbest mean reward: 390.3600\ncurrent episode reward: 528.0000\nepisodes: 1777\nexploration: 0.06513\nlearning_rate: 0.00008\nelapsed time: 10655.8 seconds (2.96 hours)\n\nTimestep: 2560000\nmean reward (100 episodes): 334.1200\nbest mean reward: 390.3600\ncurrent episode reward: 352.0000\nepisodes: 1782\nexploration: 0.06490\nlearning_rate: 0.00008\nelapsed time: 10700.2 seconds (2.97 hours)\n\nTimestep: 2570000\nmean reward (100 episodes): 341.6000\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 1790\nexploration: 0.06468\nlearning_rate: 0.00008\nelapsed time: 10744.8 seconds (2.98 hours)\n\nTimestep: 2580000\nmean reward (100 episodes): 349.5200\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 1796\nexploration: 0.06445\nlearning_rate: 0.00008\nelapsed time: 10789.2 seconds (3.00 hours)\n\nTimestep: 2590000\nmean reward (100 episodes): 348.6400\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 1802\nexploration: 0.06423\nlearning_rate: 0.00008\nelapsed time: 10834.7 seconds (3.01 hours)\n\nTimestep: 2600000\nmean reward (100 episodes): 352.6000\nbest mean reward: 390.3600\ncurrent episode reward: 396.0000\nepisodes: 1808\nexploration: 0.06400\nlearning_rate: 0.00008\nelapsed time: 10879.5 seconds (3.02 hours)\n\nTimestep: 2610000\nmean reward (100 episodes): 360.0800\nbest mean reward: 390.3600\ncurrent episode reward: 308.0000\nepisodes: 1815\nexploration: 0.06377\nlearning_rate: 0.00008\nelapsed time: 10924.7 seconds (3.03 hours)\n\nTimestep: 2620000\nmean reward (100 episodes): 355.6800\nbest mean reward: 390.3600\ncurrent episode reward: 264.0000\nepisodes: 1821\nexploration: 0.06355\nlearning_rate: 0.00008\nelapsed time: 10969.1 seconds (3.05 hours)\n\nTimestep: 2630000\nmean reward (100 episodes): 369.3200\nbest mean reward: 390.3600\ncurrent episode reward: 616.0000\nepisodes: 1828\nexploration: 0.06333\nlearning_rate: 0.00008\nelapsed time: 11014.1 seconds (3.06 hours)\n\nTimestep: 2640000\nmean reward (100 episodes): 371.5600\nbest mean reward: 390.3600\ncurrent episode reward: 440.0000\nepisodes: 1834\nexploration: 0.06310\nlearning_rate: 0.00008\nelapsed time: 11058.6 seconds (3.07 hours)\n\nTimestep: 2650000\nmean reward (100 episodes): 387.6800\nbest mean reward: 390.3600\ncurrent episode reward: 572.0000\nepisodes: 1839\nexploration: 0.06288\nlearning_rate: 0.00008\nelapsed time: 11103.3 seconds (3.08 hours)\n\nTimestep: 2660000\nmean reward (100 episodes): 388.6000\nbest mean reward: 390.3600\ncurrent episode reward: 132.0000\nepisodes: 1845\nexploration: 0.06265\nlearning_rate: 0.00008\nelapsed time: 11147.8 seconds (3.10 hours)\n\nTimestep: 2670000\nmean reward (100 episodes): 393.9200\nbest mean reward: 398.3200\ncurrent episode reward: 616.0000\nepisodes: 1850\nexploration: 0.06243\nlearning_rate: 0.00008\nelapsed time: 11192.2 seconds (3.11 hours)\n\nTimestep: 2680000\nmean reward (100 episodes): 402.7200\nbest mean reward: 404.4800\ncurrent episode reward: 308.0000\nepisodes: 1857\nexploration: 0.06220\nlearning_rate: 0.00008\nelapsed time: 11236.9 seconds (3.12 hours)\n\nTimestep: 2690000\nmean reward (100 episodes): 396.1200\nbest mean reward: 404.4800\ncurrent episode reward: 132.0000\nepisodes: 1864\nexploration: 0.06198\nlearning_rate: 0.00008\nelapsed time: 11282.0 seconds (3.13 hours)\n\nTimestep: 2700000\nmean reward (100 episodes): 401.0800\nbest mean reward: 404.4800\ncurrent episode reward: 308.0000\nepisodes: 1870\nexploration: 0.06175\nlearning_rate: 0.00008\nelapsed time: 11325.6 seconds (3.15 hours)\n\nTimestep: 2710000\nmean reward (100 episodes): 396.2400\nbest mean reward: 404.4800\ncurrent episode reward: 352.0000\nepisodes: 1877\nexploration: 0.06153\nlearning_rate: 0.00008\nelapsed time: 11370.8 seconds (3.16 hours)\n\nTimestep: 2720000\nmean reward (100 episodes): 398.2800\nbest mean reward: 404.4800\ncurrent episode reward: 660.0000\nepisodes: 1882\nexploration: 0.06130\nlearning_rate: 0.00008\nelapsed time: 11416.2 seconds (3.17 hours)\n\nTimestep: 2730000\nmean reward (100 episodes): 397.4000\nbest mean reward: 404.4800\ncurrent episode reward: 396.0000\nepisodes: 1888\nexploration: 0.06108\nlearning_rate: 0.00008\nelapsed time: 11461.3 seconds (3.18 hours)\n\nTimestep: 2740000\nmean reward (100 episodes): 399.1600\nbest mean reward: 404.4800\ncurrent episode reward: 572.0000\nepisodes: 1894\nexploration: 0.06085\nlearning_rate: 0.00008\nelapsed time: 11506.0 seconds (3.20 hours)\n\nTimestep: 2750000\nmean reward (100 episodes): 403.1200\nbest mean reward: 405.7600\ncurrent episode reward: 484.0000\nepisodes: 1901\nexploration: 0.06062\nlearning_rate: 0.00008\nelapsed time: 11551.1 seconds (3.21 hours)\n\nTimestep: 2760000\nmean reward (100 episodes): 413.4400\nbest mean reward: 414.3200\ncurrent episode reward: 308.0000\nepisodes: 1907\nexploration: 0.06040\nlearning_rate: 0.00008\nelapsed time: 11595.8 seconds (3.22 hours)\n\nTimestep: 2770000\nmean reward (100 episodes): 414.3200\nbest mean reward: 416.9600\ncurrent episode reward: 220.0000\nepisodes: 1913\nexploration: 0.06017\nlearning_rate: 0.00008\nelapsed time: 11640.3 seconds (3.23 hours)\n\nTimestep: 2780000\nmean reward (100 episodes): 420.9200\nbest mean reward: 421.8000\ncurrent episode reward: 264.0000\nepisodes: 1920\nexploration: 0.05995\nlearning_rate: 0.00008\nelapsed time: 11685.0 seconds (3.25 hours)\n\nTimestep: 2790000\nmean reward (100 episodes): 427.0800\nbest mean reward: 429.7200\ncurrent episode reward: 396.0000\nepisodes: 1926\nexploration: 0.05973\nlearning_rate: 0.00008\nelapsed time: 11729.2 seconds (3.26 hours)\n\nTimestep: 2800000\nmean reward (100 episodes): 423.5200\nbest mean reward: 429.7200\ncurrent episode reward: 484.0000\nepisodes: 1932\nexploration: 0.05950\nlearning_rate: 0.00008\nelapsed time: 11773.8 seconds (3.27 hours)\n\nTimestep: 2810000\nmean reward (100 episodes): 422.2400\nbest mean reward: 429.7200\ncurrent episode reward: 572.0000\nepisodes: 1937\nexploration: 0.05928\nlearning_rate: 0.00008\nelapsed time: 11818.1 seconds (3.28 hours)\n\nTimestep: 2820000\nmean reward (100 episodes): 417.5600\nbest mean reward: 429.7200\ncurrent episode reward: 396.0000\nepisodes: 1943\nexploration: 0.05905\nlearning_rate: 0.00008\nelapsed time: 11862.9 seconds (3.30 hours)\n\nTimestep: 2830000\nmean reward (100 episodes): 418.8400\nbest mean reward: 429.7200\ncurrent episode reward: 660.0000\nepisodes: 1948\nexploration: 0.05883\nlearning_rate: 0.00008\nelapsed time: 11908.3 seconds (3.31 hours)\n\nTimestep: 2840000\nmean reward (100 episodes): 421.4800\nbest mean reward: 429.7200\ncurrent episode reward: 660.0000\nepisodes: 1953\nexploration: 0.05860\nlearning_rate: 0.00008\nelapsed time: 11953.5 seconds (3.32 hours)\n\nTimestep: 2850000\nmean reward (100 episodes): 423.7600\nbest mean reward: 429.7200\ncurrent episode reward: 88.0000\nepisodes: 1960\nexploration: 0.05837\nlearning_rate: 0.00008\nelapsed time: 11998.7 seconds (3.33 hours)\n\nTimestep: 2860000\nmean reward (100 episodes): 407.8000\nbest mean reward: 429.7200\ncurrent episode reward: 132.0000\nepisodes: 1967\nexploration: 0.05815\nlearning_rate: 0.00008\nelapsed time: 12043.6 seconds (3.35 hours)\n\nTimestep: 2870000\nmean reward (100 episodes): 394.6000\nbest mean reward: 429.7200\ncurrent episode reward: 88.0000\nepisodes: 1975\nexploration: 0.05792\nlearning_rate: 0.00008\nelapsed time: 12089.3 seconds (3.36 hours)\n\nTimestep: 2880000\nmean reward (100 episodes): 386.2400\nbest mean reward: 429.7200\ncurrent episode reward: 264.0000\nepisodes: 1981\nexploration: 0.05770\nlearning_rate: 0.00008\nelapsed time: 12134.2 seconds (3.37 hours)\n\nTimestep: 2890000\nmean reward (100 episodes): 377.4400\nbest mean reward: 429.7200\ncurrent episode reward: 308.0000\nepisodes: 1988\nexploration: 0.05748\nlearning_rate: 0.00008\nelapsed time: 12178.8 seconds (3.38 hours)\n\nTimestep: 2900000\nmean reward (100 episodes): 376.5600\nbest mean reward: 429.7200\ncurrent episode reward: 264.0000\nepisodes: 1994\nexploration: 0.05725\nlearning_rate: 0.00008\nelapsed time: 12223.7 seconds (3.40 hours)\n\nTimestep: 2910000\nmean reward (100 episodes): 388.4400\nbest mean reward: 429.7200\ncurrent episode reward: 308.0000\nepisodes: 2000\nexploration: 0.05702\nlearning_rate: 0.00008\nelapsed time: 12268.9 seconds (3.41 hours)\n\nTimestep: 2920000\nmean reward (100 episodes): 381.2000\nbest mean reward: 429.7200\ncurrent episode reward: 352.0000\nepisodes: 2007\nexploration: 0.05680\nlearning_rate: 0.00008\nelapsed time: 12314.0 seconds (3.42 hours)\n\nTimestep: 2930000\nmean reward (100 episodes): 378.1200\nbest mean reward: 429.7200\ncurrent episode reward: 660.0000\nepisodes: 2013\nexploration: 0.05658\nlearning_rate: 0.00008\nelapsed time: 12359.3 seconds (3.43 hours)\n\nTimestep: 2940000\nmean reward (100 episodes): 370.2000\nbest mean reward: 429.7200\ncurrent episode reward: 352.0000\nepisodes: 2020\nexploration: 0.05635\nlearning_rate: 0.00008\nelapsed time: 12404.3 seconds (3.45 hours)\n\nTimestep: 2950000\nmean reward (100 episodes): 369.3200\nbest mean reward: 429.7200\ncurrent episode reward: 352.0000\nepisodes: 2026\nexploration: 0.05613\nlearning_rate: 0.00008\nelapsed time: 12449.0 seconds (3.46 hours)\n\nTimestep: 2960000\nmean reward (100 episodes): 377.6800\nbest mean reward: 429.7200\ncurrent episode reward: 308.0000\nepisodes: 2032\nexploration: 0.05590\nlearning_rate: 0.00008\nelapsed time: 12494.2 seconds (3.47 hours)\n\nTimestep: 2970000\nmean reward (100 episodes): 372.8000\nbest mean reward: 429.7200\ncurrent episode reward: 528.0000\nepisodes: 2037\nexploration: 0.05568\nlearning_rate: 0.00008\nelapsed time: 12539.0 seconds (3.48 hours)\n\nTimestep: 2980000\nmean reward (100 episodes): 365.7600\nbest mean reward: 429.7200\ncurrent episode reward: 440.0000\nepisodes: 2044\nexploration: 0.05545\nlearning_rate: 0.00008\nelapsed time: 12583.3 seconds (3.50 hours)\n\nTimestep: 2990000\nmean reward (100 episodes): 364.9200\nbest mean reward: 429.7200\ncurrent episode reward: 572.0000\nepisodes: 2049\nexploration: 0.05523\nlearning_rate: 0.00008\nelapsed time: 12627.6 seconds (3.51 hours)\n\nTimestep: 3000000\nmean reward (100 episodes): 357.3600\nbest mean reward: 429.7200\ncurrent episode reward: 264.0000\nepisodes: 2054\nexploration: 0.05500\nlearning_rate: 0.00008\nelapsed time: 12672.7 seconds (3.52 hours)\n\nTimestep: 3010000\nmean reward (100 episodes): 375.4000\nbest mean reward: 429.7200\ncurrent episode reward: 440.0000\nepisodes: 2061\nexploration: 0.05478\nlearning_rate: 0.00007\nelapsed time: 12717.5 seconds (3.53 hours)\n\nTimestep: 3020000\nmean reward (100 episodes): 385.9600\nbest mean reward: 429.7200\ncurrent episode reward: 264.0000\nepisodes: 2068\nexploration: 0.05455\nlearning_rate: 0.00007\nelapsed time: 12762.7 seconds (3.55 hours)\n\nTimestep: 3030000\nmean reward (100 episodes): 400.0400\nbest mean reward: 429.7200\ncurrent episode reward: 528.0000\nepisodes: 2074\nexploration: 0.05433\nlearning_rate: 0.00007\nelapsed time: 12807.5 seconds (3.56 hours)\n\nTimestep: 3040000\nmean reward (100 episodes): 407.5600\nbest mean reward: 429.7200\ncurrent episode reward: 352.0000\nepisodes: 2080\nexploration: 0.05410\nlearning_rate: 0.00007\nelapsed time: 12852.0 seconds (3.57 hours)\n\nTimestep: 3050000\nmean reward (100 episodes): 422.0800\nbest mean reward: 429.7200\ncurrent episode reward: 660.0000\nepisodes: 2085\nexploration: 0.05388\nlearning_rate: 0.00007\nelapsed time: 12897.5 seconds (3.58 hours)\n\nTimestep: 3060000\nmean reward (100 episodes): 430.8800\nbest mean reward: 432.2000\ncurrent episode reward: 264.0000\nepisodes: 2091\nexploration: 0.05365\nlearning_rate: 0.00007\nelapsed time: 12942.5 seconds (3.60 hours)\n\nTimestep: 3070000\nmean reward (100 episodes): 433.5200\nbest mean reward: 436.6000\ncurrent episode reward: 484.0000\nepisodes: 2096\nexploration: 0.05343\nlearning_rate: 0.00007\nelapsed time: 12987.8 seconds (3.61 hours)\n\nTimestep: 3080000\nmean reward (100 episodes): 423.8400\nbest mean reward: 436.6000\ncurrent episode reward: 396.0000\nepisodes: 2103\nexploration: 0.05320\nlearning_rate: 0.00007\nelapsed time: 13032.1 seconds (3.62 hours)\n\nTimestep: 3090000\nmean reward (100 episodes): 437.0400\nbest mean reward: 437.0400\ncurrent episode reward: 660.0000\nepisodes: 2108\nexploration: 0.05298\nlearning_rate: 0.00007\nelapsed time: 13077.3 seconds (3.63 hours)\n\nTimestep: 3100000\nmean reward (100 episodes): 447.7200\nbest mean reward: 449.4800\ncurrent episode reward: 396.0000\nepisodes: 2114\nexploration: 0.05275\nlearning_rate: 0.00007\nelapsed time: 13122.5 seconds (3.65 hours)\n\nTimestep: 3110000\nmean reward (100 episodes): 458.7600\nbest mean reward: 458.7600\ncurrent episode reward: 352.0000\nepisodes: 2119\nexploration: 0.05253\nlearning_rate: 0.00007\nelapsed time: 13168.3 seconds (3.66 hours)\n\nTimestep: 3120000\nmean reward (100 episodes): 470.2000\nbest mean reward: 470.2000\ncurrent episode reward: 616.0000\nepisodes: 2124\nexploration: 0.05230\nlearning_rate: 0.00007\nelapsed time: 13213.1 seconds (3.67 hours)\n\nTimestep: 3130000\nmean reward (100 episodes): 462.8000\nbest mean reward: 470.2000\ncurrent episode reward: 756.0000\nepisodes: 2130\nexploration: 0.05208\nlearning_rate: 0.00007\nelapsed time: 13259.3 seconds (3.68 hours)\n\nTimestep: 3140000\nmean reward (100 episodes): 473.4800\nbest mean reward: 473.4800\ncurrent episode reward: 804.0000\nepisodes: 2135\nexploration: 0.05185\nlearning_rate: 0.00007\nelapsed time: 13303.9 seconds (3.70 hours)\n\nTimestep: 3150000\nmean reward (100 episodes): 484.3200\nbest mean reward: 484.3200\ncurrent episode reward: 616.0000\nepisodes: 2139\nexploration: 0.05163\nlearning_rate: 0.00007\nelapsed time: 13349.2 seconds (3.71 hours)\n\nTimestep: 3160000\nmean reward (100 episodes): 492.7600\nbest mean reward: 492.7600\ncurrent episode reward: 528.0000\nepisodes: 2145\nexploration: 0.05140\nlearning_rate: 0.00007\nelapsed time: 13394.2 seconds (3.72 hours)\n\nTimestep: 3170000\nmean reward (100 episodes): 495.3600\nbest mean reward: 495.8400\ncurrent episode reward: 708.0000\nepisodes: 2151\nexploration: 0.05117\nlearning_rate: 0.00007\nelapsed time: 13438.9 seconds (3.73 hours)\n\nTimestep: 3180000\nmean reward (100 episodes): 494.9200\nbest mean reward: 499.3200\ncurrent episode reward: 308.0000\nepisodes: 2158\nexploration: 0.05095\nlearning_rate: 0.00007\nelapsed time: 13483.0 seconds (3.75 hours)\n\nTimestep: 3190000\nmean reward (100 episodes): 498.8800\nbest mean reward: 501.0800\ncurrent episode reward: 308.0000\nepisodes: 2164\nexploration: 0.05072\nlearning_rate: 0.00007\nelapsed time: 13527.5 seconds (3.76 hours)\n\nTimestep: 3200000\nmean reward (100 episodes): 498.0000\nbest mean reward: 501.0800\ncurrent episode reward: 484.0000\nepisodes: 2170\nexploration: 0.05050\nlearning_rate: 0.00007\nelapsed time: 13572.2 seconds (3.77 hours)\n\nTimestep: 3210000\nmean reward (100 episodes): 498.8800\nbest mean reward: 501.0800\ncurrent episode reward: 616.0000\nepisodes: 2175\nexploration: 0.05028\nlearning_rate: 0.00007\nelapsed time: 13617.1 seconds (3.78 hours)\n\nTimestep: 3220000\nmean reward (100 episodes): 506.8000\nbest mean reward: 508.5600\ncurrent episode reward: 440.0000\nepisodes: 2181\nexploration: 0.05005\nlearning_rate: 0.00007\nelapsed time: 13662.6 seconds (3.80 hours)\n\nTimestep: 3230000\nmean reward (100 episodes): 485.6800\nbest mean reward: 509.4400\ncurrent episode reward: 176.0000\nepisodes: 2188\nexploration: 0.04983\nlearning_rate: 0.00007\nelapsed time: 13707.2 seconds (3.81 hours)\n\nTimestep: 3240000\nmean reward (100 episodes): 479.0800\nbest mean reward: 509.4400\ncurrent episode reward: 352.0000\nepisodes: 2195\nexploration: 0.04960\nlearning_rate: 0.00007\nelapsed time: 13752.2 seconds (3.82 hours)\n\nTimestep: 3250000\nmean reward (100 episodes): 476.4400\nbest mean reward: 509.4400\ncurrent episode reward: 264.0000\nepisodes: 2202\nexploration: 0.04938\nlearning_rate: 0.00007\nelapsed time: 13798.1 seconds (3.83 hours)\n\nTimestep: 3260000\nmean reward (100 episodes): 471.6000\nbest mean reward: 509.4400\ncurrent episode reward: 528.0000\nepisodes: 2208\nexploration: 0.04915\nlearning_rate: 0.00007\nelapsed time: 13843.1 seconds (3.85 hours)\n\nTimestep: 3270000\nmean reward (100 episodes): 466.2000\nbest mean reward: 509.4400\ncurrent episode reward: 396.0000\nepisodes: 2214\nexploration: 0.04892\nlearning_rate: 0.00007\nelapsed time: 13888.6 seconds (3.86 hours)\n\nTimestep: 3280000\nmean reward (100 episodes): 449.0000\nbest mean reward: 509.4400\ncurrent episode reward: 264.0000\nepisodes: 2221\nexploration: 0.04870\nlearning_rate: 0.00007\nelapsed time: 13933.4 seconds (3.87 hours)\n\nTimestep: 3290000\nmean reward (100 episodes): 445.9200\nbest mean reward: 509.4400\ncurrent episode reward: 484.0000\nepisodes: 2227\nexploration: 0.04847\nlearning_rate: 0.00007\nelapsed time: 13978.6 seconds (3.88 hours)\n\nTimestep: 3300000\nmean reward (100 episodes): 442.7600\nbest mean reward: 509.4400\ncurrent episode reward: 220.0000\nepisodes: 2233\nexploration: 0.04825\nlearning_rate: 0.00007\nelapsed time: 14023.7 seconds (3.90 hours)\n\nTimestep: 3310000\nmean reward (100 episodes): 426.0800\nbest mean reward: 509.4400\ncurrent episode reward: 352.0000\nepisodes: 2239\nexploration: 0.04802\nlearning_rate: 0.00007\nelapsed time: 14068.3 seconds (3.91 hours)\n\nTimestep: 3320000\nmean reward (100 episodes): 421.1600\nbest mean reward: 509.4400\ncurrent episode reward: 264.0000\nepisodes: 2245\nexploration: 0.04780\nlearning_rate: 0.00007\nelapsed time: 14113.3 seconds (3.92 hours)\n\nTimestep: 3330000\nmean reward (100 episodes): 420.7600\nbest mean reward: 509.4400\ncurrent episode reward: 440.0000\nepisodes: 2250\nexploration: 0.04757\nlearning_rate: 0.00007\nelapsed time: 14158.2 seconds (3.93 hours)\n\nTimestep: 3340000\nmean reward (100 episodes): 425.1200\nbest mean reward: 509.4400\ncurrent episode reward: 572.0000\nepisodes: 2257\nexploration: 0.04735\nlearning_rate: 0.00007\nelapsed time: 14202.2 seconds (3.95 hours)\n\nTimestep: 3350000\nmean reward (100 episodes): 433.9600\nbest mean reward: 509.4400\ncurrent episode reward: 528.0000\nepisodes: 2262\nexploration: 0.04713\nlearning_rate: 0.00007\nelapsed time: 14246.8 seconds (3.96 hours)\n\nTimestep: 3360000\nmean reward (100 episodes): 439.2400\nbest mean reward: 509.4400\ncurrent episode reward: 660.0000\nepisodes: 2267\nexploration: 0.04690\nlearning_rate: 0.00007\nelapsed time: 14291.5 seconds (3.97 hours)\n\nTimestep: 3370000\nmean reward (100 episodes): 439.9600\nbest mean reward: 509.4400\ncurrent episode reward: 264.0000\nepisodes: 2272\nexploration: 0.04667\nlearning_rate: 0.00007\nelapsed time: 14336.6 seconds (3.98 hours)\n\nTimestep: 3380000\nmean reward (100 episodes): 440.4400\nbest mean reward: 509.4400\ncurrent episode reward: 396.0000\nepisodes: 2277\nexploration: 0.04645\nlearning_rate: 0.00007\nelapsed time: 14380.9 seconds (3.99 hours)\n\nTimestep: 3390000\nmean reward (100 episodes): 443.2400\nbest mean reward: 509.4400\ncurrent episode reward: 484.0000\nepisodes: 2282\nexploration: 0.04622\nlearning_rate: 0.00007\nelapsed time: 14425.9 seconds (4.01 hours)\n\nTimestep: 3400000\nmean reward (100 episodes): 458.8400\nbest mean reward: 509.4400\ncurrent episode reward: 176.0000\nepisodes: 2289\nexploration: 0.04600\nlearning_rate: 0.00007\nelapsed time: 14470.2 seconds (4.02 hours)\n\nTimestep: 3410000\nmean reward (100 episodes): 462.3600\nbest mean reward: 509.4400\ncurrent episode reward: 528.0000\nepisodes: 2295\nexploration: 0.04577\nlearning_rate: 0.00007\nelapsed time: 14514.9 seconds (4.03 hours)\n\nTimestep: 3420000\nmean reward (100 episodes): 473.3600\nbest mean reward: 509.4400\ncurrent episode reward: 308.0000\nepisodes: 2300\nexploration: 0.04555\nlearning_rate: 0.00007\nelapsed time: 14559.9 seconds (4.04 hours)\n\nTimestep: 3430000\nmean reward (100 episodes): 478.3200\nbest mean reward: 509.4400\ncurrent episode reward: 264.0000\nepisodes: 2306\nexploration: 0.04532\nlearning_rate: 0.00007\nelapsed time: 14604.8 seconds (4.06 hours)\n\nTimestep: 3440000\nmean reward (100 episodes): 484.0400\nbest mean reward: 509.4400\ncurrent episode reward: 264.0000\nepisodes: 2312\nexploration: 0.04510\nlearning_rate: 0.00007\nelapsed time: 14649.6 seconds (4.07 hours)\n\nTimestep: 3450000\nmean reward (100 episodes): 493.4000\nbest mean reward: 509.4400\ncurrent episode reward: 660.0000\nepisodes: 2319\nexploration: 0.04487\nlearning_rate: 0.00007\nelapsed time: 14694.5 seconds (4.08 hours)\n\nTimestep: 3460000\nmean reward (100 episodes): 507.4800\nbest mean reward: 509.4400\ncurrent episode reward: 660.0000\nepisodes: 2324\nexploration: 0.04465\nlearning_rate: 0.00007\nelapsed time: 14739.4 seconds (4.09 hours)\n\nTimestep: 3470000\nmean reward (100 episodes): 508.8800\nbest mean reward: 511.9600\ncurrent episode reward: 264.0000\nepisodes: 2330\nexploration: 0.04442\nlearning_rate: 0.00007\nelapsed time: 14785.0 seconds (4.11 hours)\n\nTimestep: 3480000\nmean reward (100 episodes): 506.8400\nbest mean reward: 511.9600\ncurrent episode reward: 852.0000\nepisodes: 2335\nexploration: 0.04420\nlearning_rate: 0.00007\nelapsed time: 14830.7 seconds (4.12 hours)\n\nTimestep: 3490000\nmean reward (100 episodes): 527.6000\nbest mean reward: 527.6000\ncurrent episode reward: 660.0000\nepisodes: 2340\nexploration: 0.04397\nlearning_rate: 0.00007\nelapsed time: 14875.4 seconds (4.13 hours)\n\nTimestep: 3500000\nmean reward (100 episodes): 537.6400\nbest mean reward: 537.6400\ncurrent episode reward: 396.0000\nepisodes: 2345\nexploration: 0.04375\nlearning_rate: 0.00007\nelapsed time: 14920.9 seconds (4.14 hours)\n\nTimestep: 3510000\nmean reward (100 episodes): 542.6000\nbest mean reward: 542.6000\ncurrent episode reward: 660.0000\nepisodes: 2350\nexploration: 0.04353\nlearning_rate: 0.00007\nelapsed time: 14967.0 seconds (4.16 hours)\n\nTimestep: 3520000\nmean reward (100 episodes): 547.5200\nbest mean reward: 547.5200\ncurrent episode reward: 756.0000\nepisodes: 2354\nexploration: 0.04330\nlearning_rate: 0.00007\nelapsed time: 15011.5 seconds (4.17 hours)\n\nTimestep: 3530000\nmean reward (100 episodes): 546.6000\nbest mean reward: 547.5200\ncurrent episode reward: 660.0000\nepisodes: 2360\nexploration: 0.04308\nlearning_rate: 0.00007\nelapsed time: 15057.3 seconds (4.18 hours)\n\nTimestep: 3540000\nmean reward (100 episodes): 558.5600\nbest mean reward: 558.5600\ncurrent episode reward: 616.0000\nepisodes: 2365\nexploration: 0.04285\nlearning_rate: 0.00007\nelapsed time: 15102.6 seconds (4.20 hours)\n\nTimestep: 3550000\nmean reward (100 episodes): 564.1200\nbest mean reward: 566.0400\ncurrent episode reward: 804.0000\nepisodes: 2371\nexploration: 0.04263\nlearning_rate: 0.00007\nelapsed time: 15148.3 seconds (4.21 hours)\n\nTimestep: 3560000\nmean reward (100 episodes): 566.7600\nbest mean reward: 567.2000\ncurrent episode reward: 756.0000\nepisodes: 2377\nexploration: 0.04240\nlearning_rate: 0.00007\nelapsed time: 15193.6 seconds (4.22 hours)\n\nTimestep: 3570000\nmean reward (100 episodes): 564.4400\nbest mean reward: 567.2000\ncurrent episode reward: 616.0000\nepisodes: 2382\nexploration: 0.04218\nlearning_rate: 0.00007\nelapsed time: 15238.5 seconds (4.23 hours)\n\nTimestep: 3580000\nmean reward (100 episodes): 568.3200\nbest mean reward: 568.3200\ncurrent episode reward: 756.0000\nepisodes: 2386\nexploration: 0.04195\nlearning_rate: 0.00007\nelapsed time: 15283.2 seconds (4.25 hours)\n\nTimestep: 3590000\nmean reward (100 episodes): 584.7600\nbest mean reward: 586.9600\ncurrent episode reward: 440.0000\nepisodes: 2391\nexploration: 0.04173\nlearning_rate: 0.00007\nelapsed time: 15328.2 seconds (4.26 hours)\n\nTimestep: 3600000\nmean reward (100 episodes): 583.0000\nbest mean reward: 588.7200\ncurrent episode reward: 528.0000\nepisodes: 2397\nexploration: 0.04150\nlearning_rate: 0.00007\nelapsed time: 15372.7 seconds (4.27 hours)\n\nTimestep: 3610000\nmean reward (100 episodes): 587.1600\nbest mean reward: 590.2400\ncurrent episode reward: 264.0000\nepisodes: 2403\nexploration: 0.04127\nlearning_rate: 0.00007\nelapsed time: 15417.3 seconds (4.28 hours)\n\nTimestep: 3620000\nmean reward (100 episodes): 587.6400\nbest mean reward: 590.2400\ncurrent episode reward: 660.0000\nepisodes: 2409\nexploration: 0.04105\nlearning_rate: 0.00007\nelapsed time: 15463.2 seconds (4.30 hours)\n\nTimestep: 3630000\nmean reward (100 episodes): 597.5200\nbest mean reward: 598.5200\ncurrent episode reward: 660.0000\nepisodes: 2416\nexploration: 0.04083\nlearning_rate: 0.00007\nelapsed time: 15508.3 seconds (4.31 hours)\n\nTimestep: 3640000\nmean reward (100 episodes): 600.4000\nbest mean reward: 600.8400\ncurrent episode reward: 616.0000\nepisodes: 2421\nexploration: 0.04060\nlearning_rate: 0.00007\nelapsed time: 15553.3 seconds (4.32 hours)\n\nTimestep: 3650000\nmean reward (100 episodes): 608.9600\nbest mean reward: 608.9600\ncurrent episode reward: 616.0000\nepisodes: 2427\nexploration: 0.04038\nlearning_rate: 0.00007\nelapsed time: 15598.1 seconds (4.33 hours)\n\nTimestep: 3660000\nmean reward (100 episodes): 614.6800\nbest mean reward: 614.6800\ncurrent episode reward: 572.0000\nepisodes: 2432\nexploration: 0.04015\nlearning_rate: 0.00007\nelapsed time: 15644.9 seconds (4.35 hours)\n\nTimestep: 3670000\nmean reward (100 episodes): 618.4800\nbest mean reward: 621.7200\ncurrent episode reward: 1284.0000\nepisodes: 2437\nexploration: 0.03993\nlearning_rate: 0.00007\nelapsed time: 15690.0 seconds (4.36 hours)\n\nTimestep: 3680000\nmean reward (100 episodes): 615.8400\nbest mean reward: 621.7200\ncurrent episode reward: 396.0000\nepisodes: 2442\nexploration: 0.03970\nlearning_rate: 0.00007\nelapsed time: 15734.8 seconds (4.37 hours)\n\nTimestep: 3690000\nmean reward (100 episodes): 618.3200\nbest mean reward: 621.7200\ncurrent episode reward: 528.0000\nepisodes: 2448\nexploration: 0.03947\nlearning_rate: 0.00007\nelapsed time: 15780.6 seconds (4.38 hours)\n\nTimestep: 3700000\nmean reward (100 episodes): 620.4000\nbest mean reward: 621.7200\ncurrent episode reward: 1140.0000\nepisodes: 2454\nexploration: 0.03925\nlearning_rate: 0.00007\nelapsed time: 15825.6 seconds (4.40 hours)\n\nTimestep: 3710000\nmean reward (100 episodes): 622.8400\nbest mean reward: 623.9200\ncurrent episode reward: 948.0000\nepisodes: 2461\nexploration: 0.03902\nlearning_rate: 0.00007\nelapsed time: 15871.0 seconds (4.41 hours)\n\nTimestep: 3720000\nmean reward (100 episodes): 619.0400\nbest mean reward: 625.6800\ncurrent episode reward: 528.0000\nepisodes: 2467\nexploration: 0.03880\nlearning_rate: 0.00007\nelapsed time: 15916.2 seconds (4.42 hours)\n\nTimestep: 3730000\nmean reward (100 episodes): 615.4400\nbest mean reward: 625.6800\ncurrent episode reward: 484.0000\nepisodes: 2474\nexploration: 0.03857\nlearning_rate: 0.00007\nelapsed time: 15962.2 seconds (4.43 hours)\n\nTimestep: 3740000\nmean reward (100 episodes): 622.8800\nbest mean reward: 625.6800\ncurrent episode reward: 708.0000\nepisodes: 2480\nexploration: 0.03835\nlearning_rate: 0.00007\nelapsed time: 16007.9 seconds (4.45 hours)\n\nTimestep: 3750000\nmean reward (100 episodes): 617.2800\nbest mean reward: 625.6800\ncurrent episode reward: 660.0000\nepisodes: 2487\nexploration: 0.03812\nlearning_rate: 0.00007\nelapsed time: 16052.5 seconds (4.46 hours)\n\nTimestep: 3760000\nmean reward (100 episodes): 623.9600\nbest mean reward: 625.6800\ncurrent episode reward: 528.0000\nepisodes: 2491\nexploration: 0.03790\nlearning_rate: 0.00007\nelapsed time: 16097.5 seconds (4.47 hours)\n\nTimestep: 3770000\nmean reward (100 episodes): 630.5200\nbest mean reward: 632.2000\ncurrent episode reward: 756.0000\nepisodes: 2498\nexploration: 0.03768\nlearning_rate: 0.00007\nelapsed time: 16142.1 seconds (4.48 hours)\n\nTimestep: 3780000\nmean reward (100 episodes): 632.3600\nbest mean reward: 634.7200\ncurrent episode reward: 616.0000\nepisodes: 2504\nexploration: 0.03745\nlearning_rate: 0.00007\nelapsed time: 16186.7 seconds (4.50 hours)\n\nTimestep: 3790000\nmean reward (100 episodes): 649.2400\nbest mean reward: 649.2400\ncurrent episode reward: 660.0000\nepisodes: 2509\nexploration: 0.03722\nlearning_rate: 0.00007\nelapsed time: 16232.2 seconds (4.51 hours)\n\nTimestep: 3800000\nmean reward (100 episodes): 653.7200\nbest mean reward: 653.7200\ncurrent episode reward: 572.0000\nepisodes: 2515\nexploration: 0.03700\nlearning_rate: 0.00007\nelapsed time: 16277.4 seconds (4.52 hours)\n\nTimestep: 3810000\nmean reward (100 episodes): 666.2400\nbest mean reward: 666.2400\ncurrent episode reward: 616.0000\nepisodes: 2521\nexploration: 0.03678\nlearning_rate: 0.00006\nelapsed time: 16323.0 seconds (4.53 hours)\n\nTimestep: 3820000\nmean reward (100 episodes): 660.0400\nbest mean reward: 666.2400\ncurrent episode reward: 708.0000\nepisodes: 2527\nexploration: 0.03655\nlearning_rate: 0.00006\nelapsed time: 16368.0 seconds (4.55 hours)\n\nTimestep: 3830000\nmean reward (100 episodes): 668.1200\nbest mean reward: 668.1200\ncurrent episode reward: 1092.0000\nepisodes: 2532\nexploration: 0.03632\nlearning_rate: 0.00006\nelapsed time: 16413.0 seconds (4.56 hours)\n\nTimestep: 3840000\nmean reward (100 episodes): 666.0800\nbest mean reward: 671.8400\ncurrent episode reward: 708.0000\nepisodes: 2537\nexploration: 0.03610\nlearning_rate: 0.00006\nelapsed time: 16458.6 seconds (4.57 hours)\n\nTimestep: 3850000\nmean reward (100 episodes): 673.8400\nbest mean reward: 673.8400\ncurrent episode reward: 756.0000\nepisodes: 2543\nexploration: 0.03587\nlearning_rate: 0.00006\nelapsed time: 16503.6 seconds (4.58 hours)\n\nTimestep: 3860000\nmean reward (100 episodes): 681.8800\nbest mean reward: 682.0000\ncurrent episode reward: 948.0000\nepisodes: 2548\nexploration: 0.03565\nlearning_rate: 0.00006\nelapsed time: 16548.8 seconds (4.60 hours)\n\nTimestep: 3870000\nmean reward (100 episodes): 689.0000\nbest mean reward: 690.9200\ncurrent episode reward: 948.0000\nepisodes: 2554\nexploration: 0.03542\nlearning_rate: 0.00006\nelapsed time: 16593.6 seconds (4.61 hours)\n\nTimestep: 3880000\nmean reward (100 episodes): 699.0000\nbest mean reward: 699.0000\ncurrent episode reward: 852.0000\nepisodes: 2560\nexploration: 0.03520\nlearning_rate: 0.00006\nelapsed time: 16638.1 seconds (4.62 hours)\n\nTimestep: 3890000\nmean reward (100 episodes): 699.3200\nbest mean reward: 699.3200\ncurrent episode reward: 1432.0000\nepisodes: 2566\nexploration: 0.03497\nlearning_rate: 0.00006\nelapsed time: 16683.2 seconds (4.63 hours)\n\nTimestep: 3900000\nmean reward (100 episodes): 703.6400\nbest mean reward: 706.3200\ncurrent episode reward: 660.0000\nepisodes: 2572\nexploration: 0.03475\nlearning_rate: 0.00006\nelapsed time: 16727.5 seconds (4.65 hours)\n\nTimestep: 3910000\nmean reward (100 episodes): 712.1600\nbest mean reward: 712.1600\ncurrent episode reward: 804.0000\nepisodes: 2578\nexploration: 0.03453\nlearning_rate: 0.00006\nelapsed time: 16772.6 seconds (4.66 hours)\n\nTimestep: 3920000\nmean reward (100 episodes): 714.6000\nbest mean reward: 715.5200\ncurrent episode reward: 708.0000\nepisodes: 2584\nexploration: 0.03430\nlearning_rate: 0.00006\nelapsed time: 16817.3 seconds (4.67 hours)\n\nTimestep: 3930000\nmean reward (100 episodes): 705.4000\nbest mean reward: 717.2400\ncurrent episode reward: 616.0000\nepisodes: 2590\nexploration: 0.03407\nlearning_rate: 0.00006\nelapsed time: 16862.2 seconds (4.68 hours)\n\nTimestep: 3940000\nmean reward (100 episodes): 717.1200\nbest mean reward: 717.7600\ncurrent episode reward: 660.0000\nepisodes: 2596\nexploration: 0.03385\nlearning_rate: 0.00006\nelapsed time: 16906.8 seconds (4.70 hours)\n\nTimestep: 3950000\nmean reward (100 episodes): 725.8000\nbest mean reward: 726.2400\ncurrent episode reward: 616.0000\nepisodes: 2602\nexploration: 0.03362\nlearning_rate: 0.00006\nelapsed time: 16951.5 seconds (4.71 hours)\n\nTimestep: 3960000\nmean reward (100 episodes): 720.1600\nbest mean reward: 726.2400\ncurrent episode reward: 660.0000\nepisodes: 2607\nexploration: 0.03340\nlearning_rate: 0.00006\nelapsed time: 16997.1 seconds (4.72 hours)\n\nTimestep: 3970000\nmean reward (100 episodes): 724.1200\nbest mean reward: 726.2400\ncurrent episode reward: 1044.0000\nepisodes: 2614\nexploration: 0.03317\nlearning_rate: 0.00006\nelapsed time: 17042.5 seconds (4.73 hours)\n\nTimestep: 3980000\nmean reward (100 episodes): 734.5600\nbest mean reward: 735.5200\ncurrent episode reward: 660.0000\nepisodes: 2619\nexploration: 0.03295\nlearning_rate: 0.00006\nelapsed time: 17087.7 seconds (4.75 hours)\n\nTimestep: 3990000\nmean reward (100 episodes): 733.1200\nbest mean reward: 735.5200\ncurrent episode reward: 660.0000\nepisodes: 2625\nexploration: 0.03272\nlearning_rate: 0.00006\nelapsed time: 17132.1 seconds (4.76 hours)\n\nTimestep: 4000000\nmean reward (100 episodes): 738.1600\nbest mean reward: 739.4800\ncurrent episode reward: 484.0000\nepisodes: 2630\nexploration: 0.03250\nlearning_rate: 0.00006\nelapsed time: 17177.4 seconds (4.77 hours)\n\nTimestep: 4010000\nmean reward (100 episodes): 734.8000\nbest mean reward: 739.4800\ncurrent episode reward: 852.0000\nepisodes: 2635\nexploration: 0.03227\nlearning_rate: 0.00006\nelapsed time: 17222.4 seconds (4.78 hours)\n\nTimestep: 4020000\nmean reward (100 episodes): 734.8000\nbest mean reward: 739.4800\ncurrent episode reward: 396.0000\nepisodes: 2642\nexploration: 0.03205\nlearning_rate: 0.00006\nelapsed time: 17267.8 seconds (4.80 hours)\n\nTimestep: 4030000\nmean reward (100 episodes): 727.2800\nbest mean reward: 739.4800\ncurrent episode reward: 660.0000\nepisodes: 2647\nexploration: 0.03183\nlearning_rate: 0.00006\nelapsed time: 17312.5 seconds (4.81 hours)\n\nTimestep: 4040000\nmean reward (100 episodes): 737.6400\nbest mean reward: 739.4800\ncurrent episode reward: 1140.0000\nepisodes: 2653\nexploration: 0.03160\nlearning_rate: 0.00006\nelapsed time: 17357.6 seconds (4.82 hours)\n\nTimestep: 4050000\nmean reward (100 episodes): 736.8400\nbest mean reward: 739.4800\ncurrent episode reward: 948.0000\nepisodes: 2658\nexploration: 0.03138\nlearning_rate: 0.00006\nelapsed time: 17402.7 seconds (4.83 hours)\n\nTimestep: 4060000\nmean reward (100 episodes): 750.2400\nbest mean reward: 750.2400\ncurrent episode reward: 900.0000\nepisodes: 2663\nexploration: 0.03115\nlearning_rate: 0.00006\nelapsed time: 17447.8 seconds (4.85 hours)\n\nTimestep: 4070000\nmean reward (100 episodes): 744.9200\nbest mean reward: 754.5600\ncurrent episode reward: 660.0000\nepisodes: 2669\nexploration: 0.03092\nlearning_rate: 0.00006\nelapsed time: 17493.8 seconds (4.86 hours)\n\nTimestep: 4080000\nmean reward (100 episodes): 751.3600\nbest mean reward: 754.5600\ncurrent episode reward: 804.0000\nepisodes: 2674\nexploration: 0.03070\nlearning_rate: 0.00006\nelapsed time: 17538.6 seconds (4.87 hours)\n\nTimestep: 4090000\nmean reward (100 episodes): 783.6000\nbest mean reward: 783.6000\ncurrent episode reward: 1284.0000\nepisodes: 2678\nexploration: 0.03048\nlearning_rate: 0.00006\nelapsed time: 17584.2 seconds (4.88 hours)\n\nTimestep: 4100000\nmean reward (100 episodes): 802.8000\nbest mean reward: 802.8000\ncurrent episode reward: 1692.0000\nepisodes: 2683\nexploration: 0.03025\nlearning_rate: 0.00006\nelapsed time: 17629.8 seconds (4.90 hours)\n\nTimestep: 4110000\nmean reward (100 episodes): 822.3200\nbest mean reward: 822.3200\ncurrent episode reward: 948.0000\nepisodes: 2688\nexploration: 0.03002\nlearning_rate: 0.00006\nelapsed time: 17674.7 seconds (4.91 hours)\n\nTimestep: 4120000\nmean reward (100 episodes): 839.4800\nbest mean reward: 839.4800\ncurrent episode reward: 2160.0000\nepisodes: 2692\nexploration: 0.02980\nlearning_rate: 0.00006\nelapsed time: 17719.4 seconds (4.92 hours)\n\nTimestep: 4130000\nmean reward (100 episodes): 857.0000\nbest mean reward: 857.0000\ncurrent episode reward: 660.0000\nepisodes: 2696\nexploration: 0.02958\nlearning_rate: 0.00006\nelapsed time: 17764.7 seconds (4.93 hours)\n\nTimestep: 4140000\nmean reward (100 episodes): 878.1200\nbest mean reward: 878.1200\ncurrent episode reward: 1140.0000\nepisodes: 2701\nexploration: 0.02935\nlearning_rate: 0.00006\nelapsed time: 17809.1 seconds (4.95 hours)\n\nTimestep: 4150000\nmean reward (100 episodes): 903.0800\nbest mean reward: 903.0800\ncurrent episode reward: 1380.0000\nepisodes: 2705\nexploration: 0.02912\nlearning_rate: 0.00006\nelapsed time: 17854.8 seconds (4.96 hours)\n\nTimestep: 4160000\nmean reward (100 episodes): 930.3200\nbest mean reward: 930.3200\ncurrent episode reward: 2004.0000\nepisodes: 2709\nexploration: 0.02890\nlearning_rate: 0.00006\nelapsed time: 17899.4 seconds (4.97 hours)\n\nTimestep: 4170000\nmean reward (100 episodes): 970.5200\nbest mean reward: 970.5200\ncurrent episode reward: 1284.0000\nepisodes: 2713\nexploration: 0.02867\nlearning_rate: 0.00006\nelapsed time: 17944.4 seconds (4.98 hours)\n\nTimestep: 4180000\nmean reward (100 episodes): 977.7200\nbest mean reward: 977.7200\ncurrent episode reward: 2004.0000\nepisodes: 2716\nexploration: 0.02845\nlearning_rate: 0.00006\nelapsed time: 17989.5 seconds (5.00 hours)\n\nTimestep: 4190000\nmean reward (100 episodes): 992.1200\nbest mean reward: 992.1200\ncurrent episode reward: 708.0000\nepisodes: 2721\nexploration: 0.02823\nlearning_rate: 0.00006\nelapsed time: 18034.6 seconds (5.01 hours)\n\nTimestep: 4200000\nmean reward (100 episodes): 1005.5600\nbest mean reward: 1005.5600\ncurrent episode reward: 1484.0000\nepisodes: 2725\nexploration: 0.02800\nlearning_rate: 0.00006\nelapsed time: 18079.8 seconds (5.02 hours)\n\nTimestep: 4210000\nmean reward (100 episodes): 1035.3600\nbest mean reward: 1035.3600\ncurrent episode reward: 1332.0000\nepisodes: 2729\nexploration: 0.02777\nlearning_rate: 0.00006\nelapsed time: 18125.5 seconds (5.03 hours)\n\nTimestep: 4220000\nmean reward (100 episodes): 1078.2000\nbest mean reward: 1079.1600\ncurrent episode reward: 708.0000\nepisodes: 2733\nexploration: 0.02755\nlearning_rate: 0.00006\nelapsed time: 18171.0 seconds (5.05 hours)\n\nTimestep: 4230000\nmean reward (100 episodes): 1106.4000\nbest mean reward: 1106.4000\ncurrent episode reward: 1236.0000\nepisodes: 2736\nexploration: 0.02733\nlearning_rate: 0.00006\nelapsed time: 18216.2 seconds (5.06 hours)\n\nTimestep: 4240000\nmean reward (100 episodes): 1136.8400\nbest mean reward: 1136.8400\ncurrent episode reward: 2004.0000\nepisodes: 2740\nexploration: 0.02710\nlearning_rate: 0.00006\nelapsed time: 18261.3 seconds (5.07 hours)\n\nTimestep: 4250000\nmean reward (100 episodes): 1154.2400\nbest mean reward: 1154.2400\ncurrent episode reward: 660.0000\nepisodes: 2744\nexploration: 0.02687\nlearning_rate: 0.00006\nelapsed time: 18306.2 seconds (5.09 hours)\n\nTimestep: 4260000\nmean reward (100 episodes): 1180.1200\nbest mean reward: 1185.4000\ncurrent episode reward: 660.0000\nepisodes: 2748\nexploration: 0.02665\nlearning_rate: 0.00006\nelapsed time: 18351.8 seconds (5.10 hours)\n\nTimestep: 4270000\nmean reward (100 episodes): 1195.8400\nbest mean reward: 1195.8400\ncurrent episode reward: 1380.0000\nepisodes: 2752\nexploration: 0.02642\nlearning_rate: 0.00006\nelapsed time: 18397.9 seconds (5.11 hours)\n\nTimestep: 4280000\nmean reward (100 episodes): 1219.4400\nbest mean reward: 1219.4400\ncurrent episode reward: 1432.0000\nepisodes: 2756\nexploration: 0.02620\nlearning_rate: 0.00006\nelapsed time: 18443.3 seconds (5.12 hours)\n\nTimestep: 4290000\nmean reward (100 episodes): 1232.2000\nbest mean reward: 1234.1200\ncurrent episode reward: 804.0000\nepisodes: 2760\nexploration: 0.02597\nlearning_rate: 0.00006\nelapsed time: 18488.2 seconds (5.14 hours)\n\nTimestep: 4300000\nmean reward (100 episodes): 1264.1200\nbest mean reward: 1264.1200\ncurrent episode reward: 1332.0000\nepisodes: 2763\nexploration: 0.02575\nlearning_rate: 0.00006\nelapsed time: 18533.7 seconds (5.15 hours)\n\nTimestep: 4310000\nmean reward (100 episodes): 1295.1200\nbest mean reward: 1295.1200\ncurrent episode reward: 2636.0000\nepisodes: 2766\nexploration: 0.02552\nlearning_rate: 0.00006\nelapsed time: 18578.8 seconds (5.16 hours)\n\nTimestep: 4320000\nmean reward (100 episodes): 1334.9200\nbest mean reward: 1334.9200\ncurrent episode reward: 1900.0000\nepisodes: 2770\nexploration: 0.02530\nlearning_rate: 0.00006\nelapsed time: 18623.8 seconds (5.17 hours)\n\nTimestep: 4330000\nmean reward (100 episodes): 1359.3600\nbest mean reward: 1359.3600\ncurrent episode reward: 2384.0000\nepisodes: 2772\nexploration: 0.02508\nlearning_rate: 0.00006\nelapsed time: 18669.2 seconds (5.19 hours)\n\nTimestep: 4340000\nmean reward (100 episodes): 1375.9600\nbest mean reward: 1375.9600\ncurrent episode reward: 2328.0000\nepisodes: 2776\nexploration: 0.02485\nlearning_rate: 0.00006\nelapsed time: 18714.9 seconds (5.20 hours)\n\nTimestep: 4350000\nmean reward (100 episodes): 1398.8800\nbest mean reward: 1398.8800\ncurrent episode reward: 2004.0000\nepisodes: 2778\nexploration: 0.02462\nlearning_rate: 0.00006\nelapsed time: 18759.3 seconds (5.21 hours)\n\nTimestep: 4360000\nmean reward (100 episodes): 1421.3600\nbest mean reward: 1421.3600\ncurrent episode reward: 1380.0000\nepisodes: 2782\nexploration: 0.02440\nlearning_rate: 0.00006\nelapsed time: 18805.2 seconds (5.22 hours)\n\nTimestep: 4370000\nmean reward (100 episodes): 1449.2000\nbest mean reward: 1449.2000\ncurrent episode reward: 1140.0000\nepisodes: 2785\nexploration: 0.02417\nlearning_rate: 0.00006\nelapsed time: 18849.4 seconds (5.24 hours)\n\nTimestep: 4380000\nmean reward (100 episodes): 1455.4400\nbest mean reward: 1455.4400\ncurrent episode reward: 948.0000\nepisodes: 2788\nexploration: 0.02395\nlearning_rate: 0.00006\nelapsed time: 18894.8 seconds (5.25 hours)\n\nTimestep: 4390000\nmean reward (100 episodes): 1473.5600\nbest mean reward: 1473.5600\ncurrent episode reward: 3000.0000\nepisodes: 2792\nexploration: 0.02372\nlearning_rate: 0.00006\nelapsed time: 18939.9 seconds (5.26 hours)\n\nTimestep: 4400000\nmean reward (100 episodes): 1505.1200\nbest mean reward: 1505.1200\ncurrent episode reward: 3084.0000\nepisodes: 2795\nexploration: 0.02350\nlearning_rate: 0.00006\nelapsed time: 18985.3 seconds (5.27 hours)\n\nTimestep: 4410000\nmean reward (100 episodes): 1537.1200\nbest mean reward: 1537.1200\ncurrent episode reward: 1380.0000\nepisodes: 2798\nexploration: 0.02327\nlearning_rate: 0.00006\nelapsed time: 19030.3 seconds (5.29 hours)\n\nTimestep: 4420000\nmean reward (100 episodes): 1556.0400\nbest mean reward: 1556.0400\ncurrent episode reward: 1332.0000\nepisodes: 2801\nexploration: 0.02305\nlearning_rate: 0.00006\nelapsed time: 19075.1 seconds (5.30 hours)\n\nTimestep: 4430000\nmean reward (100 episodes): 1586.0000\nbest mean reward: 1586.0000\ncurrent episode reward: 4156.0000\nepisodes: 2803\nexploration: 0.02282\nlearning_rate: 0.00006\nelapsed time: 19121.2 seconds (5.31 hours)\n\nTimestep: 4440000\nmean reward (100 episodes): 1612.6800\nbest mean reward: 1612.6800\ncurrent episode reward: 1432.0000\nepisodes: 2806\nexploration: 0.02260\nlearning_rate: 0.00006\nelapsed time: 19166.9 seconds (5.32 hours)\n\nTimestep: 4450000\nmean reward (100 episodes): 1638.8000\nbest mean reward: 1638.8000\ncurrent episode reward: 2832.0000\nepisodes: 2808\nexploration: 0.02237\nlearning_rate: 0.00006\nelapsed time: 19213.0 seconds (5.34 hours)\n\nTimestep: 4460000\nmean reward (100 episodes): 1655.9600\nbest mean reward: 1655.9600\ncurrent episode reward: 4028.0000\nepisodes: 2810\nexploration: 0.02215\nlearning_rate: 0.00006\nelapsed time: 19259.2 seconds (5.35 hours)\n\nTimestep: 4470000\nmean reward (100 episodes): 1662.3200\nbest mean reward: 1666.6400\ncurrent episode reward: 852.0000\nepisodes: 2813\nexploration: 0.02192\nlearning_rate: 0.00006\nelapsed time: 19304.7 seconds (5.36 hours)\n\nTimestep: 4480000\nmean reward (100 episodes): 1697.1200\nbest mean reward: 1697.1200\ncurrent episode reward: 3840.0000\nepisodes: 2816\nexploration: 0.02170\nlearning_rate: 0.00006\nelapsed time: 19349.8 seconds (5.37 hours)\n\nTimestep: 4490000\nmean reward (100 episodes): 1718.8400\nbest mean reward: 1718.8400\ncurrent episode reward: 1332.0000\nepisodes: 2819\nexploration: 0.02147\nlearning_rate: 0.00006\nelapsed time: 19395.3 seconds (5.39 hours)\n\nTimestep: 4500000\nmean reward (100 episodes): 1758.4000\nbest mean reward: 1758.4000\ncurrent episode reward: 3360.0000\nepisodes: 2821\nexploration: 0.02125\nlearning_rate: 0.00006\nelapsed time: 19440.0 seconds (5.40 hours)\n\nTimestep: 4510000\nmean reward (100 episodes): 1802.2000\nbest mean reward: 1802.2000\ncurrent episode reward: 1744.0000\nepisodes: 2824\nexploration: 0.02103\nlearning_rate: 0.00006\nelapsed time: 19485.5 seconds (5.41 hours)\n\nTimestep: 4520000\nmean reward (100 episodes): 1834.8000\nbest mean reward: 1834.8000\ncurrent episode reward: 4992.0000\nepisodes: 2826\nexploration: 0.02080\nlearning_rate: 0.00006\nelapsed time: 19530.5 seconds (5.43 hours)\n\nTimestep: 4530000\nmean reward (100 episodes): 1874.0800\nbest mean reward: 1874.0800\ncurrent episode reward: 2832.0000\nepisodes: 2829\nexploration: 0.02057\nlearning_rate: 0.00006\nelapsed time: 19575.6 seconds (5.44 hours)\n\nTimestep: 4540000\nmean reward (100 episodes): 1903.8400\nbest mean reward: 1903.8400\ncurrent episode reward: 3780.0000\nepisodes: 2830\nexploration: 0.02035\nlearning_rate: 0.00006\nelapsed time: 19620.9 seconds (5.45 hours)\n\nTimestep: 4550000\nmean reward (100 episodes): 1917.2000\nbest mean reward: 1922.6000\ncurrent episode reward: 1900.0000\nepisodes: 2832\nexploration: 0.02013\nlearning_rate: 0.00006\nelapsed time: 19666.7 seconds (5.46 hours)\n\nTimestep: 4560000\nmean reward (100 episodes): 1970.3200\nbest mean reward: 1970.3200\ncurrent episode reward: 3600.0000\nepisodes: 2834\nexploration: 0.01990\nlearning_rate: 0.00006\nelapsed time: 19712.7 seconds (5.48 hours)\n\nTimestep: 4570000\nmean reward (100 episodes): 2007.1600\nbest mean reward: 2007.1600\ncurrent episode reward: 1588.0000\nepisodes: 2837\nexploration: 0.01967\nlearning_rate: 0.00006\nelapsed time: 19758.2 seconds (5.49 hours)\n\nTimestep: 4580000\nmean reward (100 episodes): 2028.5200\nbest mean reward: 2028.5200\ncurrent episode reward: 2440.0000\nepisodes: 2840\nexploration: 0.01945\nlearning_rate: 0.00006\nelapsed time: 19803.5 seconds (5.50 hours)\n\nTimestep: 4590000\nmean reward (100 episodes): 2054.2400\nbest mean reward: 2054.2400\ncurrent episode reward: 3084.0000\nepisodes: 2842\nexploration: 0.01923\nlearning_rate: 0.00006\nelapsed time: 19848.6 seconds (5.51 hours)\n\nTimestep: 4600000\nmean reward (100 episodes): 2095.4600\nbest mean reward: 2095.4600\ncurrent episode reward: 4470.0000\nepisodes: 2844\nexploration: 0.01900\nlearning_rate: 0.00006\nelapsed time: 19893.3 seconds (5.53 hours)\n\nTimestep: 4610000\nmean reward (100 episodes): 2117.6800\nbest mean reward: 2117.6800\ncurrent episode reward: 3810.0000\nepisodes: 2846\nexploration: 0.01878\nlearning_rate: 0.00005\nelapsed time: 19938.6 seconds (5.54 hours)\n\nTimestep: 4620000\nmean reward (100 episodes): 2196.6000\nbest mean reward: 2196.6000\ncurrent episode reward: 3840.0000\nepisodes: 2848\nexploration: 0.01855\nlearning_rate: 0.00005\nelapsed time: 19983.9 seconds (5.55 hours)\n\nTimestep: 4630000\nmean reward (100 episodes): 2244.4800\nbest mean reward: 2244.4800\ncurrent episode reward: 3600.0000\nepisodes: 2850\nexploration: 0.01832\nlearning_rate: 0.00005\nelapsed time: 20029.8 seconds (5.56 hours)\n\nTimestep: 4640000\nmean reward (100 episodes): 2286.6800\nbest mean reward: 2286.6800\ncurrent episode reward: 3784.0000\nepisodes: 2852\nexploration: 0.01810\nlearning_rate: 0.00005\nelapsed time: 20075.2 seconds (5.58 hours)\n\nTimestep: 4650000\nmean reward (100 episodes): 2311.0400\nbest mean reward: 2311.0400\ncurrent episode reward: 3480.0000\nepisodes: 2853\nexploration: 0.01788\nlearning_rate: 0.00005\nelapsed time: 20120.7 seconds (5.59 hours)\n\nTimestep: 4660000\nmean reward (100 episodes): 2417.8200\nbest mean reward: 2417.8200\ncurrent episode reward: 5246.0000\nepisodes: 2855\nexploration: 0.01765\nlearning_rate: 0.00005\nelapsed time: 20166.4 seconds (5.60 hours)\n\nTimestep: 4670000\nmean reward (100 episodes): 2452.4200\nbest mean reward: 2452.4200\ncurrent episode reward: 4892.0000\nepisodes: 2856\nexploration: 0.01742\nlearning_rate: 0.00005\nelapsed time: 20211.6 seconds (5.61 hours)\n\nTimestep: 4680000\nmean reward (100 episodes): 2514.7400\nbest mean reward: 2514.7400\ncurrent episode reward: 5070.0000\nepisodes: 2858\nexploration: 0.01720\nlearning_rate: 0.00005\nelapsed time: 20257.7 seconds (5.63 hours)\n\nTimestep: 4690000\nmean reward (100 episodes): 2576.7000\nbest mean reward: 2576.7000\ncurrent episode reward: 4560.0000\nepisodes: 2860\nexploration: 0.01697\nlearning_rate: 0.00005\nelapsed time: 20303.6 seconds (5.64 hours)\n\nTimestep: 4700000\nmean reward (100 episodes): 2607.9800\nbest mean reward: 2607.9800\ncurrent episode reward: 4412.0000\nepisodes: 2862\nexploration: 0.01675\nlearning_rate: 0.00005\nelapsed time: 20349.2 seconds (5.65 hours)\n\nTimestep: 4710000\nmean reward (100 episodes): 2658.4000\nbest mean reward: 2658.4000\ncurrent episode reward: 3600.0000\nepisodes: 2864\nexploration: 0.01652\nlearning_rate: 0.00005\nelapsed time: 20394.0 seconds (5.67 hours)\n\nTimestep: 4720000\nmean reward (100 episodes): 2678.0800\nbest mean reward: 2678.0800\ncurrent episode reward: 2944.0000\nepisodes: 2866\nexploration: 0.01630\nlearning_rate: 0.00005\nelapsed time: 20439.2 seconds (5.68 hours)\n\nTimestep: 4730000\nmean reward (100 episodes): 2746.4800\nbest mean reward: 2746.4800\ncurrent episode reward: 2944.0000\nepisodes: 2868\nexploration: 0.01607\nlearning_rate: 0.00005\nelapsed time: 20484.4 seconds (5.69 hours)\n\nTimestep: 4740000\nmean reward (100 episodes): 2778.4800\nbest mean reward: 2778.4800\ncurrent episode reward: 4892.0000\nepisodes: 2869\nexploration: 0.01585\nlearning_rate: 0.00005\nelapsed time: 20528.5 seconds (5.70 hours)\n\nTimestep: 4750000\nmean reward (100 episodes): 2809.4000\nbest mean reward: 2809.4000\ncurrent episode reward: 1640.0000\nepisodes: 2871\nexploration: 0.01562\nlearning_rate: 0.00005\nelapsed time: 20574.1 seconds (5.72 hours)\n\nTimestep: 4760000\nmean reward (100 episodes): 2849.4000\nbest mean reward: 2849.4000\ncurrent episode reward: 3840.0000\nepisodes: 2873\nexploration: 0.01540\nlearning_rate: 0.00005\nelapsed time: 20619.4 seconds (5.73 hours)\n\nTimestep: 4770000\nmean reward (100 episodes): 2931.9800\nbest mean reward: 2931.9800\ncurrent episode reward: 5340.0000\nepisodes: 2875\nexploration: 0.01517\nlearning_rate: 0.00005\nelapsed time: 20665.3 seconds (5.74 hours)\n\nTimestep: 4780000\nmean reward (100 episodes): 2948.2200\nbest mean reward: 2948.2200\ncurrent episode reward: 5212.0000\nepisodes: 2877\nexploration: 0.01495\nlearning_rate: 0.00005\nelapsed time: 20710.4 seconds (5.75 hours)\n\nTimestep: 4790000\nmean reward (100 episodes): 2975.5200\nbest mean reward: 2975.5200\ncurrent episode reward: 4734.0000\nepisodes: 2878\nexploration: 0.01472\nlearning_rate: 0.00005\nelapsed time: 20755.9 seconds (5.77 hours)\n\nTimestep: 4800000\nmean reward (100 episodes): 3012.0400\nbest mean reward: 3012.0400\ncurrent episode reward: 2160.0000\nepisodes: 2881\nexploration: 0.01450\nlearning_rate: 0.00005\nelapsed time: 20800.6 seconds (5.78 hours)\n\nTimestep: 4810000\nmean reward (100 episodes): 3066.2000\nbest mean reward: 3066.2000\ncurrent episode reward: 3252.0000\nepisodes: 2883\nexploration: 0.01427\nlearning_rate: 0.00005\nelapsed time: 20845.8 seconds (5.79 hours)\n\nTimestep: 4820000\nmean reward (100 episodes): 3058.0800\nbest mean reward: 3066.2000\ncurrent episode reward: 1744.0000\nepisodes: 2885\nexploration: 0.01405\nlearning_rate: 0.00005\nelapsed time: 20891.1 seconds (5.80 hours)\n\nTimestep: 4830000\nmean reward (100 episodes): 3133.3200\nbest mean reward: 3133.3200\ncurrent episode reward: 1848.0000\nepisodes: 2888\nexploration: 0.01382\nlearning_rate: 0.00005\nelapsed time: 20936.8 seconds (5.82 hours)\n\nTimestep: 4840000\nmean reward (100 episodes): 3157.4400\nbest mean reward: 3157.4400\ncurrent episode reward: 1952.0000\nepisodes: 2890\nexploration: 0.01360\nlearning_rate: 0.00005\nelapsed time: 20982.4 seconds (5.83 hours)\n\nTimestep: 4850000\nmean reward (100 episodes): 3225.5200\nbest mean reward: 3225.5200\ncurrent episode reward: 4606.0000\nepisodes: 2892\nexploration: 0.01337\nlearning_rate: 0.00005\nelapsed time: 21027.6 seconds (5.84 hours)\n\nTimestep: 4860000\nmean reward (100 episodes): 3224.9600\nbest mean reward: 3225.5200\ncurrent episode reward: 3028.0000\nepisodes: 2895\nexploration: 0.01315\nlearning_rate: 0.00005\nelapsed time: 21073.0 seconds (5.85 hours)\n\nTimestep: 4870000\nmean reward (100 episodes): 3241.0400\nbest mean reward: 3241.0400\ncurrent episode reward: 4384.0000\nepisodes: 2896\nexploration: 0.01292\nlearning_rate: 0.00005\nelapsed time: 21118.1 seconds (5.87 hours)\n\nTimestep: 4880000\nmean reward (100 episodes): 3312.0800\nbest mean reward: 3312.0800\ncurrent episode reward: 4412.0000\nepisodes: 2898\nexploration: 0.01270\nlearning_rate: 0.00005\nelapsed time: 21162.3 seconds (5.88 hours)\n\nTimestep: 4890000\nmean reward (100 episodes): 3350.5800\nbest mean reward: 3350.5800\ncurrent episode reward: 4734.0000\nepisodes: 2900\nexploration: 0.01247\nlearning_rate: 0.00005\nelapsed time: 21207.1 seconds (5.89 hours)\n\nTimestep: 4900000\nmean reward (100 episodes): 3399.1200\nbest mean reward: 3399.1200\ncurrent episode reward: 4290.0000\nepisodes: 2902\nexploration: 0.01225\nlearning_rate: 0.00005\nelapsed time: 21251.9 seconds (5.90 hours)\n\nTimestep: 4910000\nmean reward (100 episodes): 3398.9600\nbest mean reward: 3399.1200\ncurrent episode reward: 2160.0000\nepisodes: 2904\nexploration: 0.01202\nlearning_rate: 0.00005\nelapsed time: 21297.2 seconds (5.92 hours)\n\nTimestep: 4920000\nmean reward (100 episodes): 3439.4400\nbest mean reward: 3439.4400\ncurrent episode reward: 4892.0000\nepisodes: 2906\nexploration: 0.01180\nlearning_rate: 0.00005\nelapsed time: 21342.7 seconds (5.93 hours)\n\nTimestep: 4930000\nmean reward (100 episodes): 3480.9600\nbest mean reward: 3480.9600\ncurrent episode reward: 6312.0000\nepisodes: 2907\nexploration: 0.01157\nlearning_rate: 0.00005\nelapsed time: 21389.1 seconds (5.94 hours)\n\nTimestep: 4940000\nmean reward (100 episodes): 3497.1200\nbest mean reward: 3498.8400\ncurrent episode reward: 4512.0000\nepisodes: 2910\nexploration: 0.01135\nlearning_rate: 0.00005\nelapsed time: 21433.6 seconds (5.95 hours)\n\nTimestep: 4950000\nmean reward (100 episodes): 3534.1200\nbest mean reward: 3534.1200\ncurrent episode reward: 5340.0000\nepisodes: 2911\nexploration: 0.01112\nlearning_rate: 0.00005\nelapsed time: 21478.9 seconds (5.97 hours)\n\nTimestep: 4960000\nmean reward (100 episodes): 3618.9800\nbest mean reward: 3618.9800\ncurrent episode reward: 5632.0000\nepisodes: 2913\nexploration: 0.01090\nlearning_rate: 0.00005\nelapsed time: 21524.0 seconds (5.98 hours)\n\nTimestep: 4970000\nmean reward (100 episodes): 3647.5000\nbest mean reward: 3647.5000\ncurrent episode reward: 5340.0000\nepisodes: 2916\nexploration: 0.01067\nlearning_rate: 0.00005\nelapsed time: 21569.9 seconds (5.99 hours)\n\nTimestep: 4980000\nmean reward (100 episodes): 3696.7200\nbest mean reward: 3696.7200\ncurrent episode reward: 4500.0000\nepisodes: 2918\nexploration: 0.01045\nlearning_rate: 0.00005\nelapsed time: 21615.4 seconds (6.00 hours)\n\nTimestep: 4990000\nmean reward (100 episodes): 3732.0000\nbest mean reward: 3732.0000\ncurrent episode reward: 5276.0000\nepisodes: 2920\nexploration: 0.01022\nlearning_rate: 0.00005\nelapsed time: 21661.1 seconds (6.02 hours)\n\nTimestep: 5000000\nmean reward (100 episodes): 3772.5600\nbest mean reward: 3772.5600\ncurrent episode reward: 7416.0000\nepisodes: 2921\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21706.7 seconds (6.03 hours)\n\nTimestep: 5010000\nmean reward (100 episodes): 3806.2400\nbest mean reward: 3806.2400\ncurrent episode reward: 2160.0000\nepisodes: 2923\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21751.4 seconds (6.04 hours)\n\nTimestep: 5020000\nmean reward (100 episodes): 3856.3600\nbest mean reward: 3856.3600\ncurrent episode reward: 3964.0000\nepisodes: 2925\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21796.6 seconds (6.05 hours)\n\nTimestep: 5030000\nmean reward (100 episodes): 3855.5600\nbest mean reward: 3863.9200\ncurrent episode reward: 2108.0000\nepisodes: 2927\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21841.4 seconds (6.07 hours)\n\nTimestep: 5040000\nmean reward (100 episodes): 3889.9600\nbest mean reward: 3889.9600\ncurrent episode reward: 3840.0000\nepisodes: 2929\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21887.0 seconds (6.08 hours)\n\nTimestep: 5050000\nmean reward (100 episodes): 3940.1600\nbest mean reward: 3940.1600\ncurrent episode reward: 5504.0000\nepisodes: 2931\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21931.7 seconds (6.09 hours)\n\nTimestep: 5060000\nmean reward (100 episodes): 3954.2400\nbest mean reward: 3971.3600\ncurrent episode reward: 2608.0000\nepisodes: 2933\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21976.0 seconds (6.10 hours)\n\nTimestep: 5070000\nmean reward (100 episodes): 3953.6400\nbest mean reward: 3971.3600\ncurrent episode reward: 3000.0000\nepisodes: 2935\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22021.1 seconds (6.12 hours)\n\nTimestep: 5080000\nmean reward (100 episodes): 3986.4200\nbest mean reward: 3986.4200\ncurrent episode reward: 2160.0000\nepisodes: 2937\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22066.6 seconds (6.13 hours)\n\nTimestep: 5090000\nmean reward (100 episodes): 4015.2200\nbest mean reward: 4015.2200\ncurrent episode reward: 3300.0000\nepisodes: 2939\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22111.1 seconds (6.14 hours)\n\nTimestep: 5100000\nmean reward (100 episodes): 4089.2400\nbest mean reward: 4089.2400\ncurrent episode reward: 6262.0000\nepisodes: 2941\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22156.4 seconds (6.15 hours)\n\nTimestep: 5110000\nmean reward (100 episodes): 4116.3800\nbest mean reward: 4116.3800\ncurrent episode reward: 5798.0000\nepisodes: 2942\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22200.9 seconds (6.17 hours)\n\nTimestep: 5120000\nmean reward (100 episodes): 4133.2000\nbest mean reward: 4138.9000\ncurrent episode reward: 3900.0000\nepisodes: 2944\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22247.0 seconds (6.18 hours)\n\nTimestep: 5130000\nmean reward (100 episodes): 4195.0000\nbest mean reward: 4195.0000\ncurrent episode reward: 8132.0000\nepisodes: 2945\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22291.5 seconds (6.19 hours)\n\nTimestep: 5140000\nmean reward (100 episodes): 4174.1800\nbest mean reward: 4217.8600\ncurrent episode reward: 2384.0000\nepisodes: 2948\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22336.2 seconds (6.20 hours)\n\nTimestep: 5150000\nmean reward (100 episodes): 4185.5800\nbest mean reward: 4217.8600\ncurrent episode reward: 3420.0000\nepisodes: 2950\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22381.8 seconds (6.22 hours)\n\nTimestep: 5160000\nmean reward (100 episodes): 4195.7400\nbest mean reward: 4217.8600\ncurrent episode reward: 3420.0000\nepisodes: 2952\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22427.5 seconds (6.23 hours)\n\nTimestep: 5170000\nmean reward (100 episodes): 4146.1800\nbest mean reward: 4217.8600\ncurrent episode reward: 2608.0000\nepisodes: 2954\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22472.8 seconds (6.24 hours)\n\nTimestep: 5180000\nmean reward (100 episodes): 4136.4400\nbest mean reward: 4217.8600\ncurrent episode reward: 5504.0000\nepisodes: 2956\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22517.7 seconds (6.25 hours)\n\nTimestep: 5190000\nmean reward (100 episodes): 4164.8400\nbest mean reward: 4217.8600\ncurrent episode reward: 4860.0000\nepisodes: 2958\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22562.7 seconds (6.27 hours)\n\nTimestep: 5200000\nmean reward (100 episodes): 4169.2000\nbest mean reward: 4217.8600\ncurrent episode reward: 2944.0000\nepisodes: 2960\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22607.7 seconds (6.28 hours)\n\nTimestep: 5210000\nmean reward (100 episodes): 4196.3000\nbest mean reward: 4217.8600\ncurrent episode reward: 3660.0000\nepisodes: 2962\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22653.6 seconds (6.29 hours)\n\nTimestep: 5220000\nmean reward (100 episodes): 4204.6200\nbest mean reward: 4217.8600\ncurrent episode reward: 5246.0000\nepisodes: 2963\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22699.1 seconds (6.31 hours)\n\nTimestep: 5230000\nmean reward (100 episodes): 4248.1000\nbest mean reward: 4248.1000\ncurrent episode reward: 5964.0000\nepisodes: 2965\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22744.8 seconds (6.32 hours)\n\nTimestep: 5240000\nmean reward (100 episodes): 4236.7200\nbest mean reward: 4264.0600\ncurrent episode reward: 3990.0000\nepisodes: 2967\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22789.6 seconds (6.33 hours)\n\nTimestep: 5250000\nmean reward (100 episodes): 4232.4400\nbest mean reward: 4267.5600\ncurrent episode reward: 1380.0000\nepisodes: 2969\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22835.7 seconds (6.34 hours)\n\nTimestep: 5260000\nmean reward (100 episodes): 4218.0000\nbest mean reward: 4267.5600\ncurrent episode reward: 1744.0000\nepisodes: 2972\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22881.5 seconds (6.36 hours)\n\nTimestep: 5270000\nmean reward (100 episodes): 4229.8400\nbest mean reward: 4267.5600\ncurrent episode reward: 5024.0000\nepisodes: 2973\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22926.9 seconds (6.37 hours)\n\nTimestep: 5280000\nmean reward (100 episodes): 4208.2400\nbest mean reward: 4267.5600\ncurrent episode reward: 1952.0000\nepisodes: 2976\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22972.6 seconds (6.38 hours)\n\nTimestep: 5290000\nmean reward (100 episodes): 4203.9600\nbest mean reward: 4267.5600\ncurrent episode reward: 3720.0000\nepisodes: 2978\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23018.1 seconds (6.39 hours)\n\nTimestep: 5300000\nmean reward (100 episodes): 4226.0200\nbest mean reward: 4267.5600\ncurrent episode reward: 3196.0000\nepisodes: 2981\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23064.4 seconds (6.41 hours)\n\nTimestep: 5310000\nmean reward (100 episodes): 4227.7400\nbest mean reward: 4267.5600\ncurrent episode reward: 3000.0000\nepisodes: 2983\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23109.5 seconds (6.42 hours)\n\nTimestep: 5320000\nmean reward (100 episodes): 4263.1600\nbest mean reward: 4267.5600\ncurrent episode reward: 4050.0000\nepisodes: 2985\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23154.5 seconds (6.43 hours)\n\nTimestep: 5330000\nmean reward (100 episodes): 4254.3600\nbest mean reward: 4267.5600\ncurrent episode reward: 3964.0000\nepisodes: 2987\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23199.5 seconds (6.44 hours)\n\nTimestep: 5340000\nmean reward (100 episodes): 4258.8800\nbest mean reward: 4281.9200\ncurrent episode reward: 1536.0000\nepisodes: 2989\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23244.7 seconds (6.46 hours)\n\nTimestep: 5350000\nmean reward (100 episodes): 4289.6200\nbest mean reward: 4289.6200\ncurrent episode reward: 6508.0000\nepisodes: 2991\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23290.4 seconds (6.47 hours)\n\nTimestep: 5360000\nmean reward (100 episodes): 4283.3200\nbest mean reward: 4289.6200\ncurrent episode reward: 2748.0000\nepisodes: 2993\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23335.7 seconds (6.48 hours)\n\nTimestep: 5370000\nmean reward (100 episodes): 4340.4000\nbest mean reward: 4340.4000\ncurrent episode reward: 6096.0000\nepisodes: 2995\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23381.3 seconds (6.49 hours)\n\nTimestep: 5380000\nmean reward (100 episodes): 4333.9200\nbest mean reward: 4343.2400\ncurrent episode reward: 5412.0000\nepisodes: 2997\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23427.7 seconds (6.51 hours)\n\nTimestep: 5390000\nmean reward (100 episodes): 4318.1400\nbest mean reward: 4343.2400\ncurrent episode reward: 3900.0000\nepisodes: 3000\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23473.2 seconds (6.52 hours)\n\nTimestep: 5400000\nmean reward (100 episodes): 4358.3800\nbest mean reward: 4358.3800\ncurrent episode reward: 6146.0000\nepisodes: 3002\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23519.8 seconds (6.53 hours)\n\nTimestep: 5410000\nmean reward (100 episodes): 4390.9000\nbest mean reward: 4390.9000\ncurrent episode reward: 5952.0000\nepisodes: 3004\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23566.0 seconds (6.55 hours)\n\nTimestep: 5420000\nmean reward (100 episodes): 4417.8200\nbest mean reward: 4417.8200\ncurrent episode reward: 6804.0000\nepisodes: 3006\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23612.0 seconds (6.56 hours)\n\nTimestep: 5430000\nmean reward (100 episodes): 4384.3800\nbest mean reward: 4417.8200\ncurrent episode reward: 3240.0000\nepisodes: 3008\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23657.3 seconds (6.57 hours)\n\nTimestep: 5440000\nmean reward (100 episodes): 4426.3000\nbest mean reward: 4426.3000\ncurrent episode reward: 5602.0000\nepisodes: 3010\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23704.1 seconds (6.58 hours)\n\nTimestep: 5450000\nmean reward (100 episodes): 4417.3200\nbest mean reward: 4428.8800\ncurrent episode reward: 4606.0000\nepisodes: 3012\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23750.2 seconds (6.60 hours)\n\nTimestep: 5460000\nmean reward (100 episodes): 4438.8600\nbest mean reward: 4438.8600\ncurrent episode reward: 5812.0000\nepisodes: 3014\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23796.8 seconds (6.61 hours)\n\nTimestep: 5470000\nmean reward (100 episodes): 4459.8000\nbest mean reward: 4461.6600\ncurrent episode reward: 5154.0000\nepisodes: 3016\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23841.8 seconds (6.62 hours)\n\nTimestep: 5480000\nmean reward (100 episodes): 4423.8200\nbest mean reward: 4461.6600\ncurrent episode reward: 4156.0000\nepisodes: 3018\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23887.7 seconds (6.64 hours)\n\nTimestep: 5490000\nmean reward (100 episodes): 4467.9400\nbest mean reward: 4467.9400\ncurrent episode reward: 5748.0000\nepisodes: 3020\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23933.5 seconds (6.65 hours)\n\nTimestep: 5500000\nmean reward (100 episodes): 4442.1600\nbest mean reward: 4467.9400\ncurrent episode reward: 7242.0000\nepisodes: 3022\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23979.0 seconds (6.66 hours)\n\nTimestep: 5510000\nmean reward (100 episodes): 4482.7200\nbest mean reward: 4482.7200\ncurrent episode reward: 4704.0000\nepisodes: 3024\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24024.3 seconds (6.67 hours)\n\nTimestep: 5520000\nmean reward (100 episodes): 4505.1400\nbest mean reward: 4509.1400\ncurrent episode reward: 5348.0000\nepisodes: 3026\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24070.3 seconds (6.69 hours)\n\nTimestep: 5530000\nmean reward (100 episodes): 4583.4200\nbest mean reward: 4583.4200\ncurrent episode reward: 9680.0000\nepisodes: 3028\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24116.1 seconds (6.70 hours)\n\nTimestep: 5540000\nmean reward (100 episodes): 4627.5800\nbest mean reward: 4627.5800\ncurrent episode reward: 8256.0000\nepisodes: 3029\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24161.6 seconds (6.71 hours)\n\nTimestep: 5550000\nmean reward (100 episodes): 4554.0800\nbest mean reward: 4627.5800\ncurrent episode reward: 3990.0000\nepisodes: 3032\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24207.6 seconds (6.72 hours)\n\nTimestep: 5560000\nmean reward (100 episodes): 4557.4400\nbest mean reward: 4627.5800\ncurrent episode reward: 2944.0000\nepisodes: 3033\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24253.7 seconds (6.74 hours)\n\nTimestep: 5570000\nmean reward (100 episodes): 4639.6400\nbest mean reward: 4639.6400\ncurrent episode reward: 7182.0000\nepisodes: 3035\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24299.0 seconds (6.75 hours)\n\nTimestep: 5580000\nmean reward (100 episodes): 4653.2600\nbest mean reward: 4653.2600\ncurrent episode reward: 6876.0000\nepisodes: 3038\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24344.5 seconds (6.76 hours)\n\nTimestep: 5590000\nmean reward (100 episodes): 4652.9200\nbest mean reward: 4679.8400\ncurrent episode reward: 2944.0000\nepisodes: 3040\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24390.2 seconds (6.78 hours)\n\nTimestep: 5600000\nmean reward (100 episodes): 4610.9200\nbest mean reward: 4679.8400\ncurrent episode reward: 3000.0000\nepisodes: 3042\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24436.2 seconds (6.79 hours)\n\nTimestep: 5610000\nmean reward (100 episodes): 4605.1000\nbest mean reward: 4679.8400\ncurrent episode reward: 2832.0000\nepisodes: 3044\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24481.7 seconds (6.80 hours)\n\nTimestep: 5620000\nmean reward (100 episodes): 4592.3000\nbest mean reward: 4679.8400\ncurrent episode reward: 3672.0000\nepisodes: 3046\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24527.5 seconds (6.81 hours)\n\nTimestep: 5630000\nmean reward (100 episodes): 4632.0400\nbest mean reward: 4679.8400\ncurrent episode reward: 3000.0000\nepisodes: 3048\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24572.3 seconds (6.83 hours)\n\nTimestep: 5640000\nmean reward (100 episodes): 4652.3600\nbest mean reward: 4679.8400\ncurrent episode reward: 4028.0000\nepisodes: 3050\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24616.9 seconds (6.84 hours)\n\nTimestep: 5650000\nmean reward (100 episodes): 4665.7000\nbest mean reward: 4679.8400\ncurrent episode reward: 3540.0000\nepisodes: 3052\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24663.3 seconds (6.85 hours)\n\nTimestep: 5660000\nmean reward (100 episodes): 4699.6600\nbest mean reward: 4699.6600\ncurrent episode reward: 4284.0000\nepisodes: 3055\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24708.9 seconds (6.86 hours)\n\nTimestep: 5670000\nmean reward (100 episodes): 4634.3000\nbest mean reward: 4699.6600\ncurrent episode reward: 3000.0000\nepisodes: 3057\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24754.0 seconds (6.88 hours)\n\nTimestep: 5680000\nmean reward (100 episodes): 4631.0200\nbest mean reward: 4699.6600\ncurrent episode reward: 5880.0000\nepisodes: 3059\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24799.8 seconds (6.89 hours)\n\nTimestep: 5690000\nmean reward (100 episodes): 4638.3600\nbest mean reward: 4699.6600\ncurrent episode reward: 6240.0000\nepisodes: 3061\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24845.0 seconds (6.90 hours)\n\nTimestep: 5700000\nmean reward (100 episodes): 4651.7400\nbest mean reward: 4699.6600\ncurrent episode reward: 4348.0000\nepisodes: 3063\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24891.1 seconds (6.91 hours)\n\nTimestep: 5710000\nmean reward (100 episodes): 4660.4200\nbest mean reward: 4699.6600\ncurrent episode reward: 7920.0000\nepisodes: 3065\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24936.1 seconds (6.93 hours)\n\nTimestep: 5720000\nmean reward (100 episodes): 4708.0400\nbest mean reward: 4708.0400\ncurrent episode reward: 7494.0000\nepisodes: 3067\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24981.4 seconds (6.94 hours)\n\nTimestep: 5730000\nmean reward (100 episodes): 4737.4600\nbest mean reward: 4737.4600\ncurrent episode reward: 8970.0000\nepisodes: 3068\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25026.8 seconds (6.95 hours)\n\nTimestep: 5740000\nmean reward (100 episodes): 4793.2000\nbest mean reward: 4793.2000\ncurrent episode reward: 5216.0000\nepisodes: 3071\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25072.3 seconds (6.96 hours)\n\nTimestep: 5750000\nmean reward (100 episodes): 4789.8800\nbest mean reward: 4822.1600\ncurrent episode reward: 1796.0000\nepisodes: 3073\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25117.3 seconds (6.98 hours)\n\nTimestep: 5760000\nmean reward (100 episodes): 4807.6200\nbest mean reward: 4822.1600\ncurrent episode reward: 3840.0000\nepisodes: 3076\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25162.5 seconds (6.99 hours)\n\nTimestep: 5770000\nmean reward (100 episodes): 4767.3200\nbest mean reward: 4822.1600\ncurrent episode reward: 1588.0000\nepisodes: 3078\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25208.4 seconds (7.00 hours)\n\nTimestep: 5780000\nmean reward (100 episodes): 4821.8000\nbest mean reward: 4822.1600\ncurrent episode reward: 4414.0000\nepisodes: 3080\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25254.5 seconds (7.02 hours)\n\nTimestep: 5790000\nmean reward (100 episodes): 4859.7200\nbest mean reward: 4859.7200\ncurrent episode reward: 7260.0000\nepisodes: 3082\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25300.5 seconds (7.03 hours)\n\nTimestep: 5800000\nmean reward (100 episodes): 4881.4000\nbest mean reward: 4887.3200\ncurrent episode reward: 3308.0000\nepisodes: 3084\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25345.5 seconds (7.04 hours)\n\nTimestep: 5810000\nmean reward (100 episodes): 4911.6800\nbest mean reward: 4911.6800\ncurrent episode reward: 5282.0000\nepisodes: 3086\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25390.9 seconds (7.05 hours)\n\nTimestep: 5820000\nmean reward (100 episodes): 4930.7600\nbest mean reward: 4930.7600\ncurrent episode reward: 6384.0000\nepisodes: 3088\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25436.4 seconds (7.07 hours)\n\nTimestep: 5830000\nmean reward (100 episodes): 4968.2200\nbest mean reward: 4968.2200\ncurrent episode reward: 4796.0000\nepisodes: 3090\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25482.8 seconds (7.08 hours)\n\nTimestep: 5840000\nmean reward (100 episodes): 4954.5800\nbest mean reward: 4968.2200\ncurrent episode reward: 5088.0000\nepisodes: 3092\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25528.2 seconds (7.09 hours)\n\nTimestep: 5850000\nmean reward (100 episodes): 4987.0000\nbest mean reward: 4987.0000\ncurrent episode reward: 5182.0000\nepisodes: 3094\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25573.9 seconds (7.10 hours)\n\nTimestep: 5860000\nmean reward (100 episodes): 5016.1800\nbest mean reward: 5016.1800\ncurrent episode reward: 9014.0000\nepisodes: 3095\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25618.6 seconds (7.12 hours)\n\nTimestep: 5870000\nmean reward (100 episodes): 4988.2800\nbest mean reward: 5016.1800\ncurrent episode reward: 3000.0000\nepisodes: 3097\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25664.3 seconds (7.13 hours)\n\nTimestep: 5880000\nmean reward (100 episodes): 5048.1000\nbest mean reward: 5048.1000\ncurrent episode reward: 4640.0000\nepisodes: 3099\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25709.5 seconds (7.14 hours)\n\nTimestep: 5890000\nmean reward (100 episodes): 5091.0400\nbest mean reward: 5091.0400\ncurrent episode reward: 9000.0000\nepisodes: 3101\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25754.8 seconds (7.15 hours)\n\nTimestep: 5900000\nmean reward (100 episodes): 5090.5400\nbest mean reward: 5091.0400\ncurrent episode reward: 6096.0000\nepisodes: 3102\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25799.9 seconds (7.17 hours)\n\nTimestep: 5910000\nmean reward (100 episodes): 5138.6600\nbest mean reward: 5138.6600\ncurrent episode reward: 7140.0000\nepisodes: 3104\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25845.1 seconds (7.18 hours)\n\nTimestep: 5920000\nmean reward (100 episodes): 5133.8600\nbest mean reward: 5154.2600\ncurrent episode reward: 4764.0000\nepisodes: 3106\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25889.3 seconds (7.19 hours)\n\nTimestep: 5930000\nmean reward (100 episodes): 5157.2000\nbest mean reward: 5157.2000\ncurrent episode reward: 5602.0000\nepisodes: 3108\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25935.7 seconds (7.20 hours)\n\nTimestep: 5940000\nmean reward (100 episodes): 5171.2800\nbest mean reward: 5171.2800\ncurrent episode reward: 6462.0000\nepisodes: 3109\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25981.2 seconds (7.22 hours)\n\nTimestep: 5950000\nmean reward (100 episodes): 5172.9200\nbest mean reward: 5180.9400\ncurrent episode reward: 4796.0000\nepisodes: 3111\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26026.7 seconds (7.23 hours)\n\nTimestep: 5960000\nmean reward (100 episodes): 5170.0000\nbest mean reward: 5198.9800\ncurrent episode reward: 4412.0000\nepisodes: 3114\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26072.4 seconds (7.24 hours)\n\nTimestep: 5970000\nmean reward (100 episodes): 5134.7800\nbest mean reward: 5198.9800\ncurrent episode reward: 2496.0000\nepisodes: 3116\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26117.7 seconds (7.25 hours)\n\nTimestep: 5980000\nmean reward (100 episodes): 5192.6200\nbest mean reward: 5198.9800\ncurrent episode reward: 7684.0000\nepisodes: 3117\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26163.5 seconds (7.27 hours)\n\nTimestep: 5990000\nmean reward (100 episodes): 5225.9400\nbest mean reward: 5233.6600\ncurrent episode reward: 4860.0000\nepisodes: 3119\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26209.3 seconds (7.28 hours)\n\nTimestep: 6000000\nmean reward (100 episodes): 5218.4000\nbest mean reward: 5233.6600\ncurrent episode reward: 6734.0000\nepisodes: 3121\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26254.8 seconds (7.29 hours)\n\nTimestep: 6010000\nmean reward (100 episodes): 5185.6000\nbest mean reward: 5233.6600\ncurrent episode reward: 5182.0000\nepisodes: 3123\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26299.5 seconds (7.31 hours)\n\nTimestep: 6020000\nmean reward (100 episodes): 5164.7200\nbest mean reward: 5233.6600\ncurrent episode reward: 4542.0000\nepisodes: 3125\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26345.7 seconds (7.32 hours)\n\nTimestep: 6030000\nmean reward (100 episodes): 5141.5800\nbest mean reward: 5233.6600\ncurrent episode reward: 3900.0000\nepisodes: 3127\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26391.3 seconds (7.33 hours)\n\nTimestep: 6040000\nmean reward (100 episodes): 5033.9200\nbest mean reward: 5233.6600\ncurrent episode reward: 1380.0000\nepisodes: 3130\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26436.1 seconds (7.34 hours)\n\nTimestep: 6050000\nmean reward (100 episodes): 5047.5400\nbest mean reward: 5233.6600\ncurrent episode reward: 6600.0000\nepisodes: 3132\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26481.8 seconds (7.36 hours)\n\nTimestep: 6060000\nmean reward (100 episodes): 5046.9600\nbest mean reward: 5233.6600\ncurrent episode reward: 5130.0000\nepisodes: 3134\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26526.8 seconds (7.37 hours)\n\nTimestep: 6070000\nmean reward (100 episodes): 5053.6600\nbest mean reward: 5233.6600\ncurrent episode reward: 5310.0000\nepisodes: 3137\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26571.3 seconds (7.38 hours)\n\nTimestep: 6080000\nmean reward (100 episodes): 5035.0800\nbest mean reward: 5233.6600\ncurrent episode reward: 5310.0000\nepisodes: 3139\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26616.5 seconds (7.39 hours)\n\nTimestep: 6090000\nmean reward (100 episodes): 5103.8400\nbest mean reward: 5233.6600\ncurrent episode reward: 9820.0000\nepisodes: 3140\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26662.1 seconds (7.41 hours)\n\nTimestep: 6100000\nmean reward (100 episodes): 5165.6200\nbest mean reward: 5233.6600\ncurrent episode reward: 7950.0000\nepisodes: 3142\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26707.6 seconds (7.42 hours)\n\nTimestep: 6110000\nmean reward (100 episodes): 5193.5600\nbest mean reward: 5233.6600\ncurrent episode reward: 7692.0000\nepisodes: 3143\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26753.5 seconds (7.43 hours)\n\nTimestep: 6120000\nmean reward (100 episodes): 5184.0600\nbest mean reward: 5233.6600\ncurrent episode reward: 6682.0000\nepisodes: 3145\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26798.6 seconds (7.44 hours)\n\nTimestep: 6130000\nmean reward (100 episodes): 5194.1000\nbest mean reward: 5233.6600\ncurrent episode reward: 4350.0000\nepisodes: 3147\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26844.4 seconds (7.46 hours)\n\nTimestep: 6140000\nmean reward (100 episodes): 5215.7400\nbest mean reward: 5233.6600\ncurrent episode reward: 8552.0000\nepisodes: 3149\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26890.3 seconds (7.47 hours)\n\nTimestep: 6150000\nmean reward (100 episodes): 5254.0200\nbest mean reward: 5254.0200\ncurrent episode reward: 8064.0000\nepisodes: 3151\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26936.1 seconds (7.48 hours)\n\nTimestep: 6160000\nmean reward (100 episodes): 5261.3400\nbest mean reward: 5265.6600\ncurrent episode reward: 5268.0000\nepisodes: 3153\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26982.4 seconds (7.50 hours)\n\nTimestep: 6170000\nmean reward (100 episodes): 5259.4600\nbest mean reward: 5265.6600\ncurrent episode reward: 4260.0000\nepisodes: 3155\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27028.4 seconds (7.51 hours)\n\nTimestep: 6180000\nmean reward (100 episodes): 5307.8200\nbest mean reward: 5307.8200\ncurrent episode reward: 6504.0000\nepisodes: 3157\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27074.3 seconds (7.52 hours)\n\nTimestep: 6190000\nmean reward (100 episodes): 5311.6600\nbest mean reward: 5311.6600\ncurrent episode reward: 4284.0000\nepisodes: 3158\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27119.3 seconds (7.53 hours)\n\nTimestep: 6200000\nmean reward (100 episodes): 5332.8400\nbest mean reward: 5332.8400\ncurrent episode reward: 4512.0000\nepisodes: 3160\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27164.8 seconds (7.55 hours)\n\nTimestep: 6210000\nmean reward (100 episodes): 5309.8800\nbest mean reward: 5332.8400\ncurrent episode reward: 4220.0000\nepisodes: 3162\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27210.0 seconds (7.56 hours)\n\nTimestep: 6220000\nmean reward (100 episodes): 5362.9400\nbest mean reward: 5362.9400\ncurrent episode reward: 7020.0000\nepisodes: 3164\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27256.1 seconds (7.57 hours)\n\nTimestep: 6230000\nmean reward (100 episodes): 5335.7000\nbest mean reward: 5362.9400\ncurrent episode reward: 6198.0000\nepisodes: 3166\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27301.5 seconds (7.58 hours)\n\nTimestep: 6240000\nmean reward (100 episodes): 5294.2800\nbest mean reward: 5362.9400\ncurrent episode reward: 5632.0000\nepisodes: 3168\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27346.4 seconds (7.60 hours)\n\nTimestep: 6250000\nmean reward (100 episodes): 5322.7400\nbest mean reward: 5362.9400\ncurrent episode reward: 5536.0000\nepisodes: 3170\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27391.9 seconds (7.61 hours)\n\nTimestep: 6260000\nmean reward (100 episodes): 5299.4400\nbest mean reward: 5362.9400\ncurrent episode reward: 6146.0000\nepisodes: 3172\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27436.8 seconds (7.62 hours)\n\nTimestep: 6270000\nmean reward (100 episodes): 5391.0400\nbest mean reward: 5391.0400\ncurrent episode reward: 5926.0000\nepisodes: 3174\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27482.2 seconds (7.63 hours)\n\nTimestep: 6280000\nmean reward (100 episodes): 5417.3200\nbest mean reward: 5417.3200\ncurrent episode reward: 5376.0000\nepisodes: 3176\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27527.9 seconds (7.65 hours)\n\nTimestep: 6290000\nmean reward (100 episodes): 5452.2400\nbest mean reward: 5452.2400\ncurrent episode reward: 7392.0000\nepisodes: 3177\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27573.4 seconds (7.66 hours)\n\nTimestep: 6300000\nmean reward (100 episodes): 5467.0200\nbest mean reward: 5501.7400\ncurrent episode reward: 3900.0000\nepisodes: 3180\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27619.0 seconds (7.67 hours)\n\nTimestep: 6310000\nmean reward (100 episodes): 5510.4000\nbest mean reward: 5510.4000\ncurrent episode reward: 9674.0000\nepisodes: 3181\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27664.6 seconds (7.68 hours)\n\nTimestep: 6320000\nmean reward (100 episodes): 5513.2000\nbest mean reward: 5513.2000\ncurrent episode reward: 7760.0000\nepisodes: 3183\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27710.2 seconds (7.70 hours)\n\nTimestep: 6330000\nmean reward (100 episodes): 5539.3200\nbest mean reward: 5539.3200\ncurrent episode reward: 6562.0000\nepisodes: 3185\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27756.2 seconds (7.71 hours)\n\nTimestep: 6340000\nmean reward (100 episodes): 5555.3800\nbest mean reward: 5555.3800\ncurrent episode reward: 6024.0000\nepisodes: 3187\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27801.2 seconds (7.72 hours)\n\nTimestep: 6350000\nmean reward (100 episodes): 5577.8800\nbest mean reward: 5577.8800\ncurrent episode reward: 7046.0000\nepisodes: 3189\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27847.0 seconds (7.74 hours)\n\nTimestep: 6360000\nmean reward (100 episodes): 5607.4000\nbest mean reward: 5607.4000\ncurrent episode reward: 5132.0000\nepisodes: 3191\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27892.4 seconds (7.75 hours)\n\nTimestep: 6370000\nmean reward (100 episodes): 5642.5600\nbest mean reward: 5642.5600\ncurrent episode reward: 8604.0000\nepisodes: 3192\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27937.1 seconds (7.76 hours)\n\nTimestep: 6380000\nmean reward (100 episodes): 5635.9800\nbest mean reward: 5644.6000\ncurrent episode reward: 4320.0000\nepisodes: 3194\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27982.0 seconds (7.77 hours)\n\nTimestep: 6390000\nmean reward (100 episodes): 5616.7400\nbest mean reward: 5644.6000\ncurrent episode reward: 4734.0000\nepisodes: 3197\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28026.6 seconds (7.79 hours)\n\nTimestep: 6400000\nmean reward (100 episodes): 5593.6400\nbest mean reward: 5644.6000\ncurrent episode reward: 5700.0000\nepisodes: 3198\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28072.2 seconds (7.80 hours)\n\nTimestep: 6410000\nmean reward (100 episodes): 5612.7600\nbest mean reward: 5644.6000\ncurrent episode reward: 4832.0000\nepisodes: 3200\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28118.5 seconds (7.81 hours)\n\nTimestep: 6420000\nmean reward (100 episodes): 5590.9400\nbest mean reward: 5644.6000\ncurrent episode reward: 6182.0000\nepisodes: 3202\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28163.5 seconds (7.82 hours)\n\nTimestep: 6430000\nmean reward (100 episodes): 5573.0400\nbest mean reward: 5644.6000\ncurrent episode reward: 5608.0000\nepisodes: 3204\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28209.3 seconds (7.84 hours)\n\nTimestep: 6440000\nmean reward (100 episodes): 5562.8200\nbest mean reward: 5644.6000\ncurrent episode reward: 4770.0000\nepisodes: 3206\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28255.1 seconds (7.85 hours)\n\nTimestep: 6450000\nmean reward (100 episodes): 5609.1400\nbest mean reward: 5644.6000\ncurrent episode reward: 6802.0000\nepisodes: 3208\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28301.3 seconds (7.86 hours)\n\nTimestep: 6460000\nmean reward (100 episodes): 5642.8800\nbest mean reward: 5644.6000\ncurrent episode reward: 9760.0000\nepisodes: 3210\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28346.0 seconds (7.87 hours)\n\nTimestep: 6470000\nmean reward (100 episodes): 5656.3000\nbest mean reward: 5656.3000\ncurrent episode reward: 6138.0000\nepisodes: 3211\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28392.2 seconds (7.89 hours)\n\nTimestep: 6480000\nmean reward (100 episodes): 5716.5600\nbest mean reward: 5716.5600\ncurrent episode reward: 10290.0000\nepisodes: 3213\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28438.7 seconds (7.90 hours)\n\nTimestep: 6490000\nmean reward (100 episodes): 5736.1600\nbest mean reward: 5736.1600\ncurrent episode reward: 4932.0000\nepisodes: 3215\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28484.3 seconds (7.91 hours)\n\nTimestep: 6500000\nmean reward (100 episodes): 5747.7800\nbest mean reward: 5772.1600\ncurrent episode reward: 5246.0000\nepisodes: 3217\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28528.9 seconds (7.92 hours)\n\nTimestep: 6510000\nmean reward (100 episodes): 5723.9800\nbest mean reward: 5772.1600\ncurrent episode reward: 5880.0000\nepisodes: 3218\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28574.7 seconds (7.94 hours)\n\nTimestep: 6520000\nmean reward (100 episodes): 5771.4400\nbest mean reward: 5772.1600\ncurrent episode reward: 4542.0000\nepisodes: 3220\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28620.0 seconds (7.95 hours)\n\nTimestep: 6530000\nmean reward (100 episodes): 5766.6800\nbest mean reward: 5772.1600\ncurrent episode reward: 5070.0000\nepisodes: 3222\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28665.6 seconds (7.96 hours)\n\nTimestep: 6540000\nmean reward (100 episodes): 5796.0400\nbest mean reward: 5796.0400\ncurrent episode reward: 5892.0000\nepisodes: 3224\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28710.8 seconds (7.98 hours)\n\nTimestep: 6550000\nmean reward (100 episodes): 5795.9800\nbest mean reward: 5815.3200\ncurrent episode reward: 2608.0000\nepisodes: 3226\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28755.9 seconds (7.99 hours)\n\nTimestep: 6560000\nmean reward (100 episodes): 5839.4400\nbest mean reward: 5839.4400\ncurrent episode reward: 9080.0000\nepisodes: 3228\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28800.8 seconds (8.00 hours)\n\nTimestep: 6570000\nmean reward (100 episodes): 5844.1600\nbest mean reward: 5844.1600\ncurrent episode reward: 3196.0000\nepisodes: 3230\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28846.3 seconds (8.01 hours)\n\nTimestep: 6580000\nmean reward (100 episodes): 5850.0400\nbest mean reward: 5878.8400\ncurrent episode reward: 3720.0000\nepisodes: 3232\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28892.0 seconds (8.03 hours)\n\nTimestep: 6590000\nmean reward (100 episodes): 5866.6800\nbest mean reward: 5879.5800\ncurrent episode reward: 3840.0000\nepisodes: 3234\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28937.3 seconds (8.04 hours)\n\nTimestep: 6600000\nmean reward (100 episodes): 5923.2200\nbest mean reward: 5923.2200\ncurrent episode reward: 7314.0000\nepisodes: 3236\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28983.0 seconds (8.05 hours)\n\nTimestep: 6610000\nmean reward (100 episodes): 5898.8600\nbest mean reward: 5925.5200\ncurrent episode reward: 3000.0000\nepisodes: 3238\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29028.9 seconds (8.06 hours)\n\nTimestep: 6620000\nmean reward (100 episodes): 5933.4200\nbest mean reward: 5933.4200\ncurrent episode reward: 8766.0000\nepisodes: 3239\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29073.7 seconds (8.08 hours)\n\nTimestep: 6630000\nmean reward (100 episodes): 5897.5800\nbest mean reward: 5933.4200\ncurrent episode reward: 5676.0000\nepisodes: 3241\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29119.7 seconds (8.09 hours)\n\nTimestep: 6640000\nmean reward (100 episodes): 5839.4200\nbest mean reward: 5933.4200\ncurrent episode reward: 5926.0000\nepisodes: 3243\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29165.3 seconds (8.10 hours)\n\nTimestep: 6650000\nmean reward (100 episodes): 5871.1600\nbest mean reward: 5933.4200\ncurrent episode reward: 6130.0000\nepisodes: 3245\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29210.9 seconds (8.11 hours)\n\nTimestep: 6660000\nmean reward (100 episodes): 5907.6800\nbest mean reward: 5933.4200\ncurrent episode reward: 6232.0000\nepisodes: 3247\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29256.1 seconds (8.13 hours)\n\nTimestep: 6670000\nmean reward (100 episodes): 5893.5600\nbest mean reward: 5933.4200\ncurrent episode reward: 5088.0000\nepisodes: 3249\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29301.8 seconds (8.14 hours)\n\nTimestep: 6680000\nmean reward (100 episodes): 5868.1800\nbest mean reward: 5933.4200\ncurrent episode reward: 4670.0000\nepisodes: 3251\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29346.9 seconds (8.15 hours)\n\nTimestep: 6690000\nmean reward (100 episodes): 5908.2200\nbest mean reward: 5933.4200\ncurrent episode reward: 6742.0000\nepisodes: 3253\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29392.4 seconds (8.16 hours)\n\nTimestep: 6700000\nmean reward (100 episodes): 5926.1800\nbest mean reward: 5933.4200\ncurrent episode reward: 5952.0000\nepisodes: 3254\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29438.9 seconds (8.18 hours)\n\nTimestep: 6710000\nmean reward (100 episodes): 5997.0200\nbest mean reward: 5997.0200\ncurrent episode reward: 5934.0000\nepisodes: 3256\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29484.9 seconds (8.19 hours)\n\nTimestep: 6720000\nmean reward (100 episodes): 5995.3200\nbest mean reward: 5997.0200\ncurrent episode reward: 6334.0000\nepisodes: 3257\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29530.1 seconds (8.20 hours)\n\nTimestep: 6730000\nmean reward (100 episodes): 6049.5000\nbest mean reward: 6051.8800\ncurrent episode reward: 7568.0000\nepisodes: 3259\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29574.7 seconds (8.22 hours)\n\nTimestep: 6740000\nmean reward (100 episodes): 6073.1200\nbest mean reward: 6073.1200\ncurrent episode reward: 7566.0000\nepisodes: 3261\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29619.6 seconds (8.23 hours)\n\nTimestep: 6750000\nmean reward (100 episodes): 6090.5600\nbest mean reward: 6090.5600\ncurrent episode reward: 5964.0000\nepisodes: 3262\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29666.1 seconds (8.24 hours)\n\nTimestep: 6760000\nmean reward (100 episodes): 6078.3200\nbest mean reward: 6090.5600\ncurrent episode reward: 6742.0000\nepisodes: 3265\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29711.8 seconds (8.25 hours)\n\nTimestep: 6770000\nmean reward (100 episodes): 6097.3400\nbest mean reward: 6097.3400\ncurrent episode reward: 8100.0000\nepisodes: 3266\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29757.6 seconds (8.27 hours)\n\nTimestep: 6780000\nmean reward (100 episodes): 6106.6000\nbest mean reward: 6106.6000\ncurrent episode reward: 5820.0000\nepisodes: 3268\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29803.3 seconds (8.28 hours)\n\nTimestep: 6790000\nmean reward (100 episodes): 6125.3800\nbest mean reward: 6125.3800\ncurrent episode reward: 7086.0000\nepisodes: 3270\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29848.6 seconds (8.29 hours)\n\nTimestep: 6800000\nmean reward (100 episodes): 6214.5800\nbest mean reward: 6214.5800\ncurrent episode reward: 10300.0000\nepisodes: 3271\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29894.6 seconds (8.30 hours)\n\nTimestep: 6810000\nmean reward (100 episodes): 6199.7800\nbest mean reward: 6222.9600\ncurrent episode reward: 6372.0000\nepisodes: 3273\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29940.6 seconds (8.32 hours)\n\nTimestep: 6820000\nmean reward (100 episodes): 6196.6000\nbest mean reward: 6222.9600\ncurrent episode reward: 5608.0000\nepisodes: 3274\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29986.1 seconds (8.33 hours)\n\nTimestep: 6830000\nmean reward (100 episodes): 6244.8400\nbest mean reward: 6244.8400\ncurrent episode reward: 7486.0000\nepisodes: 3276\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30032.0 seconds (8.34 hours)\n\nTimestep: 6840000\nmean reward (100 episodes): 6217.6200\nbest mean reward: 6244.8400\ncurrent episode reward: 4670.0000\nepisodes: 3277\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30077.7 seconds (8.35 hours)\n\nTimestep: 6850000\nmean reward (100 episodes): 6259.8800\nbest mean reward: 6259.8800\ncurrent episode reward: 6312.0000\nepisodes: 3279\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30122.4 seconds (8.37 hours)\n\nTimestep: 6860000\nmean reward (100 episodes): 6266.1800\nbest mean reward: 6281.8400\ncurrent episode reward: 8108.0000\nepisodes: 3281\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30167.8 seconds (8.38 hours)\n\nTimestep: 6870000\nmean reward (100 episodes): 6274.8800\nbest mean reward: 6281.8400\ncurrent episode reward: 7446.0000\nepisodes: 3283\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30213.4 seconds (8.39 hours)\n\nTimestep: 6880000\nmean reward (100 episodes): 6269.0400\nbest mean reward: 6281.8400\ncurrent episode reward: 6876.0000\nepisodes: 3285\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30259.4 seconds (8.41 hours)\n\nTimestep: 6890000\nmean reward (100 episodes): 6260.4000\nbest mean reward: 6281.8400\ncurrent episode reward: 4092.0000\nepisodes: 3286\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30305.0 seconds (8.42 hours)\n\nTimestep: 6900000\nmean reward (100 episodes): 6295.0400\nbest mean reward: 6313.8600\ncurrent episode reward: 4860.0000\nepisodes: 3288\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30350.1 seconds (8.43 hours)\n\nTimestep: 6910000\nmean reward (100 episodes): 6300.7200\nbest mean reward: 6313.8600\ncurrent episode reward: 6462.0000\nepisodes: 3290\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30395.6 seconds (8.44 hours)\n\nTimestep: 6920000\nmean reward (100 episodes): 6293.3800\nbest mean reward: 6313.8600\ncurrent episode reward: 7488.0000\nepisodes: 3292\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30441.5 seconds (8.46 hours)\n\nTimestep: 6930000\nmean reward (100 episodes): 6285.0800\nbest mean reward: 6313.8600\ncurrent episode reward: 4170.0000\nepisodes: 3294\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30486.4 seconds (8.47 hours)\n\nTimestep: 6940000\nmean reward (100 episodes): 6309.6200\nbest mean reward: 6313.8600\ncurrent episode reward: 5308.0000\nepisodes: 3296\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30531.7 seconds (8.48 hours)\n\nTimestep: 6950000\nmean reward (100 episodes): 6343.0800\nbest mean reward: 6343.0800\ncurrent episode reward: 6176.0000\nepisodes: 3298\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30577.3 seconds (8.49 hours)\n\nTimestep: 6960000\nmean reward (100 episodes): 6327.5200\nbest mean reward: 6343.0800\ncurrent episode reward: 4092.0000\nepisodes: 3300\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30623.4 seconds (8.51 hours)\n\nTimestep: 6970000\nmean reward (100 episodes): 6335.1200\nbest mean reward: 6343.0800\ncurrent episode reward: 7492.0000\nepisodes: 3301\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30668.7 seconds (8.52 hours)\n\nTimestep: 6980000\nmean reward (100 episodes): 6304.6600\nbest mean reward: 6343.0800\ncurrent episode reward: 6262.0000\nepisodes: 3303\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30714.7 seconds (8.53 hours)\n\nTimestep: 6990000\nmean reward (100 episodes): 6306.3000\nbest mean reward: 6343.0800\ncurrent episode reward: 5248.0000\nepisodes: 3306\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30760.8 seconds (8.54 hours)\n\nTimestep: 7000000\nmean reward (100 episodes): 6266.4200\nbest mean reward: 6343.0800\ncurrent episode reward: 4220.0000\nepisodes: 3308\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30806.1 seconds (8.56 hours)\n\nTimestep: 7010000\nmean reward (100 episodes): 6220.6400\nbest mean reward: 6343.0800\ncurrent episode reward: 5608.0000\nepisodes: 3310\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30851.2 seconds (8.57 hours)\n\nTimestep: 7020000\nmean reward (100 episodes): 6216.2200\nbest mean reward: 6343.0800\ncurrent episode reward: 5696.0000\nepisodes: 3311\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30896.7 seconds (8.58 hours)\n\nTimestep: 7030000\nmean reward (100 episodes): 6166.2000\nbest mean reward: 6343.0800\ncurrent episode reward: 3000.0000\nepisodes: 3314\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30943.5 seconds (8.60 hours)\n\nTimestep: 7040000\nmean reward (100 episodes): 6112.6200\nbest mean reward: 6343.0800\ncurrent episode reward: 1380.0000\nepisodes: 3316\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30989.4 seconds (8.61 hours)\n\nTimestep: 7050000\nmean reward (100 episodes): 6150.1000\nbest mean reward: 6343.0800\ncurrent episode reward: 7314.0000\nepisodes: 3318\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31035.1 seconds (8.62 hours)\n\nTimestep: 7060000\nmean reward (100 episodes): 6121.9800\nbest mean reward: 6343.0800\ncurrent episode reward: 4092.0000\nepisodes: 3320\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31081.0 seconds (8.63 hours)\n\nTimestep: 7070000\nmean reward (100 episodes): 6129.6000\nbest mean reward: 6343.0800\ncurrent episode reward: 8340.0000\nepisodes: 3322\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31127.2 seconds (8.65 hours)\n\nTimestep: 7080000\nmean reward (100 episodes): 6107.1600\nbest mean reward: 6343.0800\ncurrent episode reward: 6894.0000\nepisodes: 3324\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31173.3 seconds (8.66 hours)\n\nTimestep: 7090000\nmean reward (100 episodes): 6112.9600\nbest mean reward: 6343.0800\ncurrent episode reward: 7050.0000\nepisodes: 3325\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31218.0 seconds (8.67 hours)\n\nTimestep: 7100000\nmean reward (100 episodes): 6162.5800\nbest mean reward: 6343.0800\ncurrent episode reward: 5410.0000\nepisodes: 3327\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31263.3 seconds (8.68 hours)\n\nTimestep: 7110000\nmean reward (100 episodes): 6156.2800\nbest mean reward: 6343.0800\ncurrent episode reward: 4290.0000\nepisodes: 3330\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31308.5 seconds (8.70 hours)\n\nTimestep: 7120000\nmean reward (100 episodes): 6162.7600\nbest mean reward: 6343.0800\ncurrent episode reward: 6948.0000\nepisodes: 3331\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31353.7 seconds (8.71 hours)\n\nTimestep: 7130000\nmean reward (100 episodes): 6145.8800\nbest mean reward: 6343.0800\ncurrent episode reward: 6240.0000\nepisodes: 3334\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31398.7 seconds (8.72 hours)\n\nTimestep: 7140000\nmean reward (100 episodes): 6026.4200\nbest mean reward: 6343.0800\ncurrent episode reward: 4110.0000\nepisodes: 3337\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31444.1 seconds (8.73 hours)\n\nTimestep: 7150000\nmean reward (100 episodes): 6058.6600\nbest mean reward: 6343.0800\ncurrent episode reward: 6224.0000\nepisodes: 3338\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31489.4 seconds (8.75 hours)\n\nTimestep: 7160000\nmean reward (100 episodes): 6042.1800\nbest mean reward: 6343.0800\ncurrent episode reward: 7776.0000\nepisodes: 3340\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31535.1 seconds (8.76 hours)\n\nTimestep: 7170000\nmean reward (100 episodes): 6050.5400\nbest mean reward: 6343.0800\ncurrent episode reward: 5280.0000\nepisodes: 3342\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31580.5 seconds (8.77 hours)\n\nTimestep: 7180000\nmean reward (100 episodes): 6049.8000\nbest mean reward: 6343.0800\ncurrent episode reward: 6892.0000\nepisodes: 3344\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31625.1 seconds (8.78 hours)\n\nTimestep: 7190000\nmean reward (100 episodes): 6080.7000\nbest mean reward: 6343.0800\ncurrent episode reward: 9220.0000\nepisodes: 3345\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31671.2 seconds (8.80 hours)\n\nTimestep: 7200000\nmean reward (100 episodes): 6048.0800\nbest mean reward: 6343.0800\ncurrent episode reward: 4860.0000\nepisodes: 3347\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31717.1 seconds (8.81 hours)\n\nTimestep: 7210000\nmean reward (100 episodes): 6019.4200\nbest mean reward: 6343.0800\ncurrent episode reward: 3570.0000\nepisodes: 3349\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31762.5 seconds (8.82 hours)\n\nTimestep: 7220000\nmean reward (100 episodes): 6068.6200\nbest mean reward: 6343.0800\ncurrent episode reward: 11358.0000\nepisodes: 3350\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31808.1 seconds (8.84 hours)\n\nTimestep: 7230000\nmean reward (100 episodes): 6101.6600\nbest mean reward: 6343.0800\ncurrent episode reward: 7068.0000\nepisodes: 3352\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31854.1 seconds (8.85 hours)\n\nTimestep: 7240000\nmean reward (100 episodes): 6099.0200\nbest mean reward: 6343.0800\ncurrent episode reward: 6478.0000\nepisodes: 3353\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31900.3 seconds (8.86 hours)\n\nTimestep: 7250000\nmean reward (100 episodes): 6088.3200\nbest mean reward: 6343.0800\ncurrent episode reward: 7476.0000\nepisodes: 3355\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31945.9 seconds (8.87 hours)\n\nTimestep: 7260000\nmean reward (100 episodes): 6115.4200\nbest mean reward: 6343.0800\ncurrent episode reward: 6168.0000\nepisodes: 3357\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31991.5 seconds (8.89 hours)\n\nTimestep: 7270000\nmean reward (100 episodes): 6095.8800\nbest mean reward: 6343.0800\ncurrent episode reward: 7986.0000\nepisodes: 3358\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32036.8 seconds (8.90 hours)\n\nTimestep: 7280000\nmean reward (100 episodes): 6129.3200\nbest mean reward: 6343.0800\ncurrent episode reward: 7818.0000\nepisodes: 3360\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32082.2 seconds (8.91 hours)\n\nTimestep: 7290000\nmean reward (100 episodes): 6131.5400\nbest mean reward: 6343.0800\ncurrent episode reward: 7224.0000\nepisodes: 3362\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32127.6 seconds (8.92 hours)\n\nTimestep: 7300000\nmean reward (100 episodes): 6132.0400\nbest mean reward: 6343.0800\ncurrent episode reward: 4898.0000\nepisodes: 3364\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32172.7 seconds (8.94 hours)\n\nTimestep: 7310000\nmean reward (100 episodes): 6135.1200\nbest mean reward: 6343.0800\ncurrent episode reward: 7050.0000\nepisodes: 3365\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32218.9 seconds (8.95 hours)\n\nTimestep: 7320000\nmean reward (100 episodes): 6124.6800\nbest mean reward: 6343.0800\ncurrent episode reward: 6894.0000\nepisodes: 3367\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32264.6 seconds (8.96 hours)\n\nTimestep: 7330000\nmean reward (100 episodes): 6156.9200\nbest mean reward: 6343.0800\ncurrent episode reward: 9044.0000\nepisodes: 3368\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32309.9 seconds (8.97 hours)\n\nTimestep: 7340000\nmean reward (100 episodes): 6184.6800\nbest mean reward: 6343.0800\ncurrent episode reward: 10040.0000\nepisodes: 3369\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32355.9 seconds (8.99 hours)\n\nTimestep: 7350000\nmean reward (100 episodes): 6163.9800\nbest mean reward: 6343.0800\ncurrent episode reward: 6100.0000\nepisodes: 3371\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32401.7 seconds (9.00 hours)\n\nTimestep: 7360000\nmean reward (100 episodes): 6122.5200\nbest mean reward: 6343.0800\ncurrent episode reward: 5182.0000\nepisodes: 3373\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32446.9 seconds (9.01 hours)\n\nTimestep: 7370000\nmean reward (100 episodes): 6108.2000\nbest mean reward: 6343.0800\ncurrent episode reward: 4414.0000\nepisodes: 3375\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32492.0 seconds (9.03 hours)\n\nTimestep: 7380000\nmean reward (100 episodes): 6103.1200\nbest mean reward: 6343.0800\ncurrent episode reward: 6978.0000\nepisodes: 3376\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32537.5 seconds (9.04 hours)\n\nTimestep: 7390000\nmean reward (100 episodes): 6101.5400\nbest mean reward: 6343.0800\ncurrent episode reward: 6262.0000\nepisodes: 3378\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32582.7 seconds (9.05 hours)\n\nTimestep: 7400000\nmean reward (100 episodes): 6111.7000\nbest mean reward: 6343.0800\ncurrent episode reward: 8820.0000\nepisodes: 3380\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32627.9 seconds (9.06 hours)\n\nTimestep: 7410000\nmean reward (100 episodes): 6071.5400\nbest mean reward: 6343.0800\ncurrent episode reward: 4092.0000\nepisodes: 3381\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32673.2 seconds (9.08 hours)\n\nTimestep: 7420000\nmean reward (100 episodes): 6115.5200\nbest mean reward: 6343.0800\ncurrent episode reward: 9288.0000\nepisodes: 3383\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32718.8 seconds (9.09 hours)\n\nTimestep: 7430000\nmean reward (100 episodes): 6091.2800\nbest mean reward: 6343.0800\ncurrent episode reward: 6704.0000\nepisodes: 3385\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32763.9 seconds (9.10 hours)\n\nTimestep: 7440000\nmean reward (100 episodes): 6105.0200\nbest mean reward: 6343.0800\ncurrent episode reward: 8346.0000\nepisodes: 3387\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32810.0 seconds (9.11 hours)\n\nTimestep: 7450000\nmean reward (100 episodes): 6100.5200\nbest mean reward: 6343.0800\ncurrent episode reward: 4962.0000\nepisodes: 3389\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32855.5 seconds (9.13 hours)\n\nTimestep: 7460000\nmean reward (100 episodes): 6077.9800\nbest mean reward: 6343.0800\ncurrent episode reward: 5310.0000\nepisodes: 3391\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32901.0 seconds (9.14 hours)\n\nTimestep: 7470000\nmean reward (100 episodes): 6085.5800\nbest mean reward: 6343.0800\ncurrent episode reward: 6330.0000\nepisodes: 3393\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32946.6 seconds (9.15 hours)\n\nTimestep: 7480000\nmean reward (100 episodes): 6095.7000\nbest mean reward: 6343.0800\ncurrent episode reward: 5182.0000\nepisodes: 3394\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32992.4 seconds (9.16 hours)\n\nTimestep: 7490000\nmean reward (100 episodes): 6056.1800\nbest mean reward: 6343.0800\ncurrent episode reward: 2496.0000\nepisodes: 3397\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33037.7 seconds (9.18 hours)\n\nTimestep: 7500000\nmean reward (100 episodes): 6059.7600\nbest mean reward: 6343.0800\ncurrent episode reward: 6534.0000\nepisodes: 3398\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33083.2 seconds (9.19 hours)\n\nTimestep: 7510000\nmean reward (100 episodes): 6125.6800\nbest mean reward: 6343.0800\ncurrent episode reward: 7200.0000\nepisodes: 3400\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33129.4 seconds (9.20 hours)\n\nTimestep: 7520000\nmean reward (100 episodes): 6098.1000\nbest mean reward: 6343.0800\ncurrent episode reward: 4734.0000\nepisodes: 3401\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33174.6 seconds (9.22 hours)\n\nTimestep: 7530000\nmean reward (100 episodes): 6119.7200\nbest mean reward: 6343.0800\ncurrent episode reward: 1380.0000\nepisodes: 3403\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33219.7 seconds (9.23 hours)\n\nTimestep: 7540000\nmean reward (100 episodes): 6199.3600\nbest mean reward: 6343.0800\ncurrent episode reward: 10610.0000\nepisodes: 3405\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33265.4 seconds (9.24 hours)\n\nTimestep: 7550000\nmean reward (100 episodes): 6228.5400\nbest mean reward: 6343.0800\ncurrent episode reward: 8166.0000\nepisodes: 3406\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33310.8 seconds (9.25 hours)\n\nTimestep: 7560000\nmean reward (100 episodes): 6254.4800\nbest mean reward: 6343.0800\ncurrent episode reward: 8940.0000\nepisodes: 3407\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33356.0 seconds (9.27 hours)\n\nTimestep: 7570000\nmean reward (100 episodes): 6310.2400\nbest mean reward: 6343.0800\ncurrent episode reward: 5054.0000\nepisodes: 3409\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33401.0 seconds (9.28 hours)\n\nTimestep: 7580000\nmean reward (100 episodes): 6340.7200\nbest mean reward: 6350.0400\ncurrent episode reward: 4764.0000\nepisodes: 3411\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33446.6 seconds (9.29 hours)\n\nTimestep: 7590000\nmean reward (100 episodes): 6323.7800\nbest mean reward: 6350.0400\ncurrent episode reward: 7416.0000\nepisodes: 3413\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33492.2 seconds (9.30 hours)\n\nTimestep: 7600000\nmean reward (100 episodes): 6397.2800\nbest mean reward: 6397.2800\ncurrent episode reward: 10350.0000\nepisodes: 3414\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33537.4 seconds (9.32 hours)\n\nTimestep: 7610000\nmean reward (100 episodes): 6459.5600\nbest mean reward: 6459.5600\ncurrent episode reward: 6618.0000\nepisodes: 3416\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33583.3 seconds (9.33 hours)\n\nTimestep: 7620000\nmean reward (100 episodes): 6463.9400\nbest mean reward: 6463.9400\ncurrent episode reward: 8022.0000\nepisodes: 3418\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33628.7 seconds (9.34 hours)\n\nTimestep: 7630000\nmean reward (100 episodes): 6491.8400\nbest mean reward: 6491.8400\ncurrent episode reward: 7652.0000\nepisodes: 3419\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33673.4 seconds (9.35 hours)\n\nTimestep: 7640000\nmean reward (100 episodes): 6542.7200\nbest mean reward: 6542.7200\ncurrent episode reward: 5880.0000\nepisodes: 3421\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33718.9 seconds (9.37 hours)\n\nTimestep: 7650000\nmean reward (100 episodes): 6558.9200\nbest mean reward: 6558.9200\ncurrent episode reward: 9960.0000\nepisodes: 3422\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33764.8 seconds (9.38 hours)\n\nTimestep: 7660000\nmean reward (100 episodes): 6529.7800\nbest mean reward: 6558.9200\ncurrent episode reward: 4220.0000\nepisodes: 3424\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33810.0 seconds (9.39 hours)\n\nTimestep: 7670000\nmean reward (100 episodes): 6526.6200\nbest mean reward: 6558.9200\ncurrent episode reward: 7320.0000\nepisodes: 3426\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33855.3 seconds (9.40 hours)\n\nTimestep: 7680000\nmean reward (100 episodes): 6507.6600\nbest mean reward: 6558.9200\ncurrent episode reward: 5340.0000\nepisodes: 3428\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33901.3 seconds (9.42 hours)\n\nTimestep: 7690000\nmean reward (100 episodes): 6588.5600\nbest mean reward: 6588.5600\ncurrent episode reward: 12696.0000\nepisodes: 3429\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33947.1 seconds (9.43 hours)\n\nTimestep: 7700000\nmean reward (100 episodes): 6592.8400\nbest mean reward: 6603.5200\ncurrent episode reward: 5880.0000\nepisodes: 3431\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33992.7 seconds (9.44 hours)\n\nTimestep: 7710000\nmean reward (100 episodes): 6661.0000\nbest mean reward: 6661.0000\ncurrent episode reward: 8736.0000\nepisodes: 3433\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34037.6 seconds (9.45 hours)\n\nTimestep: 7720000\nmean reward (100 episodes): 6691.4200\nbest mean reward: 6691.4200\ncurrent episode reward: 9282.0000\nepisodes: 3434\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34082.7 seconds (9.47 hours)\n\nTimestep: 7730000\nmean reward (100 episodes): 6849.4800\nbest mean reward: 6849.4800\ncurrent episode reward: 5280.0000\nepisodes: 3436\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34128.2 seconds (9.48 hours)\n\nTimestep: 7740000\nmean reward (100 episodes): 6954.3200\nbest mean reward: 6954.3200\ncurrent episode reward: 14594.0000\nepisodes: 3437\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34174.6 seconds (9.49 hours)\n\nTimestep: 7750000\nmean reward (100 episodes): 6974.6800\nbest mean reward: 6974.6800\ncurrent episode reward: 8260.0000\nepisodes: 3438\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34219.7 seconds (9.51 hours)\n\nTimestep: 7760000\nmean reward (100 episodes): 6951.8000\nbest mean reward: 6995.3600\ncurrent episode reward: 3420.0000\nepisodes: 3440\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34265.7 seconds (9.52 hours)\n\nTimestep: 7770000\nmean reward (100 episodes): 6974.2200\nbest mean reward: 6995.3600\ncurrent episode reward: 5676.0000\nepisodes: 3442\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34311.5 seconds (9.53 hours)\n\nTimestep: 7780000\nmean reward (100 episodes): 7023.2800\nbest mean reward: 7023.2800\ncurrent episode reward: 12068.0000\nepisodes: 3443\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34357.4 seconds (9.54 hours)\n\nTimestep: 7790000\nmean reward (100 episodes): 7006.1200\nbest mean reward: 7025.4800\ncurrent episode reward: 7284.0000\nepisodes: 3445\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34403.0 seconds (9.56 hours)\n\nTimestep: 7800000\nmean reward (100 episodes): 7035.0400\nbest mean reward: 7035.0400\ncurrent episode reward: 9636.0000\nepisodes: 3446\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34449.2 seconds (9.57 hours)\n\nTimestep: 7810000\nmean reward (100 episodes): 7075.2400\nbest mean reward: 7075.2400\ncurrent episode reward: 4860.0000\nepisodes: 3448\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34495.1 seconds (9.58 hours)\n\nTimestep: 7820000\nmean reward (100 episodes): 7103.4400\nbest mean reward: 7103.4400\ncurrent episode reward: 6390.0000\nepisodes: 3449\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34540.5 seconds (9.59 hours)\n\nTimestep: 7830000\nmean reward (100 episodes): 7030.6400\nbest mean reward: 7103.4400\ncurrent episode reward: 6028.0000\nepisodes: 3451\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34586.5 seconds (9.61 hours)\n\nTimestep: 7840000\nmean reward (100 episodes): 7002.7400\nbest mean reward: 7103.4400\ncurrent episode reward: 4156.0000\nepisodes: 3453\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34632.4 seconds (9.62 hours)\n\nTimestep: 7850000\nmean reward (100 episodes): 6999.3200\nbest mean reward: 7103.4400\ncurrent episode reward: 6888.0000\nepisodes: 3455\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34677.8 seconds (9.63 hours)\n\nTimestep: 7860000\nmean reward (100 episodes): 6959.1800\nbest mean reward: 7103.4400\ncurrent episode reward: 4796.0000\nepisodes: 3456\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34723.8 seconds (9.65 hours)\n\nTimestep: 7870000\nmean reward (100 episodes): 7022.2200\nbest mean reward: 7103.4400\ncurrent episode reward: 12472.0000\nepisodes: 3457\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34770.0 seconds (9.66 hours)\n\nTimestep: 7880000\nmean reward (100 episodes): 7021.0000\nbest mean reward: 7103.4400\ncurrent episode reward: 8164.0000\nepisodes: 3459\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34815.1 seconds (9.67 hours)\n\nTimestep: 7890000\nmean reward (100 episodes): 6966.1000\nbest mean reward: 7103.4400\ncurrent episode reward: 4956.0000\nepisodes: 3461\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34861.1 seconds (9.68 hours)\n\nTimestep: 7900000\nmean reward (100 episodes): 6958.3400\nbest mean reward: 7103.4400\ncurrent episode reward: 5182.0000\nepisodes: 3463\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34907.2 seconds (9.70 hours)\n\nTimestep: 7910000\nmean reward (100 episodes): 6937.3200\nbest mean reward: 7103.4400\ncurrent episode reward: 2664.0000\nepisodes: 3465\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34952.5 seconds (9.71 hours)\n\nTimestep: 7920000\nmean reward (100 episodes): 6958.6200\nbest mean reward: 7103.4400\ncurrent episode reward: 9720.0000\nepisodes: 3466\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34997.6 seconds (9.72 hours)\n\nTimestep: 7930000\nmean reward (100 episodes): 6960.2400\nbest mean reward: 7103.4400\ncurrent episode reward: 6390.0000\nepisodes: 3468\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35042.9 seconds (9.73 hours)\n\nTimestep: 7940000\nmean reward (100 episodes): 6908.3800\nbest mean reward: 7103.4400\ncurrent episode reward: 4860.0000\nepisodes: 3470\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35088.8 seconds (9.75 hours)\n\nTimestep: 7950000\nmean reward (100 episodes): 6901.4200\nbest mean reward: 7103.4400\ncurrent episode reward: 5404.0000\nepisodes: 3471\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35135.0 seconds (9.76 hours)\n\nTimestep: 7960000\nmean reward (100 episodes): 6932.2600\nbest mean reward: 7103.4400\ncurrent episode reward: 7112.0000\nepisodes: 3472\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35179.5 seconds (9.77 hours)\n\nTimestep: 7970000\nmean reward (100 episodes): 6970.9000\nbest mean reward: 7103.4400\ncurrent episode reward: 6644.0000\nepisodes: 3474\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35224.7 seconds (9.78 hours)\n\nTimestep: 7980000\nmean reward (100 episodes): 6967.2600\nbest mean reward: 7103.4400\ncurrent episode reward: 5148.0000\nepisodes: 3476\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35270.0 seconds (9.80 hours)\n\nTimestep: 7990000\nmean reward (100 episodes): 6942.1400\nbest mean reward: 7103.4400\ncurrent episode reward: 6292.0000\nepisodes: 3478\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35315.3 seconds (9.81 hours)\n\nTimestep: 8000000\nmean reward (100 episodes): 6933.5600\nbest mean reward: 7103.4400\ncurrent episode reward: 5024.0000\nepisodes: 3480\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35362.0 seconds (9.82 hours)\n\nTimestep: 8010000\nmean reward (100 episodes): 6964.7600\nbest mean reward: 7103.4400\ncurrent episode reward: 7212.0000\nepisodes: 3481\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35407.3 seconds (9.84 hours)\n\nTimestep: 8020000\nmean reward (100 episodes): 6915.3800\nbest mean reward: 7103.4400\ncurrent episode reward: 5200.0000\nepisodes: 3483\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35452.5 seconds (9.85 hours)\n\nTimestep: 8030000\nmean reward (100 episodes): 6996.4200\nbest mean reward: 7103.4400\ncurrent episode reward: 9030.0000\nepisodes: 3485\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35497.6 seconds (9.86 hours)\n\nTimestep: 8040000\nmean reward (100 episodes): 6915.2600\nbest mean reward: 7103.4400\ncurrent episode reward: 6840.0000\nepisodes: 3488\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35542.8 seconds (9.87 hours)\n\nTimestep: 8050000\nmean reward (100 episodes): 6974.3600\nbest mean reward: 7103.4400\ncurrent episode reward: 10872.0000\nepisodes: 3489\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35588.8 seconds (9.89 hours)\n\nTimestep: 8060000\nmean reward (100 episodes): 7019.4000\nbest mean reward: 7103.4400\ncurrent episode reward: 8916.0000\nepisodes: 3490\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35634.5 seconds (9.90 hours)\n\nTimestep: 8070000\nmean reward (100 episodes): 7054.7800\nbest mean reward: 7103.4400\ncurrent episode reward: 6508.0000\nepisodes: 3492\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35679.9 seconds (9.91 hours)\n\nTimestep: 8080000\nmean reward (100 episodes): 7105.6800\nbest mean reward: 7105.6800\ncurrent episode reward: 6732.0000\nepisodes: 3494\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35725.5 seconds (9.92 hours)\n\nTimestep: 8090000\nmean reward (100 episodes): 7083.5000\nbest mean reward: 7105.6800\ncurrent episode reward: 5312.0000\nepisodes: 3495\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35771.4 seconds (9.94 hours)\n\nTimestep: 8100000\nmean reward (100 episodes): 7163.2400\nbest mean reward: 7163.2400\ncurrent episode reward: 5216.0000\nepisodes: 3497\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35816.4 seconds (9.95 hours)\n\nTimestep: 8110000\nmean reward (100 episodes): 7096.8400\nbest mean reward: 7163.2400\ncurrent episode reward: 4348.0000\nepisodes: 3499\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35861.4 seconds (9.96 hours)\n\nTimestep: 8120000\nmean reward (100 episodes): 7094.2000\nbest mean reward: 7163.2400\ncurrent episode reward: 6936.0000\nepisodes: 3500\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35907.7 seconds (9.97 hours)\n\nTimestep: 8130000\nmean reward (100 episodes): 7094.2200\nbest mean reward: 7163.2400\ncurrent episode reward: 4700.0000\nepisodes: 3502\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35953.1 seconds (9.99 hours)\n\nTimestep: 8140000\nmean reward (100 episodes): 7153.0200\nbest mean reward: 7163.2400\ncurrent episode reward: 6996.0000\nepisodes: 3504\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35998.7 seconds (10.00 hours)\n\nTimestep: 8150000\nmean reward (100 episodes): 7111.0200\nbest mean reward: 7163.2400\ncurrent episode reward: 6410.0000\nepisodes: 3505\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36043.4 seconds (10.01 hours)\n\nTimestep: 8160000\nmean reward (100 episodes): 7070.2400\nbest mean reward: 7163.2400\ncurrent episode reward: 5132.0000\nepisodes: 3507\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36087.8 seconds (10.02 hours)\n\nTimestep: 8170000\nmean reward (100 episodes): 7062.6200\nbest mean reward: 7163.2400\ncurrent episode reward: 6840.0000\nepisodes: 3509\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36134.3 seconds (10.04 hours)\n\nTimestep: 8180000\nmean reward (100 episodes): 7065.6400\nbest mean reward: 7163.2400\ncurrent episode reward: 5246.0000\nepisodes: 3511\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36179.1 seconds (10.05 hours)\n\nTimestep: 8190000\nmean reward (100 episodes): 7068.1200\nbest mean reward: 7163.2400\ncurrent episode reward: 6024.0000\nepisodes: 3513\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36223.9 seconds (10.06 hours)\n\nTimestep: 8200000\nmean reward (100 episodes): 7030.7200\nbest mean reward: 7163.2400\ncurrent episode reward: 6610.0000\nepisodes: 3514\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36269.1 seconds (10.07 hours)\n\nTimestep: 8210000\nmean reward (100 episodes): 7046.7000\nbest mean reward: 7163.2400\ncurrent episode reward: 8024.0000\nepisodes: 3516\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36314.9 seconds (10.09 hours)\n\nTimestep: 8220000\nmean reward (100 episodes): 7094.1000\nbest mean reward: 7163.2400\ncurrent episode reward: 12030.0000\nepisodes: 3517\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36361.1 seconds (10.10 hours)\n\nTimestep: 8230000\nmean reward (100 episodes): 7100.5200\nbest mean reward: 7163.2400\ncurrent episode reward: 7476.0000\nepisodes: 3519\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36406.4 seconds (10.11 hours)\n\nTimestep: 8240000\nmean reward (100 episodes): 7113.6600\nbest mean reward: 7163.2400\ncurrent episode reward: 7614.0000\nepisodes: 3520\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36451.5 seconds (10.13 hours)\n\nTimestep: 8250000\nmean reward (100 episodes): 7077.7800\nbest mean reward: 7163.2400\ncurrent episode reward: 8032.0000\nepisodes: 3522\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36497.1 seconds (10.14 hours)\n\nTimestep: 8260000\nmean reward (100 episodes): 7160.7800\nbest mean reward: 7163.2400\ncurrent episode reward: 10630.0000\nepisodes: 3524\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36543.3 seconds (10.15 hours)\n\nTimestep: 8270000\nmean reward (100 episodes): 7174.3800\nbest mean reward: 7174.3800\ncurrent episode reward: 7410.0000\nepisodes: 3525\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36589.2 seconds (10.16 hours)\n\nTimestep: 8280000\nmean reward (100 episodes): 7198.9800\nbest mean reward: 7198.9800\ncurrent episode reward: 9780.0000\nepisodes: 3526\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36634.9 seconds (10.18 hours)\n\nTimestep: 8290000\nmean reward (100 episodes): 7277.0400\nbest mean reward: 7277.0400\ncurrent episode reward: 7486.0000\nepisodes: 3528\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36680.6 seconds (10.19 hours)\n\nTimestep: 8300000\nmean reward (100 episodes): 7261.7800\nbest mean reward: 7277.0400\ncurrent episode reward: 11170.0000\nepisodes: 3529\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36726.3 seconds (10.20 hours)\n\nTimestep: 8310000\nmean reward (100 episodes): 7302.7200\nbest mean reward: 7302.7200\ncurrent episode reward: 9880.0000\nepisodes: 3530\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36771.8 seconds (10.21 hours)\n\nTimestep: 8320000\nmean reward (100 episodes): 7398.3400\nbest mean reward: 7398.8800\ncurrent episode reward: 6186.0000\nepisodes: 3532\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36818.0 seconds (10.23 hours)\n\nTimestep: 8330000\nmean reward (100 episodes): 7341.7200\nbest mean reward: 7398.8800\ncurrent episode reward: 7080.0000\nepisodes: 3534\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36863.6 seconds (10.24 hours)\n\nTimestep: 8340000\nmean reward (100 episodes): 7299.2000\nbest mean reward: 7398.8800\ncurrent episode reward: 10150.0000\nepisodes: 3535\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36909.6 seconds (10.25 hours)\n\nTimestep: 8350000\nmean reward (100 episodes): 7362.0000\nbest mean reward: 7398.8800\ncurrent episode reward: 11560.0000\nepisodes: 3536\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36954.7 seconds (10.27 hours)\n\nTimestep: 8360000\nmean reward (100 episodes): 7314.1600\nbest mean reward: 7398.8800\ncurrent episode reward: 9810.0000\nepisodes: 3537\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36999.5 seconds (10.28 hours)\n\nTimestep: 8370000\nmean reward (100 episodes): 7381.7800\nbest mean reward: 7398.8800\ncurrent episode reward: 5934.0000\nepisodes: 3540\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37045.0 seconds (10.29 hours)\n\nTimestep: 8380000\nmean reward (100 episodes): 7415.6800\nbest mean reward: 7415.6800\ncurrent episode reward: 10368.0000\nepisodes: 3541\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37090.8 seconds (10.30 hours)\n\nTimestep: 8390000\nmean reward (100 episodes): 7442.9800\nbest mean reward: 7442.9800\ncurrent episode reward: 8406.0000\nepisodes: 3542\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37135.6 seconds (10.32 hours)\n\nTimestep: 8400000\nmean reward (100 episodes): 7419.6000\nbest mean reward: 7442.9800\ncurrent episode reward: 7492.0000\nepisodes: 3544\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37180.4 seconds (10.33 hours)\n\nTimestep: 8410000\nmean reward (100 episodes): 7376.1000\nbest mean reward: 7442.9800\ncurrent episode reward: 5790.0000\nepisodes: 3546\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37225.8 seconds (10.34 hours)\n\nTimestep: 8420000\nmean reward (100 episodes): 7393.1000\nbest mean reward: 7442.9800\ncurrent episode reward: 8316.0000\nepisodes: 3548\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37271.4 seconds (10.35 hours)\n\nTimestep: 8430000\nmean reward (100 episodes): 7406.9600\nbest mean reward: 7442.9800\ncurrent episode reward: 7776.0000\nepisodes: 3549\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37317.4 seconds (10.37 hours)\n\nTimestep: 8440000\nmean reward (100 episodes): 7365.9400\nbest mean reward: 7442.9800\ncurrent episode reward: 1588.0000\nepisodes: 3551\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37362.7 seconds (10.38 hours)\n\nTimestep: 8450000\nmean reward (100 episodes): 7433.2800\nbest mean reward: 7442.9800\ncurrent episode reward: 4350.0000\nepisodes: 3553\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37408.4 seconds (10.39 hours)\n\nTimestep: 8460000\nmean reward (100 episodes): 7413.2600\nbest mean reward: 7442.9800\ncurrent episode reward: 4320.0000\nepisodes: 3555\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37454.0 seconds (10.40 hours)\n\nTimestep: 8470000\nmean reward (100 episodes): 7374.3600\nbest mean reward: 7442.9800\ncurrent episode reward: 6644.0000\nepisodes: 3557\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37499.0 seconds (10.42 hours)\n\nTimestep: 8480000\nmean reward (100 episodes): 7349.8200\nbest mean reward: 7442.9800\ncurrent episode reward: 9468.0000\nepisodes: 3559\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37544.2 seconds (10.43 hours)\n\nTimestep: 8490000\nmean reward (100 episodes): 7425.0600\nbest mean reward: 7442.9800\ncurrent episode reward: 11424.0000\nepisodes: 3560\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37590.2 seconds (10.44 hours)\n\nTimestep: 8500000\nmean reward (100 episodes): 7486.3800\nbest mean reward: 7486.3800\ncurrent episode reward: 11088.0000\nepisodes: 3561\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37636.0 seconds (10.45 hours)\n\nTimestep: 8510000\nmean reward (100 episodes): 7485.8600\nbest mean reward: 7486.3800\ncurrent episode reward: 6720.0000\nepisodes: 3563\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37681.1 seconds (10.47 hours)\n\nTimestep: 8520000\nmean reward (100 episodes): 7509.4000\nbest mean reward: 7509.4000\ncurrent episode reward: 2888.0000\nepisodes: 3565\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37727.1 seconds (10.48 hours)\n\nTimestep: 8530000\nmean reward (100 episodes): 7422.4600\nbest mean reward: 7509.4000\ncurrent episode reward: 6194.0000\nepisodes: 3567\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37772.7 seconds (10.49 hours)\n\nTimestep: 8540000\nmean reward (100 episodes): 7425.5200\nbest mean reward: 7509.4000\ncurrent episode reward: 6606.0000\nepisodes: 3569\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37817.4 seconds (10.50 hours)\n\nTimestep: 8550000\nmean reward (100 episodes): 7442.3000\nbest mean reward: 7509.4000\ncurrent episode reward: 6538.0000\nepisodes: 3570\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37862.9 seconds (10.52 hours)\n\nTimestep: 8560000\nmean reward (100 episodes): 7463.7200\nbest mean reward: 7509.4000\ncurrent episode reward: 7866.0000\nepisodes: 3572\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37908.5 seconds (10.53 hours)\n\nTimestep: 8570000\nmean reward (100 episodes): 7422.4200\nbest mean reward: 7509.4000\ncurrent episode reward: 7860.0000\nepisodes: 3574\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37954.0 seconds (10.54 hours)\n\nTimestep: 8580000\nmean reward (100 episodes): 7443.1200\nbest mean reward: 7509.4000\ncurrent episode reward: 7950.0000\nepisodes: 3575\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38000.1 seconds (10.56 hours)\n\nTimestep: 8590000\nmean reward (100 episodes): 7456.2000\nbest mean reward: 7509.4000\ncurrent episode reward: 6456.0000\nepisodes: 3576\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38045.8 seconds (10.57 hours)\n\nTimestep: 8600000\nmean reward (100 episodes): 7551.1200\nbest mean reward: 7551.1200\ncurrent episode reward: 10130.0000\nepisodes: 3578\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38091.7 seconds (10.58 hours)\n\nTimestep: 8610000\nmean reward (100 episodes): 7571.5000\nbest mean reward: 7571.5000\ncurrent episode reward: 9580.0000\nepisodes: 3579\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38137.2 seconds (10.59 hours)\n\nTimestep: 8620000\nmean reward (100 episodes): 7560.2000\nbest mean reward: 7589.4800\ncurrent episode reward: 4284.0000\nepisodes: 3581\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38183.0 seconds (10.61 hours)\n\nTimestep: 8630000\nmean reward (100 episodes): 7594.8400\nbest mean reward: 7594.8400\ncurrent episode reward: 9320.0000\nepisodes: 3583\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38228.4 seconds (10.62 hours)\n\nTimestep: 8640000\nmean reward (100 episodes): 7581.8200\nbest mean reward: 7594.8400\ncurrent episode reward: 6636.0000\nepisodes: 3584\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38274.4 seconds (10.63 hours)\n\nTimestep: 8650000\nmean reward (100 episodes): 7563.2200\nbest mean reward: 7594.8400\ncurrent episode reward: 7170.0000\nepisodes: 3585\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38319.9 seconds (10.64 hours)\n\nTimestep: 8660000\nmean reward (100 episodes): 7682.1800\nbest mean reward: 7682.1800\ncurrent episode reward: 9540.0000\nepisodes: 3587\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38365.0 seconds (10.66 hours)\n\nTimestep: 8670000\nmean reward (100 episodes): 7680.5600\nbest mean reward: 7682.1800\ncurrent episode reward: 6678.0000\nepisodes: 3588\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38410.0 seconds (10.67 hours)\n\nTimestep: 8680000\nmean reward (100 episodes): 7676.6200\nbest mean reward: 7682.1800\ncurrent episode reward: 9800.0000\nepisodes: 3590\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38455.6 seconds (10.68 hours)\n\nTimestep: 8690000\nmean reward (100 episodes): 7617.7200\nbest mean reward: 7682.1800\ncurrent episode reward: 5268.0000\nepisodes: 3592\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38501.3 seconds (10.69 hours)\n\nTimestep: 8700000\nmean reward (100 episodes): 7609.3200\nbest mean reward: 7682.1800\ncurrent episode reward: 8022.0000\nepisodes: 3594\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38546.3 seconds (10.71 hours)\n\nTimestep: 8710000\nmean reward (100 episodes): 7619.3200\nbest mean reward: 7682.1800\ncurrent episode reward: 6312.0000\nepisodes: 3595\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38591.1 seconds (10.72 hours)\n\nTimestep: 8720000\nmean reward (100 episodes): 7615.7800\nbest mean reward: 7682.1800\ncurrent episode reward: 10030.0000\nepisodes: 3597\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38637.8 seconds (10.73 hours)\n\nTimestep: 8730000\nmean reward (100 episodes): 7628.4600\nbest mean reward: 7682.1800\ncurrent episode reward: 5744.0000\nepisodes: 3598\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38682.8 seconds (10.75 hours)\n\nTimestep: 8740000\nmean reward (100 episodes): 7685.5400\nbest mean reward: 7685.5400\ncurrent episode reward: 10602.0000\nepisodes: 3600\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38727.6 seconds (10.76 hours)\n\nTimestep: 8750000\nmean reward (100 episodes): 7669.9400\nbest mean reward: 7685.5400\ncurrent episode reward: 9360.0000\nepisodes: 3601\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38773.2 seconds (10.77 hours)\n\nTimestep: 8760000\nmean reward (100 episodes): 7663.4000\nbest mean reward: 7685.5400\ncurrent episode reward: 7470.0000\nepisodes: 3603\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38818.7 seconds (10.78 hours)\n\nTimestep: 8770000\nmean reward (100 episodes): 7653.0400\nbest mean reward: 7685.5400\ncurrent episode reward: 5896.0000\nepisodes: 3605\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38864.4 seconds (10.80 hours)\n\nTimestep: 8780000\nmean reward (100 episodes): 7631.5000\nbest mean reward: 7685.5400\ncurrent episode reward: 5756.0000\nepisodes: 3607\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38909.4 seconds (10.81 hours)\n\nTimestep: 8790000\nmean reward (100 episodes): 7647.5600\nbest mean reward: 7685.5400\ncurrent episode reward: 7224.0000\nepisodes: 3609\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38954.3 seconds (10.82 hours)\n\nTimestep: 8800000\nmean reward (100 episodes): 7706.2200\nbest mean reward: 7706.2200\ncurrent episode reward: 15274.0000\nepisodes: 3610\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38998.7 seconds (10.83 hours)\n\nTimestep: 8810000\nmean reward (100 episodes): 7704.7800\nbest mean reward: 7706.2200\ncurrent episode reward: 6232.0000\nepisodes: 3612\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39043.8 seconds (10.85 hours)\n\nTimestep: 8820000\nmean reward (100 episodes): 7705.7000\nbest mean reward: 7719.0000\ncurrent episode reward: 5280.0000\nepisodes: 3614\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39089.6 seconds (10.86 hours)\n\nTimestep: 8830000\nmean reward (100 episodes): 7702.6400\nbest mean reward: 7730.4000\ncurrent episode reward: 5248.0000\nepisodes: 3616\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39135.0 seconds (10.87 hours)\n\nTimestep: 8840000\nmean reward (100 episodes): 7648.6200\nbest mean reward: 7730.4000\ncurrent episode reward: 6628.0000\nepisodes: 3617\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39180.6 seconds (10.88 hours)\n\nTimestep: 8850000\nmean reward (100 episodes): 7697.4000\nbest mean reward: 7730.4000\ncurrent episode reward: 9464.0000\nepisodes: 3619\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39226.4 seconds (10.90 hours)\n\nTimestep: 8860000\nmean reward (100 episodes): 7644.1800\nbest mean reward: 7730.4000\ncurrent episode reward: 5132.0000\nepisodes: 3621\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39271.0 seconds (10.91 hours)\n\nTimestep: 8870000\nmean reward (100 episodes): 7662.2600\nbest mean reward: 7730.4000\ncurrent episode reward: 9840.0000\nepisodes: 3622\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39316.0 seconds (10.92 hours)\n\nTimestep: 8880000\nmean reward (100 episodes): 7671.8800\nbest mean reward: 7730.4000\ncurrent episode reward: 10230.0000\nepisodes: 3624\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39360.6 seconds (10.93 hours)\n\nTimestep: 8890000\nmean reward (100 episodes): 7640.9200\nbest mean reward: 7730.4000\ncurrent episode reward: 8362.0000\nepisodes: 3626\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39406.0 seconds (10.95 hours)\n\nTimestep: 8900000\nmean reward (100 episodes): 7537.9600\nbest mean reward: 7730.4000\ncurrent episode reward: 4110.0000\nepisodes: 3628\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39451.2 seconds (10.96 hours)\n\nTimestep: 8910000\nmean reward (100 episodes): 7482.0800\nbest mean reward: 7730.4000\ncurrent episode reward: 7704.0000\nepisodes: 3630\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39496.9 seconds (10.97 hours)\n\nTimestep: 8920000\nmean reward (100 episodes): 7414.2400\nbest mean reward: 7730.4000\ncurrent episode reward: 7398.0000\nepisodes: 3632\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39542.8 seconds (10.98 hours)\n\nTimestep: 8930000\nmean reward (100 episodes): 7410.1400\nbest mean reward: 7730.4000\ncurrent episode reward: 3600.0000\nepisodes: 3634\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39588.7 seconds (11.00 hours)\n\nTimestep: 8940000\nmean reward (100 episodes): 7365.2600\nbest mean reward: 7730.4000\ncurrent episode reward: 5662.0000\nepisodes: 3635\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39634.6 seconds (11.01 hours)\n\nTimestep: 8950000\nmean reward (100 episodes): 7342.8600\nbest mean reward: 7730.4000\ncurrent episode reward: 11300.0000\nepisodes: 3637\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39680.1 seconds (11.02 hours)\n\nTimestep: 8960000\nmean reward (100 episodes): 7228.4000\nbest mean reward: 7730.4000\ncurrent episode reward: 2160.0000\nepisodes: 3639\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39725.7 seconds (11.03 hours)\n\nTimestep: 8970000\nmean reward (100 episodes): 7366.3600\nbest mean reward: 7730.4000\ncurrent episode reward: 19730.0000\nepisodes: 3640\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39771.6 seconds (11.05 hours)\n\nTimestep: 8980000\nmean reward (100 episodes): 7340.1400\nbest mean reward: 7730.4000\ncurrent episode reward: 6292.0000\nepisodes: 3642\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39817.6 seconds (11.06 hours)\n\nTimestep: 8990000\nmean reward (100 episodes): 7334.9000\nbest mean reward: 7730.4000\ncurrent episode reward: 8826.0000\nepisodes: 3643\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39864.0 seconds (11.07 hours)\n\nTimestep: 9000000\nmean reward (100 episodes): 7314.0000\nbest mean reward: 7730.4000\ncurrent episode reward: 6516.0000\nepisodes: 3645\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39909.7 seconds (11.09 hours)\n\nTimestep: 9010000\nmean reward (100 episodes): 7334.2800\nbest mean reward: 7730.4000\ncurrent episode reward: 7818.0000\nepisodes: 3646\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39955.6 seconds (11.10 hours)\n\nTimestep: 9020000\nmean reward (100 episodes): 7381.6200\nbest mean reward: 7730.4000\ncurrent episode reward: 6266.0000\nepisodes: 3648\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40000.9 seconds (11.11 hours)\n\nTimestep: 9030000\nmean reward (100 episodes): 7372.9200\nbest mean reward: 7730.4000\ncurrent episode reward: 6906.0000\nepisodes: 3649\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40045.5 seconds (11.12 hours)\n\nTimestep: 9040000\nmean reward (100 episodes): 7498.3400\nbest mean reward: 7730.4000\ncurrent episode reward: 5540.0000\nepisodes: 3651\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40091.0 seconds (11.14 hours)\n\nTimestep: 9050000\nmean reward (100 episodes): 7466.3200\nbest mean reward: 7730.4000\ncurrent episode reward: 8592.0000\nepisodes: 3653\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40136.4 seconds (11.15 hours)\n\nTimestep: 9060000\nmean reward (100 episodes): 7475.4800\nbest mean reward: 7730.4000\ncurrent episode reward: 8764.0000\nepisodes: 3654\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40181.3 seconds (11.16 hours)\n\nTimestep: 9070000\nmean reward (100 episodes): 7506.1600\nbest mean reward: 7730.4000\ncurrent episode reward: 5602.0000\nepisodes: 3656\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40227.1 seconds (11.17 hours)\n\nTimestep: 9080000\nmean reward (100 episodes): 7605.4400\nbest mean reward: 7730.4000\ncurrent episode reward: 16572.0000\nepisodes: 3657\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40272.7 seconds (11.19 hours)\n\nTimestep: 9090000\nmean reward (100 episodes): 7652.8400\nbest mean reward: 7730.4000\ncurrent episode reward: 8704.0000\nepisodes: 3658\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40318.0 seconds (11.20 hours)\n\nTimestep: 9100000\nmean reward (100 episodes): 7578.5200\nbest mean reward: 7730.4000\ncurrent episode reward: 8178.0000\nepisodes: 3660\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40363.6 seconds (11.21 hours)\n\nTimestep: 9110000\nmean reward (100 episodes): 7534.1600\nbest mean reward: 7730.4000\ncurrent episode reward: 6652.0000\nepisodes: 3661\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40409.3 seconds (11.22 hours)\n\nTimestep: 9120000\nmean reward (100 episodes): 7642.4400\nbest mean reward: 7730.4000\ncurrent episode reward: 12000.0000\nepisodes: 3663\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40454.5 seconds (11.24 hours)\n\nTimestep: 9130000\nmean reward (100 episodes): 7651.1600\nbest mean reward: 7730.4000\ncurrent episode reward: 6810.0000\nepisodes: 3665\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40499.7 seconds (11.25 hours)\n\nTimestep: 9140000\nmean reward (100 episodes): 7687.2200\nbest mean reward: 7730.4000\ncurrent episode reward: 8148.0000\nepisodes: 3666\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40545.1 seconds (11.26 hours)\n\nTimestep: 9150000\nmean reward (100 episodes): 7675.5000\nbest mean reward: 7730.4000\ncurrent episode reward: 7152.0000\nepisodes: 3668\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40590.3 seconds (11.28 hours)\n\nTimestep: 9160000\nmean reward (100 episodes): 7722.7200\nbest mean reward: 7730.4000\ncurrent episode reward: 11328.0000\nepisodes: 3669\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40636.2 seconds (11.29 hours)\n\nTimestep: 9170000\nmean reward (100 episodes): 7757.9600\nbest mean reward: 7773.7200\ncurrent episode reward: 5216.0000\nepisodes: 3671\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40682.1 seconds (11.30 hours)\n\nTimestep: 9180000\nmean reward (100 episodes): 7747.5200\nbest mean reward: 7773.7200\ncurrent episode reward: 6822.0000\nepisodes: 3672\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40727.1 seconds (11.31 hours)\n\nTimestep: 9190000\nmean reward (100 episodes): 7770.5600\nbest mean reward: 7773.7200\ncurrent episode reward: 7920.0000\nepisodes: 3674\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40771.9 seconds (11.33 hours)\n\nTimestep: 9200000\nmean reward (100 episodes): 7771.0800\nbest mean reward: 7773.7200\ncurrent episode reward: 8002.0000\nepisodes: 3675\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40817.1 seconds (11.34 hours)\n\nTimestep: 9210000\nmean reward (100 episodes): 7814.9800\nbest mean reward: 7825.8000\ncurrent episode reward: 9850.0000\nepisodes: 3677\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40862.6 seconds (11.35 hours)\n\nTimestep: 9220000\nmean reward (100 episodes): 7807.2400\nbest mean reward: 7825.8000\ncurrent episode reward: 9356.0000\nepisodes: 3678\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40907.4 seconds (11.36 hours)\n\nTimestep: 9230000\nmean reward (100 episodes): 7824.9000\nbest mean reward: 7825.8000\ncurrent episode reward: 11346.0000\nepisodes: 3679\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40953.6 seconds (11.38 hours)\n\nTimestep: 9240000\nmean reward (100 episodes): 7845.0000\nbest mean reward: 7845.0000\ncurrent episode reward: 8832.0000\nepisodes: 3680\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40999.9 seconds (11.39 hours)\n\nTimestep: 9250000\nmean reward (100 episodes): 7895.1200\nbest mean reward: 7915.2600\ncurrent episode reward: 5760.0000\nepisodes: 3682\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41046.6 seconds (11.40 hours)\n\nTimestep: 9260000\nmean reward (100 episodes): 7824.3600\nbest mean reward: 7915.2600\ncurrent episode reward: 4020.0000\nepisodes: 3684\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41092.4 seconds (11.41 hours)\n\nTimestep: 9270000\nmean reward (100 episodes): 7845.7200\nbest mean reward: 7915.2600\ncurrent episode reward: 6600.0000\nepisodes: 3686\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41138.2 seconds (11.43 hours)\n\nTimestep: 9280000\nmean reward (100 episodes): 7814.7600\nbest mean reward: 7915.2600\ncurrent episode reward: 6444.0000\nepisodes: 3687\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41183.5 seconds (11.44 hours)\n\nTimestep: 9290000\nmean reward (100 episodes): 7827.4000\nbest mean reward: 7915.2600\ncurrent episode reward: 7942.0000\nepisodes: 3688\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41229.6 seconds (11.45 hours)\n\nTimestep: 9300000\nmean reward (100 episodes): 7892.1400\nbest mean reward: 7915.2600\ncurrent episode reward: 8208.0000\nepisodes: 3690\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41274.5 seconds (11.47 hours)\n\nTimestep: 9310000\nmean reward (100 episodes): 7923.0200\nbest mean reward: 7923.0200\ncurrent episode reward: 6384.0000\nepisodes: 3692\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41319.9 seconds (11.48 hours)\n\nTimestep: 9320000\nmean reward (100 episodes): 7915.9600\nbest mean reward: 7923.0200\ncurrent episode reward: 9266.0000\nepisodes: 3694\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41365.4 seconds (11.49 hours)\n\nTimestep: 9330000\nmean reward (100 episodes): 7881.8400\nbest mean reward: 7923.0200\ncurrent episode reward: 2832.0000\nepisodes: 3696\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41412.1 seconds (11.50 hours)\n\nTimestep: 9340000\nmean reward (100 episodes): 7834.6400\nbest mean reward: 7923.0200\ncurrent episode reward: 5310.0000\nepisodes: 3697\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41457.5 seconds (11.52 hours)\n\nTimestep: 9350000\nmean reward (100 episodes): 7923.0000\nbest mean reward: 7923.6000\ncurrent episode reward: 6330.0000\nepisodes: 3699\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41503.5 seconds (11.53 hours)\n\nTimestep: 9360000\nmean reward (100 episodes): 7876.2000\nbest mean reward: 7923.6000\ncurrent episode reward: 5922.0000\nepisodes: 3700\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41548.8 seconds (11.54 hours)\n\nTimestep: 9370000\nmean reward (100 episodes): 7924.8000\nbest mean reward: 7924.8000\ncurrent episode reward: 9090.0000\nepisodes: 3702\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41594.1 seconds (11.55 hours)\n\nTimestep: 9380000\nmean reward (100 episodes): 7923.9000\nbest mean reward: 7924.8000\ncurrent episode reward: 7380.0000\nepisodes: 3703\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41639.2 seconds (11.57 hours)\n\nTimestep: 9390000\nmean reward (100 episodes): 7983.4400\nbest mean reward: 7983.4400\ncurrent episode reward: 7314.0000\nepisodes: 3705\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41685.6 seconds (11.58 hours)\n\nTimestep: 9400000\nmean reward (100 episodes): 8004.8600\nbest mean reward: 8004.8600\ncurrent episode reward: 7260.0000\nepisodes: 3706\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41730.3 seconds (11.59 hours)\n\nTimestep: 9410000\nmean reward (100 episodes): 7971.7000\nbest mean reward: 8027.8800\ncurrent episode reward: 7820.0000\nepisodes: 3709\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41775.8 seconds (11.60 hours)\n\nTimestep: 9420000\nmean reward (100 episodes): 7971.7000\nbest mean reward: 8027.8800\ncurrent episode reward: 7820.0000\nepisodes: 3709\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41821.0 seconds (11.62 hours)\n\nTimestep: 9430000\nmean reward (100 episodes): 8016.4400\nbest mean reward: 8027.8800\ncurrent episode reward: 12060.0000\nepisodes: 3711\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41866.2 seconds (11.63 hours)\n\nTimestep: 9440000\nmean reward (100 episodes): 8087.1600\nbest mean reward: 8087.1600\ncurrent episode reward: 13304.0000\nepisodes: 3712\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41912.3 seconds (11.64 hours)\n\nTimestep: 9450000\nmean reward (100 episodes): 8147.3000\nbest mean reward: 8147.3000\ncurrent episode reward: 13460.0000\nepisodes: 3713\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41958.5 seconds (11.66 hours)\n\nTimestep: 9460000\nmean reward (100 episodes): 8186.5000\nbest mean reward: 8186.5000\ncurrent episode reward: 9200.0000\nepisodes: 3714\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42004.3 seconds (11.67 hours)\n\nTimestep: 9470000\nmean reward (100 episodes): 8217.9600\nbest mean reward: 8217.9600\ncurrent episode reward: 11088.0000\nepisodes: 3715\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42049.9 seconds (11.68 hours)\n\nTimestep: 9480000\nmean reward (100 episodes): 8218.5600\nbest mean reward: 8225.3000\ncurrent episode reward: 5954.0000\nepisodes: 3717\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42095.0 seconds (11.69 hours)\n\nTimestep: 9490000\nmean reward (100 episodes): 8166.4400\nbest mean reward: 8225.3000\ncurrent episode reward: 5828.0000\nepisodes: 3719\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42140.7 seconds (11.71 hours)\n\nTimestep: 9500000\nmean reward (100 episodes): 8189.6800\nbest mean reward: 8225.3000\ncurrent episode reward: 4156.0000\nepisodes: 3721\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42186.5 seconds (11.72 hours)\n\nTimestep: 9510000\nmean reward (100 episodes): 8176.8600\nbest mean reward: 8225.3000\ncurrent episode reward: 8518.0000\nepisodes: 3723\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42232.6 seconds (11.73 hours)\n\nTimestep: 9520000\nmean reward (100 episodes): 8190.6200\nbest mean reward: 8225.3000\ncurrent episode reward: 7488.0000\nepisodes: 3725\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42278.8 seconds (11.74 hours)\n\nTimestep: 9530000\nmean reward (100 episodes): 8190.6200\nbest mean reward: 8225.3000\ncurrent episode reward: 7488.0000\nepisodes: 3725\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42325.0 seconds (11.76 hours)\n\nTimestep: 9540000\nmean reward (100 episodes): 8311.3600\nbest mean reward: 8311.3600\ncurrent episode reward: 6096.0000\nepisodes: 3728\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42370.8 seconds (11.77 hours)\n\nTimestep: 9550000\nmean reward (100 episodes): 8305.6600\nbest mean reward: 8311.3600\ncurrent episode reward: 7188.0000\nepisodes: 3729\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42416.3 seconds (11.78 hours)\n\nTimestep: 9560000\nmean reward (100 episodes): 8392.5400\nbest mean reward: 8392.5400\ncurrent episode reward: 16392.0000\nepisodes: 3730\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42461.9 seconds (11.79 hours)\n\nTimestep: 9570000\nmean reward (100 episodes): 8423.2000\nbest mean reward: 8424.9400\ncurrent episode reward: 7224.0000\nepisodes: 3732\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42507.3 seconds (11.81 hours)\n\nTimestep: 9580000\nmean reward (100 episodes): 8081.9800\nbest mean reward: 8424.9400\ncurrent episode reward: 352.0000\nepisodes: 3737\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42552.6 seconds (11.82 hours)\n\nTimestep: 9590000\nmean reward (100 episodes): 7657.0800\nbest mean reward: 8424.9400\ncurrent episode reward: 440.0000\nepisodes: 3742\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42596.8 seconds (11.83 hours)\n\nTimestep: 9600000\nmean reward (100 episodes): 7534.4800\nbest mean reward: 8424.9400\ncurrent episode reward: 852.0000\nepisodes: 3744\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42642.6 seconds (11.85 hours)\n\nTimestep: 9610000\nmean reward (100 episodes): 7410.4600\nbest mean reward: 8424.9400\ncurrent episode reward: 4542.0000\nepisodes: 3747\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42687.6 seconds (11.86 hours)\n\nTimestep: 9620000\nmean reward (100 episodes): 7343.5400\nbest mean reward: 8424.9400\ncurrent episode reward: 4320.0000\nepisodes: 3749\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42733.5 seconds (11.87 hours)\n\nTimestep: 9630000\nmean reward (100 episodes): 7293.9400\nbest mean reward: 8424.9400\ncurrent episode reward: 6028.0000\nepisodes: 3751\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42779.0 seconds (11.88 hours)\n\nTimestep: 9640000\nmean reward (100 episodes): 7288.9000\nbest mean reward: 8424.9400\ncurrent episode reward: 8916.0000\nepisodes: 3753\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42824.7 seconds (11.90 hours)\n\nTimestep: 9650000\nmean reward (100 episodes): 7285.4600\nbest mean reward: 8424.9400\ncurrent episode reward: 8420.0000\nepisodes: 3754\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42871.2 seconds (11.91 hours)\n\nTimestep: 9660000\nmean reward (100 episodes): 7270.9200\nbest mean reward: 8424.9400\ncurrent episode reward: 5582.0000\nepisodes: 3756\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42915.7 seconds (11.92 hours)\n\nTimestep: 9670000\nmean reward (100 episodes): 7134.9800\nbest mean reward: 8424.9400\ncurrent episode reward: 6720.0000\nepisodes: 3758\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42960.7 seconds (11.93 hours)\n\nTimestep: 9680000\nmean reward (100 episodes): 7144.4000\nbest mean reward: 8424.9400\ncurrent episode reward: 5582.0000\nepisodes: 3760\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43005.7 seconds (11.95 hours)\n\nTimestep: 9690000\nmean reward (100 episodes): 7096.2800\nbest mean reward: 8424.9400\ncurrent episode reward: 7476.0000\nepisodes: 3762\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43051.0 seconds (11.96 hours)\n\nTimestep: 9700000\nmean reward (100 episodes): 7026.5800\nbest mean reward: 8424.9400\ncurrent episode reward: 5480.0000\nepisodes: 3764\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43096.8 seconds (11.97 hours)\n\nTimestep: 9710000\nmean reward (100 episodes): 7015.0800\nbest mean reward: 8424.9400\ncurrent episode reward: 4668.0000\nepisodes: 3766\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43142.1 seconds (11.98 hours)\n\nTimestep: 9720000\nmean reward (100 episodes): 7057.6800\nbest mean reward: 8424.9400\ncurrent episode reward: 11430.0000\nepisodes: 3767\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43188.0 seconds (12.00 hours)\n\nTimestep: 9730000\nmean reward (100 episodes): 6987.9600\nbest mean reward: 8424.9400\ncurrent episode reward: 5216.0000\nepisodes: 3769\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43232.9 seconds (12.01 hours)\n\nTimestep: 9740000\nmean reward (100 episodes): 6926.2600\nbest mean reward: 8424.9400\ncurrent episode reward: 3964.0000\nepisodes: 3771\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43278.8 seconds (12.02 hours)\n\nTimestep: 9750000\nmean reward (100 episodes): 6814.2200\nbest mean reward: 8424.9400\ncurrent episode reward: 3420.0000\nepisodes: 3774\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43324.6 seconds (12.03 hours)\n\nTimestep: 9760000\nmean reward (100 episodes): 6800.8000\nbest mean reward: 8424.9400\ncurrent episode reward: 6660.0000\nepisodes: 3775\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43370.5 seconds (12.05 hours)\n\nTimestep: 9770000\nmean reward (100 episodes): 6732.9600\nbest mean reward: 8424.9400\ncurrent episode reward: 7080.0000\nepisodes: 3777\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43415.4 seconds (12.06 hours)\n\nTimestep: 9780000\nmean reward (100 episodes): 6640.4200\nbest mean reward: 8424.9400\ncurrent episode reward: 4740.0000\nepisodes: 3779\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43461.2 seconds (12.07 hours)\n\nTimestep: 9790000\nmean reward (100 episodes): 6625.9000\nbest mean reward: 8424.9400\ncurrent episode reward: 7380.0000\nepisodes: 3780\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43506.5 seconds (12.09 hours)\n\nTimestep: 9800000\nmean reward (100 episodes): 6677.9000\nbest mean reward: 8424.9400\ncurrent episode reward: 9130.0000\nepisodes: 3782\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43552.4 seconds (12.10 hours)\n\nTimestep: 9810000\nmean reward (100 episodes): 6818.3000\nbest mean reward: 8424.9400\ncurrent episode reward: 18900.0000\nepisodes: 3783\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43598.5 seconds (12.11 hours)\n\nTimestep: 9820000\nmean reward (100 episodes): 6789.2800\nbest mean reward: 8424.9400\ncurrent episode reward: 4800.0000\nepisodes: 3785\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43643.1 seconds (12.12 hours)\n\nTimestep: 9830000\nmean reward (100 episodes): 6788.0600\nbest mean reward: 8424.9400\ncurrent episode reward: 6478.0000\nepisodes: 3786\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43688.4 seconds (12.14 hours)\n\nTimestep: 9840000\nmean reward (100 episodes): 6809.0600\nbest mean reward: 8424.9400\ncurrent episode reward: 5896.0000\nepisodes: 3788\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43734.1 seconds (12.15 hours)\n\nTimestep: 9850000\nmean reward (100 episodes): 6650.8000\nbest mean reward: 8424.9400\ncurrent episode reward: 3750.0000\nepisodes: 3790\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43779.4 seconds (12.16 hours)\n\nTimestep: 9860000\nmean reward (100 episodes): 6676.4400\nbest mean reward: 8424.9400\ncurrent episode reward: 9300.0000\nepisodes: 3792\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43824.3 seconds (12.17 hours)\n\nTimestep: 9870000\nmean reward (100 episodes): 6702.9000\nbest mean reward: 8424.9400\ncurrent episode reward: 8436.0000\nepisodes: 3793\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43869.7 seconds (12.19 hours)\n\nTimestep: 9880000\nmean reward (100 episodes): 6683.9800\nbest mean reward: 8424.9400\ncurrent episode reward: 5922.0000\nepisodes: 3795\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43914.7 seconds (12.20 hours)\n\nTimestep: 9890000\nmean reward (100 episodes): 6698.5400\nbest mean reward: 8424.9400\ncurrent episode reward: 2776.0000\nepisodes: 3797\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43959.3 seconds (12.21 hours)\n\nTimestep: 9900000\nmean reward (100 episodes): 6637.8800\nbest mean reward: 8424.9400\ncurrent episode reward: 6300.0000\nepisodes: 3799\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44004.5 seconds (12.22 hours)\n\nTimestep: 9910000\nmean reward (100 episodes): 6644.5400\nbest mean reward: 8424.9400\ncurrent episode reward: 10430.0000\nepisodes: 3801\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44050.3 seconds (12.24 hours)\n\nTimestep: 9920000\nmean reward (100 episodes): 6660.6400\nbest mean reward: 8424.9400\ncurrent episode reward: 10700.0000\nepisodes: 3802\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44095.8 seconds (12.25 hours)\n\nTimestep: 9930000\nmean reward (100 episodes): 6614.2000\nbest mean reward: 8424.9400\ncurrent episode reward: 6720.0000\nepisodes: 3804\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44140.3 seconds (12.26 hours)\n\nTimestep: 9935208\nmean reward (100 episodes): 6646.6600\nbest mean reward: 8424.9400\ncurrent episode reward: 10560.0000\nepisodes: 3805\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44163.9 seconds (12.27 hours)\n"
  },
  {
    "path": "dqn/logs_text/BeamRider_s002.text",
    "content": "('AVAILABLE GPUS: ', [u'device: 0, name: TITAN X (Pascal), pci bus id: 0000:01:00.0'])\ntask = Task<env_id=BeamRiderNoFrameskip-v3 trials=2 max_timesteps=40000000 max_seconds=None reward_floor=363.9 reward_ceiling=60000.0>\n\nTimestep: 60000\nmean reward (100 episodes): 361.7778\nbest mean reward: -inf\ncurrent episode reward: 220.0000\nepisodes: 45\nexploration: 0.94600\nlearning_rate: 0.00010\nelapsed time: 91.4 seconds (0.03 hours)\n\nTimestep: 70000\nmean reward (100 episodes): 367.2308\nbest mean reward: -inf\ncurrent episode reward: 220.0000\nepisodes: 52\nexploration: 0.93700\nlearning_rate: 0.00010\nelapsed time: 123.4 seconds (0.03 hours)\n\nTimestep: 80000\nmean reward (100 episodes): 367.6610\nbest mean reward: -inf\ncurrent episode reward: 352.0000\nepisodes: 59\nexploration: 0.92800\nlearning_rate: 0.00010\nelapsed time: 155.9 seconds (0.04 hours)\n\nTimestep: 90000\nmean reward (100 episodes): 368.4179\nbest mean reward: -inf\ncurrent episode reward: 440.0000\nepisodes: 67\nexploration: 0.91900\nlearning_rate: 0.00010\nelapsed time: 190.2 seconds (0.05 hours)\n\nTimestep: 100000\nmean reward (100 episodes): 361.9733\nbest mean reward: -inf\ncurrent episode reward: 176.0000\nepisodes: 75\nexploration: 0.91000\nlearning_rate: 0.00010\nelapsed time: 223.0 seconds (0.06 hours)\n\nTimestep: 110000\nmean reward (100 episodes): 363.8049\nbest mean reward: -inf\ncurrent episode reward: 440.0000\nepisodes: 82\nexploration: 0.90100\nlearning_rate: 0.00010\nelapsed time: 255.8 seconds (0.07 hours)\n\nTimestep: 120000\nmean reward (100 episodes): 356.8352\nbest mean reward: -inf\ncurrent episode reward: 308.0000\nepisodes: 91\nexploration: 0.89200\nlearning_rate: 0.00010\nelapsed time: 288.6 seconds (0.08 hours)\n\nTimestep: 130000\nmean reward (100 episodes): 360.0000\nbest mean reward: -inf\ncurrent episode reward: 132.0000\nepisodes: 99\nexploration: 0.88300\nlearning_rate: 0.00010\nelapsed time: 321.2 seconds (0.09 hours)\n\nTimestep: 140000\nmean reward (100 episodes): 361.6800\nbest mean reward: 362.5600\ncurrent episode reward: 440.0000\nepisodes: 107\nexploration: 0.87400\nlearning_rate: 0.00010\nelapsed time: 354.1 seconds (0.10 hours)\n\nTimestep: 150000\nmean reward (100 episodes): 370.4800\nbest mean reward: 371.3600\ncurrent episode reward: 132.0000\nepisodes: 114\nexploration: 0.86500\nlearning_rate: 0.00010\nelapsed time: 386.8 seconds (0.11 hours)\n\nTimestep: 160000\nmean reward (100 episodes): 371.3600\nbest mean reward: 373.1200\ncurrent episode reward: 352.0000\nepisodes: 121\nexploration: 0.85600\nlearning_rate: 0.00010\nelapsed time: 419.9 seconds (0.12 hours)\n\nTimestep: 170000\nmean reward (100 episodes): 374.8800\nbest mean reward: 374.8800\ncurrent episode reward: 308.0000\nepisodes: 127\nexploration: 0.84700\nlearning_rate: 0.00010\nelapsed time: 455.1 seconds (0.13 hours)\n\nTimestep: 180000\nmean reward (100 episodes): 372.2400\nbest mean reward: 376.2000\ncurrent episode reward: 264.0000\nepisodes: 135\nexploration: 0.83800\nlearning_rate: 0.00010\nelapsed time: 488.8 seconds (0.14 hours)\n\nTimestep: 190000\nmean reward (100 episodes): 367.8400\nbest mean reward: 376.2000\ncurrent episode reward: 308.0000\nepisodes: 144\nexploration: 0.82900\nlearning_rate: 0.00010\nelapsed time: 522.5 seconds (0.15 hours)\n\nTimestep: 200000\nmean reward (100 episodes): 360.8000\nbest mean reward: 376.2000\ncurrent episode reward: 352.0000\nepisodes: 152\nexploration: 0.82000\nlearning_rate: 0.00010\nelapsed time: 556.6 seconds (0.15 hours)\n\nTimestep: 210000\nmean reward (100 episodes): 367.4000\nbest mean reward: 376.2000\ncurrent episode reward: 352.0000\nepisodes: 159\nexploration: 0.81100\nlearning_rate: 0.00010\nelapsed time: 590.6 seconds (0.16 hours)\n\nTimestep: 220000\nmean reward (100 episodes): 372.6800\nbest mean reward: 376.2000\ncurrent episode reward: 220.0000\nepisodes: 166\nexploration: 0.80200\nlearning_rate: 0.00010\nelapsed time: 624.8 seconds (0.17 hours)\n\nTimestep: 230000\nmean reward (100 episodes): 385.0000\nbest mean reward: 385.0000\ncurrent episode reward: 616.0000\nepisodes: 172\nexploration: 0.79300\nlearning_rate: 0.00010\nelapsed time: 658.8 seconds (0.18 hours)\n\nTimestep: 240000\nmean reward (100 episodes): 379.7200\nbest mean reward: 389.4000\ncurrent episode reward: 176.0000\nepisodes: 179\nexploration: 0.78400\nlearning_rate: 0.00010\nelapsed time: 692.9 seconds (0.19 hours)\n\nTimestep: 250000\nmean reward (100 episodes): 389.8400\nbest mean reward: 389.8400\ncurrent episode reward: 352.0000\nepisodes: 186\nexploration: 0.77500\nlearning_rate: 0.00010\nelapsed time: 727.4 seconds (0.20 hours)\n\nTimestep: 260000\nmean reward (100 episodes): 385.0000\nbest mean reward: 389.8400\ncurrent episode reward: 396.0000\nepisodes: 194\nexploration: 0.76600\nlearning_rate: 0.00010\nelapsed time: 762.2 seconds (0.21 hours)\n\nTimestep: 270000\nmean reward (100 episodes): 384.1200\nbest mean reward: 389.8400\ncurrent episode reward: 396.0000\nepisodes: 203\nexploration: 0.75700\nlearning_rate: 0.00010\nelapsed time: 796.6 seconds (0.22 hours)\n\nTimestep: 280000\nmean reward (100 episodes): 377.0800\nbest mean reward: 389.8400\ncurrent episode reward: 308.0000\nepisodes: 210\nexploration: 0.74800\nlearning_rate: 0.00010\nelapsed time: 831.3 seconds (0.23 hours)\n\nTimestep: 290000\nmean reward (100 episodes): 375.3200\nbest mean reward: 389.8400\ncurrent episode reward: 308.0000\nepisodes: 217\nexploration: 0.73900\nlearning_rate: 0.00010\nelapsed time: 867.1 seconds (0.24 hours)\n\nTimestep: 300000\nmean reward (100 episodes): 366.9600\nbest mean reward: 389.8400\ncurrent episode reward: 396.0000\nepisodes: 225\nexploration: 0.73000\nlearning_rate: 0.00010\nelapsed time: 903.4 seconds (0.25 hours)\n\nTimestep: 310000\nmean reward (100 episodes): 363.8800\nbest mean reward: 389.8400\ncurrent episode reward: 440.0000\nepisodes: 232\nexploration: 0.72100\nlearning_rate: 0.00010\nelapsed time: 939.2 seconds (0.26 hours)\n\nTimestep: 320000\nmean reward (100 episodes): 359.9200\nbest mean reward: 389.8400\ncurrent episode reward: 396.0000\nepisodes: 241\nexploration: 0.71200\nlearning_rate: 0.00010\nelapsed time: 975.0 seconds (0.27 hours)\n\nTimestep: 330000\nmean reward (100 episodes): 365.6400\nbest mean reward: 389.8400\ncurrent episode reward: 440.0000\nepisodes: 248\nexploration: 0.70300\nlearning_rate: 0.00010\nelapsed time: 1011.1 seconds (0.28 hours)\n\nTimestep: 340000\nmean reward (100 episodes): 360.3600\nbest mean reward: 389.8400\ncurrent episode reward: 132.0000\nepisodes: 255\nexploration: 0.69400\nlearning_rate: 0.00010\nelapsed time: 1047.7 seconds (0.29 hours)\n\nTimestep: 350000\nmean reward (100 episodes): 345.8400\nbest mean reward: 389.8400\ncurrent episode reward: 484.0000\nepisodes: 264\nexploration: 0.68500\nlearning_rate: 0.00010\nelapsed time: 1083.8 seconds (0.30 hours)\n\nTimestep: 360000\nmean reward (100 episodes): 340.5600\nbest mean reward: 389.8400\ncurrent episode reward: 440.0000\nepisodes: 270\nexploration: 0.67600\nlearning_rate: 0.00010\nelapsed time: 1120.4 seconds (0.31 hours)\n\nTimestep: 370000\nmean reward (100 episodes): 333.9600\nbest mean reward: 389.8400\ncurrent episode reward: 484.0000\nepisodes: 277\nexploration: 0.66700\nlearning_rate: 0.00010\nelapsed time: 1156.4 seconds (0.32 hours)\n\nTimestep: 380000\nmean reward (100 episodes): 335.3200\nbest mean reward: 389.8400\ncurrent episode reward: 708.0000\nepisodes: 283\nexploration: 0.65800\nlearning_rate: 0.00010\nelapsed time: 1193.4 seconds (0.33 hours)\n\nTimestep: 390000\nmean reward (100 episodes): 346.3200\nbest mean reward: 389.8400\ncurrent episode reward: 660.0000\nepisodes: 290\nexploration: 0.64900\nlearning_rate: 0.00010\nelapsed time: 1229.9 seconds (0.34 hours)\n\nTimestep: 400000\nmean reward (100 episodes): 349.4000\nbest mean reward: 389.8400\ncurrent episode reward: 396.0000\nepisodes: 297\nexploration: 0.64000\nlearning_rate: 0.00010\nelapsed time: 1266.6 seconds (0.35 hours)\n\nTimestep: 410000\nmean reward (100 episodes): 341.4800\nbest mean reward: 389.8400\ncurrent episode reward: 484.0000\nepisodes: 304\nexploration: 0.63100\nlearning_rate: 0.00010\nelapsed time: 1303.1 seconds (0.36 hours)\n\nTimestep: 420000\nmean reward (100 episodes): 341.9200\nbest mean reward: 389.8400\ncurrent episode reward: 308.0000\nepisodes: 311\nexploration: 0.62200\nlearning_rate: 0.00010\nelapsed time: 1340.2 seconds (0.37 hours)\n\nTimestep: 430000\nmean reward (100 episodes): 345.4400\nbest mean reward: 389.8400\ncurrent episode reward: 440.0000\nepisodes: 319\nexploration: 0.61300\nlearning_rate: 0.00010\nelapsed time: 1377.9 seconds (0.38 hours)\n\nTimestep: 440000\nmean reward (100 episodes): 344.5600\nbest mean reward: 389.8400\ncurrent episode reward: 528.0000\nepisodes: 326\nexploration: 0.60400\nlearning_rate: 0.00010\nelapsed time: 1415.2 seconds (0.39 hours)\n\nTimestep: 450000\nmean reward (100 episodes): 353.8000\nbest mean reward: 389.8400\ncurrent episode reward: 308.0000\nepisodes: 333\nexploration: 0.59500\nlearning_rate: 0.00010\nelapsed time: 1452.9 seconds (0.40 hours)\n\nTimestep: 460000\nmean reward (100 episodes): 355.5600\nbest mean reward: 389.8400\ncurrent episode reward: 132.0000\nepisodes: 340\nexploration: 0.58600\nlearning_rate: 0.00010\nelapsed time: 1490.4 seconds (0.41 hours)\n\nTimestep: 470000\nmean reward (100 episodes): 349.8400\nbest mean reward: 389.8400\ncurrent episode reward: 264.0000\nepisodes: 347\nexploration: 0.57700\nlearning_rate: 0.00010\nelapsed time: 1529.3 seconds (0.42 hours)\n\nTimestep: 480000\nmean reward (100 episodes): 352.9200\nbest mean reward: 389.8400\ncurrent episode reward: 572.0000\nepisodes: 356\nexploration: 0.56800\nlearning_rate: 0.00010\nelapsed time: 1567.3 seconds (0.44 hours)\n\nTimestep: 490000\nmean reward (100 episodes): 356.0000\nbest mean reward: 389.8400\ncurrent episode reward: 220.0000\nepisodes: 363\nexploration: 0.55900\nlearning_rate: 0.00010\nelapsed time: 1606.0 seconds (0.45 hours)\n\nTimestep: 500000\nmean reward (100 episodes): 359.0800\nbest mean reward: 389.8400\ncurrent episode reward: 660.0000\nepisodes: 370\nexploration: 0.55000\nlearning_rate: 0.00010\nelapsed time: 1644.7 seconds (0.46 hours)\n\nTimestep: 510000\nmean reward (100 episodes): 360.8400\nbest mean reward: 389.8400\ncurrent episode reward: 308.0000\nepisodes: 376\nexploration: 0.54100\nlearning_rate: 0.00010\nelapsed time: 1683.6 seconds (0.47 hours)\n\nTimestep: 520000\nmean reward (100 episodes): 362.1200\nbest mean reward: 389.8400\ncurrent episode reward: 528.0000\nepisodes: 383\nexploration: 0.53200\nlearning_rate: 0.00010\nelapsed time: 1721.9 seconds (0.48 hours)\n\nTimestep: 530000\nmean reward (100 episodes): 342.3200\nbest mean reward: 389.8400\ncurrent episode reward: 308.0000\nepisodes: 391\nexploration: 0.52300\nlearning_rate: 0.00010\nelapsed time: 1760.1 seconds (0.49 hours)\n\nTimestep: 540000\nmean reward (100 episodes): 348.9200\nbest mean reward: 389.8400\ncurrent episode reward: 308.0000\nepisodes: 398\nexploration: 0.51400\nlearning_rate: 0.00010\nelapsed time: 1798.1 seconds (0.50 hours)\n\nTimestep: 550000\nmean reward (100 episodes): 355.0800\nbest mean reward: 389.8400\ncurrent episode reward: 396.0000\nepisodes: 404\nexploration: 0.50500\nlearning_rate: 0.00010\nelapsed time: 1836.8 seconds (0.51 hours)\n\nTimestep: 560000\nmean reward (100 episodes): 352.8800\nbest mean reward: 389.8400\ncurrent episode reward: 308.0000\nepisodes: 411\nexploration: 0.49600\nlearning_rate: 0.00010\nelapsed time: 1875.2 seconds (0.52 hours)\n\nTimestep: 570000\nmean reward (100 episodes): 348.0400\nbest mean reward: 389.8400\ncurrent episode reward: 176.0000\nepisodes: 417\nexploration: 0.48700\nlearning_rate: 0.00010\nelapsed time: 1914.3 seconds (0.53 hours)\n\nTimestep: 580000\nmean reward (100 episodes): 355.9600\nbest mean reward: 389.8400\ncurrent episode reward: 176.0000\nepisodes: 422\nexploration: 0.47800\nlearning_rate: 0.00010\nelapsed time: 1953.6 seconds (0.54 hours)\n\nTimestep: 590000\nmean reward (100 episodes): 355.0800\nbest mean reward: 389.8400\ncurrent episode reward: 176.0000\nepisodes: 429\nexploration: 0.46900\nlearning_rate: 0.00010\nelapsed time: 1992.2 seconds (0.55 hours)\n\nTimestep: 600000\nmean reward (100 episodes): 359.9200\nbest mean reward: 389.8400\ncurrent episode reward: 220.0000\nepisodes: 436\nexploration: 0.46000\nlearning_rate: 0.00010\nelapsed time: 2031.3 seconds (0.56 hours)\n\nTimestep: 610000\nmean reward (100 episodes): 361.2800\nbest mean reward: 389.8400\ncurrent episode reward: 220.0000\nepisodes: 442\nexploration: 0.45100\nlearning_rate: 0.00010\nelapsed time: 2070.5 seconds (0.58 hours)\n\nTimestep: 620000\nmean reward (100 episodes): 360.8400\nbest mean reward: 389.8400\ncurrent episode reward: 660.0000\nepisodes: 449\nexploration: 0.44200\nlearning_rate: 0.00010\nelapsed time: 2110.8 seconds (0.59 hours)\n\nTimestep: 630000\nmean reward (100 episodes): 368.7600\nbest mean reward: 389.8400\ncurrent episode reward: 220.0000\nepisodes: 455\nexploration: 0.43300\nlearning_rate: 0.00010\nelapsed time: 2150.5 seconds (0.60 hours)\n\nTimestep: 640000\nmean reward (100 episodes): 370.5200\nbest mean reward: 389.8400\ncurrent episode reward: 132.0000\nepisodes: 462\nexploration: 0.42400\nlearning_rate: 0.00010\nelapsed time: 2189.9 seconds (0.61 hours)\n\nTimestep: 650000\nmean reward (100 episodes): 373.2400\nbest mean reward: 389.8400\ncurrent episode reward: 132.0000\nepisodes: 469\nexploration: 0.41500\nlearning_rate: 0.00010\nelapsed time: 2230.1 seconds (0.62 hours)\n\nTimestep: 660000\nmean reward (100 episodes): 368.8400\nbest mean reward: 389.8400\ncurrent episode reward: 220.0000\nepisodes: 476\nexploration: 0.40600\nlearning_rate: 0.00010\nelapsed time: 2270.0 seconds (0.63 hours)\n\nTimestep: 670000\nmean reward (100 episodes): 364.8800\nbest mean reward: 389.8400\ncurrent episode reward: 176.0000\nepisodes: 483\nexploration: 0.39700\nlearning_rate: 0.00010\nelapsed time: 2310.2 seconds (0.64 hours)\n\nTimestep: 680000\nmean reward (100 episodes): 377.2000\nbest mean reward: 389.8400\ncurrent episode reward: 308.0000\nepisodes: 489\nexploration: 0.38800\nlearning_rate: 0.00010\nelapsed time: 2350.5 seconds (0.65 hours)\n\nTimestep: 690000\nmean reward (100 episodes): 382.9200\nbest mean reward: 389.8400\ncurrent episode reward: 352.0000\nepisodes: 496\nexploration: 0.37900\nlearning_rate: 0.00010\nelapsed time: 2390.2 seconds (0.66 hours)\n\nTimestep: 700000\nmean reward (100 episodes): 379.8400\nbest mean reward: 389.8400\ncurrent episode reward: 484.0000\nepisodes: 502\nexploration: 0.37000\nlearning_rate: 0.00010\nelapsed time: 2430.0 seconds (0.67 hours)\n\nTimestep: 710000\nmean reward (100 episodes): 380.7200\nbest mean reward: 389.8400\ncurrent episode reward: 132.0000\nepisodes: 508\nexploration: 0.36100\nlearning_rate: 0.00010\nelapsed time: 2470.0 seconds (0.69 hours)\n\nTimestep: 720000\nmean reward (100 episodes): 389.0800\nbest mean reward: 389.8400\ncurrent episode reward: 528.0000\nepisodes: 515\nexploration: 0.35200\nlearning_rate: 0.00010\nelapsed time: 2511.1 seconds (0.70 hours)\n\nTimestep: 730000\nmean reward (100 episodes): 387.3200\nbest mean reward: 390.8400\ncurrent episode reward: 220.0000\nepisodes: 522\nexploration: 0.34300\nlearning_rate: 0.00010\nelapsed time: 2552.1 seconds (0.71 hours)\n\nTimestep: 740000\nmean reward (100 episodes): 379.8400\nbest mean reward: 390.8400\ncurrent episode reward: 528.0000\nepisodes: 530\nexploration: 0.33400\nlearning_rate: 0.00010\nelapsed time: 2592.8 seconds (0.72 hours)\n\nTimestep: 750000\nmean reward (100 episodes): 376.3200\nbest mean reward: 390.8400\ncurrent episode reward: 352.0000\nepisodes: 536\nexploration: 0.32500\nlearning_rate: 0.00010\nelapsed time: 2633.4 seconds (0.73 hours)\n\nTimestep: 760000\nmean reward (100 episodes): 372.3200\nbest mean reward: 390.8400\ncurrent episode reward: 308.0000\nepisodes: 544\nexploration: 0.31600\nlearning_rate: 0.00010\nelapsed time: 2675.0 seconds (0.74 hours)\n\nTimestep: 770000\nmean reward (100 episodes): 366.6000\nbest mean reward: 390.8400\ncurrent episode reward: 440.0000\nepisodes: 552\nexploration: 0.30700\nlearning_rate: 0.00010\nelapsed time: 2717.4 seconds (0.75 hours)\n\nTimestep: 780000\nmean reward (100 episodes): 361.3200\nbest mean reward: 390.8400\ncurrent episode reward: 396.0000\nepisodes: 559\nexploration: 0.29800\nlearning_rate: 0.00010\nelapsed time: 2759.3 seconds (0.77 hours)\n\nTimestep: 790000\nmean reward (100 episodes): 359.5200\nbest mean reward: 390.8400\ncurrent episode reward: 660.0000\nepisodes: 565\nexploration: 0.28900\nlearning_rate: 0.00010\nelapsed time: 2801.2 seconds (0.78 hours)\n\nTimestep: 800000\nmean reward (100 episodes): 360.3600\nbest mean reward: 390.8400\ncurrent episode reward: 132.0000\nepisodes: 571\nexploration: 0.28000\nlearning_rate: 0.00010\nelapsed time: 2842.9 seconds (0.79 hours)\n\nTimestep: 810000\nmean reward (100 episodes): 355.0800\nbest mean reward: 390.8400\ncurrent episode reward: 44.0000\nepisodes: 579\nexploration: 0.27100\nlearning_rate: 0.00010\nelapsed time: 2885.3 seconds (0.80 hours)\n\nTimestep: 820000\nmean reward (100 episodes): 360.8000\nbest mean reward: 390.8400\ncurrent episode reward: 528.0000\nepisodes: 585\nexploration: 0.26200\nlearning_rate: 0.00010\nelapsed time: 2927.3 seconds (0.81 hours)\n\nTimestep: 830000\nmean reward (100 episodes): 356.4000\nbest mean reward: 390.8400\ncurrent episode reward: 264.0000\nepisodes: 591\nexploration: 0.25300\nlearning_rate: 0.00010\nelapsed time: 2969.4 seconds (0.82 hours)\n\nTimestep: 840000\nmean reward (100 episodes): 345.8400\nbest mean reward: 390.8400\ncurrent episode reward: 308.0000\nepisodes: 599\nexploration: 0.24400\nlearning_rate: 0.00010\nelapsed time: 3011.6 seconds (0.84 hours)\n\nTimestep: 850000\nmean reward (100 episodes): 336.6000\nbest mean reward: 390.8400\ncurrent episode reward: 176.0000\nepisodes: 605\nexploration: 0.23500\nlearning_rate: 0.00010\nelapsed time: 3053.6 seconds (0.85 hours)\n\nTimestep: 860000\nmean reward (100 episodes): 332.6400\nbest mean reward: 390.8400\ncurrent episode reward: 352.0000\nepisodes: 613\nexploration: 0.22600\nlearning_rate: 0.00010\nelapsed time: 3096.1 seconds (0.86 hours)\n\nTimestep: 870000\nmean reward (100 episodes): 327.8000\nbest mean reward: 390.8400\ncurrent episode reward: 440.0000\nepisodes: 620\nexploration: 0.21700\nlearning_rate: 0.00010\nelapsed time: 3138.8 seconds (0.87 hours)\n\nTimestep: 880000\nmean reward (100 episodes): 331.7600\nbest mean reward: 390.8400\ncurrent episode reward: 484.0000\nepisodes: 627\nexploration: 0.20800\nlearning_rate: 0.00010\nelapsed time: 3180.9 seconds (0.88 hours)\n\nTimestep: 890000\nmean reward (100 episodes): 332.2000\nbest mean reward: 390.8400\ncurrent episode reward: 660.0000\nepisodes: 633\nexploration: 0.19900\nlearning_rate: 0.00010\nelapsed time: 3223.5 seconds (0.90 hours)\n\nTimestep: 900000\nmean reward (100 episodes): 334.8400\nbest mean reward: 390.8400\ncurrent episode reward: 132.0000\nepisodes: 639\nexploration: 0.19000\nlearning_rate: 0.00010\nelapsed time: 3266.3 seconds (0.91 hours)\n\nTimestep: 910000\nmean reward (100 episodes): 337.4800\nbest mean reward: 390.8400\ncurrent episode reward: 352.0000\nepisodes: 645\nexploration: 0.18100\nlearning_rate: 0.00010\nelapsed time: 3308.9 seconds (0.92 hours)\n\nTimestep: 920000\nmean reward (100 episodes): 335.2800\nbest mean reward: 390.8400\ncurrent episode reward: 484.0000\nepisodes: 653\nexploration: 0.17200\nlearning_rate: 0.00010\nelapsed time: 3352.6 seconds (0.93 hours)\n\nTimestep: 930000\nmean reward (100 episodes): 332.6400\nbest mean reward: 390.8400\ncurrent episode reward: 660.0000\nepisodes: 660\nexploration: 0.16300\nlearning_rate: 0.00010\nelapsed time: 3395.7 seconds (0.94 hours)\n\nTimestep: 940000\nmean reward (100 episodes): 339.2800\nbest mean reward: 390.8400\ncurrent episode reward: 308.0000\nepisodes: 665\nexploration: 0.15400\nlearning_rate: 0.00010\nelapsed time: 3438.9 seconds (0.96 hours)\n\nTimestep: 950000\nmean reward (100 episodes): 341.9200\nbest mean reward: 390.8400\ncurrent episode reward: 484.0000\nepisodes: 670\nexploration: 0.14500\nlearning_rate: 0.00010\nelapsed time: 3481.7 seconds (0.97 hours)\n\nTimestep: 960000\nmean reward (100 episodes): 354.6800\nbest mean reward: 390.8400\ncurrent episode reward: 308.0000\nepisodes: 676\nexploration: 0.13600\nlearning_rate: 0.00010\nelapsed time: 3525.0 seconds (0.98 hours)\n\nTimestep: 970000\nmean reward (100 episodes): 356.0000\nbest mean reward: 390.8400\ncurrent episode reward: 352.0000\nepisodes: 683\nexploration: 0.12700\nlearning_rate: 0.00010\nelapsed time: 3568.0 seconds (0.99 hours)\n\nTimestep: 980000\nmean reward (100 episodes): 348.5200\nbest mean reward: 390.8400\ncurrent episode reward: 396.0000\nepisodes: 690\nexploration: 0.11800\nlearning_rate: 0.00010\nelapsed time: 3612.3 seconds (1.00 hours)\n\nTimestep: 990000\nmean reward (100 episodes): 358.6400\nbest mean reward: 390.8400\ncurrent episode reward: 132.0000\nepisodes: 697\nexploration: 0.10900\nlearning_rate: 0.00010\nelapsed time: 3656.2 seconds (1.02 hours)\n\nTimestep: 1000000\nmean reward (100 episodes): 358.6400\nbest mean reward: 390.8400\ncurrent episode reward: 264.0000\nepisodes: 703\nexploration: 0.10000\nlearning_rate: 0.00010\nelapsed time: 3700.5 seconds (1.03 hours)\n\nTimestep: 1010000\nmean reward (100 episodes): 362.6000\nbest mean reward: 390.8400\ncurrent episode reward: 528.0000\nepisodes: 710\nexploration: 0.09978\nlearning_rate: 0.00010\nelapsed time: 3744.9 seconds (1.04 hours)\n\nTimestep: 1020000\nmean reward (100 episodes): 362.1600\nbest mean reward: 390.8400\ncurrent episode reward: 616.0000\nepisodes: 717\nexploration: 0.09955\nlearning_rate: 0.00010\nelapsed time: 3788.4 seconds (1.05 hours)\n\nTimestep: 1030000\nmean reward (100 episodes): 360.8400\nbest mean reward: 390.8400\ncurrent episode reward: 176.0000\nepisodes: 723\nexploration: 0.09933\nlearning_rate: 0.00010\nelapsed time: 3832.9 seconds (1.06 hours)\n\nTimestep: 1040000\nmean reward (100 episodes): 365.2400\nbest mean reward: 390.8400\ncurrent episode reward: 660.0000\nepisodes: 730\nexploration: 0.09910\nlearning_rate: 0.00010\nelapsed time: 3878.5 seconds (1.08 hours)\n\nTimestep: 1050000\nmean reward (100 episodes): 356.8800\nbest mean reward: 390.8400\ncurrent episode reward: 264.0000\nepisodes: 737\nexploration: 0.09888\nlearning_rate: 0.00010\nelapsed time: 3923.4 seconds (1.09 hours)\n\nTimestep: 1060000\nmean reward (100 episodes): 353.8000\nbest mean reward: 390.8400\ncurrent episode reward: 264.0000\nepisodes: 744\nexploration: 0.09865\nlearning_rate: 0.00010\nelapsed time: 3967.9 seconds (1.10 hours)\n\nTimestep: 1070000\nmean reward (100 episodes): 364.8000\nbest mean reward: 390.8400\ncurrent episode reward: 440.0000\nepisodes: 751\nexploration: 0.09842\nlearning_rate: 0.00010\nelapsed time: 4012.0 seconds (1.11 hours)\n\nTimestep: 1080000\nmean reward (100 episodes): 368.3200\nbest mean reward: 390.8400\ncurrent episode reward: 308.0000\nepisodes: 756\nexploration: 0.09820\nlearning_rate: 0.00010\nelapsed time: 4056.2 seconds (1.13 hours)\n\nTimestep: 1090000\nmean reward (100 episodes): 361.2400\nbest mean reward: 390.8400\ncurrent episode reward: 264.0000\nepisodes: 763\nexploration: 0.09798\nlearning_rate: 0.00010\nelapsed time: 4100.6 seconds (1.14 hours)\n\nTimestep: 1100000\nmean reward (100 episodes): 355.9600\nbest mean reward: 390.8400\ncurrent episode reward: 440.0000\nepisodes: 769\nexploration: 0.09775\nlearning_rate: 0.00010\nelapsed time: 4145.4 seconds (1.15 hours)\n\nTimestep: 1110000\nmean reward (100 episodes): 351.5600\nbest mean reward: 390.8400\ncurrent episode reward: 176.0000\nepisodes: 776\nexploration: 0.09753\nlearning_rate: 0.00010\nelapsed time: 4189.8 seconds (1.16 hours)\n\nTimestep: 1120000\nmean reward (100 episodes): 356.8400\nbest mean reward: 390.8400\ncurrent episode reward: 484.0000\nepisodes: 782\nexploration: 0.09730\nlearning_rate: 0.00010\nelapsed time: 4234.1 seconds (1.18 hours)\n\nTimestep: 1130000\nmean reward (100 episodes): 362.1200\nbest mean reward: 390.8400\ncurrent episode reward: 616.0000\nepisodes: 788\nexploration: 0.09708\nlearning_rate: 0.00010\nelapsed time: 4278.5 seconds (1.19 hours)\n\nTimestep: 1140000\nmean reward (100 episodes): 356.4000\nbest mean reward: 390.8400\ncurrent episode reward: 572.0000\nepisodes: 794\nexploration: 0.09685\nlearning_rate: 0.00010\nelapsed time: 4323.0 seconds (1.20 hours)\n\nTimestep: 1150000\nmean reward (100 episodes): 359.9200\nbest mean reward: 390.8400\ncurrent episode reward: 44.0000\nepisodes: 800\nexploration: 0.09663\nlearning_rate: 0.00010\nelapsed time: 4367.5 seconds (1.21 hours)\n\nTimestep: 1160000\nmean reward (100 episodes): 373.1200\nbest mean reward: 390.8400\ncurrent episode reward: 352.0000\nepisodes: 807\nexploration: 0.09640\nlearning_rate: 0.00010\nelapsed time: 4412.3 seconds (1.23 hours)\n\nTimestep: 1170000\nmean reward (100 episodes): 369.6000\nbest mean reward: 390.8400\ncurrent episode reward: 264.0000\nepisodes: 814\nexploration: 0.09618\nlearning_rate: 0.00010\nelapsed time: 4457.1 seconds (1.24 hours)\n\nTimestep: 1180000\nmean reward (100 episodes): 370.9200\nbest mean reward: 390.8400\ncurrent episode reward: 308.0000\nepisodes: 819\nexploration: 0.09595\nlearning_rate: 0.00010\nelapsed time: 4501.7 seconds (1.25 hours)\n\nTimestep: 1190000\nmean reward (100 episodes): 381.9200\nbest mean reward: 390.8400\ncurrent episode reward: 484.0000\nepisodes: 825\nexploration: 0.09573\nlearning_rate: 0.00010\nelapsed time: 4546.8 seconds (1.26 hours)\n\nTimestep: 1200000\nmean reward (100 episodes): 370.0400\nbest mean reward: 390.8400\ncurrent episode reward: 88.0000\nepisodes: 833\nexploration: 0.09550\nlearning_rate: 0.00010\nelapsed time: 4590.6 seconds (1.28 hours)\n\nTimestep: 1210000\nmean reward (100 episodes): 381.0400\nbest mean reward: 390.8400\ncurrent episode reward: 660.0000\nepisodes: 839\nexploration: 0.09527\nlearning_rate: 0.00010\nelapsed time: 4635.1 seconds (1.29 hours)\n\nTimestep: 1220000\nmean reward (100 episodes): 389.8400\nbest mean reward: 390.8400\ncurrent episode reward: 660.0000\nepisodes: 844\nexploration: 0.09505\nlearning_rate: 0.00010\nelapsed time: 4678.8 seconds (1.30 hours)\n\nTimestep: 1230000\nmean reward (100 episodes): 399.5600\nbest mean reward: 401.3200\ncurrent episode reward: 484.0000\nepisodes: 850\nexploration: 0.09483\nlearning_rate: 0.00010\nelapsed time: 4724.3 seconds (1.31 hours)\n\nTimestep: 1240000\nmean reward (100 episodes): 399.1200\nbest mean reward: 401.3200\ncurrent episode reward: 440.0000\nepisodes: 856\nexploration: 0.09460\nlearning_rate: 0.00010\nelapsed time: 4768.8 seconds (1.32 hours)\n\nTimestep: 1250000\nmean reward (100 episodes): 391.2000\nbest mean reward: 401.3200\ncurrent episode reward: 132.0000\nepisodes: 863\nexploration: 0.09438\nlearning_rate: 0.00010\nelapsed time: 4812.5 seconds (1.34 hours)\n\nTimestep: 1260000\nmean reward (100 episodes): 392.9600\nbest mean reward: 401.3200\ncurrent episode reward: 264.0000\nepisodes: 869\nexploration: 0.09415\nlearning_rate: 0.00010\nelapsed time: 4856.9 seconds (1.35 hours)\n\nTimestep: 1270000\nmean reward (100 episodes): 396.0400\nbest mean reward: 401.3200\ncurrent episode reward: 176.0000\nepisodes: 875\nexploration: 0.09393\nlearning_rate: 0.00010\nelapsed time: 4902.2 seconds (1.36 hours)\n\nTimestep: 1280000\nmean reward (100 episodes): 396.4800\nbest mean reward: 401.3200\ncurrent episode reward: 528.0000\nepisodes: 881\nexploration: 0.09370\nlearning_rate: 0.00010\nelapsed time: 4947.1 seconds (1.37 hours)\n\nTimestep: 1290000\nmean reward (100 episodes): 398.8000\nbest mean reward: 402.3200\ncurrent episode reward: 176.0000\nepisodes: 887\nexploration: 0.09348\nlearning_rate: 0.00010\nelapsed time: 4991.5 seconds (1.39 hours)\n\nTimestep: 1300000\nmean reward (100 episodes): 404.5200\nbest mean reward: 404.5200\ncurrent episode reward: 528.0000\nepisodes: 892\nexploration: 0.09325\nlearning_rate: 0.00010\nelapsed time: 5036.2 seconds (1.40 hours)\n\nTimestep: 1310000\nmean reward (100 episodes): 410.8000\nbest mean reward: 410.8000\ncurrent episode reward: 804.0000\nepisodes: 897\nexploration: 0.09303\nlearning_rate: 0.00010\nelapsed time: 5079.8 seconds (1.41 hours)\n\nTimestep: 1320000\nmean reward (100 episodes): 423.1200\nbest mean reward: 423.1200\ncurrent episode reward: 616.0000\nepisodes: 902\nexploration: 0.09280\nlearning_rate: 0.00010\nelapsed time: 5124.2 seconds (1.42 hours)\n\nTimestep: 1330000\nmean reward (100 episodes): 430.2000\nbest mean reward: 430.2000\ncurrent episode reward: 660.0000\nepisodes: 908\nexploration: 0.09258\nlearning_rate: 0.00010\nelapsed time: 5167.8 seconds (1.44 hours)\n\nTimestep: 1340000\nmean reward (100 episodes): 431.9600\nbest mean reward: 431.9600\ncurrent episode reward: 440.0000\nepisodes: 914\nexploration: 0.09235\nlearning_rate: 0.00010\nelapsed time: 5212.5 seconds (1.45 hours)\n\nTimestep: 1350000\nmean reward (100 episodes): 423.1600\nbest mean reward: 431.9600\ncurrent episode reward: 308.0000\nepisodes: 921\nexploration: 0.09213\nlearning_rate: 0.00010\nelapsed time: 5255.6 seconds (1.46 hours)\n\nTimestep: 1360000\nmean reward (100 episodes): 428.0800\nbest mean reward: 431.9600\ncurrent episode reward: 308.0000\nepisodes: 927\nexploration: 0.09190\nlearning_rate: 0.00010\nelapsed time: 5300.2 seconds (1.47 hours)\n\nTimestep: 1370000\nmean reward (100 episodes): 439.0800\nbest mean reward: 439.9600\ncurrent episode reward: 308.0000\nepisodes: 933\nexploration: 0.09168\nlearning_rate: 0.00010\nelapsed time: 5344.7 seconds (1.48 hours)\n\nTimestep: 1380000\nmean reward (100 episodes): 439.9600\nbest mean reward: 442.1600\ncurrent episode reward: 396.0000\nepisodes: 938\nexploration: 0.09145\nlearning_rate: 0.00010\nelapsed time: 5389.3 seconds (1.50 hours)\n\nTimestep: 1390000\nmean reward (100 episodes): 444.8400\nbest mean reward: 447.9200\ncurrent episode reward: 528.0000\nepisodes: 944\nexploration: 0.09123\nlearning_rate: 0.00010\nelapsed time: 5432.8 seconds (1.51 hours)\n\nTimestep: 1400000\nmean reward (100 episodes): 438.2000\nbest mean reward: 447.9200\ncurrent episode reward: 440.0000\nepisodes: 949\nexploration: 0.09100\nlearning_rate: 0.00010\nelapsed time: 5475.9 seconds (1.52 hours)\n\nTimestep: 1410000\nmean reward (100 episodes): 444.4000\nbest mean reward: 447.9200\ncurrent episode reward: 352.0000\nepisodes: 955\nexploration: 0.09078\nlearning_rate: 0.00009\nelapsed time: 5519.5 seconds (1.53 hours)\n\nTimestep: 1420000\nmean reward (100 episodes): 457.6000\nbest mean reward: 457.6000\ncurrent episode reward: 660.0000\nepisodes: 961\nexploration: 0.09055\nlearning_rate: 0.00009\nelapsed time: 5563.3 seconds (1.55 hours)\n\nTimestep: 1430000\nmean reward (100 episodes): 454.9600\nbest mean reward: 459.8000\ncurrent episode reward: 352.0000\nepisodes: 968\nexploration: 0.09033\nlearning_rate: 0.00009\nelapsed time: 5607.2 seconds (1.56 hours)\n\nTimestep: 1440000\nmean reward (100 episodes): 460.3200\nbest mean reward: 460.3200\ncurrent episode reward: 660.0000\nepisodes: 974\nexploration: 0.09010\nlearning_rate: 0.00009\nelapsed time: 5651.7 seconds (1.57 hours)\n\nTimestep: 1450000\nmean reward (100 episodes): 472.2400\nbest mean reward: 472.2400\ncurrent episode reward: 396.0000\nepisodes: 980\nexploration: 0.08988\nlearning_rate: 0.00009\nelapsed time: 5695.7 seconds (1.58 hours)\n\nTimestep: 1460000\nmean reward (100 episodes): 478.4800\nbest mean reward: 478.4800\ncurrent episode reward: 756.0000\nepisodes: 984\nexploration: 0.08965\nlearning_rate: 0.00009\nelapsed time: 5740.8 seconds (1.59 hours)\n\nTimestep: 1470000\nmean reward (100 episodes): 484.0800\nbest mean reward: 484.0800\ncurrent episode reward: 484.0000\nepisodes: 990\nexploration: 0.08943\nlearning_rate: 0.00009\nelapsed time: 5785.5 seconds (1.61 hours)\n\nTimestep: 1480000\nmean reward (100 episodes): 489.3600\nbest mean reward: 489.3600\ncurrent episode reward: 660.0000\nepisodes: 995\nexploration: 0.08920\nlearning_rate: 0.00009\nelapsed time: 5830.1 seconds (1.62 hours)\n\nTimestep: 1490000\nmean reward (100 episodes): 489.3600\nbest mean reward: 489.8000\ncurrent episode reward: 804.0000\nepisodes: 1000\nexploration: 0.08897\nlearning_rate: 0.00009\nelapsed time: 5875.0 seconds (1.63 hours)\n\nTimestep: 1500000\nmean reward (100 episodes): 499.6000\nbest mean reward: 499.6000\ncurrent episode reward: 660.0000\nepisodes: 1004\nexploration: 0.08875\nlearning_rate: 0.00009\nelapsed time: 5920.5 seconds (1.64 hours)\n\nTimestep: 1510000\nmean reward (100 episodes): 498.3600\nbest mean reward: 501.0000\ncurrent episode reward: 396.0000\nepisodes: 1009\nexploration: 0.08853\nlearning_rate: 0.00009\nelapsed time: 5964.8 seconds (1.66 hours)\n\nTimestep: 1520000\nmean reward (100 episodes): 509.9200\nbest mean reward: 509.9200\ncurrent episode reward: 484.0000\nepisodes: 1015\nexploration: 0.08830\nlearning_rate: 0.00009\nelapsed time: 6009.3 seconds (1.67 hours)\n\nTimestep: 1530000\nmean reward (100 episodes): 517.2000\nbest mean reward: 522.4800\ncurrent episode reward: 132.0000\nepisodes: 1020\nexploration: 0.08808\nlearning_rate: 0.00009\nelapsed time: 6054.2 seconds (1.68 hours)\n\nTimestep: 1540000\nmean reward (100 episodes): 523.7200\nbest mean reward: 524.6800\ncurrent episode reward: 660.0000\nepisodes: 1025\nexploration: 0.08785\nlearning_rate: 0.00009\nelapsed time: 6098.8 seconds (1.69 hours)\n\nTimestep: 1550000\nmean reward (100 episodes): 531.4800\nbest mean reward: 531.4800\ncurrent episode reward: 900.0000\nepisodes: 1028\nexploration: 0.08763\nlearning_rate: 0.00009\nelapsed time: 6143.1 seconds (1.71 hours)\n\nTimestep: 1560000\nmean reward (100 episodes): 544.9200\nbest mean reward: 545.8000\ncurrent episode reward: 220.0000\nepisodes: 1033\nexploration: 0.08740\nlearning_rate: 0.00009\nelapsed time: 6187.2 seconds (1.72 hours)\n\nTimestep: 1570000\nmean reward (100 episodes): 548.1600\nbest mean reward: 549.9200\ncurrent episode reward: 528.0000\nepisodes: 1038\nexploration: 0.08718\nlearning_rate: 0.00009\nelapsed time: 6231.4 seconds (1.73 hours)\n\nTimestep: 1580000\nmean reward (100 episodes): 549.4400\nbest mean reward: 549.9200\ncurrent episode reward: 660.0000\nepisodes: 1043\nexploration: 0.08695\nlearning_rate: 0.00009\nelapsed time: 6275.6 seconds (1.74 hours)\n\nTimestep: 1590000\nmean reward (100 episodes): 551.7200\nbest mean reward: 553.4800\ncurrent episode reward: 352.0000\nepisodes: 1049\nexploration: 0.08673\nlearning_rate: 0.00009\nelapsed time: 6319.2 seconds (1.76 hours)\n\nTimestep: 1600000\nmean reward (100 episodes): 551.4400\nbest mean reward: 553.6400\ncurrent episode reward: 352.0000\nepisodes: 1054\nexploration: 0.08650\nlearning_rate: 0.00009\nelapsed time: 6363.8 seconds (1.77 hours)\n\nTimestep: 1610000\nmean reward (100 episodes): 558.4800\nbest mean reward: 558.4800\ncurrent episode reward: 660.0000\nepisodes: 1058\nexploration: 0.08628\nlearning_rate: 0.00009\nelapsed time: 6407.8 seconds (1.78 hours)\n\nTimestep: 1620000\nmean reward (100 episodes): 574.2000\nbest mean reward: 574.2000\ncurrent episode reward: 660.0000\nepisodes: 1062\nexploration: 0.08605\nlearning_rate: 0.00009\nelapsed time: 6451.9 seconds (1.79 hours)\n\nTimestep: 1630000\nmean reward (100 episodes): 592.3600\nbest mean reward: 592.3600\ncurrent episode reward: 708.0000\nepisodes: 1067\nexploration: 0.08582\nlearning_rate: 0.00009\nelapsed time: 6496.5 seconds (1.80 hours)\n\nTimestep: 1640000\nmean reward (100 episodes): 593.1600\nbest mean reward: 595.4400\ncurrent episode reward: 396.0000\nepisodes: 1071\nexploration: 0.08560\nlearning_rate: 0.00009\nelapsed time: 6540.7 seconds (1.82 hours)\n\nTimestep: 1650000\nmean reward (100 episodes): 605.2800\nbest mean reward: 605.2800\ncurrent episode reward: 900.0000\nepisodes: 1074\nexploration: 0.08538\nlearning_rate: 0.00009\nelapsed time: 6585.0 seconds (1.83 hours)\n\nTimestep: 1660000\nmean reward (100 episodes): 619.2000\nbest mean reward: 619.2000\ncurrent episode reward: 1140.0000\nepisodes: 1078\nexploration: 0.08515\nlearning_rate: 0.00009\nelapsed time: 6629.6 seconds (1.84 hours)\n\nTimestep: 1670000\nmean reward (100 episodes): 621.8400\nbest mean reward: 623.6000\ncurrent episode reward: 528.0000\nepisodes: 1083\nexploration: 0.08493\nlearning_rate: 0.00009\nelapsed time: 6674.7 seconds (1.85 hours)\n\nTimestep: 1680000\nmean reward (100 episodes): 626.4000\nbest mean reward: 627.7200\ncurrent episode reward: 660.0000\nepisodes: 1088\nexploration: 0.08470\nlearning_rate: 0.00009\nelapsed time: 6719.5 seconds (1.87 hours)\n\nTimestep: 1690000\nmean reward (100 episodes): 622.8800\nbest mean reward: 627.7200\ncurrent episode reward: 572.0000\nepisodes: 1093\nexploration: 0.08448\nlearning_rate: 0.00009\nelapsed time: 6764.0 seconds (1.88 hours)\n\nTimestep: 1700000\nmean reward (100 episodes): 626.2400\nbest mean reward: 627.7200\ncurrent episode reward: 852.0000\nepisodes: 1096\nexploration: 0.08425\nlearning_rate: 0.00009\nelapsed time: 6808.5 seconds (1.89 hours)\n\nTimestep: 1710000\nmean reward (100 episodes): 623.7600\nbest mean reward: 631.8000\ncurrent episode reward: 616.0000\nepisodes: 1101\nexploration: 0.08403\nlearning_rate: 0.00009\nelapsed time: 6853.0 seconds (1.90 hours)\n\nTimestep: 1720000\nmean reward (100 episodes): 625.6000\nbest mean reward: 631.8000\ncurrent episode reward: 440.0000\nepisodes: 1107\nexploration: 0.08380\nlearning_rate: 0.00009\nelapsed time: 6897.3 seconds (1.92 hours)\n\nTimestep: 1730000\nmean reward (100 episodes): 632.6400\nbest mean reward: 632.6400\ncurrent episode reward: 852.0000\nepisodes: 1111\nexploration: 0.08358\nlearning_rate: 0.00009\nelapsed time: 6941.9 seconds (1.93 hours)\n\nTimestep: 1740000\nmean reward (100 episodes): 629.8800\nbest mean reward: 632.6400\ncurrent episode reward: 660.0000\nepisodes: 1115\nexploration: 0.08335\nlearning_rate: 0.00009\nelapsed time: 6985.8 seconds (1.94 hours)\n\nTimestep: 1750000\nmean reward (100 episodes): 639.2800\nbest mean reward: 639.2800\ncurrent episode reward: 484.0000\nepisodes: 1119\nexploration: 0.08313\nlearning_rate: 0.00009\nelapsed time: 7030.4 seconds (1.95 hours)\n\nTimestep: 1760000\nmean reward (100 episodes): 651.2800\nbest mean reward: 651.2800\ncurrent episode reward: 1044.0000\nepisodes: 1124\nexploration: 0.08290\nlearning_rate: 0.00009\nelapsed time: 7074.4 seconds (1.97 hours)\n\nTimestep: 1770000\nmean reward (100 episodes): 655.1200\nbest mean reward: 655.6000\ncurrent episode reward: 948.0000\nepisodes: 1128\nexploration: 0.08267\nlearning_rate: 0.00009\nelapsed time: 7118.6 seconds (1.98 hours)\n\nTimestep: 1780000\nmean reward (100 episodes): 657.2400\nbest mean reward: 659.4400\ncurrent episode reward: 440.0000\nepisodes: 1132\nexploration: 0.08245\nlearning_rate: 0.00009\nelapsed time: 7163.6 seconds (1.99 hours)\n\nTimestep: 1790000\nmean reward (100 episodes): 666.4000\nbest mean reward: 666.4000\ncurrent episode reward: 1236.0000\nepisodes: 1136\nexploration: 0.08223\nlearning_rate: 0.00009\nelapsed time: 7208.0 seconds (2.00 hours)\n\nTimestep: 1800000\nmean reward (100 episodes): 673.5200\nbest mean reward: 673.5200\ncurrent episode reward: 756.0000\nepisodes: 1140\nexploration: 0.08200\nlearning_rate: 0.00009\nelapsed time: 7253.1 seconds (2.01 hours)\n\nTimestep: 1810000\nmean reward (100 episodes): 685.4400\nbest mean reward: 685.4400\ncurrent episode reward: 1380.0000\nepisodes: 1144\nexploration: 0.08178\nlearning_rate: 0.00009\nelapsed time: 7296.9 seconds (2.03 hours)\n\nTimestep: 1820000\nmean reward (100 episodes): 698.2800\nbest mean reward: 698.2800\ncurrent episode reward: 804.0000\nepisodes: 1148\nexploration: 0.08155\nlearning_rate: 0.00009\nelapsed time: 7341.3 seconds (2.04 hours)\n\nTimestep: 1830000\nmean reward (100 episodes): 702.9600\nbest mean reward: 702.9600\ncurrent episode reward: 352.0000\nepisodes: 1154\nexploration: 0.08133\nlearning_rate: 0.00009\nelapsed time: 7386.0 seconds (2.05 hours)\n\nTimestep: 1840000\nmean reward (100 episodes): 689.9200\nbest mean reward: 702.9600\ncurrent episode reward: 660.0000\nepisodes: 1160\nexploration: 0.08110\nlearning_rate: 0.00009\nelapsed time: 7430.3 seconds (2.06 hours)\n\nTimestep: 1850000\nmean reward (100 episodes): 684.6000\nbest mean reward: 702.9600\ncurrent episode reward: 660.0000\nepisodes: 1164\nexploration: 0.08088\nlearning_rate: 0.00009\nelapsed time: 7474.5 seconds (2.08 hours)\n\nTimestep: 1860000\nmean reward (100 episodes): 686.5200\nbest mean reward: 702.9600\ncurrent episode reward: 852.0000\nepisodes: 1167\nexploration: 0.08065\nlearning_rate: 0.00009\nelapsed time: 7519.1 seconds (2.09 hours)\n\nTimestep: 1870000\nmean reward (100 episodes): 692.8000\nbest mean reward: 702.9600\ncurrent episode reward: 308.0000\nepisodes: 1172\nexploration: 0.08042\nlearning_rate: 0.00009\nelapsed time: 7563.0 seconds (2.10 hours)\n\nTimestep: 1880000\nmean reward (100 episodes): 692.8000\nbest mean reward: 702.9600\ncurrent episode reward: 756.0000\nepisodes: 1175\nexploration: 0.08020\nlearning_rate: 0.00009\nelapsed time: 7607.5 seconds (2.11 hours)\n\nTimestep: 1890000\nmean reward (100 episodes): 694.8400\nbest mean reward: 704.9200\ncurrent episode reward: 396.0000\nepisodes: 1179\nexploration: 0.07998\nlearning_rate: 0.00009\nelapsed time: 7651.8 seconds (2.13 hours)\n\nTimestep: 1900000\nmean reward (100 episodes): 703.6400\nbest mean reward: 704.9200\ncurrent episode reward: 756.0000\nepisodes: 1183\nexploration: 0.07975\nlearning_rate: 0.00009\nelapsed time: 7696.3 seconds (2.14 hours)\n\nTimestep: 1910000\nmean reward (100 episodes): 712.0400\nbest mean reward: 712.0400\ncurrent episode reward: 756.0000\nepisodes: 1186\nexploration: 0.07952\nlearning_rate: 0.00009\nelapsed time: 7740.2 seconds (2.15 hours)\n\nTimestep: 1920000\nmean reward (100 episodes): 735.4000\nbest mean reward: 735.4000\ncurrent episode reward: 2108.0000\nepisodes: 1189\nexploration: 0.07930\nlearning_rate: 0.00009\nelapsed time: 7783.8 seconds (2.16 hours)\n\nTimestep: 1930000\nmean reward (100 episodes): 752.8000\nbest mean reward: 752.8000\ncurrent episode reward: 440.0000\nepisodes: 1192\nexploration: 0.07908\nlearning_rate: 0.00009\nelapsed time: 7828.0 seconds (2.17 hours)\n\nTimestep: 1940000\nmean reward (100 episodes): 763.7600\nbest mean reward: 764.2400\ncurrent episode reward: 756.0000\nepisodes: 1195\nexploration: 0.07885\nlearning_rate: 0.00009\nelapsed time: 7872.6 seconds (2.19 hours)\n\nTimestep: 1950000\nmean reward (100 episodes): 778.1600\nbest mean reward: 778.1600\ncurrent episode reward: 1092.0000\nepisodes: 1199\nexploration: 0.07863\nlearning_rate: 0.00009\nelapsed time: 7916.7 seconds (2.20 hours)\n\nTimestep: 1960000\nmean reward (100 episodes): 783.3600\nbest mean reward: 784.7600\ncurrent episode reward: 528.0000\nepisodes: 1203\nexploration: 0.07840\nlearning_rate: 0.00009\nelapsed time: 7960.6 seconds (2.21 hours)\n\nTimestep: 1970000\nmean reward (100 episodes): 794.5600\nbest mean reward: 794.5600\ncurrent episode reward: 1588.0000\nepisodes: 1205\nexploration: 0.07818\nlearning_rate: 0.00009\nelapsed time: 8005.3 seconds (2.22 hours)\n\nTimestep: 1980000\nmean reward (100 episodes): 810.0400\nbest mean reward: 810.0400\ncurrent episode reward: 1380.0000\nepisodes: 1208\nexploration: 0.07795\nlearning_rate: 0.00009\nelapsed time: 8049.2 seconds (2.24 hours)\n\nTimestep: 1990000\nmean reward (100 episodes): 816.0000\nbest mean reward: 816.0000\ncurrent episode reward: 1380.0000\nepisodes: 1211\nexploration: 0.07773\nlearning_rate: 0.00009\nelapsed time: 8093.7 seconds (2.25 hours)\n\nTimestep: 2000000\nmean reward (100 episodes): 833.0400\nbest mean reward: 833.0400\ncurrent episode reward: 1380.0000\nepisodes: 1215\nexploration: 0.07750\nlearning_rate: 0.00009\nelapsed time: 8138.0 seconds (2.26 hours)\n\nTimestep: 2010000\nmean reward (100 episodes): 832.4000\nbest mean reward: 833.0400\ncurrent episode reward: 660.0000\nepisodes: 1219\nexploration: 0.07728\nlearning_rate: 0.00009\nelapsed time: 8182.9 seconds (2.27 hours)\n\nTimestep: 2020000\nmean reward (100 episodes): 851.2000\nbest mean reward: 851.2000\ncurrent episode reward: 1380.0000\nepisodes: 1221\nexploration: 0.07705\nlearning_rate: 0.00009\nelapsed time: 8227.8 seconds (2.29 hours)\n\nTimestep: 2030000\nmean reward (100 episodes): 862.9200\nbest mean reward: 862.9200\ncurrent episode reward: 1380.0000\nepisodes: 1224\nexploration: 0.07683\nlearning_rate: 0.00009\nelapsed time: 8272.3 seconds (2.30 hours)\n\nTimestep: 2040000\nmean reward (100 episodes): 870.6400\nbest mean reward: 870.6400\ncurrent episode reward: 660.0000\nepisodes: 1227\nexploration: 0.07660\nlearning_rate: 0.00009\nelapsed time: 8317.0 seconds (2.31 hours)\n\nTimestep: 2050000\nmean reward (100 episodes): 869.7200\nbest mean reward: 874.4800\ncurrent episode reward: 948.0000\nepisodes: 1231\nexploration: 0.07637\nlearning_rate: 0.00009\nelapsed time: 8361.0 seconds (2.32 hours)\n\nTimestep: 2060000\nmean reward (100 episodes): 869.3200\nbest mean reward: 874.4800\ncurrent episode reward: 660.0000\nepisodes: 1235\nexploration: 0.07615\nlearning_rate: 0.00009\nelapsed time: 8405.3 seconds (2.33 hours)\n\nTimestep: 2070000\nmean reward (100 episodes): 871.0800\nbest mean reward: 874.4800\ncurrent episode reward: 660.0000\nepisodes: 1239\nexploration: 0.07593\nlearning_rate: 0.00009\nelapsed time: 8450.0 seconds (2.35 hours)\n\nTimestep: 2080000\nmean reward (100 episodes): 882.4400\nbest mean reward: 882.4400\ncurrent episode reward: 1380.0000\nepisodes: 1242\nexploration: 0.07570\nlearning_rate: 0.00009\nelapsed time: 8494.0 seconds (2.36 hours)\n\nTimestep: 2090000\nmean reward (100 episodes): 895.1600\nbest mean reward: 895.1600\ncurrent episode reward: 1692.0000\nepisodes: 1245\nexploration: 0.07548\nlearning_rate: 0.00009\nelapsed time: 8539.3 seconds (2.37 hours)\n\nTimestep: 2100000\nmean reward (100 episodes): 901.2000\nbest mean reward: 901.2000\ncurrent episode reward: 1744.0000\nepisodes: 1248\nexploration: 0.07525\nlearning_rate: 0.00009\nelapsed time: 8583.6 seconds (2.38 hours)\n\nTimestep: 2110000\nmean reward (100 episodes): 928.0800\nbest mean reward: 928.0800\ncurrent episode reward: 756.0000\nepisodes: 1251\nexploration: 0.07503\nlearning_rate: 0.00009\nelapsed time: 8628.1 seconds (2.40 hours)\n\nTimestep: 2120000\nmean reward (100 episodes): 944.1600\nbest mean reward: 944.1600\ncurrent episode reward: 1284.0000\nepisodes: 1254\nexploration: 0.07480\nlearning_rate: 0.00009\nelapsed time: 8673.0 seconds (2.41 hours)\n\nTimestep: 2130000\nmean reward (100 episodes): 958.2000\nbest mean reward: 958.2000\ncurrent episode reward: 1432.0000\nepisodes: 1257\nexploration: 0.07458\nlearning_rate: 0.00009\nelapsed time: 8716.9 seconds (2.42 hours)\n\nTimestep: 2140000\nmean reward (100 episodes): 995.6600\nbest mean reward: 995.6600\ncurrent episode reward: 4230.0000\nepisodes: 1258\nexploration: 0.07435\nlearning_rate: 0.00009\nelapsed time: 8761.6 seconds (2.43 hours)\n\nTimestep: 2150000\nmean reward (100 episodes): 1008.2200\nbest mean reward: 1008.2200\ncurrent episode reward: 756.0000\nepisodes: 1261\nexploration: 0.07412\nlearning_rate: 0.00009\nelapsed time: 8806.1 seconds (2.45 hours)\n\nTimestep: 2160000\nmean reward (100 episodes): 1028.2600\nbest mean reward: 1028.2600\ncurrent episode reward: 1380.0000\nepisodes: 1265\nexploration: 0.07390\nlearning_rate: 0.00009\nelapsed time: 8850.7 seconds (2.46 hours)\n\nTimestep: 2170000\nmean reward (100 episodes): 1032.7400\nbest mean reward: 1032.7400\ncurrent episode reward: 1536.0000\nepisodes: 1268\nexploration: 0.07368\nlearning_rate: 0.00009\nelapsed time: 8895.9 seconds (2.47 hours)\n\nTimestep: 2180000\nmean reward (100 episodes): 1024.7800\nbest mean reward: 1032.7400\ncurrent episode reward: 660.0000\nepisodes: 1272\nexploration: 0.07345\nlearning_rate: 0.00009\nelapsed time: 8940.2 seconds (2.48 hours)\n\nTimestep: 2190000\nmean reward (100 episodes): 1044.4200\nbest mean reward: 1044.4200\ncurrent episode reward: 852.0000\nepisodes: 1275\nexploration: 0.07322\nlearning_rate: 0.00009\nelapsed time: 8984.8 seconds (2.50 hours)\n\nTimestep: 2200000\nmean reward (100 episodes): 1033.5800\nbest mean reward: 1044.4200\ncurrent episode reward: 352.0000\nepisodes: 1279\nexploration: 0.07300\nlearning_rate: 0.00009\nelapsed time: 9029.7 seconds (2.51 hours)\n\nTimestep: 2210000\nmean reward (100 episodes): 1054.0200\nbest mean reward: 1054.0200\ncurrent episode reward: 2160.0000\nepisodes: 1281\nexploration: 0.07278\nlearning_rate: 0.00008\nelapsed time: 9074.4 seconds (2.52 hours)\n\nTimestep: 2220000\nmean reward (100 episodes): 1074.1000\nbest mean reward: 1074.1000\ncurrent episode reward: 2860.0000\nepisodes: 1284\nexploration: 0.07255\nlearning_rate: 0.00008\nelapsed time: 9119.3 seconds (2.53 hours)\n\nTimestep: 2230000\nmean reward (100 episodes): 1084.7000\nbest mean reward: 1086.6200\ncurrent episode reward: 1092.0000\nepisodes: 1287\nexploration: 0.07233\nlearning_rate: 0.00008\nelapsed time: 9164.0 seconds (2.55 hours)\n\nTimestep: 2240000\nmean reward (100 episodes): 1083.5400\nbest mean reward: 1097.5400\ncurrent episode reward: 708.0000\nepisodes: 1289\nexploration: 0.07210\nlearning_rate: 0.00008\nelapsed time: 9209.4 seconds (2.56 hours)\n\nTimestep: 2250000\nmean reward (100 episodes): 1083.5400\nbest mean reward: 1097.5400\ncurrent episode reward: 1284.0000\nepisodes: 1292\nexploration: 0.07187\nlearning_rate: 0.00008\nelapsed time: 9253.5 seconds (2.57 hours)\n\nTimestep: 2260000\nmean reward (100 episodes): 1087.9000\nbest mean reward: 1097.5400\ncurrent episode reward: 1380.0000\nepisodes: 1294\nexploration: 0.07165\nlearning_rate: 0.00008\nelapsed time: 9298.8 seconds (2.58 hours)\n\nTimestep: 2270000\nmean reward (100 episodes): 1134.2600\nbest mean reward: 1134.2600\ncurrent episode reward: 2272.0000\nepisodes: 1296\nexploration: 0.07143\nlearning_rate: 0.00008\nelapsed time: 9344.4 seconds (2.60 hours)\n\nTimestep: 2280000\nmean reward (100 episodes): 1169.8400\nbest mean reward: 1173.2000\ncurrent episode reward: 756.0000\nepisodes: 1299\nexploration: 0.07120\nlearning_rate: 0.00008\nelapsed time: 9389.4 seconds (2.61 hours)\n\nTimestep: 2290000\nmean reward (100 episodes): 1178.9600\nbest mean reward: 1178.9600\ncurrent episode reward: 1380.0000\nepisodes: 1301\nexploration: 0.07097\nlearning_rate: 0.00008\nelapsed time: 9433.9 seconds (2.62 hours)\n\nTimestep: 2300000\nmean reward (100 episodes): 1217.1600\nbest mean reward: 1217.1600\ncurrent episode reward: 2552.0000\nepisodes: 1303\nexploration: 0.07075\nlearning_rate: 0.00008\nelapsed time: 9478.1 seconds (2.63 hours)\n\nTimestep: 2310000\nmean reward (100 episodes): 1205.9600\nbest mean reward: 1217.1600\ncurrent episode reward: 996.0000\nepisodes: 1306\nexploration: 0.07053\nlearning_rate: 0.00008\nelapsed time: 9523.1 seconds (2.65 hours)\n\nTimestep: 2320000\nmean reward (100 episodes): 1217.8800\nbest mean reward: 1217.8800\ncurrent episode reward: 1044.0000\nepisodes: 1309\nexploration: 0.07030\nlearning_rate: 0.00008\nelapsed time: 9567.2 seconds (2.66 hours)\n\nTimestep: 2330000\nmean reward (100 episodes): 1218.8400\nbest mean reward: 1223.6400\ncurrent episode reward: 996.0000\nepisodes: 1312\nexploration: 0.07007\nlearning_rate: 0.00008\nelapsed time: 9611.8 seconds (2.67 hours)\n\nTimestep: 2340000\nmean reward (100 episodes): 1250.4400\nbest mean reward: 1250.4400\ncurrent episode reward: 2108.0000\nepisodes: 1314\nexploration: 0.06985\nlearning_rate: 0.00008\nelapsed time: 9656.5 seconds (2.68 hours)\n\nTimestep: 2350000\nmean reward (100 episodes): 1261.5600\nbest mean reward: 1261.5600\ncurrent episode reward: 1484.0000\nepisodes: 1317\nexploration: 0.06962\nlearning_rate: 0.00008\nelapsed time: 9700.8 seconds (2.69 hours)\n\nTimestep: 2360000\nmean reward (100 episodes): 1253.3600\nbest mean reward: 1261.5600\ncurrent episode reward: 1432.0000\nepisodes: 1320\nexploration: 0.06940\nlearning_rate: 0.00008\nelapsed time: 9745.3 seconds (2.71 hours)\n\nTimestep: 2370000\nmean reward (100 episodes): 1258.6400\nbest mean reward: 1261.5600\ncurrent episode reward: 1140.0000\nepisodes: 1323\nexploration: 0.06918\nlearning_rate: 0.00008\nelapsed time: 9789.7 seconds (2.72 hours)\n\nTimestep: 2380000\nmean reward (100 episodes): 1255.7200\nbest mean reward: 1261.5600\ncurrent episode reward: 1380.0000\nepisodes: 1326\nexploration: 0.06895\nlearning_rate: 0.00008\nelapsed time: 9835.0 seconds (2.73 hours)\n\nTimestep: 2390000\nmean reward (100 episodes): 1263.3600\nbest mean reward: 1263.3600\ncurrent episode reward: 1380.0000\nepisodes: 1329\nexploration: 0.06873\nlearning_rate: 0.00008\nelapsed time: 9879.2 seconds (2.74 hours)\n\nTimestep: 2400000\nmean reward (100 episodes): 1271.5200\nbest mean reward: 1271.5200\ncurrent episode reward: 1044.0000\nepisodes: 1331\nexploration: 0.06850\nlearning_rate: 0.00008\nelapsed time: 9923.7 seconds (2.76 hours)\n\nTimestep: 2410000\nmean reward (100 episodes): 1300.9200\nbest mean reward: 1300.9200\ncurrent episode reward: 1044.0000\nepisodes: 1334\nexploration: 0.06828\nlearning_rate: 0.00008\nelapsed time: 9967.6 seconds (2.77 hours)\n\nTimestep: 2420000\nmean reward (100 episodes): 1315.4400\nbest mean reward: 1315.9200\ncurrent episode reward: 1092.0000\nepisodes: 1336\nexploration: 0.06805\nlearning_rate: 0.00008\nelapsed time: 10012.9 seconds (2.78 hours)\n\nTimestep: 2430000\nmean reward (100 episodes): 1347.3600\nbest mean reward: 1347.3600\ncurrent episode reward: 2160.0000\nepisodes: 1339\nexploration: 0.06782\nlearning_rate: 0.00008\nelapsed time: 10057.7 seconds (2.79 hours)\n\nTimestep: 2440000\nmean reward (100 episodes): 1367.6800\nbest mean reward: 1367.6800\ncurrent episode reward: 2692.0000\nepisodes: 1341\nexploration: 0.06760\nlearning_rate: 0.00008\nelapsed time: 10102.3 seconds (2.81 hours)\n\nTimestep: 2450000\nmean reward (100 episodes): 1356.7200\nbest mean reward: 1368.2000\ncurrent episode reward: 616.0000\nepisodes: 1344\nexploration: 0.06738\nlearning_rate: 0.00008\nelapsed time: 10146.5 seconds (2.82 hours)\n\nTimestep: 2460000\nmean reward (100 episodes): 1384.0000\nbest mean reward: 1384.0000\ncurrent episode reward: 1380.0000\nepisodes: 1347\nexploration: 0.06715\nlearning_rate: 0.00008\nelapsed time: 10191.4 seconds (2.83 hours)\n\nTimestep: 2470000\nmean reward (100 episodes): 1371.1600\nbest mean reward: 1388.1600\ncurrent episode reward: 756.0000\nepisodes: 1350\nexploration: 0.06693\nlearning_rate: 0.00008\nelapsed time: 10235.6 seconds (2.84 hours)\n\nTimestep: 2480000\nmean reward (100 episodes): 1380.6400\nbest mean reward: 1388.1600\ncurrent episode reward: 2160.0000\nepisodes: 1353\nexploration: 0.06670\nlearning_rate: 0.00008\nelapsed time: 10281.0 seconds (2.86 hours)\n\nTimestep: 2490000\nmean reward (100 episodes): 1391.6400\nbest mean reward: 1391.6400\ncurrent episode reward: 1952.0000\nepisodes: 1355\nexploration: 0.06648\nlearning_rate: 0.00008\nelapsed time: 10325.7 seconds (2.87 hours)\n\nTimestep: 2500000\nmean reward (100 episodes): 1375.6600\nbest mean reward: 1403.6800\ncurrent episode reward: 2056.0000\nepisodes: 1358\nexploration: 0.06625\nlearning_rate: 0.00008\nelapsed time: 10370.6 seconds (2.88 hours)\n\nTimestep: 2510000\nmean reward (100 episodes): 1396.9000\nbest mean reward: 1403.6800\ncurrent episode reward: 2056.0000\nepisodes: 1360\nexploration: 0.06603\nlearning_rate: 0.00008\nelapsed time: 10415.6 seconds (2.89 hours)\n\nTimestep: 2520000\nmean reward (100 episodes): 1419.9400\nbest mean reward: 1419.9400\ncurrent episode reward: 3060.0000\nepisodes: 1361\nexploration: 0.06580\nlearning_rate: 0.00008\nelapsed time: 10460.5 seconds (2.91 hours)\n\nTimestep: 2530000\nmean reward (100 episodes): 1433.9800\nbest mean reward: 1433.9800\ncurrent episode reward: 1332.0000\nepisodes: 1364\nexploration: 0.06557\nlearning_rate: 0.00008\nelapsed time: 10504.7 seconds (2.92 hours)\n\nTimestep: 2540000\nmean reward (100 episodes): 1432.6200\nbest mean reward: 1433.9800\ncurrent episode reward: 1692.0000\nepisodes: 1368\nexploration: 0.06535\nlearning_rate: 0.00008\nelapsed time: 10549.3 seconds (2.93 hours)\n\nTimestep: 2550000\nmean reward (100 episodes): 1449.6200\nbest mean reward: 1449.6200\ncurrent episode reward: 1692.0000\nepisodes: 1370\nexploration: 0.06513\nlearning_rate: 0.00008\nelapsed time: 10593.5 seconds (2.94 hours)\n\nTimestep: 2560000\nmean reward (100 episodes): 1465.2600\nbest mean reward: 1465.2600\ncurrent episode reward: 1744.0000\nepisodes: 1373\nexploration: 0.06490\nlearning_rate: 0.00008\nelapsed time: 10638.1 seconds (2.96 hours)\n\nTimestep: 2570000\nmean reward (100 episodes): 1459.5400\nbest mean reward: 1465.2600\ncurrent episode reward: 852.0000\nepisodes: 1376\nexploration: 0.06468\nlearning_rate: 0.00008\nelapsed time: 10682.4 seconds (2.97 hours)\n\nTimestep: 2580000\nmean reward (100 episodes): 1482.4200\nbest mean reward: 1483.3800\ncurrent episode reward: 708.0000\nepisodes: 1378\nexploration: 0.06445\nlearning_rate: 0.00008\nelapsed time: 10726.5 seconds (2.98 hours)\n\nTimestep: 2590000\nmean reward (100 episodes): 1488.8600\nbest mean reward: 1494.7800\ncurrent episode reward: 996.0000\nepisodes: 1380\nexploration: 0.06423\nlearning_rate: 0.00008\nelapsed time: 10771.7 seconds (2.99 hours)\n\nTimestep: 2600000\nmean reward (100 episodes): 1534.1200\nbest mean reward: 1534.1200\ncurrent episode reward: 2692.0000\nepisodes: 1383\nexploration: 0.06400\nlearning_rate: 0.00008\nelapsed time: 10816.4 seconds (3.00 hours)\n\nTimestep: 2610000\nmean reward (100 episodes): 1515.6000\nbest mean reward: 1534.1200\ncurrent episode reward: 1332.0000\nepisodes: 1386\nexploration: 0.06377\nlearning_rate: 0.00008\nelapsed time: 10861.3 seconds (3.02 hours)\n\nTimestep: 2620000\nmean reward (100 episodes): 1543.3800\nbest mean reward: 1543.3800\ncurrent episode reward: 3870.0000\nepisodes: 1387\nexploration: 0.06355\nlearning_rate: 0.00008\nelapsed time: 10905.6 seconds (3.03 hours)\n\nTimestep: 2630000\nmean reward (100 episodes): 1577.0200\nbest mean reward: 1577.0200\ncurrent episode reward: 2972.0000\nepisodes: 1389\nexploration: 0.06333\nlearning_rate: 0.00008\nelapsed time: 10950.2 seconds (3.04 hours)\n\nTimestep: 2640000\nmean reward (100 episodes): 1581.2200\nbest mean reward: 1581.2200\ncurrent episode reward: 1484.0000\nepisodes: 1391\nexploration: 0.06310\nlearning_rate: 0.00008\nelapsed time: 10994.4 seconds (3.05 hours)\n\nTimestep: 2650000\nmean reward (100 episodes): 1613.0200\nbest mean reward: 1613.0200\ncurrent episode reward: 3084.0000\nepisodes: 1394\nexploration: 0.06288\nlearning_rate: 0.00008\nelapsed time: 11038.9 seconds (3.07 hours)\n\nTimestep: 2660000\nmean reward (100 episodes): 1587.7000\nbest mean reward: 1613.0200\ncurrent episode reward: 2860.0000\nepisodes: 1396\nexploration: 0.06265\nlearning_rate: 0.00008\nelapsed time: 11084.0 seconds (3.08 hours)\n\nTimestep: 2670000\nmean reward (100 episodes): 1578.2400\nbest mean reward: 1613.0200\ncurrent episode reward: 2108.0000\nepisodes: 1399\nexploration: 0.06243\nlearning_rate: 0.00008\nelapsed time: 11128.6 seconds (3.09 hours)\n\nTimestep: 2680000\nmean reward (100 episodes): 1576.6000\nbest mean reward: 1613.0200\ncurrent episode reward: 2916.0000\nepisodes: 1402\nexploration: 0.06220\nlearning_rate: 0.00008\nelapsed time: 11173.6 seconds (3.10 hours)\n\nTimestep: 2690000\nmean reward (100 episodes): 1573.3600\nbest mean reward: 1613.0200\ncurrent episode reward: 1796.0000\nepisodes: 1405\nexploration: 0.06198\nlearning_rate: 0.00008\nelapsed time: 11217.5 seconds (3.12 hours)\n\nTimestep: 2700000\nmean reward (100 episodes): 1579.3200\nbest mean reward: 1613.0200\ncurrent episode reward: 2160.0000\nepisodes: 1408\nexploration: 0.06175\nlearning_rate: 0.00008\nelapsed time: 11263.0 seconds (3.13 hours)\n\nTimestep: 2710000\nmean reward (100 episodes): 1578.3600\nbest mean reward: 1613.0200\ncurrent episode reward: 1284.0000\nepisodes: 1410\nexploration: 0.06153\nlearning_rate: 0.00008\nelapsed time: 11307.9 seconds (3.14 hours)\n\nTimestep: 2720000\nmean reward (100 episodes): 1575.7200\nbest mean reward: 1613.0200\ncurrent episode reward: 660.0000\nepisodes: 1414\nexploration: 0.06130\nlearning_rate: 0.00008\nelapsed time: 11352.6 seconds (3.15 hours)\n\nTimestep: 2730000\nmean reward (100 episodes): 1599.6000\nbest mean reward: 1613.0200\ncurrent episode reward: 2108.0000\nepisodes: 1416\nexploration: 0.06108\nlearning_rate: 0.00008\nelapsed time: 11396.5 seconds (3.17 hours)\n\nTimestep: 2740000\nmean reward (100 episodes): 1630.4800\nbest mean reward: 1630.4800\ncurrent episode reward: 3900.0000\nepisodes: 1418\nexploration: 0.06085\nlearning_rate: 0.00008\nelapsed time: 11441.4 seconds (3.18 hours)\n\nTimestep: 2750000\nmean reward (100 episodes): 1627.5600\nbest mean reward: 1634.8000\ncurrent episode reward: 1044.0000\nepisodes: 1422\nexploration: 0.06062\nlearning_rate: 0.00008\nelapsed time: 11485.9 seconds (3.19 hours)\n\nTimestep: 2760000\nmean reward (100 episodes): 1643.6000\nbest mean reward: 1643.6000\ncurrent episode reward: 2888.0000\nepisodes: 1425\nexploration: 0.06040\nlearning_rate: 0.00008\nelapsed time: 11531.2 seconds (3.20 hours)\n\nTimestep: 2770000\nmean reward (100 episodes): 1645.7200\nbest mean reward: 1646.2000\ncurrent episode reward: 1140.0000\nepisodes: 1427\nexploration: 0.06017\nlearning_rate: 0.00008\nelapsed time: 11576.2 seconds (3.22 hours)\n\nTimestep: 2780000\nmean reward (100 episodes): 1673.4000\nbest mean reward: 1673.4000\ncurrent episode reward: 3000.0000\nepisodes: 1429\nexploration: 0.05995\nlearning_rate: 0.00008\nelapsed time: 11621.4 seconds (3.23 hours)\n\nTimestep: 2790000\nmean reward (100 episodes): 1666.0800\nbest mean reward: 1676.7600\ncurrent episode reward: 1092.0000\nepisodes: 1432\nexploration: 0.05973\nlearning_rate: 0.00008\nelapsed time: 11666.0 seconds (3.24 hours)\n\nTimestep: 2800000\nmean reward (100 episodes): 1693.6400\nbest mean reward: 1694.1600\ncurrent episode reward: 2108.0000\nepisodes: 1435\nexploration: 0.05950\nlearning_rate: 0.00008\nelapsed time: 11710.5 seconds (3.25 hours)\n\nTimestep: 2810000\nmean reward (100 episodes): 1698.2400\nbest mean reward: 1698.2400\ncurrent episode reward: 1900.0000\nepisodes: 1438\nexploration: 0.05928\nlearning_rate: 0.00008\nelapsed time: 11755.8 seconds (3.27 hours)\n\nTimestep: 2820000\nmean reward (100 episodes): 1704.4800\nbest mean reward: 1704.4800\ncurrent episode reward: 2004.0000\nepisodes: 1440\nexploration: 0.05905\nlearning_rate: 0.00008\nelapsed time: 11801.3 seconds (3.28 hours)\n\nTimestep: 2830000\nmean reward (100 episodes): 1713.0000\nbest mean reward: 1713.0000\ncurrent episode reward: 1188.0000\nepisodes: 1443\nexploration: 0.05883\nlearning_rate: 0.00008\nelapsed time: 11847.1 seconds (3.29 hours)\n\nTimestep: 2840000\nmean reward (100 episodes): 1723.5200\nbest mean reward: 1740.4800\ncurrent episode reward: 1380.0000\nepisodes: 1446\nexploration: 0.05860\nlearning_rate: 0.00008\nelapsed time: 11891.2 seconds (3.30 hours)\n\nTimestep: 2850000\nmean reward (100 episodes): 1760.1200\nbest mean reward: 1760.1200\ncurrent episode reward: 2972.0000\nepisodes: 1449\nexploration: 0.05837\nlearning_rate: 0.00008\nelapsed time: 11936.0 seconds (3.32 hours)\n\nTimestep: 2860000\nmean reward (100 episodes): 1782.6400\nbest mean reward: 1786.4800\ncurrent episode reward: 804.0000\nepisodes: 1452\nexploration: 0.05815\nlearning_rate: 0.00008\nelapsed time: 11981.4 seconds (3.33 hours)\n\nTimestep: 2870000\nmean reward (100 episodes): 1759.5200\nbest mean reward: 1786.4800\ncurrent episode reward: 852.0000\nepisodes: 1456\nexploration: 0.05792\nlearning_rate: 0.00008\nelapsed time: 12026.3 seconds (3.34 hours)\n\nTimestep: 2880000\nmean reward (100 episodes): 1768.8400\nbest mean reward: 1786.4800\ncurrent episode reward: 1380.0000\nepisodes: 1459\nexploration: 0.05770\nlearning_rate: 0.00008\nelapsed time: 12070.9 seconds (3.35 hours)\n\nTimestep: 2890000\nmean reward (100 episodes): 1778.5200\nbest mean reward: 1786.4800\ncurrent episode reward: 3420.0000\nepisodes: 1461\nexploration: 0.05748\nlearning_rate: 0.00008\nelapsed time: 12115.9 seconds (3.37 hours)\n\nTimestep: 2900000\nmean reward (100 episodes): 1805.1600\nbest mean reward: 1805.1600\ncurrent episode reward: 2888.0000\nepisodes: 1464\nexploration: 0.05725\nlearning_rate: 0.00008\nelapsed time: 12160.8 seconds (3.38 hours)\n\nTimestep: 2910000\nmean reward (100 episodes): 1816.9200\nbest mean reward: 1820.0400\ncurrent episode reward: 1380.0000\nepisodes: 1468\nexploration: 0.05702\nlearning_rate: 0.00008\nelapsed time: 12205.3 seconds (3.39 hours)\n\nTimestep: 2920000\nmean reward (100 episodes): 1834.8000\nbest mean reward: 1834.8000\ncurrent episode reward: 1380.0000\nepisodes: 1471\nexploration: 0.05680\nlearning_rate: 0.00008\nelapsed time: 12249.7 seconds (3.40 hours)\n\nTimestep: 2930000\nmean reward (100 episodes): 1838.8400\nbest mean reward: 1842.0000\ncurrent episode reward: 1380.0000\nepisodes: 1475\nexploration: 0.05658\nlearning_rate: 0.00008\nelapsed time: 12294.3 seconds (3.42 hours)\n\nTimestep: 2940000\nmean reward (100 episodes): 1856.6800\nbest mean reward: 1856.6800\ncurrent episode reward: 1380.0000\nepisodes: 1478\nexploration: 0.05635\nlearning_rate: 0.00008\nelapsed time: 12340.3 seconds (3.43 hours)\n\nTimestep: 2950000\nmean reward (100 episodes): 1840.5800\nbest mean reward: 1868.7200\ncurrent episode reward: 1536.0000\nepisodes: 1481\nexploration: 0.05613\nlearning_rate: 0.00008\nelapsed time: 12385.0 seconds (3.44 hours)\n\nTimestep: 2960000\nmean reward (100 episodes): 1848.6600\nbest mean reward: 1868.7200\ncurrent episode reward: 3900.0000\nepisodes: 1483\nexploration: 0.05590\nlearning_rate: 0.00008\nelapsed time: 12430.0 seconds (3.45 hours)\n\nTimestep: 2970000\nmean reward (100 episodes): 1916.3200\nbest mean reward: 1916.3200\ncurrent episode reward: 3480.0000\nepisodes: 1485\nexploration: 0.05568\nlearning_rate: 0.00008\nelapsed time: 12475.5 seconds (3.47 hours)\n\nTimestep: 2980000\nmean reward (100 episodes): 1913.2000\nbest mean reward: 1946.5000\ncurrent episode reward: 1380.0000\nepisodes: 1488\nexploration: 0.05545\nlearning_rate: 0.00008\nelapsed time: 12520.2 seconds (3.48 hours)\n\nTimestep: 2990000\nmean reward (100 episodes): 1896.2800\nbest mean reward: 1946.5000\ncurrent episode reward: 1380.0000\nepisodes: 1492\nexploration: 0.05523\nlearning_rate: 0.00008\nelapsed time: 12564.3 seconds (3.49 hours)\n\nTimestep: 3000000\nmean reward (100 episodes): 1876.0800\nbest mean reward: 1946.5000\ncurrent episode reward: 2160.0000\nepisodes: 1496\nexploration: 0.05500\nlearning_rate: 0.00008\nelapsed time: 12610.4 seconds (3.50 hours)\n\nTimestep: 3010000\nmean reward (100 episodes): 1921.7400\nbest mean reward: 1946.5000\ncurrent episode reward: 2160.0000\nepisodes: 1498\nexploration: 0.05478\nlearning_rate: 0.00007\nelapsed time: 12654.7 seconds (3.52 hours)\n\nTimestep: 3020000\nmean reward (100 episodes): 1977.1800\nbest mean reward: 1977.1800\ncurrent episode reward: 4448.0000\nepisodes: 1500\nexploration: 0.05455\nlearning_rate: 0.00007\nelapsed time: 12699.4 seconds (3.53 hours)\n\nTimestep: 3030000\nmean reward (100 episodes): 2006.2800\nbest mean reward: 2008.3200\ncurrent episode reward: 2160.0000\nepisodes: 1503\nexploration: 0.05433\nlearning_rate: 0.00007\nelapsed time: 12744.4 seconds (3.54 hours)\n\nTimestep: 3040000\nmean reward (100 episodes): 2028.4400\nbest mean reward: 2028.4400\ncurrent episode reward: 1692.0000\nepisodes: 1506\nexploration: 0.05410\nlearning_rate: 0.00007\nelapsed time: 12788.9 seconds (3.55 hours)\n\nTimestep: 3050000\nmean reward (100 episodes): 2056.7200\nbest mean reward: 2056.7200\ncurrent episode reward: 3364.0000\nepisodes: 1509\nexploration: 0.05388\nlearning_rate: 0.00007\nelapsed time: 12834.3 seconds (3.57 hours)\n\nTimestep: 3060000\nmean reward (100 episodes): 2062.0800\nbest mean reward: 2071.6400\ncurrent episode reward: 1952.0000\nepisodes: 1512\nexploration: 0.05365\nlearning_rate: 0.00007\nelapsed time: 12879.3 seconds (3.58 hours)\n\nTimestep: 3070000\nmean reward (100 episodes): 2059.4000\nbest mean reward: 2075.5200\ncurrent episode reward: 1332.0000\nepisodes: 1515\nexploration: 0.05343\nlearning_rate: 0.00007\nelapsed time: 12924.1 seconds (3.59 hours)\n\nTimestep: 3080000\nmean reward (100 episodes): 2051.9200\nbest mean reward: 2075.5200\ncurrent episode reward: 1640.0000\nepisodes: 1518\nexploration: 0.05320\nlearning_rate: 0.00007\nelapsed time: 12969.4 seconds (3.60 hours)\n\nTimestep: 3090000\nmean reward (100 episodes): 2102.0800\nbest mean reward: 2102.0800\ncurrent episode reward: 2056.0000\nepisodes: 1521\nexploration: 0.05298\nlearning_rate: 0.00007\nelapsed time: 13014.2 seconds (3.62 hours)\n\nTimestep: 3100000\nmean reward (100 episodes): 2106.1200\nbest mean reward: 2121.2000\ncurrent episode reward: 1380.0000\nepisodes: 1525\nexploration: 0.05275\nlearning_rate: 0.00007\nelapsed time: 13059.2 seconds (3.63 hours)\n\nTimestep: 3110000\nmean reward (100 episodes): 2106.0800\nbest mean reward: 2121.2000\ncurrent episode reward: 1332.0000\nepisodes: 1528\nexploration: 0.05253\nlearning_rate: 0.00007\nelapsed time: 13105.3 seconds (3.64 hours)\n\nTimestep: 3120000\nmean reward (100 episodes): 2143.3200\nbest mean reward: 2143.3200\ncurrent episode reward: 4740.0000\nepisodes: 1530\nexploration: 0.05230\nlearning_rate: 0.00007\nelapsed time: 13150.1 seconds (3.65 hours)\n\nTimestep: 3130000\nmean reward (100 episodes): 2196.7000\nbest mean reward: 2196.7000\ncurrent episode reward: 3840.0000\nepisodes: 1533\nexploration: 0.05208\nlearning_rate: 0.00007\nelapsed time: 13195.5 seconds (3.67 hours)\n\nTimestep: 3140000\nmean reward (100 episodes): 2205.9200\nbest mean reward: 2205.9200\ncurrent episode reward: 4478.0000\nepisodes: 1535\nexploration: 0.05185\nlearning_rate: 0.00007\nelapsed time: 13240.2 seconds (3.68 hours)\n\nTimestep: 3150000\nmean reward (100 episodes): 2259.2000\nbest mean reward: 2263.8800\ncurrent episode reward: 1692.0000\nepisodes: 1539\nexploration: 0.05163\nlearning_rate: 0.00007\nelapsed time: 13285.5 seconds (3.69 hours)\n\nTimestep: 3160000\nmean reward (100 episodes): 2295.0000\nbest mean reward: 2295.0000\ncurrent episode reward: 4350.0000\nepisodes: 1541\nexploration: 0.05140\nlearning_rate: 0.00007\nelapsed time: 13331.2 seconds (3.70 hours)\n\nTimestep: 3170000\nmean reward (100 episodes): 2366.1000\nbest mean reward: 2366.1000\ncurrent episode reward: 5474.0000\nepisodes: 1543\nexploration: 0.05117\nlearning_rate: 0.00007\nelapsed time: 13376.1 seconds (3.72 hours)\n\nTimestep: 3180000\nmean reward (100 episodes): 2396.8400\nbest mean reward: 2396.8400\ncurrent episode reward: 2860.0000\nepisodes: 1545\nexploration: 0.05095\nlearning_rate: 0.00007\nelapsed time: 13420.8 seconds (3.73 hours)\n\nTimestep: 3190000\nmean reward (100 episodes): 2452.5200\nbest mean reward: 2452.5200\ncurrent episode reward: 5268.0000\nepisodes: 1547\nexploration: 0.05072\nlearning_rate: 0.00007\nelapsed time: 13465.8 seconds (3.74 hours)\n\nTimestep: 3200000\nmean reward (100 episodes): 2493.6200\nbest mean reward: 2493.6200\ncurrent episode reward: 3660.0000\nepisodes: 1549\nexploration: 0.05050\nlearning_rate: 0.00007\nelapsed time: 13511.0 seconds (3.75 hours)\n\nTimestep: 3210000\nmean reward (100 episodes): 2509.2600\nbest mean reward: 2509.2600\ncurrent episode reward: 2664.0000\nepisodes: 1551\nexploration: 0.05028\nlearning_rate: 0.00007\nelapsed time: 13556.2 seconds (3.77 hours)\n\nTimestep: 3220000\nmean reward (100 episodes): 2568.1800\nbest mean reward: 2568.1800\ncurrent episode reward: 2328.0000\nepisodes: 1554\nexploration: 0.05005\nlearning_rate: 0.00007\nelapsed time: 13601.4 seconds (3.78 hours)\n\nTimestep: 3230000\nmean reward (100 episodes): 2612.7800\nbest mean reward: 2612.7800\ncurrent episode reward: 2552.0000\nepisodes: 1556\nexploration: 0.04983\nlearning_rate: 0.00007\nelapsed time: 13646.3 seconds (3.79 hours)\n\nTimestep: 3240000\nmean reward (100 episodes): 2676.4800\nbest mean reward: 2676.4800\ncurrent episode reward: 2160.0000\nepisodes: 1559\nexploration: 0.04960\nlearning_rate: 0.00007\nelapsed time: 13692.0 seconds (3.80 hours)\n\nTimestep: 3250000\nmean reward (100 episodes): 2672.0000\nbest mean reward: 2679.0000\ncurrent episode reward: 2720.0000\nepisodes: 1561\nexploration: 0.04938\nlearning_rate: 0.00007\nelapsed time: 13736.6 seconds (3.82 hours)\n\nTimestep: 3260000\nmean reward (100 episodes): 2704.2600\nbest mean reward: 2704.2600\ncurrent episode reward: 2440.0000\nepisodes: 1563\nexploration: 0.04915\nlearning_rate: 0.00007\nelapsed time: 13781.1 seconds (3.83 hours)\n\nTimestep: 3270000\nmean reward (100 episodes): 2736.7400\nbest mean reward: 2736.7400\ncurrent episode reward: 4156.0000\nepisodes: 1565\nexploration: 0.04892\nlearning_rate: 0.00007\nelapsed time: 13826.4 seconds (3.84 hours)\n\nTimestep: 3280000\nmean reward (100 episodes): 2797.8200\nbest mean reward: 2797.8200\ncurrent episode reward: 4320.0000\nepisodes: 1567\nexploration: 0.04870\nlearning_rate: 0.00007\nelapsed time: 13872.4 seconds (3.85 hours)\n\nTimestep: 3290000\nmean reward (100 episodes): 2836.3400\nbest mean reward: 2836.3400\ncurrent episode reward: 4156.0000\nepisodes: 1570\nexploration: 0.04847\nlearning_rate: 0.00007\nelapsed time: 13917.2 seconds (3.87 hours)\n\nTimestep: 3300000\nmean reward (100 episodes): 2938.6200\nbest mean reward: 2938.6200\ncurrent episode reward: 5734.0000\nepisodes: 1572\nexploration: 0.04825\nlearning_rate: 0.00007\nelapsed time: 13962.0 seconds (3.88 hours)\n\nTimestep: 3310000\nmean reward (100 episodes): 2986.0600\nbest mean reward: 2986.0600\ncurrent episode reward: 3420.0000\nepisodes: 1575\nexploration: 0.04802\nlearning_rate: 0.00007\nelapsed time: 14007.2 seconds (3.89 hours)\n\nTimestep: 3320000\nmean reward (100 episodes): 2990.8200\nbest mean reward: 2994.4600\ncurrent episode reward: 2440.0000\nepisodes: 1577\nexploration: 0.04780\nlearning_rate: 0.00007\nelapsed time: 14051.9 seconds (3.90 hours)\n\nTimestep: 3330000\nmean reward (100 episodes): 3036.9400\nbest mean reward: 3036.9400\ncurrent episode reward: 2004.0000\nepisodes: 1580\nexploration: 0.04757\nlearning_rate: 0.00007\nelapsed time: 14096.3 seconds (3.92 hours)\n\nTimestep: 3340000\nmean reward (100 episodes): 3095.7200\nbest mean reward: 3095.7200\ncurrent episode reward: 5602.0000\nepisodes: 1582\nexploration: 0.04735\nlearning_rate: 0.00007\nelapsed time: 14141.6 seconds (3.93 hours)\n\nTimestep: 3350000\nmean reward (100 episodes): 3084.9000\nbest mean reward: 3112.1600\ncurrent episode reward: 3000.0000\nepisodes: 1584\nexploration: 0.04713\nlearning_rate: 0.00007\nelapsed time: 14186.7 seconds (3.94 hours)\n\nTimestep: 3360000\nmean reward (100 episodes): 3073.5400\nbest mean reward: 3112.1600\ncurrent episode reward: 1744.0000\nepisodes: 1587\nexploration: 0.04690\nlearning_rate: 0.00007\nelapsed time: 14232.2 seconds (3.95 hours)\n\nTimestep: 3370000\nmean reward (100 episodes): 3129.7800\nbest mean reward: 3129.7800\ncurrent episode reward: 4320.0000\nepisodes: 1589\nexploration: 0.04667\nlearning_rate: 0.00007\nelapsed time: 14276.5 seconds (3.97 hours)\n\nTimestep: 3380000\nmean reward (100 episodes): 3184.7800\nbest mean reward: 3184.7800\ncurrent episode reward: 3900.0000\nepisodes: 1592\nexploration: 0.04645\nlearning_rate: 0.00007\nelapsed time: 14321.2 seconds (3.98 hours)\n\nTimestep: 3390000\nmean reward (100 episodes): 3270.9800\nbest mean reward: 3270.9800\ncurrent episode reward: 5508.0000\nepisodes: 1594\nexploration: 0.04622\nlearning_rate: 0.00007\nelapsed time: 14366.0 seconds (3.99 hours)\n\nTimestep: 3400000\nmean reward (100 episodes): 3290.1400\nbest mean reward: 3293.7800\ncurrent episode reward: 1796.0000\nepisodes: 1596\nexploration: 0.04600\nlearning_rate: 0.00007\nelapsed time: 14410.4 seconds (4.00 hours)\n\nTimestep: 3410000\nmean reward (100 episodes): 3270.1400\nbest mean reward: 3293.7800\ncurrent episode reward: 4734.0000\nepisodes: 1599\nexploration: 0.04577\nlearning_rate: 0.00007\nelapsed time: 14455.7 seconds (4.02 hours)\n\nTimestep: 3420000\nmean reward (100 episodes): 3285.8400\nbest mean reward: 3293.7800\ncurrent episode reward: 4960.0000\nepisodes: 1601\nexploration: 0.04555\nlearning_rate: 0.00007\nelapsed time: 14500.0 seconds (4.03 hours)\n\nTimestep: 3430000\nmean reward (100 episodes): 3327.6200\nbest mean reward: 3327.6200\ncurrent episode reward: 5310.0000\nepisodes: 1604\nexploration: 0.04532\nlearning_rate: 0.00007\nelapsed time: 14544.9 seconds (4.04 hours)\n\nTimestep: 3440000\nmean reward (100 episodes): 3329.2600\nbest mean reward: 3329.2600\ncurrent episode reward: 2888.0000\nepisodes: 1608\nexploration: 0.04510\nlearning_rate: 0.00007\nelapsed time: 14589.1 seconds (4.05 hours)\n\nTimestep: 3450000\nmean reward (100 episodes): 3343.9000\nbest mean reward: 3343.9000\ncurrent episode reward: 3000.0000\nepisodes: 1610\nexploration: 0.04487\nlearning_rate: 0.00007\nelapsed time: 14634.1 seconds (4.07 hours)\n\nTimestep: 3460000\nmean reward (100 episodes): 3408.1400\nbest mean reward: 3408.1400\ncurrent episode reward: 5340.0000\nepisodes: 1612\nexploration: 0.04465\nlearning_rate: 0.00007\nelapsed time: 14679.7 seconds (4.08 hours)\n\nTimestep: 3470000\nmean reward (100 episodes): 3431.7800\nbest mean reward: 3431.7800\ncurrent episode reward: 1848.0000\nepisodes: 1614\nexploration: 0.04442\nlearning_rate: 0.00007\nelapsed time: 14724.5 seconds (4.09 hours)\n\nTimestep: 3480000\nmean reward (100 episodes): 3485.1200\nbest mean reward: 3495.0800\ncurrent episode reward: 2004.0000\nepisodes: 1617\nexploration: 0.04420\nlearning_rate: 0.00007\nelapsed time: 14770.1 seconds (4.10 hours)\n\nTimestep: 3490000\nmean reward (100 episodes): 3552.4400\nbest mean reward: 3552.4400\ncurrent episode reward: 6596.0000\nepisodes: 1619\nexploration: 0.04397\nlearning_rate: 0.00007\nelapsed time: 14814.7 seconds (4.12 hours)\n\nTimestep: 3500000\nmean reward (100 episodes): 3603.9800\nbest mean reward: 3603.9800\ncurrent episode reward: 5190.0000\nepisodes: 1621\nexploration: 0.04375\nlearning_rate: 0.00007\nelapsed time: 14859.7 seconds (4.13 hours)\n\nTimestep: 3510000\nmean reward (100 episodes): 3692.8200\nbest mean reward: 3692.8200\ncurrent episode reward: 5676.0000\nepisodes: 1623\nexploration: 0.04353\nlearning_rate: 0.00007\nelapsed time: 14905.3 seconds (4.14 hours)\n\nTimestep: 3520000\nmean reward (100 episodes): 3719.1000\nbest mean reward: 3719.1000\ncurrent episode reward: 4320.0000\nepisodes: 1625\nexploration: 0.04330\nlearning_rate: 0.00007\nelapsed time: 14950.5 seconds (4.15 hours)\n\nTimestep: 3530000\nmean reward (100 episodes): 3836.7400\nbest mean reward: 3836.7400\ncurrent episode reward: 5662.0000\nepisodes: 1628\nexploration: 0.04308\nlearning_rate: 0.00007\nelapsed time: 14994.8 seconds (4.17 hours)\n\nTimestep: 3540000\nmean reward (100 episodes): 3768.2400\nbest mean reward: 3836.7400\ncurrent episode reward: 2160.0000\nepisodes: 1631\nexploration: 0.04285\nlearning_rate: 0.00007\nelapsed time: 15039.9 seconds (4.18 hours)\n\nTimestep: 3550000\nmean reward (100 episodes): 3773.7600\nbest mean reward: 3836.7400\ncurrent episode reward: 1640.0000\nepisodes: 1634\nexploration: 0.04263\nlearning_rate: 0.00007\nelapsed time: 15085.1 seconds (4.19 hours)\n\nTimestep: 3560000\nmean reward (100 episodes): 3772.7000\nbest mean reward: 3836.7400\ncurrent episode reward: 4050.0000\nepisodes: 1636\nexploration: 0.04240\nlearning_rate: 0.00007\nelapsed time: 15130.0 seconds (4.20 hours)\n\nTimestep: 3570000\nmean reward (100 episodes): 3802.3800\nbest mean reward: 3836.7400\ncurrent episode reward: 5884.0000\nepisodes: 1638\nexploration: 0.04218\nlearning_rate: 0.00007\nelapsed time: 15175.5 seconds (4.22 hours)\n\nTimestep: 3580000\nmean reward (100 episodes): 3833.0800\nbest mean reward: 3836.7400\ncurrent episode reward: 4604.0000\nepisodes: 1640\nexploration: 0.04195\nlearning_rate: 0.00007\nelapsed time: 15220.7 seconds (4.23 hours)\n\nTimestep: 3590000\nmean reward (100 episodes): 3856.1600\nbest mean reward: 3856.1600\ncurrent episode reward: 5312.0000\nepisodes: 1642\nexploration: 0.04173\nlearning_rate: 0.00007\nelapsed time: 15265.5 seconds (4.24 hours)\n\nTimestep: 3600000\nmean reward (100 episodes): 3834.9600\nbest mean reward: 3856.1600\ncurrent episode reward: 5312.0000\nepisodes: 1644\nexploration: 0.04150\nlearning_rate: 0.00007\nelapsed time: 15310.2 seconds (4.25 hours)\n\nTimestep: 3610000\nmean reward (100 episodes): 3832.2800\nbest mean reward: 3859.1600\ncurrent episode reward: 3000.0000\nepisodes: 1647\nexploration: 0.04127\nlearning_rate: 0.00007\nelapsed time: 15355.4 seconds (4.27 hours)\n\nTimestep: 3620000\nmean reward (100 episodes): 3800.6200\nbest mean reward: 3859.1600\ncurrent episode reward: 4540.0000\nepisodes: 1650\nexploration: 0.04105\nlearning_rate: 0.00007\nelapsed time: 15400.1 seconds (4.28 hours)\n\nTimestep: 3630000\nmean reward (100 episodes): 3807.1000\nbest mean reward: 3859.1600\ncurrent episode reward: 3900.0000\nepisodes: 1652\nexploration: 0.04083\nlearning_rate: 0.00007\nelapsed time: 15444.9 seconds (4.29 hours)\n\nTimestep: 3640000\nmean reward (100 episodes): 3836.9400\nbest mean reward: 3859.1600\ncurrent episode reward: 3420.0000\nepisodes: 1655\nexploration: 0.04060\nlearning_rate: 0.00007\nelapsed time: 15490.7 seconds (4.30 hours)\n\nTimestep: 3650000\nmean reward (100 episodes): 3859.9400\nbest mean reward: 3860.0200\ncurrent episode reward: 5718.0000\nepisodes: 1657\nexploration: 0.04038\nlearning_rate: 0.00007\nelapsed time: 15535.2 seconds (4.32 hours)\n\nTimestep: 3660000\nmean reward (100 episodes): 3876.3000\nbest mean reward: 3876.3000\ncurrent episode reward: 4640.0000\nepisodes: 1659\nexploration: 0.04015\nlearning_rate: 0.00007\nelapsed time: 15580.4 seconds (4.33 hours)\n\nTimestep: 3670000\nmean reward (100 episodes): 3909.2000\nbest mean reward: 3909.2000\ncurrent episode reward: 5446.0000\nepisodes: 1661\nexploration: 0.03993\nlearning_rate: 0.00007\nelapsed time: 15626.2 seconds (4.34 hours)\n\nTimestep: 3680000\nmean reward (100 episodes): 3944.6800\nbest mean reward: 3944.6800\ncurrent episode reward: 5726.0000\nepisodes: 1664\nexploration: 0.03970\nlearning_rate: 0.00007\nelapsed time: 15670.9 seconds (4.35 hours)\n\nTimestep: 3690000\nmean reward (100 episodes): 3948.2800\nbest mean reward: 3948.2800\ncurrent episode reward: 4604.0000\nepisodes: 1666\nexploration: 0.03947\nlearning_rate: 0.00007\nelapsed time: 15716.3 seconds (4.37 hours)\n\nTimestep: 3700000\nmean reward (100 episodes): 3947.1200\nbest mean reward: 3948.2800\ncurrent episode reward: 4140.0000\nepisodes: 1668\nexploration: 0.03925\nlearning_rate: 0.00007\nelapsed time: 15761.9 seconds (4.38 hours)\n\nTimestep: 3710000\nmean reward (100 episodes): 3915.7800\nbest mean reward: 3977.6000\ncurrent episode reward: 1952.0000\nepisodes: 1671\nexploration: 0.03902\nlearning_rate: 0.00007\nelapsed time: 15807.2 seconds (4.39 hours)\n\nTimestep: 3720000\nmean reward (100 episodes): 3937.4600\nbest mean reward: 3977.6000\ncurrent episode reward: 5786.0000\nepisodes: 1673\nexploration: 0.03880\nlearning_rate: 0.00007\nelapsed time: 15852.2 seconds (4.40 hours)\n\nTimestep: 3730000\nmean reward (100 episodes): 3931.9000\nbest mean reward: 3977.6000\ncurrent episode reward: 3060.0000\nepisodes: 1674\nexploration: 0.03857\nlearning_rate: 0.00007\nelapsed time: 15897.5 seconds (4.42 hours)\n\nTimestep: 3740000\nmean reward (100 episodes): 4043.3200\nbest mean reward: 4043.3200\ncurrent episode reward: 8512.0000\nepisodes: 1676\nexploration: 0.03835\nlearning_rate: 0.00007\nelapsed time: 15942.8 seconds (4.43 hours)\n\nTimestep: 3750000\nmean reward (100 episodes): 4017.7600\nbest mean reward: 4045.5600\ncurrent episode reward: 1952.0000\nepisodes: 1680\nexploration: 0.03812\nlearning_rate: 0.00007\nelapsed time: 15987.0 seconds (4.44 hours)\n\nTimestep: 3760000\nmean reward (100 episodes): 4038.6000\nbest mean reward: 4045.5600\ncurrent episode reward: 6082.0000\nepisodes: 1682\nexploration: 0.03790\nlearning_rate: 0.00007\nelapsed time: 16033.3 seconds (4.45 hours)\n\nTimestep: 3770000\nmean reward (100 episodes): 4045.3400\nbest mean reward: 4045.5600\ncurrent episode reward: 5378.0000\nepisodes: 1684\nexploration: 0.03768\nlearning_rate: 0.00007\nelapsed time: 16079.1 seconds (4.47 hours)\n\nTimestep: 3780000\nmean reward (100 episodes): 4040.3200\nbest mean reward: 4045.5600\ncurrent episode reward: 3900.0000\nepisodes: 1687\nexploration: 0.03745\nlearning_rate: 0.00007\nelapsed time: 16123.5 seconds (4.48 hours)\n\nTimestep: 3790000\nmean reward (100 episodes): 4046.7200\nbest mean reward: 4059.9200\ncurrent episode reward: 3000.0000\nepisodes: 1689\nexploration: 0.03722\nlearning_rate: 0.00007\nelapsed time: 16168.0 seconds (4.49 hours)\n\nTimestep: 3800000\nmean reward (100 episodes): 4086.8800\nbest mean reward: 4086.8800\ncurrent episode reward: 6576.0000\nepisodes: 1691\nexploration: 0.03700\nlearning_rate: 0.00007\nelapsed time: 16212.9 seconds (4.50 hours)\n\nTimestep: 3810000\nmean reward (100 episodes): 4062.3200\nbest mean reward: 4086.8800\ncurrent episode reward: 4960.0000\nepisodes: 1694\nexploration: 0.03678\nlearning_rate: 0.00006\nelapsed time: 16256.9 seconds (4.52 hours)\n\nTimestep: 3820000\nmean reward (100 episodes): 4100.0600\nbest mean reward: 4100.0600\ncurrent episode reward: 3900.0000\nepisodes: 1696\nexploration: 0.03655\nlearning_rate: 0.00006\nelapsed time: 16301.2 seconds (4.53 hours)\n\nTimestep: 3830000\nmean reward (100 episodes): 4082.9000\nbest mean reward: 4110.2000\ncurrent episode reward: 2004.0000\nepisodes: 1699\nexploration: 0.03632\nlearning_rate: 0.00006\nelapsed time: 16345.9 seconds (4.54 hours)\n\nTimestep: 3840000\nmean reward (100 episodes): 4064.1400\nbest mean reward: 4110.2000\ncurrent episode reward: 3660.0000\nepisodes: 1702\nexploration: 0.03610\nlearning_rate: 0.00006\nelapsed time: 16390.9 seconds (4.55 hours)\n\nTimestep: 3850000\nmean reward (100 episodes): 4058.4400\nbest mean reward: 4110.2000\ncurrent episode reward: 3900.0000\nepisodes: 1704\nexploration: 0.03587\nlearning_rate: 0.00006\nelapsed time: 16435.6 seconds (4.57 hours)\n\nTimestep: 3860000\nmean reward (100 episodes): 4135.4400\nbest mean reward: 4135.4400\ncurrent episode reward: 4156.0000\nepisodes: 1707\nexploration: 0.03565\nlearning_rate: 0.00006\nelapsed time: 16480.9 seconds (4.58 hours)\n\nTimestep: 3870000\nmean reward (100 episodes): 4150.8200\nbest mean reward: 4165.4600\ncurrent episode reward: 1536.0000\nepisodes: 1710\nexploration: 0.03542\nlearning_rate: 0.00006\nelapsed time: 16526.5 seconds (4.59 hours)\n\nTimestep: 3880000\nmean reward (100 episodes): 4146.6800\nbest mean reward: 4165.4600\ncurrent episode reward: 4448.0000\nepisodes: 1712\nexploration: 0.03520\nlearning_rate: 0.00006\nelapsed time: 16571.5 seconds (4.60 hours)\n\nTimestep: 3890000\nmean reward (100 episodes): 4199.0600\nbest mean reward: 4199.0600\ncurrent episode reward: 6894.0000\nepisodes: 1714\nexploration: 0.03497\nlearning_rate: 0.00006\nelapsed time: 16617.0 seconds (4.62 hours)\n\nTimestep: 3900000\nmean reward (100 episodes): 4227.4400\nbest mean reward: 4227.4400\ncurrent episode reward: 6978.0000\nepisodes: 1715\nexploration: 0.03475\nlearning_rate: 0.00006\nelapsed time: 16661.8 seconds (4.63 hours)\n\nTimestep: 3910000\nmean reward (100 episodes): 4259.0000\nbest mean reward: 4259.0000\ncurrent episode reward: 6164.0000\nepisodes: 1717\nexploration: 0.03453\nlearning_rate: 0.00006\nelapsed time: 16706.9 seconds (4.64 hours)\n\nTimestep: 3920000\nmean reward (100 episodes): 4187.5800\nbest mean reward: 4259.0000\ncurrent episode reward: 2160.0000\nepisodes: 1720\nexploration: 0.03430\nlearning_rate: 0.00006\nelapsed time: 16751.8 seconds (4.65 hours)\n\nTimestep: 3930000\nmean reward (100 episodes): 4171.6600\nbest mean reward: 4259.0000\ncurrent episode reward: 4350.0000\nepisodes: 1722\nexploration: 0.03407\nlearning_rate: 0.00006\nelapsed time: 16796.3 seconds (4.67 hours)\n\nTimestep: 3940000\nmean reward (100 episodes): 4200.7800\nbest mean reward: 4259.0000\ncurrent episode reward: 4996.0000\nepisodes: 1724\nexploration: 0.03385\nlearning_rate: 0.00006\nelapsed time: 16841.3 seconds (4.68 hours)\n\nTimestep: 3950000\nmean reward (100 episodes): 4214.2400\nbest mean reward: 4259.0000\ncurrent episode reward: 4768.0000\nepisodes: 1726\nexploration: 0.03362\nlearning_rate: 0.00006\nelapsed time: 16887.2 seconds (4.69 hours)\n\nTimestep: 3960000\nmean reward (100 episodes): 4199.1800\nbest mean reward: 4259.0000\ncurrent episode reward: 4092.0000\nepisodes: 1728\nexploration: 0.03340\nlearning_rate: 0.00006\nelapsed time: 16931.6 seconds (4.70 hours)\n\nTimestep: 3970000\nmean reward (100 episodes): 4241.4600\nbest mean reward: 4259.0000\ncurrent episode reward: 3900.0000\nepisodes: 1731\nexploration: 0.03317\nlearning_rate: 0.00006\nelapsed time: 16976.5 seconds (4.72 hours)\n\nTimestep: 3980000\nmean reward (100 episodes): 4270.8600\nbest mean reward: 4270.8600\ncurrent episode reward: 6780.0000\nepisodes: 1732\nexploration: 0.03295\nlearning_rate: 0.00006\nelapsed time: 17022.1 seconds (4.73 hours)\n\nTimestep: 3990000\nmean reward (100 episodes): 4341.7600\nbest mean reward: 4341.7600\ncurrent episode reward: 4220.0000\nepisodes: 1734\nexploration: 0.03272\nlearning_rate: 0.00006\nelapsed time: 17066.8 seconds (4.74 hours)\n\nTimestep: 4000000\nmean reward (100 episodes): 4367.6000\nbest mean reward: 4367.6000\ncurrent episode reward: 3720.0000\nepisodes: 1737\nexploration: 0.03250\nlearning_rate: 0.00006\nelapsed time: 17112.4 seconds (4.75 hours)\n\nTimestep: 4010000\nmean reward (100 episodes): 4378.9400\nbest mean reward: 4379.2400\ncurrent episode reward: 4670.0000\nepisodes: 1739\nexploration: 0.03227\nlearning_rate: 0.00006\nelapsed time: 17157.9 seconds (4.77 hours)\n\nTimestep: 4020000\nmean reward (100 episodes): 4393.4800\nbest mean reward: 4417.1400\ncurrent episode reward: 2944.0000\nepisodes: 1741\nexploration: 0.03205\nlearning_rate: 0.00006\nelapsed time: 17203.2 seconds (4.78 hours)\n\nTimestep: 4030000\nmean reward (100 episodes): 4423.6000\nbest mean reward: 4423.6000\ncurrent episode reward: 5440.0000\nepisodes: 1743\nexploration: 0.03183\nlearning_rate: 0.00006\nelapsed time: 17247.8 seconds (4.79 hours)\n\nTimestep: 4040000\nmean reward (100 episodes): 4413.9800\nbest mean reward: 4424.5800\ncurrent episode reward: 4220.0000\nepisodes: 1745\nexploration: 0.03160\nlearning_rate: 0.00006\nelapsed time: 17293.0 seconds (4.80 hours)\n\nTimestep: 4050000\nmean reward (100 episodes): 4435.3800\nbest mean reward: 4435.3800\ncurrent episode reward: 5952.0000\nepisodes: 1747\nexploration: 0.03138\nlearning_rate: 0.00006\nelapsed time: 17337.7 seconds (4.82 hours)\n\nTimestep: 4060000\nmean reward (100 episodes): 4485.5600\nbest mean reward: 4485.5600\ncurrent episode reward: 5064.0000\nepisodes: 1750\nexploration: 0.03115\nlearning_rate: 0.00006\nelapsed time: 17382.4 seconds (4.83 hours)\n\nTimestep: 4070000\nmean reward (100 episodes): 4522.8600\nbest mean reward: 4522.8600\ncurrent episode reward: 6562.0000\nepisodes: 1751\nexploration: 0.03092\nlearning_rate: 0.00006\nelapsed time: 17428.1 seconds (4.84 hours)\n\nTimestep: 4080000\nmean reward (100 episodes): 4580.2400\nbest mean reward: 4580.2400\ncurrent episode reward: 6840.0000\nepisodes: 1753\nexploration: 0.03070\nlearning_rate: 0.00006\nelapsed time: 17473.2 seconds (4.85 hours)\n\nTimestep: 4090000\nmean reward (100 episodes): 4625.4200\nbest mean reward: 4625.4200\ncurrent episode reward: 4832.0000\nepisodes: 1755\nexploration: 0.03048\nlearning_rate: 0.00006\nelapsed time: 17518.7 seconds (4.87 hours)\n\nTimestep: 4100000\nmean reward (100 episodes): 4581.6000\nbest mean reward: 4625.4200\ncurrent episode reward: 2160.0000\nepisodes: 1758\nexploration: 0.03025\nlearning_rate: 0.00006\nelapsed time: 17564.4 seconds (4.88 hours)\n\nTimestep: 4110000\nmean reward (100 episodes): 4597.2800\nbest mean reward: 4625.4200\ncurrent episode reward: 5084.0000\nepisodes: 1760\nexploration: 0.03002\nlearning_rate: 0.00006\nelapsed time: 17609.6 seconds (4.89 hours)\n\nTimestep: 4120000\nmean reward (100 episodes): 4591.1600\nbest mean reward: 4625.4200\ncurrent episode reward: 4410.0000\nepisodes: 1762\nexploration: 0.02980\nlearning_rate: 0.00006\nelapsed time: 17655.1 seconds (4.90 hours)\n\nTimestep: 4130000\nmean reward (100 episodes): 4611.1000\nbest mean reward: 4625.4200\ncurrent episode reward: 6780.0000\nepisodes: 1764\nexploration: 0.02958\nlearning_rate: 0.00006\nelapsed time: 17700.2 seconds (4.92 hours)\n\nTimestep: 4140000\nmean reward (100 episodes): 4646.6800\nbest mean reward: 4646.6800\ncurrent episode reward: 7834.0000\nepisodes: 1766\nexploration: 0.02935\nlearning_rate: 0.00006\nelapsed time: 17745.7 seconds (4.93 hours)\n\nTimestep: 4150000\nmean reward (100 episodes): 4655.6000\nbest mean reward: 4655.6000\ncurrent episode reward: 4576.0000\nepisodes: 1768\nexploration: 0.02912\nlearning_rate: 0.00006\nelapsed time: 17790.7 seconds (4.94 hours)\n\nTimestep: 4160000\nmean reward (100 episodes): 4689.7400\nbest mean reward: 4689.7400\ncurrent episode reward: 8214.0000\nepisodes: 1770\nexploration: 0.02890\nlearning_rate: 0.00006\nelapsed time: 17834.9 seconds (4.95 hours)\n\nTimestep: 4170000\nmean reward (100 episodes): 4685.8200\nbest mean reward: 4713.7200\ncurrent episode reward: 3240.0000\nepisodes: 1773\nexploration: 0.02867\nlearning_rate: 0.00006\nelapsed time: 17879.9 seconds (4.97 hours)\n\nTimestep: 4180000\nmean reward (100 episodes): 4641.6400\nbest mean reward: 4713.7200\ncurrent episode reward: 4092.0000\nepisodes: 1775\nexploration: 0.02845\nlearning_rate: 0.00006\nelapsed time: 17925.6 seconds (4.98 hours)\n\nTimestep: 4190000\nmean reward (100 episodes): 4628.2400\nbest mean reward: 4713.7200\ncurrent episode reward: 4704.0000\nepisodes: 1777\nexploration: 0.02823\nlearning_rate: 0.00006\nelapsed time: 17970.6 seconds (4.99 hours)\n\nTimestep: 4200000\nmean reward (100 episodes): 4694.8400\nbest mean reward: 4713.7200\ncurrent episode reward: 5408.0000\nepisodes: 1779\nexploration: 0.02800\nlearning_rate: 0.00006\nelapsed time: 18015.7 seconds (5.00 hours)\n\nTimestep: 4210000\nmean reward (100 episodes): 4718.8000\nbest mean reward: 4739.1200\ncurrent episode reward: 4050.0000\nepisodes: 1782\nexploration: 0.02777\nlearning_rate: 0.00006\nelapsed time: 18061.0 seconds (5.02 hours)\n\nTimestep: 4220000\nmean reward (100 episodes): 4743.8200\nbest mean reward: 4743.8200\ncurrent episode reward: 6342.0000\nepisodes: 1783\nexploration: 0.02755\nlearning_rate: 0.00006\nelapsed time: 18106.1 seconds (5.03 hours)\n\nTimestep: 4230000\nmean reward (100 episodes): 4843.8200\nbest mean reward: 4843.8200\ncurrent episode reward: 6728.0000\nepisodes: 1785\nexploration: 0.02733\nlearning_rate: 0.00006\nelapsed time: 18151.3 seconds (5.04 hours)\n\nTimestep: 4240000\nmean reward (100 episodes): 4868.9400\nbest mean reward: 4873.7400\ncurrent episode reward: 5700.0000\nepisodes: 1788\nexploration: 0.02710\nlearning_rate: 0.00006\nelapsed time: 18196.5 seconds (5.05 hours)\n\nTimestep: 4250000\nmean reward (100 episodes): 4917.0200\nbest mean reward: 4917.0200\ncurrent episode reward: 6810.0000\nepisodes: 1790\nexploration: 0.02687\nlearning_rate: 0.00006\nelapsed time: 18241.3 seconds (5.07 hours)\n\nTimestep: 4260000\nmean reward (100 episodes): 4937.8600\nbest mean reward: 4937.8600\ncurrent episode reward: 8660.0000\nepisodes: 1791\nexploration: 0.02665\nlearning_rate: 0.00006\nelapsed time: 18286.7 seconds (5.08 hours)\n\nTimestep: 4270000\nmean reward (100 episodes): 4950.8600\nbest mean reward: 4950.8600\ncurrent episode reward: 5744.0000\nepisodes: 1793\nexploration: 0.02642\nlearning_rate: 0.00006\nelapsed time: 18332.0 seconds (5.09 hours)\n\nTimestep: 4280000\nmean reward (100 episodes): 4941.8800\nbest mean reward: 4950.8600\ncurrent episode reward: 4260.0000\nepisodes: 1795\nexploration: 0.02620\nlearning_rate: 0.00006\nelapsed time: 18377.4 seconds (5.10 hours)\n\nTimestep: 4290000\nmean reward (100 episodes): 4975.3000\nbest mean reward: 4975.3000\ncurrent episode reward: 5926.0000\nepisodes: 1797\nexploration: 0.02597\nlearning_rate: 0.00006\nelapsed time: 18423.2 seconds (5.12 hours)\n\nTimestep: 4300000\nmean reward (100 episodes): 5046.3600\nbest mean reward: 5046.3600\ncurrent episode reward: 4200.0000\nepisodes: 1799\nexploration: 0.02575\nlearning_rate: 0.00006\nelapsed time: 18468.7 seconds (5.13 hours)\n\nTimestep: 4310000\nmean reward (100 episodes): 5088.2400\nbest mean reward: 5088.2400\ncurrent episode reward: 2832.0000\nepisodes: 1801\nexploration: 0.02552\nlearning_rate: 0.00006\nelapsed time: 18513.8 seconds (5.14 hours)\n\nTimestep: 4320000\nmean reward (100 episodes): 5159.4400\nbest mean reward: 5159.4400\ncurrent episode reward: 5200.0000\nepisodes: 1803\nexploration: 0.02530\nlearning_rate: 0.00006\nelapsed time: 18558.2 seconds (5.16 hours)\n\nTimestep: 4330000\nmean reward (100 episodes): 5175.3200\nbest mean reward: 5179.7800\ncurrent episode reward: 5054.0000\nepisodes: 1805\nexploration: 0.02508\nlearning_rate: 0.00006\nelapsed time: 18603.7 seconds (5.17 hours)\n\nTimestep: 4340000\nmean reward (100 episodes): 5210.8400\nbest mean reward: 5210.8400\ncurrent episode reward: 5820.0000\nepisodes: 1807\nexploration: 0.02485\nlearning_rate: 0.00006\nelapsed time: 18649.2 seconds (5.18 hours)\n\nTimestep: 4350000\nmean reward (100 episodes): 5216.5600\nbest mean reward: 5217.4800\ncurrent episode reward: 5378.0000\nepisodes: 1809\nexploration: 0.02462\nlearning_rate: 0.00006\nelapsed time: 18694.2 seconds (5.19 hours)\n\nTimestep: 4360000\nmean reward (100 episodes): 5267.9000\nbest mean reward: 5267.9000\ncurrent episode reward: 5484.0000\nepisodes: 1811\nexploration: 0.02440\nlearning_rate: 0.00006\nelapsed time: 18738.6 seconds (5.21 hours)\n\nTimestep: 4370000\nmean reward (100 episodes): 5342.8200\nbest mean reward: 5342.8200\ncurrent episode reward: 10302.0000\nepisodes: 1813\nexploration: 0.02417\nlearning_rate: 0.00006\nelapsed time: 18784.3 seconds (5.22 hours)\n\nTimestep: 4380000\nmean reward (100 episodes): 5258.9600\nbest mean reward: 5342.8200\ncurrent episode reward: 1900.0000\nepisodes: 1816\nexploration: 0.02395\nlearning_rate: 0.00006\nelapsed time: 18829.5 seconds (5.23 hours)\n\nTimestep: 4390000\nmean reward (100 episodes): 5283.2000\nbest mean reward: 5342.8200\ncurrent episode reward: 7182.0000\nepisodes: 1818\nexploration: 0.02372\nlearning_rate: 0.00006\nelapsed time: 18874.9 seconds (5.24 hours)\n\nTimestep: 4400000\nmean reward (100 episodes): 5305.2000\nbest mean reward: 5342.8200\ncurrent episode reward: 6100.0000\nepisodes: 1819\nexploration: 0.02350\nlearning_rate: 0.00006\nelapsed time: 18919.7 seconds (5.26 hours)\n\nTimestep: 4410000\nmean reward (100 episodes): 5366.6200\nbest mean reward: 5374.6000\ncurrent episode reward: 4542.0000\nepisodes: 1821\nexploration: 0.02327\nlearning_rate: 0.00006\nelapsed time: 18964.6 seconds (5.27 hours)\n\nTimestep: 4420000\nmean reward (100 episodes): 5359.5600\nbest mean reward: 5374.6000\ncurrent episode reward: 4156.0000\nepisodes: 1823\nexploration: 0.02305\nlearning_rate: 0.00006\nelapsed time: 19010.1 seconds (5.28 hours)\n\nTimestep: 4430000\nmean reward (100 episodes): 5412.8000\nbest mean reward: 5412.8000\ncurrent episode reward: 10320.0000\nepisodes: 1824\nexploration: 0.02282\nlearning_rate: 0.00006\nelapsed time: 19054.5 seconds (5.29 hours)\n\nTimestep: 4440000\nmean reward (100 episodes): 5429.3200\nbest mean reward: 5442.4000\ncurrent episode reward: 4732.0000\nepisodes: 1827\nexploration: 0.02260\nlearning_rate: 0.00006\nelapsed time: 19100.2 seconds (5.31 hours)\n\nTimestep: 4450000\nmean reward (100 episodes): 5481.8000\nbest mean reward: 5481.8000\ncurrent episode reward: 7800.0000\nepisodes: 1829\nexploration: 0.02237\nlearning_rate: 0.00006\nelapsed time: 19144.8 seconds (5.32 hours)\n\nTimestep: 4460000\nmean reward (100 episodes): 5531.2200\nbest mean reward: 5536.0200\ncurrent episode reward: 3420.0000\nepisodes: 1831\nexploration: 0.02215\nlearning_rate: 0.00006\nelapsed time: 19189.9 seconds (5.33 hours)\n\nTimestep: 4470000\nmean reward (100 episodes): 5491.9400\nbest mean reward: 5536.0200\ncurrent episode reward: 5602.0000\nepisodes: 1833\nexploration: 0.02192\nlearning_rate: 0.00006\nelapsed time: 19235.0 seconds (5.34 hours)\n\nTimestep: 4480000\nmean reward (100 episodes): 5512.6800\nbest mean reward: 5536.0200\ncurrent episode reward: 4860.0000\nepisodes: 1835\nexploration: 0.02170\nlearning_rate: 0.00006\nelapsed time: 19280.7 seconds (5.36 hours)\n\nTimestep: 4490000\nmean reward (100 episodes): 5552.7600\nbest mean reward: 5552.7600\ncurrent episode reward: 5540.0000\nepisodes: 1837\nexploration: 0.02147\nlearning_rate: 0.00006\nelapsed time: 19326.0 seconds (5.37 hours)\n\nTimestep: 4500000\nmean reward (100 episodes): 5510.5800\nbest mean reward: 5552.7600\ncurrent episode reward: 5340.0000\nepisodes: 1839\nexploration: 0.02125\nlearning_rate: 0.00006\nelapsed time: 19371.4 seconds (5.38 hours)\n\nTimestep: 4510000\nmean reward (100 episodes): 5544.8600\nbest mean reward: 5552.7600\ncurrent episode reward: 9486.0000\nepisodes: 1841\nexploration: 0.02103\nlearning_rate: 0.00006\nelapsed time: 19416.3 seconds (5.39 hours)\n\nTimestep: 4520000\nmean reward (100 episodes): 5528.9400\nbest mean reward: 5552.7600\ncurrent episode reward: 6732.0000\nepisodes: 1843\nexploration: 0.02080\nlearning_rate: 0.00006\nelapsed time: 19461.1 seconds (5.41 hours)\n\nTimestep: 4530000\nmean reward (100 episodes): 5551.9600\nbest mean reward: 5552.7600\ncurrent episode reward: 5744.0000\nepisodes: 1846\nexploration: 0.02057\nlearning_rate: 0.00006\nelapsed time: 19506.8 seconds (5.42 hours)\n\nTimestep: 4540000\nmean reward (100 episodes): 5526.4600\nbest mean reward: 5552.7600\ncurrent episode reward: 4560.0000\nepisodes: 1848\nexploration: 0.02035\nlearning_rate: 0.00006\nelapsed time: 19551.7 seconds (5.43 hours)\n\nTimestep: 4550000\nmean reward (100 episodes): 5532.4600\nbest mean reward: 5552.7600\ncurrent episode reward: 4320.0000\nepisodes: 1849\nexploration: 0.02013\nlearning_rate: 0.00006\nelapsed time: 19596.1 seconds (5.44 hours)\n\nTimestep: 4560000\nmean reward (100 episodes): 5588.2400\nbest mean reward: 5603.6200\ncurrent episode reward: 5024.0000\nepisodes: 1851\nexploration: 0.01990\nlearning_rate: 0.00006\nelapsed time: 19641.5 seconds (5.46 hours)\n\nTimestep: 4570000\nmean reward (100 episodes): 5584.2000\nbest mean reward: 5603.6200\ncurrent episode reward: 7164.0000\nepisodes: 1852\nexploration: 0.01967\nlearning_rate: 0.00006\nelapsed time: 19686.5 seconds (5.47 hours)\n\nTimestep: 4580000\nmean reward (100 episodes): 5593.0600\nbest mean reward: 5610.3800\ncurrent episode reward: 6300.0000\nepisodes: 1854\nexploration: 0.01945\nlearning_rate: 0.00006\nelapsed time: 19731.5 seconds (5.48 hours)\n\nTimestep: 4590000\nmean reward (100 episodes): 5625.1600\nbest mean reward: 5625.1600\ncurrent episode reward: 3060.0000\nepisodes: 1856\nexploration: 0.01923\nlearning_rate: 0.00006\nelapsed time: 19776.4 seconds (5.49 hours)\n\nTimestep: 4600000\nmean reward (100 episodes): 5637.3000\nbest mean reward: 5637.3000\ncurrent episode reward: 5154.0000\nepisodes: 1859\nexploration: 0.01900\nlearning_rate: 0.00006\nelapsed time: 19821.3 seconds (5.51 hours)\n\nTimestep: 4610000\nmean reward (100 episodes): 5633.4000\nbest mean reward: 5639.2600\ncurrent episode reward: 4478.0000\nepisodes: 1861\nexploration: 0.01878\nlearning_rate: 0.00005\nelapsed time: 19866.2 seconds (5.52 hours)\n\nTimestep: 4620000\nmean reward (100 episodes): 5682.3000\nbest mean reward: 5687.9000\ncurrent episode reward: 4640.0000\nepisodes: 1863\nexploration: 0.01855\nlearning_rate: 0.00005\nelapsed time: 19912.0 seconds (5.53 hours)\n\nTimestep: 4630000\nmean reward (100 episodes): 5701.6200\nbest mean reward: 5701.6200\ncurrent episode reward: 8712.0000\nepisodes: 1864\nexploration: 0.01832\nlearning_rate: 0.00005\nelapsed time: 19958.1 seconds (5.54 hours)\n\nTimestep: 4640000\nmean reward (100 episodes): 5699.1400\nbest mean reward: 5725.3200\ncurrent episode reward: 5216.0000\nepisodes: 1866\nexploration: 0.01810\nlearning_rate: 0.00005\nelapsed time: 20003.8 seconds (5.56 hours)\n\nTimestep: 4650000\nmean reward (100 episodes): 5742.2200\nbest mean reward: 5742.2200\ncurrent episode reward: 5700.0000\nepisodes: 1869\nexploration: 0.01788\nlearning_rate: 0.00005\nelapsed time: 20048.9 seconds (5.57 hours)\n\nTimestep: 4660000\nmean reward (100 episodes): 5715.0600\nbest mean reward: 5742.2200\ncurrent episode reward: 5756.0000\nepisodes: 1871\nexploration: 0.01765\nlearning_rate: 0.00005\nelapsed time: 20094.9 seconds (5.58 hours)\n\nTimestep: 4670000\nmean reward (100 episodes): 5762.2800\nbest mean reward: 5762.2800\ncurrent episode reward: 6062.0000\nepisodes: 1873\nexploration: 0.01742\nlearning_rate: 0.00005\nelapsed time: 20140.4 seconds (5.59 hours)\n\nTimestep: 4680000\nmean reward (100 episodes): 5780.3800\nbest mean reward: 5780.3800\ncurrent episode reward: 5410.0000\nepisodes: 1874\nexploration: 0.01720\nlearning_rate: 0.00005\nelapsed time: 20185.9 seconds (5.61 hours)\n\nTimestep: 4690000\nmean reward (100 episodes): 5826.4600\nbest mean reward: 5881.3400\ncurrent episode reward: 1796.0000\nepisodes: 1877\nexploration: 0.01697\nlearning_rate: 0.00005\nelapsed time: 20230.8 seconds (5.62 hours)\n\nTimestep: 4700000\nmean reward (100 episodes): 5834.4400\nbest mean reward: 5881.3400\ncurrent episode reward: 7098.0000\nepisodes: 1878\nexploration: 0.01675\nlearning_rate: 0.00005\nelapsed time: 20276.2 seconds (5.63 hours)\n\nTimestep: 4710000\nmean reward (100 episodes): 5843.0800\nbest mean reward: 5881.3400\ncurrent episode reward: 5280.0000\nepisodes: 1881\nexploration: 0.01652\nlearning_rate: 0.00005\nelapsed time: 20321.2 seconds (5.64 hours)\n\nTimestep: 4720000\nmean reward (100 episodes): 5816.5800\nbest mean reward: 5881.3400\ncurrent episode reward: 2552.0000\nepisodes: 1883\nexploration: 0.01630\nlearning_rate: 0.00005\nelapsed time: 20366.0 seconds (5.66 hours)\n\nTimestep: 4730000\nmean reward (100 episodes): 5783.9600\nbest mean reward: 5881.3400\ncurrent episode reward: 6096.0000\nepisodes: 1885\nexploration: 0.01607\nlearning_rate: 0.00005\nelapsed time: 20411.4 seconds (5.67 hours)\n\nTimestep: 4740000\nmean reward (100 episodes): 5790.5800\nbest mean reward: 5881.3400\ncurrent episode reward: 4796.0000\nepisodes: 1887\nexploration: 0.01585\nlearning_rate: 0.00005\nelapsed time: 20456.4 seconds (5.68 hours)\n\nTimestep: 4750000\nmean reward (100 episodes): 5786.0800\nbest mean reward: 5881.3400\ncurrent episode reward: 4576.0000\nepisodes: 1889\nexploration: 0.01562\nlearning_rate: 0.00005\nelapsed time: 20502.6 seconds (5.70 hours)\n\nTimestep: 4760000\nmean reward (100 episodes): 5785.3000\nbest mean reward: 5881.3400\ncurrent episode reward: 6732.0000\nepisodes: 1890\nexploration: 0.01540\nlearning_rate: 0.00005\nelapsed time: 20547.6 seconds (5.71 hours)\n\nTimestep: 4770000\nmean reward (100 episodes): 5876.4000\nbest mean reward: 5881.3400\ncurrent episode reward: 5880.0000\nepisodes: 1892\nexploration: 0.01517\nlearning_rate: 0.00005\nelapsed time: 20592.6 seconds (5.72 hours)\n\nTimestep: 4780000\nmean reward (100 episodes): 5871.4800\nbest mean reward: 5881.3400\ncurrent episode reward: 5280.0000\nepisodes: 1894\nexploration: 0.01495\nlearning_rate: 0.00005\nelapsed time: 20638.4 seconds (5.73 hours)\n\nTimestep: 4790000\nmean reward (100 episodes): 5914.6400\nbest mean reward: 5927.1800\ncurrent episode reward: 4412.0000\nepisodes: 1896\nexploration: 0.01472\nlearning_rate: 0.00005\nelapsed time: 20684.0 seconds (5.75 hours)\n\nTimestep: 4800000\nmean reward (100 episodes): 5885.0600\nbest mean reward: 5927.1800\ncurrent episode reward: 3300.0000\nepisodes: 1898\nexploration: 0.01450\nlearning_rate: 0.00005\nelapsed time: 20729.7 seconds (5.76 hours)\n\nTimestep: 4810000\nmean reward (100 episodes): 5907.4600\nbest mean reward: 5927.1800\ncurrent episode reward: 10230.0000\nepisodes: 1900\nexploration: 0.01427\nlearning_rate: 0.00005\nelapsed time: 20775.7 seconds (5.77 hours)\n\nTimestep: 4820000\nmean reward (100 episodes): 5930.6800\nbest mean reward: 5930.6800\ncurrent episode reward: 5154.0000\nepisodes: 1901\nexploration: 0.01405\nlearning_rate: 0.00005\nelapsed time: 20820.8 seconds (5.78 hours)\n\nTimestep: 4830000\nmean reward (100 episodes): 5914.8200\nbest mean reward: 5942.7600\ncurrent episode reward: 3140.0000\nepisodes: 1904\nexploration: 0.01382\nlearning_rate: 0.00005\nelapsed time: 20866.0 seconds (5.80 hours)\n\nTimestep: 4840000\nmean reward (100 episodes): 5902.0400\nbest mean reward: 5942.7600\ncurrent episode reward: 3360.0000\nepisodes: 1906\nexploration: 0.01360\nlearning_rate: 0.00005\nelapsed time: 20911.7 seconds (5.81 hours)\n\nTimestep: 4850000\nmean reward (100 episodes): 5865.5600\nbest mean reward: 5942.7600\ncurrent episode reward: 3000.0000\nepisodes: 1908\nexploration: 0.01337\nlearning_rate: 0.00005\nelapsed time: 20957.1 seconds (5.82 hours)\n\nTimestep: 4860000\nmean reward (100 episodes): 5867.4000\nbest mean reward: 5942.7600\ncurrent episode reward: 5246.0000\nepisodes: 1910\nexploration: 0.01315\nlearning_rate: 0.00005\nelapsed time: 21002.2 seconds (5.83 hours)\n\nTimestep: 4870000\nmean reward (100 episodes): 5814.4000\nbest mean reward: 5942.7600\ncurrent episode reward: 4448.0000\nepisodes: 1913\nexploration: 0.01292\nlearning_rate: 0.00005\nelapsed time: 21047.3 seconds (5.85 hours)\n\nTimestep: 4880000\nmean reward (100 episodes): 5855.0800\nbest mean reward: 5942.7600\ncurrent episode reward: 8224.0000\nepisodes: 1914\nexploration: 0.01270\nlearning_rate: 0.00005\nelapsed time: 21092.6 seconds (5.86 hours)\n\nTimestep: 4890000\nmean reward (100 episodes): 5963.2600\nbest mean reward: 5963.2600\ncurrent episode reward: 8024.0000\nepisodes: 1916\nexploration: 0.01247\nlearning_rate: 0.00005\nelapsed time: 21137.7 seconds (5.87 hours)\n\nTimestep: 4900000\nmean reward (100 episodes): 5949.6000\nbest mean reward: 5963.2600\ncurrent episode reward: 5820.0000\nepisodes: 1918\nexploration: 0.01225\nlearning_rate: 0.00005\nelapsed time: 21182.8 seconds (5.88 hours)\n\nTimestep: 4910000\nmean reward (100 episodes): 5856.1400\nbest mean reward: 5963.2600\ncurrent episode reward: 3600.0000\nepisodes: 1921\nexploration: 0.01202\nlearning_rate: 0.00005\nelapsed time: 21227.8 seconds (5.90 hours)\n\nTimestep: 4920000\nmean reward (100 episodes): 5854.2000\nbest mean reward: 5963.2600\ncurrent episode reward: 6002.0000\nepisodes: 1923\nexploration: 0.01180\nlearning_rate: 0.00005\nelapsed time: 21272.9 seconds (5.91 hours)\n\nTimestep: 4930000\nmean reward (100 episodes): 5786.5000\nbest mean reward: 5963.2600\ncurrent episode reward: 3840.0000\nepisodes: 1925\nexploration: 0.01157\nlearning_rate: 0.00005\nelapsed time: 21318.1 seconds (5.92 hours)\n\nTimestep: 4940000\nmean reward (100 episodes): 5831.2200\nbest mean reward: 5963.2600\ncurrent episode reward: 5340.0000\nepisodes: 1927\nexploration: 0.01135\nlearning_rate: 0.00005\nelapsed time: 21363.9 seconds (5.93 hours)\n\nTimestep: 4950000\nmean reward (100 episodes): 5846.7800\nbest mean reward: 5963.2600\ncurrent episode reward: 7188.0000\nepisodes: 1928\nexploration: 0.01112\nlearning_rate: 0.00005\nelapsed time: 21408.5 seconds (5.95 hours)\n\nTimestep: 4960000\nmean reward (100 episodes): 5866.6000\nbest mean reward: 5963.2600\ncurrent episode reward: 5280.0000\nepisodes: 1930\nexploration: 0.01090\nlearning_rate: 0.00005\nelapsed time: 21453.5 seconds (5.96 hours)\n\nTimestep: 4970000\nmean reward (100 episodes): 5930.1400\nbest mean reward: 5963.2600\ncurrent episode reward: 6096.0000\nepisodes: 1932\nexploration: 0.01067\nlearning_rate: 0.00005\nelapsed time: 21498.7 seconds (5.97 hours)\n\nTimestep: 4980000\nmean reward (100 episodes): 5962.8200\nbest mean reward: 5963.2600\ncurrent episode reward: 8870.0000\nepisodes: 1933\nexploration: 0.01045\nlearning_rate: 0.00005\nelapsed time: 21544.1 seconds (5.98 hours)\n\nTimestep: 4990000\nmean reward (100 episodes): 5947.0800\nbest mean reward: 5963.2600\ncurrent episode reward: 5152.0000\nepisodes: 1935\nexploration: 0.01022\nlearning_rate: 0.00005\nelapsed time: 21589.3 seconds (6.00 hours)\n\nTimestep: 5000000\nmean reward (100 episodes): 5961.7400\nbest mean reward: 5975.5800\ncurrent episode reward: 4156.0000\nepisodes: 1937\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21634.4 seconds (6.01 hours)\n\nTimestep: 5010000\nmean reward (100 episodes): 5998.3800\nbest mean reward: 5998.3800\ncurrent episode reward: 5824.0000\nepisodes: 1938\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21679.3 seconds (6.02 hours)\n\nTimestep: 5020000\nmean reward (100 episodes): 5998.7800\nbest mean reward: 6041.5200\ncurrent episode reward: 5212.0000\nepisodes: 1941\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21723.8 seconds (6.03 hours)\n\nTimestep: 5030000\nmean reward (100 episodes): 6043.2400\nbest mean reward: 6043.2400\ncurrent episode reward: 7446.0000\nepisodes: 1942\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21768.5 seconds (6.05 hours)\n\nTimestep: 5040000\nmean reward (100 episodes): 6072.0600\nbest mean reward: 6072.0600\ncurrent episode reward: 4508.0000\nepisodes: 1944\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21813.7 seconds (6.06 hours)\n\nTimestep: 5050000\nmean reward (100 episodes): 6091.6000\nbest mean reward: 6110.6400\ncurrent episode reward: 3840.0000\nepisodes: 1946\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21858.7 seconds (6.07 hours)\n\nTimestep: 5060000\nmean reward (100 episodes): 6095.9200\nbest mean reward: 6110.6400\ncurrent episode reward: 5200.0000\nepisodes: 1947\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21903.9 seconds (6.08 hours)\n\nTimestep: 5070000\nmean reward (100 episodes): 6153.2200\nbest mean reward: 6153.2200\ncurrent episode reward: 10290.0000\nepisodes: 1948\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21950.1 seconds (6.10 hours)\n\nTimestep: 5080000\nmean reward (100 episodes): 6159.4000\nbest mean reward: 6245.2600\ncurrent episode reward: 3240.0000\nepisodes: 1951\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21995.6 seconds (6.11 hours)\n\nTimestep: 5090000\nmean reward (100 episodes): 6174.3600\nbest mean reward: 6245.2600\ncurrent episode reward: 8660.0000\nepisodes: 1952\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22041.1 seconds (6.12 hours)\n\nTimestep: 5100000\nmean reward (100 episodes): 6159.7600\nbest mean reward: 6245.2600\ncurrent episode reward: 7998.0000\nepisodes: 1953\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22086.0 seconds (6.14 hours)\n\nTimestep: 5110000\nmean reward (100 episodes): 6218.2400\nbest mean reward: 6245.2600\ncurrent episode reward: 9960.0000\nepisodes: 1955\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22131.1 seconds (6.15 hours)\n\nTimestep: 5120000\nmean reward (100 episodes): 6290.2400\nbest mean reward: 6290.2400\ncurrent episode reward: 10260.0000\nepisodes: 1956\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22177.1 seconds (6.16 hours)\n\nTimestep: 5130000\nmean reward (100 episodes): 6394.8600\nbest mean reward: 6394.8600\ncurrent episode reward: 6852.0000\nepisodes: 1958\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22222.9 seconds (6.17 hours)\n\nTimestep: 5140000\nmean reward (100 episodes): 6442.0200\nbest mean reward: 6442.0200\ncurrent episode reward: 9870.0000\nepisodes: 1959\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22267.9 seconds (6.19 hours)\n\nTimestep: 5150000\nmean reward (100 episodes): 6496.6800\nbest mean reward: 6496.6800\ncurrent episode reward: 9030.0000\nepisodes: 1961\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22313.5 seconds (6.20 hours)\n\nTimestep: 5160000\nmean reward (100 episodes): 6484.3600\nbest mean reward: 6496.6800\ncurrent episode reward: 8628.0000\nepisodes: 1962\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22359.0 seconds (6.21 hours)\n\nTimestep: 5170000\nmean reward (100 episodes): 6525.5400\nbest mean reward: 6525.5400\ncurrent episode reward: 12510.0000\nepisodes: 1964\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22405.0 seconds (6.22 hours)\n\nTimestep: 5180000\nmean reward (100 episodes): 6534.8400\nbest mean reward: 6534.8400\ncurrent episode reward: 8232.0000\nepisodes: 1966\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22450.5 seconds (6.24 hours)\n\nTimestep: 5190000\nmean reward (100 episodes): 6543.5800\nbest mean reward: 6543.5800\ncurrent episode reward: 6456.0000\nepisodes: 1967\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22497.0 seconds (6.25 hours)\n\nTimestep: 5200000\nmean reward (100 episodes): 6611.6400\nbest mean reward: 6611.6400\ncurrent episode reward: 8388.0000\nepisodes: 1969\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22542.0 seconds (6.26 hours)\n\nTimestep: 5210000\nmean reward (100 episodes): 6638.9000\nbest mean reward: 6638.9000\ncurrent episode reward: 7128.0000\nepisodes: 1971\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22587.3 seconds (6.27 hours)\n\nTimestep: 5220000\nmean reward (100 episodes): 6654.6200\nbest mean reward: 6654.6200\ncurrent episode reward: 7192.0000\nepisodes: 1972\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22633.7 seconds (6.29 hours)\n\nTimestep: 5230000\nmean reward (100 episodes): 6687.8600\nbest mean reward: 6687.8600\ncurrent episode reward: 7112.0000\nepisodes: 1974\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22679.3 seconds (6.30 hours)\n\nTimestep: 5240000\nmean reward (100 episodes): 6594.3000\nbest mean reward: 6687.8600\ncurrent episode reward: 4832.0000\nepisodes: 1975\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22724.6 seconds (6.31 hours)\n\nTimestep: 5250000\nmean reward (100 episodes): 6719.3600\nbest mean reward: 6719.3600\ncurrent episode reward: 6456.0000\nepisodes: 1977\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22770.9 seconds (6.33 hours)\n\nTimestep: 5260000\nmean reward (100 episodes): 6712.6400\nbest mean reward: 6721.1000\ncurrent episode reward: 7650.0000\nepisodes: 1979\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22816.4 seconds (6.34 hours)\n\nTimestep: 5270000\nmean reward (100 episodes): 6785.4400\nbest mean reward: 6785.4400\ncurrent episode reward: 10760.0000\nepisodes: 1980\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22861.9 seconds (6.35 hours)\n\nTimestep: 5280000\nmean reward (100 episodes): 6801.2600\nbest mean reward: 6801.2600\ncurrent episode reward: 6322.0000\nepisodes: 1982\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22906.8 seconds (6.36 hours)\n\nTimestep: 5290000\nmean reward (100 episodes): 6829.0800\nbest mean reward: 6833.3000\ncurrent episode reward: 7498.0000\nepisodes: 1984\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22950.5 seconds (6.38 hours)\n\nTimestep: 5300000\nmean reward (100 episodes): 6886.1200\nbest mean reward: 6886.1200\ncurrent episode reward: 9390.0000\nepisodes: 1986\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22995.7 seconds (6.39 hours)\n\nTimestep: 5310000\nmean reward (100 episodes): 6897.4400\nbest mean reward: 6897.4400\ncurrent episode reward: 7620.0000\nepisodes: 1988\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23041.5 seconds (6.40 hours)\n\nTimestep: 5320000\nmean reward (100 episodes): 6916.1800\nbest mean reward: 6928.1200\ncurrent episode reward: 5538.0000\nepisodes: 1990\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23086.6 seconds (6.41 hours)\n\nTimestep: 5330000\nmean reward (100 episodes): 6797.7400\nbest mean reward: 6928.1200\ncurrent episode reward: 6810.0000\nepisodes: 1992\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23131.6 seconds (6.43 hours)\n\nTimestep: 5340000\nmean reward (100 episodes): 6796.7000\nbest mean reward: 6928.1200\ncurrent episode reward: 5756.0000\nepisodes: 1994\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23177.0 seconds (6.44 hours)\n\nTimestep: 5350000\nmean reward (100 episodes): 6700.5400\nbest mean reward: 6928.1200\ncurrent episode reward: 3300.0000\nepisodes: 1997\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23222.0 seconds (6.45 hours)\n\nTimestep: 5360000\nmean reward (100 episodes): 6763.1400\nbest mean reward: 6928.1200\ncurrent episode reward: 9560.0000\nepisodes: 1998\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23267.4 seconds (6.46 hours)\n\nTimestep: 5370000\nmean reward (100 episodes): 6718.8400\nbest mean reward: 6928.1200\ncurrent episode reward: 5200.0000\nepisodes: 2000\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23313.7 seconds (6.48 hours)\n\nTimestep: 5380000\nmean reward (100 episodes): 6713.0800\nbest mean reward: 6928.1200\ncurrent episode reward: 7212.0000\nepisodes: 2002\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23359.4 seconds (6.49 hours)\n\nTimestep: 5390000\nmean reward (100 episodes): 6782.3400\nbest mean reward: 6928.1200\ncurrent episode reward: 5544.0000\nepisodes: 2004\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23405.5 seconds (6.50 hours)\n\nTimestep: 5400000\nmean reward (100 episodes): 6833.5800\nbest mean reward: 6928.1200\ncurrent episode reward: 10400.0000\nepisodes: 2005\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23450.8 seconds (6.51 hours)\n\nTimestep: 5410000\nmean reward (100 episodes): 6915.9600\nbest mean reward: 6928.1200\ncurrent episode reward: 11598.0000\nepisodes: 2006\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23495.9 seconds (6.53 hours)\n\nTimestep: 5420000\nmean reward (100 episodes): 7014.9400\nbest mean reward: 7014.9400\ncurrent episode reward: 9124.0000\nepisodes: 2008\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23540.2 seconds (6.54 hours)\n\nTimestep: 5430000\nmean reward (100 episodes): 6987.9800\nbest mean reward: 7018.8400\ncurrent episode reward: 2160.0000\nepisodes: 2010\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23584.8 seconds (6.55 hours)\n\nTimestep: 5440000\nmean reward (100 episodes): 7002.6200\nbest mean reward: 7018.8400\ncurrent episode reward: 8820.0000\nepisodes: 2011\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23630.1 seconds (6.56 hours)\n\nTimestep: 5450000\nmean reward (100 episodes): 7096.1400\nbest mean reward: 7096.1400\ncurrent episode reward: 5130.0000\nepisodes: 2013\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23675.2 seconds (6.58 hours)\n\nTimestep: 5460000\nmean reward (100 episodes): 7059.2000\nbest mean reward: 7096.1400\ncurrent episode reward: 8584.0000\nepisodes: 2015\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23720.0 seconds (6.59 hours)\n\nTimestep: 5470000\nmean reward (100 episodes): 7073.6000\nbest mean reward: 7096.1400\ncurrent episode reward: 8482.0000\nepisodes: 2017\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23763.9 seconds (6.60 hours)\n\nTimestep: 5480000\nmean reward (100 episodes): 7084.3400\nbest mean reward: 7096.1400\ncurrent episode reward: 6894.0000\nepisodes: 2018\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23807.8 seconds (6.61 hours)\n\nTimestep: 5490000\nmean reward (100 episodes): 7119.0800\nbest mean reward: 7119.0800\ncurrent episode reward: 8214.0000\nepisodes: 2019\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23853.7 seconds (6.63 hours)\n\nTimestep: 5500000\nmean reward (100 episodes): 7242.7200\nbest mean reward: 7242.7200\ncurrent episode reward: 10230.0000\nepisodes: 2021\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23898.1 seconds (6.64 hours)\n\nTimestep: 5510000\nmean reward (100 episodes): 7321.7400\nbest mean reward: 7321.7400\ncurrent episode reward: 8644.0000\nepisodes: 2023\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23943.3 seconds (6.65 hours)\n\nTimestep: 5520000\nmean reward (100 episodes): 7312.9800\nbest mean reward: 7321.7400\ncurrent episode reward: 9174.0000\nepisodes: 2024\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23989.4 seconds (6.66 hours)\n\nTimestep: 5530000\nmean reward (100 episodes): 7388.6400\nbest mean reward: 7407.7800\ncurrent episode reward: 5090.0000\nepisodes: 2026\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24035.3 seconds (6.68 hours)\n\nTimestep: 5540000\nmean reward (100 episodes): 7398.6400\nbest mean reward: 7407.7800\ncurrent episode reward: 6340.0000\nepisodes: 2027\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24080.5 seconds (6.69 hours)\n\nTimestep: 5550000\nmean reward (100 episodes): 7350.5800\nbest mean reward: 7407.7800\ncurrent episode reward: 7170.0000\nepisodes: 2029\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24126.3 seconds (6.70 hours)\n\nTimestep: 5560000\nmean reward (100 episodes): 7345.1800\nbest mean reward: 7407.7800\ncurrent episode reward: 3900.0000\nepisodes: 2031\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24171.2 seconds (6.71 hours)\n\nTimestep: 5570000\nmean reward (100 episodes): 7297.9000\nbest mean reward: 7407.7800\ncurrent episode reward: 3140.0000\nepisodes: 2034\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24216.6 seconds (6.73 hours)\n\nTimestep: 5580000\nmean reward (100 episodes): 7352.6800\nbest mean reward: 7407.7800\ncurrent episode reward: 10630.0000\nepisodes: 2035\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24261.1 seconds (6.74 hours)\n\nTimestep: 5590000\nmean reward (100 episodes): 7377.0600\nbest mean reward: 7407.7800\ncurrent episode reward: 5884.0000\nepisodes: 2037\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24306.4 seconds (6.75 hours)\n\nTimestep: 5600000\nmean reward (100 episodes): 7461.3200\nbest mean reward: 7461.3200\ncurrent episode reward: 14250.0000\nepisodes: 2038\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24351.3 seconds (6.76 hours)\n\nTimestep: 5610000\nmean reward (100 episodes): 7401.4400\nbest mean reward: 7461.3200\ncurrent episode reward: 4050.0000\nepisodes: 2040\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24396.0 seconds (6.78 hours)\n\nTimestep: 5620000\nmean reward (100 episodes): 7449.6200\nbest mean reward: 7461.3200\ncurrent episode reward: 10030.0000\nepisodes: 2041\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24441.7 seconds (6.79 hours)\n\nTimestep: 5630000\nmean reward (100 episodes): 7571.7200\nbest mean reward: 7571.7200\ncurrent episode reward: 19656.0000\nepisodes: 2042\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24487.7 seconds (6.80 hours)\n\nTimestep: 5640000\nmean reward (100 episodes): 7573.7200\nbest mean reward: 7573.7200\ncurrent episode reward: 9270.0000\nepisodes: 2043\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24532.5 seconds (6.81 hours)\n\nTimestep: 5650000\nmean reward (100 episodes): 7608.0600\nbest mean reward: 7627.5400\ncurrent episode reward: 6742.0000\nepisodes: 2045\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24577.1 seconds (6.83 hours)\n\nTimestep: 5660000\nmean reward (100 episodes): 7653.0600\nbest mean reward: 7653.0600\ncurrent episode reward: 8340.0000\nepisodes: 2046\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24622.3 seconds (6.84 hours)\n\nTimestep: 5670000\nmean reward (100 episodes): 7688.7200\nbest mean reward: 7704.2600\ncurrent episode reward: 8736.0000\nepisodes: 2048\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24666.8 seconds (6.85 hours)\n\nTimestep: 5680000\nmean reward (100 episodes): 7636.4600\nbest mean reward: 7704.2600\ncurrent episode reward: 8298.0000\nepisodes: 2049\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24712.5 seconds (6.86 hours)\n\nTimestep: 5690000\nmean reward (100 episodes): 7726.4000\nbest mean reward: 7726.4000\ncurrent episode reward: 14372.0000\nepisodes: 2050\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24758.7 seconds (6.88 hours)\n\nTimestep: 5700000\nmean reward (100 episodes): 7808.7000\nbest mean reward: 7808.7000\ncurrent episode reward: 10980.0000\nepisodes: 2052\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24804.5 seconds (6.89 hours)\n\nTimestep: 5710000\nmean reward (100 episodes): 7827.1200\nbest mean reward: 7827.1200\ncurrent episode reward: 9840.0000\nepisodes: 2053\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24850.0 seconds (6.90 hours)\n\nTimestep: 5720000\nmean reward (100 episodes): 7806.3600\nbest mean reward: 7838.9200\ncurrent episode reward: 6704.0000\nepisodes: 2055\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24896.1 seconds (6.92 hours)\n\nTimestep: 5730000\nmean reward (100 episodes): 7800.8600\nbest mean reward: 7838.9200\ncurrent episode reward: 9710.0000\nepisodes: 2056\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24941.6 seconds (6.93 hours)\n\nTimestep: 5740000\nmean reward (100 episodes): 7784.1200\nbest mean reward: 7838.9200\ncurrent episode reward: 9336.0000\nepisodes: 2057\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24987.5 seconds (6.94 hours)\n\nTimestep: 5750000\nmean reward (100 episodes): 7744.4000\nbest mean reward: 7838.9200\ncurrent episode reward: 4860.0000\nepisodes: 2059\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25033.2 seconds (6.95 hours)\n\nTimestep: 5760000\nmean reward (100 episodes): 7802.8200\nbest mean reward: 7838.9200\ncurrent episode reward: 12036.0000\nepisodes: 2060\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25078.4 seconds (6.97 hours)\n\nTimestep: 5770000\nmean reward (100 episodes): 7817.4600\nbest mean reward: 7838.9200\ncurrent episode reward: 10494.0000\nepisodes: 2061\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25123.8 seconds (6.98 hours)\n\nTimestep: 5780000\nmean reward (100 episodes): 7932.3800\nbest mean reward: 7932.3800\ncurrent episode reward: 10978.0000\nepisodes: 2063\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25169.5 seconds (6.99 hours)\n\nTimestep: 5790000\nmean reward (100 episodes): 7868.6200\nbest mean reward: 7932.3800\ncurrent episode reward: 5880.0000\nepisodes: 2065\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25215.3 seconds (7.00 hours)\n\nTimestep: 5800000\nmean reward (100 episodes): 7868.6200\nbest mean reward: 7932.3800\ncurrent episode reward: 5880.0000\nepisodes: 2065\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25260.8 seconds (7.02 hours)\n\nTimestep: 5810000\nmean reward (100 episodes): 8024.8400\nbest mean reward: 8024.8400\ncurrent episode reward: 11532.0000\nepisodes: 2067\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25306.3 seconds (7.03 hours)\n\nTimestep: 5820000\nmean reward (100 episodes): 7943.0200\nbest mean reward: 8024.8400\ncurrent episode reward: 4350.0000\nepisodes: 2069\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25351.6 seconds (7.04 hours)\n\nTimestep: 5830000\nmean reward (100 episodes): 7978.5800\nbest mean reward: 8024.8400\ncurrent episode reward: 6240.0000\nepisodes: 2071\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25396.4 seconds (7.05 hours)\n\nTimestep: 5840000\nmean reward (100 episodes): 7978.8800\nbest mean reward: 8024.8400\ncurrent episode reward: 8330.0000\nepisodes: 2073\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25441.3 seconds (7.07 hours)\n\nTimestep: 5850000\nmean reward (100 episodes): 7961.5600\nbest mean reward: 8024.8400\ncurrent episode reward: 3964.0000\nepisodes: 2075\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25485.6 seconds (7.08 hours)\n\nTimestep: 5860000\nmean reward (100 episodes): 7976.8600\nbest mean reward: 8024.8400\ncurrent episode reward: 11928.0000\nepisodes: 2076\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25530.6 seconds (7.09 hours)\n\nTimestep: 5870000\nmean reward (100 episodes): 7998.8600\nbest mean reward: 8024.8400\ncurrent episode reward: 6804.0000\nepisodes: 2078\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25576.3 seconds (7.10 hours)\n\nTimestep: 5880000\nmean reward (100 episodes): 7986.0800\nbest mean reward: 8024.8400\ncurrent episode reward: 6372.0000\nepisodes: 2079\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25621.8 seconds (7.12 hours)\n\nTimestep: 5890000\nmean reward (100 episodes): 7924.8000\nbest mean reward: 8024.8400\ncurrent episode reward: 5024.0000\nepisodes: 2082\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25667.5 seconds (7.13 hours)\n\nTimestep: 5900000\nmean reward (100 episodes): 7902.8800\nbest mean reward: 8024.8400\ncurrent episode reward: 7098.0000\nepisodes: 2084\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25712.4 seconds (7.14 hours)\n\nTimestep: 5910000\nmean reward (100 episodes): 7907.7600\nbest mean reward: 8024.8400\ncurrent episode reward: 8208.0000\nepisodes: 2085\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25758.5 seconds (7.16 hours)\n\nTimestep: 5920000\nmean reward (100 episodes): 7884.1200\nbest mean reward: 8024.8400\ncurrent episode reward: 7026.0000\nepisodes: 2086\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25804.0 seconds (7.17 hours)\n\nTimestep: 5930000\nmean reward (100 episodes): 7943.4800\nbest mean reward: 8024.8400\ncurrent episode reward: 5246.0000\nepisodes: 2088\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25848.8 seconds (7.18 hours)\n\nTimestep: 5940000\nmean reward (100 episodes): 7947.3600\nbest mean reward: 8024.8400\ncurrent episode reward: 8162.0000\nepisodes: 2090\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25894.1 seconds (7.19 hours)\n\nTimestep: 5950000\nmean reward (100 episodes): 8006.9600\nbest mean reward: 8024.8400\ncurrent episode reward: 8210.0000\nepisodes: 2092\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25939.2 seconds (7.21 hours)\n\nTimestep: 5960000\nmean reward (100 episodes): 8041.7000\nbest mean reward: 8041.7000\ncurrent episode reward: 7758.0000\nepisodes: 2093\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25984.2 seconds (7.22 hours)\n\nTimestep: 5970000\nmean reward (100 episodes): 8075.2200\nbest mean reward: 8081.8600\ncurrent episode reward: 3720.0000\nepisodes: 2095\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26029.7 seconds (7.23 hours)\n\nTimestep: 5980000\nmean reward (100 episodes): 8188.0000\nbest mean reward: 8188.0000\ncurrent episode reward: 6508.0000\nepisodes: 2097\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26074.6 seconds (7.24 hours)\n\nTimestep: 5990000\nmean reward (100 episodes): 8179.3000\nbest mean reward: 8188.0000\ncurrent episode reward: 7154.0000\nepisodes: 2099\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26118.9 seconds (7.26 hours)\n\nTimestep: 6000000\nmean reward (100 episodes): 8216.8600\nbest mean reward: 8216.8600\ncurrent episode reward: 8956.0000\nepisodes: 2100\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26164.6 seconds (7.27 hours)\n\nTimestep: 6010000\nmean reward (100 episodes): 8255.2200\nbest mean reward: 8267.1000\ncurrent episode reward: 6024.0000\nepisodes: 2102\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26209.2 seconds (7.28 hours)\n\nTimestep: 6020000\nmean reward (100 episodes): 8215.1800\nbest mean reward: 8267.1000\ncurrent episode reward: 6716.0000\nepisodes: 2103\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26254.2 seconds (7.29 hours)\n\nTimestep: 6030000\nmean reward (100 episodes): 8266.6600\nbest mean reward: 8267.1000\ncurrent episode reward: 10692.0000\nepisodes: 2104\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26299.2 seconds (7.31 hours)\n\nTimestep: 6040000\nmean reward (100 episodes): 8258.2400\nbest mean reward: 8301.6200\ncurrent episode reward: 7260.0000\nepisodes: 2106\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26344.5 seconds (7.32 hours)\n\nTimestep: 6050000\nmean reward (100 episodes): 8223.5600\nbest mean reward: 8301.6200\ncurrent episode reward: 5990.0000\nepisodes: 2108\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26390.3 seconds (7.33 hours)\n\nTimestep: 6060000\nmean reward (100 episodes): 8279.5200\nbest mean reward: 8301.6200\ncurrent episode reward: 7284.0000\nepisodes: 2110\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26435.1 seconds (7.34 hours)\n\nTimestep: 6070000\nmean reward (100 episodes): 8179.4000\nbest mean reward: 8301.6200\ncurrent episode reward: 6644.0000\nepisodes: 2112\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26479.8 seconds (7.36 hours)\n\nTimestep: 6080000\nmean reward (100 episodes): 8213.1800\nbest mean reward: 8301.6200\ncurrent episode reward: 8508.0000\nepisodes: 2113\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26525.2 seconds (7.37 hours)\n\nTimestep: 6090000\nmean reward (100 episodes): 8271.1400\nbest mean reward: 8301.6200\ncurrent episode reward: 9700.0000\nepisodes: 2115\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26570.3 seconds (7.38 hours)\n\nTimestep: 6100000\nmean reward (100 episodes): 8286.2200\nbest mean reward: 8301.6200\ncurrent episode reward: 7702.0000\nepisodes: 2116\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26615.3 seconds (7.39 hours)\n\nTimestep: 6110000\nmean reward (100 episodes): 8293.1400\nbest mean reward: 8318.5800\ncurrent episode reward: 4350.0000\nepisodes: 2118\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26660.0 seconds (7.41 hours)\n\nTimestep: 6120000\nmean reward (100 episodes): 8307.8600\nbest mean reward: 8318.5800\ncurrent episode reward: 8568.0000\nepisodes: 2120\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26706.0 seconds (7.42 hours)\n\nTimestep: 6130000\nmean reward (100 episodes): 8245.3600\nbest mean reward: 8318.5800\ncurrent episode reward: 6508.0000\nepisodes: 2122\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26751.1 seconds (7.43 hours)\n\nTimestep: 6140000\nmean reward (100 episodes): 8297.3400\nbest mean reward: 8318.5800\ncurrent episode reward: 13842.0000\nepisodes: 2123\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26796.5 seconds (7.44 hours)\n\nTimestep: 6150000\nmean reward (100 episodes): 8193.8000\nbest mean reward: 8318.5800\ncurrent episode reward: 6924.0000\nepisodes: 2125\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26841.8 seconds (7.46 hours)\n\nTimestep: 6160000\nmean reward (100 episodes): 8264.7000\nbest mean reward: 8318.5800\ncurrent episode reward: 12180.0000\nepisodes: 2126\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26887.1 seconds (7.47 hours)\n\nTimestep: 6170000\nmean reward (100 episodes): 8250.9800\nbest mean reward: 8318.5800\ncurrent episode reward: 7494.0000\nepisodes: 2128\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26932.5 seconds (7.48 hours)\n\nTimestep: 6180000\nmean reward (100 episodes): 8210.1600\nbest mean reward: 8318.5800\ncurrent episode reward: 4768.0000\nepisodes: 2130\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26977.9 seconds (7.49 hours)\n\nTimestep: 6190000\nmean reward (100 episodes): 8251.9200\nbest mean reward: 8318.5800\ncurrent episode reward: 2832.0000\nepisodes: 2132\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27023.9 seconds (7.51 hours)\n\nTimestep: 6200000\nmean reward (100 episodes): 8296.7200\nbest mean reward: 8318.5800\ncurrent episode reward: 6810.0000\nepisodes: 2134\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27069.0 seconds (7.52 hours)\n\nTimestep: 6210000\nmean reward (100 episodes): 8202.9000\nbest mean reward: 8318.5800\ncurrent episode reward: 6546.0000\nepisodes: 2136\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27113.9 seconds (7.53 hours)\n\nTimestep: 6220000\nmean reward (100 episodes): 8128.6200\nbest mean reward: 8318.5800\ncurrent episode reward: 5812.0000\nepisodes: 2138\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27159.0 seconds (7.54 hours)\n\nTimestep: 6230000\nmean reward (100 episodes): 8155.3800\nbest mean reward: 8318.5800\ncurrent episode reward: 8232.0000\nepisodes: 2140\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27204.4 seconds (7.56 hours)\n\nTimestep: 6240000\nmean reward (100 episodes): 7997.8600\nbest mean reward: 8318.5800\ncurrent episode reward: 7914.0000\nepisodes: 2142\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27249.4 seconds (7.57 hours)\n\nTimestep: 6250000\nmean reward (100 episodes): 8054.4800\nbest mean reward: 8318.5800\ncurrent episode reward: 14932.0000\nepisodes: 2143\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27294.3 seconds (7.58 hours)\n\nTimestep: 6260000\nmean reward (100 episodes): 8008.2000\nbest mean reward: 8318.5800\ncurrent episode reward: 4576.0000\nepisodes: 2145\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27339.4 seconds (7.59 hours)\n\nTimestep: 6270000\nmean reward (100 episodes): 7927.5000\nbest mean reward: 8318.5800\ncurrent episode reward: 8430.0000\nepisodes: 2147\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27383.3 seconds (7.61 hours)\n\nTimestep: 6280000\nmean reward (100 episodes): 7951.9400\nbest mean reward: 8318.5800\ncurrent episode reward: 11180.0000\nepisodes: 2148\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27429.0 seconds (7.62 hours)\n\nTimestep: 6290000\nmean reward (100 episodes): 7991.1000\nbest mean reward: 8318.5800\ncurrent episode reward: 12214.0000\nepisodes: 2149\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27475.2 seconds (7.63 hours)\n\nTimestep: 6300000\nmean reward (100 episodes): 7976.5600\nbest mean reward: 8318.5800\ncurrent episode reward: 9410.0000\nepisodes: 2151\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27520.4 seconds (7.64 hours)\n\nTimestep: 6310000\nmean reward (100 episodes): 7981.3000\nbest mean reward: 8318.5800\ncurrent episode reward: 11454.0000\nepisodes: 2152\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27564.9 seconds (7.66 hours)\n\nTimestep: 6320000\nmean reward (100 episodes): 7940.0400\nbest mean reward: 8318.5800\ncurrent episode reward: 5730.0000\nepisodes: 2154\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27610.1 seconds (7.67 hours)\n\nTimestep: 6330000\nmean reward (100 episodes): 7932.2600\nbest mean reward: 8318.5800\ncurrent episode reward: 5926.0000\nepisodes: 2155\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27654.8 seconds (7.68 hours)\n\nTimestep: 6340000\nmean reward (100 episodes): 7915.6200\nbest mean reward: 8318.5800\ncurrent episode reward: 8322.0000\nepisodes: 2157\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27699.5 seconds (7.69 hours)\n\nTimestep: 6350000\nmean reward (100 episodes): 7895.2800\nbest mean reward: 8318.5800\ncurrent episode reward: 5856.0000\nepisodes: 2158\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27744.1 seconds (7.71 hours)\n\nTimestep: 6360000\nmean reward (100 episodes): 7921.0200\nbest mean reward: 8318.5800\ncurrent episode reward: 9900.0000\nepisodes: 2160\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27789.1 seconds (7.72 hours)\n\nTimestep: 6370000\nmean reward (100 episodes): 7895.1600\nbest mean reward: 8318.5800\ncurrent episode reward: 7908.0000\nepisodes: 2161\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27834.2 seconds (7.73 hours)\n\nTimestep: 6380000\nmean reward (100 episodes): 7836.7400\nbest mean reward: 8318.5800\ncurrent episode reward: 8260.0000\nepisodes: 2162\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27879.5 seconds (7.74 hours)\n\nTimestep: 6390000\nmean reward (100 episodes): 7906.7400\nbest mean reward: 8318.5800\ncurrent episode reward: 6146.0000\nepisodes: 2164\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27925.4 seconds (7.76 hours)\n\nTimestep: 6400000\nmean reward (100 episodes): 7914.1200\nbest mean reward: 8318.5800\ncurrent episode reward: 6618.0000\nepisodes: 2165\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27970.3 seconds (7.77 hours)\n\nTimestep: 6410000\nmean reward (100 episodes): 7842.6800\nbest mean reward: 8318.5800\ncurrent episode reward: 6198.0000\nepisodes: 2167\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28014.7 seconds (7.78 hours)\n\nTimestep: 6420000\nmean reward (100 episodes): 7866.4400\nbest mean reward: 8318.5800\ncurrent episode reward: 7692.0000\nepisodes: 2168\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28059.8 seconds (7.79 hours)\n\nTimestep: 6430000\nmean reward (100 episodes): 7929.8000\nbest mean reward: 8318.5800\ncurrent episode reward: 9396.0000\nepisodes: 2170\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28105.3 seconds (7.81 hours)\n\nTimestep: 6440000\nmean reward (100 episodes): 7996.6400\nbest mean reward: 8318.5800\ncurrent episode reward: 12924.0000\nepisodes: 2171\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28151.6 seconds (7.82 hours)\n\nTimestep: 6450000\nmean reward (100 episodes): 7971.5800\nbest mean reward: 8318.5800\ncurrent episode reward: 6546.0000\nepisodes: 2173\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28197.4 seconds (7.83 hours)\n\nTimestep: 6460000\nmean reward (100 episodes): 8042.2200\nbest mean reward: 8318.5800\ncurrent episode reward: 13312.0000\nepisodes: 2174\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28243.4 seconds (7.85 hours)\n\nTimestep: 6470000\nmean reward (100 episodes): 8100.6200\nbest mean reward: 8318.5800\ncurrent episode reward: 9804.0000\nepisodes: 2175\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28289.1 seconds (7.86 hours)\n\nTimestep: 6480000\nmean reward (100 episodes): 7991.6000\nbest mean reward: 8318.5800\ncurrent episode reward: 4680.0000\nepisodes: 2177\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28334.6 seconds (7.87 hours)\n\nTimestep: 6490000\nmean reward (100 episodes): 8020.2400\nbest mean reward: 8318.5800\ncurrent episode reward: 8720.0000\nepisodes: 2179\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28379.7 seconds (7.88 hours)\n\nTimestep: 6500000\nmean reward (100 episodes): 8088.0800\nbest mean reward: 8318.5800\ncurrent episode reward: 15444.0000\nepisodes: 2180\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28424.8 seconds (7.90 hours)\n\nTimestep: 6510000\nmean reward (100 episodes): 8186.5000\nbest mean reward: 8318.5800\ncurrent episode reward: 12842.0000\nepisodes: 2181\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28470.7 seconds (7.91 hours)\n\nTimestep: 6520000\nmean reward (100 episodes): 8284.7800\nbest mean reward: 8318.5800\ncurrent episode reward: 5070.0000\nepisodes: 2183\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28516.4 seconds (7.92 hours)\n\nTimestep: 6530000\nmean reward (100 episodes): 8277.8000\nbest mean reward: 8318.5800\ncurrent episode reward: 9716.0000\nepisodes: 2185\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28561.1 seconds (7.93 hours)\n\nTimestep: 6540000\nmean reward (100 episodes): 8274.1400\nbest mean reward: 8318.5800\ncurrent episode reward: 6660.0000\nepisodes: 2186\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28606.2 seconds (7.95 hours)\n\nTimestep: 6550000\nmean reward (100 episodes): 8284.1600\nbest mean reward: 8318.5800\ncurrent episode reward: 7652.0000\nepisodes: 2188\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28651.5 seconds (7.96 hours)\n\nTimestep: 6560000\nmean reward (100 episodes): 8304.7800\nbest mean reward: 8318.5800\ncurrent episode reward: 7470.0000\nepisodes: 2189\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28696.2 seconds (7.97 hours)\n\nTimestep: 6570000\nmean reward (100 episodes): 8302.2800\nbest mean reward: 8318.5800\ncurrent episode reward: 9640.0000\nepisodes: 2191\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28741.1 seconds (7.98 hours)\n\nTimestep: 6580000\nmean reward (100 episodes): 8274.1200\nbest mean reward: 8318.5800\ncurrent episode reward: 6096.0000\nepisodes: 2193\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28786.2 seconds (8.00 hours)\n\nTimestep: 6590000\nmean reward (100 episodes): 8261.6000\nbest mean reward: 8318.5800\ncurrent episode reward: 7920.0000\nepisodes: 2195\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28831.5 seconds (8.01 hours)\n\nTimestep: 6600000\nmean reward (100 episodes): 8336.0000\nbest mean reward: 8336.0000\ncurrent episode reward: 18930.0000\nepisodes: 2196\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28876.9 seconds (8.02 hours)\n\nTimestep: 6610000\nmean reward (100 episodes): 8327.2800\nbest mean reward: 8336.0000\ncurrent episode reward: 5636.0000\nepisodes: 2197\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28921.4 seconds (8.03 hours)\n\nTimestep: 6620000\nmean reward (100 episodes): 8324.1400\nbest mean reward: 8336.0000\ncurrent episode reward: 7692.0000\nepisodes: 2199\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28967.1 seconds (8.05 hours)\n\nTimestep: 6630000\nmean reward (100 episodes): 8294.5400\nbest mean reward: 8345.0800\ncurrent episode reward: 6126.0000\nepisodes: 2201\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29011.8 seconds (8.06 hours)\n\nTimestep: 6640000\nmean reward (100 episodes): 8303.9600\nbest mean reward: 8345.0800\ncurrent episode reward: 8886.0000\nepisodes: 2203\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29057.0 seconds (8.07 hours)\n\nTimestep: 6650000\nmean reward (100 episodes): 8299.0400\nbest mean reward: 8345.0800\ncurrent episode reward: 10200.0000\nepisodes: 2204\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29102.5 seconds (8.08 hours)\n\nTimestep: 6660000\nmean reward (100 episodes): 8248.5200\nbest mean reward: 8345.0800\ncurrent episode reward: 9010.0000\nepisodes: 2206\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29147.7 seconds (8.10 hours)\n\nTimestep: 6670000\nmean reward (100 episodes): 8284.9800\nbest mean reward: 8345.0800\ncurrent episode reward: 11946.0000\nepisodes: 2207\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29192.2 seconds (8.11 hours)\n\nTimestep: 6680000\nmean reward (100 episodes): 8276.8000\nbest mean reward: 8345.0800\ncurrent episode reward: 5440.0000\nepisodes: 2209\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29237.4 seconds (8.12 hours)\n\nTimestep: 6690000\nmean reward (100 episodes): 8249.1000\nbest mean reward: 8345.0800\ncurrent episode reward: 4606.0000\nepisodes: 2211\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29282.1 seconds (8.13 hours)\n\nTimestep: 6700000\nmean reward (100 episodes): 8279.5400\nbest mean reward: 8345.0800\ncurrent episode reward: 7896.0000\nepisodes: 2213\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29327.0 seconds (8.15 hours)\n\nTimestep: 6710000\nmean reward (100 episodes): 8297.0200\nbest mean reward: 8345.0800\ncurrent episode reward: 10968.0000\nepisodes: 2214\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29372.9 seconds (8.16 hours)\n\nTimestep: 6720000\nmean reward (100 episodes): 8261.1000\nbest mean reward: 8345.0800\ncurrent episode reward: 7098.0000\nepisodes: 2216\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29417.9 seconds (8.17 hours)\n\nTimestep: 6730000\nmean reward (100 episodes): 8249.8200\nbest mean reward: 8345.0800\ncurrent episode reward: 10590.0000\nepisodes: 2217\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29462.5 seconds (8.18 hours)\n\nTimestep: 6740000\nmean reward (100 episodes): 8271.3400\nbest mean reward: 8345.0800\ncurrent episode reward: 8444.0000\nepisodes: 2219\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29507.8 seconds (8.20 hours)\n\nTimestep: 6750000\nmean reward (100 episodes): 8325.6600\nbest mean reward: 8345.0800\ncurrent episode reward: 14000.0000\nepisodes: 2220\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29553.2 seconds (8.21 hours)\n\nTimestep: 6760000\nmean reward (100 episodes): 8375.9600\nbest mean reward: 8375.9600\ncurrent episode reward: 8310.0000\nepisodes: 2222\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29598.2 seconds (8.22 hours)\n\nTimestep: 6770000\nmean reward (100 episodes): 8346.7200\nbest mean reward: 8375.9600\ncurrent episode reward: 5880.0000\nepisodes: 2224\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29643.7 seconds (8.23 hours)\n\nTimestep: 6780000\nmean reward (100 episodes): 8323.5400\nbest mean reward: 8375.9600\ncurrent episode reward: 4606.0000\nepisodes: 2225\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29689.1 seconds (8.25 hours)\n\nTimestep: 6790000\nmean reward (100 episodes): 8287.7800\nbest mean reward: 8375.9600\ncurrent episode reward: 3990.0000\nepisodes: 2227\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29735.2 seconds (8.26 hours)\n\nTimestep: 6800000\nmean reward (100 episodes): 8306.1000\nbest mean reward: 8375.9600\ncurrent episode reward: 6712.0000\nepisodes: 2229\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29780.9 seconds (8.27 hours)\n\nTimestep: 6810000\nmean reward (100 episodes): 8254.7800\nbest mean reward: 8375.9600\ncurrent episode reward: 6864.0000\nepisodes: 2231\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29825.8 seconds (8.28 hours)\n\nTimestep: 6820000\nmean reward (100 episodes): 8358.6200\nbest mean reward: 8375.9600\ncurrent episode reward: 13216.0000\nepisodes: 2232\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29871.2 seconds (8.30 hours)\n\nTimestep: 6830000\nmean reward (100 episodes): 8365.1600\nbest mean reward: 8375.9600\ncurrent episode reward: 8226.0000\nepisodes: 2233\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29917.0 seconds (8.31 hours)\n\nTimestep: 6840000\nmean reward (100 episodes): 8473.9200\nbest mean reward: 8473.9200\ncurrent episode reward: 10360.0000\nepisodes: 2235\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29962.1 seconds (8.32 hours)\n\nTimestep: 6850000\nmean reward (100 episodes): 8448.7400\nbest mean reward: 8473.9200\ncurrent episode reward: 4028.0000\nepisodes: 2236\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30007.3 seconds (8.34 hours)\n\nTimestep: 6860000\nmean reward (100 episodes): 8506.9600\nbest mean reward: 8506.9600\ncurrent episode reward: 12716.0000\nepisodes: 2237\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30052.5 seconds (8.35 hours)\n\nTimestep: 6870000\nmean reward (100 episodes): 8652.3000\nbest mean reward: 8652.3000\ncurrent episode reward: 8346.0000\nepisodes: 2239\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30097.5 seconds (8.36 hours)\n\nTimestep: 6880000\nmean reward (100 episodes): 8714.2800\nbest mean reward: 8714.2800\ncurrent episode reward: 14430.0000\nepisodes: 2240\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30142.4 seconds (8.37 hours)\n\nTimestep: 6890000\nmean reward (100 episodes): 8660.4400\nbest mean reward: 8714.2800\ncurrent episode reward: 4230.0000\nepisodes: 2242\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30188.1 seconds (8.39 hours)\n\nTimestep: 6900000\nmean reward (100 episodes): 8619.1800\nbest mean reward: 8714.2800\ncurrent episode reward: 5280.0000\nepisodes: 2244\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30233.6 seconds (8.40 hours)\n\nTimestep: 6910000\nmean reward (100 episodes): 8643.8000\nbest mean reward: 8714.2800\ncurrent episode reward: 7038.0000\nepisodes: 2245\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30278.9 seconds (8.41 hours)\n\nTimestep: 6920000\nmean reward (100 episodes): 8740.3000\nbest mean reward: 8740.3000\ncurrent episode reward: 9800.0000\nepisodes: 2247\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30324.1 seconds (8.42 hours)\n\nTimestep: 6930000\nmean reward (100 episodes): 8639.9600\nbest mean reward: 8740.3000\ncurrent episode reward: 9268.0000\nepisodes: 2249\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30369.4 seconds (8.44 hours)\n\nTimestep: 6940000\nmean reward (100 episodes): 8561.9800\nbest mean reward: 8740.3000\ncurrent episode reward: 4860.0000\nepisodes: 2250\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30414.5 seconds (8.45 hours)\n\nTimestep: 6950000\nmean reward (100 episodes): 8466.1200\nbest mean reward: 8740.3000\ncurrent episode reward: 2108.0000\nepisodes: 2252\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30460.5 seconds (8.46 hours)\n\nTimestep: 6960000\nmean reward (100 episodes): 8440.1800\nbest mean reward: 8740.3000\ncurrent episode reward: 8740.0000\nepisodes: 2253\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30505.6 seconds (8.47 hours)\n\nTimestep: 6970000\nmean reward (100 episodes): 8541.7200\nbest mean reward: 8740.3000\ncurrent episode reward: 7530.0000\nepisodes: 2255\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30551.5 seconds (8.49 hours)\n\nTimestep: 6980000\nmean reward (100 episodes): 8540.6200\nbest mean reward: 8740.3000\ncurrent episode reward: 8950.0000\nepisodes: 2256\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30596.5 seconds (8.50 hours)\n\nTimestep: 6990000\nmean reward (100 episodes): 8553.7400\nbest mean reward: 8740.3000\ncurrent episode reward: 5760.0000\nepisodes: 2258\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30641.5 seconds (8.51 hours)\n\nTimestep: 7000000\nmean reward (100 episodes): 8438.6400\nbest mean reward: 8740.3000\ncurrent episode reward: 5866.0000\nepisodes: 2261\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30686.7 seconds (8.52 hours)\n\nTimestep: 7010000\nmean reward (100 episodes): 8480.5400\nbest mean reward: 8740.3000\ncurrent episode reward: 12450.0000\nepisodes: 2262\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30732.7 seconds (8.54 hours)\n\nTimestep: 7020000\nmean reward (100 episodes): 8381.4400\nbest mean reward: 8740.3000\ncurrent episode reward: 7200.0000\nepisodes: 2263\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30777.0 seconds (8.55 hours)\n\nTimestep: 7030000\nmean reward (100 episodes): 8470.2800\nbest mean reward: 8740.3000\ncurrent episode reward: 8580.0000\nepisodes: 2265\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30822.8 seconds (8.56 hours)\n\nTimestep: 7040000\nmean reward (100 episodes): 8364.4400\nbest mean reward: 8740.3000\ncurrent episode reward: 6384.0000\nepisodes: 2266\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30868.2 seconds (8.57 hours)\n\nTimestep: 7050000\nmean reward (100 episodes): 8430.8800\nbest mean reward: 8740.3000\ncurrent episode reward: 13352.0000\nepisodes: 2268\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30913.3 seconds (8.59 hours)\n\nTimestep: 7060000\nmean reward (100 episodes): 8394.3800\nbest mean reward: 8740.3000\ncurrent episode reward: 7530.0000\nepisodes: 2269\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30958.9 seconds (8.60 hours)\n\nTimestep: 7070000\nmean reward (100 episodes): 8355.3400\nbest mean reward: 8740.3000\ncurrent episode reward: 5216.0000\nepisodes: 2271\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31003.8 seconds (8.61 hours)\n\nTimestep: 7080000\nmean reward (100 episodes): 8364.3400\nbest mean reward: 8740.3000\ncurrent episode reward: 6516.0000\nepisodes: 2273\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31048.8 seconds (8.62 hours)\n\nTimestep: 7090000\nmean reward (100 episodes): 8447.9800\nbest mean reward: 8740.3000\ncurrent episode reward: 21676.0000\nepisodes: 2274\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31093.5 seconds (8.64 hours)\n\nTimestep: 7100000\nmean reward (100 episodes): 8410.9000\nbest mean reward: 8740.3000\ncurrent episode reward: 6096.0000\nepisodes: 2275\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31138.0 seconds (8.65 hours)\n\nTimestep: 7110000\nmean reward (100 episodes): 8491.8000\nbest mean reward: 8740.3000\ncurrent episode reward: 5280.0000\nepisodes: 2277\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31182.9 seconds (8.66 hours)\n\nTimestep: 7120000\nmean reward (100 episodes): 8445.3200\nbest mean reward: 8740.3000\ncurrent episode reward: 7428.0000\nepisodes: 2279\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31227.3 seconds (8.67 hours)\n\nTimestep: 7130000\nmean reward (100 episodes): 8480.0800\nbest mean reward: 8740.3000\ncurrent episode reward: 18920.0000\nepisodes: 2280\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31272.7 seconds (8.69 hours)\n\nTimestep: 7140000\nmean reward (100 episodes): 8434.3400\nbest mean reward: 8740.3000\ncurrent episode reward: 8268.0000\nepisodes: 2281\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31318.6 seconds (8.70 hours)\n\nTimestep: 7150000\nmean reward (100 episodes): 8544.0400\nbest mean reward: 8740.3000\ncurrent episode reward: 24716.0000\nepisodes: 2282\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31364.0 seconds (8.71 hours)\n\nTimestep: 7160000\nmean reward (100 episodes): 8617.8400\nbest mean reward: 8740.3000\ncurrent episode reward: 12450.0000\nepisodes: 2283\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31408.7 seconds (8.72 hours)\n\nTimestep: 7170000\nmean reward (100 episodes): 8756.4800\nbest mean reward: 8756.4800\ncurrent episode reward: 18756.0000\nepisodes: 2284\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31454.0 seconds (8.74 hours)\n\nTimestep: 7180000\nmean reward (100 episodes): 8752.8400\nbest mean reward: 8756.4800\ncurrent episode reward: 7230.0000\nepisodes: 2286\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31499.1 seconds (8.75 hours)\n\nTimestep: 7190000\nmean reward (100 episodes): 8739.8800\nbest mean reward: 8756.4800\ncurrent episode reward: 9810.0000\nepisodes: 2287\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31543.9 seconds (8.76 hours)\n\nTimestep: 7200000\nmean reward (100 episodes): 8871.8600\nbest mean reward: 8871.8600\ncurrent episode reward: 20850.0000\nepisodes: 2288\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31589.0 seconds (8.77 hours)\n\nTimestep: 7210000\nmean reward (100 episodes): 8888.0800\nbest mean reward: 8888.0800\ncurrent episode reward: 6804.0000\nepisodes: 2290\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31634.4 seconds (8.79 hours)\n\nTimestep: 7220000\nmean reward (100 episodes): 8856.2400\nbest mean reward: 8888.0800\ncurrent episode reward: 6456.0000\nepisodes: 2291\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31679.0 seconds (8.80 hours)\n\nTimestep: 7230000\nmean reward (100 episodes): 9018.7800\nbest mean reward: 9018.7800\ncurrent episode reward: 23310.0000\nepisodes: 2292\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31725.0 seconds (8.81 hours)\n\nTimestep: 7240000\nmean reward (100 episodes): 9105.7200\nbest mean reward: 9105.7200\ncurrent episode reward: 14790.0000\nepisodes: 2293\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31770.1 seconds (8.83 hours)\n\nTimestep: 7250000\nmean reward (100 episodes): 9221.8800\nbest mean reward: 9221.8800\ncurrent episode reward: 15936.0000\nepisodes: 2294\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31815.9 seconds (8.84 hours)\n\nTimestep: 7260000\nmean reward (100 episodes): 9264.4800\nbest mean reward: 9264.4800\ncurrent episode reward: 12180.0000\nepisodes: 2295\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31861.2 seconds (8.85 hours)\n\nTimestep: 7270000\nmean reward (100 episodes): 9365.6200\nbest mean reward: 9365.6200\ncurrent episode reward: 29044.0000\nepisodes: 2296\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31906.6 seconds (8.86 hours)\n\nTimestep: 7280000\nmean reward (100 episodes): 9474.8600\nbest mean reward: 9474.8600\ncurrent episode reward: 16560.0000\nepisodes: 2297\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31952.1 seconds (8.88 hours)\n\nTimestep: 7290000\nmean reward (100 episodes): 9529.0400\nbest mean reward: 9529.0400\ncurrent episode reward: 11820.0000\nepisodes: 2298\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31997.4 seconds (8.89 hours)\n\nTimestep: 7300000\nmean reward (100 episodes): 9516.6800\nbest mean reward: 9529.0400\ncurrent episode reward: 6456.0000\nepisodes: 2299\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32043.3 seconds (8.90 hours)\n\nTimestep: 7310000\nmean reward (100 episodes): 9578.0800\nbest mean reward: 9578.0800\ncurrent episode reward: 12132.0000\nepisodes: 2301\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32088.6 seconds (8.91 hours)\n\nTimestep: 7320000\nmean reward (100 episodes): 9575.5200\nbest mean reward: 9578.0800\ncurrent episode reward: 4540.0000\nepisodes: 2302\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32133.6 seconds (8.93 hours)\n\nTimestep: 7330000\nmean reward (100 episodes): 9602.1600\nbest mean reward: 9626.5800\ncurrent episode reward: 7758.0000\nepisodes: 2304\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32179.5 seconds (8.94 hours)\n\nTimestep: 7340000\nmean reward (100 episodes): 9570.2200\nbest mean reward: 9626.5800\ncurrent episode reward: 3900.0000\nepisodes: 2305\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32224.7 seconds (8.95 hours)\n\nTimestep: 7350000\nmean reward (100 episodes): 9619.4400\nbest mean reward: 9673.6200\ncurrent episode reward: 6528.0000\nepisodes: 2307\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32270.5 seconds (8.96 hours)\n\nTimestep: 7360000\nmean reward (100 episodes): 9685.8000\nbest mean reward: 9685.8000\ncurrent episode reward: 13530.0000\nepisodes: 2308\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32315.7 seconds (8.98 hours)\n\nTimestep: 7370000\nmean reward (100 episodes): 9767.8200\nbest mean reward: 9767.8200\ncurrent episode reward: 13642.0000\nepisodes: 2309\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32361.2 seconds (8.99 hours)\n\nTimestep: 7380000\nmean reward (100 episodes): 9801.9600\nbest mean reward: 9801.9600\ncurrent episode reward: 7320.0000\nepisodes: 2311\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32406.5 seconds (9.00 hours)\n\nTimestep: 7390000\nmean reward (100 episodes): 9766.4200\nbest mean reward: 9801.9600\ncurrent episode reward: 9750.0000\nepisodes: 2313\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32451.0 seconds (9.01 hours)\n\nTimestep: 7400000\nmean reward (100 episodes): 9740.3600\nbest mean reward: 9801.9600\ncurrent episode reward: 8362.0000\nepisodes: 2314\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32497.2 seconds (9.03 hours)\n\nTimestep: 7410000\nmean reward (100 episodes): 9776.3800\nbest mean reward: 9801.9600\ncurrent episode reward: 8740.0000\nepisodes: 2316\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32542.0 seconds (9.04 hours)\n\nTimestep: 7420000\nmean reward (100 episodes): 9734.8000\nbest mean reward: 9801.9600\ncurrent episode reward: 6432.0000\nepisodes: 2317\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32587.1 seconds (9.05 hours)\n\nTimestep: 7430000\nmean reward (100 episodes): 9758.7800\nbest mean reward: 9801.9600\ncurrent episode reward: 4606.0000\nepisodes: 2319\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32632.9 seconds (9.06 hours)\n\nTimestep: 7440000\nmean reward (100 episodes): 9709.9800\nbest mean reward: 9801.9600\ncurrent episode reward: 5086.0000\nepisodes: 2321\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32678.3 seconds (9.08 hours)\n\nTimestep: 7450000\nmean reward (100 episodes): 9705.7800\nbest mean reward: 9801.9600\ncurrent episode reward: 7890.0000\nepisodes: 2322\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32722.9 seconds (9.09 hours)\n\nTimestep: 7460000\nmean reward (100 episodes): 9689.1000\nbest mean reward: 9801.9600\ncurrent episode reward: 8600.0000\nepisodes: 2324\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32768.6 seconds (9.10 hours)\n\nTimestep: 7470000\nmean reward (100 episodes): 9722.8800\nbest mean reward: 9801.9600\ncurrent episode reward: 6648.0000\nepisodes: 2326\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32813.8 seconds (9.11 hours)\n\nTimestep: 7480000\nmean reward (100 episodes): 9717.5200\nbest mean reward: 9801.9600\ncurrent episode reward: 5472.0000\nepisodes: 2328\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32858.9 seconds (9.13 hours)\n\nTimestep: 7490000\nmean reward (100 episodes): 9764.7600\nbest mean reward: 9801.9600\ncurrent episode reward: 11436.0000\nepisodes: 2329\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32904.7 seconds (9.14 hours)\n\nTimestep: 7500000\nmean reward (100 episodes): 9811.0200\nbest mean reward: 9811.0200\ncurrent episode reward: 9422.0000\nepisodes: 2330\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32950.3 seconds (9.15 hours)\n\nTimestep: 7510000\nmean reward (100 episodes): 9773.4400\nbest mean reward: 9834.6800\ncurrent episode reward: 7092.0000\nepisodes: 2332\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32994.8 seconds (9.17 hours)\n\nTimestep: 7520000\nmean reward (100 episodes): 9715.5200\nbest mean reward: 9834.6800\ncurrent episode reward: 7060.0000\nepisodes: 2334\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33040.2 seconds (9.18 hours)\n\nTimestep: 7530000\nmean reward (100 episodes): 9682.1800\nbest mean reward: 9834.6800\ncurrent episode reward: 7026.0000\nepisodes: 2335\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33086.0 seconds (9.19 hours)\n\nTimestep: 7540000\nmean reward (100 episodes): 9709.6800\nbest mean reward: 9834.6800\ncurrent episode reward: 4860.0000\nepisodes: 2337\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33131.9 seconds (9.20 hours)\n\nTimestep: 7550000\nmean reward (100 episodes): 9618.0200\nbest mean reward: 9834.6800\ncurrent episode reward: 6254.0000\nepisodes: 2338\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33177.4 seconds (9.22 hours)\n\nTimestep: 7560000\nmean reward (100 episodes): 9659.9400\nbest mean reward: 9834.6800\ncurrent episode reward: 12538.0000\nepisodes: 2339\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33222.3 seconds (9.23 hours)\n\nTimestep: 7570000\nmean reward (100 episodes): 9671.1600\nbest mean reward: 9834.6800\ncurrent episode reward: 15552.0000\nepisodes: 2340\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33267.2 seconds (9.24 hours)\n\nTimestep: 7580000\nmean reward (100 episodes): 9853.4200\nbest mean reward: 9853.4200\ncurrent episode reward: 22546.0000\nepisodes: 2341\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33312.9 seconds (9.25 hours)\n\nTimestep: 7590000\nmean reward (100 episodes): 9885.3800\nbest mean reward: 9909.0200\ncurrent episode reward: 10590.0000\nepisodes: 2343\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33357.7 seconds (9.27 hours)\n\nTimestep: 7600000\nmean reward (100 episodes): 9929.2800\nbest mean reward: 9929.2800\ncurrent episode reward: 9670.0000\nepisodes: 2344\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33402.9 seconds (9.28 hours)\n\nTimestep: 7610000\nmean reward (100 episodes): 10001.4800\nbest mean reward: 10001.4800\ncurrent episode reward: 14258.0000\nepisodes: 2345\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33448.7 seconds (9.29 hours)\n\nTimestep: 7620000\nmean reward (100 episodes): 9925.7600\nbest mean reward: 10001.4800\ncurrent episode reward: 5632.0000\nepisodes: 2347\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33493.9 seconds (9.30 hours)\n\nTimestep: 7630000\nmean reward (100 episodes): 10016.1000\nbest mean reward: 10016.1000\ncurrent episode reward: 13126.0000\nepisodes: 2348\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33539.1 seconds (9.32 hours)\n\nTimestep: 7640000\nmean reward (100 episodes): 10083.3200\nbest mean reward: 10083.3200\ncurrent episode reward: 15990.0000\nepisodes: 2349\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33583.9 seconds (9.33 hours)\n\nTimestep: 7650000\nmean reward (100 episodes): 10097.2600\nbest mean reward: 10097.2600\ncurrent episode reward: 6254.0000\nepisodes: 2350\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33629.0 seconds (9.34 hours)\n\nTimestep: 7660000\nmean reward (100 episodes): 10177.4000\nbest mean reward: 10177.4000\ncurrent episode reward: 17184.0000\nepisodes: 2351\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33673.6 seconds (9.35 hours)\n\nTimestep: 7670000\nmean reward (100 episodes): 10211.2400\nbest mean reward: 10239.8400\ncurrent episode reward: 5880.0000\nepisodes: 2353\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33717.9 seconds (9.37 hours)\n\nTimestep: 7680000\nmean reward (100 episodes): 10158.7400\nbest mean reward: 10239.8400\ncurrent episode reward: 9030.0000\nepisodes: 2354\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33763.0 seconds (9.38 hours)\n\nTimestep: 7690000\nmean reward (100 episodes): 10224.2200\nbest mean reward: 10251.1000\ncurrent episode reward: 6262.0000\nepisodes: 2356\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33808.0 seconds (9.39 hours)\n\nTimestep: 7700000\nmean reward (100 episodes): 10340.2800\nbest mean reward: 10340.2800\ncurrent episode reward: 21336.0000\nepisodes: 2357\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33853.5 seconds (9.40 hours)\n\nTimestep: 7710000\nmean reward (100 episodes): 10340.2800\nbest mean reward: 10340.2800\ncurrent episode reward: 21336.0000\nepisodes: 2357\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33898.8 seconds (9.42 hours)\n\nTimestep: 7720000\nmean reward (100 episodes): 10511.7000\nbest mean reward: 10511.7000\ncurrent episode reward: 4992.0000\nepisodes: 2360\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33943.5 seconds (9.43 hours)\n\nTimestep: 7730000\nmean reward (100 episodes): 10511.7000\nbest mean reward: 10511.7000\ncurrent episode reward: 4992.0000\nepisodes: 2360\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33988.8 seconds (9.44 hours)\n\nTimestep: 7740000\nmean reward (100 episodes): 10610.1600\nbest mean reward: 10680.5600\ncurrent episode reward: 5410.0000\nepisodes: 2362\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34034.5 seconds (9.45 hours)\n\nTimestep: 7750000\nmean reward (100 episodes): 10550.5800\nbest mean reward: 10680.5600\ncurrent episode reward: 6996.0000\nepisodes: 2364\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34079.7 seconds (9.47 hours)\n\nTimestep: 7760000\nmean reward (100 episodes): 10544.8800\nbest mean reward: 10680.5600\ncurrent episode reward: 8010.0000\nepisodes: 2365\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34124.0 seconds (9.48 hours)\n\nTimestep: 7770000\nmean reward (100 episodes): 10633.2000\nbest mean reward: 10680.5600\ncurrent episode reward: 15216.0000\nepisodes: 2366\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34168.9 seconds (9.49 hours)\n\nTimestep: 7780000\nmean reward (100 episodes): 10663.6000\nbest mean reward: 10708.6200\ncurrent episode reward: 8850.0000\nepisodes: 2368\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34214.2 seconds (9.50 hours)\n\nTimestep: 7790000\nmean reward (100 episodes): 10663.7400\nbest mean reward: 10708.6200\ncurrent episode reward: 7544.0000\nepisodes: 2369\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34259.5 seconds (9.52 hours)\n\nTimestep: 7800000\nmean reward (100 episodes): 10704.9400\nbest mean reward: 10708.6200\ncurrent episode reward: 8734.0000\nepisodes: 2371\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34304.7 seconds (9.53 hours)\n\nTimestep: 7810000\nmean reward (100 episodes): 10693.8600\nbest mean reward: 10708.6200\ncurrent episode reward: 5676.0000\nepisodes: 2372\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34349.0 seconds (9.54 hours)\n\nTimestep: 7820000\nmean reward (100 episodes): 10541.0600\nbest mean reward: 10708.6200\ncurrent episode reward: 6384.0000\nepisodes: 2374\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34394.1 seconds (9.55 hours)\n\nTimestep: 7830000\nmean reward (100 episodes): 10510.5600\nbest mean reward: 10708.6200\ncurrent episode reward: 4384.0000\nepisodes: 2376\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34438.5 seconds (9.57 hours)\n\nTimestep: 7840000\nmean reward (100 episodes): 10589.2400\nbest mean reward: 10708.6200\ncurrent episode reward: 5598.0000\nepisodes: 2378\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34483.7 seconds (9.58 hours)\n\nTimestep: 7850000\nmean reward (100 episodes): 10430.4800\nbest mean reward: 10708.6200\ncurrent episode reward: 4796.0000\nepisodes: 2380\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34529.3 seconds (9.59 hours)\n\nTimestep: 7860000\nmean reward (100 episodes): 10403.8800\nbest mean reward: 10708.6200\ncurrent episode reward: 5608.0000\nepisodes: 2381\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34574.8 seconds (9.60 hours)\n\nTimestep: 7870000\nmean reward (100 episodes): 10213.2400\nbest mean reward: 10708.6200\ncurrent episode reward: 6300.0000\nepisodes: 2383\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34619.4 seconds (9.62 hours)\n\nTimestep: 7880000\nmean reward (100 episodes): 10071.6200\nbest mean reward: 10708.6200\ncurrent episode reward: 6470.0000\nepisodes: 2385\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34665.2 seconds (9.63 hours)\n\nTimestep: 7890000\nmean reward (100 episodes): 10102.2200\nbest mean reward: 10708.6200\ncurrent episode reward: 10290.0000\nepisodes: 2386\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34710.6 seconds (9.64 hours)\n\nTimestep: 7900000\nmean reward (100 episodes): 9952.3600\nbest mean reward: 10708.6200\ncurrent episode reward: 6690.0000\nepisodes: 2388\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34756.4 seconds (9.65 hours)\n\nTimestep: 7910000\nmean reward (100 episodes): 9900.8800\nbest mean reward: 10708.6200\ncurrent episode reward: 1284.0000\nepisodes: 2391\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34801.4 seconds (9.67 hours)\n\nTimestep: 7920000\nmean reward (100 episodes): 9778.1800\nbest mean reward: 10708.6200\ncurrent episode reward: 11040.0000\nepisodes: 2392\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34846.1 seconds (9.68 hours)\n\nTimestep: 7930000\nmean reward (100 episodes): 9647.1000\nbest mean reward: 10708.6200\ncurrent episode reward: 8298.0000\nepisodes: 2394\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34891.6 seconds (9.69 hours)\n\nTimestep: 7940000\nmean reward (100 episodes): 9647.5400\nbest mean reward: 10708.6200\ncurrent episode reward: 12224.0000\nepisodes: 2395\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34936.7 seconds (9.70 hours)\n\nTimestep: 7950000\nmean reward (100 episodes): 9322.7000\nbest mean reward: 10708.6200\ncurrent episode reward: 4092.0000\nepisodes: 2397\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34982.3 seconds (9.72 hours)\n\nTimestep: 7960000\nmean reward (100 episodes): 9247.5400\nbest mean reward: 10708.6200\ncurrent episode reward: 4832.0000\nepisodes: 2399\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35027.7 seconds (9.73 hours)\n\nTimestep: 7970000\nmean reward (100 episodes): 9228.8000\nbest mean reward: 10708.6200\ncurrent episode reward: 9310.0000\nepisodes: 2400\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35073.6 seconds (9.74 hours)\n\nTimestep: 7980000\nmean reward (100 episodes): 9201.0800\nbest mean reward: 10708.6200\ncurrent episode reward: 7264.0000\nepisodes: 2402\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35118.1 seconds (9.76 hours)\n\nTimestep: 7990000\nmean reward (100 episodes): 9120.8000\nbest mean reward: 10708.6200\ncurrent episode reward: 5964.0000\nepisodes: 2403\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35163.5 seconds (9.77 hours)\n\nTimestep: 8000000\nmean reward (100 episodes): 9212.1200\nbest mean reward: 10708.6200\ncurrent episode reward: 8012.0000\nepisodes: 2405\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35208.5 seconds (9.78 hours)\n\nTimestep: 8010000\nmean reward (100 episodes): 9165.5600\nbest mean reward: 10708.6200\ncurrent episode reward: 14694.0000\nepisodes: 2406\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35253.8 seconds (9.79 hours)\n\nTimestep: 8020000\nmean reward (100 episodes): 9236.7400\nbest mean reward: 10708.6200\ncurrent episode reward: 13646.0000\nepisodes: 2407\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35299.4 seconds (9.81 hours)\n\nTimestep: 8030000\nmean reward (100 episodes): 9105.1800\nbest mean reward: 10708.6200\ncurrent episode reward: 6864.0000\nepisodes: 2409\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35345.3 seconds (9.82 hours)\n\nTimestep: 8040000\nmean reward (100 episodes): 9136.7800\nbest mean reward: 10708.6200\ncurrent episode reward: 9014.0000\nepisodes: 2410\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35390.2 seconds (9.83 hours)\n\nTimestep: 8050000\nmean reward (100 episodes): 9236.9800\nbest mean reward: 10708.6200\ncurrent episode reward: 17340.0000\nepisodes: 2411\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35435.3 seconds (9.84 hours)\n\nTimestep: 8060000\nmean reward (100 episodes): 9238.9800\nbest mean reward: 10708.6200\ncurrent episode reward: 5880.0000\nepisodes: 2413\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35481.1 seconds (9.86 hours)\n\nTimestep: 8070000\nmean reward (100 episodes): 9202.9400\nbest mean reward: 10708.6200\ncurrent episode reward: 5924.0000\nepisodes: 2415\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35527.3 seconds (9.87 hours)\n\nTimestep: 8080000\nmean reward (100 episodes): 9270.9000\nbest mean reward: 10708.6200\ncurrent episode reward: 15536.0000\nepisodes: 2416\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35572.6 seconds (9.88 hours)\n\nTimestep: 8090000\nmean reward (100 episodes): 9358.9800\nbest mean reward: 10708.6200\ncurrent episode reward: 15240.0000\nepisodes: 2417\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35617.7 seconds (9.89 hours)\n\nTimestep: 8100000\nmean reward (100 episodes): 9394.8400\nbest mean reward: 10708.6200\ncurrent episode reward: 16788.0000\nepisodes: 2418\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35664.0 seconds (9.91 hours)\n\nTimestep: 8110000\nmean reward (100 episodes): 9494.9600\nbest mean reward: 10708.6200\ncurrent episode reward: 14618.0000\nepisodes: 2419\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35709.5 seconds (9.92 hours)\n\nTimestep: 8120000\nmean reward (100 episodes): 9486.2200\nbest mean reward: 10708.6200\ncurrent episode reward: 8764.0000\nepisodes: 2421\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35755.2 seconds (9.93 hours)\n\nTimestep: 8130000\nmean reward (100 episodes): 9492.1200\nbest mean reward: 10708.6200\ncurrent episode reward: 7446.0000\nepisodes: 2423\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35800.0 seconds (9.94 hours)\n\nTimestep: 8140000\nmean reward (100 episodes): 9492.1200\nbest mean reward: 10708.6200\ncurrent episode reward: 7446.0000\nepisodes: 2423\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35844.9 seconds (9.96 hours)\n\nTimestep: 8150000\nmean reward (100 episodes): 9540.8200\nbest mean reward: 10708.6200\ncurrent episode reward: 6762.0000\nepisodes: 2425\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35890.2 seconds (9.97 hours)\n\nTimestep: 8160000\nmean reward (100 episodes): 9541.6200\nbest mean reward: 10708.6200\ncurrent episode reward: 8962.0000\nepisodes: 2427\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35934.8 seconds (9.98 hours)\n\nTimestep: 8170000\nmean reward (100 episodes): 9470.5800\nbest mean reward: 10708.6200\ncurrent episode reward: 6804.0000\nepisodes: 2429\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35980.1 seconds (9.99 hours)\n\nTimestep: 8180000\nmean reward (100 episodes): 9456.3800\nbest mean reward: 10708.6200\ncurrent episode reward: 8172.0000\nepisodes: 2431\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36025.3 seconds (10.01 hours)\n\nTimestep: 8190000\nmean reward (100 episodes): 9449.9400\nbest mean reward: 10708.6200\ncurrent episode reward: 7576.0000\nepisodes: 2433\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36071.3 seconds (10.02 hours)\n\nTimestep: 8200000\nmean reward (100 episodes): 9473.9400\nbest mean reward: 10708.6200\ncurrent episode reward: 9460.0000\nepisodes: 2434\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36117.1 seconds (10.03 hours)\n\nTimestep: 8210000\nmean reward (100 episodes): 9413.0200\nbest mean reward: 10708.6200\ncurrent episode reward: 5730.0000\nepisodes: 2436\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36162.3 seconds (10.05 hours)\n\nTimestep: 8220000\nmean reward (100 episodes): 9400.7200\nbest mean reward: 10708.6200\ncurrent episode reward: 4928.0000\nepisodes: 2438\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36207.5 seconds (10.06 hours)\n\nTimestep: 8230000\nmean reward (100 episodes): 9347.6400\nbest mean reward: 10708.6200\ncurrent episode reward: 7230.0000\nepisodes: 2439\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36252.6 seconds (10.07 hours)\n\nTimestep: 8240000\nmean reward (100 episodes): 9369.3600\nbest mean reward: 10708.6200\ncurrent episode reward: 17724.0000\nepisodes: 2440\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36297.3 seconds (10.08 hours)\n\nTimestep: 8250000\nmean reward (100 episodes): 9249.0800\nbest mean reward: 10708.6200\ncurrent episode reward: 8584.0000\nepisodes: 2442\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36342.3 seconds (10.10 hours)\n\nTimestep: 8260000\nmean reward (100 episodes): 9149.2000\nbest mean reward: 10708.6200\ncurrent episode reward: 4320.0000\nepisodes: 2444\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36387.0 seconds (10.11 hours)\n\nTimestep: 8270000\nmean reward (100 episodes): 9157.5200\nbest mean reward: 10708.6200\ncurrent episode reward: 15090.0000\nepisodes: 2445\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36433.2 seconds (10.12 hours)\n\nTimestep: 8280000\nmean reward (100 episodes): 9195.3600\nbest mean reward: 10708.6200\ncurrent episode reward: 6864.0000\nepisodes: 2447\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36478.9 seconds (10.13 hours)\n\nTimestep: 8290000\nmean reward (100 episodes): 9030.7800\nbest mean reward: 10708.6200\ncurrent episode reward: 7380.0000\nepisodes: 2449\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36524.2 seconds (10.15 hours)\n\nTimestep: 8300000\nmean reward (100 episodes): 9107.1400\nbest mean reward: 10708.6200\ncurrent episode reward: 13890.0000\nepisodes: 2450\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36569.9 seconds (10.16 hours)\n\nTimestep: 8310000\nmean reward (100 episodes): 9032.4400\nbest mean reward: 10708.6200\ncurrent episode reward: 4604.0000\nepisodes: 2452\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36615.6 seconds (10.17 hours)\n\nTimestep: 8320000\nmean reward (100 episodes): 9062.0200\nbest mean reward: 10708.6200\ncurrent episode reward: 8838.0000\nepisodes: 2453\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36660.5 seconds (10.18 hours)\n\nTimestep: 8330000\nmean reward (100 episodes): 9115.7200\nbest mean reward: 10708.6200\ncurrent episode reward: 14400.0000\nepisodes: 2454\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36706.5 seconds (10.20 hours)\n\nTimestep: 8340000\nmean reward (100 episodes): 9049.2600\nbest mean reward: 10708.6200\ncurrent episode reward: 7762.0000\nepisodes: 2456\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36751.5 seconds (10.21 hours)\n\nTimestep: 8350000\nmean reward (100 episodes): 8773.2800\nbest mean reward: 10708.6200\ncurrent episode reward: 7622.0000\nepisodes: 2458\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36796.7 seconds (10.22 hours)\n\nTimestep: 8360000\nmean reward (100 episodes): 8769.2600\nbest mean reward: 10708.6200\ncurrent episode reward: 6810.0000\nepisodes: 2459\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36841.4 seconds (10.23 hours)\n\nTimestep: 8370000\nmean reward (100 episodes): 8639.3600\nbest mean reward: 10708.6200\ncurrent episode reward: 6414.0000\nepisodes: 2461\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36886.7 seconds (10.25 hours)\n\nTimestep: 8380000\nmean reward (100 episodes): 8696.8600\nbest mean reward: 10708.6200\ncurrent episode reward: 9044.0000\nepisodes: 2463\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36932.1 seconds (10.26 hours)\n\nTimestep: 8390000\nmean reward (100 episodes): 8683.8600\nbest mean reward: 10708.6200\ncurrent episode reward: 5696.0000\nepisodes: 2464\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36976.3 seconds (10.27 hours)\n\nTimestep: 8400000\nmean reward (100 episodes): 8762.2600\nbest mean reward: 10708.6200\ncurrent episode reward: 15850.0000\nepisodes: 2465\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37022.2 seconds (10.28 hours)\n\nTimestep: 8410000\nmean reward (100 episodes): 8679.7000\nbest mean reward: 10708.6200\ncurrent episode reward: 6960.0000\nepisodes: 2466\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37067.8 seconds (10.30 hours)\n\nTimestep: 8420000\nmean reward (100 episodes): 8710.9200\nbest mean reward: 10708.6200\ncurrent episode reward: 7386.0000\nepisodes: 2468\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37112.4 seconds (10.31 hours)\n\nTimestep: 8430000\nmean reward (100 episodes): 8700.8600\nbest mean reward: 10708.6200\ncurrent episode reward: 6538.0000\nepisodes: 2469\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37157.3 seconds (10.32 hours)\n\nTimestep: 8440000\nmean reward (100 episodes): 8687.2600\nbest mean reward: 10708.6200\ncurrent episode reward: 6390.0000\nepisodes: 2471\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37203.2 seconds (10.33 hours)\n\nTimestep: 8450000\nmean reward (100 episodes): 8832.2000\nbest mean reward: 10708.6200\ncurrent episode reward: 20170.0000\nepisodes: 2472\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37249.2 seconds (10.35 hours)\n\nTimestep: 8460000\nmean reward (100 episodes): 8965.5600\nbest mean reward: 10708.6200\ncurrent episode reward: 19864.0000\nepisodes: 2473\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37294.8 seconds (10.36 hours)\n\nTimestep: 8470000\nmean reward (100 episodes): 8916.4200\nbest mean reward: 10708.6200\ncurrent episode reward: 4860.0000\nepisodes: 2475\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37339.8 seconds (10.37 hours)\n\nTimestep: 8480000\nmean reward (100 episodes): 9016.1800\nbest mean reward: 10708.6200\ncurrent episode reward: 14360.0000\nepisodes: 2476\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37385.1 seconds (10.38 hours)\n\nTimestep: 8490000\nmean reward (100 episodes): 8975.9000\nbest mean reward: 10708.6200\ncurrent episode reward: 7486.0000\nepisodes: 2477\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37429.7 seconds (10.40 hours)\n\nTimestep: 8500000\nmean reward (100 episodes): 9039.6400\nbest mean reward: 10708.6200\ncurrent episode reward: 11972.0000\nepisodes: 2478\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37475.0 seconds (10.41 hours)\n\nTimestep: 8510000\nmean reward (100 episodes): 9163.1000\nbest mean reward: 10708.6200\ncurrent episode reward: 9098.0000\nepisodes: 2480\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37520.2 seconds (10.42 hours)\n\nTimestep: 8520000\nmean reward (100 episodes): 9208.7200\nbest mean reward: 10708.6200\ncurrent episode reward: 10170.0000\nepisodes: 2481\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37565.5 seconds (10.43 hours)\n\nTimestep: 8530000\nmean reward (100 episodes): 9233.4000\nbest mean reward: 10708.6200\ncurrent episode reward: 10680.0000\nepisodes: 2483\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37610.5 seconds (10.45 hours)\n\nTimestep: 8540000\nmean reward (100 episodes): 9308.2000\nbest mean reward: 10708.6200\ncurrent episode reward: 14386.0000\nepisodes: 2484\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37655.3 seconds (10.46 hours)\n\nTimestep: 8550000\nmean reward (100 episodes): 9360.2000\nbest mean reward: 10708.6200\ncurrent episode reward: 11670.0000\nepisodes: 2485\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37699.9 seconds (10.47 hours)\n\nTimestep: 8560000\nmean reward (100 episodes): 9395.9000\nbest mean reward: 10708.6200\ncurrent episode reward: 13860.0000\nepisodes: 2486\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37745.0 seconds (10.48 hours)\n\nTimestep: 8570000\nmean reward (100 episodes): 9432.6800\nbest mean reward: 10708.6200\ncurrent episode reward: 11112.0000\nepisodes: 2488\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37790.8 seconds (10.50 hours)\n\nTimestep: 8580000\nmean reward (100 episodes): 9410.3800\nbest mean reward: 10708.6200\ncurrent episode reward: 5544.0000\nepisodes: 2489\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37836.7 seconds (10.51 hours)\n\nTimestep: 8590000\nmean reward (100 episodes): 9479.9600\nbest mean reward: 10708.6200\ncurrent episode reward: 6402.0000\nepisodes: 2491\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37881.6 seconds (10.52 hours)\n\nTimestep: 8600000\nmean reward (100 episodes): 9450.4800\nbest mean reward: 10708.6200\ncurrent episode reward: 6652.0000\nepisodes: 2493\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37926.8 seconds (10.54 hours)\n\nTimestep: 8610000\nmean reward (100 episodes): 9428.4600\nbest mean reward: 10708.6200\ncurrent episode reward: 6096.0000\nepisodes: 2494\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37971.8 seconds (10.55 hours)\n\nTimestep: 8620000\nmean reward (100 episodes): 9365.0600\nbest mean reward: 10708.6200\ncurrent episode reward: 7290.0000\nepisodes: 2496\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38016.3 seconds (10.56 hours)\n\nTimestep: 8630000\nmean reward (100 episodes): 9516.1600\nbest mean reward: 10708.6200\ncurrent episode reward: 19202.0000\nepisodes: 2497\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38061.4 seconds (10.57 hours)\n\nTimestep: 8640000\nmean reward (100 episodes): 9591.7600\nbest mean reward: 10708.6200\ncurrent episode reward: 4898.0000\nepisodes: 2499\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38106.9 seconds (10.59 hours)\n\nTimestep: 8650000\nmean reward (100 episodes): 9547.9400\nbest mean reward: 10708.6200\ncurrent episode reward: 4928.0000\nepisodes: 2500\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38152.8 seconds (10.60 hours)\n\nTimestep: 8660000\nmean reward (100 episodes): 9591.8200\nbest mean reward: 10708.6200\ncurrent episode reward: 7038.0000\nepisodes: 2502\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38198.7 seconds (10.61 hours)\n\nTimestep: 8670000\nmean reward (100 episodes): 9534.6200\nbest mean reward: 10708.6200\ncurrent episode reward: 5666.0000\nepisodes: 2504\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38243.7 seconds (10.62 hours)\n\nTimestep: 8680000\nmean reward (100 episodes): 9723.6000\nbest mean reward: 10708.6200\ncurrent episode reward: 26910.0000\nepisodes: 2505\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38290.0 seconds (10.64 hours)\n\nTimestep: 8690000\nmean reward (100 episodes): 9622.7000\nbest mean reward: 10708.6200\ncurrent episode reward: 4604.0000\nepisodes: 2506\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38335.6 seconds (10.65 hours)\n\nTimestep: 8700000\nmean reward (100 episodes): 9664.2600\nbest mean reward: 10708.6200\ncurrent episode reward: 7416.0000\nepisodes: 2508\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38381.0 seconds (10.66 hours)\n\nTimestep: 8710000\nmean reward (100 episodes): 9713.6200\nbest mean reward: 10708.6200\ncurrent episode reward: 11800.0000\nepisodes: 2509\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38425.7 seconds (10.67 hours)\n\nTimestep: 8720000\nmean reward (100 episodes): 9771.0400\nbest mean reward: 10708.6200\ncurrent episode reward: 14756.0000\nepisodes: 2510\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38471.4 seconds (10.69 hours)\n\nTimestep: 8730000\nmean reward (100 episodes): 9682.4600\nbest mean reward: 10708.6200\ncurrent episode reward: 8482.0000\nepisodes: 2511\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38515.8 seconds (10.70 hours)\n\nTimestep: 8740000\nmean reward (100 episodes): 9738.4400\nbest mean reward: 10708.6200\ncurrent episode reward: 6156.0000\nepisodes: 2513\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38561.9 seconds (10.71 hours)\n\nTimestep: 8750000\nmean reward (100 episodes): 9747.5800\nbest mean reward: 10708.6200\ncurrent episode reward: 8420.0000\nepisodes: 2514\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38606.8 seconds (10.72 hours)\n\nTimestep: 8760000\nmean reward (100 episodes): 9795.7400\nbest mean reward: 10708.6200\ncurrent episode reward: 10740.0000\nepisodes: 2515\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38651.8 seconds (10.74 hours)\n\nTimestep: 8770000\nmean reward (100 episodes): 9778.6800\nbest mean reward: 10708.6200\ncurrent episode reward: 10490.0000\nepisodes: 2517\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38697.6 seconds (10.75 hours)\n\nTimestep: 8780000\nmean reward (100 episodes): 9673.8000\nbest mean reward: 10708.6200\ncurrent episode reward: 6300.0000\nepisodes: 2518\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38742.5 seconds (10.76 hours)\n\nTimestep: 8790000\nmean reward (100 episodes): 9630.7400\nbest mean reward: 10708.6200\ncurrent episode reward: 10312.0000\nepisodes: 2519\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38787.2 seconds (10.77 hours)\n\nTimestep: 8800000\nmean reward (100 episodes): 9693.1200\nbest mean reward: 10708.6200\ncurrent episode reward: 9660.0000\nepisodes: 2521\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38833.3 seconds (10.79 hours)\n\nTimestep: 8810000\nmean reward (100 episodes): 9710.0800\nbest mean reward: 10708.6200\ncurrent episode reward: 10566.0000\nepisodes: 2523\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38878.3 seconds (10.80 hours)\n\nTimestep: 8820000\nmean reward (100 episodes): 9550.9800\nbest mean reward: 10708.6200\ncurrent episode reward: 4320.0000\nepisodes: 2525\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38923.4 seconds (10.81 hours)\n\nTimestep: 8830000\nmean reward (100 episodes): 9541.7200\nbest mean reward: 10708.6200\ncurrent episode reward: 6690.0000\nepisodes: 2527\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38968.9 seconds (10.82 hours)\n\nTimestep: 8840000\nmean reward (100 episodes): 9621.2800\nbest mean reward: 10708.6200\ncurrent episode reward: 12420.0000\nepisodes: 2529\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39015.2 seconds (10.84 hours)\n\nTimestep: 8850000\nmean reward (100 episodes): 9610.7800\nbest mean reward: 10708.6200\ncurrent episode reward: 8010.0000\nepisodes: 2530\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39060.7 seconds (10.85 hours)\n\nTimestep: 8860000\nmean reward (100 episodes): 9558.6200\nbest mean reward: 10708.6200\ncurrent episode reward: 6274.0000\nepisodes: 2533\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39105.7 seconds (10.86 hours)\n\nTimestep: 8870000\nmean reward (100 episodes): 9537.2800\nbest mean reward: 10708.6200\ncurrent episode reward: 7326.0000\nepisodes: 2534\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39150.9 seconds (10.88 hours)\n\nTimestep: 8880000\nmean reward (100 episodes): 9581.8400\nbest mean reward: 10708.6200\ncurrent episode reward: 13064.0000\nepisodes: 2536\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39196.2 seconds (10.89 hours)\n\nTimestep: 8890000\nmean reward (100 episodes): 9610.7600\nbest mean reward: 10708.6200\ncurrent episode reward: 5348.0000\nepisodes: 2538\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39241.3 seconds (10.90 hours)\n\nTimestep: 8900000\nmean reward (100 episodes): 9612.3200\nbest mean reward: 10708.6200\ncurrent episode reward: 7386.0000\nepisodes: 2539\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39286.4 seconds (10.91 hours)\n\nTimestep: 8910000\nmean reward (100 episodes): 9534.2600\nbest mean reward: 10708.6200\ncurrent episode reward: 15312.0000\nepisodes: 2541\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39331.8 seconds (10.93 hours)\n\nTimestep: 8920000\nmean reward (100 episodes): 9503.9400\nbest mean reward: 10708.6200\ncurrent episode reward: 5552.0000\nepisodes: 2542\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39377.7 seconds (10.94 hours)\n\nTimestep: 8930000\nmean reward (100 episodes): 9597.7200\nbest mean reward: 10708.6200\ncurrent episode reward: 8690.0000\nepisodes: 2544\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39422.0 seconds (10.95 hours)\n\nTimestep: 8940000\nmean reward (100 episodes): 9558.8200\nbest mean reward: 10708.6200\ncurrent episode reward: 11200.0000\nepisodes: 2545\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39467.9 seconds (10.96 hours)\n\nTimestep: 8950000\nmean reward (100 episodes): 9552.1400\nbest mean reward: 10708.6200\ncurrent episode reward: 5212.0000\nepisodes: 2547\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39513.3 seconds (10.98 hours)\n\nTimestep: 8960000\nmean reward (100 episodes): 9561.9200\nbest mean reward: 10708.6200\ncurrent episode reward: 5812.0000\nepisodes: 2549\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39558.7 seconds (10.99 hours)\n\nTimestep: 8970000\nmean reward (100 episodes): 9579.6200\nbest mean reward: 10708.6200\ncurrent episode reward: 15660.0000\nepisodes: 2550\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39604.1 seconds (11.00 hours)\n\nTimestep: 8980000\nmean reward (100 episodes): 9567.9400\nbest mean reward: 10708.6200\ncurrent episode reward: 12294.0000\nepisodes: 2551\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39649.2 seconds (11.01 hours)\n\nTimestep: 8990000\nmean reward (100 episodes): 9710.4000\nbest mean reward: 10708.6200\ncurrent episode reward: 18850.0000\nepisodes: 2552\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39695.5 seconds (11.03 hours)\n\nTimestep: 9000000\nmean reward (100 episodes): 9706.6000\nbest mean reward: 10708.6200\ncurrent episode reward: 8458.0000\nepisodes: 2553\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39741.4 seconds (11.04 hours)\n\nTimestep: 9010000\nmean reward (100 episodes): 9737.0000\nbest mean reward: 10708.6200\ncurrent episode reward: 8750.0000\nepisodes: 2555\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39786.9 seconds (11.05 hours)\n\nTimestep: 9020000\nmean reward (100 episodes): 9698.7600\nbest mean reward: 10708.6200\ncurrent episode reward: 4284.0000\nepisodes: 2557\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39831.6 seconds (11.06 hours)\n\nTimestep: 9030000\nmean reward (100 episodes): 9607.9200\nbest mean reward: 10708.6200\ncurrent episode reward: 2552.0000\nepisodes: 2560\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39877.0 seconds (11.08 hours)\n\nTimestep: 9040000\nmean reward (100 episodes): 9708.3800\nbest mean reward: 10708.6200\ncurrent episode reward: 16460.0000\nepisodes: 2561\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39922.3 seconds (11.09 hours)\n\nTimestep: 9050000\nmean reward (100 episodes): 9708.3800\nbest mean reward: 10708.6200\ncurrent episode reward: 16460.0000\nepisodes: 2561\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39967.2 seconds (11.10 hours)\n\nTimestep: 9060000\nmean reward (100 episodes): 9858.2000\nbest mean reward: 10708.6200\ncurrent episode reward: 14310.0000\nepisodes: 2563\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40012.6 seconds (11.11 hours)\n\nTimestep: 9070000\nmean reward (100 episodes): 9904.7400\nbest mean reward: 10708.6200\ncurrent episode reward: 10350.0000\nepisodes: 2564\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40057.1 seconds (11.13 hours)\n\nTimestep: 9080000\nmean reward (100 episodes): 9816.4400\nbest mean reward: 10708.6200\ncurrent episode reward: 8764.0000\nepisodes: 2566\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40102.6 seconds (11.14 hours)\n\nTimestep: 9090000\nmean reward (100 episodes): 9718.1400\nbest mean reward: 10708.6200\ncurrent episode reward: 9480.0000\nepisodes: 2567\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40147.7 seconds (11.15 hours)\n\nTimestep: 9100000\nmean reward (100 episodes): 9757.7600\nbest mean reward: 10708.6200\ncurrent episode reward: 7956.0000\nepisodes: 2569\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40192.9 seconds (11.16 hours)\n\nTimestep: 9110000\nmean reward (100 episodes): 9740.8400\nbest mean reward: 10708.6200\ncurrent episode reward: 13094.0000\nepisodes: 2570\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40238.1 seconds (11.18 hours)\n\nTimestep: 9120000\nmean reward (100 episodes): 9806.9400\nbest mean reward: 10708.6200\ncurrent episode reward: 13000.0000\nepisodes: 2571\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40283.5 seconds (11.19 hours)\n\nTimestep: 9130000\nmean reward (100 episodes): 9558.5400\nbest mean reward: 10708.6200\ncurrent episode reward: 5858.0000\nepisodes: 2573\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40328.6 seconds (11.20 hours)\n\nTimestep: 9140000\nmean reward (100 episodes): 9548.7800\nbest mean reward: 10708.6200\ncurrent episode reward: 5726.0000\nepisodes: 2575\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40373.8 seconds (11.21 hours)\n\nTimestep: 9150000\nmean reward (100 episodes): 9654.8200\nbest mean reward: 10708.6200\ncurrent episode reward: 24964.0000\nepisodes: 2576\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40419.1 seconds (11.23 hours)\n\nTimestep: 9160000\nmean reward (100 episodes): 9566.4600\nbest mean reward: 10708.6200\ncurrent episode reward: 6210.0000\nepisodes: 2578\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40464.6 seconds (11.24 hours)\n\nTimestep: 9170000\nmean reward (100 episodes): 9510.5800\nbest mean reward: 10708.6200\ncurrent episode reward: 8132.0000\nepisodes: 2579\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40510.3 seconds (11.25 hours)\n\nTimestep: 9180000\nmean reward (100 episodes): 9506.9000\nbest mean reward: 10708.6200\ncurrent episode reward: 4350.0000\nepisodes: 2581\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40555.4 seconds (11.27 hours)\n\nTimestep: 9190000\nmean reward (100 episodes): 9600.8400\nbest mean reward: 10708.6200\ncurrent episode reward: 19284.0000\nepisodes: 2582\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40600.9 seconds (11.28 hours)\n\nTimestep: 9200000\nmean reward (100 episodes): 9450.2400\nbest mean reward: 10708.6200\ncurrent episode reward: 8002.0000\nepisodes: 2584\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40646.5 seconds (11.29 hours)\n\nTimestep: 9210000\nmean reward (100 episodes): 9343.2000\nbest mean reward: 10708.6200\ncurrent episode reward: 8386.0000\nepisodes: 2586\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40691.4 seconds (11.30 hours)\n\nTimestep: 9220000\nmean reward (100 episodes): 9348.7400\nbest mean reward: 10708.6200\ncurrent episode reward: 8794.0000\nepisodes: 2587\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40737.4 seconds (11.32 hours)\n\nTimestep: 9230000\nmean reward (100 episodes): 9376.5400\nbest mean reward: 10708.6200\ncurrent episode reward: 13892.0000\nepisodes: 2588\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40782.8 seconds (11.33 hours)\n\nTimestep: 9240000\nmean reward (100 episodes): 9470.2800\nbest mean reward: 10708.6200\ncurrent episode reward: 6678.0000\nepisodes: 2590\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40827.2 seconds (11.34 hours)\n\nTimestep: 9250000\nmean reward (100 episodes): 9485.4600\nbest mean reward: 10708.6200\ncurrent episode reward: 7920.0000\nepisodes: 2591\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40873.4 seconds (11.35 hours)\n\nTimestep: 9260000\nmean reward (100 episodes): 9510.6800\nbest mean reward: 10708.6200\ncurrent episode reward: 7500.0000\nepisodes: 2593\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40918.7 seconds (11.37 hours)\n\nTimestep: 9270000\nmean reward (100 episodes): 9514.3000\nbest mean reward: 10708.6200\ncurrent episode reward: 6724.0000\nepisodes: 2595\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40963.6 seconds (11.38 hours)\n\nTimestep: 9280000\nmean reward (100 episodes): 9616.6600\nbest mean reward: 10708.6200\ncurrent episode reward: 17526.0000\nepisodes: 2596\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41009.4 seconds (11.39 hours)\n\nTimestep: 9290000\nmean reward (100 episodes): 9532.1400\nbest mean reward: 10708.6200\ncurrent episode reward: 10750.0000\nepisodes: 2597\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41054.6 seconds (11.40 hours)\n\nTimestep: 9300000\nmean reward (100 episodes): 9552.8400\nbest mean reward: 10708.6200\ncurrent episode reward: 10920.0000\nepisodes: 2599\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41100.1 seconds (11.42 hours)\n\nTimestep: 9310000\nmean reward (100 episodes): 9581.3800\nbest mean reward: 10708.6200\ncurrent episode reward: 7782.0000\nepisodes: 2600\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41145.5 seconds (11.43 hours)\n\nTimestep: 9320000\nmean reward (100 episodes): 9655.3000\nbest mean reward: 10708.6200\ncurrent episode reward: 18642.0000\nepisodes: 2601\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41190.9 seconds (11.44 hours)\n\nTimestep: 9330000\nmean reward (100 episodes): 9639.9000\nbest mean reward: 10708.6200\ncurrent episode reward: 8346.0000\nepisodes: 2604\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41235.5 seconds (11.45 hours)\n\nTimestep: 9340000\nmean reward (100 episodes): 9455.3200\nbest mean reward: 10708.6200\ncurrent episode reward: 8452.0000\nepisodes: 2605\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41281.1 seconds (11.47 hours)\n\nTimestep: 9350000\nmean reward (100 episodes): 9437.8200\nbest mean reward: 10708.6200\ncurrent episode reward: 8122.0000\nepisodes: 2607\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41326.5 seconds (11.48 hours)\n\nTimestep: 9360000\nmean reward (100 episodes): 9449.5800\nbest mean reward: 10708.6200\ncurrent episode reward: 8592.0000\nepisodes: 2608\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41372.1 seconds (11.49 hours)\n\nTimestep: 9370000\nmean reward (100 episodes): 9502.7600\nbest mean reward: 10708.6200\ncurrent episode reward: 17118.0000\nepisodes: 2609\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41417.8 seconds (11.50 hours)\n\nTimestep: 9380000\nmean reward (100 episodes): 9425.2200\nbest mean reward: 10708.6200\ncurrent episode reward: 7264.0000\nepisodes: 2611\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41463.4 seconds (11.52 hours)\n\nTimestep: 9390000\nmean reward (100 episodes): 9350.4800\nbest mean reward: 10708.6200\ncurrent episode reward: 6810.0000\nepisodes: 2612\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41508.7 seconds (11.53 hours)\n\nTimestep: 9400000\nmean reward (100 episodes): 9344.4800\nbest mean reward: 10708.6200\ncurrent episode reward: 5952.0000\nepisodes: 2614\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41554.5 seconds (11.54 hours)\n\nTimestep: 9410000\nmean reward (100 episodes): 9322.3600\nbest mean reward: 10708.6200\ncurrent episode reward: 8528.0000\nepisodes: 2615\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41599.5 seconds (11.56 hours)\n\nTimestep: 9420000\nmean reward (100 episodes): 9241.8000\nbest mean reward: 10708.6200\ncurrent episode reward: 5854.0000\nepisodes: 2617\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41644.5 seconds (11.57 hours)\n\nTimestep: 9430000\nmean reward (100 episodes): 9239.4000\nbest mean reward: 10708.6200\ncurrent episode reward: 7912.0000\nepisodes: 2619\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41690.7 seconds (11.58 hours)\n\nTimestep: 9440000\nmean reward (100 episodes): 9157.0800\nbest mean reward: 10708.6200\ncurrent episode reward: 5440.0000\nepisodes: 2620\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41736.1 seconds (11.59 hours)\n\nTimestep: 9450000\nmean reward (100 episodes): 9262.0000\nbest mean reward: 10708.6200\ncurrent episode reward: 7668.0000\nepisodes: 2622\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41781.5 seconds (11.61 hours)\n\nTimestep: 9460000\nmean reward (100 episodes): 9267.5400\nbest mean reward: 10708.6200\ncurrent episode reward: 11120.0000\nepisodes: 2623\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41826.9 seconds (11.62 hours)\n\nTimestep: 9470000\nmean reward (100 episodes): 9296.5400\nbest mean reward: 10708.6200\ncurrent episode reward: 5666.0000\nepisodes: 2626\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41871.9 seconds (11.63 hours)\n\nTimestep: 9480000\nmean reward (100 episodes): 9323.9400\nbest mean reward: 10708.6200\ncurrent episode reward: 5500.0000\nepisodes: 2628\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41917.4 seconds (11.64 hours)\n\nTimestep: 9490000\nmean reward (100 episodes): 9311.0400\nbest mean reward: 10708.6200\ncurrent episode reward: 11130.0000\nepisodes: 2629\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41963.2 seconds (11.66 hours)\n\nTimestep: 9500000\nmean reward (100 episodes): 9295.9800\nbest mean reward: 10708.6200\ncurrent episode reward: 6504.0000\nepisodes: 2630\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42008.8 seconds (11.67 hours)\n\nTimestep: 9510000\nmean reward (100 episodes): 9415.2200\nbest mean reward: 10708.6200\ncurrent episode reward: 7176.0000\nepisodes: 2632\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42054.3 seconds (11.68 hours)\n\nTimestep: 9520000\nmean reward (100 episodes): 9544.8800\nbest mean reward: 10708.6200\ncurrent episode reward: 19240.0000\nepisodes: 2633\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42100.0 seconds (11.69 hours)\n\nTimestep: 9530000\nmean reward (100 episodes): 9570.0200\nbest mean reward: 10708.6200\ncurrent episode reward: 9840.0000\nepisodes: 2634\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42145.7 seconds (11.71 hours)\n\nTimestep: 9540000\nmean reward (100 episodes): 9626.6000\nbest mean reward: 10708.6200\ncurrent episode reward: 12618.0000\nepisodes: 2635\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42189.9 seconds (11.72 hours)\n\nTimestep: 9550000\nmean reward (100 episodes): 9675.6600\nbest mean reward: 10708.6200\ncurrent episode reward: 17970.0000\nepisodes: 2636\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42235.2 seconds (11.73 hours)\n\nTimestep: 9560000\nmean reward (100 episodes): 9764.7600\nbest mean reward: 10708.6200\ncurrent episode reward: 16338.0000\nepisodes: 2637\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42280.7 seconds (11.74 hours)\n\nTimestep: 9570000\nmean reward (100 episodes): 9944.6800\nbest mean reward: 10708.6200\ncurrent episode reward: 23340.0000\nepisodes: 2638\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42326.2 seconds (11.76 hours)\n\nTimestep: 9580000\nmean reward (100 episodes): 9992.6200\nbest mean reward: 10708.6200\ncurrent episode reward: 12180.0000\nepisodes: 2639\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42371.0 seconds (11.77 hours)\n\nTimestep: 9590000\nmean reward (100 episodes): 9871.7400\nbest mean reward: 10708.6200\ncurrent episode reward: 3964.0000\nepisodes: 2642\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42417.1 seconds (11.78 hours)\n\nTimestep: 9600000\nmean reward (100 episodes): 9931.0400\nbest mean reward: 10708.6200\ncurrent episode reward: 16890.0000\nepisodes: 2643\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42462.0 seconds (11.80 hours)\n\nTimestep: 9610000\nmean reward (100 episodes): 9952.4400\nbest mean reward: 10708.6200\ncurrent episode reward: 10830.0000\nepisodes: 2644\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42507.2 seconds (11.81 hours)\n\nTimestep: 9620000\nmean reward (100 episodes): 9897.2400\nbest mean reward: 10708.6200\ncurrent episode reward: 8734.0000\nepisodes: 2646\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42552.3 seconds (11.82 hours)\n\nTimestep: 9630000\nmean reward (100 episodes): 9919.1600\nbest mean reward: 10708.6200\ncurrent episode reward: 4928.0000\nepisodes: 2648\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42597.6 seconds (11.83 hours)\n\nTimestep: 9640000\nmean reward (100 episodes): 9961.8400\nbest mean reward: 10708.6200\ncurrent episode reward: 10080.0000\nepisodes: 2649\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42643.2 seconds (11.85 hours)\n\nTimestep: 9650000\nmean reward (100 episodes): 9884.3800\nbest mean reward: 10708.6200\ncurrent episode reward: 11118.0000\nepisodes: 2651\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42688.8 seconds (11.86 hours)\n\nTimestep: 9660000\nmean reward (100 episodes): 9806.7800\nbest mean reward: 10708.6200\ncurrent episode reward: 11090.0000\nepisodes: 2652\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42735.2 seconds (11.87 hours)\n\nTimestep: 9670000\nmean reward (100 episodes): 9817.1400\nbest mean reward: 10708.6200\ncurrent episode reward: 9494.0000\nepisodes: 2653\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42780.3 seconds (11.88 hours)\n\nTimestep: 9680000\nmean reward (100 episodes): 9817.8200\nbest mean reward: 10708.6200\ncurrent episode reward: 17378.0000\nepisodes: 2654\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42825.6 seconds (11.90 hours)\n\nTimestep: 9690000\nmean reward (100 episodes): 9851.2200\nbest mean reward: 10708.6200\ncurrent episode reward: 12090.0000\nepisodes: 2655\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42871.3 seconds (11.91 hours)\n\nTimestep: 9700000\nmean reward (100 episodes): 9985.6000\nbest mean reward: 10708.6200\ncurrent episode reward: 10848.0000\nepisodes: 2657\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42916.6 seconds (11.92 hours)\n\nTimestep: 9710000\nmean reward (100 episodes): 10028.8000\nbest mean reward: 10708.6200\ncurrent episode reward: 9888.0000\nepisodes: 2658\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42962.4 seconds (11.93 hours)\n\nTimestep: 9720000\nmean reward (100 episodes): 10093.9800\nbest mean reward: 10708.6200\ncurrent episode reward: 8610.0000\nepisodes: 2660\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43007.1 seconds (11.95 hours)\n\nTimestep: 9730000\nmean reward (100 episodes): 10008.6400\nbest mean reward: 10708.6200\ncurrent episode reward: 7926.0000\nepisodes: 2661\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43052.5 seconds (11.96 hours)\n\nTimestep: 9740000\nmean reward (100 episodes): 9958.1800\nbest mean reward: 10708.6200\ncurrent episode reward: 14100.0000\nepisodes: 2662\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43097.0 seconds (11.97 hours)\n\nTimestep: 9750000\nmean reward (100 episodes): 9824.0800\nbest mean reward: 10708.6200\ncurrent episode reward: 1380.0000\nepisodes: 2664\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43141.4 seconds (11.98 hours)\n\nTimestep: 9760000\nmean reward (100 episodes): 9896.5200\nbest mean reward: 10708.6200\ncurrent episode reward: 12460.0000\nepisodes: 2665\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43187.1 seconds (12.00 hours)\n\nTimestep: 9770000\nmean reward (100 episodes): 10047.5000\nbest mean reward: 10708.6200\ncurrent episode reward: 23862.0000\nepisodes: 2666\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43232.3 seconds (12.01 hours)\n\nTimestep: 9780000\nmean reward (100 episodes): 10077.6600\nbest mean reward: 10708.6200\ncurrent episode reward: 10018.0000\nepisodes: 2668\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43278.2 seconds (12.02 hours)\n\nTimestep: 9790000\nmean reward (100 episodes): 10001.0200\nbest mean reward: 10708.6200\ncurrent episode reward: 6322.0000\nepisodes: 2670\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43323.8 seconds (12.03 hours)\n\nTimestep: 9800000\nmean reward (100 episodes): 9969.9200\nbest mean reward: 10708.6200\ncurrent episode reward: 9890.0000\nepisodes: 2671\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43368.2 seconds (12.05 hours)\n\nTimestep: 9810000\nmean reward (100 episodes): 9980.9200\nbest mean reward: 10708.6200\ncurrent episode reward: 5608.0000\nepisodes: 2673\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43413.2 seconds (12.06 hours)\n\nTimestep: 9820000\nmean reward (100 episodes): 10015.9800\nbest mean reward: 10708.6200\ncurrent episode reward: 9896.0000\nepisodes: 2674\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43458.5 seconds (12.07 hours)\n\nTimestep: 9830000\nmean reward (100 episodes): 9886.2600\nbest mean reward: 10708.6200\ncurrent episode reward: 6444.0000\nepisodes: 2676\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43504.0 seconds (12.08 hours)\n\nTimestep: 9840000\nmean reward (100 episodes): 9977.9800\nbest mean reward: 10708.6200\ncurrent episode reward: 13584.0000\nepisodes: 2677\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43549.0 seconds (12.10 hours)\n\nTimestep: 9850000\nmean reward (100 episodes): 10067.0400\nbest mean reward: 10708.6200\ncurrent episode reward: 15116.0000\nepisodes: 2678\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43594.0 seconds (12.11 hours)\n\nTimestep: 9860000\nmean reward (100 episodes): 10112.9200\nbest mean reward: 10708.6200\ncurrent episode reward: 12720.0000\nepisodes: 2679\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43639.4 seconds (12.12 hours)\n\nTimestep: 9870000\nmean reward (100 episodes): 10085.7200\nbest mean reward: 10708.6200\ncurrent episode reward: 9220.0000\nepisodes: 2681\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43684.8 seconds (12.13 hours)\n\nTimestep: 9880000\nmean reward (100 episodes): 9995.8800\nbest mean reward: 10708.6200\ncurrent episode reward: 10300.0000\nepisodes: 2682\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43730.0 seconds (12.15 hours)\n\nTimestep: 9890000\nmean reward (100 episodes): 10078.3800\nbest mean reward: 10708.6200\ncurrent episode reward: 10254.0000\nepisodes: 2683\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43775.0 seconds (12.16 hours)\n\nTimestep: 9900000\nmean reward (100 episodes): 10107.6600\nbest mean reward: 10708.6200\ncurrent episode reward: 5730.0000\nepisodes: 2685\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43819.5 seconds (12.17 hours)\n\nTimestep: 9910000\nmean reward (100 episodes): 10099.1000\nbest mean reward: 10708.6200\ncurrent episode reward: 8374.0000\nepisodes: 2687\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43865.3 seconds (12.18 hours)\n\nTimestep: 9920000\nmean reward (100 episodes): 10034.0400\nbest mean reward: 10708.6200\ncurrent episode reward: 7386.0000\nepisodes: 2688\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43910.4 seconds (12.20 hours)\n\nTimestep: 9930000\nmean reward (100 episodes): 10022.9800\nbest mean reward: 10708.6200\ncurrent episode reward: 6258.0000\nepisodes: 2690\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43955.4 seconds (12.21 hours)\n\nTimestep: 9940000\nmean reward (100 episodes): 10018.4800\nbest mean reward: 10708.6200\ncurrent episode reward: 7470.0000\nepisodes: 2691\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44000.0 seconds (12.22 hours)\n\nTimestep: 9950000\nmean reward (100 episodes): 10076.1200\nbest mean reward: 10708.6200\ncurrent episode reward: 18198.0000\nepisodes: 2692\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44046.0 seconds (12.23 hours)\n\nTimestep: 9953926\nmean reward (100 episodes): 10053.9200\nbest mean reward: 10708.6200\ncurrent episode reward: 5280.0000\nepisodes: 2693\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44063.8 seconds (12.24 hours)\n"
  },
  {
    "path": "dqn/logs_text/Breakout_s001.text",
    "content": "('AVAILABLE GPUS: ', [u'device: 0, name: TITAN X (Pascal), pci bus id: 0000:01:00.0'])\ntask = Task<env_id=BreakoutNoFrameskip-v3 trials=2 max_timesteps=40000000 max_seconds=None reward_floor=1.7 reward_ceiling=800.0>\n\nTimestep: 60000\nmean reward (100 episodes): 1.5200\nbest mean reward: 1.8200\ncurrent episode reward: 1.0000\nepisodes: 331\nexploration: 0.94600\nlearning_rate: 0.00010\nelapsed time: 102.5 seconds (0.03 hours)\n\nTimestep: 70000\nmean reward (100 episodes): 1.5000\nbest mean reward: 1.8200\ncurrent episode reward: 1.0000\nepisodes: 385\nexploration: 0.93700\nlearning_rate: 0.00010\nelapsed time: 136.7 seconds (0.04 hours)\n\nTimestep: 80000\nmean reward (100 episodes): 1.7200\nbest mean reward: 1.8200\ncurrent episode reward: 1.0000\nepisodes: 441\nexploration: 0.92800\nlearning_rate: 0.00010\nelapsed time: 170.3 seconds (0.05 hours)\n\nTimestep: 90000\nmean reward (100 episodes): 1.4700\nbest mean reward: 1.8200\ncurrent episode reward: 5.0000\nepisodes: 499\nexploration: 0.91900\nlearning_rate: 0.00010\nelapsed time: 203.9 seconds (0.06 hours)\n\nTimestep: 100000\nmean reward (100 episodes): 1.6900\nbest mean reward: 1.8200\ncurrent episode reward: 3.0000\nepisodes: 554\nexploration: 0.91000\nlearning_rate: 0.00010\nelapsed time: 238.1 seconds (0.07 hours)\n\nTimestep: 110000\nmean reward (100 episodes): 1.5100\nbest mean reward: 1.8200\ncurrent episode reward: 2.0000\nepisodes: 614\nexploration: 0.90100\nlearning_rate: 0.00010\nelapsed time: 272.0 seconds (0.08 hours)\n\nTimestep: 120000\nmean reward (100 episodes): 1.4300\nbest mean reward: 1.8200\ncurrent episode reward: 2.0000\nepisodes: 672\nexploration: 0.89200\nlearning_rate: 0.00010\nelapsed time: 306.0 seconds (0.08 hours)\n\nTimestep: 130000\nmean reward (100 episodes): 1.7500\nbest mean reward: 1.8200\ncurrent episode reward: 7.0000\nepisodes: 722\nexploration: 0.88300\nlearning_rate: 0.00010\nelapsed time: 339.7 seconds (0.09 hours)\n\nTimestep: 140000\nmean reward (100 episodes): 1.7400\nbest mean reward: 1.8200\ncurrent episode reward: 4.0000\nepisodes: 778\nexploration: 0.87400\nlearning_rate: 0.00010\nelapsed time: 374.2 seconds (0.10 hours)\n\nTimestep: 150000\nmean reward (100 episodes): 1.5500\nbest mean reward: 1.8200\ncurrent episode reward: 1.0000\nepisodes: 836\nexploration: 0.86500\nlearning_rate: 0.00010\nelapsed time: 408.0 seconds (0.11 hours)\n\nTimestep: 160000\nmean reward (100 episodes): 1.5300\nbest mean reward: 1.8200\ncurrent episode reward: 1.0000\nepisodes: 895\nexploration: 0.85600\nlearning_rate: 0.00010\nelapsed time: 441.9 seconds (0.12 hours)\n\nTimestep: 170000\nmean reward (100 episodes): 1.4200\nbest mean reward: 1.8200\ncurrent episode reward: 0.0000\nepisodes: 952\nexploration: 0.84700\nlearning_rate: 0.00010\nelapsed time: 476.0 seconds (0.13 hours)\n\nTimestep: 180000\nmean reward (100 episodes): 1.5200\nbest mean reward: 1.8200\ncurrent episode reward: 2.0000\nepisodes: 1006\nexploration: 0.83800\nlearning_rate: 0.00010\nelapsed time: 511.2 seconds (0.14 hours)\n\nTimestep: 190000\nmean reward (100 episodes): 1.5900\nbest mean reward: 1.8200\ncurrent episode reward: 0.0000\nepisodes: 1063\nexploration: 0.82900\nlearning_rate: 0.00010\nelapsed time: 545.7 seconds (0.15 hours)\n\nTimestep: 200000\nmean reward (100 episodes): 1.4000\nbest mean reward: 1.8200\ncurrent episode reward: 1.0000\nepisodes: 1121\nexploration: 0.82000\nlearning_rate: 0.00010\nelapsed time: 580.2 seconds (0.16 hours)\n\nTimestep: 210000\nmean reward (100 episodes): 1.5200\nbest mean reward: 1.8200\ncurrent episode reward: 3.0000\nepisodes: 1175\nexploration: 0.81100\nlearning_rate: 0.00010\nelapsed time: 614.4 seconds (0.17 hours)\n\nTimestep: 220000\nmean reward (100 episodes): 1.6700\nbest mean reward: 1.8200\ncurrent episode reward: 4.0000\nepisodes: 1229\nexploration: 0.80200\nlearning_rate: 0.00010\nelapsed time: 649.2 seconds (0.18 hours)\n\nTimestep: 230000\nmean reward (100 episodes): 1.9000\nbest mean reward: 1.9000\ncurrent episode reward: 3.0000\nepisodes: 1279\nexploration: 0.79300\nlearning_rate: 0.00010\nelapsed time: 684.1 seconds (0.19 hours)\n\nTimestep: 240000\nmean reward (100 episodes): 2.0300\nbest mean reward: 2.1100\ncurrent episode reward: 4.0000\nepisodes: 1330\nexploration: 0.78400\nlearning_rate: 0.00010\nelapsed time: 718.9 seconds (0.20 hours)\n\nTimestep: 250000\nmean reward (100 episodes): 1.9100\nbest mean reward: 2.1300\ncurrent episode reward: 2.0000\nepisodes: 1383\nexploration: 0.77500\nlearning_rate: 0.00010\nelapsed time: 753.7 seconds (0.21 hours)\n\nTimestep: 260000\nmean reward (100 episodes): 1.9000\nbest mean reward: 2.1300\ncurrent episode reward: 0.0000\nepisodes: 1436\nexploration: 0.76600\nlearning_rate: 0.00010\nelapsed time: 788.5 seconds (0.22 hours)\n\nTimestep: 270000\nmean reward (100 episodes): 2.1400\nbest mean reward: 2.1400\ncurrent episode reward: 4.0000\nepisodes: 1483\nexploration: 0.75700\nlearning_rate: 0.00010\nelapsed time: 823.5 seconds (0.23 hours)\n\nTimestep: 280000\nmean reward (100 episodes): 2.4000\nbest mean reward: 2.4100\ncurrent episode reward: 2.0000\nepisodes: 1530\nexploration: 0.74800\nlearning_rate: 0.00010\nelapsed time: 858.8 seconds (0.24 hours)\n\nTimestep: 290000\nmean reward (100 episodes): 2.5000\nbest mean reward: 2.5900\ncurrent episode reward: 0.0000\nepisodes: 1575\nexploration: 0.73900\nlearning_rate: 0.00010\nelapsed time: 894.1 seconds (0.25 hours)\n\nTimestep: 300000\nmean reward (100 episodes): 2.8400\nbest mean reward: 2.8400\ncurrent episode reward: 5.0000\nepisodes: 1619\nexploration: 0.73000\nlearning_rate: 0.00010\nelapsed time: 929.4 seconds (0.26 hours)\n\nTimestep: 310000\nmean reward (100 episodes): 3.1500\nbest mean reward: 3.2400\ncurrent episode reward: 4.0000\nepisodes: 1657\nexploration: 0.72100\nlearning_rate: 0.00010\nelapsed time: 964.7 seconds (0.27 hours)\n\nTimestep: 320000\nmean reward (100 episodes): 3.5100\nbest mean reward: 3.5700\ncurrent episode reward: 3.0000\nepisodes: 1696\nexploration: 0.71200\nlearning_rate: 0.00010\nelapsed time: 1000.2 seconds (0.28 hours)\n\nTimestep: 330000\nmean reward (100 episodes): 4.0300\nbest mean reward: 4.0300\ncurrent episode reward: 5.0000\nepisodes: 1731\nexploration: 0.70300\nlearning_rate: 0.00010\nelapsed time: 1035.5 seconds (0.29 hours)\n\nTimestep: 340000\nmean reward (100 episodes): 4.0800\nbest mean reward: 4.0800\ncurrent episode reward: 4.0000\nepisodes: 1768\nexploration: 0.69400\nlearning_rate: 0.00010\nelapsed time: 1071.3 seconds (0.30 hours)\n\nTimestep: 350000\nmean reward (100 episodes): 4.5300\nbest mean reward: 4.6200\ncurrent episode reward: 3.0000\nepisodes: 1798\nexploration: 0.68500\nlearning_rate: 0.00010\nelapsed time: 1106.9 seconds (0.31 hours)\n\nTimestep: 360000\nmean reward (100 episodes): 4.6200\nbest mean reward: 4.6900\ncurrent episode reward: 2.0000\nepisodes: 1833\nexploration: 0.67600\nlearning_rate: 0.00010\nelapsed time: 1142.8 seconds (0.32 hours)\n\nTimestep: 370000\nmean reward (100 episodes): 5.0300\nbest mean reward: 5.0600\ncurrent episode reward: 6.0000\nepisodes: 1864\nexploration: 0.66700\nlearning_rate: 0.00010\nelapsed time: 1178.5 seconds (0.33 hours)\n\nTimestep: 380000\nmean reward (100 episodes): 5.1200\nbest mean reward: 5.4000\ncurrent episode reward: 3.0000\nepisodes: 1895\nexploration: 0.65800\nlearning_rate: 0.00010\nelapsed time: 1214.1 seconds (0.34 hours)\n\nTimestep: 390000\nmean reward (100 episodes): 5.5900\nbest mean reward: 5.5900\ncurrent episode reward: 6.0000\nepisodes: 1924\nexploration: 0.64900\nlearning_rate: 0.00010\nelapsed time: 1250.2 seconds (0.35 hours)\n\nTimestep: 400000\nmean reward (100 episodes): 5.6200\nbest mean reward: 5.7500\ncurrent episode reward: 5.0000\nepisodes: 1956\nexploration: 0.64000\nlearning_rate: 0.00010\nelapsed time: 1286.5 seconds (0.36 hours)\n\nTimestep: 410000\nmean reward (100 episodes): 5.7000\nbest mean reward: 5.7500\ncurrent episode reward: 2.0000\nepisodes: 1986\nexploration: 0.63100\nlearning_rate: 0.00010\nelapsed time: 1322.7 seconds (0.37 hours)\n\nTimestep: 420000\nmean reward (100 episodes): 5.5800\nbest mean reward: 5.7500\ncurrent episode reward: 4.0000\nepisodes: 2014\nexploration: 0.62200\nlearning_rate: 0.00010\nelapsed time: 1360.6 seconds (0.38 hours)\n\nTimestep: 430000\nmean reward (100 episodes): 5.5400\nbest mean reward: 5.7500\ncurrent episode reward: 9.0000\nepisodes: 2046\nexploration: 0.61300\nlearning_rate: 0.00010\nelapsed time: 1397.2 seconds (0.39 hours)\n\nTimestep: 440000\nmean reward (100 episodes): 5.9200\nbest mean reward: 5.9400\ncurrent episode reward: 5.0000\nepisodes: 2073\nexploration: 0.60400\nlearning_rate: 0.00010\nelapsed time: 1434.1 seconds (0.40 hours)\n\nTimestep: 450000\nmean reward (100 episodes): 6.0600\nbest mean reward: 6.1000\ncurrent episode reward: 5.0000\nepisodes: 2102\nexploration: 0.59500\nlearning_rate: 0.00010\nelapsed time: 1471.0 seconds (0.41 hours)\n\nTimestep: 460000\nmean reward (100 episodes): 6.0700\nbest mean reward: 6.1300\ncurrent episode reward: 5.0000\nepisodes: 2131\nexploration: 0.58600\nlearning_rate: 0.00010\nelapsed time: 1508.5 seconds (0.42 hours)\n\nTimestep: 470000\nmean reward (100 episodes): 6.3500\nbest mean reward: 6.4600\ncurrent episode reward: 7.0000\nepisodes: 2158\nexploration: 0.57700\nlearning_rate: 0.00010\nelapsed time: 1546.4 seconds (0.43 hours)\n\nTimestep: 480000\nmean reward (100 episodes): 6.2200\nbest mean reward: 6.5200\ncurrent episode reward: 7.0000\nepisodes: 2185\nexploration: 0.56800\nlearning_rate: 0.00010\nelapsed time: 1583.4 seconds (0.44 hours)\n\nTimestep: 490000\nmean reward (100 episodes): 6.5600\nbest mean reward: 6.6200\ncurrent episode reward: 9.0000\nepisodes: 2212\nexploration: 0.55900\nlearning_rate: 0.00010\nelapsed time: 1620.8 seconds (0.45 hours)\n\nTimestep: 500000\nmean reward (100 episodes): 6.9100\nbest mean reward: 6.9400\ncurrent episode reward: 13.0000\nepisodes: 2238\nexploration: 0.55000\nlearning_rate: 0.00010\nelapsed time: 1658.2 seconds (0.46 hours)\n\nTimestep: 510000\nmean reward (100 episodes): 7.2200\nbest mean reward: 7.3300\ncurrent episode reward: 4.0000\nepisodes: 2263\nexploration: 0.54100\nlearning_rate: 0.00010\nelapsed time: 1695.5 seconds (0.47 hours)\n\nTimestep: 520000\nmean reward (100 episodes): 7.3300\nbest mean reward: 7.4300\ncurrent episode reward: 10.0000\nepisodes: 2289\nexploration: 0.53200\nlearning_rate: 0.00010\nelapsed time: 1733.5 seconds (0.48 hours)\n\nTimestep: 530000\nmean reward (100 episodes): 7.7200\nbest mean reward: 7.8900\ncurrent episode reward: 4.0000\nepisodes: 2315\nexploration: 0.52300\nlearning_rate: 0.00010\nelapsed time: 1770.6 seconds (0.49 hours)\n\nTimestep: 540000\nmean reward (100 episodes): 7.5900\nbest mean reward: 7.8900\ncurrent episode reward: 2.0000\nepisodes: 2343\nexploration: 0.51400\nlearning_rate: 0.00010\nelapsed time: 1808.0 seconds (0.50 hours)\n\nTimestep: 550000\nmean reward (100 episodes): 7.5700\nbest mean reward: 7.8900\ncurrent episode reward: 8.0000\nepisodes: 2368\nexploration: 0.50500\nlearning_rate: 0.00010\nelapsed time: 1846.2 seconds (0.51 hours)\n\nTimestep: 560000\nmean reward (100 episodes): 7.3200\nbest mean reward: 7.8900\ncurrent episode reward: 7.0000\nepisodes: 2396\nexploration: 0.49600\nlearning_rate: 0.00010\nelapsed time: 1884.0 seconds (0.52 hours)\n\nTimestep: 570000\nmean reward (100 episodes): 7.5200\nbest mean reward: 7.8900\ncurrent episode reward: 6.0000\nepisodes: 2421\nexploration: 0.48700\nlearning_rate: 0.00010\nelapsed time: 1922.1 seconds (0.53 hours)\n\nTimestep: 580000\nmean reward (100 episodes): 7.5500\nbest mean reward: 7.8900\ncurrent episode reward: 10.0000\nepisodes: 2447\nexploration: 0.47800\nlearning_rate: 0.00010\nelapsed time: 1960.0 seconds (0.54 hours)\n\nTimestep: 590000\nmean reward (100 episodes): 7.8200\nbest mean reward: 7.8900\ncurrent episode reward: 8.0000\nepisodes: 2470\nexploration: 0.46900\nlearning_rate: 0.00010\nelapsed time: 1998.4 seconds (0.56 hours)\n\nTimestep: 600000\nmean reward (100 episodes): 8.2500\nbest mean reward: 8.2500\ncurrent episode reward: 5.0000\nepisodes: 2493\nexploration: 0.46000\nlearning_rate: 0.00010\nelapsed time: 2037.0 seconds (0.57 hours)\n\nTimestep: 610000\nmean reward (100 episodes): 8.6000\nbest mean reward: 8.7800\ncurrent episode reward: 8.0000\nepisodes: 2516\nexploration: 0.45100\nlearning_rate: 0.00010\nelapsed time: 2074.9 seconds (0.58 hours)\n\nTimestep: 620000\nmean reward (100 episodes): 8.8400\nbest mean reward: 8.8600\ncurrent episode reward: 7.0000\nepisodes: 2540\nexploration: 0.44200\nlearning_rate: 0.00010\nelapsed time: 2114.5 seconds (0.59 hours)\n\nTimestep: 630000\nmean reward (100 episodes): 8.7800\nbest mean reward: 8.9500\ncurrent episode reward: 15.0000\nepisodes: 2564\nexploration: 0.43300\nlearning_rate: 0.00010\nelapsed time: 2153.9 seconds (0.60 hours)\n\nTimestep: 640000\nmean reward (100 episodes): 8.8100\nbest mean reward: 8.9500\ncurrent episode reward: 3.0000\nepisodes: 2586\nexploration: 0.42400\nlearning_rate: 0.00010\nelapsed time: 2193.2 seconds (0.61 hours)\n\nTimestep: 650000\nmean reward (100 episodes): 8.6300\nbest mean reward: 9.0500\ncurrent episode reward: 5.0000\nepisodes: 2610\nexploration: 0.41500\nlearning_rate: 0.00010\nelapsed time: 2231.9 seconds (0.62 hours)\n\nTimestep: 660000\nmean reward (100 episodes): 8.9600\nbest mean reward: 9.0500\ncurrent episode reward: 10.0000\nepisodes: 2631\nexploration: 0.40600\nlearning_rate: 0.00010\nelapsed time: 2270.2 seconds (0.63 hours)\n\nTimestep: 670000\nmean reward (100 episodes): 9.4500\nbest mean reward: 9.4500\ncurrent episode reward: 19.0000\nepisodes: 2654\nexploration: 0.39700\nlearning_rate: 0.00010\nelapsed time: 2309.1 seconds (0.64 hours)\n\nTimestep: 680000\nmean reward (100 episodes): 9.8700\nbest mean reward: 10.0200\ncurrent episode reward: 7.0000\nepisodes: 2675\nexploration: 0.38800\nlearning_rate: 0.00010\nelapsed time: 2348.1 seconds (0.65 hours)\n\nTimestep: 690000\nmean reward (100 episodes): 9.9800\nbest mean reward: 10.0200\ncurrent episode reward: 9.0000\nepisodes: 2696\nexploration: 0.37900\nlearning_rate: 0.00010\nelapsed time: 2387.0 seconds (0.66 hours)\n\nTimestep: 700000\nmean reward (100 episodes): 10.3600\nbest mean reward: 10.4100\ncurrent episode reward: 1.0000\nepisodes: 2718\nexploration: 0.37000\nlearning_rate: 0.00010\nelapsed time: 2426.2 seconds (0.67 hours)\n\nTimestep: 710000\nmean reward (100 episodes): 10.2100\nbest mean reward: 10.4800\ncurrent episode reward: 15.0000\nepisodes: 2741\nexploration: 0.36100\nlearning_rate: 0.00010\nelapsed time: 2465.8 seconds (0.68 hours)\n\nTimestep: 720000\nmean reward (100 episodes): 10.3000\nbest mean reward: 10.5200\ncurrent episode reward: 11.0000\nepisodes: 2760\nexploration: 0.35200\nlearning_rate: 0.00010\nelapsed time: 2505.5 seconds (0.70 hours)\n\nTimestep: 730000\nmean reward (100 episodes): 10.4600\nbest mean reward: 10.6400\ncurrent episode reward: 9.0000\nepisodes: 2782\nexploration: 0.34300\nlearning_rate: 0.00010\nelapsed time: 2544.8 seconds (0.71 hours)\n\nTimestep: 740000\nmean reward (100 episodes): 10.5100\nbest mean reward: 10.6400\ncurrent episode reward: 15.0000\nepisodes: 2804\nexploration: 0.33400\nlearning_rate: 0.00010\nelapsed time: 2584.7 seconds (0.72 hours)\n\nTimestep: 750000\nmean reward (100 episodes): 11.2000\nbest mean reward: 11.2300\ncurrent episode reward: 11.0000\nepisodes: 2820\nexploration: 0.32500\nlearning_rate: 0.00010\nelapsed time: 2624.3 seconds (0.73 hours)\n\nTimestep: 760000\nmean reward (100 episodes): 12.1700\nbest mean reward: 12.1700\ncurrent episode reward: 5.0000\nepisodes: 2838\nexploration: 0.31600\nlearning_rate: 0.00010\nelapsed time: 2665.3 seconds (0.74 hours)\n\nTimestep: 770000\nmean reward (100 episodes): 13.0800\nbest mean reward: 13.1100\ncurrent episode reward: 16.0000\nepisodes: 2854\nexploration: 0.30700\nlearning_rate: 0.00010\nelapsed time: 2706.5 seconds (0.75 hours)\n\nTimestep: 780000\nmean reward (100 episodes): 13.5100\nbest mean reward: 13.5100\ncurrent episode reward: 21.0000\nepisodes: 2873\nexploration: 0.29800\nlearning_rate: 0.00010\nelapsed time: 2747.8 seconds (0.76 hours)\n\nTimestep: 790000\nmean reward (100 episodes): 14.2300\nbest mean reward: 14.3100\ncurrent episode reward: 10.0000\nepisodes: 2891\nexploration: 0.28900\nlearning_rate: 0.00010\nelapsed time: 2789.2 seconds (0.77 hours)\n\nTimestep: 800000\nmean reward (100 episodes): 14.2600\nbest mean reward: 14.5000\ncurrent episode reward: 13.0000\nepisodes: 2910\nexploration: 0.28000\nlearning_rate: 0.00010\nelapsed time: 2830.1 seconds (0.79 hours)\n\nTimestep: 810000\nmean reward (100 episodes): 14.3300\nbest mean reward: 14.6000\ncurrent episode reward: 13.0000\nepisodes: 2927\nexploration: 0.27100\nlearning_rate: 0.00010\nelapsed time: 2871.5 seconds (0.80 hours)\n\nTimestep: 820000\nmean reward (100 episodes): 14.8300\nbest mean reward: 14.9500\ncurrent episode reward: 18.0000\nepisodes: 2943\nexploration: 0.26200\nlearning_rate: 0.00010\nelapsed time: 2912.6 seconds (0.81 hours)\n\nTimestep: 830000\nmean reward (100 episodes): 15.4000\nbest mean reward: 15.5300\ncurrent episode reward: 15.0000\nepisodes: 2957\nexploration: 0.25300\nlearning_rate: 0.00010\nelapsed time: 2953.6 seconds (0.82 hours)\n\nTimestep: 840000\nmean reward (100 episodes): 16.6500\nbest mean reward: 16.6500\ncurrent episode reward: 38.0000\nepisodes: 2970\nexploration: 0.24400\nlearning_rate: 0.00010\nelapsed time: 2995.5 seconds (0.83 hours)\n\nTimestep: 850000\nmean reward (100 episodes): 17.1200\nbest mean reward: 17.1200\ncurrent episode reward: 28.0000\nepisodes: 2987\nexploration: 0.23500\nlearning_rate: 0.00010\nelapsed time: 3037.5 seconds (0.84 hours)\n\nTimestep: 860000\nmean reward (100 episodes): 18.3200\nbest mean reward: 18.3200\ncurrent episode reward: 31.0000\nepisodes: 3001\nexploration: 0.22600\nlearning_rate: 0.00010\nelapsed time: 3082.1 seconds (0.86 hours)\n\nTimestep: 870000\nmean reward (100 episodes): 19.0900\nbest mean reward: 19.0900\ncurrent episode reward: 39.0000\nepisodes: 3014\nexploration: 0.21700\nlearning_rate: 0.00010\nelapsed time: 3125.0 seconds (0.87 hours)\n\nTimestep: 880000\nmean reward (100 episodes): 20.5900\nbest mean reward: 20.5900\ncurrent episode reward: 28.0000\nepisodes: 3027\nexploration: 0.20800\nlearning_rate: 0.00010\nelapsed time: 3167.8 seconds (0.88 hours)\n\nTimestep: 890000\nmean reward (100 episodes): 21.4400\nbest mean reward: 21.4400\ncurrent episode reward: 33.0000\nepisodes: 3039\nexploration: 0.19900\nlearning_rate: 0.00010\nelapsed time: 3210.6 seconds (0.89 hours)\n\nTimestep: 900000\nmean reward (100 episodes): 21.8600\nbest mean reward: 22.0300\ncurrent episode reward: 23.0000\nepisodes: 3051\nexploration: 0.19000\nlearning_rate: 0.00010\nelapsed time: 3253.4 seconds (0.90 hours)\n\nTimestep: 910000\nmean reward (100 episodes): 22.5000\nbest mean reward: 22.5000\ncurrent episode reward: 33.0000\nepisodes: 3066\nexploration: 0.18100\nlearning_rate: 0.00010\nelapsed time: 3295.9 seconds (0.92 hours)\n\nTimestep: 920000\nmean reward (100 episodes): 23.0100\nbest mean reward: 23.0100\ncurrent episode reward: 32.0000\nepisodes: 3077\nexploration: 0.17200\nlearning_rate: 0.00010\nelapsed time: 3338.8 seconds (0.93 hours)\n\nTimestep: 930000\nmean reward (100 episodes): 24.0300\nbest mean reward: 24.0300\ncurrent episode reward: 30.0000\nepisodes: 3089\nexploration: 0.16300\nlearning_rate: 0.00010\nelapsed time: 3381.1 seconds (0.94 hours)\n\nTimestep: 940000\nmean reward (100 episodes): 25.2400\nbest mean reward: 25.2400\ncurrent episode reward: 42.0000\nepisodes: 3101\nexploration: 0.15400\nlearning_rate: 0.00010\nelapsed time: 3424.0 seconds (0.95 hours)\n\nTimestep: 950000\nmean reward (100 episodes): 26.3400\nbest mean reward: 26.3400\ncurrent episode reward: 34.0000\nepisodes: 3112\nexploration: 0.14500\nlearning_rate: 0.00010\nelapsed time: 3467.3 seconds (0.96 hours)\n\nTimestep: 960000\nmean reward (100 episodes): 27.3600\nbest mean reward: 27.4200\ncurrent episode reward: 42.0000\nepisodes: 3122\nexploration: 0.13600\nlearning_rate: 0.00010\nelapsed time: 3511.3 seconds (0.98 hours)\n\nTimestep: 970000\nmean reward (100 episodes): 28.3200\nbest mean reward: 28.3200\ncurrent episode reward: 37.0000\nepisodes: 3133\nexploration: 0.12700\nlearning_rate: 0.00010\nelapsed time: 3554.2 seconds (0.99 hours)\n\nTimestep: 980000\nmean reward (100 episodes): 29.0700\nbest mean reward: 29.0700\ncurrent episode reward: 34.0000\nepisodes: 3143\nexploration: 0.11800\nlearning_rate: 0.00010\nelapsed time: 3598.1 seconds (1.00 hours)\n\nTimestep: 990000\nmean reward (100 episodes): 30.9100\nbest mean reward: 30.9600\ncurrent episode reward: 11.0000\nepisodes: 3153\nexploration: 0.10900\nlearning_rate: 0.00010\nelapsed time: 3641.5 seconds (1.01 hours)\n\nTimestep: 1000000\nmean reward (100 episodes): 32.5100\nbest mean reward: 32.5100\ncurrent episode reward: 25.0000\nepisodes: 3163\nexploration: 0.10000\nlearning_rate: 0.00010\nelapsed time: 3684.6 seconds (1.02 hours)\n\nTimestep: 1010000\nmean reward (100 episodes): 34.2300\nbest mean reward: 34.2300\ncurrent episode reward: 19.0000\nepisodes: 3173\nexploration: 0.09978\nlearning_rate: 0.00010\nelapsed time: 3727.4 seconds (1.04 hours)\n\nTimestep: 1020000\nmean reward (100 episodes): 35.4700\nbest mean reward: 35.4700\ncurrent episode reward: 42.0000\nepisodes: 3183\nexploration: 0.09955\nlearning_rate: 0.00010\nelapsed time: 3770.7 seconds (1.05 hours)\n\nTimestep: 1030000\nmean reward (100 episodes): 37.0400\nbest mean reward: 37.0400\ncurrent episode reward: 78.0000\nepisodes: 3191\nexploration: 0.09933\nlearning_rate: 0.00010\nelapsed time: 3813.8 seconds (1.06 hours)\n\nTimestep: 1040000\nmean reward (100 episodes): 37.8800\nbest mean reward: 37.8800\ncurrent episode reward: 58.0000\nepisodes: 3201\nexploration: 0.09910\nlearning_rate: 0.00010\nelapsed time: 3857.4 seconds (1.07 hours)\n\nTimestep: 1050000\nmean reward (100 episodes): 39.5500\nbest mean reward: 39.5900\ncurrent episode reward: 46.0000\nepisodes: 3211\nexploration: 0.09888\nlearning_rate: 0.00010\nelapsed time: 3901.2 seconds (1.08 hours)\n\nTimestep: 1060000\nmean reward (100 episodes): 40.2400\nbest mean reward: 40.3000\ncurrent episode reward: 38.0000\nepisodes: 3220\nexploration: 0.09865\nlearning_rate: 0.00010\nelapsed time: 3944.7 seconds (1.10 hours)\n\nTimestep: 1070000\nmean reward (100 episodes): 40.7500\nbest mean reward: 40.7500\ncurrent episode reward: 74.0000\nepisodes: 3229\nexploration: 0.09842\nlearning_rate: 0.00010\nelapsed time: 3988.4 seconds (1.11 hours)\n\nTimestep: 1080000\nmean reward (100 episodes): 41.4200\nbest mean reward: 41.4200\ncurrent episode reward: 24.0000\nepisodes: 3239\nexploration: 0.09820\nlearning_rate: 0.00010\nelapsed time: 4031.8 seconds (1.12 hours)\n\nTimestep: 1090000\nmean reward (100 episodes): 42.0700\nbest mean reward: 42.0700\ncurrent episode reward: 86.0000\nepisodes: 3248\nexploration: 0.09798\nlearning_rate: 0.00010\nelapsed time: 4075.1 seconds (1.13 hours)\n\nTimestep: 1100000\nmean reward (100 episodes): 43.2100\nbest mean reward: 43.2100\ncurrent episode reward: 77.0000\nepisodes: 3256\nexploration: 0.09775\nlearning_rate: 0.00010\nelapsed time: 4118.6 seconds (1.14 hours)\n\nTimestep: 1110000\nmean reward (100 episodes): 43.8300\nbest mean reward: 43.8300\ncurrent episode reward: 54.0000\nepisodes: 3264\nexploration: 0.09753\nlearning_rate: 0.00010\nelapsed time: 4162.6 seconds (1.16 hours)\n\nTimestep: 1120000\nmean reward (100 episodes): 44.6800\nbest mean reward: 44.6800\ncurrent episode reward: 46.0000\nepisodes: 3273\nexploration: 0.09730\nlearning_rate: 0.00010\nelapsed time: 4206.5 seconds (1.17 hours)\n\nTimestep: 1130000\nmean reward (100 episodes): 44.9000\nbest mean reward: 44.9000\ncurrent episode reward: 61.0000\nepisodes: 3281\nexploration: 0.09708\nlearning_rate: 0.00010\nelapsed time: 4249.6 seconds (1.18 hours)\n\nTimestep: 1140000\nmean reward (100 episodes): 45.4400\nbest mean reward: 45.7700\ncurrent episode reward: 45.0000\nepisodes: 3290\nexploration: 0.09685\nlearning_rate: 0.00010\nelapsed time: 4293.2 seconds (1.19 hours)\n\nTimestep: 1150000\nmean reward (100 episodes): 45.6200\nbest mean reward: 45.7700\ncurrent episode reward: 40.0000\nepisodes: 3299\nexploration: 0.09663\nlearning_rate: 0.00010\nelapsed time: 4336.9 seconds (1.20 hours)\n\nTimestep: 1160000\nmean reward (100 episodes): 45.4900\nbest mean reward: 46.5500\ncurrent episode reward: 33.0000\nepisodes: 3308\nexploration: 0.09640\nlearning_rate: 0.00010\nelapsed time: 4380.7 seconds (1.22 hours)\n\nTimestep: 1170000\nmean reward (100 episodes): 46.2700\nbest mean reward: 47.1200\ncurrent episode reward: 48.0000\nepisodes: 3318\nexploration: 0.09618\nlearning_rate: 0.00010\nelapsed time: 4423.9 seconds (1.23 hours)\n\nTimestep: 1180000\nmean reward (100 episodes): 46.8500\nbest mean reward: 47.1200\ncurrent episode reward: 64.0000\nepisodes: 3327\nexploration: 0.09595\nlearning_rate: 0.00010\nelapsed time: 4467.3 seconds (1.24 hours)\n\nTimestep: 1190000\nmean reward (100 episodes): 47.9400\nbest mean reward: 47.9400\ncurrent episode reward: 75.0000\nepisodes: 3335\nexploration: 0.09573\nlearning_rate: 0.00010\nelapsed time: 4511.7 seconds (1.25 hours)\n\nTimestep: 1200000\nmean reward (100 episodes): 48.0400\nbest mean reward: 48.1500\ncurrent episode reward: 33.0000\nepisodes: 3344\nexploration: 0.09550\nlearning_rate: 0.00010\nelapsed time: 4555.0 seconds (1.27 hours)\n\nTimestep: 1210000\nmean reward (100 episodes): 48.3100\nbest mean reward: 48.4700\ncurrent episode reward: 82.0000\nepisodes: 3352\nexploration: 0.09527\nlearning_rate: 0.00010\nelapsed time: 4599.2 seconds (1.28 hours)\n\nTimestep: 1220000\nmean reward (100 episodes): 48.7100\nbest mean reward: 48.7100\ncurrent episode reward: 50.0000\nepisodes: 3360\nexploration: 0.09505\nlearning_rate: 0.00010\nelapsed time: 4643.0 seconds (1.29 hours)\n\nTimestep: 1230000\nmean reward (100 episodes): 48.7900\nbest mean reward: 49.4700\ncurrent episode reward: 0.0000\nepisodes: 3369\nexploration: 0.09483\nlearning_rate: 0.00010\nelapsed time: 4687.3 seconds (1.30 hours)\n\nTimestep: 1240000\nmean reward (100 episodes): 48.3000\nbest mean reward: 49.4700\ncurrent episode reward: 19.0000\nepisodes: 3378\nexploration: 0.09460\nlearning_rate: 0.00010\nelapsed time: 4731.3 seconds (1.31 hours)\n\nTimestep: 1250000\nmean reward (100 episodes): 48.3500\nbest mean reward: 49.4700\ncurrent episode reward: 76.0000\nepisodes: 3387\nexploration: 0.09438\nlearning_rate: 0.00010\nelapsed time: 4775.2 seconds (1.33 hours)\n\nTimestep: 1260000\nmean reward (100 episodes): 49.2100\nbest mean reward: 49.6700\ncurrent episode reward: 56.0000\nepisodes: 3396\nexploration: 0.09415\nlearning_rate: 0.00010\nelapsed time: 4819.4 seconds (1.34 hours)\n\nTimestep: 1270000\nmean reward (100 episodes): 49.7500\nbest mean reward: 49.7500\ncurrent episode reward: 59.0000\nepisodes: 3404\nexploration: 0.09393\nlearning_rate: 0.00010\nelapsed time: 4863.2 seconds (1.35 hours)\n\nTimestep: 1280000\nmean reward (100 episodes): 50.6200\nbest mean reward: 50.6200\ncurrent episode reward: 69.0000\nepisodes: 3412\nexploration: 0.09370\nlearning_rate: 0.00010\nelapsed time: 4906.5 seconds (1.36 hours)\n\nTimestep: 1290000\nmean reward (100 episodes): 51.0400\nbest mean reward: 51.2000\ncurrent episode reward: 74.0000\nepisodes: 3421\nexploration: 0.09348\nlearning_rate: 0.00010\nelapsed time: 4950.0 seconds (1.38 hours)\n\nTimestep: 1300000\nmean reward (100 episodes): 53.0000\nbest mean reward: 53.0000\ncurrent episode reward: 70.0000\nepisodes: 3428\nexploration: 0.09325\nlearning_rate: 0.00010\nelapsed time: 4993.6 seconds (1.39 hours)\n\nTimestep: 1310000\nmean reward (100 episodes): 52.4300\nbest mean reward: 53.0700\ncurrent episode reward: 64.0000\nepisodes: 3437\nexploration: 0.09303\nlearning_rate: 0.00010\nelapsed time: 5038.2 seconds (1.40 hours)\n\nTimestep: 1320000\nmean reward (100 episodes): 53.0900\nbest mean reward: 53.2400\ncurrent episode reward: 61.0000\nepisodes: 3446\nexploration: 0.09280\nlearning_rate: 0.00010\nelapsed time: 5082.2 seconds (1.41 hours)\n\nTimestep: 1330000\nmean reward (100 episodes): 53.1400\nbest mean reward: 53.2400\ncurrent episode reward: 61.0000\nepisodes: 3454\nexploration: 0.09258\nlearning_rate: 0.00010\nelapsed time: 5126.0 seconds (1.42 hours)\n\nTimestep: 1340000\nmean reward (100 episodes): 52.3600\nbest mean reward: 53.2400\ncurrent episode reward: 57.0000\nepisodes: 3463\nexploration: 0.09235\nlearning_rate: 0.00010\nelapsed time: 5170.4 seconds (1.44 hours)\n\nTimestep: 1350000\nmean reward (100 episodes): 51.9900\nbest mean reward: 53.2400\ncurrent episode reward: 95.0000\nepisodes: 3473\nexploration: 0.09213\nlearning_rate: 0.00010\nelapsed time: 5214.7 seconds (1.45 hours)\n\nTimestep: 1360000\nmean reward (100 episodes): 52.4500\nbest mean reward: 53.2400\ncurrent episode reward: 59.0000\nepisodes: 3481\nexploration: 0.09190\nlearning_rate: 0.00010\nelapsed time: 5258.7 seconds (1.46 hours)\n\nTimestep: 1370000\nmean reward (100 episodes): 53.4500\nbest mean reward: 53.5900\ncurrent episode reward: 41.0000\nepisodes: 3489\nexploration: 0.09168\nlearning_rate: 0.00010\nelapsed time: 5303.2 seconds (1.47 hours)\n\nTimestep: 1380000\nmean reward (100 episodes): 53.9800\nbest mean reward: 54.0300\ncurrent episode reward: 57.0000\nepisodes: 3497\nexploration: 0.09145\nlearning_rate: 0.00010\nelapsed time: 5347.5 seconds (1.49 hours)\n\nTimestep: 1390000\nmean reward (100 episodes): 54.7000\nbest mean reward: 54.7000\ncurrent episode reward: 60.0000\nepisodes: 3505\nexploration: 0.09123\nlearning_rate: 0.00010\nelapsed time: 5392.3 seconds (1.50 hours)\n\nTimestep: 1400000\nmean reward (100 episodes): 54.5800\nbest mean reward: 54.7000\ncurrent episode reward: 70.0000\nepisodes: 3513\nexploration: 0.09100\nlearning_rate: 0.00010\nelapsed time: 5436.1 seconds (1.51 hours)\n\nTimestep: 1410000\nmean reward (100 episodes): 54.0600\nbest mean reward: 55.0200\ncurrent episode reward: 76.0000\nepisodes: 3523\nexploration: 0.09078\nlearning_rate: 0.00009\nelapsed time: 5480.8 seconds (1.52 hours)\n\nTimestep: 1420000\nmean reward (100 episodes): 52.0400\nbest mean reward: 55.0200\ncurrent episode reward: 70.0000\nepisodes: 3533\nexploration: 0.09055\nlearning_rate: 0.00009\nelapsed time: 5523.8 seconds (1.53 hours)\n\nTimestep: 1430000\nmean reward (100 episodes): 52.6600\nbest mean reward: 55.0200\ncurrent episode reward: 51.0000\nepisodes: 3540\nexploration: 0.09033\nlearning_rate: 0.00009\nelapsed time: 5567.4 seconds (1.55 hours)\n\nTimestep: 1440000\nmean reward (100 episodes): 53.1600\nbest mean reward: 55.0200\ncurrent episode reward: 51.0000\nepisodes: 3549\nexploration: 0.09010\nlearning_rate: 0.00009\nelapsed time: 5610.5 seconds (1.56 hours)\n\nTimestep: 1450000\nmean reward (100 episodes): 53.9900\nbest mean reward: 55.0200\ncurrent episode reward: 85.0000\nepisodes: 3557\nexploration: 0.08988\nlearning_rate: 0.00009\nelapsed time: 5653.9 seconds (1.57 hours)\n\nTimestep: 1460000\nmean reward (100 episodes): 54.6500\nbest mean reward: 55.0200\ncurrent episode reward: 86.0000\nepisodes: 3565\nexploration: 0.08965\nlearning_rate: 0.00009\nelapsed time: 5697.6 seconds (1.58 hours)\n\nTimestep: 1470000\nmean reward (100 episodes): 57.1400\nbest mean reward: 57.1400\ncurrent episode reward: 83.0000\nepisodes: 3572\nexploration: 0.08943\nlearning_rate: 0.00009\nelapsed time: 5741.2 seconds (1.59 hours)\n\nTimestep: 1480000\nmean reward (100 episodes): 58.3600\nbest mean reward: 58.6500\ncurrent episode reward: 37.0000\nepisodes: 3580\nexploration: 0.08920\nlearning_rate: 0.00009\nelapsed time: 5784.9 seconds (1.61 hours)\n\nTimestep: 1490000\nmean reward (100 episodes): 59.0100\nbest mean reward: 59.0100\ncurrent episode reward: 74.0000\nepisodes: 3587\nexploration: 0.08897\nlearning_rate: 0.00009\nelapsed time: 5828.8 seconds (1.62 hours)\n\nTimestep: 1500000\nmean reward (100 episodes): 60.0200\nbest mean reward: 60.0900\ncurrent episode reward: 63.0000\nepisodes: 3594\nexploration: 0.08875\nlearning_rate: 0.00009\nelapsed time: 5871.2 seconds (1.63 hours)\n\nTimestep: 1510000\nmean reward (100 episodes): 62.6900\nbest mean reward: 62.6900\ncurrent episode reward: 76.0000\nepisodes: 3601\nexploration: 0.08853\nlearning_rate: 0.00009\nelapsed time: 5915.5 seconds (1.64 hours)\n\nTimestep: 1520000\nmean reward (100 episodes): 53.7900\nbest mean reward: 62.6900\ncurrent episode reward: 8.0000\nepisodes: 3623\nexploration: 0.08830\nlearning_rate: 0.00009\nelapsed time: 5959.2 seconds (1.66 hours)\n\nTimestep: 1530000\nmean reward (100 episodes): 48.2900\nbest mean reward: 62.6900\ncurrent episode reward: 65.0000\nepisodes: 3640\nexploration: 0.08808\nlearning_rate: 0.00009\nelapsed time: 6003.7 seconds (1.67 hours)\n\nTimestep: 1540000\nmean reward (100 episodes): 48.2400\nbest mean reward: 62.6900\ncurrent episode reward: 63.0000\nepisodes: 3647\nexploration: 0.08785\nlearning_rate: 0.00009\nelapsed time: 6047.4 seconds (1.68 hours)\n\nTimestep: 1550000\nmean reward (100 episodes): 49.2100\nbest mean reward: 62.6900\ncurrent episode reward: 66.0000\nepisodes: 3655\nexploration: 0.08763\nlearning_rate: 0.00009\nelapsed time: 6092.1 seconds (1.69 hours)\n\nTimestep: 1560000\nmean reward (100 episodes): 48.5300\nbest mean reward: 62.6900\ncurrent episode reward: 4.0000\nepisodes: 3664\nexploration: 0.08740\nlearning_rate: 0.00009\nelapsed time: 6135.5 seconds (1.70 hours)\n\nTimestep: 1570000\nmean reward (100 episodes): 47.8000\nbest mean reward: 62.6900\ncurrent episode reward: 86.0000\nepisodes: 3672\nexploration: 0.08718\nlearning_rate: 0.00009\nelapsed time: 6179.5 seconds (1.72 hours)\n\nTimestep: 1580000\nmean reward (100 episodes): 47.7100\nbest mean reward: 62.6900\ncurrent episode reward: 92.0000\nepisodes: 3680\nexploration: 0.08695\nlearning_rate: 0.00009\nelapsed time: 6223.6 seconds (1.73 hours)\n\nTimestep: 1590000\nmean reward (100 episodes): 37.2400\nbest mean reward: 62.6900\ncurrent episode reward: 67.0000\nepisodes: 3699\nexploration: 0.08673\nlearning_rate: 0.00009\nelapsed time: 6267.5 seconds (1.74 hours)\n\nTimestep: 1600000\nmean reward (100 episodes): 39.0500\nbest mean reward: 62.6900\ncurrent episode reward: 50.0000\nepisodes: 3707\nexploration: 0.08650\nlearning_rate: 0.00009\nelapsed time: 6311.2 seconds (1.75 hours)\n\nTimestep: 1610000\nmean reward (100 episodes): 43.0800\nbest mean reward: 62.6900\ncurrent episode reward: 67.0000\nepisodes: 3715\nexploration: 0.08628\nlearning_rate: 0.00009\nelapsed time: 6354.7 seconds (1.77 hours)\n\nTimestep: 1620000\nmean reward (100 episodes): 47.3700\nbest mean reward: 62.6900\ncurrent episode reward: 48.0000\nepisodes: 3725\nexploration: 0.08605\nlearning_rate: 0.00009\nelapsed time: 6399.5 seconds (1.78 hours)\n\nTimestep: 1630000\nmean reward (100 episodes): 50.8100\nbest mean reward: 62.6900\ncurrent episode reward: 5.0000\nepisodes: 3740\nexploration: 0.08582\nlearning_rate: 0.00009\nelapsed time: 6443.5 seconds (1.79 hours)\n\nTimestep: 1640000\nmean reward (100 episodes): 45.9900\nbest mean reward: 62.6900\ncurrent episode reward: 44.0000\nepisodes: 3753\nexploration: 0.08560\nlearning_rate: 0.00009\nelapsed time: 6487.6 seconds (1.80 hours)\n\nTimestep: 1650000\nmean reward (100 episodes): 48.6700\nbest mean reward: 62.6900\ncurrent episode reward: 214.0000\nepisodes: 3760\nexploration: 0.08538\nlearning_rate: 0.00009\nelapsed time: 6531.4 seconds (1.81 hours)\n\nTimestep: 1660000\nmean reward (100 episodes): 47.0200\nbest mean reward: 62.6900\ncurrent episode reward: 80.0000\nepisodes: 3771\nexploration: 0.08515\nlearning_rate: 0.00009\nelapsed time: 6575.2 seconds (1.83 hours)\n\nTimestep: 1670000\nmean reward (100 episodes): 45.2800\nbest mean reward: 62.6900\ncurrent episode reward: 13.0000\nepisodes: 3783\nexploration: 0.08493\nlearning_rate: 0.00009\nelapsed time: 6620.0 seconds (1.84 hours)\n\nTimestep: 1680000\nmean reward (100 episodes): 50.6100\nbest mean reward: 62.6900\ncurrent episode reward: 35.0000\nepisodes: 3791\nexploration: 0.08470\nlearning_rate: 0.00009\nelapsed time: 6663.9 seconds (1.85 hours)\n\nTimestep: 1690000\nmean reward (100 episodes): 51.5800\nbest mean reward: 62.6900\ncurrent episode reward: 69.0000\nepisodes: 3800\nexploration: 0.08448\nlearning_rate: 0.00009\nelapsed time: 6707.5 seconds (1.86 hours)\n\nTimestep: 1700000\nmean reward (100 episodes): 48.1300\nbest mean reward: 62.6900\ncurrent episode reward: 82.0000\nepisodes: 3812\nexploration: 0.08425\nlearning_rate: 0.00009\nelapsed time: 6751.8 seconds (1.88 hours)\n\nTimestep: 1710000\nmean reward (100 episodes): 50.1500\nbest mean reward: 62.6900\ncurrent episode reward: 85.0000\nepisodes: 3820\nexploration: 0.08403\nlearning_rate: 0.00009\nelapsed time: 6795.7 seconds (1.89 hours)\n\nTimestep: 1720000\nmean reward (100 episodes): 47.5400\nbest mean reward: 62.6900\ncurrent episode reward: 2.0000\nepisodes: 3830\nexploration: 0.08380\nlearning_rate: 0.00009\nelapsed time: 6840.0 seconds (1.90 hours)\n\nTimestep: 1730000\nmean reward (100 episodes): 50.1500\nbest mean reward: 62.6900\ncurrent episode reward: 16.0000\nepisodes: 3842\nexploration: 0.08358\nlearning_rate: 0.00009\nelapsed time: 6884.2 seconds (1.91 hours)\n\nTimestep: 1740000\nmean reward (100 episodes): 47.9600\nbest mean reward: 62.6900\ncurrent episode reward: 57.0000\nepisodes: 3857\nexploration: 0.08335\nlearning_rate: 0.00009\nelapsed time: 6928.5 seconds (1.92 hours)\n\nTimestep: 1750000\nmean reward (100 episodes): 47.2700\nbest mean reward: 62.6900\ncurrent episode reward: 60.0000\nepisodes: 3866\nexploration: 0.08313\nlearning_rate: 0.00009\nelapsed time: 6972.9 seconds (1.94 hours)\n\nTimestep: 1760000\nmean reward (100 episodes): 47.7000\nbest mean reward: 62.6900\ncurrent episode reward: 51.0000\nepisodes: 3874\nexploration: 0.08290\nlearning_rate: 0.00009\nelapsed time: 7017.1 seconds (1.95 hours)\n\nTimestep: 1770000\nmean reward (100 episodes): 50.1800\nbest mean reward: 62.6900\ncurrent episode reward: 74.0000\nepisodes: 3881\nexploration: 0.08267\nlearning_rate: 0.00009\nelapsed time: 7061.0 seconds (1.96 hours)\n\nTimestep: 1780000\nmean reward (100 episodes): 50.3500\nbest mean reward: 62.6900\ncurrent episode reward: 83.0000\nepisodes: 3890\nexploration: 0.08245\nlearning_rate: 0.00009\nelapsed time: 7105.7 seconds (1.97 hours)\n\nTimestep: 1790000\nmean reward (100 episodes): 51.6500\nbest mean reward: 62.6900\ncurrent episode reward: 55.0000\nepisodes: 3897\nexploration: 0.08223\nlearning_rate: 0.00009\nelapsed time: 7149.7 seconds (1.99 hours)\n\nTimestep: 1800000\nmean reward (100 episodes): 52.7000\nbest mean reward: 62.6900\ncurrent episode reward: 62.0000\nepisodes: 3907\nexploration: 0.08200\nlearning_rate: 0.00009\nelapsed time: 7193.4 seconds (2.00 hours)\n\nTimestep: 1810000\nmean reward (100 episodes): 54.0400\nbest mean reward: 62.6900\ncurrent episode reward: 77.0000\nepisodes: 3915\nexploration: 0.08178\nlearning_rate: 0.00009\nelapsed time: 7238.0 seconds (2.01 hours)\n\nTimestep: 1820000\nmean reward (100 episodes): 53.2300\nbest mean reward: 62.6900\ncurrent episode reward: 67.0000\nepisodes: 3927\nexploration: 0.08155\nlearning_rate: 0.00009\nelapsed time: 7281.9 seconds (2.02 hours)\n\nTimestep: 1830000\nmean reward (100 episodes): 57.4200\nbest mean reward: 62.6900\ncurrent episode reward: 25.0000\nepisodes: 3935\nexploration: 0.08133\nlearning_rate: 0.00009\nelapsed time: 7325.7 seconds (2.03 hours)\n\nTimestep: 1840000\nmean reward (100 episodes): 58.0700\nbest mean reward: 62.6900\ncurrent episode reward: 93.0000\nepisodes: 3945\nexploration: 0.08110\nlearning_rate: 0.00009\nelapsed time: 7369.5 seconds (2.05 hours)\n\nTimestep: 1850000\nmean reward (100 episodes): 63.0600\nbest mean reward: 63.0600\ncurrent episode reward: 94.0000\nepisodes: 3951\nexploration: 0.08088\nlearning_rate: 0.00009\nelapsed time: 7414.0 seconds (2.06 hours)\n\nTimestep: 1860000\nmean reward (100 episodes): 64.1700\nbest mean reward: 64.3800\ncurrent episode reward: 82.0000\nepisodes: 3959\nexploration: 0.08065\nlearning_rate: 0.00009\nelapsed time: 7458.1 seconds (2.07 hours)\n\nTimestep: 1870000\nmean reward (100 episodes): 64.1700\nbest mean reward: 65.3400\ncurrent episode reward: 71.0000\nepisodes: 3969\nexploration: 0.08042\nlearning_rate: 0.00009\nelapsed time: 7501.8 seconds (2.08 hours)\n\nTimestep: 1880000\nmean reward (100 episodes): 63.8400\nbest mean reward: 65.3400\ncurrent episode reward: 53.0000\nepisodes: 3977\nexploration: 0.08020\nlearning_rate: 0.00009\nelapsed time: 7545.2 seconds (2.10 hours)\n\nTimestep: 1890000\nmean reward (100 episodes): 62.9500\nbest mean reward: 65.3400\ncurrent episode reward: 42.0000\nepisodes: 3986\nexploration: 0.07998\nlearning_rate: 0.00009\nelapsed time: 7588.9 seconds (2.11 hours)\n\nTimestep: 1900000\nmean reward (100 episodes): 65.0900\nbest mean reward: 65.4400\ncurrent episode reward: 27.0000\nepisodes: 3995\nexploration: 0.07975\nlearning_rate: 0.00009\nelapsed time: 7632.8 seconds (2.12 hours)\n\nTimestep: 1910000\nmean reward (100 episodes): 65.4600\nbest mean reward: 66.2700\ncurrent episode reward: 52.0000\nepisodes: 4003\nexploration: 0.07952\nlearning_rate: 0.00009\nelapsed time: 7678.4 seconds (2.13 hours)\n\nTimestep: 1920000\nmean reward (100 episodes): 66.4500\nbest mean reward: 66.4500\ncurrent episode reward: 77.0000\nepisodes: 4010\nexploration: 0.07930\nlearning_rate: 0.00009\nelapsed time: 7723.0 seconds (2.15 hours)\n\nTimestep: 1930000\nmean reward (100 episodes): 68.1600\nbest mean reward: 68.5300\ncurrent episode reward: 23.0000\nepisodes: 4018\nexploration: 0.07908\nlearning_rate: 0.00009\nelapsed time: 7766.9 seconds (2.16 hours)\n\nTimestep: 1940000\nmean reward (100 episodes): 67.4400\nbest mean reward: 69.2700\ncurrent episode reward: 64.0000\nepisodes: 4027\nexploration: 0.07885\nlearning_rate: 0.00009\nelapsed time: 7810.7 seconds (2.17 hours)\n\nTimestep: 1950000\nmean reward (100 episodes): 67.7700\nbest mean reward: 69.2700\ncurrent episode reward: 100.0000\nepisodes: 4035\nexploration: 0.07863\nlearning_rate: 0.00009\nelapsed time: 7853.9 seconds (2.18 hours)\n\nTimestep: 1960000\nmean reward (100 episodes): 66.9000\nbest mean reward: 69.5200\ncurrent episode reward: 31.0000\nepisodes: 4046\nexploration: 0.07840\nlearning_rate: 0.00009\nelapsed time: 7898.7 seconds (2.19 hours)\n\nTimestep: 1970000\nmean reward (100 episodes): 66.5700\nbest mean reward: 69.5200\ncurrent episode reward: 42.0000\nepisodes: 4053\nexploration: 0.07818\nlearning_rate: 0.00009\nelapsed time: 7942.6 seconds (2.21 hours)\n\nTimestep: 1980000\nmean reward (100 episodes): 66.3400\nbest mean reward: 69.5200\ncurrent episode reward: 71.0000\nepisodes: 4061\nexploration: 0.07795\nlearning_rate: 0.00009\nelapsed time: 7987.0 seconds (2.22 hours)\n\nTimestep: 1990000\nmean reward (100 episodes): 61.3400\nbest mean reward: 69.5200\ncurrent episode reward: 226.0000\nepisodes: 4078\nexploration: 0.07773\nlearning_rate: 0.00009\nelapsed time: 8031.9 seconds (2.23 hours)\n\nTimestep: 2000000\nmean reward (100 episodes): 64.0100\nbest mean reward: 69.5200\ncurrent episode reward: 53.0000\nepisodes: 4086\nexploration: 0.07750\nlearning_rate: 0.00009\nelapsed time: 8076.1 seconds (2.24 hours)\n\nTimestep: 2010000\nmean reward (100 episodes): 60.4200\nbest mean reward: 69.5200\ncurrent episode reward: 45.0000\nepisodes: 4095\nexploration: 0.07728\nlearning_rate: 0.00009\nelapsed time: 8120.8 seconds (2.26 hours)\n\nTimestep: 2020000\nmean reward (100 episodes): 60.0400\nbest mean reward: 69.5200\ncurrent episode reward: 63.0000\nepisodes: 4103\nexploration: 0.07705\nlearning_rate: 0.00009\nelapsed time: 8164.7 seconds (2.27 hours)\n\nTimestep: 2030000\nmean reward (100 episodes): 62.3500\nbest mean reward: 69.5200\ncurrent episode reward: 123.0000\nepisodes: 4111\nexploration: 0.07683\nlearning_rate: 0.00009\nelapsed time: 8208.6 seconds (2.28 hours)\n\nTimestep: 2040000\nmean reward (100 episodes): 62.9500\nbest mean reward: 69.5200\ncurrent episode reward: 67.0000\nepisodes: 4118\nexploration: 0.07660\nlearning_rate: 0.00009\nelapsed time: 8253.4 seconds (2.29 hours)\n\nTimestep: 2050000\nmean reward (100 episodes): 65.4100\nbest mean reward: 69.5200\ncurrent episode reward: 78.0000\nepisodes: 4125\nexploration: 0.07637\nlearning_rate: 0.00009\nelapsed time: 8297.3 seconds (2.30 hours)\n\nTimestep: 2060000\nmean reward (100 episodes): 65.5800\nbest mean reward: 69.5200\ncurrent episode reward: 63.0000\nepisodes: 4134\nexploration: 0.07615\nlearning_rate: 0.00009\nelapsed time: 8341.3 seconds (2.32 hours)\n\nTimestep: 2070000\nmean reward (100 episodes): 67.3000\nbest mean reward: 69.5200\ncurrent episode reward: 62.0000\nepisodes: 4142\nexploration: 0.07593\nlearning_rate: 0.00009\nelapsed time: 8385.5 seconds (2.33 hours)\n\nTimestep: 2080000\nmean reward (100 episodes): 72.3400\nbest mean reward: 72.8500\ncurrent episode reward: 99.0000\nepisodes: 4149\nexploration: 0.07570\nlearning_rate: 0.00009\nelapsed time: 8429.5 seconds (2.34 hours)\n\nTimestep: 2090000\nmean reward (100 episodes): 74.6800\nbest mean reward: 74.6900\ncurrent episode reward: 59.0000\nepisodes: 4156\nexploration: 0.07548\nlearning_rate: 0.00009\nelapsed time: 8473.5 seconds (2.35 hours)\n\nTimestep: 2100000\nmean reward (100 episodes): 76.6200\nbest mean reward: 76.6200\ncurrent episode reward: 88.0000\nepisodes: 4163\nexploration: 0.07525\nlearning_rate: 0.00009\nelapsed time: 8517.6 seconds (2.37 hours)\n\nTimestep: 2110000\nmean reward (100 episodes): 83.8600\nbest mean reward: 83.8600\ncurrent episode reward: 74.0000\nepisodes: 4170\nexploration: 0.07503\nlearning_rate: 0.00009\nelapsed time: 8560.8 seconds (2.38 hours)\n\nTimestep: 2120000\nmean reward (100 episodes): 85.1000\nbest mean reward: 87.1600\ncurrent episode reward: 120.0000\nepisodes: 4178\nexploration: 0.07480\nlearning_rate: 0.00009\nelapsed time: 8604.4 seconds (2.39 hours)\n\nTimestep: 2130000\nmean reward (100 episodes): 84.5700\nbest mean reward: 87.1600\ncurrent episode reward: 99.0000\nepisodes: 4185\nexploration: 0.07458\nlearning_rate: 0.00009\nelapsed time: 8648.6 seconds (2.40 hours)\n\nTimestep: 2140000\nmean reward (100 episodes): 86.9900\nbest mean reward: 87.1600\ncurrent episode reward: 113.0000\nepisodes: 4193\nexploration: 0.07435\nlearning_rate: 0.00009\nelapsed time: 8691.9 seconds (2.41 hours)\n\nTimestep: 2150000\nmean reward (100 episodes): 89.0400\nbest mean reward: 89.2600\ncurrent episode reward: 32.0000\nepisodes: 4200\nexploration: 0.07412\nlearning_rate: 0.00009\nelapsed time: 8736.0 seconds (2.43 hours)\n\nTimestep: 2160000\nmean reward (100 episodes): 88.5400\nbest mean reward: 90.0300\ncurrent episode reward: 56.0000\nepisodes: 4208\nexploration: 0.07390\nlearning_rate: 0.00009\nelapsed time: 8780.2 seconds (2.44 hours)\n\nTimestep: 2170000\nmean reward (100 episodes): 85.6700\nbest mean reward: 90.0300\ncurrent episode reward: 68.0000\nepisodes: 4216\nexploration: 0.07368\nlearning_rate: 0.00009\nelapsed time: 8824.1 seconds (2.45 hours)\n\nTimestep: 2180000\nmean reward (100 episodes): 86.5100\nbest mean reward: 90.0300\ncurrent episode reward: 115.0000\nepisodes: 4223\nexploration: 0.07345\nlearning_rate: 0.00009\nelapsed time: 8868.2 seconds (2.46 hours)\n\nTimestep: 2190000\nmean reward (100 episodes): 90.1700\nbest mean reward: 90.1700\ncurrent episode reward: 102.0000\nepisodes: 4230\nexploration: 0.07322\nlearning_rate: 0.00009\nelapsed time: 8911.7 seconds (2.48 hours)\n\nTimestep: 2200000\nmean reward (100 episodes): 85.3200\nbest mean reward: 90.1700\ncurrent episode reward: 40.0000\nepisodes: 4240\nexploration: 0.07300\nlearning_rate: 0.00009\nelapsed time: 8956.9 seconds (2.49 hours)\n\nTimestep: 2210000\nmean reward (100 episodes): 77.5200\nbest mean reward: 90.1700\ncurrent episode reward: 61.0000\nepisodes: 4252\nexploration: 0.07278\nlearning_rate: 0.00008\nelapsed time: 9000.4 seconds (2.50 hours)\n\nTimestep: 2220000\nmean reward (100 episodes): 76.0000\nbest mean reward: 90.1700\ncurrent episode reward: 50.0000\nepisodes: 4260\nexploration: 0.07255\nlearning_rate: 0.00008\nelapsed time: 9044.0 seconds (2.51 hours)\n\nTimestep: 2230000\nmean reward (100 episodes): 78.6900\nbest mean reward: 90.1700\ncurrent episode reward: 102.0000\nepisodes: 4267\nexploration: 0.07233\nlearning_rate: 0.00008\nelapsed time: 9088.5 seconds (2.52 hours)\n\nTimestep: 2240000\nmean reward (100 episodes): 78.7500\nbest mean reward: 90.1700\ncurrent episode reward: 109.0000\nepisodes: 4274\nexploration: 0.07210\nlearning_rate: 0.00008\nelapsed time: 9132.7 seconds (2.54 hours)\n\nTimestep: 2250000\nmean reward (100 episodes): 80.1000\nbest mean reward: 90.1700\ncurrent episode reward: 122.0000\nepisodes: 4281\nexploration: 0.07187\nlearning_rate: 0.00008\nelapsed time: 9176.7 seconds (2.55 hours)\n\nTimestep: 2260000\nmean reward (100 episodes): 82.6400\nbest mean reward: 90.1700\ncurrent episode reward: 69.0000\nepisodes: 4288\nexploration: 0.07165\nlearning_rate: 0.00008\nelapsed time: 9219.8 seconds (2.56 hours)\n\nTimestep: 2270000\nmean reward (100 episodes): 82.2100\nbest mean reward: 90.1700\ncurrent episode reward: 134.0000\nepisodes: 4296\nexploration: 0.07143\nlearning_rate: 0.00008\nelapsed time: 9263.6 seconds (2.57 hours)\n\nTimestep: 2280000\nmean reward (100 episodes): 83.6400\nbest mean reward: 90.1700\ncurrent episode reward: 45.0000\nepisodes: 4303\nexploration: 0.07120\nlearning_rate: 0.00008\nelapsed time: 9307.8 seconds (2.59 hours)\n\nTimestep: 2290000\nmean reward (100 episodes): 87.3600\nbest mean reward: 90.1700\ncurrent episode reward: 239.0000\nepisodes: 4310\nexploration: 0.07097\nlearning_rate: 0.00008\nelapsed time: 9350.9 seconds (2.60 hours)\n\nTimestep: 2300000\nmean reward (100 episodes): 88.5000\nbest mean reward: 90.1700\ncurrent episode reward: 73.0000\nepisodes: 4318\nexploration: 0.07075\nlearning_rate: 0.00008\nelapsed time: 9395.0 seconds (2.61 hours)\n\nTimestep: 2310000\nmean reward (100 episodes): 87.2500\nbest mean reward: 90.1700\ncurrent episode reward: 155.0000\nepisodes: 4325\nexploration: 0.07053\nlearning_rate: 0.00008\nelapsed time: 9438.3 seconds (2.62 hours)\n\nTimestep: 2320000\nmean reward (100 episodes): 86.5000\nbest mean reward: 90.1700\ncurrent episode reward: 76.0000\nepisodes: 4333\nexploration: 0.07030\nlearning_rate: 0.00008\nelapsed time: 9483.0 seconds (2.63 hours)\n\nTimestep: 2330000\nmean reward (100 episodes): 91.4700\nbest mean reward: 91.4700\ncurrent episode reward: 174.0000\nepisodes: 4340\nexploration: 0.07007\nlearning_rate: 0.00008\nelapsed time: 9526.6 seconds (2.65 hours)\n\nTimestep: 2340000\nmean reward (100 episodes): 94.8900\nbest mean reward: 94.8900\ncurrent episode reward: 77.0000\nepisodes: 4348\nexploration: 0.06985\nlearning_rate: 0.00008\nelapsed time: 9570.5 seconds (2.66 hours)\n\nTimestep: 2350000\nmean reward (100 episodes): 96.1800\nbest mean reward: 97.4300\ncurrent episode reward: 131.0000\nepisodes: 4356\nexploration: 0.06962\nlearning_rate: 0.00008\nelapsed time: 9614.1 seconds (2.67 hours)\n\nTimestep: 2360000\nmean reward (100 episodes): 98.1300\nbest mean reward: 99.7200\ncurrent episode reward: 11.0000\nepisodes: 4363\nexploration: 0.06940\nlearning_rate: 0.00008\nelapsed time: 9657.8 seconds (2.68 hours)\n\nTimestep: 2370000\nmean reward (100 episodes): 97.8200\nbest mean reward: 99.7200\ncurrent episode reward: 132.0000\nepisodes: 4370\nexploration: 0.06918\nlearning_rate: 0.00008\nelapsed time: 9702.4 seconds (2.70 hours)\n\nTimestep: 2380000\nmean reward (100 episodes): 99.8600\nbest mean reward: 99.8600\ncurrent episode reward: 106.0000\nepisodes: 4376\nexploration: 0.06895\nlearning_rate: 0.00008\nelapsed time: 9746.5 seconds (2.71 hours)\n\nTimestep: 2390000\nmean reward (100 episodes): 101.2000\nbest mean reward: 102.7600\ncurrent episode reward: 131.0000\nepisodes: 4382\nexploration: 0.06873\nlearning_rate: 0.00008\nelapsed time: 9790.3 seconds (2.72 hours)\n\nTimestep: 2400000\nmean reward (100 episodes): 103.5900\nbest mean reward: 104.3900\ncurrent episode reward: 97.0000\nepisodes: 4389\nexploration: 0.06850\nlearning_rate: 0.00008\nelapsed time: 9834.3 seconds (2.73 hours)\n\nTimestep: 2410000\nmean reward (100 episodes): 104.8700\nbest mean reward: 105.9100\ncurrent episode reward: 23.0000\nepisodes: 4397\nexploration: 0.06828\nlearning_rate: 0.00008\nelapsed time: 9877.9 seconds (2.74 hours)\n\nTimestep: 2420000\nmean reward (100 episodes): 104.0900\nbest mean reward: 105.9100\ncurrent episode reward: 40.0000\nepisodes: 4404\nexploration: 0.06805\nlearning_rate: 0.00008\nelapsed time: 9921.3 seconds (2.76 hours)\n\nTimestep: 2430000\nmean reward (100 episodes): 101.6400\nbest mean reward: 105.9100\ncurrent episode reward: 58.0000\nepisodes: 4412\nexploration: 0.06782\nlearning_rate: 0.00008\nelapsed time: 9965.4 seconds (2.77 hours)\n\nTimestep: 2440000\nmean reward (100 episodes): 102.3500\nbest mean reward: 105.9100\ncurrent episode reward: 31.0000\nepisodes: 4419\nexploration: 0.06760\nlearning_rate: 0.00008\nelapsed time: 10009.1 seconds (2.78 hours)\n\nTimestep: 2450000\nmean reward (100 episodes): 103.7500\nbest mean reward: 105.9100\ncurrent episode reward: 121.0000\nepisodes: 4426\nexploration: 0.06738\nlearning_rate: 0.00008\nelapsed time: 10053.1 seconds (2.79 hours)\n\nTimestep: 2460000\nmean reward (100 episodes): 104.3100\nbest mean reward: 105.9100\ncurrent episode reward: 186.0000\nepisodes: 4433\nexploration: 0.06715\nlearning_rate: 0.00008\nelapsed time: 10096.8 seconds (2.80 hours)\n\nTimestep: 2470000\nmean reward (100 episodes): 104.2800\nbest mean reward: 105.9100\ncurrent episode reward: 75.0000\nepisodes: 4441\nexploration: 0.06693\nlearning_rate: 0.00008\nelapsed time: 10141.5 seconds (2.82 hours)\n\nTimestep: 2480000\nmean reward (100 episodes): 109.9400\nbest mean reward: 109.9400\ncurrent episode reward: 108.0000\nepisodes: 4448\nexploration: 0.06670\nlearning_rate: 0.00008\nelapsed time: 10185.3 seconds (2.83 hours)\n\nTimestep: 2490000\nmean reward (100 episodes): 110.7200\nbest mean reward: 110.7200\ncurrent episode reward: 146.0000\nepisodes: 4454\nexploration: 0.06648\nlearning_rate: 0.00008\nelapsed time: 10229.3 seconds (2.84 hours)\n\nTimestep: 2500000\nmean reward (100 episodes): 110.0400\nbest mean reward: 111.1300\ncurrent episode reward: 115.0000\nepisodes: 4462\nexploration: 0.06625\nlearning_rate: 0.00008\nelapsed time: 10273.0 seconds (2.85 hours)\n\nTimestep: 2510000\nmean reward (100 episodes): 110.3300\nbest mean reward: 111.5600\ncurrent episode reward: 105.0000\nepisodes: 4469\nexploration: 0.06603\nlearning_rate: 0.00008\nelapsed time: 10316.5 seconds (2.87 hours)\n\nTimestep: 2520000\nmean reward (100 episodes): 109.4700\nbest mean reward: 111.5600\ncurrent episode reward: 139.0000\nepisodes: 4475\nexploration: 0.06580\nlearning_rate: 0.00008\nelapsed time: 10360.9 seconds (2.88 hours)\n\nTimestep: 2530000\nmean reward (100 episodes): 108.9800\nbest mean reward: 111.5800\ncurrent episode reward: 115.0000\nepisodes: 4482\nexploration: 0.06557\nlearning_rate: 0.00008\nelapsed time: 10404.9 seconds (2.89 hours)\n\nTimestep: 2540000\nmean reward (100 episodes): 111.2700\nbest mean reward: 111.5800\ncurrent episode reward: 136.0000\nepisodes: 4488\nexploration: 0.06535\nlearning_rate: 0.00008\nelapsed time: 10448.5 seconds (2.90 hours)\n\nTimestep: 2550000\nmean reward (100 episodes): 112.0800\nbest mean reward: 113.7300\ncurrent episode reward: 101.0000\nepisodes: 4496\nexploration: 0.06513\nlearning_rate: 0.00008\nelapsed time: 10492.0 seconds (2.91 hours)\n\nTimestep: 2560000\nmean reward (100 episodes): 113.1200\nbest mean reward: 114.1700\ncurrent episode reward: 78.0000\nepisodes: 4504\nexploration: 0.06490\nlearning_rate: 0.00008\nelapsed time: 10535.8 seconds (2.93 hours)\n\nTimestep: 2570000\nmean reward (100 episodes): 115.5700\nbest mean reward: 115.5700\ncurrent episode reward: 227.0000\nepisodes: 4511\nexploration: 0.06468\nlearning_rate: 0.00008\nelapsed time: 10579.3 seconds (2.94 hours)\n\nTimestep: 2580000\nmean reward (100 episodes): 117.3200\nbest mean reward: 118.4200\ncurrent episode reward: 89.0000\nepisodes: 4517\nexploration: 0.06445\nlearning_rate: 0.00008\nelapsed time: 10622.9 seconds (2.95 hours)\n\nTimestep: 2590000\nmean reward (100 episodes): 119.5300\nbest mean reward: 120.0500\ncurrent episode reward: 95.0000\nepisodes: 4524\nexploration: 0.06423\nlearning_rate: 0.00008\nelapsed time: 10667.9 seconds (2.96 hours)\n\nTimestep: 2600000\nmean reward (100 episodes): 121.2800\nbest mean reward: 121.2800\ncurrent episode reward: 165.0000\nepisodes: 4532\nexploration: 0.06400\nlearning_rate: 0.00008\nelapsed time: 10711.9 seconds (2.98 hours)\n\nTimestep: 2610000\nmean reward (100 episodes): 117.6700\nbest mean reward: 121.5100\ncurrent episode reward: 73.0000\nepisodes: 4540\nexploration: 0.06377\nlearning_rate: 0.00008\nelapsed time: 10755.5 seconds (2.99 hours)\n\nTimestep: 2620000\nmean reward (100 episodes): 116.8700\nbest mean reward: 121.5100\ncurrent episode reward: 170.0000\nepisodes: 4546\nexploration: 0.06355\nlearning_rate: 0.00008\nelapsed time: 10799.6 seconds (3.00 hours)\n\nTimestep: 2630000\nmean reward (100 episodes): 118.4800\nbest mean reward: 121.5100\ncurrent episode reward: 91.0000\nepisodes: 4554\nexploration: 0.06333\nlearning_rate: 0.00008\nelapsed time: 10843.0 seconds (3.01 hours)\n\nTimestep: 2640000\nmean reward (100 episodes): 123.2500\nbest mean reward: 123.8800\ncurrent episode reward: 170.0000\nepisodes: 4560\nexploration: 0.06310\nlearning_rate: 0.00008\nelapsed time: 10887.1 seconds (3.02 hours)\n\nTimestep: 2650000\nmean reward (100 episodes): 124.2700\nbest mean reward: 125.5400\ncurrent episode reward: 106.0000\nepisodes: 4568\nexploration: 0.06288\nlearning_rate: 0.00008\nelapsed time: 10931.3 seconds (3.04 hours)\n\nTimestep: 2660000\nmean reward (100 episodes): 123.0700\nbest mean reward: 125.5400\ncurrent episode reward: 49.0000\nepisodes: 4575\nexploration: 0.06265\nlearning_rate: 0.00008\nelapsed time: 10975.1 seconds (3.05 hours)\n\nTimestep: 2670000\nmean reward (100 episodes): 123.4100\nbest mean reward: 125.5400\ncurrent episode reward: 180.0000\nepisodes: 4582\nexploration: 0.06243\nlearning_rate: 0.00008\nelapsed time: 11019.6 seconds (3.06 hours)\n\nTimestep: 2680000\nmean reward (100 episodes): 118.2200\nbest mean reward: 125.5400\ncurrent episode reward: 53.0000\nepisodes: 4590\nexploration: 0.06220\nlearning_rate: 0.00008\nelapsed time: 11063.0 seconds (3.07 hours)\n\nTimestep: 2690000\nmean reward (100 episodes): 116.7000\nbest mean reward: 125.5400\ncurrent episode reward: 151.0000\nepisodes: 4597\nexploration: 0.06198\nlearning_rate: 0.00008\nelapsed time: 11107.0 seconds (3.09 hours)\n\nTimestep: 2700000\nmean reward (100 episodes): 120.3800\nbest mean reward: 125.5400\ncurrent episode reward: 135.0000\nepisodes: 4604\nexploration: 0.06175\nlearning_rate: 0.00008\nelapsed time: 11150.9 seconds (3.10 hours)\n\nTimestep: 2710000\nmean reward (100 episodes): 118.2000\nbest mean reward: 125.5400\ncurrent episode reward: 54.0000\nepisodes: 4611\nexploration: 0.06153\nlearning_rate: 0.00008\nelapsed time: 11194.4 seconds (3.11 hours)\n\nTimestep: 2720000\nmean reward (100 episodes): 116.2900\nbest mean reward: 125.5400\ncurrent episode reward: 57.0000\nepisodes: 4619\nexploration: 0.06130\nlearning_rate: 0.00008\nelapsed time: 11237.7 seconds (3.12 hours)\n\nTimestep: 2730000\nmean reward (100 episodes): 117.0300\nbest mean reward: 125.5400\ncurrent episode reward: 276.0000\nepisodes: 4626\nexploration: 0.06108\nlearning_rate: 0.00008\nelapsed time: 11282.2 seconds (3.13 hours)\n\nTimestep: 2740000\nmean reward (100 episodes): 118.7200\nbest mean reward: 125.5400\ncurrent episode reward: 126.0000\nepisodes: 4632\nexploration: 0.06085\nlearning_rate: 0.00008\nelapsed time: 11326.6 seconds (3.15 hours)\n\nTimestep: 2750000\nmean reward (100 episodes): 125.0700\nbest mean reward: 125.5400\ncurrent episode reward: 270.0000\nepisodes: 4639\nexploration: 0.06062\nlearning_rate: 0.00008\nelapsed time: 11370.6 seconds (3.16 hours)\n\nTimestep: 2760000\nmean reward (100 episodes): 128.3400\nbest mean reward: 128.3400\ncurrent episode reward: 185.0000\nepisodes: 4645\nexploration: 0.06040\nlearning_rate: 0.00008\nelapsed time: 11414.6 seconds (3.17 hours)\n\nTimestep: 2770000\nmean reward (100 episodes): 126.5100\nbest mean reward: 128.3400\ncurrent episode reward: 230.0000\nepisodes: 4652\nexploration: 0.06017\nlearning_rate: 0.00008\nelapsed time: 11459.1 seconds (3.18 hours)\n\nTimestep: 2780000\nmean reward (100 episodes): 123.3200\nbest mean reward: 128.3400\ncurrent episode reward: 154.0000\nepisodes: 4659\nexploration: 0.05995\nlearning_rate: 0.00008\nelapsed time: 11502.4 seconds (3.20 hours)\n\nTimestep: 2790000\nmean reward (100 episodes): 120.5900\nbest mean reward: 128.3400\ncurrent episode reward: 87.0000\nepisodes: 4666\nexploration: 0.05973\nlearning_rate: 0.00008\nelapsed time: 11547.4 seconds (3.21 hours)\n\nTimestep: 2800000\nmean reward (100 episodes): 119.2300\nbest mean reward: 128.3400\ncurrent episode reward: 82.0000\nepisodes: 4675\nexploration: 0.05950\nlearning_rate: 0.00008\nelapsed time: 11592.5 seconds (3.22 hours)\n\nTimestep: 2810000\nmean reward (100 episodes): 116.6300\nbest mean reward: 128.3400\ncurrent episode reward: 106.0000\nepisodes: 4683\nexploration: 0.05928\nlearning_rate: 0.00008\nelapsed time: 11636.1 seconds (3.23 hours)\n\nTimestep: 2820000\nmean reward (100 episodes): 116.3000\nbest mean reward: 128.3400\ncurrent episode reward: 276.0000\nepisodes: 4691\nexploration: 0.05905\nlearning_rate: 0.00008\nelapsed time: 11680.2 seconds (3.24 hours)\n\nTimestep: 2830000\nmean reward (100 episodes): 113.0800\nbest mean reward: 128.3400\ncurrent episode reward: 130.0000\nepisodes: 4699\nexploration: 0.05883\nlearning_rate: 0.00008\nelapsed time: 11723.9 seconds (3.26 hours)\n\nTimestep: 2840000\nmean reward (100 episodes): 107.1600\nbest mean reward: 128.3400\ncurrent episode reward: 39.0000\nepisodes: 4708\nexploration: 0.05860\nlearning_rate: 0.00008\nelapsed time: 11767.6 seconds (3.27 hours)\n\nTimestep: 2850000\nmean reward (100 episodes): 100.8600\nbest mean reward: 128.3400\ncurrent episode reward: 32.0000\nepisodes: 4719\nexploration: 0.05837\nlearning_rate: 0.00008\nelapsed time: 11811.9 seconds (3.28 hours)\n\nTimestep: 2860000\nmean reward (100 episodes): 88.0700\nbest mean reward: 128.3400\ncurrent episode reward: 21.0000\nepisodes: 4731\nexploration: 0.05815\nlearning_rate: 0.00008\nelapsed time: 11856.5 seconds (3.29 hours)\n\nTimestep: 2870000\nmean reward (100 episodes): 66.7300\nbest mean reward: 128.3400\ncurrent episode reward: 15.0000\nepisodes: 4746\nexploration: 0.05792\nlearning_rate: 0.00008\nelapsed time: 11901.0 seconds (3.31 hours)\n\nTimestep: 2880000\nmean reward (100 episodes): 45.2200\nbest mean reward: 128.3400\ncurrent episode reward: 4.0000\nepisodes: 4767\nexploration: 0.05770\nlearning_rate: 0.00008\nelapsed time: 11944.9 seconds (3.32 hours)\n\nTimestep: 2890000\nmean reward (100 episodes): 23.2100\nbest mean reward: 128.3400\ncurrent episode reward: 13.0000\nepisodes: 4796\nexploration: 0.05748\nlearning_rate: 0.00008\nelapsed time: 11988.9 seconds (3.33 hours)\n\nTimestep: 2900000\nmean reward (100 episodes): 8.2300\nbest mean reward: 128.3400\ncurrent episode reward: 3.0000\nepisodes: 4834\nexploration: 0.05725\nlearning_rate: 0.00008\nelapsed time: 12032.5 seconds (3.34 hours)\n\nTimestep: 2910000\nmean reward (100 episodes): 3.7400\nbest mean reward: 128.3400\ncurrent episode reward: 1.0000\nepisodes: 4880\nexploration: 0.05702\nlearning_rate: 0.00008\nelapsed time: 12076.6 seconds (3.35 hours)\n\nTimestep: 2920000\nmean reward (100 episodes): 2.2300\nbest mean reward: 128.3400\ncurrent episode reward: 6.0000\nepisodes: 4934\nexploration: 0.05680\nlearning_rate: 0.00008\nelapsed time: 12121.4 seconds (3.37 hours)\n\nTimestep: 2930000\nmean reward (100 episodes): 2.0400\nbest mean reward: 128.3400\ncurrent episode reward: 4.0000\nepisodes: 4983\nexploration: 0.05658\nlearning_rate: 0.00008\nelapsed time: 12166.0 seconds (3.38 hours)\n\nTimestep: 2940000\nmean reward (100 episodes): 2.0300\nbest mean reward: 128.3400\ncurrent episode reward: 1.0000\nepisodes: 5036\nexploration: 0.05635\nlearning_rate: 0.00008\nelapsed time: 12211.0 seconds (3.39 hours)\n\nTimestep: 2950000\nmean reward (100 episodes): 2.4700\nbest mean reward: 128.3400\ncurrent episode reward: 3.0000\nepisodes: 5079\nexploration: 0.05613\nlearning_rate: 0.00008\nelapsed time: 12255.4 seconds (3.40 hours)\n\nTimestep: 2960000\nmean reward (100 episodes): 2.9300\nbest mean reward: 128.3400\ncurrent episode reward: 4.0000\nepisodes: 5122\nexploration: 0.05590\nlearning_rate: 0.00008\nelapsed time: 12299.5 seconds (3.42 hours)\n\nTimestep: 2970000\nmean reward (100 episodes): 3.0100\nbest mean reward: 128.3400\ncurrent episode reward: 6.0000\nepisodes: 5166\nexploration: 0.05568\nlearning_rate: 0.00008\nelapsed time: 12343.6 seconds (3.43 hours)\n\nTimestep: 2980000\nmean reward (100 episodes): 2.8900\nbest mean reward: 128.3400\ncurrent episode reward: 5.0000\nepisodes: 5211\nexploration: 0.05545\nlearning_rate: 0.00008\nelapsed time: 12388.3 seconds (3.44 hours)\n\nTimestep: 2990000\nmean reward (100 episodes): 2.4000\nbest mean reward: 128.3400\ncurrent episode reward: 0.0000\nepisodes: 5264\nexploration: 0.05523\nlearning_rate: 0.00008\nelapsed time: 12432.5 seconds (3.45 hours)\n\nTimestep: 3000000\nmean reward (100 episodes): 2.2300\nbest mean reward: 128.3400\ncurrent episode reward: 3.0000\nepisodes: 5312\nexploration: 0.05500\nlearning_rate: 0.00008\nelapsed time: 12476.8 seconds (3.47 hours)\n\nTimestep: 3010000\nmean reward (100 episodes): 2.3100\nbest mean reward: 128.3400\ncurrent episode reward: 2.0000\nepisodes: 5361\nexploration: 0.05478\nlearning_rate: 0.00007\nelapsed time: 12520.4 seconds (3.48 hours)\n\nTimestep: 3020000\nmean reward (100 episodes): 2.4500\nbest mean reward: 128.3400\ncurrent episode reward: 2.0000\nepisodes: 5407\nexploration: 0.05455\nlearning_rate: 0.00007\nelapsed time: 12564.6 seconds (3.49 hours)\n\nTimestep: 3030000\nmean reward (100 episodes): 2.4200\nbest mean reward: 128.3400\ncurrent episode reward: 2.0000\nepisodes: 5454\nexploration: 0.05433\nlearning_rate: 0.00007\nelapsed time: 12609.0 seconds (3.50 hours)\n\nTimestep: 3040000\nmean reward (100 episodes): 2.6000\nbest mean reward: 128.3400\ncurrent episode reward: 1.0000\nepisodes: 5499\nexploration: 0.05410\nlearning_rate: 0.00007\nelapsed time: 12653.8 seconds (3.51 hours)\n\nTimestep: 3050000\nmean reward (100 episodes): 2.3200\nbest mean reward: 128.3400\ncurrent episode reward: 1.0000\nepisodes: 5550\nexploration: 0.05388\nlearning_rate: 0.00007\nelapsed time: 12698.1 seconds (3.53 hours)\n\nTimestep: 3060000\nmean reward (100 episodes): 2.0000\nbest mean reward: 128.3400\ncurrent episode reward: 3.0000\nepisodes: 5601\nexploration: 0.05365\nlearning_rate: 0.00007\nelapsed time: 12742.3 seconds (3.54 hours)\n\nTimestep: 3070000\nmean reward (100 episodes): 2.4400\nbest mean reward: 128.3400\ncurrent episode reward: 7.0000\nepisodes: 5645\nexploration: 0.05343\nlearning_rate: 0.00007\nelapsed time: 12786.8 seconds (3.55 hours)\n\nTimestep: 3080000\nmean reward (100 episodes): 3.4400\nbest mean reward: 128.3400\ncurrent episode reward: 4.0000\nepisodes: 5678\nexploration: 0.05320\nlearning_rate: 0.00007\nelapsed time: 12831.7 seconds (3.56 hours)\n\nTimestep: 3090000\nmean reward (100 episodes): 3.9200\nbest mean reward: 128.3400\ncurrent episode reward: 5.0000\nepisodes: 5717\nexploration: 0.05298\nlearning_rate: 0.00007\nelapsed time: 12876.3 seconds (3.58 hours)\n\nTimestep: 3100000\nmean reward (100 episodes): 4.6700\nbest mean reward: 128.3400\ncurrent episode reward: 2.0000\nepisodes: 5749\nexploration: 0.05275\nlearning_rate: 0.00007\nelapsed time: 12920.0 seconds (3.59 hours)\n\nTimestep: 3110000\nmean reward (100 episodes): 4.7300\nbest mean reward: 128.3400\ncurrent episode reward: 6.0000\nepisodes: 5782\nexploration: 0.05253\nlearning_rate: 0.00007\nelapsed time: 12963.7 seconds (3.60 hours)\n\nTimestep: 3120000\nmean reward (100 episodes): 4.7300\nbest mean reward: 128.3400\ncurrent episode reward: 2.0000\nepisodes: 5819\nexploration: 0.05230\nlearning_rate: 0.00007\nelapsed time: 13007.8 seconds (3.61 hours)\n\nTimestep: 3130000\nmean reward (100 episodes): 4.3400\nbest mean reward: 128.3400\ncurrent episode reward: 3.0000\nepisodes: 5856\nexploration: 0.05208\nlearning_rate: 0.00007\nelapsed time: 13052.3 seconds (3.63 hours)\n\nTimestep: 3140000\nmean reward (100 episodes): 4.2200\nbest mean reward: 128.3400\ncurrent episode reward: 1.0000\nepisodes: 5895\nexploration: 0.05185\nlearning_rate: 0.00007\nelapsed time: 13096.2 seconds (3.64 hours)\n\nTimestep: 3150000\nmean reward (100 episodes): 4.1300\nbest mean reward: 128.3400\ncurrent episode reward: 1.0000\nepisodes: 5931\nexploration: 0.05163\nlearning_rate: 0.00007\nelapsed time: 13140.4 seconds (3.65 hours)\n\nTimestep: 3160000\nmean reward (100 episodes): 4.2400\nbest mean reward: 128.3400\ncurrent episode reward: 4.0000\nepisodes: 5968\nexploration: 0.05140\nlearning_rate: 0.00007\nelapsed time: 13184.6 seconds (3.66 hours)\n\nTimestep: 3170000\nmean reward (100 episodes): 4.6400\nbest mean reward: 128.3400\ncurrent episode reward: 17.0000\nepisodes: 6002\nexploration: 0.05117\nlearning_rate: 0.00007\nelapsed time: 13229.2 seconds (3.67 hours)\n\nTimestep: 3180000\nmean reward (100 episodes): 4.7800\nbest mean reward: 128.3400\ncurrent episode reward: 3.0000\nepisodes: 6035\nexploration: 0.05095\nlearning_rate: 0.00007\nelapsed time: 13273.2 seconds (3.69 hours)\n\nTimestep: 3190000\nmean reward (100 episodes): 4.7600\nbest mean reward: 128.3400\ncurrent episode reward: 0.0000\nepisodes: 6071\nexploration: 0.05072\nlearning_rate: 0.00007\nelapsed time: 13317.4 seconds (3.70 hours)\n\nTimestep: 3200000\nmean reward (100 episodes): 4.3400\nbest mean reward: 128.3400\ncurrent episode reward: 4.0000\nepisodes: 6108\nexploration: 0.05050\nlearning_rate: 0.00007\nelapsed time: 13361.6 seconds (3.71 hours)\n\nTimestep: 3210000\nmean reward (100 episodes): 4.0000\nbest mean reward: 128.3400\ncurrent episode reward: 7.0000\nepisodes: 6144\nexploration: 0.05028\nlearning_rate: 0.00007\nelapsed time: 13407.1 seconds (3.72 hours)\n\nTimestep: 3220000\nmean reward (100 episodes): 4.6200\nbest mean reward: 128.3400\ncurrent episode reward: 6.0000\nepisodes: 6175\nexploration: 0.05005\nlearning_rate: 0.00007\nelapsed time: 13451.1 seconds (3.74 hours)\n\nTimestep: 3230000\nmean reward (100 episodes): 5.1100\nbest mean reward: 128.3400\ncurrent episode reward: 8.0000\nepisodes: 6206\nexploration: 0.04983\nlearning_rate: 0.00007\nelapsed time: 13495.0 seconds (3.75 hours)\n\nTimestep: 3240000\nmean reward (100 episodes): 5.4900\nbest mean reward: 128.3400\ncurrent episode reward: 5.0000\nepisodes: 6236\nexploration: 0.04960\nlearning_rate: 0.00007\nelapsed time: 13538.7 seconds (3.76 hours)\n\nTimestep: 3250000\nmean reward (100 episodes): 6.0200\nbest mean reward: 128.3400\ncurrent episode reward: 7.0000\nepisodes: 6264\nexploration: 0.04938\nlearning_rate: 0.00007\nelapsed time: 13582.8 seconds (3.77 hours)\n\nTimestep: 3260000\nmean reward (100 episodes): 5.6000\nbest mean reward: 128.3400\ncurrent episode reward: 8.0000\nepisodes: 6298\nexploration: 0.04915\nlearning_rate: 0.00007\nelapsed time: 13627.2 seconds (3.79 hours)\n\nTimestep: 3270000\nmean reward (100 episodes): 5.5800\nbest mean reward: 128.3400\ncurrent episode reward: 1.0000\nepisodes: 6328\nexploration: 0.04892\nlearning_rate: 0.00007\nelapsed time: 13671.8 seconds (3.80 hours)\n\nTimestep: 3280000\nmean reward (100 episodes): 5.5100\nbest mean reward: 128.3400\ncurrent episode reward: 5.0000\nepisodes: 6356\nexploration: 0.04870\nlearning_rate: 0.00007\nelapsed time: 13716.0 seconds (3.81 hours)\n\nTimestep: 3290000\nmean reward (100 episodes): 5.8700\nbest mean reward: 128.3400\ncurrent episode reward: 5.0000\nepisodes: 6387\nexploration: 0.04847\nlearning_rate: 0.00007\nelapsed time: 13759.9 seconds (3.82 hours)\n\nTimestep: 3300000\nmean reward (100 episodes): 5.7400\nbest mean reward: 128.3400\ncurrent episode reward: 5.0000\nepisodes: 6419\nexploration: 0.04825\nlearning_rate: 0.00007\nelapsed time: 13803.9 seconds (3.83 hours)\n\nTimestep: 3310000\nmean reward (100 episodes): 5.3400\nbest mean reward: 128.3400\ncurrent episode reward: 2.0000\nepisodes: 6452\nexploration: 0.04802\nlearning_rate: 0.00007\nelapsed time: 13847.8 seconds (3.85 hours)\n\nTimestep: 3320000\nmean reward (100 episodes): 5.6800\nbest mean reward: 128.3400\ncurrent episode reward: 6.0000\nepisodes: 6478\nexploration: 0.04780\nlearning_rate: 0.00007\nelapsed time: 13891.8 seconds (3.86 hours)\n\nTimestep: 3330000\nmean reward (100 episodes): 6.2600\nbest mean reward: 128.3400\ncurrent episode reward: 2.0000\nepisodes: 6505\nexploration: 0.04757\nlearning_rate: 0.00007\nelapsed time: 13935.7 seconds (3.87 hours)\n\nTimestep: 3340000\nmean reward (100 episodes): 6.9100\nbest mean reward: 128.3400\ncurrent episode reward: 6.0000\nepisodes: 6530\nexploration: 0.04735\nlearning_rate: 0.00007\nelapsed time: 13979.8 seconds (3.88 hours)\n\nTimestep: 3350000\nmean reward (100 episodes): 7.4800\nbest mean reward: 128.3400\ncurrent episode reward: 11.0000\nepisodes: 6556\nexploration: 0.04713\nlearning_rate: 0.00007\nelapsed time: 14024.1 seconds (3.90 hours)\n\nTimestep: 3360000\nmean reward (100 episodes): 7.7900\nbest mean reward: 128.3400\ncurrent episode reward: 12.0000\nepisodes: 6580\nexploration: 0.04690\nlearning_rate: 0.00007\nelapsed time: 14068.3 seconds (3.91 hours)\n\nTimestep: 3370000\nmean reward (100 episodes): 8.3600\nbest mean reward: 128.3400\ncurrent episode reward: 7.0000\nepisodes: 6601\nexploration: 0.04667\nlearning_rate: 0.00007\nelapsed time: 14110.7 seconds (3.92 hours)\n\nTimestep: 3380000\nmean reward (100 episodes): 8.6900\nbest mean reward: 128.3400\ncurrent episode reward: 5.0000\nepisodes: 6623\nexploration: 0.04645\nlearning_rate: 0.00007\nelapsed time: 14154.5 seconds (3.93 hours)\n\nTimestep: 3390000\nmean reward (100 episodes): 9.6500\nbest mean reward: 128.3400\ncurrent episode reward: 5.0000\nepisodes: 6641\nexploration: 0.04622\nlearning_rate: 0.00007\nelapsed time: 14197.8 seconds (3.94 hours)\n\nTimestep: 3400000\nmean reward (100 episodes): 10.5000\nbest mean reward: 128.3400\ncurrent episode reward: 8.0000\nepisodes: 6660\nexploration: 0.04600\nlearning_rate: 0.00007\nelapsed time: 14241.7 seconds (3.96 hours)\n\nTimestep: 3410000\nmean reward (100 episodes): 10.3900\nbest mean reward: 128.3400\ncurrent episode reward: 8.0000\nepisodes: 6684\nexploration: 0.04577\nlearning_rate: 0.00007\nelapsed time: 14285.8 seconds (3.97 hours)\n\nTimestep: 3420000\nmean reward (100 episodes): 10.4900\nbest mean reward: 128.3400\ncurrent episode reward: 13.0000\nepisodes: 6704\nexploration: 0.04555\nlearning_rate: 0.00007\nelapsed time: 14330.2 seconds (3.98 hours)\n\nTimestep: 3430000\nmean reward (100 episodes): 10.9900\nbest mean reward: 128.3400\ncurrent episode reward: 18.0000\nepisodes: 6723\nexploration: 0.04532\nlearning_rate: 0.00007\nelapsed time: 14374.4 seconds (3.99 hours)\n\nTimestep: 3440000\nmean reward (100 episodes): 11.2900\nbest mean reward: 128.3400\ncurrent episode reward: 15.0000\nepisodes: 6741\nexploration: 0.04510\nlearning_rate: 0.00007\nelapsed time: 14418.3 seconds (4.01 hours)\n\nTimestep: 3450000\nmean reward (100 episodes): 10.8800\nbest mean reward: 128.3400\ncurrent episode reward: 9.0000\nepisodes: 6762\nexploration: 0.04487\nlearning_rate: 0.00007\nelapsed time: 14462.5 seconds (4.02 hours)\n\nTimestep: 3460000\nmean reward (100 episodes): 11.6100\nbest mean reward: 128.3400\ncurrent episode reward: 9.0000\nepisodes: 6780\nexploration: 0.04465\nlearning_rate: 0.00007\nelapsed time: 14506.7 seconds (4.03 hours)\n\nTimestep: 3470000\nmean reward (100 episodes): 12.4500\nbest mean reward: 128.3400\ncurrent episode reward: 13.0000\nepisodes: 6797\nexploration: 0.04442\nlearning_rate: 0.00007\nelapsed time: 14551.6 seconds (4.04 hours)\n\nTimestep: 3480000\nmean reward (100 episodes): 13.5100\nbest mean reward: 128.3400\ncurrent episode reward: 11.0000\nepisodes: 6810\nexploration: 0.04420\nlearning_rate: 0.00007\nelapsed time: 14596.9 seconds (4.05 hours)\n\nTimestep: 3490000\nmean reward (100 episodes): 13.0400\nbest mean reward: 128.3400\ncurrent episode reward: 5.0000\nepisodes: 6832\nexploration: 0.04397\nlearning_rate: 0.00007\nelapsed time: 14640.7 seconds (4.07 hours)\n\nTimestep: 3500000\nmean reward (100 episodes): 13.3300\nbest mean reward: 128.3400\ncurrent episode reward: 19.0000\nepisodes: 6851\nexploration: 0.04375\nlearning_rate: 0.00007\nelapsed time: 14685.2 seconds (4.08 hours)\n\nTimestep: 3510000\nmean reward (100 episodes): 14.0400\nbest mean reward: 128.3400\ncurrent episode reward: 17.0000\nepisodes: 6867\nexploration: 0.04353\nlearning_rate: 0.00007\nelapsed time: 14728.6 seconds (4.09 hours)\n\nTimestep: 3520000\nmean reward (100 episodes): 14.6300\nbest mean reward: 128.3400\ncurrent episode reward: 21.0000\nepisodes: 6882\nexploration: 0.04330\nlearning_rate: 0.00007\nelapsed time: 14772.7 seconds (4.10 hours)\n\nTimestep: 3530000\nmean reward (100 episodes): 14.4300\nbest mean reward: 128.3400\ncurrent episode reward: 12.0000\nepisodes: 6900\nexploration: 0.04308\nlearning_rate: 0.00007\nelapsed time: 14817.1 seconds (4.12 hours)\n\nTimestep: 3540000\nmean reward (100 episodes): 13.9200\nbest mean reward: 128.3400\ncurrent episode reward: 7.0000\nepisodes: 6915\nexploration: 0.04285\nlearning_rate: 0.00007\nelapsed time: 14861.9 seconds (4.13 hours)\n\nTimestep: 3550000\nmean reward (100 episodes): 15.1900\nbest mean reward: 128.3400\ncurrent episode reward: 30.0000\nepisodes: 6931\nexploration: 0.04263\nlearning_rate: 0.00007\nelapsed time: 14905.5 seconds (4.14 hours)\n\nTimestep: 3560000\nmean reward (100 episodes): 15.6200\nbest mean reward: 128.3400\ncurrent episode reward: 8.0000\nepisodes: 6948\nexploration: 0.04240\nlearning_rate: 0.00007\nelapsed time: 14949.9 seconds (4.15 hours)\n\nTimestep: 3570000\nmean reward (100 episodes): 15.7100\nbest mean reward: 128.3400\ncurrent episode reward: 18.0000\nepisodes: 6963\nexploration: 0.04218\nlearning_rate: 0.00007\nelapsed time: 14994.2 seconds (4.17 hours)\n\nTimestep: 3580000\nmean reward (100 episodes): 15.3800\nbest mean reward: 128.3400\ncurrent episode reward: 26.0000\nepisodes: 6980\nexploration: 0.04195\nlearning_rate: 0.00007\nelapsed time: 15038.0 seconds (4.18 hours)\n\nTimestep: 3590000\nmean reward (100 episodes): 16.3800\nbest mean reward: 128.3400\ncurrent episode reward: 28.0000\nepisodes: 6994\nexploration: 0.04173\nlearning_rate: 0.00007\nelapsed time: 15082.0 seconds (4.19 hours)\n\nTimestep: 3600000\nmean reward (100 episodes): 17.2300\nbest mean reward: 128.3400\ncurrent episode reward: 22.0000\nepisodes: 7007\nexploration: 0.04150\nlearning_rate: 0.00007\nelapsed time: 15128.1 seconds (4.20 hours)\n\nTimestep: 3610000\nmean reward (100 episodes): 17.4000\nbest mean reward: 128.3400\ncurrent episode reward: 17.0000\nepisodes: 7022\nexploration: 0.04127\nlearning_rate: 0.00007\nelapsed time: 15172.2 seconds (4.21 hours)\n\nTimestep: 3620000\nmean reward (100 episodes): 17.9800\nbest mean reward: 128.3400\ncurrent episode reward: 18.0000\nepisodes: 7035\nexploration: 0.04105\nlearning_rate: 0.00007\nelapsed time: 15216.2 seconds (4.23 hours)\n\nTimestep: 3630000\nmean reward (100 episodes): 18.9600\nbest mean reward: 128.3400\ncurrent episode reward: 12.0000\nepisodes: 7051\nexploration: 0.04083\nlearning_rate: 0.00007\nelapsed time: 15260.2 seconds (4.24 hours)\n\nTimestep: 3640000\nmean reward (100 episodes): 19.7300\nbest mean reward: 128.3400\ncurrent episode reward: 30.0000\nepisodes: 7063\nexploration: 0.04060\nlearning_rate: 0.00007\nelapsed time: 15304.6 seconds (4.25 hours)\n\nTimestep: 3650000\nmean reward (100 episodes): 20.6900\nbest mean reward: 128.3400\ncurrent episode reward: 34.0000\nepisodes: 7078\nexploration: 0.04038\nlearning_rate: 0.00007\nelapsed time: 15348.3 seconds (4.26 hours)\n\nTimestep: 3660000\nmean reward (100 episodes): 20.8900\nbest mean reward: 128.3400\ncurrent episode reward: 20.0000\nepisodes: 7090\nexploration: 0.04015\nlearning_rate: 0.00007\nelapsed time: 15392.4 seconds (4.28 hours)\n\nTimestep: 3670000\nmean reward (100 episodes): 20.4300\nbest mean reward: 128.3400\ncurrent episode reward: 19.0000\nepisodes: 7106\nexploration: 0.03993\nlearning_rate: 0.00007\nelapsed time: 15436.0 seconds (4.29 hours)\n\nTimestep: 3680000\nmean reward (100 episodes): 20.7100\nbest mean reward: 128.3400\ncurrent episode reward: 17.0000\nepisodes: 7119\nexploration: 0.03970\nlearning_rate: 0.00007\nelapsed time: 15479.9 seconds (4.30 hours)\n\nTimestep: 3690000\nmean reward (100 episodes): 21.2200\nbest mean reward: 128.3400\ncurrent episode reward: 30.0000\nepisodes: 7131\nexploration: 0.03947\nlearning_rate: 0.00007\nelapsed time: 15524.4 seconds (4.31 hours)\n\nTimestep: 3700000\nmean reward (100 episodes): 21.2300\nbest mean reward: 128.3400\ncurrent episode reward: 27.0000\nepisodes: 7144\nexploration: 0.03925\nlearning_rate: 0.00007\nelapsed time: 15568.2 seconds (4.32 hours)\n\nTimestep: 3710000\nmean reward (100 episodes): 21.2400\nbest mean reward: 128.3400\ncurrent episode reward: 10.0000\nepisodes: 7159\nexploration: 0.03902\nlearning_rate: 0.00007\nelapsed time: 15612.4 seconds (4.34 hours)\n\nTimestep: 3720000\nmean reward (100 episodes): 21.5800\nbest mean reward: 128.3400\ncurrent episode reward: 19.0000\nepisodes: 7172\nexploration: 0.03880\nlearning_rate: 0.00007\nelapsed time: 15656.7 seconds (4.35 hours)\n\nTimestep: 3730000\nmean reward (100 episodes): 21.6700\nbest mean reward: 128.3400\ncurrent episode reward: 17.0000\nepisodes: 7184\nexploration: 0.03857\nlearning_rate: 0.00007\nelapsed time: 15701.0 seconds (4.36 hours)\n\nTimestep: 3740000\nmean reward (100 episodes): 21.9500\nbest mean reward: 128.3400\ncurrent episode reward: 40.0000\nepisodes: 7196\nexploration: 0.03835\nlearning_rate: 0.00007\nelapsed time: 15745.5 seconds (4.37 hours)\n\nTimestep: 3750000\nmean reward (100 episodes): 23.4100\nbest mean reward: 128.3400\ncurrent episode reward: 36.0000\nepisodes: 7207\nexploration: 0.03812\nlearning_rate: 0.00007\nelapsed time: 15789.7 seconds (4.39 hours)\n\nTimestep: 3760000\nmean reward (100 episodes): 24.5100\nbest mean reward: 128.3400\ncurrent episode reward: 23.0000\nepisodes: 7218\nexploration: 0.03790\nlearning_rate: 0.00007\nelapsed time: 15834.2 seconds (4.40 hours)\n\nTimestep: 3770000\nmean reward (100 episodes): 24.7500\nbest mean reward: 128.3400\ncurrent episode reward: 31.0000\nepisodes: 7230\nexploration: 0.03768\nlearning_rate: 0.00007\nelapsed time: 15877.8 seconds (4.41 hours)\n\nTimestep: 3780000\nmean reward (100 episodes): 25.5800\nbest mean reward: 128.3400\ncurrent episode reward: 22.0000\nepisodes: 7241\nexploration: 0.03745\nlearning_rate: 0.00007\nelapsed time: 15922.3 seconds (4.42 hours)\n\nTimestep: 3790000\nmean reward (100 episodes): 26.0200\nbest mean reward: 128.3400\ncurrent episode reward: 14.0000\nepisodes: 7253\nexploration: 0.03722\nlearning_rate: 0.00007\nelapsed time: 15967.1 seconds (4.44 hours)\n\nTimestep: 3800000\nmean reward (100 episodes): 26.1900\nbest mean reward: 128.3400\ncurrent episode reward: 17.0000\nepisodes: 7266\nexploration: 0.03700\nlearning_rate: 0.00007\nelapsed time: 16011.4 seconds (4.45 hours)\n\nTimestep: 3810000\nmean reward (100 episodes): 26.4500\nbest mean reward: 128.3400\ncurrent episode reward: 19.0000\nepisodes: 7278\nexploration: 0.03678\nlearning_rate: 0.00006\nelapsed time: 16054.8 seconds (4.46 hours)\n\nTimestep: 3820000\nmean reward (100 episodes): 27.3500\nbest mean reward: 128.3400\ncurrent episode reward: 34.0000\nepisodes: 7289\nexploration: 0.03655\nlearning_rate: 0.00006\nelapsed time: 16099.5 seconds (4.47 hours)\n\nTimestep: 3830000\nmean reward (100 episodes): 27.4100\nbest mean reward: 128.3400\ncurrent episode reward: 50.0000\nepisodes: 7301\nexploration: 0.03632\nlearning_rate: 0.00006\nelapsed time: 16143.7 seconds (4.48 hours)\n\nTimestep: 3840000\nmean reward (100 episodes): 27.5700\nbest mean reward: 128.3400\ncurrent episode reward: 21.0000\nepisodes: 7312\nexploration: 0.03610\nlearning_rate: 0.00006\nelapsed time: 16187.9 seconds (4.50 hours)\n\nTimestep: 3850000\nmean reward (100 episodes): 27.9000\nbest mean reward: 128.3400\ncurrent episode reward: 24.0000\nepisodes: 7323\nexploration: 0.03587\nlearning_rate: 0.00006\nelapsed time: 16232.3 seconds (4.51 hours)\n\nTimestep: 3860000\nmean reward (100 episodes): 31.0300\nbest mean reward: 128.3400\ncurrent episode reward: 56.0000\nepisodes: 7333\nexploration: 0.03565\nlearning_rate: 0.00006\nelapsed time: 16276.6 seconds (4.52 hours)\n\nTimestep: 3870000\nmean reward (100 episodes): 31.4900\nbest mean reward: 128.3400\ncurrent episode reward: 18.0000\nepisodes: 7343\nexploration: 0.03542\nlearning_rate: 0.00006\nelapsed time: 16320.9 seconds (4.53 hours)\n\nTimestep: 3880000\nmean reward (100 episodes): 32.1100\nbest mean reward: 128.3400\ncurrent episode reward: 36.0000\nepisodes: 7353\nexploration: 0.03520\nlearning_rate: 0.00006\nelapsed time: 16365.2 seconds (4.55 hours)\n\nTimestep: 3890000\nmean reward (100 episodes): 33.6500\nbest mean reward: 128.3400\ncurrent episode reward: 73.0000\nepisodes: 7363\nexploration: 0.03497\nlearning_rate: 0.00006\nelapsed time: 16409.5 seconds (4.56 hours)\n\nTimestep: 3900000\nmean reward (100 episodes): 35.2900\nbest mean reward: 128.3400\ncurrent episode reward: 45.0000\nepisodes: 7372\nexploration: 0.03475\nlearning_rate: 0.00006\nelapsed time: 16453.4 seconds (4.57 hours)\n\nTimestep: 3910000\nmean reward (100 episodes): 36.0800\nbest mean reward: 128.3400\ncurrent episode reward: 42.0000\nepisodes: 7383\nexploration: 0.03453\nlearning_rate: 0.00006\nelapsed time: 16497.7 seconds (4.58 hours)\n\nTimestep: 3920000\nmean reward (100 episodes): 37.0600\nbest mean reward: 128.3400\ncurrent episode reward: 56.0000\nepisodes: 7392\nexploration: 0.03430\nlearning_rate: 0.00006\nelapsed time: 16541.6 seconds (4.59 hours)\n\nTimestep: 3930000\nmean reward (100 episodes): 38.4700\nbest mean reward: 128.3400\ncurrent episode reward: 65.0000\nepisodes: 7401\nexploration: 0.03407\nlearning_rate: 0.00006\nelapsed time: 16586.5 seconds (4.61 hours)\n\nTimestep: 3940000\nmean reward (100 episodes): 39.3900\nbest mean reward: 128.3400\ncurrent episode reward: 21.0000\nepisodes: 7410\nexploration: 0.03385\nlearning_rate: 0.00006\nelapsed time: 16630.4 seconds (4.62 hours)\n\nTimestep: 3950000\nmean reward (100 episodes): 40.0100\nbest mean reward: 128.3400\ncurrent episode reward: 57.0000\nepisodes: 7418\nexploration: 0.03362\nlearning_rate: 0.00006\nelapsed time: 16674.3 seconds (4.63 hours)\n\nTimestep: 3960000\nmean reward (100 episodes): 38.3500\nbest mean reward: 128.3400\ncurrent episode reward: 22.0000\nepisodes: 7429\nexploration: 0.03340\nlearning_rate: 0.00006\nelapsed time: 16719.2 seconds (4.64 hours)\n\nTimestep: 3970000\nmean reward (100 episodes): 38.1800\nbest mean reward: 128.3400\ncurrent episode reward: 31.0000\nepisodes: 7438\nexploration: 0.03317\nlearning_rate: 0.00006\nelapsed time: 16762.9 seconds (4.66 hours)\n\nTimestep: 3980000\nmean reward (100 episodes): 39.4400\nbest mean reward: 128.3400\ncurrent episode reward: 60.0000\nepisodes: 7448\nexploration: 0.03295\nlearning_rate: 0.00006\nelapsed time: 16806.8 seconds (4.67 hours)\n\nTimestep: 3990000\nmean reward (100 episodes): 40.6100\nbest mean reward: 128.3400\ncurrent episode reward: 42.0000\nepisodes: 7457\nexploration: 0.03272\nlearning_rate: 0.00006\nelapsed time: 16850.6 seconds (4.68 hours)\n\nTimestep: 4000000\nmean reward (100 episodes): 40.5600\nbest mean reward: 128.3400\ncurrent episode reward: 40.0000\nepisodes: 7467\nexploration: 0.03250\nlearning_rate: 0.00006\nelapsed time: 16894.9 seconds (4.69 hours)\n\nTimestep: 4010000\nmean reward (100 episodes): 41.7000\nbest mean reward: 128.3400\ncurrent episode reward: 54.0000\nepisodes: 7475\nexploration: 0.03227\nlearning_rate: 0.00006\nelapsed time: 16938.4 seconds (4.71 hours)\n\nTimestep: 4020000\nmean reward (100 episodes): 41.9300\nbest mean reward: 128.3400\ncurrent episode reward: 44.0000\nepisodes: 7485\nexploration: 0.03205\nlearning_rate: 0.00006\nelapsed time: 16982.4 seconds (4.72 hours)\n\nTimestep: 4030000\nmean reward (100 episodes): 42.5300\nbest mean reward: 128.3400\ncurrent episode reward: 38.0000\nepisodes: 7494\nexploration: 0.03183\nlearning_rate: 0.00006\nelapsed time: 17026.1 seconds (4.73 hours)\n\nTimestep: 4040000\nmean reward (100 episodes): 43.7500\nbest mean reward: 128.3400\ncurrent episode reward: 48.0000\nepisodes: 7501\nexploration: 0.03160\nlearning_rate: 0.00006\nelapsed time: 17069.8 seconds (4.74 hours)\n\nTimestep: 4050000\nmean reward (100 episodes): 44.4300\nbest mean reward: 128.3400\ncurrent episode reward: 41.0000\nepisodes: 7510\nexploration: 0.03138\nlearning_rate: 0.00006\nelapsed time: 17113.8 seconds (4.75 hours)\n\nTimestep: 4060000\nmean reward (100 episodes): 45.6300\nbest mean reward: 128.3400\ncurrent episode reward: 62.0000\nepisodes: 7517\nexploration: 0.03115\nlearning_rate: 0.00006\nelapsed time: 17158.0 seconds (4.77 hours)\n\nTimestep: 4070000\nmean reward (100 episodes): 46.9900\nbest mean reward: 128.3400\ncurrent episode reward: 66.0000\nepisodes: 7525\nexploration: 0.03092\nlearning_rate: 0.00006\nelapsed time: 17201.7 seconds (4.78 hours)\n\nTimestep: 4080000\nmean reward (100 episodes): 47.2300\nbest mean reward: 128.3400\ncurrent episode reward: 52.0000\nepisodes: 7534\nexploration: 0.03070\nlearning_rate: 0.00006\nelapsed time: 17245.5 seconds (4.79 hours)\n\nTimestep: 4090000\nmean reward (100 episodes): 47.5300\nbest mean reward: 128.3400\ncurrent episode reward: 22.0000\nepisodes: 7543\nexploration: 0.03048\nlearning_rate: 0.00006\nelapsed time: 17289.6 seconds (4.80 hours)\n\nTimestep: 4100000\nmean reward (100 episodes): 47.7700\nbest mean reward: 128.3400\ncurrent episode reward: 39.0000\nepisodes: 7552\nexploration: 0.03025\nlearning_rate: 0.00006\nelapsed time: 17334.1 seconds (4.82 hours)\n\nTimestep: 4110000\nmean reward (100 episodes): 47.6300\nbest mean reward: 128.3400\ncurrent episode reward: 37.0000\nepisodes: 7561\nexploration: 0.03002\nlearning_rate: 0.00006\nelapsed time: 17378.6 seconds (4.83 hours)\n\nTimestep: 4120000\nmean reward (100 episodes): 48.7100\nbest mean reward: 128.3400\ncurrent episode reward: 53.0000\nepisodes: 7569\nexploration: 0.02980\nlearning_rate: 0.00006\nelapsed time: 17422.7 seconds (4.84 hours)\n\nTimestep: 4130000\nmean reward (100 episodes): 49.3300\nbest mean reward: 128.3400\ncurrent episode reward: 72.0000\nepisodes: 7577\nexploration: 0.02958\nlearning_rate: 0.00006\nelapsed time: 17467.2 seconds (4.85 hours)\n\nTimestep: 4140000\nmean reward (100 episodes): 49.6400\nbest mean reward: 128.3400\ncurrent episode reward: 33.0000\nepisodes: 7586\nexploration: 0.02935\nlearning_rate: 0.00006\nelapsed time: 17511.9 seconds (4.86 hours)\n\nTimestep: 4150000\nmean reward (100 episodes): 49.7600\nbest mean reward: 128.3400\ncurrent episode reward: 62.0000\nepisodes: 7594\nexploration: 0.02912\nlearning_rate: 0.00006\nelapsed time: 17556.7 seconds (4.88 hours)\n\nTimestep: 4160000\nmean reward (100 episodes): 50.1200\nbest mean reward: 128.3400\ncurrent episode reward: 57.0000\nepisodes: 7601\nexploration: 0.02890\nlearning_rate: 0.00006\nelapsed time: 17601.0 seconds (4.89 hours)\n\nTimestep: 4170000\nmean reward (100 episodes): 50.7500\nbest mean reward: 128.3400\ncurrent episode reward: 56.0000\nepisodes: 7609\nexploration: 0.02867\nlearning_rate: 0.00006\nelapsed time: 17645.2 seconds (4.90 hours)\n\nTimestep: 4180000\nmean reward (100 episodes): 50.8800\nbest mean reward: 128.3400\ncurrent episode reward: 69.0000\nepisodes: 7617\nexploration: 0.02845\nlearning_rate: 0.00006\nelapsed time: 17689.7 seconds (4.91 hours)\n\nTimestep: 4190000\nmean reward (100 episodes): 51.2700\nbest mean reward: 128.3400\ncurrent episode reward: 53.0000\nepisodes: 7625\nexploration: 0.02823\nlearning_rate: 0.00006\nelapsed time: 17734.1 seconds (4.93 hours)\n\nTimestep: 4200000\nmean reward (100 episodes): 52.6500\nbest mean reward: 128.3400\ncurrent episode reward: 70.0000\nepisodes: 7632\nexploration: 0.02800\nlearning_rate: 0.00006\nelapsed time: 17778.4 seconds (4.94 hours)\n\nTimestep: 4210000\nmean reward (100 episodes): 52.9400\nbest mean reward: 128.3400\ncurrent episode reward: 26.0000\nepisodes: 7641\nexploration: 0.02777\nlearning_rate: 0.00006\nelapsed time: 17822.6 seconds (4.95 hours)\n\nTimestep: 4220000\nmean reward (100 episodes): 54.0400\nbest mean reward: 128.3400\ncurrent episode reward: 72.0000\nepisodes: 7649\nexploration: 0.02755\nlearning_rate: 0.00006\nelapsed time: 17866.4 seconds (4.96 hours)\n\nTimestep: 4230000\nmean reward (100 episodes): 55.4600\nbest mean reward: 128.3400\ncurrent episode reward: 73.0000\nepisodes: 7657\nexploration: 0.02733\nlearning_rate: 0.00006\nelapsed time: 17910.1 seconds (4.98 hours)\n\nTimestep: 4240000\nmean reward (100 episodes): 55.8000\nbest mean reward: 128.3400\ncurrent episode reward: 36.0000\nepisodes: 7665\nexploration: 0.02710\nlearning_rate: 0.00006\nelapsed time: 17954.4 seconds (4.99 hours)\n\nTimestep: 4250000\nmean reward (100 episodes): 55.3100\nbest mean reward: 128.3400\ncurrent episode reward: 34.0000\nepisodes: 7673\nexploration: 0.02687\nlearning_rate: 0.00006\nelapsed time: 17998.9 seconds (5.00 hours)\n\nTimestep: 4260000\nmean reward (100 episodes): 54.9400\nbest mean reward: 128.3400\ncurrent episode reward: 32.0000\nepisodes: 7682\nexploration: 0.02665\nlearning_rate: 0.00006\nelapsed time: 18043.3 seconds (5.01 hours)\n\nTimestep: 4270000\nmean reward (100 episodes): 56.1600\nbest mean reward: 128.3400\ncurrent episode reward: 53.0000\nepisodes: 7690\nexploration: 0.02642\nlearning_rate: 0.00006\nelapsed time: 18087.2 seconds (5.02 hours)\n\nTimestep: 4280000\nmean reward (100 episodes): 56.8900\nbest mean reward: 128.3400\ncurrent episode reward: 78.0000\nepisodes: 7697\nexploration: 0.02620\nlearning_rate: 0.00006\nelapsed time: 18131.5 seconds (5.04 hours)\n\nTimestep: 4290000\nmean reward (100 episodes): 56.8500\nbest mean reward: 128.3400\ncurrent episode reward: 70.0000\nepisodes: 7704\nexploration: 0.02597\nlearning_rate: 0.00006\nelapsed time: 18176.1 seconds (5.05 hours)\n\nTimestep: 4300000\nmean reward (100 episodes): 57.9300\nbest mean reward: 128.3400\ncurrent episode reward: 76.0000\nepisodes: 7712\nexploration: 0.02575\nlearning_rate: 0.00006\nelapsed time: 18220.0 seconds (5.06 hours)\n\nTimestep: 4310000\nmean reward (100 episodes): 57.0500\nbest mean reward: 128.3400\ncurrent episode reward: 64.0000\nepisodes: 7720\nexploration: 0.02552\nlearning_rate: 0.00006\nelapsed time: 18263.4 seconds (5.07 hours)\n\nTimestep: 4320000\nmean reward (100 episodes): 57.9700\nbest mean reward: 128.3400\ncurrent episode reward: 84.0000\nepisodes: 7727\nexploration: 0.02530\nlearning_rate: 0.00006\nelapsed time: 18307.8 seconds (5.09 hours)\n\nTimestep: 4330000\nmean reward (100 episodes): 58.9000\nbest mean reward: 128.3400\ncurrent episode reward: 54.0000\nepisodes: 7735\nexploration: 0.02508\nlearning_rate: 0.00006\nelapsed time: 18352.3 seconds (5.10 hours)\n\nTimestep: 4340000\nmean reward (100 episodes): 59.6900\nbest mean reward: 128.3400\ncurrent episode reward: 66.0000\nepisodes: 7742\nexploration: 0.02485\nlearning_rate: 0.00006\nelapsed time: 18396.1 seconds (5.11 hours)\n\nTimestep: 4350000\nmean reward (100 episodes): 60.2600\nbest mean reward: 128.3400\ncurrent episode reward: 65.0000\nepisodes: 7750\nexploration: 0.02462\nlearning_rate: 0.00006\nelapsed time: 18440.5 seconds (5.12 hours)\n\nTimestep: 4360000\nmean reward (100 episodes): 60.9700\nbest mean reward: 128.3400\ncurrent episode reward: 81.0000\nepisodes: 7757\nexploration: 0.02440\nlearning_rate: 0.00006\nelapsed time: 18485.1 seconds (5.13 hours)\n\nTimestep: 4370000\nmean reward (100 episodes): 61.8800\nbest mean reward: 128.3400\ncurrent episode reward: 89.0000\nepisodes: 7764\nexploration: 0.02417\nlearning_rate: 0.00006\nelapsed time: 18529.2 seconds (5.15 hours)\n\nTimestep: 4380000\nmean reward (100 episodes): 62.2800\nbest mean reward: 128.3400\ncurrent episode reward: 39.0000\nepisodes: 7772\nexploration: 0.02395\nlearning_rate: 0.00006\nelapsed time: 18573.5 seconds (5.16 hours)\n\nTimestep: 4390000\nmean reward (100 episodes): 63.7500\nbest mean reward: 128.3400\ncurrent episode reward: 45.0000\nepisodes: 7780\nexploration: 0.02372\nlearning_rate: 0.00006\nelapsed time: 18618.4 seconds (5.17 hours)\n\nTimestep: 4400000\nmean reward (100 episodes): 63.5300\nbest mean reward: 128.3400\ncurrent episode reward: 61.0000\nepisodes: 7788\nexploration: 0.02350\nlearning_rate: 0.00006\nelapsed time: 18662.0 seconds (5.18 hours)\n\nTimestep: 4410000\nmean reward (100 episodes): 63.6100\nbest mean reward: 128.3400\ncurrent episode reward: 72.0000\nepisodes: 7796\nexploration: 0.02327\nlearning_rate: 0.00006\nelapsed time: 18706.2 seconds (5.20 hours)\n\nTimestep: 4420000\nmean reward (100 episodes): 63.3800\nbest mean reward: 128.3400\ncurrent episode reward: 94.0000\nepisodes: 7804\nexploration: 0.02305\nlearning_rate: 0.00006\nelapsed time: 18751.7 seconds (5.21 hours)\n\nTimestep: 4430000\nmean reward (100 episodes): 64.2900\nbest mean reward: 128.3400\ncurrent episode reward: 101.0000\nepisodes: 7811\nexploration: 0.02282\nlearning_rate: 0.00006\nelapsed time: 18797.0 seconds (5.22 hours)\n\nTimestep: 4440000\nmean reward (100 episodes): 64.6100\nbest mean reward: 128.3400\ncurrent episode reward: 72.0000\nepisodes: 7818\nexploration: 0.02260\nlearning_rate: 0.00006\nelapsed time: 18842.2 seconds (5.23 hours)\n\nTimestep: 4450000\nmean reward (100 episodes): 64.4600\nbest mean reward: 128.3400\ncurrent episode reward: 62.0000\nepisodes: 7826\nexploration: 0.02237\nlearning_rate: 0.00006\nelapsed time: 18886.3 seconds (5.25 hours)\n\nTimestep: 4460000\nmean reward (100 episodes): 65.0200\nbest mean reward: 128.3400\ncurrent episode reward: 60.0000\nepisodes: 7833\nexploration: 0.02215\nlearning_rate: 0.00006\nelapsed time: 18930.8 seconds (5.26 hours)\n\nTimestep: 4470000\nmean reward (100 episodes): 65.4500\nbest mean reward: 128.3400\ncurrent episode reward: 89.0000\nepisodes: 7839\nexploration: 0.02192\nlearning_rate: 0.00006\nelapsed time: 18975.0 seconds (5.27 hours)\n\nTimestep: 4480000\nmean reward (100 episodes): 65.8500\nbest mean reward: 128.3400\ncurrent episode reward: 63.0000\nepisodes: 7847\nexploration: 0.02170\nlearning_rate: 0.00006\nelapsed time: 19019.9 seconds (5.28 hours)\n\nTimestep: 4490000\nmean reward (100 episodes): 66.7000\nbest mean reward: 128.3400\ncurrent episode reward: 121.0000\nepisodes: 7854\nexploration: 0.02147\nlearning_rate: 0.00006\nelapsed time: 19064.5 seconds (5.30 hours)\n\nTimestep: 4500000\nmean reward (100 episodes): 66.3500\nbest mean reward: 128.3400\ncurrent episode reward: 63.0000\nepisodes: 7862\nexploration: 0.02125\nlearning_rate: 0.00006\nelapsed time: 19109.3 seconds (5.31 hours)\n\nTimestep: 4510000\nmean reward (100 episodes): 67.2900\nbest mean reward: 128.3400\ncurrent episode reward: 91.0000\nepisodes: 7869\nexploration: 0.02103\nlearning_rate: 0.00006\nelapsed time: 19154.8 seconds (5.32 hours)\n\nTimestep: 4520000\nmean reward (100 episodes): 67.0000\nbest mean reward: 128.3400\ncurrent episode reward: 61.0000\nepisodes: 7877\nexploration: 0.02080\nlearning_rate: 0.00006\nelapsed time: 19198.8 seconds (5.33 hours)\n\nTimestep: 4530000\nmean reward (100 episodes): 68.1000\nbest mean reward: 128.3400\ncurrent episode reward: 60.0000\nepisodes: 7883\nexploration: 0.02057\nlearning_rate: 0.00006\nelapsed time: 19243.4 seconds (5.35 hours)\n\nTimestep: 4540000\nmean reward (100 episodes): 69.7000\nbest mean reward: 128.3400\ncurrent episode reward: 81.0000\nepisodes: 7891\nexploration: 0.02035\nlearning_rate: 0.00006\nelapsed time: 19287.3 seconds (5.36 hours)\n\nTimestep: 4550000\nmean reward (100 episodes): 70.4400\nbest mean reward: 128.3400\ncurrent episode reward: 56.0000\nepisodes: 7898\nexploration: 0.02013\nlearning_rate: 0.00006\nelapsed time: 19331.9 seconds (5.37 hours)\n\nTimestep: 4560000\nmean reward (100 episodes): 71.5800\nbest mean reward: 128.3400\ncurrent episode reward: 69.0000\nepisodes: 7905\nexploration: 0.01990\nlearning_rate: 0.00006\nelapsed time: 19376.3 seconds (5.38 hours)\n\nTimestep: 4570000\nmean reward (100 episodes): 72.5900\nbest mean reward: 128.3400\ncurrent episode reward: 109.0000\nepisodes: 7912\nexploration: 0.01967\nlearning_rate: 0.00006\nelapsed time: 19420.7 seconds (5.39 hours)\n\nTimestep: 4580000\nmean reward (100 episodes): 73.6500\nbest mean reward: 128.3400\ncurrent episode reward: 101.0000\nepisodes: 7919\nexploration: 0.01945\nlearning_rate: 0.00006\nelapsed time: 19465.3 seconds (5.41 hours)\n\nTimestep: 4590000\nmean reward (100 episodes): 51.8300\nbest mean reward: 128.3400\ncurrent episode reward: 2.0000\nepisodes: 7954\nexploration: 0.01923\nlearning_rate: 0.00006\nelapsed time: 19509.4 seconds (5.42 hours)\n\nTimestep: 4600000\nmean reward (100 episodes): 33.9200\nbest mean reward: 128.3400\ncurrent episode reward: 10.0000\nepisodes: 7982\nexploration: 0.01900\nlearning_rate: 0.00006\nelapsed time: 19553.6 seconds (5.43 hours)\n\nTimestep: 4610000\nmean reward (100 episodes): 24.4800\nbest mean reward: 128.3400\ncurrent episode reward: 32.0000\nepisodes: 7999\nexploration: 0.01878\nlearning_rate: 0.00005\nelapsed time: 19598.2 seconds (5.44 hours)\n\nTimestep: 4620000\nmean reward (100 episodes): 22.7200\nbest mean reward: 128.3400\ncurrent episode reward: 43.0000\nepisodes: 8007\nexploration: 0.01855\nlearning_rate: 0.00005\nelapsed time: 19645.6 seconds (5.46 hours)\n\nTimestep: 4630000\nmean reward (100 episodes): 21.0900\nbest mean reward: 128.3400\ncurrent episode reward: 91.0000\nepisodes: 8014\nexploration: 0.01832\nlearning_rate: 0.00005\nelapsed time: 19690.5 seconds (5.47 hours)\n\nTimestep: 4640000\nmean reward (100 episodes): 21.6200\nbest mean reward: 128.3400\ncurrent episode reward: 76.0000\nepisodes: 8021\nexploration: 0.01810\nlearning_rate: 0.00005\nelapsed time: 19735.6 seconds (5.48 hours)\n\nTimestep: 4650000\nmean reward (100 episodes): 26.5100\nbest mean reward: 128.3400\ncurrent episode reward: 89.0000\nepisodes: 8028\nexploration: 0.01788\nlearning_rate: 0.00005\nelapsed time: 19780.7 seconds (5.49 hours)\n\nTimestep: 4660000\nmean reward (100 episodes): 31.8200\nbest mean reward: 128.3400\ncurrent episode reward: 81.0000\nepisodes: 8035\nexploration: 0.01765\nlearning_rate: 0.00005\nelapsed time: 19825.3 seconds (5.51 hours)\n\nTimestep: 4670000\nmean reward (100 episodes): 38.1100\nbest mean reward: 128.3400\ncurrent episode reward: 106.0000\nepisodes: 8042\nexploration: 0.01742\nlearning_rate: 0.00005\nelapsed time: 19869.3 seconds (5.52 hours)\n\nTimestep: 4680000\nmean reward (100 episodes): 43.0100\nbest mean reward: 128.3400\ncurrent episode reward: 105.0000\nepisodes: 8049\nexploration: 0.01720\nlearning_rate: 0.00005\nelapsed time: 19913.9 seconds (5.53 hours)\n\nTimestep: 4690000\nmean reward (100 episodes): 49.1100\nbest mean reward: 128.3400\ncurrent episode reward: 77.0000\nepisodes: 8057\nexploration: 0.01697\nlearning_rate: 0.00005\nelapsed time: 19958.7 seconds (5.54 hours)\n\nTimestep: 4700000\nmean reward (100 episodes): 54.8500\nbest mean reward: 128.3400\ncurrent episode reward: 64.0000\nepisodes: 8065\nexploration: 0.01675\nlearning_rate: 0.00005\nelapsed time: 20003.1 seconds (5.56 hours)\n\nTimestep: 4710000\nmean reward (100 episodes): 61.8900\nbest mean reward: 128.3400\ncurrent episode reward: 78.0000\nepisodes: 8071\nexploration: 0.01652\nlearning_rate: 0.00005\nelapsed time: 20047.3 seconds (5.57 hours)\n\nTimestep: 4720000\nmean reward (100 episodes): 67.8900\nbest mean reward: 128.3400\ncurrent episode reward: 85.0000\nepisodes: 8077\nexploration: 0.01630\nlearning_rate: 0.00005\nelapsed time: 20091.2 seconds (5.58 hours)\n\nTimestep: 4730000\nmean reward (100 episodes): 73.1600\nbest mean reward: 128.3400\ncurrent episode reward: 121.0000\nepisodes: 8084\nexploration: 0.01607\nlearning_rate: 0.00005\nelapsed time: 20135.7 seconds (5.59 hours)\n\nTimestep: 4740000\nmean reward (100 episodes): 79.8300\nbest mean reward: 128.3400\ncurrent episode reward: 101.0000\nepisodes: 8091\nexploration: 0.01585\nlearning_rate: 0.00005\nelapsed time: 20180.2 seconds (5.61 hours)\n\nTimestep: 4750000\nmean reward (100 episodes): 85.6400\nbest mean reward: 128.3400\ncurrent episode reward: 197.0000\nepisodes: 8097\nexploration: 0.01562\nlearning_rate: 0.00005\nelapsed time: 20223.6 seconds (5.62 hours)\n\nTimestep: 4760000\nmean reward (100 episodes): 87.7500\nbest mean reward: 128.3400\ncurrent episode reward: 86.0000\nepisodes: 8104\nexploration: 0.01540\nlearning_rate: 0.00005\nelapsed time: 20268.2 seconds (5.63 hours)\n\nTimestep: 4770000\nmean reward (100 episodes): 90.2300\nbest mean reward: 128.3400\ncurrent episode reward: 114.0000\nepisodes: 8111\nexploration: 0.01517\nlearning_rate: 0.00005\nelapsed time: 20312.9 seconds (5.64 hours)\n\nTimestep: 4780000\nmean reward (100 episodes): 90.9000\nbest mean reward: 128.3400\ncurrent episode reward: 104.0000\nepisodes: 8118\nexploration: 0.01495\nlearning_rate: 0.00005\nelapsed time: 20358.0 seconds (5.66 hours)\n\nTimestep: 4790000\nmean reward (100 episodes): 93.3900\nbest mean reward: 128.3400\ncurrent episode reward: 79.0000\nepisodes: 8124\nexploration: 0.01472\nlearning_rate: 0.00005\nelapsed time: 20402.6 seconds (5.67 hours)\n\nTimestep: 4800000\nmean reward (100 episodes): 95.7100\nbest mean reward: 128.3400\ncurrent episode reward: 71.0000\nepisodes: 8131\nexploration: 0.01450\nlearning_rate: 0.00005\nelapsed time: 20447.1 seconds (5.68 hours)\n\nTimestep: 4810000\nmean reward (100 episodes): 91.8300\nbest mean reward: 128.3400\ncurrent episode reward: 78.0000\nepisodes: 8141\nexploration: 0.01427\nlearning_rate: 0.00005\nelapsed time: 20491.7 seconds (5.69 hours)\n\nTimestep: 4820000\nmean reward (100 episodes): 93.2400\nbest mean reward: 128.3400\ncurrent episode reward: 45.0000\nepisodes: 8148\nexploration: 0.01405\nlearning_rate: 0.00005\nelapsed time: 20536.9 seconds (5.70 hours)\n\nTimestep: 4830000\nmean reward (100 episodes): 92.2000\nbest mean reward: 128.3400\ncurrent episode reward: 69.0000\nepisodes: 8156\nexploration: 0.01382\nlearning_rate: 0.00005\nelapsed time: 20581.3 seconds (5.72 hours)\n\nTimestep: 4840000\nmean reward (100 episodes): 95.3700\nbest mean reward: 128.3400\ncurrent episode reward: 115.0000\nepisodes: 8163\nexploration: 0.01360\nlearning_rate: 0.00005\nelapsed time: 20625.8 seconds (5.73 hours)\n\nTimestep: 4850000\nmean reward (100 episodes): 95.2800\nbest mean reward: 128.3400\ncurrent episode reward: 84.0000\nepisodes: 8170\nexploration: 0.01337\nlearning_rate: 0.00005\nelapsed time: 20670.3 seconds (5.74 hours)\n\nTimestep: 4860000\nmean reward (100 episodes): 96.2000\nbest mean reward: 128.3400\ncurrent episode reward: 116.0000\nepisodes: 8177\nexploration: 0.01315\nlearning_rate: 0.00005\nelapsed time: 20715.0 seconds (5.75 hours)\n\nTimestep: 4870000\nmean reward (100 episodes): 98.0600\nbest mean reward: 128.3400\ncurrent episode reward: 166.0000\nepisodes: 8183\nexploration: 0.01292\nlearning_rate: 0.00005\nelapsed time: 20758.9 seconds (5.77 hours)\n\nTimestep: 4880000\nmean reward (100 episodes): 99.1300\nbest mean reward: 128.3400\ncurrent episode reward: 116.0000\nepisodes: 8190\nexploration: 0.01270\nlearning_rate: 0.00005\nelapsed time: 20803.5 seconds (5.78 hours)\n\nTimestep: 4890000\nmean reward (100 episodes): 99.6300\nbest mean reward: 128.3400\ncurrent episode reward: 145.0000\nepisodes: 8196\nexploration: 0.01247\nlearning_rate: 0.00005\nelapsed time: 20847.5 seconds (5.79 hours)\n\nTimestep: 4900000\nmean reward (100 episodes): 98.7500\nbest mean reward: 128.3400\ncurrent episode reward: 89.0000\nepisodes: 8204\nexploration: 0.01225\nlearning_rate: 0.00005\nelapsed time: 20892.5 seconds (5.80 hours)\n\nTimestep: 4910000\nmean reward (100 episodes): 99.7800\nbest mean reward: 128.3400\ncurrent episode reward: 118.0000\nepisodes: 8211\nexploration: 0.01202\nlearning_rate: 0.00005\nelapsed time: 20937.5 seconds (5.82 hours)\n\nTimestep: 4920000\nmean reward (100 episodes): 102.0700\nbest mean reward: 128.3400\ncurrent episode reward: 132.0000\nepisodes: 8217\nexploration: 0.01180\nlearning_rate: 0.00005\nelapsed time: 20982.1 seconds (5.83 hours)\n\nTimestep: 4930000\nmean reward (100 episodes): 101.8500\nbest mean reward: 128.3400\ncurrent episode reward: 80.0000\nepisodes: 8224\nexploration: 0.01157\nlearning_rate: 0.00005\nelapsed time: 21025.6 seconds (5.84 hours)\n\nTimestep: 4940000\nmean reward (100 episodes): 102.1400\nbest mean reward: 128.3400\ncurrent episode reward: 120.0000\nepisodes: 8230\nexploration: 0.01135\nlearning_rate: 0.00005\nelapsed time: 21070.9 seconds (5.85 hours)\n\nTimestep: 4950000\nmean reward (100 episodes): 108.4500\nbest mean reward: 128.3400\ncurrent episode reward: 81.0000\nepisodes: 8237\nexploration: 0.01112\nlearning_rate: 0.00005\nelapsed time: 21115.9 seconds (5.87 hours)\n\nTimestep: 4960000\nmean reward (100 episodes): 110.1700\nbest mean reward: 128.3400\ncurrent episode reward: 110.0000\nepisodes: 8243\nexploration: 0.01090\nlearning_rate: 0.00005\nelapsed time: 21160.2 seconds (5.88 hours)\n\nTimestep: 4970000\nmean reward (100 episodes): 112.2100\nbest mean reward: 128.3400\ncurrent episode reward: 90.0000\nepisodes: 8250\nexploration: 0.01067\nlearning_rate: 0.00005\nelapsed time: 21204.5 seconds (5.89 hours)\n\nTimestep: 4980000\nmean reward (100 episodes): 114.9100\nbest mean reward: 128.3400\ncurrent episode reward: 231.0000\nepisodes: 8257\nexploration: 0.01045\nlearning_rate: 0.00005\nelapsed time: 21248.6 seconds (5.90 hours)\n\nTimestep: 4990000\nmean reward (100 episodes): 114.3800\nbest mean reward: 128.3400\ncurrent episode reward: 155.0000\nepisodes: 8264\nexploration: 0.01022\nlearning_rate: 0.00005\nelapsed time: 21292.9 seconds (5.91 hours)\n\nTimestep: 5000000\nmean reward (100 episodes): 114.8300\nbest mean reward: 128.3400\ncurrent episode reward: 166.0000\nepisodes: 8270\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21337.8 seconds (5.93 hours)\n\nTimestep: 5010000\nmean reward (100 episodes): 117.5400\nbest mean reward: 128.3400\ncurrent episode reward: 84.0000\nepisodes: 8276\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21383.1 seconds (5.94 hours)\n\nTimestep: 5020000\nmean reward (100 episodes): 119.7300\nbest mean reward: 128.3400\ncurrent episode reward: 282.0000\nepisodes: 8283\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21427.9 seconds (5.95 hours)\n\nTimestep: 5030000\nmean reward (100 episodes): 120.6200\nbest mean reward: 128.3400\ncurrent episode reward: 241.0000\nepisodes: 8289\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21472.3 seconds (5.96 hours)\n\nTimestep: 5040000\nmean reward (100 episodes): 124.6200\nbest mean reward: 128.3400\ncurrent episode reward: 153.0000\nepisodes: 8295\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21516.4 seconds (5.98 hours)\n\nTimestep: 5050000\nmean reward (100 episodes): 126.2000\nbest mean reward: 128.3400\ncurrent episode reward: 73.0000\nepisodes: 8302\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21560.8 seconds (5.99 hours)\n\nTimestep: 5060000\nmean reward (100 episodes): 130.6000\nbest mean reward: 130.6000\ncurrent episode reward: 225.0000\nepisodes: 8309\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21605.2 seconds (6.00 hours)\n\nTimestep: 5070000\nmean reward (100 episodes): 132.5700\nbest mean reward: 132.6500\ncurrent episode reward: 109.0000\nepisodes: 8315\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21649.3 seconds (6.01 hours)\n\nTimestep: 5080000\nmean reward (100 episodes): 131.4100\nbest mean reward: 132.6600\ncurrent episode reward: 105.0000\nepisodes: 8322\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21694.1 seconds (6.03 hours)\n\nTimestep: 5090000\nmean reward (100 episodes): 131.0800\nbest mean reward: 132.6600\ncurrent episode reward: 92.0000\nepisodes: 8329\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21738.9 seconds (6.04 hours)\n\nTimestep: 5100000\nmean reward (100 episodes): 130.4400\nbest mean reward: 132.6600\ncurrent episode reward: 150.0000\nepisodes: 8335\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21783.0 seconds (6.05 hours)\n\nTimestep: 5110000\nmean reward (100 episodes): 134.2100\nbest mean reward: 134.2100\ncurrent episode reward: 168.0000\nepisodes: 8342\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21826.4 seconds (6.06 hours)\n\nTimestep: 5120000\nmean reward (100 episodes): 135.9800\nbest mean reward: 136.0300\ncurrent episode reward: 102.0000\nepisodes: 8348\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21870.5 seconds (6.08 hours)\n\nTimestep: 5130000\nmean reward (100 episodes): 138.2900\nbest mean reward: 138.2900\ncurrent episode reward: 178.0000\nepisodes: 8354\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21915.4 seconds (6.09 hours)\n\nTimestep: 5140000\nmean reward (100 episodes): 143.4600\nbest mean reward: 143.4600\ncurrent episode reward: 246.0000\nepisodes: 8361\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21961.0 seconds (6.10 hours)\n\nTimestep: 5150000\nmean reward (100 episodes): 145.6200\nbest mean reward: 145.6200\ncurrent episode reward: 198.0000\nepisodes: 8368\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22006.0 seconds (6.11 hours)\n\nTimestep: 5160000\nmean reward (100 episodes): 146.8700\nbest mean reward: 146.8700\ncurrent episode reward: 256.0000\nepisodes: 8374\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22050.3 seconds (6.13 hours)\n\nTimestep: 5170000\nmean reward (100 episodes): 151.2100\nbest mean reward: 151.4700\ncurrent episode reward: 144.0000\nepisodes: 8381\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22095.2 seconds (6.14 hours)\n\nTimestep: 5180000\nmean reward (100 episodes): 151.5700\nbest mean reward: 152.5300\ncurrent episode reward: 95.0000\nepisodes: 8388\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22139.7 seconds (6.15 hours)\n\nTimestep: 5190000\nmean reward (100 episodes): 150.9400\nbest mean reward: 152.5300\ncurrent episode reward: 242.0000\nepisodes: 8395\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22184.3 seconds (6.16 hours)\n\nTimestep: 5200000\nmean reward (100 episodes): 155.3300\nbest mean reward: 155.3300\ncurrent episode reward: 265.0000\nepisodes: 8402\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22228.9 seconds (6.17 hours)\n\nTimestep: 5210000\nmean reward (100 episodes): 151.9700\nbest mean reward: 156.4100\ncurrent episode reward: 90.0000\nepisodes: 8409\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22272.8 seconds (6.19 hours)\n\nTimestep: 5220000\nmean reward (100 episodes): 152.2600\nbest mean reward: 156.4100\ncurrent episode reward: 191.0000\nepisodes: 8416\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22316.9 seconds (6.20 hours)\n\nTimestep: 5230000\nmean reward (100 episodes): 154.7900\nbest mean reward: 156.4100\ncurrent episode reward: 192.0000\nepisodes: 8422\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22361.3 seconds (6.21 hours)\n\nTimestep: 5240000\nmean reward (100 episodes): 159.2500\nbest mean reward: 159.2500\ncurrent episode reward: 132.0000\nepisodes: 8429\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22405.4 seconds (6.22 hours)\n\nTimestep: 5250000\nmean reward (100 episodes): 163.0300\nbest mean reward: 163.0500\ncurrent episode reward: 207.0000\nepisodes: 8435\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22449.9 seconds (6.24 hours)\n\nTimestep: 5260000\nmean reward (100 episodes): 162.8200\nbest mean reward: 164.0200\ncurrent episode reward: 216.0000\nepisodes: 8441\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22494.0 seconds (6.25 hours)\n\nTimestep: 5270000\nmean reward (100 episodes): 164.4400\nbest mean reward: 164.4400\ncurrent episode reward: 231.0000\nepisodes: 8447\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22538.5 seconds (6.26 hours)\n\nTimestep: 5280000\nmean reward (100 episodes): 169.6700\nbest mean reward: 169.6700\ncurrent episode reward: 141.0000\nepisodes: 8453\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22582.9 seconds (6.27 hours)\n\nTimestep: 5290000\nmean reward (100 episodes): 170.9500\nbest mean reward: 171.6300\ncurrent episode reward: 165.0000\nepisodes: 8459\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22627.6 seconds (6.29 hours)\n\nTimestep: 5300000\nmean reward (100 episodes): 177.1000\nbest mean reward: 177.1000\ncurrent episode reward: 284.0000\nepisodes: 8466\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22671.8 seconds (6.30 hours)\n\nTimestep: 5310000\nmean reward (100 episodes): 179.5800\nbest mean reward: 180.0300\ncurrent episode reward: 221.0000\nepisodes: 8472\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22716.2 seconds (6.31 hours)\n\nTimestep: 5320000\nmean reward (100 episodes): 176.2300\nbest mean reward: 180.0300\ncurrent episode reward: 206.0000\nepisodes: 8478\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22760.3 seconds (6.32 hours)\n\nTimestep: 5330000\nmean reward (100 episodes): 179.5400\nbest mean reward: 180.0300\ncurrent episode reward: 176.0000\nepisodes: 8484\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22805.5 seconds (6.33 hours)\n\nTimestep: 5340000\nmean reward (100 episodes): 182.3400\nbest mean reward: 182.3400\ncurrent episode reward: 178.0000\nepisodes: 8490\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22849.5 seconds (6.35 hours)\n\nTimestep: 5350000\nmean reward (100 episodes): 184.0900\nbest mean reward: 184.0900\ncurrent episode reward: 260.0000\nepisodes: 8496\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22894.2 seconds (6.36 hours)\n\nTimestep: 5360000\nmean reward (100 episodes): 177.3500\nbest mean reward: 185.4400\ncurrent episode reward: 61.0000\nepisodes: 8504\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22938.6 seconds (6.37 hours)\n\nTimestep: 5370000\nmean reward (100 episodes): 181.9100\nbest mean reward: 185.4400\ncurrent episode reward: 212.0000\nepisodes: 8510\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22983.5 seconds (6.38 hours)\n\nTimestep: 5380000\nmean reward (100 episodes): 181.6000\nbest mean reward: 185.4400\ncurrent episode reward: 127.0000\nepisodes: 8516\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23028.4 seconds (6.40 hours)\n\nTimestep: 5390000\nmean reward (100 episodes): 180.3300\nbest mean reward: 185.4400\ncurrent episode reward: 274.0000\nepisodes: 8523\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23073.7 seconds (6.41 hours)\n\nTimestep: 5400000\nmean reward (100 episodes): 177.7300\nbest mean reward: 185.4400\ncurrent episode reward: 116.0000\nepisodes: 8530\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23118.3 seconds (6.42 hours)\n\nTimestep: 5410000\nmean reward (100 episodes): 175.9300\nbest mean reward: 185.4400\ncurrent episode reward: 151.0000\nepisodes: 8536\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23162.2 seconds (6.43 hours)\n\nTimestep: 5420000\nmean reward (100 episodes): 175.3900\nbest mean reward: 185.4400\ncurrent episode reward: 308.0000\nepisodes: 8543\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23207.3 seconds (6.45 hours)\n\nTimestep: 5430000\nmean reward (100 episodes): 172.6500\nbest mean reward: 185.4400\ncurrent episode reward: 85.0000\nepisodes: 8549\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23251.2 seconds (6.46 hours)\n\nTimestep: 5440000\nmean reward (100 episodes): 171.0200\nbest mean reward: 185.4400\ncurrent episode reward: 263.0000\nepisodes: 8555\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23295.5 seconds (6.47 hours)\n\nTimestep: 5450000\nmean reward (100 episodes): 172.1900\nbest mean reward: 185.4400\ncurrent episode reward: 310.0000\nepisodes: 8562\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23340.1 seconds (6.48 hours)\n\nTimestep: 5460000\nmean reward (100 episodes): 169.2100\nbest mean reward: 185.4400\ncurrent episode reward: 130.0000\nepisodes: 8568\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23384.7 seconds (6.50 hours)\n\nTimestep: 5470000\nmean reward (100 episodes): 171.1200\nbest mean reward: 185.4400\ncurrent episode reward: 85.0000\nepisodes: 8574\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23429.5 seconds (6.51 hours)\n\nTimestep: 5480000\nmean reward (100 episodes): 177.6500\nbest mean reward: 185.4400\ncurrent episode reward: 269.0000\nepisodes: 8580\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23474.4 seconds (6.52 hours)\n\nTimestep: 5490000\nmean reward (100 episodes): 180.0800\nbest mean reward: 185.4400\ncurrent episode reward: 334.0000\nepisodes: 8586\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23518.7 seconds (6.53 hours)\n\nTimestep: 5500000\nmean reward (100 episodes): 180.5200\nbest mean reward: 185.4400\ncurrent episode reward: 211.0000\nepisodes: 8592\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23563.8 seconds (6.55 hours)\n\nTimestep: 5510000\nmean reward (100 episodes): 179.3700\nbest mean reward: 185.4400\ncurrent episode reward: 229.0000\nepisodes: 8596\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23608.6 seconds (6.56 hours)\n\nTimestep: 5520000\nmean reward (100 episodes): 187.6900\nbest mean reward: 187.6900\ncurrent episode reward: 256.0000\nepisodes: 8602\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23653.5 seconds (6.57 hours)\n\nTimestep: 5530000\nmean reward (100 episodes): 193.2500\nbest mean reward: 193.2500\ncurrent episode reward: 232.0000\nepisodes: 8608\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23697.1 seconds (6.58 hours)\n\nTimestep: 5540000\nmean reward (100 episodes): 197.0000\nbest mean reward: 197.0000\ncurrent episode reward: 228.0000\nepisodes: 8614\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23741.2 seconds (6.59 hours)\n\nTimestep: 5550000\nmean reward (100 episodes): 200.6100\nbest mean reward: 200.6100\ncurrent episode reward: 252.0000\nepisodes: 8620\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23785.6 seconds (6.61 hours)\n\nTimestep: 5560000\nmean reward (100 episodes): 204.4300\nbest mean reward: 204.4400\ncurrent episode reward: 255.0000\nepisodes: 8626\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23830.7 seconds (6.62 hours)\n\nTimestep: 5570000\nmean reward (100 episodes): 212.8400\nbest mean reward: 212.8400\ncurrent episode reward: 233.0000\nepisodes: 8632\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23874.4 seconds (6.63 hours)\n\nTimestep: 5580000\nmean reward (100 episodes): 218.6900\nbest mean reward: 218.6900\ncurrent episode reward: 271.0000\nepisodes: 8638\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23919.2 seconds (6.64 hours)\n\nTimestep: 5590000\nmean reward (100 episodes): 226.0700\nbest mean reward: 226.0700\ncurrent episode reward: 283.0000\nepisodes: 8644\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23963.9 seconds (6.66 hours)\n\nTimestep: 5600000\nmean reward (100 episodes): 232.7900\nbest mean reward: 232.7900\ncurrent episode reward: 317.0000\nepisodes: 8651\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24009.3 seconds (6.67 hours)\n\nTimestep: 5610000\nmean reward (100 episodes): 233.8100\nbest mean reward: 234.9700\ncurrent episode reward: 133.0000\nepisodes: 8656\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24054.0 seconds (6.68 hours)\n\nTimestep: 5620000\nmean reward (100 episodes): 233.9900\nbest mean reward: 236.0800\ncurrent episode reward: 270.0000\nepisodes: 8663\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24098.8 seconds (6.69 hours)\n\nTimestep: 5630000\nmean reward (100 episodes): 236.7100\nbest mean reward: 239.0900\ncurrent episode reward: 182.0000\nepisodes: 8669\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24142.7 seconds (6.71 hours)\n\nTimestep: 5640000\nmean reward (100 episodes): 238.5700\nbest mean reward: 239.0900\ncurrent episode reward: 245.0000\nepisodes: 8676\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24187.3 seconds (6.72 hours)\n\nTimestep: 5650000\nmean reward (100 episodes): 239.1300\nbest mean reward: 239.1300\ncurrent episode reward: 336.0000\nepisodes: 8682\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24231.4 seconds (6.73 hours)\n\nTimestep: 5660000\nmean reward (100 episodes): 238.6900\nbest mean reward: 241.0000\ncurrent episode reward: 140.0000\nepisodes: 8687\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24276.5 seconds (6.74 hours)\n\nTimestep: 5670000\nmean reward (100 episodes): 240.7300\nbest mean reward: 241.0000\ncurrent episode reward: 281.0000\nepisodes: 8692\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24321.7 seconds (6.76 hours)\n\nTimestep: 5680000\nmean reward (100 episodes): 246.4600\nbest mean reward: 246.4600\ncurrent episode reward: 286.0000\nepisodes: 8698\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24365.7 seconds (6.77 hours)\n\nTimestep: 5690000\nmean reward (100 episodes): 247.1100\nbest mean reward: 247.1500\ncurrent episode reward: 251.0000\nepisodes: 8704\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24409.6 seconds (6.78 hours)\n\nTimestep: 5700000\nmean reward (100 episodes): 251.5500\nbest mean reward: 251.5500\ncurrent episode reward: 324.0000\nepisodes: 8710\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24454.4 seconds (6.79 hours)\n\nTimestep: 5710000\nmean reward (100 episodes): 257.4600\nbest mean reward: 257.4600\ncurrent episode reward: 271.0000\nepisodes: 8715\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24498.2 seconds (6.81 hours)\n\nTimestep: 5720000\nmean reward (100 episodes): 260.2800\nbest mean reward: 260.2800\ncurrent episode reward: 413.0000\nepisodes: 8721\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24542.3 seconds (6.82 hours)\n\nTimestep: 5730000\nmean reward (100 episodes): 261.1400\nbest mean reward: 261.1400\ncurrent episode reward: 265.0000\nepisodes: 8727\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24587.1 seconds (6.83 hours)\n\nTimestep: 5740000\nmean reward (100 episodes): 262.3200\nbest mean reward: 262.3200\ncurrent episode reward: 257.0000\nepisodes: 8732\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24632.2 seconds (6.84 hours)\n\nTimestep: 5750000\nmean reward (100 episodes): 264.2400\nbest mean reward: 264.2400\ncurrent episode reward: 372.0000\nepisodes: 8737\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24676.1 seconds (6.85 hours)\n\nTimestep: 5760000\nmean reward (100 episodes): 262.8100\nbest mean reward: 266.2000\ncurrent episode reward: 281.0000\nepisodes: 8744\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24720.9 seconds (6.87 hours)\n\nTimestep: 5770000\nmean reward (100 episodes): 258.7400\nbest mean reward: 266.2000\ncurrent episode reward: 116.0000\nepisodes: 8751\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24765.3 seconds (6.88 hours)\n\nTimestep: 5780000\nmean reward (100 episodes): 258.6300\nbest mean reward: 266.2000\ncurrent episode reward: 252.0000\nepisodes: 8757\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24809.3 seconds (6.89 hours)\n\nTimestep: 5790000\nmean reward (100 episodes): 260.6500\nbest mean reward: 266.2000\ncurrent episode reward: 218.0000\nepisodes: 8763\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24854.4 seconds (6.90 hours)\n\nTimestep: 5800000\nmean reward (100 episodes): 262.2700\nbest mean reward: 266.2000\ncurrent episode reward: 277.0000\nepisodes: 8768\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24897.9 seconds (6.92 hours)\n\nTimestep: 5810000\nmean reward (100 episodes): 264.4000\nbest mean reward: 266.2000\ncurrent episode reward: 249.0000\nepisodes: 8775\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24942.4 seconds (6.93 hours)\n\nTimestep: 5820000\nmean reward (100 episodes): 266.5700\nbest mean reward: 267.4300\ncurrent episode reward: 268.0000\nepisodes: 8780\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24987.3 seconds (6.94 hours)\n\nTimestep: 5830000\nmean reward (100 episodes): 268.8800\nbest mean reward: 269.5600\ncurrent episode reward: 233.0000\nepisodes: 8785\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25031.5 seconds (6.95 hours)\n\nTimestep: 5840000\nmean reward (100 episodes): 272.9300\nbest mean reward: 272.9300\ncurrent episode reward: 406.0000\nepisodes: 8790\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25075.5 seconds (6.97 hours)\n\nTimestep: 5850000\nmean reward (100 episodes): 272.6200\nbest mean reward: 272.9600\ncurrent episode reward: 317.0000\nepisodes: 8796\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25120.1 seconds (6.98 hours)\n\nTimestep: 5860000\nmean reward (100 episodes): 276.3300\nbest mean reward: 276.3300\ncurrent episode reward: 297.0000\nepisodes: 8801\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25164.9 seconds (6.99 hours)\n\nTimestep: 5870000\nmean reward (100 episodes): 277.4500\nbest mean reward: 278.1900\ncurrent episode reward: 288.0000\nepisodes: 8806\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25208.9 seconds (7.00 hours)\n\nTimestep: 5880000\nmean reward (100 episodes): 276.4100\nbest mean reward: 278.1900\ncurrent episode reward: 400.0000\nepisodes: 8811\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25253.4 seconds (7.01 hours)\n\nTimestep: 5890000\nmean reward (100 episodes): 279.2900\nbest mean reward: 279.2900\ncurrent episode reward: 292.0000\nepisodes: 8817\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25297.6 seconds (7.03 hours)\n\nTimestep: 5900000\nmean reward (100 episodes): 281.7200\nbest mean reward: 282.5600\ncurrent episode reward: 226.0000\nepisodes: 8823\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25341.7 seconds (7.04 hours)\n\nTimestep: 5910000\nmean reward (100 episodes): 282.2600\nbest mean reward: 282.5600\ncurrent episode reward: 375.0000\nepisodes: 8828\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25385.8 seconds (7.05 hours)\n\nTimestep: 5920000\nmean reward (100 episodes): 283.6100\nbest mean reward: 283.6100\ncurrent episode reward: 297.0000\nepisodes: 8834\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25430.2 seconds (7.06 hours)\n\nTimestep: 5930000\nmean reward (100 episodes): 280.2000\nbest mean reward: 283.6100\ncurrent episode reward: 357.0000\nepisodes: 8839\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25474.3 seconds (7.08 hours)\n\nTimestep: 5940000\nmean reward (100 episodes): 284.9500\nbest mean reward: 285.1700\ncurrent episode reward: 142.0000\nepisodes: 8845\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25518.4 seconds (7.09 hours)\n\nTimestep: 5950000\nmean reward (100 episodes): 288.2400\nbest mean reward: 288.8400\ncurrent episode reward: 253.0000\nepisodes: 8850\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25562.8 seconds (7.10 hours)\n\nTimestep: 5960000\nmean reward (100 episodes): 296.1700\nbest mean reward: 296.9100\ncurrent episode reward: 275.0000\nepisodes: 8855\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25607.8 seconds (7.11 hours)\n\nTimestep: 5970000\nmean reward (100 episodes): 296.2400\nbest mean reward: 299.0700\ncurrent episode reward: 251.0000\nepisodes: 8861\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25653.2 seconds (7.13 hours)\n\nTimestep: 5980000\nmean reward (100 episodes): 296.7000\nbest mean reward: 299.0700\ncurrent episode reward: 296.0000\nepisodes: 8866\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25698.4 seconds (7.14 hours)\n\nTimestep: 5990000\nmean reward (100 episodes): 298.7000\nbest mean reward: 299.5400\ncurrent episode reward: 264.0000\nepisodes: 8871\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25742.1 seconds (7.15 hours)\n\nTimestep: 6000000\nmean reward (100 episodes): 297.5400\nbest mean reward: 299.5400\ncurrent episode reward: 296.0000\nepisodes: 8877\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25786.7 seconds (7.16 hours)\n\nTimestep: 6010000\nmean reward (100 episodes): 298.8600\nbest mean reward: 299.7300\ncurrent episode reward: 211.0000\nepisodes: 8881\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25830.7 seconds (7.18 hours)\n\nTimestep: 6020000\nmean reward (100 episodes): 297.3700\nbest mean reward: 299.7600\ncurrent episode reward: 284.0000\nepisodes: 8887\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25875.6 seconds (7.19 hours)\n\nTimestep: 6030000\nmean reward (100 episodes): 297.6800\nbest mean reward: 299.7600\ncurrent episode reward: 365.0000\nepisodes: 8893\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25920.1 seconds (7.20 hours)\n\nTimestep: 6040000\nmean reward (100 episodes): 293.4200\nbest mean reward: 299.7600\ncurrent episode reward: 232.0000\nepisodes: 8898\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25963.3 seconds (7.21 hours)\n\nTimestep: 6050000\nmean reward (100 episodes): 291.6800\nbest mean reward: 299.7600\ncurrent episode reward: 313.0000\nepisodes: 8904\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26007.3 seconds (7.22 hours)\n\nTimestep: 6060000\nmean reward (100 episodes): 293.8500\nbest mean reward: 299.7600\ncurrent episode reward: 387.0000\nepisodes: 8909\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26052.0 seconds (7.24 hours)\n\nTimestep: 6070000\nmean reward (100 episodes): 294.4900\nbest mean reward: 299.7600\ncurrent episode reward: 379.0000\nepisodes: 8914\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26096.4 seconds (7.25 hours)\n\nTimestep: 6080000\nmean reward (100 episodes): 296.5500\nbest mean reward: 299.7600\ncurrent episode reward: 407.0000\nepisodes: 8919\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26140.8 seconds (7.26 hours)\n\nTimestep: 6090000\nmean reward (100 episodes): 297.4900\nbest mean reward: 299.7600\ncurrent episode reward: 229.0000\nepisodes: 8924\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26184.7 seconds (7.27 hours)\n\nTimestep: 6100000\nmean reward (100 episodes): 298.1900\nbest mean reward: 299.7600\ncurrent episode reward: 410.0000\nepisodes: 8929\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26228.9 seconds (7.29 hours)\n\nTimestep: 6110000\nmean reward (100 episodes): 295.7200\nbest mean reward: 299.7600\ncurrent episode reward: 305.0000\nepisodes: 8934\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26272.6 seconds (7.30 hours)\n\nTimestep: 6120000\nmean reward (100 episodes): 295.1500\nbest mean reward: 299.7600\ncurrent episode reward: 375.0000\nepisodes: 8940\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26317.3 seconds (7.31 hours)\n\nTimestep: 6130000\nmean reward (100 episodes): 295.7300\nbest mean reward: 299.7600\ncurrent episode reward: 399.0000\nepisodes: 8944\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26361.6 seconds (7.32 hours)\n\nTimestep: 6140000\nmean reward (100 episodes): 299.0200\nbest mean reward: 300.1700\ncurrent episode reward: 323.0000\nepisodes: 8949\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26406.0 seconds (7.34 hours)\n\nTimestep: 6150000\nmean reward (100 episodes): 298.9200\nbest mean reward: 300.1700\ncurrent episode reward: 338.0000\nepisodes: 8954\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26449.3 seconds (7.35 hours)\n\nTimestep: 6160000\nmean reward (100 episodes): 301.6900\nbest mean reward: 301.6900\ncurrent episode reward: 314.0000\nepisodes: 8959\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26493.6 seconds (7.36 hours)\n\nTimestep: 6170000\nmean reward (100 episodes): 304.4200\nbest mean reward: 304.4600\ncurrent episode reward: 249.0000\nepisodes: 8965\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26538.3 seconds (7.37 hours)\n\nTimestep: 6180000\nmean reward (100 episodes): 305.1500\nbest mean reward: 305.1500\ncurrent episode reward: 389.0000\nepisodes: 8969\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26582.9 seconds (7.38 hours)\n\nTimestep: 6190000\nmean reward (100 episodes): 309.6800\nbest mean reward: 309.6800\ncurrent episode reward: 314.0000\nepisodes: 8973\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26627.6 seconds (7.40 hours)\n\nTimestep: 6200000\nmean reward (100 episodes): 310.1600\nbest mean reward: 312.2100\ncurrent episode reward: 361.0000\nepisodes: 8978\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26671.1 seconds (7.41 hours)\n\nTimestep: 6210000\nmean reward (100 episodes): 310.0500\nbest mean reward: 312.2100\ncurrent episode reward: 270.0000\nepisodes: 8983\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26714.8 seconds (7.42 hours)\n\nTimestep: 6220000\nmean reward (100 episodes): 313.8400\nbest mean reward: 313.8400\ncurrent episode reward: 306.0000\nepisodes: 8988\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26758.3 seconds (7.43 hours)\n\nTimestep: 6230000\nmean reward (100 episodes): 316.5400\nbest mean reward: 316.5400\ncurrent episode reward: 406.0000\nepisodes: 8993\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26802.5 seconds (7.45 hours)\n\nTimestep: 6240000\nmean reward (100 episodes): 319.2500\nbest mean reward: 319.5300\ncurrent episode reward: 350.0000\nepisodes: 8999\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26846.4 seconds (7.46 hours)\n\nTimestep: 6250000\nmean reward (100 episodes): 321.5400\nbest mean reward: 321.5400\ncurrent episode reward: 358.0000\nepisodes: 9004\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26895.4 seconds (7.47 hours)\n\nTimestep: 6260000\nmean reward (100 episodes): 318.5100\nbest mean reward: 321.9400\ncurrent episode reward: 350.0000\nepisodes: 9009\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26939.7 seconds (7.48 hours)\n\nTimestep: 6270000\nmean reward (100 episodes): 317.4600\nbest mean reward: 321.9400\ncurrent episode reward: 338.0000\nepisodes: 9013\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26984.8 seconds (7.50 hours)\n\nTimestep: 6280000\nmean reward (100 episodes): 315.8400\nbest mean reward: 321.9400\ncurrent episode reward: 329.0000\nepisodes: 9017\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27029.8 seconds (7.51 hours)\n\nTimestep: 6290000\nmean reward (100 episodes): 316.4200\nbest mean reward: 321.9400\ncurrent episode reward: 358.0000\nepisodes: 9022\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27074.6 seconds (7.52 hours)\n\nTimestep: 6300000\nmean reward (100 episodes): 318.0500\nbest mean reward: 321.9400\ncurrent episode reward: 312.0000\nepisodes: 9027\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27120.1 seconds (7.53 hours)\n\nTimestep: 6310000\nmean reward (100 episodes): 319.2600\nbest mean reward: 321.9400\ncurrent episode reward: 354.0000\nepisodes: 9033\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27164.1 seconds (7.55 hours)\n\nTimestep: 6320000\nmean reward (100 episodes): 322.5900\nbest mean reward: 322.5900\ncurrent episode reward: 371.0000\nepisodes: 9038\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27208.7 seconds (7.56 hours)\n\nTimestep: 6330000\nmean reward (100 episodes): 325.0700\nbest mean reward: 325.0700\ncurrent episode reward: 340.0000\nepisodes: 9043\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27253.2 seconds (7.57 hours)\n\nTimestep: 6340000\nmean reward (100 episodes): 323.7000\nbest mean reward: 325.0700\ncurrent episode reward: 335.0000\nepisodes: 9048\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27297.7 seconds (7.58 hours)\n\nTimestep: 6350000\nmean reward (100 episodes): 322.9200\nbest mean reward: 325.0700\ncurrent episode reward: 376.0000\nepisodes: 9053\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27342.1 seconds (7.60 hours)\n\nTimestep: 6360000\nmean reward (100 episodes): 324.9900\nbest mean reward: 325.0700\ncurrent episode reward: 440.0000\nepisodes: 9057\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27386.4 seconds (7.61 hours)\n\nTimestep: 6370000\nmean reward (100 episodes): 323.4700\nbest mean reward: 325.2900\ncurrent episode reward: 290.0000\nepisodes: 9061\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27430.0 seconds (7.62 hours)\n\nTimestep: 6380000\nmean reward (100 episodes): 326.4400\nbest mean reward: 326.4400\ncurrent episode reward: 401.0000\nepisodes: 9065\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27474.6 seconds (7.63 hours)\n\nTimestep: 6390000\nmean reward (100 episodes): 326.9700\nbest mean reward: 327.3300\ncurrent episode reward: 417.0000\nepisodes: 9069\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27518.6 seconds (7.64 hours)\n\nTimestep: 6400000\nmean reward (100 episodes): 326.8400\nbest mean reward: 327.3300\ncurrent episode reward: 422.0000\nepisodes: 9074\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27563.2 seconds (7.66 hours)\n\nTimestep: 6410000\nmean reward (100 episodes): 329.1500\nbest mean reward: 329.1500\ncurrent episode reward: 408.0000\nepisodes: 9079\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27607.8 seconds (7.67 hours)\n\nTimestep: 6420000\nmean reward (100 episodes): 330.9400\nbest mean reward: 330.9400\ncurrent episode reward: 404.0000\nepisodes: 9082\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27652.1 seconds (7.68 hours)\n\nTimestep: 6430000\nmean reward (100 episodes): 332.6200\nbest mean reward: 333.1400\ncurrent episode reward: 368.0000\nepisodes: 9088\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27696.8 seconds (7.69 hours)\n\nTimestep: 6440000\nmean reward (100 episodes): 333.9600\nbest mean reward: 333.9600\ncurrent episode reward: 363.0000\nepisodes: 9092\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27741.5 seconds (7.71 hours)\n\nTimestep: 6450000\nmean reward (100 episodes): 334.4600\nbest mean reward: 334.4600\ncurrent episode reward: 391.0000\nepisodes: 9095\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27786.3 seconds (7.72 hours)\n\nTimestep: 6460000\nmean reward (100 episodes): 333.5200\nbest mean reward: 335.8300\ncurrent episode reward: 279.0000\nepisodes: 9101\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27830.2 seconds (7.73 hours)\n\nTimestep: 6470000\nmean reward (100 episodes): 335.7700\nbest mean reward: 335.8300\ncurrent episode reward: 334.0000\nepisodes: 9106\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27874.3 seconds (7.74 hours)\n\nTimestep: 6480000\nmean reward (100 episodes): 337.4700\nbest mean reward: 337.4800\ncurrent episode reward: 299.0000\nepisodes: 9108\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27919.2 seconds (7.76 hours)\n\nTimestep: 6490000\nmean reward (100 episodes): 339.5800\nbest mean reward: 340.3200\ncurrent episode reward: 264.0000\nepisodes: 9113\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27963.2 seconds (7.77 hours)\n\nTimestep: 6500000\nmean reward (100 episodes): 339.1100\nbest mean reward: 340.7900\ncurrent episode reward: 232.0000\nepisodes: 9118\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28007.6 seconds (7.78 hours)\n\nTimestep: 6510000\nmean reward (100 episodes): 340.5000\nbest mean reward: 340.7900\ncurrent episode reward: 382.0000\nepisodes: 9122\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28051.8 seconds (7.79 hours)\n\nTimestep: 6520000\nmean reward (100 episodes): 341.9900\nbest mean reward: 341.9900\ncurrent episode reward: 373.0000\nepisodes: 9127\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28096.5 seconds (7.80 hours)\n\nTimestep: 6530000\nmean reward (100 episodes): 344.0400\nbest mean reward: 345.0000\ncurrent episode reward: 209.0000\nepisodes: 9131\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28140.6 seconds (7.82 hours)\n\nTimestep: 6540000\nmean reward (100 episodes): 342.2200\nbest mean reward: 345.0000\ncurrent episode reward: 315.0000\nepisodes: 9136\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28184.8 seconds (7.83 hours)\n\nTimestep: 6550000\nmean reward (100 episodes): 343.8900\nbest mean reward: 345.0000\ncurrent episode reward: 417.0000\nepisodes: 9141\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28229.7 seconds (7.84 hours)\n\nTimestep: 6560000\nmean reward (100 episodes): 345.0000\nbest mean reward: 345.0000\ncurrent episode reward: 403.0000\nepisodes: 9144\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28273.9 seconds (7.85 hours)\n\nTimestep: 6570000\nmean reward (100 episodes): 346.8200\nbest mean reward: 346.8200\ncurrent episode reward: 391.0000\nepisodes: 9149\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28318.5 seconds (7.87 hours)\n\nTimestep: 6580000\nmean reward (100 episodes): 350.9400\nbest mean reward: 350.9400\ncurrent episode reward: 397.0000\nepisodes: 9153\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28362.5 seconds (7.88 hours)\n\nTimestep: 6590000\nmean reward (100 episodes): 350.8100\nbest mean reward: 351.0600\ncurrent episode reward: 405.0000\nepisodes: 9158\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28407.7 seconds (7.89 hours)\n\nTimestep: 6600000\nmean reward (100 episodes): 348.2900\nbest mean reward: 351.0600\ncurrent episode reward: 302.0000\nepisodes: 9163\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28451.9 seconds (7.90 hours)\n\nTimestep: 6610000\nmean reward (100 episodes): 348.9400\nbest mean reward: 351.0600\ncurrent episode reward: 404.0000\nepisodes: 9166\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28496.6 seconds (7.92 hours)\n\nTimestep: 6620000\nmean reward (100 episodes): 350.0100\nbest mean reward: 351.0600\ncurrent episode reward: 320.0000\nepisodes: 9169\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28541.5 seconds (7.93 hours)\n\nTimestep: 6630000\nmean reward (100 episodes): 349.7100\nbest mean reward: 351.0600\ncurrent episode reward: 355.0000\nepisodes: 9174\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28585.5 seconds (7.94 hours)\n\nTimestep: 6640000\nmean reward (100 episodes): 349.4100\nbest mean reward: 351.0600\ncurrent episode reward: 227.0000\nepisodes: 9178\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28629.5 seconds (7.95 hours)\n\nTimestep: 6650000\nmean reward (100 episodes): 349.0300\nbest mean reward: 351.0600\ncurrent episode reward: 424.0000\nepisodes: 9181\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28674.1 seconds (7.97 hours)\n\nTimestep: 6660000\nmean reward (100 episodes): 347.0600\nbest mean reward: 351.0600\ncurrent episode reward: 318.0000\nepisodes: 9186\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28718.6 seconds (7.98 hours)\n\nTimestep: 6670000\nmean reward (100 episodes): 347.0600\nbest mean reward: 351.0600\ncurrent episode reward: 358.0000\nepisodes: 9191\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28762.8 seconds (7.99 hours)\n\nTimestep: 6680000\nmean reward (100 episodes): 347.6800\nbest mean reward: 351.0600\ncurrent episode reward: 398.0000\nepisodes: 9195\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28807.1 seconds (8.00 hours)\n\nTimestep: 6690000\nmean reward (100 episodes): 349.5000\nbest mean reward: 351.0600\ncurrent episode reward: 359.0000\nepisodes: 9200\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28851.7 seconds (8.01 hours)\n\nTimestep: 6700000\nmean reward (100 episodes): 350.6700\nbest mean reward: 351.0600\ncurrent episode reward: 386.0000\nepisodes: 9204\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28896.0 seconds (8.03 hours)\n\nTimestep: 6710000\nmean reward (100 episodes): 351.2100\nbest mean reward: 351.2100\ncurrent episode reward: 398.0000\nepisodes: 9207\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28939.7 seconds (8.04 hours)\n\nTimestep: 6720000\nmean reward (100 episodes): 351.8300\nbest mean reward: 352.4600\ncurrent episode reward: 367.0000\nepisodes: 9210\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28984.2 seconds (8.05 hours)\n\nTimestep: 6730000\nmean reward (100 episodes): 352.9100\nbest mean reward: 352.9100\ncurrent episode reward: 420.0000\nepisodes: 9214\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29028.3 seconds (8.06 hours)\n\nTimestep: 6740000\nmean reward (100 episodes): 355.4400\nbest mean reward: 355.6200\ncurrent episode reward: 373.0000\nepisodes: 9219\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29072.7 seconds (8.08 hours)\n\nTimestep: 6750000\nmean reward (100 episodes): 355.8700\nbest mean reward: 355.8700\ncurrent episode reward: 373.0000\nepisodes: 9223\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29117.1 seconds (8.09 hours)\n\nTimestep: 6760000\nmean reward (100 episodes): 354.4200\nbest mean reward: 355.8700\ncurrent episode reward: 377.0000\nepisodes: 9228\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29161.5 seconds (8.10 hours)\n\nTimestep: 6770000\nmean reward (100 episodes): 356.7900\nbest mean reward: 356.7900\ncurrent episode reward: 374.0000\nepisodes: 9231\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29205.8 seconds (8.11 hours)\n\nTimestep: 6780000\nmean reward (100 episodes): 360.8000\nbest mean reward: 360.9900\ncurrent episode reward: 309.0000\nepisodes: 9236\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29250.5 seconds (8.13 hours)\n\nTimestep: 6790000\nmean reward (100 episodes): 359.8400\nbest mean reward: 361.0400\ncurrent episode reward: 379.0000\nepisodes: 9240\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29294.9 seconds (8.14 hours)\n\nTimestep: 6800000\nmean reward (100 episodes): 358.1800\nbest mean reward: 361.0400\ncurrent episode reward: 301.0000\nepisodes: 9244\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29339.1 seconds (8.15 hours)\n\nTimestep: 6810000\nmean reward (100 episodes): 357.9300\nbest mean reward: 361.0400\ncurrent episode reward: 398.0000\nepisodes: 9248\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29383.4 seconds (8.16 hours)\n\nTimestep: 6820000\nmean reward (100 episodes): 356.7500\nbest mean reward: 361.0400\ncurrent episode reward: 417.0000\nepisodes: 9252\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29427.6 seconds (8.17 hours)\n\nTimestep: 6830000\nmean reward (100 episodes): 356.0800\nbest mean reward: 361.0400\ncurrent episode reward: 375.0000\nepisodes: 9257\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29472.0 seconds (8.19 hours)\n\nTimestep: 6840000\nmean reward (100 episodes): 359.2400\nbest mean reward: 361.0400\ncurrent episode reward: 373.0000\nepisodes: 9261\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29516.5 seconds (8.20 hours)\n\nTimestep: 6850000\nmean reward (100 episodes): 359.7200\nbest mean reward: 361.0400\ncurrent episode reward: 380.0000\nepisodes: 9265\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29560.8 seconds (8.21 hours)\n\nTimestep: 6860000\nmean reward (100 episodes): 355.9800\nbest mean reward: 361.0400\ncurrent episode reward: 373.0000\nepisodes: 9270\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29604.7 seconds (8.22 hours)\n\nTimestep: 6870000\nmean reward (100 episodes): 357.9300\nbest mean reward: 361.0400\ncurrent episode reward: 413.0000\nepisodes: 9274\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29649.0 seconds (8.24 hours)\n\nTimestep: 6880000\nmean reward (100 episodes): 357.2800\nbest mean reward: 361.0400\ncurrent episode reward: 206.0000\nepisodes: 9279\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29694.4 seconds (8.25 hours)\n\nTimestep: 6890000\nmean reward (100 episodes): 355.7200\nbest mean reward: 361.0400\ncurrent episode reward: 365.0000\nepisodes: 9282\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29738.7 seconds (8.26 hours)\n\nTimestep: 6900000\nmean reward (100 episodes): 357.5400\nbest mean reward: 361.0400\ncurrent episode reward: 325.0000\nepisodes: 9285\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29783.5 seconds (8.27 hours)\n\nTimestep: 6910000\nmean reward (100 episodes): 360.6000\nbest mean reward: 361.0400\ncurrent episode reward: 421.0000\nepisodes: 9289\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29828.6 seconds (8.29 hours)\n\nTimestep: 6920000\nmean reward (100 episodes): 364.2600\nbest mean reward: 364.6100\ncurrent episode reward: 362.0000\nepisodes: 9294\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29873.0 seconds (8.30 hours)\n\nTimestep: 6930000\nmean reward (100 episodes): 364.3800\nbest mean reward: 364.6100\ncurrent episode reward: 355.0000\nepisodes: 9298\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29917.4 seconds (8.31 hours)\n\nTimestep: 6940000\nmean reward (100 episodes): 363.8100\nbest mean reward: 364.6100\ncurrent episode reward: 392.0000\nepisodes: 9302\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29961.8 seconds (8.32 hours)\n\nTimestep: 6950000\nmean reward (100 episodes): 364.3800\nbest mean reward: 364.8200\ncurrent episode reward: 380.0000\nepisodes: 9305\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30006.0 seconds (8.33 hours)\n\nTimestep: 6960000\nmean reward (100 episodes): 365.6200\nbest mean reward: 365.6200\ncurrent episode reward: 400.0000\nepisodes: 9309\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30051.4 seconds (8.35 hours)\n\nTimestep: 6970000\nmean reward (100 episodes): 365.5800\nbest mean reward: 365.8000\ncurrent episode reward: 402.0000\nepisodes: 9311\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30095.6 seconds (8.36 hours)\n\nTimestep: 6980000\nmean reward (100 episodes): 364.5400\nbest mean reward: 366.8500\ncurrent episode reward: 346.0000\nepisodes: 9315\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30140.3 seconds (8.37 hours)\n\nTimestep: 6990000\nmean reward (100 episodes): 360.7900\nbest mean reward: 366.8500\ncurrent episode reward: 65.0000\nepisodes: 9319\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30184.7 seconds (8.38 hours)\n\nTimestep: 7000000\nmean reward (100 episodes): 363.1700\nbest mean reward: 366.8500\ncurrent episode reward: 374.0000\nepisodes: 9324\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30228.5 seconds (8.40 hours)\n\nTimestep: 7010000\nmean reward (100 episodes): 362.7300\nbest mean reward: 366.8500\ncurrent episode reward: 283.0000\nepisodes: 9328\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30273.9 seconds (8.41 hours)\n\nTimestep: 7020000\nmean reward (100 episodes): 362.4900\nbest mean reward: 366.8500\ncurrent episode reward: 386.0000\nepisodes: 9332\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30318.6 seconds (8.42 hours)\n\nTimestep: 7030000\nmean reward (100 episodes): 363.6200\nbest mean reward: 366.8500\ncurrent episode reward: 407.0000\nepisodes: 9336\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30363.7 seconds (8.43 hours)\n\nTimestep: 7040000\nmean reward (100 episodes): 364.9200\nbest mean reward: 366.8500\ncurrent episode reward: 343.0000\nepisodes: 9339\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30408.5 seconds (8.45 hours)\n\nTimestep: 7050000\nmean reward (100 episodes): 364.9400\nbest mean reward: 366.8500\ncurrent episode reward: 388.0000\nepisodes: 9341\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30453.6 seconds (8.46 hours)\n\nTimestep: 7060000\nmean reward (100 episodes): 366.6400\nbest mean reward: 367.3200\ncurrent episode reward: 346.0000\nepisodes: 9346\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30498.0 seconds (8.47 hours)\n\nTimestep: 7070000\nmean reward (100 episodes): 366.0800\nbest mean reward: 367.3200\ncurrent episode reward: 404.0000\nepisodes: 9350\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30542.5 seconds (8.48 hours)\n\nTimestep: 7080000\nmean reward (100 episodes): 365.5400\nbest mean reward: 367.3200\ncurrent episode reward: 385.0000\nepisodes: 9355\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30587.2 seconds (8.50 hours)\n\nTimestep: 7090000\nmean reward (100 episodes): 364.3900\nbest mean reward: 367.3200\ncurrent episode reward: 322.0000\nepisodes: 9359\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30632.1 seconds (8.51 hours)\n\nTimestep: 7100000\nmean reward (100 episodes): 365.1700\nbest mean reward: 367.3200\ncurrent episode reward: 428.0000\nepisodes: 9363\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30676.6 seconds (8.52 hours)\n\nTimestep: 7110000\nmean reward (100 episodes): 365.9500\nbest mean reward: 367.3200\ncurrent episode reward: 332.0000\nepisodes: 9366\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30720.1 seconds (8.53 hours)\n\nTimestep: 7120000\nmean reward (100 episodes): 368.4200\nbest mean reward: 368.4200\ncurrent episode reward: 383.0000\nepisodes: 9369\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30764.8 seconds (8.55 hours)\n\nTimestep: 7130000\nmean reward (100 episodes): 367.0900\nbest mean reward: 368.5300\ncurrent episode reward: 424.0000\nepisodes: 9373\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30809.2 seconds (8.56 hours)\n\nTimestep: 7140000\nmean reward (100 episodes): 367.5800\nbest mean reward: 368.5300\ncurrent episode reward: 412.0000\nepisodes: 9377\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30853.7 seconds (8.57 hours)\n\nTimestep: 7150000\nmean reward (100 episodes): 370.0500\nbest mean reward: 370.0500\ncurrent episode reward: 442.0000\nepisodes: 9381\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30898.7 seconds (8.58 hours)\n\nTimestep: 7160000\nmean reward (100 episodes): 371.5300\nbest mean reward: 371.5300\ncurrent episode reward: 417.0000\nepisodes: 9386\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30943.7 seconds (8.60 hours)\n\nTimestep: 7170000\nmean reward (100 episodes): 367.8700\nbest mean reward: 372.0000\ncurrent episode reward: 399.0000\nepisodes: 9390\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30987.4 seconds (8.61 hours)\n\nTimestep: 7180000\nmean reward (100 episodes): 366.9500\nbest mean reward: 372.0000\ncurrent episode reward: 277.0000\nepisodes: 9393\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31031.2 seconds (8.62 hours)\n\nTimestep: 7190000\nmean reward (100 episodes): 370.8700\nbest mean reward: 372.0000\ncurrent episode reward: 458.0000\nepisodes: 9397\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31075.5 seconds (8.63 hours)\n\nTimestep: 7200000\nmean reward (100 episodes): 370.9700\nbest mean reward: 372.0000\ncurrent episode reward: 385.0000\nepisodes: 9400\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31120.0 seconds (8.64 hours)\n\nTimestep: 7210000\nmean reward (100 episodes): 370.7300\nbest mean reward: 372.0000\ncurrent episode reward: 416.0000\nepisodes: 9403\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31164.4 seconds (8.66 hours)\n\nTimestep: 7220000\nmean reward (100 episodes): 370.9300\nbest mean reward: 372.0000\ncurrent episode reward: 360.0000\nepisodes: 9407\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31209.0 seconds (8.67 hours)\n\nTimestep: 7230000\nmean reward (100 episodes): 368.7000\nbest mean reward: 372.0000\ncurrent episode reward: 360.0000\nepisodes: 9412\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31254.3 seconds (8.68 hours)\n\nTimestep: 7240000\nmean reward (100 episodes): 370.4100\nbest mean reward: 372.0000\ncurrent episode reward: 398.0000\nepisodes: 9415\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31298.3 seconds (8.69 hours)\n\nTimestep: 7250000\nmean reward (100 episodes): 376.8900\nbest mean reward: 376.8900\ncurrent episode reward: 330.0000\nepisodes: 9418\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31343.2 seconds (8.71 hours)\n\nTimestep: 7260000\nmean reward (100 episodes): 380.6200\nbest mean reward: 380.6200\ncurrent episode reward: 423.0000\nepisodes: 9420\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31388.2 seconds (8.72 hours)\n\nTimestep: 7270000\nmean reward (100 episodes): 380.2700\nbest mean reward: 380.6200\ncurrent episode reward: 359.0000\nepisodes: 9424\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31433.1 seconds (8.73 hours)\n\nTimestep: 7280000\nmean reward (100 episodes): 381.6100\nbest mean reward: 381.6100\ncurrent episode reward: 340.0000\nepisodes: 9428\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31477.4 seconds (8.74 hours)\n\nTimestep: 7290000\nmean reward (100 episodes): 382.1700\nbest mean reward: 382.1700\ncurrent episode reward: 425.0000\nepisodes: 9429\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31522.8 seconds (8.76 hours)\n\nTimestep: 7300000\nmean reward (100 episodes): 380.3700\nbest mean reward: 382.5300\ncurrent episode reward: 425.0000\nepisodes: 9433\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31567.2 seconds (8.77 hours)\n\nTimestep: 7310000\nmean reward (100 episodes): 378.7700\nbest mean reward: 382.5300\ncurrent episode reward: 228.0000\nepisodes: 9436\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31612.0 seconds (8.78 hours)\n\nTimestep: 7320000\nmean reward (100 episodes): 378.6600\nbest mean reward: 382.5300\ncurrent episode reward: 354.0000\nepisodes: 9440\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31656.4 seconds (8.79 hours)\n\nTimestep: 7330000\nmean reward (100 episodes): 376.5700\nbest mean reward: 382.5300\ncurrent episode reward: 377.0000\nepisodes: 9445\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31700.9 seconds (8.81 hours)\n\nTimestep: 7340000\nmean reward (100 episodes): 380.8800\nbest mean reward: 382.5300\ncurrent episode reward: 416.0000\nepisodes: 9448\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31745.1 seconds (8.82 hours)\n\nTimestep: 7350000\nmean reward (100 episodes): 380.5400\nbest mean reward: 382.5300\ncurrent episode reward: 452.0000\nepisodes: 9452\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31789.0 seconds (8.83 hours)\n\nTimestep: 7360000\nmean reward (100 episodes): 379.3700\nbest mean reward: 382.5300\ncurrent episode reward: 334.0000\nepisodes: 9457\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31833.7 seconds (8.84 hours)\n\nTimestep: 7370000\nmean reward (100 episodes): 377.9400\nbest mean reward: 382.5300\ncurrent episode reward: 408.0000\nepisodes: 9461\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31878.4 seconds (8.86 hours)\n\nTimestep: 7380000\nmean reward (100 episodes): 379.0700\nbest mean reward: 382.5300\ncurrent episode reward: 387.0000\nepisodes: 9465\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31923.6 seconds (8.87 hours)\n\nTimestep: 7390000\nmean reward (100 episodes): 379.4000\nbest mean reward: 382.5300\ncurrent episode reward: 361.0000\nepisodes: 9469\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31967.5 seconds (8.88 hours)\n\nTimestep: 7400000\nmean reward (100 episodes): 376.5300\nbest mean reward: 382.5300\ncurrent episode reward: 278.0000\nepisodes: 9474\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32011.8 seconds (8.89 hours)\n\nTimestep: 7410000\nmean reward (100 episodes): 377.3700\nbest mean reward: 382.5300\ncurrent episode reward: 424.0000\nepisodes: 9477\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32056.6 seconds (8.90 hours)\n\nTimestep: 7420000\nmean reward (100 episodes): 379.1400\nbest mean reward: 382.5300\ncurrent episode reward: 407.0000\nepisodes: 9481\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32101.6 seconds (8.92 hours)\n\nTimestep: 7430000\nmean reward (100 episodes): 379.2500\nbest mean reward: 382.5300\ncurrent episode reward: 421.0000\nepisodes: 9483\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32146.5 seconds (8.93 hours)\n\nTimestep: 7440000\nmean reward (100 episodes): 378.3200\nbest mean reward: 382.5300\ncurrent episode reward: 404.0000\nepisodes: 9487\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32190.4 seconds (8.94 hours)\n\nTimestep: 7450000\nmean reward (100 episodes): 376.9900\nbest mean reward: 382.5300\ncurrent episode reward: 294.0000\nepisodes: 9491\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32234.3 seconds (8.95 hours)\n\nTimestep: 7460000\nmean reward (100 episodes): 381.5800\nbest mean reward: 382.5300\ncurrent episode reward: 398.0000\nepisodes: 9494\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32278.6 seconds (8.97 hours)\n\nTimestep: 7470000\nmean reward (100 episodes): 381.6800\nbest mean reward: 382.5300\ncurrent episode reward: 417.0000\nepisodes: 9496\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32323.0 seconds (8.98 hours)\n\nTimestep: 7480000\nmean reward (100 episodes): 382.3400\nbest mean reward: 382.5300\ncurrent episode reward: 379.0000\nepisodes: 9499\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32366.8 seconds (8.99 hours)\n\nTimestep: 7490000\nmean reward (100 episodes): 381.0400\nbest mean reward: 383.6900\ncurrent episode reward: 379.0000\nepisodes: 9504\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32411.1 seconds (9.00 hours)\n\nTimestep: 7500000\nmean reward (100 episodes): 379.6800\nbest mean reward: 383.6900\ncurrent episode reward: 262.0000\nepisodes: 9505\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32454.9 seconds (9.02 hours)\n\nTimestep: 7510000\nmean reward (100 episodes): 377.5700\nbest mean reward: 383.6900\ncurrent episode reward: 242.0000\nepisodes: 9509\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32500.1 seconds (9.03 hours)\n\nTimestep: 7520000\nmean reward (100 episodes): 378.5600\nbest mean reward: 383.6900\ncurrent episode reward: 329.0000\nepisodes: 9512\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32545.0 seconds (9.04 hours)\n\nTimestep: 7530000\nmean reward (100 episodes): 378.5200\nbest mean reward: 383.6900\ncurrent episode reward: 389.0000\nepisodes: 9516\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32589.4 seconds (9.05 hours)\n\nTimestep: 7540000\nmean reward (100 episodes): 373.9100\nbest mean reward: 383.6900\ncurrent episode reward: 377.0000\nepisodes: 9520\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32633.4 seconds (9.06 hours)\n\nTimestep: 7550000\nmean reward (100 episodes): 374.2800\nbest mean reward: 383.6900\ncurrent episode reward: 382.0000\nepisodes: 9523\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32677.6 seconds (9.08 hours)\n\nTimestep: 7560000\nmean reward (100 episodes): 373.7000\nbest mean reward: 383.6900\ncurrent episode reward: 307.0000\nepisodes: 9527\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32722.3 seconds (9.09 hours)\n\nTimestep: 7570000\nmean reward (100 episodes): 374.7000\nbest mean reward: 383.6900\ncurrent episode reward: 345.0000\nepisodes: 9532\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32767.3 seconds (9.10 hours)\n\nTimestep: 7580000\nmean reward (100 episodes): 374.7100\nbest mean reward: 383.6900\ncurrent episode reward: 427.0000\nepisodes: 9535\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32812.0 seconds (9.11 hours)\n\nTimestep: 7590000\nmean reward (100 episodes): 377.5900\nbest mean reward: 383.6900\ncurrent episode reward: 411.0000\nepisodes: 9539\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32856.5 seconds (9.13 hours)\n\nTimestep: 7600000\nmean reward (100 episodes): 376.0200\nbest mean reward: 383.6900\ncurrent episode reward: 374.0000\nepisodes: 9543\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32901.0 seconds (9.14 hours)\n\nTimestep: 7610000\nmean reward (100 episodes): 374.4500\nbest mean reward: 383.6900\ncurrent episode reward: 190.0000\nepisodes: 9546\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32945.5 seconds (9.15 hours)\n\nTimestep: 7620000\nmean reward (100 episodes): 374.6200\nbest mean reward: 383.6900\ncurrent episode reward: 396.0000\nepisodes: 9549\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32990.0 seconds (9.16 hours)\n\nTimestep: 7630000\nmean reward (100 episodes): 373.7300\nbest mean reward: 383.6900\ncurrent episode reward: 396.0000\nepisodes: 9553\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33034.7 seconds (9.18 hours)\n\nTimestep: 7640000\nmean reward (100 episodes): 375.0600\nbest mean reward: 383.6900\ncurrent episode reward: 424.0000\nepisodes: 9555\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33079.6 seconds (9.19 hours)\n\nTimestep: 7650000\nmean reward (100 episodes): 374.9200\nbest mean reward: 383.6900\ncurrent episode reward: 381.0000\nepisodes: 9558\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33124.1 seconds (9.20 hours)\n\nTimestep: 7660000\nmean reward (100 episodes): 378.1400\nbest mean reward: 383.6900\ncurrent episode reward: 461.0000\nepisodes: 9561\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33169.2 seconds (9.21 hours)\n\nTimestep: 7670000\nmean reward (100 episodes): 377.9100\nbest mean reward: 383.6900\ncurrent episode reward: 414.0000\nepisodes: 9565\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33213.4 seconds (9.23 hours)\n\nTimestep: 7680000\nmean reward (100 episodes): 377.8600\nbest mean reward: 383.6900\ncurrent episode reward: 373.0000\nepisodes: 9569\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33258.1 seconds (9.24 hours)\n\nTimestep: 7690000\nmean reward (100 episodes): 379.8100\nbest mean reward: 383.6900\ncurrent episode reward: 418.0000\nepisodes: 9572\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33302.1 seconds (9.25 hours)\n\nTimestep: 7700000\nmean reward (100 episodes): 384.4500\nbest mean reward: 385.5800\ncurrent episode reward: 305.0000\nepisodes: 9575\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33346.7 seconds (9.26 hours)\n\nTimestep: 7710000\nmean reward (100 episodes): 383.8800\nbest mean reward: 385.5800\ncurrent episode reward: 397.0000\nepisodes: 9578\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33390.8 seconds (9.28 hours)\n\nTimestep: 7720000\nmean reward (100 episodes): 382.2400\nbest mean reward: 385.5800\ncurrent episode reward: 409.0000\nepisodes: 9582\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33435.5 seconds (9.29 hours)\n\nTimestep: 7730000\nmean reward (100 episodes): 383.9000\nbest mean reward: 385.5800\ncurrent episode reward: 620.0000\nepisodes: 9584\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33479.3 seconds (9.30 hours)\n\nTimestep: 7740000\nmean reward (100 episodes): 385.2600\nbest mean reward: 385.5800\ncurrent episode reward: 459.0000\nepisodes: 9587\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33524.0 seconds (9.31 hours)\n\nTimestep: 7750000\nmean reward (100 episodes): 386.6400\nbest mean reward: 386.6400\ncurrent episode reward: 404.0000\nepisodes: 9589\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33568.4 seconds (9.32 hours)\n\nTimestep: 7760000\nmean reward (100 episodes): 384.4200\nbest mean reward: 388.0500\ncurrent episode reward: 409.0000\nepisodes: 9593\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33613.6 seconds (9.34 hours)\n\nTimestep: 7770000\nmean reward (100 episodes): 382.9500\nbest mean reward: 388.0500\ncurrent episode reward: 413.0000\nepisodes: 9597\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33658.6 seconds (9.35 hours)\n\nTimestep: 7780000\nmean reward (100 episodes): 381.0700\nbest mean reward: 388.0500\ncurrent episode reward: 309.0000\nepisodes: 9600\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33703.5 seconds (9.36 hours)\n\nTimestep: 7790000\nmean reward (100 episodes): 383.3600\nbest mean reward: 388.0500\ncurrent episode reward: 388.0000\nepisodes: 9603\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33747.5 seconds (9.37 hours)\n\nTimestep: 7800000\nmean reward (100 episodes): 384.7400\nbest mean reward: 388.0500\ncurrent episode reward: 333.0000\nepisodes: 9606\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33792.3 seconds (9.39 hours)\n\nTimestep: 7810000\nmean reward (100 episodes): 387.3600\nbest mean reward: 388.0500\ncurrent episode reward: 428.0000\nepisodes: 9609\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33836.8 seconds (9.40 hours)\n\nTimestep: 7820000\nmean reward (100 episodes): 387.6600\nbest mean reward: 388.0500\ncurrent episode reward: 425.0000\nepisodes: 9612\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33880.5 seconds (9.41 hours)\n\nTimestep: 7830000\nmean reward (100 episodes): 387.4300\nbest mean reward: 388.0500\ncurrent episode reward: 399.0000\nepisodes: 9615\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33924.9 seconds (9.42 hours)\n\nTimestep: 7840000\nmean reward (100 episodes): 386.9500\nbest mean reward: 388.0500\ncurrent episode reward: 384.0000\nepisodes: 9618\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33969.3 seconds (9.44 hours)\n\nTimestep: 7850000\nmean reward (100 episodes): 386.8300\nbest mean reward: 388.0500\ncurrent episode reward: 392.0000\nepisodes: 9622\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34013.7 seconds (9.45 hours)\n\nTimestep: 7860000\nmean reward (100 episodes): 387.2500\nbest mean reward: 388.0500\ncurrent episode reward: 408.0000\nepisodes: 9626\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34058.4 seconds (9.46 hours)\n\nTimestep: 7870000\nmean reward (100 episodes): 389.0000\nbest mean reward: 389.0900\ncurrent episode reward: 396.0000\nepisodes: 9630\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34102.8 seconds (9.47 hours)\n\nTimestep: 7880000\nmean reward (100 episodes): 388.1700\nbest mean reward: 390.4400\ncurrent episode reward: 297.0000\nepisodes: 9634\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34147.0 seconds (9.49 hours)\n\nTimestep: 7890000\nmean reward (100 episodes): 384.5700\nbest mean reward: 390.4400\ncurrent episode reward: 117.0000\nepisodes: 9637\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34191.6 seconds (9.50 hours)\n\nTimestep: 7900000\nmean reward (100 episodes): 384.4200\nbest mean reward: 390.4400\ncurrent episode reward: 435.0000\nepisodes: 9641\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34236.8 seconds (9.51 hours)\n\nTimestep: 7910000\nmean reward (100 episodes): 385.3400\nbest mean reward: 390.4400\ncurrent episode reward: 371.0000\nepisodes: 9645\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34281.2 seconds (9.52 hours)\n\nTimestep: 7920000\nmean reward (100 episodes): 386.6400\nbest mean reward: 390.4400\ncurrent episode reward: 530.0000\nepisodes: 9649\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34325.4 seconds (9.53 hours)\n\nTimestep: 7930000\nmean reward (100 episodes): 386.4200\nbest mean reward: 390.4400\ncurrent episode reward: 396.0000\nepisodes: 9653\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34369.2 seconds (9.55 hours)\n\nTimestep: 7940000\nmean reward (100 episodes): 386.0500\nbest mean reward: 390.4400\ncurrent episode reward: 381.0000\nepisodes: 9656\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34413.7 seconds (9.56 hours)\n\nTimestep: 7950000\nmean reward (100 episodes): 382.9900\nbest mean reward: 390.4400\ncurrent episode reward: 94.0000\nepisodes: 9660\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34458.9 seconds (9.57 hours)\n\nTimestep: 7960000\nmean reward (100 episodes): 383.5500\nbest mean reward: 390.4400\ncurrent episode reward: 399.0000\nepisodes: 9663\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34504.1 seconds (9.58 hours)\n\nTimestep: 7970000\nmean reward (100 episodes): 383.2300\nbest mean reward: 390.4400\ncurrent episode reward: 387.0000\nepisodes: 9666\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34548.5 seconds (9.60 hours)\n\nTimestep: 7980000\nmean reward (100 episodes): 386.1100\nbest mean reward: 390.4400\ncurrent episode reward: 444.0000\nepisodes: 9669\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34592.5 seconds (9.61 hours)\n\nTimestep: 7990000\nmean reward (100 episodes): 380.1200\nbest mean reward: 390.4400\ncurrent episode reward: 386.0000\nepisodes: 9674\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34636.8 seconds (9.62 hours)\n\nTimestep: 8000000\nmean reward (100 episodes): 378.5100\nbest mean reward: 390.4400\ncurrent episode reward: 166.0000\nepisodes: 9677\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34681.2 seconds (9.63 hours)\n\nTimestep: 8010000\nmean reward (100 episodes): 379.5000\nbest mean reward: 390.4400\ncurrent episode reward: 420.0000\nepisodes: 9680\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34724.7 seconds (9.65 hours)\n\nTimestep: 8020000\nmean reward (100 episodes): 376.8000\nbest mean reward: 390.4400\ncurrent episode reward: 377.0000\nepisodes: 9684\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34769.1 seconds (9.66 hours)\n\nTimestep: 8030000\nmean reward (100 episodes): 375.7100\nbest mean reward: 390.4400\ncurrent episode reward: 428.0000\nepisodes: 9688\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34813.6 seconds (9.67 hours)\n\nTimestep: 8040000\nmean reward (100 episodes): 372.8700\nbest mean reward: 390.4400\ncurrent episode reward: 390.0000\nepisodes: 9692\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34858.7 seconds (9.68 hours)\n\nTimestep: 8050000\nmean reward (100 episodes): 374.9400\nbest mean reward: 390.4400\ncurrent episode reward: 347.0000\nepisodes: 9695\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34903.7 seconds (9.70 hours)\n\nTimestep: 8060000\nmean reward (100 episodes): 369.5900\nbest mean reward: 390.4400\ncurrent episode reward: 234.0000\nepisodes: 9701\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34948.6 seconds (9.71 hours)\n\nTimestep: 8070000\nmean reward (100 episodes): 369.2800\nbest mean reward: 390.4400\ncurrent episode reward: 403.0000\nepisodes: 9704\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34993.1 seconds (9.72 hours)\n\nTimestep: 8080000\nmean reward (100 episodes): 373.4000\nbest mean reward: 390.4400\ncurrent episode reward: 416.0000\nepisodes: 9706\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35037.4 seconds (9.73 hours)\n\nTimestep: 8090000\nmean reward (100 episodes): 371.9000\nbest mean reward: 390.4400\ncurrent episode reward: 416.0000\nepisodes: 9710\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35082.2 seconds (9.75 hours)\n\nTimestep: 8100000\nmean reward (100 episodes): 377.5000\nbest mean reward: 390.4400\ncurrent episode reward: 830.0000\nepisodes: 9711\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35127.0 seconds (9.76 hours)\n\nTimestep: 8110000\nmean reward (100 episodes): 376.7000\nbest mean reward: 390.4400\ncurrent episode reward: 424.0000\nepisodes: 9715\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35170.9 seconds (9.77 hours)\n\nTimestep: 8120000\nmean reward (100 episodes): 377.1400\nbest mean reward: 390.4400\ncurrent episode reward: 425.0000\nepisodes: 9717\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35215.2 seconds (9.78 hours)\n\nTimestep: 8130000\nmean reward (100 episodes): 377.6400\nbest mean reward: 390.4400\ncurrent episode reward: 411.0000\nepisodes: 9719\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35260.1 seconds (9.79 hours)\n\nTimestep: 8140000\nmean reward (100 episodes): 378.1200\nbest mean reward: 390.4400\ncurrent episode reward: 414.0000\nepisodes: 9720\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35305.3 seconds (9.81 hours)\n\nTimestep: 8150000\nmean reward (100 episodes): 378.9800\nbest mean reward: 390.4400\ncurrent episode reward: 408.0000\nepisodes: 9722\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35349.4 seconds (9.82 hours)\n\nTimestep: 8160000\nmean reward (100 episodes): 378.3400\nbest mean reward: 390.4400\ncurrent episode reward: 413.0000\nepisodes: 9725\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35393.6 seconds (9.83 hours)\n\nTimestep: 8170000\nmean reward (100 episodes): 377.0700\nbest mean reward: 390.4400\ncurrent episode reward: 428.0000\nepisodes: 9730\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35437.7 seconds (9.84 hours)\n\nTimestep: 8180000\nmean reward (100 episodes): 378.5800\nbest mean reward: 390.4400\ncurrent episode reward: 435.0000\nepisodes: 9733\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35482.1 seconds (9.86 hours)\n\nTimestep: 8190000\nmean reward (100 episodes): 379.5300\nbest mean reward: 390.4400\ncurrent episode reward: 359.0000\nepisodes: 9736\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35526.8 seconds (9.87 hours)\n\nTimestep: 8200000\nmean reward (100 episodes): 383.4800\nbest mean reward: 390.4400\ncurrent episode reward: 424.0000\nepisodes: 9740\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35571.2 seconds (9.88 hours)\n\nTimestep: 8210000\nmean reward (100 episodes): 382.9200\nbest mean reward: 390.4400\ncurrent episode reward: 310.0000\nepisodes: 9743\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35615.8 seconds (9.89 hours)\n\nTimestep: 8220000\nmean reward (100 episodes): 380.0200\nbest mean reward: 390.4400\ncurrent episode reward: 90.0000\nepisodes: 9748\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35660.4 seconds (9.91 hours)\n\nTimestep: 8230000\nmean reward (100 episodes): 375.4800\nbest mean reward: 390.4400\ncurrent episode reward: 124.0000\nepisodes: 9753\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35705.1 seconds (9.92 hours)\n\nTimestep: 8240000\nmean reward (100 episodes): 373.8900\nbest mean reward: 390.4400\ncurrent episode reward: 275.0000\nepisodes: 9755\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35750.3 seconds (9.93 hours)\n\nTimestep: 8250000\nmean reward (100 episodes): 374.5100\nbest mean reward: 390.4400\ncurrent episode reward: 428.0000\nepisodes: 9758\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35794.4 seconds (9.94 hours)\n\nTimestep: 8260000\nmean reward (100 episodes): 378.2300\nbest mean reward: 390.4400\ncurrent episode reward: 220.0000\nepisodes: 9762\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35838.6 seconds (9.96 hours)\n\nTimestep: 8270000\nmean reward (100 episodes): 376.1300\nbest mean reward: 390.4400\ncurrent episode reward: 381.0000\nepisodes: 9767\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35883.4 seconds (9.97 hours)\n\nTimestep: 8280000\nmean reward (100 episodes): 374.3900\nbest mean reward: 390.4400\ncurrent episode reward: 227.0000\nepisodes: 9771\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35927.8 seconds (9.98 hours)\n\nTimestep: 8290000\nmean reward (100 episodes): 376.7800\nbest mean reward: 390.4400\ncurrent episode reward: 435.0000\nepisodes: 9774\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35972.0 seconds (9.99 hours)\n\nTimestep: 8300000\nmean reward (100 episodes): 377.0900\nbest mean reward: 390.4400\ncurrent episode reward: 332.0000\nepisodes: 9779\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36016.2 seconds (10.00 hours)\n\nTimestep: 8310000\nmean reward (100 episodes): 377.5200\nbest mean reward: 390.4400\ncurrent episode reward: 334.0000\nepisodes: 9782\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36060.6 seconds (10.02 hours)\n\nTimestep: 8320000\nmean reward (100 episodes): 378.4900\nbest mean reward: 390.4400\ncurrent episode reward: 426.0000\nepisodes: 9785\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36104.3 seconds (10.03 hours)\n\nTimestep: 8330000\nmean reward (100 episodes): 377.7600\nbest mean reward: 390.4400\ncurrent episode reward: 382.0000\nepisodes: 9788\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36147.1 seconds (10.04 hours)\n\nTimestep: 8340000\nmean reward (100 episodes): 379.5400\nbest mean reward: 390.4400\ncurrent episode reward: 388.0000\nepisodes: 9791\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36190.9 seconds (10.05 hours)\n\nTimestep: 8350000\nmean reward (100 episodes): 378.2000\nbest mean reward: 390.4400\ncurrent episode reward: 313.0000\nepisodes: 9795\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36236.0 seconds (10.07 hours)\n\nTimestep: 8360000\nmean reward (100 episodes): 378.5400\nbest mean reward: 390.4400\ncurrent episode reward: 437.0000\nepisodes: 9797\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36280.9 seconds (10.08 hours)\n\nTimestep: 8370000\nmean reward (100 episodes): 380.8500\nbest mean reward: 390.4400\ncurrent episode reward: 392.0000\nepisodes: 9799\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36325.1 seconds (10.09 hours)\n\nTimestep: 8380000\nmean reward (100 episodes): 384.3500\nbest mean reward: 390.4400\ncurrent episode reward: 315.0000\nepisodes: 9802\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36368.9 seconds (10.10 hours)\n\nTimestep: 8390000\nmean reward (100 episodes): 377.9800\nbest mean reward: 390.4400\ncurrent episode reward: 216.0000\nepisodes: 9806\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36413.5 seconds (10.11 hours)\n\nTimestep: 8400000\nmean reward (100 episodes): 371.9900\nbest mean reward: 390.4400\ncurrent episode reward: 360.0000\nepisodes: 9811\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36457.8 seconds (10.13 hours)\n\nTimestep: 8410000\nmean reward (100 episodes): 371.6700\nbest mean reward: 390.4400\ncurrent episode reward: 321.0000\nepisodes: 9815\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36502.4 seconds (10.14 hours)\n\nTimestep: 8420000\nmean reward (100 episodes): 361.9900\nbest mean reward: 390.4400\ncurrent episode reward: 107.0000\nepisodes: 9820\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36546.8 seconds (10.15 hours)\n\nTimestep: 8430000\nmean reward (100 episodes): 362.3400\nbest mean reward: 390.4400\ncurrent episode reward: 422.0000\nepisodes: 9824\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36591.9 seconds (10.16 hours)\n\nTimestep: 8440000\nmean reward (100 episodes): 360.4400\nbest mean reward: 390.4400\ncurrent episode reward: 425.0000\nepisodes: 9828\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36635.9 seconds (10.18 hours)\n\nTimestep: 8450000\nmean reward (100 episodes): 359.6500\nbest mean reward: 390.4400\ncurrent episode reward: 409.0000\nepisodes: 9832\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36681.6 seconds (10.19 hours)\n\nTimestep: 8460000\nmean reward (100 episodes): 359.8200\nbest mean reward: 390.4400\ncurrent episode reward: 418.0000\nepisodes: 9836\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36726.6 seconds (10.20 hours)\n\nTimestep: 8470000\nmean reward (100 episodes): 360.3700\nbest mean reward: 390.4400\ncurrent episode reward: 425.0000\nepisodes: 9839\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36771.5 seconds (10.21 hours)\n\nTimestep: 8480000\nmean reward (100 episodes): 359.8900\nbest mean reward: 390.4400\ncurrent episode reward: 391.0000\nepisodes: 9842\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36815.6 seconds (10.23 hours)\n\nTimestep: 8490000\nmean reward (100 episodes): 363.9000\nbest mean reward: 390.4400\ncurrent episode reward: 395.0000\nepisodes: 9845\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36860.0 seconds (10.24 hours)\n\nTimestep: 8500000\nmean reward (100 episodes): 366.3800\nbest mean reward: 390.4400\ncurrent episode reward: 156.0000\nepisodes: 9848\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36904.9 seconds (10.25 hours)\n\nTimestep: 8510000\nmean reward (100 episodes): 371.2900\nbest mean reward: 390.4400\ncurrent episode reward: 298.0000\nepisodes: 9852\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36949.1 seconds (10.26 hours)\n\nTimestep: 8520000\nmean reward (100 episodes): 374.0700\nbest mean reward: 390.4400\ncurrent episode reward: 402.0000\nepisodes: 9853\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36992.9 seconds (10.28 hours)\n\nTimestep: 8530000\nmean reward (100 episodes): 375.2900\nbest mean reward: 390.4400\ncurrent episode reward: 386.0000\nepisodes: 9857\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37037.0 seconds (10.29 hours)\n\nTimestep: 8540000\nmean reward (100 episodes): 371.0800\nbest mean reward: 390.4400\ncurrent episode reward: 393.0000\nepisodes: 9860\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37080.9 seconds (10.30 hours)\n\nTimestep: 8550000\nmean reward (100 episodes): 372.9000\nbest mean reward: 390.4400\ncurrent episode reward: 402.0000\nepisodes: 9862\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37126.0 seconds (10.31 hours)\n\nTimestep: 8560000\nmean reward (100 episodes): 371.8800\nbest mean reward: 390.4400\ncurrent episode reward: 299.0000\nepisodes: 9867\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37170.1 seconds (10.33 hours)\n\nTimestep: 8570000\nmean reward (100 episodes): 372.9500\nbest mean reward: 390.4400\ncurrent episode reward: 373.0000\nepisodes: 9870\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37215.5 seconds (10.34 hours)\n\nTimestep: 8580000\nmean reward (100 episodes): 373.6400\nbest mean reward: 390.4400\ncurrent episode reward: 422.0000\nepisodes: 9873\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37260.0 seconds (10.35 hours)\n\nTimestep: 8590000\nmean reward (100 episodes): 374.6300\nbest mean reward: 390.4400\ncurrent episode reward: 411.0000\nepisodes: 9876\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37304.9 seconds (10.36 hours)\n\nTimestep: 8600000\nmean reward (100 episodes): 373.2000\nbest mean reward: 390.4400\ncurrent episode reward: 347.0000\nepisodes: 9880\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37350.5 seconds (10.38 hours)\n\nTimestep: 8610000\nmean reward (100 episodes): 373.8400\nbest mean reward: 390.4400\ncurrent episode reward: 327.0000\nepisodes: 9884\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37394.8 seconds (10.39 hours)\n\nTimestep: 8620000\nmean reward (100 episodes): 373.7400\nbest mean reward: 390.4400\ncurrent episode reward: 363.0000\nepisodes: 9888\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37440.3 seconds (10.40 hours)\n\nTimestep: 8630000\nmean reward (100 episodes): 372.7000\nbest mean reward: 390.4400\ncurrent episode reward: 324.0000\nepisodes: 9892\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37485.3 seconds (10.41 hours)\n\nTimestep: 8640000\nmean reward (100 episodes): 373.8700\nbest mean reward: 390.4400\ncurrent episode reward: 398.0000\nepisodes: 9895\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37530.1 seconds (10.43 hours)\n\nTimestep: 8650000\nmean reward (100 episodes): 370.9900\nbest mean reward: 390.4400\ncurrent episode reward: 347.0000\nepisodes: 9898\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37574.3 seconds (10.44 hours)\n\nTimestep: 8660000\nmean reward (100 episodes): 371.1200\nbest mean reward: 390.4400\ncurrent episode reward: 427.0000\nepisodes: 9901\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37619.3 seconds (10.45 hours)\n\nTimestep: 8670000\nmean reward (100 episodes): 370.4800\nbest mean reward: 390.4400\ncurrent episode reward: 436.0000\nepisodes: 9905\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37663.9 seconds (10.46 hours)\n\nTimestep: 8680000\nmean reward (100 episodes): 373.4600\nbest mean reward: 390.4400\ncurrent episode reward: 408.0000\nepisodes: 9908\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37708.0 seconds (10.47 hours)\n\nTimestep: 8690000\nmean reward (100 episodes): 373.2400\nbest mean reward: 390.4400\ncurrent episode reward: 377.0000\nepisodes: 9912\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37752.4 seconds (10.49 hours)\n\nTimestep: 8700000\nmean reward (100 episodes): 375.7700\nbest mean reward: 390.4400\ncurrent episode reward: 348.0000\nepisodes: 9917\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37797.2 seconds (10.50 hours)\n\nTimestep: 8710000\nmean reward (100 episodes): 373.3500\nbest mean reward: 390.4400\ncurrent episode reward: 193.0000\nepisodes: 9919\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37841.5 seconds (10.51 hours)\n\nTimestep: 8720000\nmean reward (100 episodes): 376.2600\nbest mean reward: 390.4400\ncurrent episode reward: 419.0000\nepisodes: 9922\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37886.7 seconds (10.52 hours)\n\nTimestep: 8730000\nmean reward (100 episodes): 376.6100\nbest mean reward: 390.4400\ncurrent episode reward: 258.0000\nepisodes: 9925\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37931.1 seconds (10.54 hours)\n\nTimestep: 8740000\nmean reward (100 episodes): 377.8000\nbest mean reward: 390.4400\ncurrent episode reward: 344.0000\nepisodes: 9927\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37975.5 seconds (10.55 hours)\n\nTimestep: 8750000\nmean reward (100 episodes): 377.5700\nbest mean reward: 390.4400\ncurrent episode reward: 379.0000\nepisodes: 9929\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38019.2 seconds (10.56 hours)\n\nTimestep: 8760000\nmean reward (100 episodes): 375.1600\nbest mean reward: 390.4400\ncurrent episode reward: 434.0000\nepisodes: 9933\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38063.8 seconds (10.57 hours)\n\nTimestep: 8770000\nmean reward (100 episodes): 375.2000\nbest mean reward: 390.4400\ncurrent episode reward: 342.0000\nepisodes: 9936\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38108.6 seconds (10.59 hours)\n\nTimestep: 8780000\nmean reward (100 episodes): 373.5200\nbest mean reward: 390.4400\ncurrent episode reward: 427.0000\nepisodes: 9938\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38152.7 seconds (10.60 hours)\n\nTimestep: 8790000\nmean reward (100 episodes): 371.0500\nbest mean reward: 390.4400\ncurrent episode reward: 104.0000\nepisodes: 9942\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38197.0 seconds (10.61 hours)\n\nTimestep: 8800000\nmean reward (100 episodes): 367.5000\nbest mean reward: 390.4400\ncurrent episode reward: 380.0000\nepisodes: 9946\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38240.9 seconds (10.62 hours)\n\nTimestep: 8810000\nmean reward (100 episodes): 369.3600\nbest mean reward: 390.4400\ncurrent episode reward: 428.0000\nepisodes: 9949\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38285.2 seconds (10.63 hours)\n\nTimestep: 8820000\nmean reward (100 episodes): 367.8600\nbest mean reward: 390.4400\ncurrent episode reward: 410.0000\nepisodes: 9953\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38330.0 seconds (10.65 hours)\n\nTimestep: 8830000\nmean reward (100 episodes): 368.3800\nbest mean reward: 390.4400\ncurrent episode reward: 422.0000\nepisodes: 9956\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38374.7 seconds (10.66 hours)\n\nTimestep: 8840000\nmean reward (100 episodes): 370.6500\nbest mean reward: 390.4400\ncurrent episode reward: 395.0000\nepisodes: 9959\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38419.0 seconds (10.67 hours)\n\nTimestep: 8850000\nmean reward (100 episodes): 368.9400\nbest mean reward: 390.4400\ncurrent episode reward: 372.0000\nepisodes: 9963\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38463.6 seconds (10.68 hours)\n\nTimestep: 8860000\nmean reward (100 episodes): 369.4900\nbest mean reward: 390.4400\ncurrent episode reward: 338.0000\nepisodes: 9967\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38508.2 seconds (10.70 hours)\n\nTimestep: 8870000\nmean reward (100 episodes): 369.0800\nbest mean reward: 390.4400\ncurrent episode reward: 390.0000\nepisodes: 9970\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38553.7 seconds (10.71 hours)\n\nTimestep: 8880000\nmean reward (100 episodes): 367.3900\nbest mean reward: 390.4400\ncurrent episode reward: 268.0000\nepisodes: 9975\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38598.9 seconds (10.72 hours)\n\nTimestep: 8890000\nmean reward (100 episodes): 369.2900\nbest mean reward: 390.4400\ncurrent episode reward: 416.0000\nepisodes: 9978\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38643.4 seconds (10.73 hours)\n\nTimestep: 8900000\nmean reward (100 episodes): 370.0900\nbest mean reward: 390.4400\ncurrent episode reward: 441.0000\nepisodes: 9981\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38687.7 seconds (10.75 hours)\n\nTimestep: 8910000\nmean reward (100 episodes): 368.9800\nbest mean reward: 390.4400\ncurrent episode reward: 423.0000\nepisodes: 9985\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38732.4 seconds (10.76 hours)\n\nTimestep: 8920000\nmean reward (100 episodes): 364.6400\nbest mean reward: 390.4400\ncurrent episode reward: 405.0000\nepisodes: 9989\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38777.2 seconds (10.77 hours)\n\nTimestep: 8930000\nmean reward (100 episodes): 368.6100\nbest mean reward: 390.4400\ncurrent episode reward: 406.0000\nepisodes: 9993\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38821.6 seconds (10.78 hours)\n\nTimestep: 8940000\nmean reward (100 episodes): 369.7500\nbest mean reward: 390.4400\ncurrent episode reward: 417.0000\nepisodes: 9997\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38865.8 seconds (10.80 hours)\n\nTimestep: 8950000\nmean reward (100 episodes): 367.3400\nbest mean reward: 390.4400\ncurrent episode reward: 415.0000\nepisodes: 10002\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38914.5 seconds (10.81 hours)\n\nTimestep: 8960000\nmean reward (100 episodes): 370.0100\nbest mean reward: 390.4400\ncurrent episode reward: 418.0000\nepisodes: 10006\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38959.4 seconds (10.82 hours)\n\nTimestep: 8970000\nmean reward (100 episodes): 369.0200\nbest mean reward: 390.4400\ncurrent episode reward: 200.0000\nepisodes: 10009\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39003.5 seconds (10.83 hours)\n\nTimestep: 8980000\nmean reward (100 episodes): 368.3000\nbest mean reward: 390.4400\ncurrent episode reward: 428.0000\nepisodes: 10013\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39047.9 seconds (10.85 hours)\n\nTimestep: 8990000\nmean reward (100 episodes): 370.2100\nbest mean reward: 390.4400\ncurrent episode reward: 431.0000\nepisodes: 10016\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39092.5 seconds (10.86 hours)\n\nTimestep: 9000000\nmean reward (100 episodes): 373.9900\nbest mean reward: 390.4400\ncurrent episode reward: 416.0000\nepisodes: 10020\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39136.8 seconds (10.87 hours)\n\nTimestep: 9010000\nmean reward (100 episodes): 374.3900\nbest mean reward: 390.4400\ncurrent episode reward: 417.0000\nepisodes: 10022\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39180.5 seconds (10.88 hours)\n\nTimestep: 9020000\nmean reward (100 episodes): 375.8500\nbest mean reward: 390.4400\ncurrent episode reward: 393.0000\nepisodes: 10026\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39224.8 seconds (10.90 hours)\n\nTimestep: 9030000\nmean reward (100 episodes): 376.2400\nbest mean reward: 390.4400\ncurrent episode reward: 428.0000\nepisodes: 10031\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39269.5 seconds (10.91 hours)\n\nTimestep: 9040000\nmean reward (100 episodes): 375.5000\nbest mean reward: 390.4400\ncurrent episode reward: 399.0000\nepisodes: 10035\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39314.0 seconds (10.92 hours)\n\nTimestep: 9050000\nmean reward (100 episodes): 377.6800\nbest mean reward: 390.4400\ncurrent episode reward: 344.0000\nepisodes: 10038\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39357.7 seconds (10.93 hours)\n\nTimestep: 9060000\nmean reward (100 episodes): 377.6600\nbest mean reward: 390.4400\ncurrent episode reward: 422.0000\nepisodes: 10040\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39402.2 seconds (10.95 hours)\n\nTimestep: 9070000\nmean reward (100 episodes): 378.3600\nbest mean reward: 390.4400\ncurrent episode reward: 424.0000\nepisodes: 10044\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39446.2 seconds (10.96 hours)\n\nTimestep: 9080000\nmean reward (100 episodes): 378.7600\nbest mean reward: 390.4400\ncurrent episode reward: 398.0000\nepisodes: 10048\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39490.9 seconds (10.97 hours)\n\nTimestep: 9090000\nmean reward (100 episodes): 377.4600\nbest mean reward: 390.4400\ncurrent episode reward: 306.0000\nepisodes: 10052\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39535.7 seconds (10.98 hours)\n\nTimestep: 9100000\nmean reward (100 episodes): 380.0800\nbest mean reward: 390.4400\ncurrent episode reward: 791.0000\nepisodes: 10055\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39580.6 seconds (10.99 hours)\n\nTimestep: 9110000\nmean reward (100 episodes): 377.6900\nbest mean reward: 390.4400\ncurrent episode reward: 424.0000\nepisodes: 10059\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39625.4 seconds (11.01 hours)\n\nTimestep: 9120000\nmean reward (100 episodes): 376.9200\nbest mean reward: 390.4400\ncurrent episode reward: 459.0000\nepisodes: 10063\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39670.2 seconds (11.02 hours)\n\nTimestep: 9130000\nmean reward (100 episodes): 379.0200\nbest mean reward: 390.4400\ncurrent episode reward: 412.0000\nepisodes: 10067\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39714.6 seconds (11.03 hours)\n\nTimestep: 9140000\nmean reward (100 episodes): 379.2900\nbest mean reward: 390.4400\ncurrent episode reward: 401.0000\nepisodes: 10070\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39758.8 seconds (11.04 hours)\n\nTimestep: 9150000\nmean reward (100 episodes): 379.9300\nbest mean reward: 390.4400\ncurrent episode reward: 420.0000\nepisodes: 10072\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39803.5 seconds (11.06 hours)\n\nTimestep: 9160000\nmean reward (100 episodes): 382.5100\nbest mean reward: 390.4400\ncurrent episode reward: 423.0000\nepisodes: 10075\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39847.6 seconds (11.07 hours)\n\nTimestep: 9170000\nmean reward (100 episodes): 381.8100\nbest mean reward: 390.4400\ncurrent episode reward: 357.0000\nepisodes: 10078\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39892.8 seconds (11.08 hours)\n\nTimestep: 9180000\nmean reward (100 episodes): 385.0900\nbest mean reward: 390.4400\ncurrent episode reward: 412.0000\nepisodes: 10082\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39937.5 seconds (11.09 hours)\n\nTimestep: 9190000\nmean reward (100 episodes): 388.0000\nbest mean reward: 390.4400\ncurrent episode reward: 667.0000\nepisodes: 10085\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39981.5 seconds (11.11 hours)\n\nTimestep: 9200000\nmean reward (100 episodes): 382.6500\nbest mean reward: 390.4400\ncurrent episode reward: 92.0000\nepisodes: 10090\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40025.8 seconds (11.12 hours)\n\nTimestep: 9210000\nmean reward (100 episodes): 383.5000\nbest mean reward: 390.4400\ncurrent episode reward: 419.0000\nepisodes: 10093\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40070.5 seconds (11.13 hours)\n\nTimestep: 9220000\nmean reward (100 episodes): 388.0300\nbest mean reward: 390.4400\ncurrent episode reward: 342.0000\nepisodes: 10096\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40114.8 seconds (11.14 hours)\n\nTimestep: 9230000\nmean reward (100 episodes): 390.0100\nbest mean reward: 390.4400\ncurrent episode reward: 379.0000\nepisodes: 10099\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40158.3 seconds (11.16 hours)\n\nTimestep: 9240000\nmean reward (100 episodes): 391.1600\nbest mean reward: 391.1600\ncurrent episode reward: 434.0000\nepisodes: 10103\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40203.3 seconds (11.17 hours)\n\nTimestep: 9250000\nmean reward (100 episodes): 391.4500\nbest mean reward: 391.6900\ncurrent episode reward: 387.0000\nepisodes: 10105\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40248.1 seconds (11.18 hours)\n\nTimestep: 9260000\nmean reward (100 episodes): 394.7600\nbest mean reward: 394.7600\ncurrent episode reward: 328.0000\nepisodes: 10110\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40292.7 seconds (11.19 hours)\n\nTimestep: 9270000\nmean reward (100 episodes): 394.4500\nbest mean reward: 394.9400\ncurrent episode reward: 393.0000\nepisodes: 10113\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40337.2 seconds (11.20 hours)\n\nTimestep: 9280000\nmean reward (100 episodes): 396.7000\nbest mean reward: 397.5100\ncurrent episode reward: 402.0000\nepisodes: 10117\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40381.7 seconds (11.22 hours)\n\nTimestep: 9290000\nmean reward (100 episodes): 396.6500\nbest mean reward: 397.5100\ncurrent episode reward: 418.0000\nepisodes: 10119\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40426.2 seconds (11.23 hours)\n\nTimestep: 9300000\nmean reward (100 episodes): 395.8000\nbest mean reward: 397.5100\ncurrent episode reward: 380.0000\nepisodes: 10122\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40470.4 seconds (11.24 hours)\n\nTimestep: 9310000\nmean reward (100 episodes): 390.8900\nbest mean reward: 397.5100\ncurrent episode reward: 381.0000\nepisodes: 10127\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40515.2 seconds (11.25 hours)\n\nTimestep: 9320000\nmean reward (100 episodes): 393.2000\nbest mean reward: 397.5100\ncurrent episode reward: 411.0000\nepisodes: 10130\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40559.1 seconds (11.27 hours)\n\nTimestep: 9330000\nmean reward (100 episodes): 393.1800\nbest mean reward: 397.5100\ncurrent episode reward: 369.0000\nepisodes: 10133\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40602.6 seconds (11.28 hours)\n\nTimestep: 9340000\nmean reward (100 episodes): 393.2500\nbest mean reward: 397.5100\ncurrent episode reward: 425.0000\nepisodes: 10138\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40646.8 seconds (11.29 hours)\n\nTimestep: 9350000\nmean reward (100 episodes): 392.7300\nbest mean reward: 397.5100\ncurrent episode reward: 398.0000\nepisodes: 10140\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40690.7 seconds (11.30 hours)\n\nTimestep: 9360000\nmean reward (100 episodes): 392.8300\nbest mean reward: 397.5100\ncurrent episode reward: 125.0000\nepisodes: 10144\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40735.9 seconds (11.32 hours)\n\nTimestep: 9370000\nmean reward (100 episodes): 391.9300\nbest mean reward: 397.5100\ncurrent episode reward: 405.0000\nepisodes: 10149\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40780.4 seconds (11.33 hours)\n\nTimestep: 9380000\nmean reward (100 episodes): 392.6500\nbest mean reward: 397.5100\ncurrent episode reward: 410.0000\nepisodes: 10153\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40825.4 seconds (11.34 hours)\n\nTimestep: 9390000\nmean reward (100 episodes): 390.0800\nbest mean reward: 397.5100\ncurrent episode reward: 421.0000\nepisodes: 10156\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40869.9 seconds (11.35 hours)\n\nTimestep: 9400000\nmean reward (100 episodes): 390.3300\nbest mean reward: 397.5100\ncurrent episode reward: 428.0000\nepisodes: 10159\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40914.4 seconds (11.37 hours)\n\nTimestep: 9410000\nmean reward (100 episodes): 391.8900\nbest mean reward: 397.5100\ncurrent episode reward: 300.0000\nepisodes: 10164\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40959.3 seconds (11.38 hours)\n\nTimestep: 9420000\nmean reward (100 episodes): 392.0700\nbest mean reward: 397.5100\ncurrent episode reward: 420.0000\nepisodes: 10167\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41003.5 seconds (11.39 hours)\n\nTimestep: 9430000\nmean reward (100 episodes): 388.5700\nbest mean reward: 397.5100\ncurrent episode reward: 390.0000\nepisodes: 10171\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41049.4 seconds (11.40 hours)\n\nTimestep: 9440000\nmean reward (100 episodes): 387.6600\nbest mean reward: 397.5100\ncurrent episode reward: 369.0000\nepisodes: 10174\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41094.8 seconds (11.42 hours)\n\nTimestep: 9450000\nmean reward (100 episodes): 387.1900\nbest mean reward: 397.5100\ncurrent episode reward: 428.0000\nepisodes: 10177\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41138.8 seconds (11.43 hours)\n\nTimestep: 9460000\nmean reward (100 episodes): 384.8600\nbest mean reward: 397.5100\ncurrent episode reward: 417.0000\nepisodes: 10181\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41183.1 seconds (11.44 hours)\n\nTimestep: 9470000\nmean reward (100 episodes): 386.6700\nbest mean reward: 397.5100\ncurrent episode reward: 424.0000\nepisodes: 10184\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41228.0 seconds (11.45 hours)\n\nTimestep: 9480000\nmean reward (100 episodes): 386.8900\nbest mean reward: 397.5100\ncurrent episode reward: 437.0000\nepisodes: 10188\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41272.5 seconds (11.46 hours)\n\nTimestep: 9490000\nmean reward (100 episodes): 394.2400\nbest mean reward: 397.5100\ncurrent episode reward: 420.0000\nepisodes: 10191\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41317.0 seconds (11.48 hours)\n\nTimestep: 9500000\nmean reward (100 episodes): 395.2000\nbest mean reward: 397.5100\ncurrent episode reward: 366.0000\nepisodes: 10194\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41361.6 seconds (11.49 hours)\n\nTimestep: 9510000\nmean reward (100 episodes): 389.2800\nbest mean reward: 397.5100\ncurrent episode reward: 131.0000\nepisodes: 10197\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41406.2 seconds (11.50 hours)\n\nTimestep: 9520000\nmean reward (100 episodes): 389.8800\nbest mean reward: 397.5100\ncurrent episode reward: 421.0000\nepisodes: 10201\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41451.3 seconds (11.51 hours)\n\nTimestep: 9530000\nmean reward (100 episodes): 386.7600\nbest mean reward: 397.5100\ncurrent episode reward: 415.0000\nepisodes: 10205\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41495.1 seconds (11.53 hours)\n\nTimestep: 9540000\nmean reward (100 episodes): 387.7400\nbest mean reward: 397.5100\ncurrent episode reward: 412.0000\nepisodes: 10209\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41539.4 seconds (11.54 hours)\n\nTimestep: 9550000\nmean reward (100 episodes): 387.4400\nbest mean reward: 397.5100\ncurrent episode reward: 412.0000\nepisodes: 10213\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41584.0 seconds (11.55 hours)\n\nTimestep: 9560000\nmean reward (100 episodes): 385.8800\nbest mean reward: 397.5100\ncurrent episode reward: 428.0000\nepisodes: 10215\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41629.0 seconds (11.56 hours)\n\nTimestep: 9570000\nmean reward (100 episodes): 386.6200\nbest mean reward: 397.5100\ncurrent episode reward: 297.0000\nepisodes: 10219\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41674.3 seconds (11.58 hours)\n\nTimestep: 9580000\nmean reward (100 episodes): 390.4500\nbest mean reward: 397.5100\ncurrent episode reward: 810.0000\nepisodes: 10222\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41718.7 seconds (11.59 hours)\n\nTimestep: 9590000\nmean reward (100 episodes): 396.2800\nbest mean reward: 397.5100\ncurrent episode reward: 427.0000\nepisodes: 10226\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41763.1 seconds (11.60 hours)\n\nTimestep: 9600000\nmean reward (100 episodes): 396.5200\nbest mean reward: 397.5100\ncurrent episode reward: 421.0000\nepisodes: 10228\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41807.9 seconds (11.61 hours)\n\nTimestep: 9610000\nmean reward (100 episodes): 394.2100\nbest mean reward: 397.5100\ncurrent episode reward: 194.0000\nepisodes: 10231\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41852.9 seconds (11.63 hours)\n\nTimestep: 9620000\nmean reward (100 episodes): 394.3000\nbest mean reward: 397.5100\ncurrent episode reward: 283.0000\nepisodes: 10235\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41897.9 seconds (11.64 hours)\n\nTimestep: 9630000\nmean reward (100 episodes): 394.2700\nbest mean reward: 397.5100\ncurrent episode reward: 406.0000\nepisodes: 10238\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41942.4 seconds (11.65 hours)\n\nTimestep: 9640000\nmean reward (100 episodes): 395.5100\nbest mean reward: 397.5100\ncurrent episode reward: 424.0000\nepisodes: 10242\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41986.6 seconds (11.66 hours)\n\nTimestep: 9650000\nmean reward (100 episodes): 395.7000\nbest mean reward: 398.0700\ncurrent episode reward: 375.0000\nepisodes: 10247\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42031.8 seconds (11.68 hours)\n\nTimestep: 9660000\nmean reward (100 episodes): 395.3000\nbest mean reward: 398.0700\ncurrent episode reward: 331.0000\nepisodes: 10251\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42076.2 seconds (11.69 hours)\n\nTimestep: 9670000\nmean reward (100 episodes): 396.6700\nbest mean reward: 398.0700\ncurrent episode reward: 412.0000\nepisodes: 10254\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42120.8 seconds (11.70 hours)\n\nTimestep: 9680000\nmean reward (100 episodes): 397.4900\nbest mean reward: 398.0700\ncurrent episode reward: 416.0000\nepisodes: 10257\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42165.5 seconds (11.71 hours)\n\nTimestep: 9690000\nmean reward (100 episodes): 396.8500\nbest mean reward: 398.0700\ncurrent episode reward: 334.0000\nepisodes: 10260\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42209.8 seconds (11.72 hours)\n\nTimestep: 9700000\nmean reward (100 episodes): 394.9400\nbest mean reward: 398.0700\ncurrent episode reward: 401.0000\nepisodes: 10265\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42254.6 seconds (11.74 hours)\n\nTimestep: 9710000\nmean reward (100 episodes): 396.9900\nbest mean reward: 398.0700\ncurrent episode reward: 626.0000\nepisodes: 10269\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42298.9 seconds (11.75 hours)\n\nTimestep: 9713708\nmean reward (100 episodes): 395.5300\nbest mean reward: 398.0700\ncurrent episode reward: 253.0000\nepisodes: 10270\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42315.7 seconds (11.75 hours)\n"
  },
  {
    "path": "dqn/logs_text/Breakout_s002.text",
    "content": "('AVAILABLE GPUS: ', [u'device: 0, name: TITAN X (Pascal), pci bus id: 0000:01:00.0'])\ntask = Task<env_id=BreakoutNoFrameskip-v3 trials=2 max_timesteps=40000000 max_seconds=None reward_floor=1.7 reward_ceiling=800.0>\n\nTimestep: 60000\nmean reward (100 episodes): 1.5100\nbest mean reward: 1.6200\ncurrent episode reward: 4.0000\nepisodes: 339\nexploration: 0.94600\nlearning_rate: 0.00010\nelapsed time: 100.0 seconds (0.03 hours)\n\nTimestep: 70000\nmean reward (100 episodes): 1.6100\nbest mean reward: 1.6200\ncurrent episode reward: 2.0000\nepisodes: 397\nexploration: 0.93700\nlearning_rate: 0.00010\nelapsed time: 133.9 seconds (0.04 hours)\n\nTimestep: 80000\nmean reward (100 episodes): 1.4200\nbest mean reward: 1.6200\ncurrent episode reward: 0.0000\nepisodes: 455\nexploration: 0.92800\nlearning_rate: 0.00010\nelapsed time: 167.1 seconds (0.05 hours)\n\nTimestep: 90000\nmean reward (100 episodes): 1.6300\nbest mean reward: 1.7400\ncurrent episode reward: 3.0000\nepisodes: 508\nexploration: 0.91900\nlearning_rate: 0.00010\nelapsed time: 200.3 seconds (0.06 hours)\n\nTimestep: 100000\nmean reward (100 episodes): 1.7200\nbest mean reward: 1.7600\ncurrent episode reward: 4.0000\nepisodes: 564\nexploration: 0.91000\nlearning_rate: 0.00010\nelapsed time: 234.3 seconds (0.07 hours)\n\nTimestep: 110000\nmean reward (100 episodes): 1.6800\nbest mean reward: 1.8100\ncurrent episode reward: 0.0000\nepisodes: 619\nexploration: 0.90100\nlearning_rate: 0.00010\nelapsed time: 268.2 seconds (0.07 hours)\n\nTimestep: 120000\nmean reward (100 episodes): 1.6500\nbest mean reward: 1.8100\ncurrent episode reward: 0.0000\nepisodes: 672\nexploration: 0.89200\nlearning_rate: 0.00010\nelapsed time: 301.6 seconds (0.08 hours)\n\nTimestep: 130000\nmean reward (100 episodes): 1.8200\nbest mean reward: 1.9000\ncurrent episode reward: 0.0000\nepisodes: 726\nexploration: 0.88300\nlearning_rate: 0.00010\nelapsed time: 335.2 seconds (0.09 hours)\n\nTimestep: 140000\nmean reward (100 episodes): 1.6900\nbest mean reward: 1.9500\ncurrent episode reward: 1.0000\nepisodes: 782\nexploration: 0.87400\nlearning_rate: 0.00010\nelapsed time: 369.6 seconds (0.10 hours)\n\nTimestep: 150000\nmean reward (100 episodes): 1.4600\nbest mean reward: 1.9500\ncurrent episode reward: 0.0000\nepisodes: 839\nexploration: 0.86500\nlearning_rate: 0.00010\nelapsed time: 403.5 seconds (0.11 hours)\n\nTimestep: 160000\nmean reward (100 episodes): 1.4100\nbest mean reward: 1.9500\ncurrent episode reward: 4.0000\nepisodes: 899\nexploration: 0.85600\nlearning_rate: 0.00010\nelapsed time: 437.4 seconds (0.12 hours)\n\nTimestep: 170000\nmean reward (100 episodes): 1.4100\nbest mean reward: 1.9500\ncurrent episode reward: 2.0000\nepisodes: 958\nexploration: 0.84700\nlearning_rate: 0.00010\nelapsed time: 471.8 seconds (0.13 hours)\n\nTimestep: 180000\nmean reward (100 episodes): 1.5900\nbest mean reward: 1.9500\ncurrent episode reward: 2.0000\nepisodes: 1010\nexploration: 0.83800\nlearning_rate: 0.00010\nelapsed time: 506.6 seconds (0.14 hours)\n\nTimestep: 190000\nmean reward (100 episodes): 1.7500\nbest mean reward: 1.9500\ncurrent episode reward: 1.0000\nepisodes: 1064\nexploration: 0.82900\nlearning_rate: 0.00010\nelapsed time: 540.8 seconds (0.15 hours)\n\nTimestep: 200000\nmean reward (100 episodes): 1.8000\nbest mean reward: 1.9500\ncurrent episode reward: 6.0000\nepisodes: 1116\nexploration: 0.82000\nlearning_rate: 0.00010\nelapsed time: 575.1 seconds (0.16 hours)\n\nTimestep: 210000\nmean reward (100 episodes): 2.3800\nbest mean reward: 2.3800\ncurrent episode reward: 8.0000\nepisodes: 1159\nexploration: 0.81100\nlearning_rate: 0.00010\nelapsed time: 609.4 seconds (0.17 hours)\n\nTimestep: 220000\nmean reward (100 episodes): 2.5500\nbest mean reward: 2.5700\ncurrent episode reward: 1.0000\nepisodes: 1207\nexploration: 0.80200\nlearning_rate: 0.00010\nelapsed time: 643.8 seconds (0.18 hours)\n\nTimestep: 230000\nmean reward (100 episodes): 2.5400\nbest mean reward: 2.6600\ncurrent episode reward: 3.0000\nepisodes: 1252\nexploration: 0.79300\nlearning_rate: 0.00010\nelapsed time: 678.4 seconds (0.19 hours)\n\nTimestep: 240000\nmean reward (100 episodes): 2.6000\nbest mean reward: 2.6600\ncurrent episode reward: 1.0000\nepisodes: 1300\nexploration: 0.78400\nlearning_rate: 0.00010\nelapsed time: 713.1 seconds (0.20 hours)\n\nTimestep: 250000\nmean reward (100 episodes): 2.9000\nbest mean reward: 2.9300\ncurrent episode reward: 0.0000\nepisodes: 1340\nexploration: 0.77500\nlearning_rate: 0.00010\nelapsed time: 747.5 seconds (0.21 hours)\n\nTimestep: 260000\nmean reward (100 episodes): 3.2200\nbest mean reward: 3.2400\ncurrent episode reward: 4.0000\nepisodes: 1380\nexploration: 0.76600\nlearning_rate: 0.00010\nelapsed time: 782.4 seconds (0.22 hours)\n\nTimestep: 270000\nmean reward (100 episodes): 3.4600\nbest mean reward: 3.5400\ncurrent episode reward: 0.0000\nepisodes: 1419\nexploration: 0.75700\nlearning_rate: 0.00010\nelapsed time: 817.0 seconds (0.23 hours)\n\nTimestep: 280000\nmean reward (100 episodes): 3.1700\nbest mean reward: 3.5400\ncurrent episode reward: 1.0000\nepisodes: 1462\nexploration: 0.74800\nlearning_rate: 0.00010\nelapsed time: 851.9 seconds (0.24 hours)\n\nTimestep: 290000\nmean reward (100 episodes): 3.7700\nbest mean reward: 3.8500\ncurrent episode reward: 2.0000\nepisodes: 1495\nexploration: 0.73900\nlearning_rate: 0.00010\nelapsed time: 887.0 seconds (0.25 hours)\n\nTimestep: 300000\nmean reward (100 episodes): 4.1400\nbest mean reward: 4.1400\ncurrent episode reward: 2.0000\nepisodes: 1530\nexploration: 0.73000\nlearning_rate: 0.00010\nelapsed time: 921.6 seconds (0.26 hours)\n\nTimestep: 310000\nmean reward (100 episodes): 4.6800\nbest mean reward: 4.6800\ncurrent episode reward: 7.0000\nepisodes: 1564\nexploration: 0.72100\nlearning_rate: 0.00010\nelapsed time: 956.6 seconds (0.27 hours)\n\nTimestep: 320000\nmean reward (100 episodes): 4.3800\nbest mean reward: 4.7600\ncurrent episode reward: 2.0000\nepisodes: 1600\nexploration: 0.71200\nlearning_rate: 0.00010\nelapsed time: 991.8 seconds (0.28 hours)\n\nTimestep: 330000\nmean reward (100 episodes): 4.8400\nbest mean reward: 4.8400\ncurrent episode reward: 4.0000\nepisodes: 1630\nexploration: 0.70300\nlearning_rate: 0.00010\nelapsed time: 1027.2 seconds (0.29 hours)\n\nTimestep: 340000\nmean reward (100 episodes): 4.9600\nbest mean reward: 5.0900\ncurrent episode reward: 2.0000\nepisodes: 1664\nexploration: 0.69400\nlearning_rate: 0.00010\nelapsed time: 1062.6 seconds (0.30 hours)\n\nTimestep: 350000\nmean reward (100 episodes): 4.9100\nbest mean reward: 5.0900\ncurrent episode reward: 9.0000\nepisodes: 1699\nexploration: 0.68500\nlearning_rate: 0.00010\nelapsed time: 1098.3 seconds (0.31 hours)\n\nTimestep: 360000\nmean reward (100 episodes): 4.5900\nbest mean reward: 5.0900\ncurrent episode reward: 8.0000\nepisodes: 1733\nexploration: 0.67600\nlearning_rate: 0.00010\nelapsed time: 1133.9 seconds (0.31 hours)\n\nTimestep: 370000\nmean reward (100 episodes): 4.3700\nbest mean reward: 5.0900\ncurrent episode reward: 6.0000\nepisodes: 1770\nexploration: 0.66700\nlearning_rate: 0.00010\nelapsed time: 1169.9 seconds (0.32 hours)\n\nTimestep: 380000\nmean reward (100 episodes): 4.4200\nbest mean reward: 5.0900\ncurrent episode reward: 6.0000\nepisodes: 1805\nexploration: 0.65800\nlearning_rate: 0.00010\nelapsed time: 1205.7 seconds (0.33 hours)\n\nTimestep: 390000\nmean reward (100 episodes): 4.2800\nbest mean reward: 5.0900\ncurrent episode reward: 5.0000\nepisodes: 1839\nexploration: 0.64900\nlearning_rate: 0.00010\nelapsed time: 1242.1 seconds (0.35 hours)\n\nTimestep: 400000\nmean reward (100 episodes): 4.8100\nbest mean reward: 5.0900\ncurrent episode reward: 2.0000\nepisodes: 1871\nexploration: 0.64000\nlearning_rate: 0.00010\nelapsed time: 1278.1 seconds (0.36 hours)\n\nTimestep: 410000\nmean reward (100 episodes): 5.0400\nbest mean reward: 5.2300\ncurrent episode reward: 3.0000\nepisodes: 1904\nexploration: 0.63100\nlearning_rate: 0.00010\nelapsed time: 1314.3 seconds (0.37 hours)\n\nTimestep: 420000\nmean reward (100 episodes): 5.4300\nbest mean reward: 5.4900\ncurrent episode reward: 8.0000\nepisodes: 1933\nexploration: 0.62200\nlearning_rate: 0.00010\nelapsed time: 1350.8 seconds (0.38 hours)\n\nTimestep: 430000\nmean reward (100 episodes): 5.4600\nbest mean reward: 5.6000\ncurrent episode reward: 3.0000\nepisodes: 1963\nexploration: 0.61300\nlearning_rate: 0.00010\nelapsed time: 1387.1 seconds (0.39 hours)\n\nTimestep: 440000\nmean reward (100 episodes): 5.9000\nbest mean reward: 5.9400\ncurrent episode reward: 5.0000\nepisodes: 1991\nexploration: 0.60400\nlearning_rate: 0.00010\nelapsed time: 1423.4 seconds (0.40 hours)\n\nTimestep: 450000\nmean reward (100 episodes): 6.3000\nbest mean reward: 6.4500\ncurrent episode reward: 4.0000\nepisodes: 2020\nexploration: 0.59500\nlearning_rate: 0.00010\nelapsed time: 1462.4 seconds (0.41 hours)\n\nTimestep: 460000\nmean reward (100 episodes): 6.4500\nbest mean reward: 6.5800\ncurrent episode reward: 3.0000\nepisodes: 2047\nexploration: 0.58600\nlearning_rate: 0.00010\nelapsed time: 1500.2 seconds (0.42 hours)\n\nTimestep: 470000\nmean reward (100 episodes): 6.7700\nbest mean reward: 6.9400\ncurrent episode reward: 6.0000\nepisodes: 2075\nexploration: 0.57700\nlearning_rate: 0.00010\nelapsed time: 1537.7 seconds (0.43 hours)\n\nTimestep: 480000\nmean reward (100 episodes): 6.6000\nbest mean reward: 6.9400\ncurrent episode reward: 9.0000\nepisodes: 2103\nexploration: 0.56800\nlearning_rate: 0.00010\nelapsed time: 1575.3 seconds (0.44 hours)\n\nTimestep: 490000\nmean reward (100 episodes): 6.7900\nbest mean reward: 6.9400\ncurrent episode reward: 7.0000\nepisodes: 2130\nexploration: 0.55900\nlearning_rate: 0.00010\nelapsed time: 1612.7 seconds (0.45 hours)\n\nTimestep: 500000\nmean reward (100 episodes): 6.7800\nbest mean reward: 6.9400\ncurrent episode reward: 7.0000\nepisodes: 2159\nexploration: 0.55000\nlearning_rate: 0.00010\nelapsed time: 1651.1 seconds (0.46 hours)\n\nTimestep: 510000\nmean reward (100 episodes): 6.6800\nbest mean reward: 6.9400\ncurrent episode reward: 8.0000\nepisodes: 2187\nexploration: 0.54100\nlearning_rate: 0.00010\nelapsed time: 1689.1 seconds (0.47 hours)\n\nTimestep: 520000\nmean reward (100 episodes): 6.4600\nbest mean reward: 6.9400\ncurrent episode reward: 11.0000\nepisodes: 2217\nexploration: 0.53200\nlearning_rate: 0.00010\nelapsed time: 1727.1 seconds (0.48 hours)\n\nTimestep: 530000\nmean reward (100 episodes): 6.6100\nbest mean reward: 6.9400\ncurrent episode reward: 6.0000\nepisodes: 2243\nexploration: 0.52300\nlearning_rate: 0.00010\nelapsed time: 1765.8 seconds (0.49 hours)\n\nTimestep: 540000\nmean reward (100 episodes): 6.8300\nbest mean reward: 6.9400\ncurrent episode reward: 7.0000\nepisodes: 2269\nexploration: 0.51400\nlearning_rate: 0.00010\nelapsed time: 1803.9 seconds (0.50 hours)\n\nTimestep: 550000\nmean reward (100 episodes): 7.0800\nbest mean reward: 7.0900\ncurrent episode reward: 4.0000\nepisodes: 2296\nexploration: 0.50500\nlearning_rate: 0.00010\nelapsed time: 1842.5 seconds (0.51 hours)\n\nTimestep: 560000\nmean reward (100 episodes): 7.7100\nbest mean reward: 7.7400\ncurrent episode reward: 3.0000\nepisodes: 2321\nexploration: 0.49600\nlearning_rate: 0.00010\nelapsed time: 1880.8 seconds (0.52 hours)\n\nTimestep: 570000\nmean reward (100 episodes): 7.8200\nbest mean reward: 7.8300\ncurrent episode reward: 10.0000\nepisodes: 2346\nexploration: 0.48700\nlearning_rate: 0.00010\nelapsed time: 1919.5 seconds (0.53 hours)\n\nTimestep: 580000\nmean reward (100 episodes): 7.9300\nbest mean reward: 8.2800\ncurrent episode reward: 10.0000\nepisodes: 2370\nexploration: 0.47800\nlearning_rate: 0.00010\nelapsed time: 1958.3 seconds (0.54 hours)\n\nTimestep: 590000\nmean reward (100 episodes): 8.1400\nbest mean reward: 8.3000\ncurrent episode reward: 6.0000\nepisodes: 2393\nexploration: 0.46900\nlearning_rate: 0.00010\nelapsed time: 1997.5 seconds (0.55 hours)\n\nTimestep: 600000\nmean reward (100 episodes): 8.4800\nbest mean reward: 8.6400\ncurrent episode reward: 19.0000\nepisodes: 2414\nexploration: 0.46000\nlearning_rate: 0.00010\nelapsed time: 2035.7 seconds (0.57 hours)\n\nTimestep: 610000\nmean reward (100 episodes): 8.7400\nbest mean reward: 8.7400\ncurrent episode reward: 8.0000\nepisodes: 2439\nexploration: 0.45100\nlearning_rate: 0.00010\nelapsed time: 2075.0 seconds (0.58 hours)\n\nTimestep: 620000\nmean reward (100 episodes): 8.5400\nbest mean reward: 8.8000\ncurrent episode reward: 17.0000\nepisodes: 2463\nexploration: 0.44200\nlearning_rate: 0.00010\nelapsed time: 2114.2 seconds (0.59 hours)\n\nTimestep: 630000\nmean reward (100 episodes): 9.2300\nbest mean reward: 9.2300\ncurrent episode reward: 9.0000\nepisodes: 2485\nexploration: 0.43300\nlearning_rate: 0.00010\nelapsed time: 2153.0 seconds (0.60 hours)\n\nTimestep: 640000\nmean reward (100 episodes): 9.0800\nbest mean reward: 9.3300\ncurrent episode reward: 5.0000\nepisodes: 2508\nexploration: 0.42400\nlearning_rate: 0.00010\nelapsed time: 2192.3 seconds (0.61 hours)\n\nTimestep: 650000\nmean reward (100 episodes): 9.0000\nbest mean reward: 9.3300\ncurrent episode reward: 10.0000\nepisodes: 2532\nexploration: 0.41500\nlearning_rate: 0.00010\nelapsed time: 2231.9 seconds (0.62 hours)\n\nTimestep: 660000\nmean reward (100 episodes): 9.0200\nbest mean reward: 9.3300\ncurrent episode reward: 7.0000\nepisodes: 2554\nexploration: 0.40600\nlearning_rate: 0.00010\nelapsed time: 2271.1 seconds (0.63 hours)\n\nTimestep: 670000\nmean reward (100 episodes): 8.9300\nbest mean reward: 9.3300\ncurrent episode reward: 5.0000\nepisodes: 2577\nexploration: 0.39700\nlearning_rate: 0.00010\nelapsed time: 2310.2 seconds (0.64 hours)\n\nTimestep: 680000\nmean reward (100 episodes): 9.1500\nbest mean reward: 9.3300\ncurrent episode reward: 17.0000\nepisodes: 2598\nexploration: 0.38800\nlearning_rate: 0.00010\nelapsed time: 2349.9 seconds (0.65 hours)\n\nTimestep: 690000\nmean reward (100 episodes): 9.5400\nbest mean reward: 9.5600\ncurrent episode reward: 9.0000\nepisodes: 2618\nexploration: 0.37900\nlearning_rate: 0.00010\nelapsed time: 2389.8 seconds (0.66 hours)\n\nTimestep: 700000\nmean reward (100 episodes): 10.0900\nbest mean reward: 10.1100\ncurrent episode reward: 8.0000\nepisodes: 2639\nexploration: 0.37000\nlearning_rate: 0.00010\nelapsed time: 2429.4 seconds (0.67 hours)\n\nTimestep: 710000\nmean reward (100 episodes): 10.5800\nbest mean reward: 10.5800\ncurrent episode reward: 20.0000\nepisodes: 2659\nexploration: 0.36100\nlearning_rate: 0.00010\nelapsed time: 2469.7 seconds (0.69 hours)\n\nTimestep: 720000\nmean reward (100 episodes): 11.2900\nbest mean reward: 11.2900\ncurrent episode reward: 15.0000\nepisodes: 2679\nexploration: 0.35200\nlearning_rate: 0.00010\nelapsed time: 2509.2 seconds (0.70 hours)\n\nTimestep: 730000\nmean reward (100 episodes): 11.8200\nbest mean reward: 11.8200\ncurrent episode reward: 12.0000\nepisodes: 2697\nexploration: 0.34300\nlearning_rate: 0.00010\nelapsed time: 2549.2 seconds (0.71 hours)\n\nTimestep: 740000\nmean reward (100 episodes): 12.5700\nbest mean reward: 12.5700\ncurrent episode reward: 9.0000\nepisodes: 2713\nexploration: 0.33400\nlearning_rate: 0.00010\nelapsed time: 2589.8 seconds (0.72 hours)\n\nTimestep: 750000\nmean reward (100 episodes): 12.9200\nbest mean reward: 12.9600\ncurrent episode reward: 7.0000\nepisodes: 2732\nexploration: 0.32500\nlearning_rate: 0.00010\nelapsed time: 2630.1 seconds (0.73 hours)\n\nTimestep: 760000\nmean reward (100 episodes): 13.6100\nbest mean reward: 13.6100\ncurrent episode reward: 17.0000\nepisodes: 2749\nexploration: 0.31600\nlearning_rate: 0.00010\nelapsed time: 2670.9 seconds (0.74 hours)\n\nTimestep: 770000\nmean reward (100 episodes): 14.1000\nbest mean reward: 14.1000\ncurrent episode reward: 13.0000\nepisodes: 2767\nexploration: 0.30700\nlearning_rate: 0.00010\nelapsed time: 2711.3 seconds (0.75 hours)\n\nTimestep: 780000\nmean reward (100 episodes): 14.5100\nbest mean reward: 14.5100\ncurrent episode reward: 17.0000\nepisodes: 2783\nexploration: 0.29800\nlearning_rate: 0.00010\nelapsed time: 2753.5 seconds (0.76 hours)\n\nTimestep: 790000\nmean reward (100 episodes): 14.7100\nbest mean reward: 14.7500\ncurrent episode reward: 12.0000\nepisodes: 2801\nexploration: 0.28900\nlearning_rate: 0.00010\nelapsed time: 2795.1 seconds (0.78 hours)\n\nTimestep: 800000\nmean reward (100 episodes): 14.8500\nbest mean reward: 14.8500\ncurrent episode reward: 16.0000\nepisodes: 2816\nexploration: 0.28000\nlearning_rate: 0.00010\nelapsed time: 2836.6 seconds (0.79 hours)\n\nTimestep: 810000\nmean reward (100 episodes): 15.4600\nbest mean reward: 15.4600\ncurrent episode reward: 21.0000\nepisodes: 2831\nexploration: 0.27100\nlearning_rate: 0.00010\nelapsed time: 2878.6 seconds (0.80 hours)\n\nTimestep: 820000\nmean reward (100 episodes): 16.0600\nbest mean reward: 16.0600\ncurrent episode reward: 16.0000\nepisodes: 2847\nexploration: 0.26200\nlearning_rate: 0.00010\nelapsed time: 2921.0 seconds (0.81 hours)\n\nTimestep: 830000\nmean reward (100 episodes): 16.2000\nbest mean reward: 16.2900\ncurrent episode reward: 16.0000\nepisodes: 2864\nexploration: 0.25300\nlearning_rate: 0.00010\nelapsed time: 2962.7 seconds (0.82 hours)\n\nTimestep: 840000\nmean reward (100 episodes): 17.0000\nbest mean reward: 17.0000\ncurrent episode reward: 24.0000\nepisodes: 2878\nexploration: 0.24400\nlearning_rate: 0.00010\nelapsed time: 3004.4 seconds (0.83 hours)\n\nTimestep: 850000\nmean reward (100 episodes): 17.9300\nbest mean reward: 17.9300\ncurrent episode reward: 32.0000\nepisodes: 2891\nexploration: 0.23500\nlearning_rate: 0.00010\nelapsed time: 3046.0 seconds (0.85 hours)\n\nTimestep: 860000\nmean reward (100 episodes): 18.2800\nbest mean reward: 18.4500\ncurrent episode reward: 19.0000\nepisodes: 2906\nexploration: 0.22600\nlearning_rate: 0.00010\nelapsed time: 3087.1 seconds (0.86 hours)\n\nTimestep: 870000\nmean reward (100 episodes): 18.5600\nbest mean reward: 18.5600\ncurrent episode reward: 30.0000\nepisodes: 2922\nexploration: 0.21700\nlearning_rate: 0.00010\nelapsed time: 3128.7 seconds (0.87 hours)\n\nTimestep: 880000\nmean reward (100 episodes): 18.8600\nbest mean reward: 18.8600\ncurrent episode reward: 29.0000\nepisodes: 2936\nexploration: 0.20800\nlearning_rate: 0.00010\nelapsed time: 3170.4 seconds (0.88 hours)\n\nTimestep: 890000\nmean reward (100 episodes): 19.5600\nbest mean reward: 19.5600\ncurrent episode reward: 28.0000\nepisodes: 2949\nexploration: 0.19900\nlearning_rate: 0.00010\nelapsed time: 3212.4 seconds (0.89 hours)\n\nTimestep: 900000\nmean reward (100 episodes): 20.1700\nbest mean reward: 20.2700\ncurrent episode reward: 6.0000\nepisodes: 2963\nexploration: 0.19000\nlearning_rate: 0.00010\nelapsed time: 3255.4 seconds (0.90 hours)\n\nTimestep: 910000\nmean reward (100 episodes): 21.0100\nbest mean reward: 21.0100\ncurrent episode reward: 33.0000\nepisodes: 2975\nexploration: 0.18100\nlearning_rate: 0.00010\nelapsed time: 3297.6 seconds (0.92 hours)\n\nTimestep: 920000\nmean reward (100 episodes): 21.5900\nbest mean reward: 21.5900\ncurrent episode reward: 18.0000\nepisodes: 2987\nexploration: 0.17200\nlearning_rate: 0.00010\nelapsed time: 3340.8 seconds (0.93 hours)\n\nTimestep: 930000\nmean reward (100 episodes): 21.9800\nbest mean reward: 22.0900\ncurrent episode reward: 17.0000\nepisodes: 2998\nexploration: 0.16300\nlearning_rate: 0.00010\nelapsed time: 3384.0 seconds (0.94 hours)\n\nTimestep: 940000\nmean reward (100 episodes): 23.6200\nbest mean reward: 23.6200\ncurrent episode reward: 26.0000\nepisodes: 3010\nexploration: 0.15400\nlearning_rate: 0.00010\nelapsed time: 3429.7 seconds (0.95 hours)\n\nTimestep: 950000\nmean reward (100 episodes): 25.6700\nbest mean reward: 25.6700\ncurrent episode reward: 24.0000\nepisodes: 3021\nexploration: 0.14500\nlearning_rate: 0.00010\nelapsed time: 3472.7 seconds (0.96 hours)\n\nTimestep: 960000\nmean reward (100 episodes): 27.1600\nbest mean reward: 27.1600\ncurrent episode reward: 77.0000\nepisodes: 3031\nexploration: 0.13600\nlearning_rate: 0.00010\nelapsed time: 3516.2 seconds (0.98 hours)\n\nTimestep: 970000\nmean reward (100 episodes): 27.8800\nbest mean reward: 27.8800\ncurrent episode reward: 27.0000\nepisodes: 3043\nexploration: 0.12700\nlearning_rate: 0.00010\nelapsed time: 3559.8 seconds (0.99 hours)\n\nTimestep: 980000\nmean reward (100 episodes): 28.5900\nbest mean reward: 28.6200\ncurrent episode reward: 23.0000\nepisodes: 3054\nexploration: 0.11800\nlearning_rate: 0.00010\nelapsed time: 3603.1 seconds (1.00 hours)\n\nTimestep: 990000\nmean reward (100 episodes): 30.4000\nbest mean reward: 30.4000\ncurrent episode reward: 42.0000\nepisodes: 3063\nexploration: 0.10900\nlearning_rate: 0.00010\nelapsed time: 3646.6 seconds (1.01 hours)\n\nTimestep: 1000000\nmean reward (100 episodes): 31.4200\nbest mean reward: 31.4200\ncurrent episode reward: 37.0000\nepisodes: 3073\nexploration: 0.10000\nlearning_rate: 0.00010\nelapsed time: 3690.1 seconds (1.03 hours)\n\nTimestep: 1010000\nmean reward (100 episodes): 32.5200\nbest mean reward: 32.5400\ncurrent episode reward: 20.0000\nepisodes: 3083\nexploration: 0.09978\nlearning_rate: 0.00010\nelapsed time: 3734.1 seconds (1.04 hours)\n\nTimestep: 1020000\nmean reward (100 episodes): 33.1100\nbest mean reward: 33.1100\ncurrent episode reward: 37.0000\nepisodes: 3092\nexploration: 0.09955\nlearning_rate: 0.00010\nelapsed time: 3778.0 seconds (1.05 hours)\n\nTimestep: 1030000\nmean reward (100 episodes): 34.9400\nbest mean reward: 34.9400\ncurrent episode reward: 58.0000\nepisodes: 3102\nexploration: 0.09933\nlearning_rate: 0.00010\nelapsed time: 3822.1 seconds (1.06 hours)\n\nTimestep: 1040000\nmean reward (100 episodes): 35.8100\nbest mean reward: 35.8600\ncurrent episode reward: 34.0000\nepisodes: 3111\nexploration: 0.09910\nlearning_rate: 0.00010\nelapsed time: 3865.4 seconds (1.07 hours)\n\nTimestep: 1050000\nmean reward (100 episodes): 35.8700\nbest mean reward: 36.1100\ncurrent episode reward: 36.0000\nepisodes: 3121\nexploration: 0.09888\nlearning_rate: 0.00010\nelapsed time: 3908.8 seconds (1.09 hours)\n\nTimestep: 1060000\nmean reward (100 episodes): 37.1500\nbest mean reward: 37.1500\ncurrent episode reward: 25.0000\nepisodes: 3130\nexploration: 0.09865\nlearning_rate: 0.00010\nelapsed time: 3952.8 seconds (1.10 hours)\n\nTimestep: 1070000\nmean reward (100 episodes): 38.1000\nbest mean reward: 38.4700\ncurrent episode reward: 18.0000\nepisodes: 3139\nexploration: 0.09842\nlearning_rate: 0.00010\nelapsed time: 3996.8 seconds (1.11 hours)\n\nTimestep: 1080000\nmean reward (100 episodes): 40.0500\nbest mean reward: 40.0500\ncurrent episode reward: 47.0000\nepisodes: 3148\nexploration: 0.09820\nlearning_rate: 0.00010\nelapsed time: 4040.3 seconds (1.12 hours)\n\nTimestep: 1090000\nmean reward (100 episodes): 40.7000\nbest mean reward: 40.7300\ncurrent episode reward: 29.0000\nepisodes: 3157\nexploration: 0.09798\nlearning_rate: 0.00010\nelapsed time: 4083.5 seconds (1.13 hours)\n\nTimestep: 1100000\nmean reward (100 episodes): 40.7500\nbest mean reward: 41.1300\ncurrent episode reward: 15.0000\nepisodes: 3166\nexploration: 0.09775\nlearning_rate: 0.00010\nelapsed time: 4127.3 seconds (1.15 hours)\n\nTimestep: 1110000\nmean reward (100 episodes): 42.2200\nbest mean reward: 42.2200\ncurrent episode reward: 54.0000\nepisodes: 3175\nexploration: 0.09753\nlearning_rate: 0.00010\nelapsed time: 4170.4 seconds (1.16 hours)\n\nTimestep: 1120000\nmean reward (100 episodes): 43.2900\nbest mean reward: 43.2900\ncurrent episode reward: 30.0000\nepisodes: 3183\nexploration: 0.09730\nlearning_rate: 0.00010\nelapsed time: 4214.7 seconds (1.17 hours)\n\nTimestep: 1130000\nmean reward (100 episodes): 44.2100\nbest mean reward: 44.3900\ncurrent episode reward: 41.0000\nepisodes: 3192\nexploration: 0.09708\nlearning_rate: 0.00010\nelapsed time: 4259.0 seconds (1.18 hours)\n\nTimestep: 1140000\nmean reward (100 episodes): 45.4100\nbest mean reward: 45.4100\ncurrent episode reward: 50.0000\nepisodes: 3201\nexploration: 0.09685\nlearning_rate: 0.00010\nelapsed time: 4302.3 seconds (1.20 hours)\n\nTimestep: 1150000\nmean reward (100 episodes): 45.0600\nbest mean reward: 45.4100\ncurrent episode reward: 52.0000\nepisodes: 3211\nexploration: 0.09663\nlearning_rate: 0.00010\nelapsed time: 4346.1 seconds (1.21 hours)\n\nTimestep: 1160000\nmean reward (100 episodes): 45.7400\nbest mean reward: 45.7400\ncurrent episode reward: 49.0000\nepisodes: 3220\nexploration: 0.09640\nlearning_rate: 0.00010\nelapsed time: 4389.8 seconds (1.22 hours)\n\nTimestep: 1170000\nmean reward (100 episodes): 47.0400\nbest mean reward: 47.1500\ncurrent episode reward: 43.0000\nepisodes: 3227\nexploration: 0.09618\nlearning_rate: 0.00010\nelapsed time: 4434.1 seconds (1.23 hours)\n\nTimestep: 1180000\nmean reward (100 episodes): 47.1900\nbest mean reward: 47.5900\ncurrent episode reward: 38.0000\nepisodes: 3236\nexploration: 0.09595\nlearning_rate: 0.00010\nelapsed time: 4476.4 seconds (1.24 hours)\n\nTimestep: 1190000\nmean reward (100 episodes): 47.4500\nbest mean reward: 47.9400\ncurrent episode reward: 46.0000\nepisodes: 3245\nexploration: 0.09573\nlearning_rate: 0.00010\nelapsed time: 4519.7 seconds (1.26 hours)\n\nTimestep: 1200000\nmean reward (100 episodes): 48.7300\nbest mean reward: 48.7300\ncurrent episode reward: 65.0000\nepisodes: 3253\nexploration: 0.09550\nlearning_rate: 0.00010\nelapsed time: 4563.2 seconds (1.27 hours)\n\nTimestep: 1210000\nmean reward (100 episodes): 49.2600\nbest mean reward: 49.3100\ncurrent episode reward: 47.0000\nepisodes: 3260\nexploration: 0.09527\nlearning_rate: 0.00010\nelapsed time: 4607.1 seconds (1.28 hours)\n\nTimestep: 1220000\nmean reward (100 episodes): 50.1300\nbest mean reward: 50.3300\ncurrent episode reward: 67.0000\nepisodes: 3269\nexploration: 0.09505\nlearning_rate: 0.00010\nelapsed time: 4651.0 seconds (1.29 hours)\n\nTimestep: 1230000\nmean reward (100 episodes): 50.5100\nbest mean reward: 50.6300\ncurrent episode reward: 44.0000\nepisodes: 3277\nexploration: 0.09483\nlearning_rate: 0.00010\nelapsed time: 4694.5 seconds (1.30 hours)\n\nTimestep: 1240000\nmean reward (100 episodes): 49.8300\nbest mean reward: 50.6300\ncurrent episode reward: 50.0000\nepisodes: 3287\nexploration: 0.09460\nlearning_rate: 0.00010\nelapsed time: 4738.9 seconds (1.32 hours)\n\nTimestep: 1250000\nmean reward (100 episodes): 49.1500\nbest mean reward: 50.6300\ncurrent episode reward: 37.0000\nepisodes: 3296\nexploration: 0.09438\nlearning_rate: 0.00010\nelapsed time: 4783.0 seconds (1.33 hours)\n\nTimestep: 1260000\nmean reward (100 episodes): 49.5200\nbest mean reward: 50.6300\ncurrent episode reward: 75.0000\nepisodes: 3304\nexploration: 0.09415\nlearning_rate: 0.00010\nelapsed time: 4827.5 seconds (1.34 hours)\n\nTimestep: 1270000\nmean reward (100 episodes): 51.3300\nbest mean reward: 51.3300\ncurrent episode reward: 51.0000\nepisodes: 3312\nexploration: 0.09393\nlearning_rate: 0.00010\nelapsed time: 4870.8 seconds (1.35 hours)\n\nTimestep: 1280000\nmean reward (100 episodes): 50.9300\nbest mean reward: 52.0300\ncurrent episode reward: 35.0000\nepisodes: 3322\nexploration: 0.09370\nlearning_rate: 0.00010\nelapsed time: 4914.4 seconds (1.37 hours)\n\nTimestep: 1290000\nmean reward (100 episodes): 50.3700\nbest mean reward: 52.0300\ncurrent episode reward: 52.0000\nepisodes: 3330\nexploration: 0.09348\nlearning_rate: 0.00010\nelapsed time: 4957.9 seconds (1.38 hours)\n\nTimestep: 1300000\nmean reward (100 episodes): 51.3400\nbest mean reward: 52.0300\ncurrent episode reward: 44.0000\nepisodes: 3338\nexploration: 0.09325\nlearning_rate: 0.00010\nelapsed time: 5001.5 seconds (1.39 hours)\n\nTimestep: 1310000\nmean reward (100 episodes): 51.4500\nbest mean reward: 52.0700\ncurrent episode reward: 26.0000\nepisodes: 3347\nexploration: 0.09303\nlearning_rate: 0.00010\nelapsed time: 5045.0 seconds (1.40 hours)\n\nTimestep: 1320000\nmean reward (100 episodes): 51.6600\nbest mean reward: 52.0700\ncurrent episode reward: 57.0000\nepisodes: 3356\nexploration: 0.09280\nlearning_rate: 0.00010\nelapsed time: 5088.8 seconds (1.41 hours)\n\nTimestep: 1330000\nmean reward (100 episodes): 51.4000\nbest mean reward: 52.0700\ncurrent episode reward: 33.0000\nepisodes: 3363\nexploration: 0.09258\nlearning_rate: 0.00010\nelapsed time: 5132.1 seconds (1.43 hours)\n\nTimestep: 1340000\nmean reward (100 episodes): 51.9000\nbest mean reward: 52.0700\ncurrent episode reward: 63.0000\nepisodes: 3372\nexploration: 0.09235\nlearning_rate: 0.00010\nelapsed time: 5176.2 seconds (1.44 hours)\n\nTimestep: 1350000\nmean reward (100 episodes): 52.7400\nbest mean reward: 52.7400\ncurrent episode reward: 56.0000\nepisodes: 3379\nexploration: 0.09213\nlearning_rate: 0.00010\nelapsed time: 5220.8 seconds (1.45 hours)\n\nTimestep: 1360000\nmean reward (100 episodes): 52.9300\nbest mean reward: 52.9300\ncurrent episode reward: 58.0000\nepisodes: 3388\nexploration: 0.09190\nlearning_rate: 0.00010\nelapsed time: 5265.0 seconds (1.46 hours)\n\nTimestep: 1370000\nmean reward (100 episodes): 54.8300\nbest mean reward: 54.8300\ncurrent episode reward: 73.0000\nepisodes: 3395\nexploration: 0.09168\nlearning_rate: 0.00010\nelapsed time: 5308.8 seconds (1.47 hours)\n\nTimestep: 1380000\nmean reward (100 episodes): 55.9300\nbest mean reward: 56.0800\ncurrent episode reward: 60.0000\nepisodes: 3404\nexploration: 0.09145\nlearning_rate: 0.00010\nelapsed time: 5352.2 seconds (1.49 hours)\n\nTimestep: 1390000\nmean reward (100 episodes): 56.5900\nbest mean reward: 56.5900\ncurrent episode reward: 75.0000\nepisodes: 3411\nexploration: 0.09123\nlearning_rate: 0.00010\nelapsed time: 5396.8 seconds (1.50 hours)\n\nTimestep: 1400000\nmean reward (100 episodes): 57.7000\nbest mean reward: 57.9500\ncurrent episode reward: 40.0000\nepisodes: 3418\nexploration: 0.09100\nlearning_rate: 0.00010\nelapsed time: 5440.9 seconds (1.51 hours)\n\nTimestep: 1410000\nmean reward (100 episodes): 58.5000\nbest mean reward: 58.7100\ncurrent episode reward: 57.0000\nepisodes: 3426\nexploration: 0.09078\nlearning_rate: 0.00009\nelapsed time: 5484.9 seconds (1.52 hours)\n\nTimestep: 1420000\nmean reward (100 episodes): 58.4400\nbest mean reward: 58.7100\ncurrent episode reward: 60.0000\nepisodes: 3434\nexploration: 0.09055\nlearning_rate: 0.00009\nelapsed time: 5528.4 seconds (1.54 hours)\n\nTimestep: 1430000\nmean reward (100 episodes): 58.8200\nbest mean reward: 59.0000\ncurrent episode reward: 81.0000\nepisodes: 3442\nexploration: 0.09033\nlearning_rate: 0.00009\nelapsed time: 5571.4 seconds (1.55 hours)\n\nTimestep: 1440000\nmean reward (100 episodes): 59.8500\nbest mean reward: 59.8500\ncurrent episode reward: 71.0000\nepisodes: 3450\nexploration: 0.09010\nlearning_rate: 0.00009\nelapsed time: 5615.7 seconds (1.56 hours)\n\nTimestep: 1450000\nmean reward (100 episodes): 60.7900\nbest mean reward: 60.7900\ncurrent episode reward: 72.0000\nepisodes: 3458\nexploration: 0.08988\nlearning_rate: 0.00009\nelapsed time: 5659.3 seconds (1.57 hours)\n\nTimestep: 1460000\nmean reward (100 episodes): 61.3300\nbest mean reward: 61.4000\ncurrent episode reward: 61.0000\nepisodes: 3465\nexploration: 0.08965\nlearning_rate: 0.00009\nelapsed time: 5703.3 seconds (1.58 hours)\n\nTimestep: 1470000\nmean reward (100 episodes): 62.1800\nbest mean reward: 62.5400\ncurrent episode reward: 119.0000\nepisodes: 3473\nexploration: 0.08943\nlearning_rate: 0.00009\nelapsed time: 5747.2 seconds (1.60 hours)\n\nTimestep: 1480000\nmean reward (100 episodes): 63.7500\nbest mean reward: 63.7500\ncurrent episode reward: 99.0000\nepisodes: 3480\nexploration: 0.08920\nlearning_rate: 0.00009\nelapsed time: 5790.7 seconds (1.61 hours)\n\nTimestep: 1490000\nmean reward (100 episodes): 64.4700\nbest mean reward: 64.4700\ncurrent episode reward: 59.0000\nepisodes: 3488\nexploration: 0.08897\nlearning_rate: 0.00009\nelapsed time: 5834.8 seconds (1.62 hours)\n\nTimestep: 1500000\nmean reward (100 episodes): 66.5700\nbest mean reward: 66.7800\ncurrent episode reward: 52.0000\nepisodes: 3495\nexploration: 0.08875\nlearning_rate: 0.00009\nelapsed time: 5878.6 seconds (1.63 hours)\n\nTimestep: 1510000\nmean reward (100 episodes): 65.7300\nbest mean reward: 67.1500\ncurrent episode reward: 35.0000\nepisodes: 3504\nexploration: 0.08853\nlearning_rate: 0.00009\nelapsed time: 5922.9 seconds (1.65 hours)\n\nTimestep: 1520000\nmean reward (100 episodes): 59.6800\nbest mean reward: 67.1500\ncurrent episode reward: 7.0000\nepisodes: 3520\nexploration: 0.08830\nlearning_rate: 0.00009\nelapsed time: 5967.2 seconds (1.66 hours)\n\nTimestep: 1530000\nmean reward (100 episodes): 51.7300\nbest mean reward: 67.1500\ncurrent episode reward: 41.0000\nepisodes: 3537\nexploration: 0.08808\nlearning_rate: 0.00009\nelapsed time: 6010.8 seconds (1.67 hours)\n\nTimestep: 1540000\nmean reward (100 episodes): 52.8300\nbest mean reward: 67.1500\ncurrent episode reward: 85.0000\nepisodes: 3545\nexploration: 0.08785\nlearning_rate: 0.00009\nelapsed time: 6054.6 seconds (1.68 hours)\n\nTimestep: 1550000\nmean reward (100 episodes): 52.7100\nbest mean reward: 67.1500\ncurrent episode reward: 83.0000\nepisodes: 3553\nexploration: 0.08763\nlearning_rate: 0.00009\nelapsed time: 6097.7 seconds (1.69 hours)\n\nTimestep: 1560000\nmean reward (100 episodes): 52.4400\nbest mean reward: 67.1500\ncurrent episode reward: 71.0000\nepisodes: 3561\nexploration: 0.08740\nlearning_rate: 0.00009\nelapsed time: 6141.1 seconds (1.71 hours)\n\nTimestep: 1570000\nmean reward (100 episodes): 52.5800\nbest mean reward: 67.1500\ncurrent episode reward: 63.0000\nepisodes: 3568\nexploration: 0.08718\nlearning_rate: 0.00009\nelapsed time: 6185.3 seconds (1.72 hours)\n\nTimestep: 1580000\nmean reward (100 episodes): 44.3700\nbest mean reward: 67.1500\ncurrent episode reward: 57.0000\nepisodes: 3586\nexploration: 0.08695\nlearning_rate: 0.00009\nelapsed time: 6229.2 seconds (1.73 hours)\n\nTimestep: 1590000\nmean reward (100 episodes): 39.7800\nbest mean reward: 67.1500\ncurrent episode reward: 28.0000\nepisodes: 3596\nexploration: 0.08673\nlearning_rate: 0.00009\nelapsed time: 6272.7 seconds (1.74 hours)\n\nTimestep: 1600000\nmean reward (100 episodes): 35.6100\nbest mean reward: 67.1500\ncurrent episode reward: 5.0000\nepisodes: 3613\nexploration: 0.08650\nlearning_rate: 0.00009\nelapsed time: 6316.3 seconds (1.75 hours)\n\nTimestep: 1610000\nmean reward (100 episodes): 38.7800\nbest mean reward: 67.1500\ncurrent episode reward: 72.0000\nepisodes: 3625\nexploration: 0.08628\nlearning_rate: 0.00009\nelapsed time: 6360.5 seconds (1.77 hours)\n\nTimestep: 1620000\nmean reward (100 episodes): 40.3100\nbest mean reward: 67.1500\ncurrent episode reward: 2.0000\nepisodes: 3639\nexploration: 0.08605\nlearning_rate: 0.00009\nelapsed time: 6403.8 seconds (1.78 hours)\n\nTimestep: 1630000\nmean reward (100 episodes): 39.3600\nbest mean reward: 67.1500\ncurrent episode reward: 59.0000\nepisodes: 3647\nexploration: 0.08582\nlearning_rate: 0.00009\nelapsed time: 6447.7 seconds (1.79 hours)\n\nTimestep: 1640000\nmean reward (100 episodes): 39.2500\nbest mean reward: 67.1500\ncurrent episode reward: 55.0000\nepisodes: 3656\nexploration: 0.08560\nlearning_rate: 0.00009\nelapsed time: 6491.0 seconds (1.80 hours)\n\nTimestep: 1650000\nmean reward (100 episodes): 30.7300\nbest mean reward: 67.1500\ncurrent episode reward: 1.0000\nepisodes: 3685\nexploration: 0.08538\nlearning_rate: 0.00009\nelapsed time: 6535.2 seconds (1.82 hours)\n\nTimestep: 1660000\nmean reward (100 episodes): 14.9300\nbest mean reward: 67.1500\ncurrent episode reward: 11.0000\nepisodes: 3731\nexploration: 0.08515\nlearning_rate: 0.00009\nelapsed time: 6579.8 seconds (1.83 hours)\n\nTimestep: 1670000\nmean reward (100 episodes): 11.6500\nbest mean reward: 67.1500\ncurrent episode reward: 49.0000\nepisodes: 3749\nexploration: 0.08493\nlearning_rate: 0.00009\nelapsed time: 6624.3 seconds (1.84 hours)\n\nTimestep: 1680000\nmean reward (100 episodes): 11.7900\nbest mean reward: 67.1500\ncurrent episode reward: 68.0000\nepisodes: 3756\nexploration: 0.08470\nlearning_rate: 0.00009\nelapsed time: 6668.0 seconds (1.85 hours)\n\nTimestep: 1690000\nmean reward (100 episodes): 14.2000\nbest mean reward: 67.1500\ncurrent episode reward: 3.0000\nepisodes: 3769\nexploration: 0.08448\nlearning_rate: 0.00009\nelapsed time: 6711.5 seconds (1.86 hours)\n\nTimestep: 1700000\nmean reward (100 episodes): 17.4200\nbest mean reward: 67.1500\ncurrent episode reward: 69.0000\nepisodes: 3787\nexploration: 0.08425\nlearning_rate: 0.00009\nelapsed time: 6755.5 seconds (1.88 hours)\n\nTimestep: 1710000\nmean reward (100 episodes): 20.7400\nbest mean reward: 67.1500\ncurrent episode reward: 24.0000\nepisodes: 3807\nexploration: 0.08403\nlearning_rate: 0.00009\nelapsed time: 6799.2 seconds (1.89 hours)\n\nTimestep: 1720000\nmean reward (100 episodes): 25.2900\nbest mean reward: 67.1500\ncurrent episode reward: 52.0000\nepisodes: 3815\nexploration: 0.08380\nlearning_rate: 0.00009\nelapsed time: 6842.8 seconds (1.90 hours)\n\nTimestep: 1730000\nmean reward (100 episodes): 30.3800\nbest mean reward: 67.1500\ncurrent episode reward: 84.0000\nepisodes: 3823\nexploration: 0.08358\nlearning_rate: 0.00009\nelapsed time: 6887.0 seconds (1.91 hours)\n\nTimestep: 1740000\nmean reward (100 episodes): 34.9900\nbest mean reward: 67.1500\ncurrent episode reward: 57.0000\nepisodes: 3831\nexploration: 0.08335\nlearning_rate: 0.00009\nelapsed time: 6930.3 seconds (1.93 hours)\n\nTimestep: 1750000\nmean reward (100 episodes): 39.5500\nbest mean reward: 67.1500\ncurrent episode reward: 87.0000\nepisodes: 3838\nexploration: 0.08313\nlearning_rate: 0.00009\nelapsed time: 6974.6 seconds (1.94 hours)\n\nTimestep: 1760000\nmean reward (100 episodes): 43.0800\nbest mean reward: 67.1500\ncurrent episode reward: 32.0000\nepisodes: 3846\nexploration: 0.08290\nlearning_rate: 0.00009\nelapsed time: 7018.2 seconds (1.95 hours)\n\nTimestep: 1770000\nmean reward (100 episodes): 34.4400\nbest mean reward: 67.1500\ncurrent episode reward: 59.0000\nepisodes: 3870\nexploration: 0.08267\nlearning_rate: 0.00009\nelapsed time: 7062.3 seconds (1.96 hours)\n\nTimestep: 1780000\nmean reward (100 episodes): 38.7400\nbest mean reward: 67.1500\ncurrent episode reward: 59.0000\nepisodes: 3879\nexploration: 0.08245\nlearning_rate: 0.00009\nelapsed time: 7106.8 seconds (1.97 hours)\n\nTimestep: 1790000\nmean reward (100 episodes): 40.5300\nbest mean reward: 67.1500\ncurrent episode reward: 71.0000\nepisodes: 3887\nexploration: 0.08223\nlearning_rate: 0.00009\nelapsed time: 7150.7 seconds (1.99 hours)\n\nTimestep: 1800000\nmean reward (100 episodes): 33.9100\nbest mean reward: 67.1500\ncurrent episode reward: 2.0000\nepisodes: 3917\nexploration: 0.08200\nlearning_rate: 0.00009\nelapsed time: 7195.6 seconds (2.00 hours)\n\nTimestep: 1810000\nmean reward (100 episodes): 21.9100\nbest mean reward: 67.1500\ncurrent episode reward: 46.0000\nepisodes: 3939\nexploration: 0.08178\nlearning_rate: 0.00009\nelapsed time: 7240.1 seconds (2.01 hours)\n\nTimestep: 1820000\nmean reward (100 episodes): 24.4800\nbest mean reward: 67.1500\ncurrent episode reward: 52.0000\nepisodes: 3947\nexploration: 0.08155\nlearning_rate: 0.00009\nelapsed time: 7284.6 seconds (2.02 hours)\n\nTimestep: 1830000\nmean reward (100 episodes): 28.4000\nbest mean reward: 67.1500\ncurrent episode reward: 52.0000\nepisodes: 3960\nexploration: 0.08133\nlearning_rate: 0.00009\nelapsed time: 7328.7 seconds (2.04 hours)\n\nTimestep: 1840000\nmean reward (100 episodes): 32.8000\nbest mean reward: 67.1500\ncurrent episode reward: 62.0000\nepisodes: 3969\nexploration: 0.08110\nlearning_rate: 0.00009\nelapsed time: 7372.3 seconds (2.05 hours)\n\nTimestep: 1850000\nmean reward (100 episodes): 31.3800\nbest mean reward: 67.1500\ncurrent episode reward: 73.0000\nepisodes: 3979\nexploration: 0.08088\nlearning_rate: 0.00009\nelapsed time: 7416.4 seconds (2.06 hours)\n\nTimestep: 1860000\nmean reward (100 episodes): 31.2300\nbest mean reward: 67.1500\ncurrent episode reward: 104.0000\nepisodes: 3987\nexploration: 0.08065\nlearning_rate: 0.00009\nelapsed time: 7459.9 seconds (2.07 hours)\n\nTimestep: 1870000\nmean reward (100 episodes): 31.3200\nbest mean reward: 67.1500\ncurrent episode reward: 20.0000\nepisodes: 4003\nexploration: 0.08042\nlearning_rate: 0.00009\nelapsed time: 7504.9 seconds (2.08 hours)\n\nTimestep: 1880000\nmean reward (100 episodes): 36.2500\nbest mean reward: 67.1500\ncurrent episode reward: 89.0000\nepisodes: 4011\nexploration: 0.08020\nlearning_rate: 0.00009\nelapsed time: 7549.0 seconds (2.10 hours)\n\nTimestep: 1890000\nmean reward (100 episodes): 40.9800\nbest mean reward: 67.1500\ncurrent episode reward: 55.0000\nepisodes: 4018\nexploration: 0.07998\nlearning_rate: 0.00009\nelapsed time: 7593.7 seconds (2.11 hours)\n\nTimestep: 1900000\nmean reward (100 episodes): 46.0700\nbest mean reward: 67.1500\ncurrent episode reward: 48.0000\nepisodes: 4025\nexploration: 0.07975\nlearning_rate: 0.00009\nelapsed time: 7637.5 seconds (2.12 hours)\n\nTimestep: 1910000\nmean reward (100 episodes): 50.8200\nbest mean reward: 67.1500\ncurrent episode reward: 41.0000\nepisodes: 4034\nexploration: 0.07952\nlearning_rate: 0.00009\nelapsed time: 7681.1 seconds (2.13 hours)\n\nTimestep: 1920000\nmean reward (100 episodes): 53.7400\nbest mean reward: 67.1500\ncurrent episode reward: 51.0000\nepisodes: 4041\nexploration: 0.07930\nlearning_rate: 0.00009\nelapsed time: 7725.1 seconds (2.15 hours)\n\nTimestep: 1930000\nmean reward (100 episodes): 49.8400\nbest mean reward: 67.1500\ncurrent episode reward: 5.0000\nepisodes: 4052\nexploration: 0.07908\nlearning_rate: 0.00009\nelapsed time: 7768.4 seconds (2.16 hours)\n\nTimestep: 1940000\nmean reward (100 episodes): 53.3900\nbest mean reward: 67.1500\ncurrent episode reward: 93.0000\nepisodes: 4060\nexploration: 0.07885\nlearning_rate: 0.00009\nelapsed time: 7811.6 seconds (2.17 hours)\n\nTimestep: 1950000\nmean reward (100 episodes): 55.7100\nbest mean reward: 67.1500\ncurrent episode reward: 67.0000\nepisodes: 4069\nexploration: 0.07863\nlearning_rate: 0.00009\nelapsed time: 7855.2 seconds (2.18 hours)\n\nTimestep: 1960000\nmean reward (100 episodes): 55.6300\nbest mean reward: 67.1500\ncurrent episode reward: 4.0000\nepisodes: 4081\nexploration: 0.07840\nlearning_rate: 0.00009\nelapsed time: 7897.9 seconds (2.19 hours)\n\nTimestep: 1970000\nmean reward (100 episodes): 51.9900\nbest mean reward: 67.1500\ncurrent episode reward: 18.0000\nepisodes: 4101\nexploration: 0.07818\nlearning_rate: 0.00009\nelapsed time: 7941.5 seconds (2.21 hours)\n\nTimestep: 1980000\nmean reward (100 episodes): 52.4800\nbest mean reward: 67.1500\ncurrent episode reward: 86.0000\nepisodes: 4109\nexploration: 0.07795\nlearning_rate: 0.00009\nelapsed time: 7985.7 seconds (2.22 hours)\n\nTimestep: 1990000\nmean reward (100 episodes): 47.4800\nbest mean reward: 67.1500\ncurrent episode reward: 49.0000\nepisodes: 4122\nexploration: 0.07773\nlearning_rate: 0.00009\nelapsed time: 8029.8 seconds (2.23 hours)\n\nTimestep: 2000000\nmean reward (100 episodes): 46.3600\nbest mean reward: 67.1500\ncurrent episode reward: 23.0000\nepisodes: 4130\nexploration: 0.07750\nlearning_rate: 0.00009\nelapsed time: 8073.6 seconds (2.24 hours)\n\nTimestep: 2010000\nmean reward (100 episodes): 44.8400\nbest mean reward: 67.1500\ncurrent episode reward: 51.0000\nepisodes: 4139\nexploration: 0.07728\nlearning_rate: 0.00009\nelapsed time: 8117.3 seconds (2.25 hours)\n\nTimestep: 2020000\nmean reward (100 episodes): 44.0600\nbest mean reward: 67.1500\ncurrent episode reward: 103.0000\nepisodes: 4149\nexploration: 0.07705\nlearning_rate: 0.00009\nelapsed time: 8161.1 seconds (2.27 hours)\n\nTimestep: 2030000\nmean reward (100 episodes): 44.5300\nbest mean reward: 67.1500\ncurrent episode reward: 63.0000\nepisodes: 4158\nexploration: 0.07683\nlearning_rate: 0.00009\nelapsed time: 8205.0 seconds (2.28 hours)\n\nTimestep: 2040000\nmean reward (100 episodes): 42.0000\nbest mean reward: 67.1500\ncurrent episode reward: 10.0000\nepisodes: 4167\nexploration: 0.07660\nlearning_rate: 0.00009\nelapsed time: 8248.8 seconds (2.29 hours)\n\nTimestep: 2050000\nmean reward (100 episodes): 40.2700\nbest mean reward: 67.1500\ncurrent episode reward: 79.0000\nepisodes: 4176\nexploration: 0.07637\nlearning_rate: 0.00009\nelapsed time: 8292.6 seconds (2.30 hours)\n\nTimestep: 2060000\nmean reward (100 episodes): 44.8200\nbest mean reward: 67.1500\ncurrent episode reward: 68.0000\nepisodes: 4183\nexploration: 0.07615\nlearning_rate: 0.00009\nelapsed time: 8336.7 seconds (2.32 hours)\n\nTimestep: 2070000\nmean reward (100 episodes): 46.6700\nbest mean reward: 67.1500\ncurrent episode reward: 1.0000\nepisodes: 4193\nexploration: 0.07593\nlearning_rate: 0.00009\nelapsed time: 8380.5 seconds (2.33 hours)\n\nTimestep: 2080000\nmean reward (100 episodes): 47.5900\nbest mean reward: 67.1500\ncurrent episode reward: 13.0000\nepisodes: 4209\nexploration: 0.07570\nlearning_rate: 0.00009\nelapsed time: 8424.0 seconds (2.34 hours)\n\nTimestep: 2090000\nmean reward (100 episodes): 42.7100\nbest mean reward: 67.1500\ncurrent episode reward: 41.0000\nepisodes: 4228\nexploration: 0.07548\nlearning_rate: 0.00009\nelapsed time: 8467.8 seconds (2.35 hours)\n\nTimestep: 2100000\nmean reward (100 episodes): 42.8100\nbest mean reward: 67.1500\ncurrent episode reward: 96.0000\nepisodes: 4236\nexploration: 0.07525\nlearning_rate: 0.00009\nelapsed time: 8511.3 seconds (2.36 hours)\n\nTimestep: 2110000\nmean reward (100 episodes): 46.3100\nbest mean reward: 67.1500\ncurrent episode reward: 59.0000\nepisodes: 4244\nexploration: 0.07503\nlearning_rate: 0.00009\nelapsed time: 8555.4 seconds (2.38 hours)\n\nTimestep: 2120000\nmean reward (100 episodes): 46.9600\nbest mean reward: 67.1500\ncurrent episode reward: 47.0000\nepisodes: 4251\nexploration: 0.07480\nlearning_rate: 0.00009\nelapsed time: 8599.3 seconds (2.39 hours)\n\nTimestep: 2130000\nmean reward (100 episodes): 45.2900\nbest mean reward: 67.1500\ncurrent episode reward: 95.0000\nepisodes: 4262\nexploration: 0.07458\nlearning_rate: 0.00009\nelapsed time: 8643.3 seconds (2.40 hours)\n\nTimestep: 2140000\nmean reward (100 episodes): 46.7800\nbest mean reward: 67.1500\ncurrent episode reward: 64.0000\nepisodes: 4270\nexploration: 0.07435\nlearning_rate: 0.00009\nelapsed time: 8687.6 seconds (2.41 hours)\n\nTimestep: 2150000\nmean reward (100 episodes): 45.1700\nbest mean reward: 67.1500\ncurrent episode reward: 126.0000\nepisodes: 4280\nexploration: 0.07412\nlearning_rate: 0.00009\nelapsed time: 8731.3 seconds (2.43 hours)\n\nTimestep: 2160000\nmean reward (100 episodes): 42.9900\nbest mean reward: 67.1500\ncurrent episode reward: 63.0000\nepisodes: 4293\nexploration: 0.07390\nlearning_rate: 0.00009\nelapsed time: 8776.2 seconds (2.44 hours)\n\nTimestep: 2170000\nmean reward (100 episodes): 42.5900\nbest mean reward: 67.1500\ncurrent episode reward: 56.0000\nepisodes: 4301\nexploration: 0.07368\nlearning_rate: 0.00009\nelapsed time: 8820.3 seconds (2.45 hours)\n\nTimestep: 2180000\nmean reward (100 episodes): 47.0900\nbest mean reward: 67.1500\ncurrent episode reward: 77.0000\nepisodes: 4309\nexploration: 0.07345\nlearning_rate: 0.00009\nelapsed time: 8864.3 seconds (2.46 hours)\n\nTimestep: 2190000\nmean reward (100 episodes): 53.5600\nbest mean reward: 67.1500\ncurrent episode reward: 50.0000\nepisodes: 4318\nexploration: 0.07322\nlearning_rate: 0.00009\nelapsed time: 8909.0 seconds (2.47 hours)\n\nTimestep: 2200000\nmean reward (100 episodes): 56.9300\nbest mean reward: 67.1500\ncurrent episode reward: 94.0000\nepisodes: 4326\nexploration: 0.07300\nlearning_rate: 0.00009\nelapsed time: 8952.9 seconds (2.49 hours)\n\nTimestep: 2210000\nmean reward (100 episodes): 57.2400\nbest mean reward: 67.1500\ncurrent episode reward: 53.0000\nepisodes: 4335\nexploration: 0.07278\nlearning_rate: 0.00008\nelapsed time: 8995.9 seconds (2.50 hours)\n\nTimestep: 2220000\nmean reward (100 episodes): 55.5600\nbest mean reward: 67.1500\ncurrent episode reward: 47.0000\nepisodes: 4343\nexploration: 0.07255\nlearning_rate: 0.00008\nelapsed time: 9040.6 seconds (2.51 hours)\n\nTimestep: 2230000\nmean reward (100 episodes): 54.1500\nbest mean reward: 67.1500\ncurrent episode reward: 62.0000\nepisodes: 4353\nexploration: 0.07233\nlearning_rate: 0.00008\nelapsed time: 9084.8 seconds (2.52 hours)\n\nTimestep: 2240000\nmean reward (100 episodes): 54.5200\nbest mean reward: 67.1500\ncurrent episode reward: 73.0000\nepisodes: 4362\nexploration: 0.07210\nlearning_rate: 0.00008\nelapsed time: 9129.1 seconds (2.54 hours)\n\nTimestep: 2250000\nmean reward (100 episodes): 52.7400\nbest mean reward: 67.1500\ncurrent episode reward: 83.0000\nepisodes: 4371\nexploration: 0.07187\nlearning_rate: 0.00008\nelapsed time: 9173.4 seconds (2.55 hours)\n\nTimestep: 2260000\nmean reward (100 episodes): 54.1000\nbest mean reward: 67.1500\ncurrent episode reward: 53.0000\nepisodes: 4380\nexploration: 0.07165\nlearning_rate: 0.00008\nelapsed time: 9217.1 seconds (2.56 hours)\n\nTimestep: 2270000\nmean reward (100 episodes): 57.0500\nbest mean reward: 67.1500\ncurrent episode reward: 85.0000\nepisodes: 4391\nexploration: 0.07143\nlearning_rate: 0.00008\nelapsed time: 9260.7 seconds (2.57 hours)\n\nTimestep: 2280000\nmean reward (100 episodes): 57.5100\nbest mean reward: 67.1500\ncurrent episode reward: 74.0000\nepisodes: 4398\nexploration: 0.07120\nlearning_rate: 0.00008\nelapsed time: 9305.2 seconds (2.58 hours)\n\nTimestep: 2290000\nmean reward (100 episodes): 51.1600\nbest mean reward: 67.1500\ncurrent episode reward: 47.0000\nepisodes: 4413\nexploration: 0.07097\nlearning_rate: 0.00008\nelapsed time: 9349.3 seconds (2.60 hours)\n\nTimestep: 2300000\nmean reward (100 episodes): 50.2600\nbest mean reward: 67.1500\ncurrent episode reward: 94.0000\nepisodes: 4423\nexploration: 0.07075\nlearning_rate: 0.00008\nelapsed time: 9393.6 seconds (2.61 hours)\n\nTimestep: 2310000\nmean reward (100 episodes): 52.7600\nbest mean reward: 67.1500\ncurrent episode reward: 127.0000\nepisodes: 4431\nexploration: 0.07053\nlearning_rate: 0.00008\nelapsed time: 9437.5 seconds (2.62 hours)\n\nTimestep: 2320000\nmean reward (100 episodes): 54.1300\nbest mean reward: 67.1500\ncurrent episode reward: 71.0000\nepisodes: 4438\nexploration: 0.07030\nlearning_rate: 0.00008\nelapsed time: 9481.2 seconds (2.63 hours)\n\nTimestep: 2330000\nmean reward (100 episodes): 56.3500\nbest mean reward: 67.1500\ncurrent episode reward: 54.0000\nepisodes: 4446\nexploration: 0.07007\nlearning_rate: 0.00008\nelapsed time: 9524.5 seconds (2.65 hours)\n\nTimestep: 2340000\nmean reward (100 episodes): 61.4800\nbest mean reward: 67.1500\ncurrent episode reward: 67.0000\nepisodes: 4454\nexploration: 0.06985\nlearning_rate: 0.00008\nelapsed time: 9568.0 seconds (2.66 hours)\n\nTimestep: 2350000\nmean reward (100 episodes): 62.8000\nbest mean reward: 67.1500\ncurrent episode reward: 73.0000\nepisodes: 4461\nexploration: 0.06962\nlearning_rate: 0.00008\nelapsed time: 9611.8 seconds (2.67 hours)\n\nTimestep: 2360000\nmean reward (100 episodes): 65.9300\nbest mean reward: 67.1500\ncurrent episode reward: 26.0000\nepisodes: 4469\nexploration: 0.06940\nlearning_rate: 0.00008\nelapsed time: 9655.6 seconds (2.68 hours)\n\nTimestep: 2370000\nmean reward (100 episodes): 65.0200\nbest mean reward: 67.1500\ncurrent episode reward: 88.0000\nepisodes: 4480\nexploration: 0.06918\nlearning_rate: 0.00008\nelapsed time: 9699.2 seconds (2.69 hours)\n\nTimestep: 2380000\nmean reward (100 episodes): 64.7900\nbest mean reward: 67.1500\ncurrent episode reward: 7.0000\nepisodes: 4489\nexploration: 0.06895\nlearning_rate: 0.00008\nelapsed time: 9743.3 seconds (2.71 hours)\n\nTimestep: 2390000\nmean reward (100 episodes): 64.8800\nbest mean reward: 67.1500\ncurrent episode reward: 57.0000\nepisodes: 4496\nexploration: 0.06873\nlearning_rate: 0.00008\nelapsed time: 9787.0 seconds (2.72 hours)\n\nTimestep: 2400000\nmean reward (100 episodes): 67.0700\nbest mean reward: 67.1500\ncurrent episode reward: 34.0000\nepisodes: 4505\nexploration: 0.06850\nlearning_rate: 0.00008\nelapsed time: 9830.6 seconds (2.73 hours)\n\nTimestep: 2410000\nmean reward (100 episodes): 69.4900\nbest mean reward: 70.1700\ncurrent episode reward: 3.0000\nepisodes: 4514\nexploration: 0.06828\nlearning_rate: 0.00008\nelapsed time: 9875.3 seconds (2.74 hours)\n\nTimestep: 2420000\nmean reward (100 episodes): 69.6200\nbest mean reward: 70.1700\ncurrent episode reward: 68.0000\nepisodes: 4523\nexploration: 0.06805\nlearning_rate: 0.00008\nelapsed time: 9918.6 seconds (2.76 hours)\n\nTimestep: 2430000\nmean reward (100 episodes): 72.1800\nbest mean reward: 72.1800\ncurrent episode reward: 283.0000\nepisodes: 4530\nexploration: 0.06782\nlearning_rate: 0.00008\nelapsed time: 9962.2 seconds (2.77 hours)\n\nTimestep: 2440000\nmean reward (100 episodes): 71.5300\nbest mean reward: 72.1800\ncurrent episode reward: 102.0000\nepisodes: 4538\nexploration: 0.06760\nlearning_rate: 0.00008\nelapsed time: 10005.8 seconds (2.78 hours)\n\nTimestep: 2450000\nmean reward (100 episodes): 70.1400\nbest mean reward: 72.1800\ncurrent episode reward: 117.0000\nepisodes: 4546\nexploration: 0.06738\nlearning_rate: 0.00008\nelapsed time: 10049.4 seconds (2.79 hours)\n\nTimestep: 2460000\nmean reward (100 episodes): 67.4800\nbest mean reward: 72.1800\ncurrent episode reward: 49.0000\nepisodes: 4554\nexploration: 0.06715\nlearning_rate: 0.00008\nelapsed time: 10092.9 seconds (2.80 hours)\n\nTimestep: 2470000\nmean reward (100 episodes): 63.1300\nbest mean reward: 72.1800\ncurrent episode reward: 40.0000\nepisodes: 4566\nexploration: 0.06693\nlearning_rate: 0.00008\nelapsed time: 10136.7 seconds (2.82 hours)\n\nTimestep: 2480000\nmean reward (100 episodes): 64.3100\nbest mean reward: 72.1800\ncurrent episode reward: 20.0000\nepisodes: 4574\nexploration: 0.06670\nlearning_rate: 0.00008\nelapsed time: 10180.7 seconds (2.83 hours)\n\nTimestep: 2490000\nmean reward (100 episodes): 69.3200\nbest mean reward: 72.1800\ncurrent episode reward: 114.0000\nepisodes: 4581\nexploration: 0.06648\nlearning_rate: 0.00008\nelapsed time: 10224.8 seconds (2.84 hours)\n\nTimestep: 2500000\nmean reward (100 episodes): 72.7700\nbest mean reward: 72.7700\ncurrent episode reward: 44.0000\nepisodes: 4588\nexploration: 0.06625\nlearning_rate: 0.00008\nelapsed time: 10268.5 seconds (2.85 hours)\n\nTimestep: 2510000\nmean reward (100 episodes): 73.9600\nbest mean reward: 74.9100\ncurrent episode reward: 88.0000\nepisodes: 4596\nexploration: 0.06603\nlearning_rate: 0.00008\nelapsed time: 10313.5 seconds (2.86 hours)\n\nTimestep: 2520000\nmean reward (100 episodes): 75.3100\nbest mean reward: 75.3700\ncurrent episode reward: 65.0000\nepisodes: 4603\nexploration: 0.06580\nlearning_rate: 0.00008\nelapsed time: 10357.7 seconds (2.88 hours)\n\nTimestep: 2530000\nmean reward (100 episodes): 74.6200\nbest mean reward: 75.4100\ncurrent episode reward: 100.0000\nepisodes: 4611\nexploration: 0.06557\nlearning_rate: 0.00008\nelapsed time: 10401.6 seconds (2.89 hours)\n\nTimestep: 2540000\nmean reward (100 episodes): 77.6600\nbest mean reward: 77.6600\ncurrent episode reward: 87.0000\nepisodes: 4619\nexploration: 0.06535\nlearning_rate: 0.00008\nelapsed time: 10445.7 seconds (2.90 hours)\n\nTimestep: 2550000\nmean reward (100 episodes): 78.1200\nbest mean reward: 78.2100\ncurrent episode reward: 71.0000\nepisodes: 4626\nexploration: 0.06513\nlearning_rate: 0.00008\nelapsed time: 10490.5 seconds (2.91 hours)\n\nTimestep: 2560000\nmean reward (100 episodes): 76.0000\nbest mean reward: 78.2900\ncurrent episode reward: 36.0000\nepisodes: 4635\nexploration: 0.06490\nlearning_rate: 0.00008\nelapsed time: 10534.3 seconds (2.93 hours)\n\nTimestep: 2570000\nmean reward (100 episodes): 73.1200\nbest mean reward: 78.2900\ncurrent episode reward: 65.0000\nepisodes: 4645\nexploration: 0.06468\nlearning_rate: 0.00008\nelapsed time: 10578.2 seconds (2.94 hours)\n\nTimestep: 2580000\nmean reward (100 episodes): 72.5700\nbest mean reward: 78.2900\ncurrent episode reward: 104.0000\nepisodes: 4653\nexploration: 0.06445\nlearning_rate: 0.00008\nelapsed time: 10622.4 seconds (2.95 hours)\n\nTimestep: 2590000\nmean reward (100 episodes): 73.2500\nbest mean reward: 78.2900\ncurrent episode reward: 62.0000\nepisodes: 4660\nexploration: 0.06423\nlearning_rate: 0.00008\nelapsed time: 10666.7 seconds (2.96 hours)\n\nTimestep: 2600000\nmean reward (100 episodes): 77.0000\nbest mean reward: 78.2900\ncurrent episode reward: 100.0000\nepisodes: 4668\nexploration: 0.06400\nlearning_rate: 0.00008\nelapsed time: 10711.1 seconds (2.98 hours)\n\nTimestep: 2610000\nmean reward (100 episodes): 78.5000\nbest mean reward: 78.7900\ncurrent episode reward: 51.0000\nepisodes: 4676\nexploration: 0.06377\nlearning_rate: 0.00008\nelapsed time: 10755.4 seconds (2.99 hours)\n\nTimestep: 2620000\nmean reward (100 episodes): 74.9000\nbest mean reward: 78.9000\ncurrent episode reward: 111.0000\nepisodes: 4683\nexploration: 0.06355\nlearning_rate: 0.00008\nelapsed time: 10799.1 seconds (3.00 hours)\n\nTimestep: 2630000\nmean reward (100 episodes): 74.9700\nbest mean reward: 78.9000\ncurrent episode reward: 35.0000\nepisodes: 4691\nexploration: 0.06333\nlearning_rate: 0.00008\nelapsed time: 10842.7 seconds (3.01 hours)\n\nTimestep: 2640000\nmean reward (100 episodes): 73.1800\nbest mean reward: 78.9000\ncurrent episode reward: 41.0000\nepisodes: 4699\nexploration: 0.06310\nlearning_rate: 0.00008\nelapsed time: 10886.5 seconds (3.02 hours)\n\nTimestep: 2650000\nmean reward (100 episodes): 74.2100\nbest mean reward: 78.9000\ncurrent episode reward: 35.0000\nepisodes: 4708\nexploration: 0.06288\nlearning_rate: 0.00008\nelapsed time: 10930.9 seconds (3.04 hours)\n\nTimestep: 2660000\nmean reward (100 episodes): 71.7900\nbest mean reward: 78.9000\ncurrent episode reward: 91.0000\nepisodes: 4716\nexploration: 0.06265\nlearning_rate: 0.00008\nelapsed time: 10975.4 seconds (3.05 hours)\n\nTimestep: 2670000\nmean reward (100 episodes): 75.0100\nbest mean reward: 78.9000\ncurrent episode reward: 137.0000\nepisodes: 4723\nexploration: 0.06243\nlearning_rate: 0.00008\nelapsed time: 11019.4 seconds (3.06 hours)\n\nTimestep: 2680000\nmean reward (100 episodes): 79.4000\nbest mean reward: 79.6900\ncurrent episode reward: 82.0000\nepisodes: 4729\nexploration: 0.06220\nlearning_rate: 0.00008\nelapsed time: 11063.7 seconds (3.07 hours)\n\nTimestep: 2690000\nmean reward (100 episodes): 81.4500\nbest mean reward: 81.7700\ncurrent episode reward: 37.0000\nepisodes: 4739\nexploration: 0.06198\nlearning_rate: 0.00008\nelapsed time: 11108.2 seconds (3.09 hours)\n\nTimestep: 2700000\nmean reward (100 episodes): 83.0400\nbest mean reward: 83.9900\ncurrent episode reward: 54.0000\nepisodes: 4747\nexploration: 0.06175\nlearning_rate: 0.00008\nelapsed time: 11151.4 seconds (3.10 hours)\n\nTimestep: 2710000\nmean reward (100 episodes): 84.3500\nbest mean reward: 84.8800\ncurrent episode reward: 45.0000\nepisodes: 4755\nexploration: 0.06153\nlearning_rate: 0.00008\nelapsed time: 11194.9 seconds (3.11 hours)\n\nTimestep: 2720000\nmean reward (100 episodes): 84.0900\nbest mean reward: 84.8800\ncurrent episode reward: 72.0000\nepisodes: 4762\nexploration: 0.06130\nlearning_rate: 0.00008\nelapsed time: 11239.2 seconds (3.12 hours)\n\nTimestep: 2730000\nmean reward (100 episodes): 86.1800\nbest mean reward: 86.4700\ncurrent episode reward: 124.0000\nepisodes: 4770\nexploration: 0.06108\nlearning_rate: 0.00008\nelapsed time: 11282.8 seconds (3.13 hours)\n\nTimestep: 2740000\nmean reward (100 episodes): 84.8000\nbest mean reward: 86.4700\ncurrent episode reward: 126.0000\nepisodes: 4777\nexploration: 0.06085\nlearning_rate: 0.00008\nelapsed time: 11327.3 seconds (3.15 hours)\n\nTimestep: 2750000\nmean reward (100 episodes): 85.0100\nbest mean reward: 87.1300\ncurrent episode reward: 91.0000\nepisodes: 4784\nexploration: 0.06062\nlearning_rate: 0.00008\nelapsed time: 11371.7 seconds (3.16 hours)\n\nTimestep: 2760000\nmean reward (100 episodes): 88.9200\nbest mean reward: 88.9200\ncurrent episode reward: 122.0000\nepisodes: 4792\nexploration: 0.06040\nlearning_rate: 0.00008\nelapsed time: 11415.5 seconds (3.17 hours)\n\nTimestep: 2770000\nmean reward (100 episodes): 89.7000\nbest mean reward: 89.7900\ncurrent episode reward: 82.0000\nepisodes: 4801\nexploration: 0.06017\nlearning_rate: 0.00008\nelapsed time: 11459.5 seconds (3.18 hours)\n\nTimestep: 2780000\nmean reward (100 episodes): 91.0400\nbest mean reward: 91.0400\ncurrent episode reward: 120.0000\nepisodes: 4808\nexploration: 0.05995\nlearning_rate: 0.00008\nelapsed time: 11503.2 seconds (3.20 hours)\n\nTimestep: 2790000\nmean reward (100 episodes): 94.8700\nbest mean reward: 94.8700\ncurrent episode reward: 86.0000\nepisodes: 4815\nexploration: 0.05973\nlearning_rate: 0.00008\nelapsed time: 11546.9 seconds (3.21 hours)\n\nTimestep: 2800000\nmean reward (100 episodes): 95.0600\nbest mean reward: 95.2300\ncurrent episode reward: 137.0000\nepisodes: 4822\nexploration: 0.05950\nlearning_rate: 0.00008\nelapsed time: 11590.3 seconds (3.22 hours)\n\nTimestep: 2810000\nmean reward (100 episodes): 92.4300\nbest mean reward: 95.2300\ncurrent episode reward: 227.0000\nepisodes: 4829\nexploration: 0.05928\nlearning_rate: 0.00008\nelapsed time: 11633.7 seconds (3.23 hours)\n\nTimestep: 2820000\nmean reward (100 episodes): 90.6600\nbest mean reward: 95.2300\ncurrent episode reward: 35.0000\nepisodes: 4839\nexploration: 0.05905\nlearning_rate: 0.00008\nelapsed time: 11677.4 seconds (3.24 hours)\n\nTimestep: 2830000\nmean reward (100 episodes): 88.6900\nbest mean reward: 95.2300\ncurrent episode reward: 115.0000\nepisodes: 4848\nexploration: 0.05883\nlearning_rate: 0.00008\nelapsed time: 11722.2 seconds (3.26 hours)\n\nTimestep: 2840000\nmean reward (100 episodes): 91.8500\nbest mean reward: 95.2300\ncurrent episode reward: 177.0000\nepisodes: 4855\nexploration: 0.05860\nlearning_rate: 0.00008\nelapsed time: 11766.2 seconds (3.27 hours)\n\nTimestep: 2850000\nmean reward (100 episodes): 92.1300\nbest mean reward: 95.2300\ncurrent episode reward: 235.0000\nepisodes: 4862\nexploration: 0.05837\nlearning_rate: 0.00008\nelapsed time: 11810.7 seconds (3.28 hours)\n\nTimestep: 2860000\nmean reward (100 episodes): 88.5600\nbest mean reward: 95.2300\ncurrent episode reward: 30.0000\nepisodes: 4873\nexploration: 0.05815\nlearning_rate: 0.00008\nelapsed time: 11854.9 seconds (3.29 hours)\n\nTimestep: 2870000\nmean reward (100 episodes): 88.3600\nbest mean reward: 95.2300\ncurrent episode reward: 110.0000\nepisodes: 4880\nexploration: 0.05792\nlearning_rate: 0.00008\nelapsed time: 11898.8 seconds (3.31 hours)\n\nTimestep: 2880000\nmean reward (100 episodes): 82.1600\nbest mean reward: 95.2300\ncurrent episode reward: 72.0000\nepisodes: 4893\nexploration: 0.05770\nlearning_rate: 0.00008\nelapsed time: 11942.6 seconds (3.32 hours)\n\nTimestep: 2890000\nmean reward (100 episodes): 83.7900\nbest mean reward: 95.2300\ncurrent episode reward: 80.0000\nepisodes: 4900\nexploration: 0.05748\nlearning_rate: 0.00008\nelapsed time: 11986.9 seconds (3.33 hours)\n\nTimestep: 2900000\nmean reward (100 episodes): 88.6200\nbest mean reward: 95.2300\ncurrent episode reward: 139.0000\nepisodes: 4907\nexploration: 0.05725\nlearning_rate: 0.00008\nelapsed time: 12031.1 seconds (3.34 hours)\n\nTimestep: 2910000\nmean reward (100 episodes): 88.3300\nbest mean reward: 95.2300\ncurrent episode reward: 81.0000\nepisodes: 4914\nexploration: 0.05702\nlearning_rate: 0.00008\nelapsed time: 12075.1 seconds (3.35 hours)\n\nTimestep: 2920000\nmean reward (100 episodes): 87.4500\nbest mean reward: 95.2300\ncurrent episode reward: 113.0000\nepisodes: 4921\nexploration: 0.05680\nlearning_rate: 0.00008\nelapsed time: 12119.1 seconds (3.37 hours)\n\nTimestep: 2930000\nmean reward (100 episodes): 89.0200\nbest mean reward: 95.2300\ncurrent episode reward: 100.0000\nepisodes: 4927\nexploration: 0.05658\nlearning_rate: 0.00008\nelapsed time: 12163.0 seconds (3.38 hours)\n\nTimestep: 2940000\nmean reward (100 episodes): 88.0600\nbest mean reward: 95.2300\ncurrent episode reward: 116.0000\nepisodes: 4934\nexploration: 0.05635\nlearning_rate: 0.00008\nelapsed time: 12207.3 seconds (3.39 hours)\n\nTimestep: 2950000\nmean reward (100 episodes): 92.6000\nbest mean reward: 95.2300\ncurrent episode reward: 177.0000\nepisodes: 4942\nexploration: 0.05613\nlearning_rate: 0.00008\nelapsed time: 12252.3 seconds (3.40 hours)\n\nTimestep: 2960000\nmean reward (100 episodes): 93.8800\nbest mean reward: 95.2300\ncurrent episode reward: 88.0000\nepisodes: 4949\nexploration: 0.05590\nlearning_rate: 0.00008\nelapsed time: 12296.0 seconds (3.42 hours)\n\nTimestep: 2970000\nmean reward (100 episodes): 93.2700\nbest mean reward: 95.2900\ncurrent episode reward: 116.0000\nepisodes: 4957\nexploration: 0.05568\nlearning_rate: 0.00008\nelapsed time: 12340.3 seconds (3.43 hours)\n\nTimestep: 2980000\nmean reward (100 episodes): 90.9100\nbest mean reward: 95.2900\ncurrent episode reward: 148.0000\nepisodes: 4964\nexploration: 0.05545\nlearning_rate: 0.00008\nelapsed time: 12384.1 seconds (3.44 hours)\n\nTimestep: 2990000\nmean reward (100 episodes): 93.6100\nbest mean reward: 95.2900\ncurrent episode reward: 38.0000\nepisodes: 4971\nexploration: 0.05523\nlearning_rate: 0.00008\nelapsed time: 12428.4 seconds (3.45 hours)\n\nTimestep: 3000000\nmean reward (100 episodes): 94.1900\nbest mean reward: 95.6800\ncurrent episode reward: 73.0000\nepisodes: 4979\nexploration: 0.05500\nlearning_rate: 0.00008\nelapsed time: 12473.1 seconds (3.46 hours)\n\nTimestep: 3010000\nmean reward (100 episodes): 94.6000\nbest mean reward: 95.6800\ncurrent episode reward: 93.0000\nepisodes: 4985\nexploration: 0.05478\nlearning_rate: 0.00007\nelapsed time: 12517.1 seconds (3.48 hours)\n\nTimestep: 3020000\nmean reward (100 episodes): 97.8000\nbest mean reward: 98.4800\ncurrent episode reward: 49.0000\nepisodes: 4995\nexploration: 0.05455\nlearning_rate: 0.00007\nelapsed time: 12560.7 seconds (3.49 hours)\n\nTimestep: 3030000\nmean reward (100 episodes): 99.7500\nbest mean reward: 99.7500\ncurrent episode reward: 81.0000\nepisodes: 5002\nexploration: 0.05433\nlearning_rate: 0.00007\nelapsed time: 12609.0 seconds (3.50 hours)\n\nTimestep: 3040000\nmean reward (100 episodes): 95.6500\nbest mean reward: 101.3000\ncurrent episode reward: 10.0000\nepisodes: 5011\nexploration: 0.05410\nlearning_rate: 0.00007\nelapsed time: 12653.3 seconds (3.51 hours)\n\nTimestep: 3050000\nmean reward (100 episodes): 97.4800\nbest mean reward: 101.3000\ncurrent episode reward: 58.0000\nepisodes: 5017\nexploration: 0.05388\nlearning_rate: 0.00007\nelapsed time: 12696.5 seconds (3.53 hours)\n\nTimestep: 3060000\nmean reward (100 episodes): 94.4800\nbest mean reward: 101.3000\ncurrent episode reward: 163.0000\nepisodes: 5025\nexploration: 0.05365\nlearning_rate: 0.00007\nelapsed time: 12740.8 seconds (3.54 hours)\n\nTimestep: 3070000\nmean reward (100 episodes): 93.9900\nbest mean reward: 101.3000\ncurrent episode reward: 9.0000\nepisodes: 5033\nexploration: 0.05343\nlearning_rate: 0.00007\nelapsed time: 12785.0 seconds (3.55 hours)\n\nTimestep: 3080000\nmean reward (100 episodes): 98.3400\nbest mean reward: 101.3000\ncurrent episode reward: 153.0000\nepisodes: 5040\nexploration: 0.05320\nlearning_rate: 0.00007\nelapsed time: 12829.6 seconds (3.56 hours)\n\nTimestep: 3090000\nmean reward (100 episodes): 100.5300\nbest mean reward: 101.3000\ncurrent episode reward: 122.0000\nepisodes: 5046\nexploration: 0.05298\nlearning_rate: 0.00007\nelapsed time: 12874.0 seconds (3.58 hours)\n\nTimestep: 3100000\nmean reward (100 episodes): 103.3000\nbest mean reward: 103.3000\ncurrent episode reward: 283.0000\nepisodes: 5053\nexploration: 0.05275\nlearning_rate: 0.00007\nelapsed time: 12918.1 seconds (3.59 hours)\n\nTimestep: 3110000\nmean reward (100 episodes): 107.6200\nbest mean reward: 107.7600\ncurrent episode reward: 83.0000\nepisodes: 5060\nexploration: 0.05253\nlearning_rate: 0.00007\nelapsed time: 12961.9 seconds (3.60 hours)\n\nTimestep: 3120000\nmean reward (100 episodes): 107.3000\nbest mean reward: 108.1500\ncurrent episode reward: 61.0000\nepisodes: 5068\nexploration: 0.05230\nlearning_rate: 0.00007\nelapsed time: 13006.3 seconds (3.61 hours)\n\nTimestep: 3130000\nmean reward (100 episodes): 111.8100\nbest mean reward: 111.8100\ncurrent episode reward: 45.0000\nepisodes: 5075\nexploration: 0.05208\nlearning_rate: 0.00007\nelapsed time: 13050.9 seconds (3.63 hours)\n\nTimestep: 3140000\nmean reward (100 episodes): 111.7200\nbest mean reward: 113.3700\ncurrent episode reward: 97.0000\nepisodes: 5081\nexploration: 0.05185\nlearning_rate: 0.00007\nelapsed time: 13094.2 seconds (3.64 hours)\n\nTimestep: 3150000\nmean reward (100 episodes): 115.4300\nbest mean reward: 115.4300\ncurrent episode reward: 187.0000\nepisodes: 5088\nexploration: 0.05163\nlearning_rate: 0.00007\nelapsed time: 13138.5 seconds (3.65 hours)\n\nTimestep: 3160000\nmean reward (100 episodes): 121.3600\nbest mean reward: 121.3600\ncurrent episode reward: 174.0000\nepisodes: 5095\nexploration: 0.05140\nlearning_rate: 0.00007\nelapsed time: 13182.1 seconds (3.66 hours)\n\nTimestep: 3170000\nmean reward (100 episodes): 122.8500\nbest mean reward: 122.8800\ncurrent episode reward: 109.0000\nepisodes: 5101\nexploration: 0.05117\nlearning_rate: 0.00007\nelapsed time: 13225.7 seconds (3.67 hours)\n\nTimestep: 3180000\nmean reward (100 episodes): 124.1700\nbest mean reward: 125.1800\ncurrent episode reward: 128.0000\nepisodes: 5108\nexploration: 0.05095\nlearning_rate: 0.00007\nelapsed time: 13269.8 seconds (3.69 hours)\n\nTimestep: 3190000\nmean reward (100 episodes): 122.4600\nbest mean reward: 126.1100\ncurrent episode reward: 16.0000\nepisodes: 5118\nexploration: 0.05072\nlearning_rate: 0.00007\nelapsed time: 13314.1 seconds (3.70 hours)\n\nTimestep: 3200000\nmean reward (100 episodes): 122.5800\nbest mean reward: 126.1100\ncurrent episode reward: 77.0000\nepisodes: 5126\nexploration: 0.05050\nlearning_rate: 0.00007\nelapsed time: 13358.1 seconds (3.71 hours)\n\nTimestep: 3210000\nmean reward (100 episodes): 122.9400\nbest mean reward: 126.1100\ncurrent episode reward: 126.0000\nepisodes: 5132\nexploration: 0.05028\nlearning_rate: 0.00007\nelapsed time: 13403.0 seconds (3.72 hours)\n\nTimestep: 3220000\nmean reward (100 episodes): 125.1400\nbest mean reward: 126.1100\ncurrent episode reward: 143.0000\nepisodes: 5139\nexploration: 0.05005\nlearning_rate: 0.00007\nelapsed time: 13447.5 seconds (3.74 hours)\n\nTimestep: 3230000\nmean reward (100 episodes): 125.5200\nbest mean reward: 126.1100\ncurrent episode reward: 236.0000\nepisodes: 5146\nexploration: 0.04983\nlearning_rate: 0.00007\nelapsed time: 13491.6 seconds (3.75 hours)\n\nTimestep: 3240000\nmean reward (100 episodes): 122.2600\nbest mean reward: 126.1100\ncurrent episode reward: 193.0000\nepisodes: 5153\nexploration: 0.04960\nlearning_rate: 0.00007\nelapsed time: 13535.7 seconds (3.76 hours)\n\nTimestep: 3250000\nmean reward (100 episodes): 121.0000\nbest mean reward: 126.1100\ncurrent episode reward: 63.0000\nepisodes: 5160\nexploration: 0.04938\nlearning_rate: 0.00007\nelapsed time: 13579.8 seconds (3.77 hours)\n\nTimestep: 3260000\nmean reward (100 episodes): 122.2600\nbest mean reward: 126.1100\ncurrent episode reward: 89.0000\nepisodes: 5166\nexploration: 0.04915\nlearning_rate: 0.00007\nelapsed time: 13623.7 seconds (3.78 hours)\n\nTimestep: 3270000\nmean reward (100 episodes): 121.9000\nbest mean reward: 126.1100\ncurrent episode reward: 204.0000\nepisodes: 5173\nexploration: 0.04892\nlearning_rate: 0.00007\nelapsed time: 13667.7 seconds (3.80 hours)\n\nTimestep: 3280000\nmean reward (100 episodes): 123.5600\nbest mean reward: 126.1100\ncurrent episode reward: 103.0000\nepisodes: 5181\nexploration: 0.04870\nlearning_rate: 0.00007\nelapsed time: 13712.3 seconds (3.81 hours)\n\nTimestep: 3290000\nmean reward (100 episodes): 122.2500\nbest mean reward: 126.1100\ncurrent episode reward: 3.0000\nepisodes: 5188\nexploration: 0.04847\nlearning_rate: 0.00007\nelapsed time: 13756.9 seconds (3.82 hours)\n\nTimestep: 3300000\nmean reward (100 episodes): 115.3700\nbest mean reward: 126.1100\ncurrent episode reward: 131.0000\nepisodes: 5196\nexploration: 0.04825\nlearning_rate: 0.00007\nelapsed time: 13800.7 seconds (3.83 hours)\n\nTimestep: 3310000\nmean reward (100 episodes): 111.0500\nbest mean reward: 126.1100\ncurrent episode reward: 113.0000\nepisodes: 5202\nexploration: 0.04802\nlearning_rate: 0.00007\nelapsed time: 13845.4 seconds (3.85 hours)\n\nTimestep: 3320000\nmean reward (100 episodes): 114.0600\nbest mean reward: 126.1100\ncurrent episode reward: 54.0000\nepisodes: 5209\nexploration: 0.04780\nlearning_rate: 0.00007\nelapsed time: 13888.8 seconds (3.86 hours)\n\nTimestep: 3330000\nmean reward (100 episodes): 118.6400\nbest mean reward: 126.1100\ncurrent episode reward: 125.0000\nepisodes: 5216\nexploration: 0.04757\nlearning_rate: 0.00007\nelapsed time: 13933.2 seconds (3.87 hours)\n\nTimestep: 3340000\nmean reward (100 episodes): 125.0800\nbest mean reward: 126.1100\ncurrent episode reward: 128.0000\nepisodes: 5223\nexploration: 0.04735\nlearning_rate: 0.00007\nelapsed time: 13976.7 seconds (3.88 hours)\n\nTimestep: 3350000\nmean reward (100 episodes): 129.3300\nbest mean reward: 129.3300\ncurrent episode reward: 244.0000\nepisodes: 5230\nexploration: 0.04713\nlearning_rate: 0.00007\nelapsed time: 14020.8 seconds (3.89 hours)\n\nTimestep: 3360000\nmean reward (100 episodes): 127.2900\nbest mean reward: 129.9000\ncurrent episode reward: 81.0000\nepisodes: 5237\nexploration: 0.04690\nlearning_rate: 0.00007\nelapsed time: 14065.1 seconds (3.91 hours)\n\nTimestep: 3370000\nmean reward (100 episodes): 127.1400\nbest mean reward: 129.9000\ncurrent episode reward: 131.0000\nepisodes: 5243\nexploration: 0.04667\nlearning_rate: 0.00007\nelapsed time: 14109.9 seconds (3.92 hours)\n\nTimestep: 3380000\nmean reward (100 episodes): 132.2600\nbest mean reward: 132.2600\ncurrent episode reward: 87.0000\nepisodes: 5250\nexploration: 0.04645\nlearning_rate: 0.00007\nelapsed time: 14153.3 seconds (3.93 hours)\n\nTimestep: 3390000\nmean reward (100 episodes): 134.8200\nbest mean reward: 135.0900\ncurrent episode reward: 135.0000\nepisodes: 5257\nexploration: 0.04622\nlearning_rate: 0.00007\nelapsed time: 14197.8 seconds (3.94 hours)\n\nTimestep: 3400000\nmean reward (100 episodes): 138.5500\nbest mean reward: 138.5500\ncurrent episode reward: 279.0000\nepisodes: 5264\nexploration: 0.04600\nlearning_rate: 0.00007\nelapsed time: 14242.3 seconds (3.96 hours)\n\nTimestep: 3410000\nmean reward (100 episodes): 140.9900\nbest mean reward: 141.5600\ncurrent episode reward: 260.0000\nepisodes: 5271\nexploration: 0.04577\nlearning_rate: 0.00007\nelapsed time: 14286.8 seconds (3.97 hours)\n\nTimestep: 3420000\nmean reward (100 episodes): 138.1800\nbest mean reward: 141.5600\ncurrent episode reward: 106.0000\nepisodes: 5279\nexploration: 0.04555\nlearning_rate: 0.00007\nelapsed time: 14331.4 seconds (3.98 hours)\n\nTimestep: 3430000\nmean reward (100 episodes): 138.7400\nbest mean reward: 141.5600\ncurrent episode reward: 140.0000\nepisodes: 5285\nexploration: 0.04532\nlearning_rate: 0.00007\nelapsed time: 14375.5 seconds (3.99 hours)\n\nTimestep: 3440000\nmean reward (100 episodes): 148.6000\nbest mean reward: 148.6000\ncurrent episode reward: 96.0000\nepisodes: 5292\nexploration: 0.04510\nlearning_rate: 0.00007\nelapsed time: 14419.6 seconds (4.01 hours)\n\nTimestep: 3450000\nmean reward (100 episodes): 150.7600\nbest mean reward: 152.1500\ncurrent episode reward: 20.0000\nepisodes: 5299\nexploration: 0.04487\nlearning_rate: 0.00007\nelapsed time: 14462.9 seconds (4.02 hours)\n\nTimestep: 3460000\nmean reward (100 episodes): 146.0300\nbest mean reward: 152.1500\ncurrent episode reward: 97.0000\nepisodes: 5307\nexploration: 0.04465\nlearning_rate: 0.00007\nelapsed time: 14506.7 seconds (4.03 hours)\n\nTimestep: 3470000\nmean reward (100 episodes): 146.0500\nbest mean reward: 152.1500\ncurrent episode reward: 203.0000\nepisodes: 5313\nexploration: 0.04442\nlearning_rate: 0.00007\nelapsed time: 14551.2 seconds (4.04 hours)\n\nTimestep: 3480000\nmean reward (100 episodes): 142.6300\nbest mean reward: 152.1500\ncurrent episode reward: 100.0000\nepisodes: 5320\nexploration: 0.04420\nlearning_rate: 0.00007\nelapsed time: 14595.3 seconds (4.05 hours)\n\nTimestep: 3490000\nmean reward (100 episodes): 139.7200\nbest mean reward: 152.1500\ncurrent episode reward: 92.0000\nepisodes: 5328\nexploration: 0.04397\nlearning_rate: 0.00007\nelapsed time: 14639.6 seconds (4.07 hours)\n\nTimestep: 3500000\nmean reward (100 episodes): 139.6100\nbest mean reward: 152.1500\ncurrent episode reward: 113.0000\nepisodes: 5334\nexploration: 0.04375\nlearning_rate: 0.00007\nelapsed time: 14684.4 seconds (4.08 hours)\n\nTimestep: 3510000\nmean reward (100 episodes): 134.0500\nbest mean reward: 152.1500\ncurrent episode reward: 76.0000\nepisodes: 5342\nexploration: 0.04353\nlearning_rate: 0.00007\nelapsed time: 14728.1 seconds (4.09 hours)\n\nTimestep: 3520000\nmean reward (100 episodes): 132.4400\nbest mean reward: 152.1500\ncurrent episode reward: 139.0000\nepisodes: 5348\nexploration: 0.04330\nlearning_rate: 0.00007\nelapsed time: 14772.7 seconds (4.10 hours)\n\nTimestep: 3530000\nmean reward (100 episodes): 130.8800\nbest mean reward: 152.1500\ncurrent episode reward: 175.0000\nepisodes: 5354\nexploration: 0.04308\nlearning_rate: 0.00007\nelapsed time: 14816.8 seconds (4.12 hours)\n\nTimestep: 3540000\nmean reward (100 episodes): 128.9400\nbest mean reward: 152.1500\ncurrent episode reward: 109.0000\nepisodes: 5362\nexploration: 0.04285\nlearning_rate: 0.00007\nelapsed time: 14861.5 seconds (4.13 hours)\n\nTimestep: 3550000\nmean reward (100 episodes): 126.3600\nbest mean reward: 152.1500\ncurrent episode reward: 20.0000\nepisodes: 5369\nexploration: 0.04263\nlearning_rate: 0.00007\nelapsed time: 14906.4 seconds (4.14 hours)\n\nTimestep: 3560000\nmean reward (100 episodes): 120.9100\nbest mean reward: 152.1500\ncurrent episode reward: 75.0000\nepisodes: 5378\nexploration: 0.04240\nlearning_rate: 0.00007\nelapsed time: 14950.6 seconds (4.15 hours)\n\nTimestep: 3570000\nmean reward (100 episodes): 112.8200\nbest mean reward: 152.1500\ncurrent episode reward: 23.0000\nepisodes: 5387\nexploration: 0.04218\nlearning_rate: 0.00007\nelapsed time: 14995.0 seconds (4.17 hours)\n\nTimestep: 3580000\nmean reward (100 episodes): 103.1900\nbest mean reward: 152.1500\ncurrent episode reward: 105.0000\nepisodes: 5396\nexploration: 0.04195\nlearning_rate: 0.00007\nelapsed time: 15039.8 seconds (4.18 hours)\n\nTimestep: 3590000\nmean reward (100 episodes): 103.8700\nbest mean reward: 152.1500\ncurrent episode reward: 34.0000\nepisodes: 5405\nexploration: 0.04173\nlearning_rate: 0.00007\nelapsed time: 15083.8 seconds (4.19 hours)\n\nTimestep: 3600000\nmean reward (100 episodes): 99.5200\nbest mean reward: 152.1500\ncurrent episode reward: 112.0000\nepisodes: 5413\nexploration: 0.04150\nlearning_rate: 0.00007\nelapsed time: 15128.7 seconds (4.20 hours)\n\nTimestep: 3610000\nmean reward (100 episodes): 98.6500\nbest mean reward: 152.1500\ncurrent episode reward: 79.0000\nepisodes: 5420\nexploration: 0.04127\nlearning_rate: 0.00007\nelapsed time: 15172.9 seconds (4.21 hours)\n\nTimestep: 3620000\nmean reward (100 episodes): 95.2500\nbest mean reward: 152.1500\ncurrent episode reward: 39.0000\nepisodes: 5430\nexploration: 0.04105\nlearning_rate: 0.00007\nelapsed time: 15217.1 seconds (4.23 hours)\n\nTimestep: 3630000\nmean reward (100 episodes): 80.0700\nbest mean reward: 152.1500\ncurrent episode reward: 50.0000\nepisodes: 5448\nexploration: 0.04083\nlearning_rate: 0.00007\nelapsed time: 15262.1 seconds (4.24 hours)\n\nTimestep: 3640000\nmean reward (100 episodes): 73.5800\nbest mean reward: 152.1500\ncurrent episode reward: 47.0000\nepisodes: 5456\nexploration: 0.04060\nlearning_rate: 0.00007\nelapsed time: 15306.7 seconds (4.25 hours)\n\nTimestep: 3650000\nmean reward (100 episodes): 66.4300\nbest mean reward: 152.1500\ncurrent episode reward: 34.0000\nepisodes: 5466\nexploration: 0.04038\nlearning_rate: 0.00007\nelapsed time: 15351.1 seconds (4.26 hours)\n\nTimestep: 3660000\nmean reward (100 episodes): 56.1100\nbest mean reward: 152.1500\ncurrent episode reward: 26.0000\nepisodes: 5483\nexploration: 0.04015\nlearning_rate: 0.00007\nelapsed time: 15394.9 seconds (4.28 hours)\n\nTimestep: 3670000\nmean reward (100 episodes): 42.6200\nbest mean reward: 152.1500\ncurrent episode reward: 14.0000\nepisodes: 5504\nexploration: 0.03993\nlearning_rate: 0.00007\nelapsed time: 15439.4 seconds (4.29 hours)\n\nTimestep: 3680000\nmean reward (100 episodes): 32.2600\nbest mean reward: 152.1500\ncurrent episode reward: 5.0000\nepisodes: 5522\nexploration: 0.03970\nlearning_rate: 0.00007\nelapsed time: 15483.3 seconds (4.30 hours)\n\nTimestep: 3690000\nmean reward (100 episodes): 23.3300\nbest mean reward: 152.1500\ncurrent episode reward: 10.0000\nepisodes: 5545\nexploration: 0.03947\nlearning_rate: 0.00007\nelapsed time: 15528.3 seconds (4.31 hours)\n\nTimestep: 3700000\nmean reward (100 episodes): 10.5200\nbest mean reward: 152.1500\ncurrent episode reward: 8.0000\nepisodes: 5576\nexploration: 0.03925\nlearning_rate: 0.00007\nelapsed time: 15572.6 seconds (4.33 hours)\n\nTimestep: 3710000\nmean reward (100 episodes): 8.5600\nbest mean reward: 152.1500\ncurrent episode reward: 10.0000\nepisodes: 5605\nexploration: 0.03902\nlearning_rate: 0.00007\nelapsed time: 15616.8 seconds (4.34 hours)\n\nTimestep: 3720000\nmean reward (100 episodes): 6.0800\nbest mean reward: 152.1500\ncurrent episode reward: 8.0000\nepisodes: 5639\nexploration: 0.03880\nlearning_rate: 0.00007\nelapsed time: 15661.6 seconds (4.35 hours)\n\nTimestep: 3730000\nmean reward (100 episodes): 4.6700\nbest mean reward: 152.1500\ncurrent episode reward: 3.0000\nepisodes: 5680\nexploration: 0.03857\nlearning_rate: 0.00007\nelapsed time: 15706.0 seconds (4.36 hours)\n\nTimestep: 3740000\nmean reward (100 episodes): 3.2600\nbest mean reward: 152.1500\ncurrent episode reward: 2.0000\nepisodes: 5727\nexploration: 0.03835\nlearning_rate: 0.00007\nelapsed time: 15750.7 seconds (4.38 hours)\n\nTimestep: 3750000\nmean reward (100 episodes): 2.4600\nbest mean reward: 152.1500\ncurrent episode reward: 4.0000\nepisodes: 5777\nexploration: 0.03812\nlearning_rate: 0.00007\nelapsed time: 15795.7 seconds (4.39 hours)\n\nTimestep: 3760000\nmean reward (100 episodes): 2.0300\nbest mean reward: 152.1500\ncurrent episode reward: 3.0000\nepisodes: 5833\nexploration: 0.03790\nlearning_rate: 0.00007\nelapsed time: 15840.9 seconds (4.40 hours)\n\nTimestep: 3770000\nmean reward (100 episodes): 1.8000\nbest mean reward: 152.1500\ncurrent episode reward: 0.0000\nepisodes: 5888\nexploration: 0.03768\nlearning_rate: 0.00007\nelapsed time: 15885.5 seconds (4.41 hours)\n\nTimestep: 3780000\nmean reward (100 episodes): 1.6600\nbest mean reward: 152.1500\ncurrent episode reward: 4.0000\nepisodes: 5943\nexploration: 0.03745\nlearning_rate: 0.00007\nelapsed time: 15930.0 seconds (4.42 hours)\n\nTimestep: 3790000\nmean reward (100 episodes): 1.6700\nbest mean reward: 152.1500\ncurrent episode reward: 3.0000\nepisodes: 6000\nexploration: 0.03722\nlearning_rate: 0.00007\nelapsed time: 15975.5 seconds (4.44 hours)\n\nTimestep: 3800000\nmean reward (100 episodes): 1.4800\nbest mean reward: 152.1500\ncurrent episode reward: 1.0000\nepisodes: 6058\nexploration: 0.03700\nlearning_rate: 0.00007\nelapsed time: 16020.8 seconds (4.45 hours)\n\nTimestep: 3810000\nmean reward (100 episodes): 1.8000\nbest mean reward: 152.1500\ncurrent episode reward: 0.0000\nepisodes: 6110\nexploration: 0.03678\nlearning_rate: 0.00006\nelapsed time: 16065.5 seconds (4.46 hours)\n\nTimestep: 3820000\nmean reward (100 episodes): 1.7500\nbest mean reward: 152.1500\ncurrent episode reward: 1.0000\nepisodes: 6169\nexploration: 0.03655\nlearning_rate: 0.00006\nelapsed time: 16110.3 seconds (4.48 hours)\n\nTimestep: 3830000\nmean reward (100 episodes): 1.5500\nbest mean reward: 152.1500\ncurrent episode reward: 1.0000\nepisodes: 6227\nexploration: 0.03632\nlearning_rate: 0.00006\nelapsed time: 16155.1 seconds (4.49 hours)\n\nTimestep: 3840000\nmean reward (100 episodes): 1.8500\nbest mean reward: 152.1500\ncurrent episode reward: 2.0000\nepisodes: 6281\nexploration: 0.03610\nlearning_rate: 0.00006\nelapsed time: 16200.6 seconds (4.50 hours)\n\nTimestep: 3850000\nmean reward (100 episodes): 1.9400\nbest mean reward: 152.1500\ncurrent episode reward: 4.0000\nepisodes: 6334\nexploration: 0.03587\nlearning_rate: 0.00006\nelapsed time: 16245.6 seconds (4.51 hours)\n\nTimestep: 3860000\nmean reward (100 episodes): 1.9700\nbest mean reward: 152.1500\ncurrent episode reward: 1.0000\nepisodes: 6388\nexploration: 0.03565\nlearning_rate: 0.00006\nelapsed time: 16290.5 seconds (4.53 hours)\n\nTimestep: 3870000\nmean reward (100 episodes): 1.8800\nbest mean reward: 152.1500\ncurrent episode reward: 5.0000\nepisodes: 6443\nexploration: 0.03542\nlearning_rate: 0.00006\nelapsed time: 16335.7 seconds (4.54 hours)\n\nTimestep: 3880000\nmean reward (100 episodes): 1.6400\nbest mean reward: 152.1500\ncurrent episode reward: 1.0000\nepisodes: 6501\nexploration: 0.03520\nlearning_rate: 0.00006\nelapsed time: 16380.8 seconds (4.55 hours)\n\nTimestep: 3890000\nmean reward (100 episodes): 1.5600\nbest mean reward: 152.1500\ncurrent episode reward: 0.0000\nepisodes: 6559\nexploration: 0.03497\nlearning_rate: 0.00006\nelapsed time: 16425.4 seconds (4.56 hours)\n\nTimestep: 3900000\nmean reward (100 episodes): 1.6500\nbest mean reward: 152.1500\ncurrent episode reward: 0.0000\nepisodes: 6615\nexploration: 0.03475\nlearning_rate: 0.00006\nelapsed time: 16469.9 seconds (4.57 hours)\n\nTimestep: 3910000\nmean reward (100 episodes): 1.6100\nbest mean reward: 152.1500\ncurrent episode reward: 2.0000\nepisodes: 6674\nexploration: 0.03453\nlearning_rate: 0.00006\nelapsed time: 16514.5 seconds (4.59 hours)\n\nTimestep: 3920000\nmean reward (100 episodes): 1.1800\nbest mean reward: 152.1500\ncurrent episode reward: 1.0000\nepisodes: 6737\nexploration: 0.03430\nlearning_rate: 0.00006\nelapsed time: 16559.7 seconds (4.60 hours)\n\nTimestep: 3930000\nmean reward (100 episodes): 1.2500\nbest mean reward: 152.1500\ncurrent episode reward: 0.0000\nepisodes: 6798\nexploration: 0.03407\nlearning_rate: 0.00006\nelapsed time: 16604.5 seconds (4.61 hours)\n\nTimestep: 3940000\nmean reward (100 episodes): 1.5200\nbest mean reward: 152.1500\ncurrent episode reward: 2.0000\nepisodes: 6854\nexploration: 0.03385\nlearning_rate: 0.00006\nelapsed time: 16648.7 seconds (4.62 hours)\n\nTimestep: 3950000\nmean reward (100 episodes): 2.0600\nbest mean reward: 152.1500\ncurrent episode reward: 1.0000\nepisodes: 6903\nexploration: 0.03362\nlearning_rate: 0.00006\nelapsed time: 16693.6 seconds (4.64 hours)\n\nTimestep: 3960000\nmean reward (100 episodes): 2.2000\nbest mean reward: 152.1500\ncurrent episode reward: 3.0000\nepisodes: 6955\nexploration: 0.03340\nlearning_rate: 0.00006\nelapsed time: 16737.9 seconds (4.65 hours)\n\nTimestep: 3970000\nmean reward (100 episodes): 1.9700\nbest mean reward: 152.1500\ncurrent episode reward: 1.0000\nepisodes: 7008\nexploration: 0.03317\nlearning_rate: 0.00006\nelapsed time: 16783.1 seconds (4.66 hours)\n\nTimestep: 3980000\nmean reward (100 episodes): 1.9300\nbest mean reward: 152.1500\ncurrent episode reward: 0.0000\nepisodes: 7060\nexploration: 0.03295\nlearning_rate: 0.00006\nelapsed time: 16828.1 seconds (4.67 hours)\n\nTimestep: 3990000\nmean reward (100 episodes): 2.1100\nbest mean reward: 152.1500\ncurrent episode reward: 3.0000\nepisodes: 7111\nexploration: 0.03272\nlearning_rate: 0.00006\nelapsed time: 16873.0 seconds (4.69 hours)\n\nTimestep: 4000000\nmean reward (100 episodes): 2.2500\nbest mean reward: 152.1500\ncurrent episode reward: 3.0000\nepisodes: 7160\nexploration: 0.03250\nlearning_rate: 0.00006\nelapsed time: 16917.6 seconds (4.70 hours)\n\nTimestep: 4010000\nmean reward (100 episodes): 2.3500\nbest mean reward: 152.1500\ncurrent episode reward: 4.0000\nepisodes: 7210\nexploration: 0.03227\nlearning_rate: 0.00006\nelapsed time: 16962.5 seconds (4.71 hours)\n\nTimestep: 4020000\nmean reward (100 episodes): 2.1700\nbest mean reward: 152.1500\ncurrent episode reward: 7.0000\nepisodes: 7262\nexploration: 0.03205\nlearning_rate: 0.00006\nelapsed time: 17007.3 seconds (4.72 hours)\n\nTimestep: 4030000\nmean reward (100 episodes): 2.2000\nbest mean reward: 152.1500\ncurrent episode reward: 4.0000\nepisodes: 7311\nexploration: 0.03183\nlearning_rate: 0.00006\nelapsed time: 17052.1 seconds (4.74 hours)\n\nTimestep: 4040000\nmean reward (100 episodes): 2.1700\nbest mean reward: 152.1500\ncurrent episode reward: 4.0000\nepisodes: 7363\nexploration: 0.03160\nlearning_rate: 0.00006\nelapsed time: 17096.3 seconds (4.75 hours)\n\nTimestep: 4050000\nmean reward (100 episodes): 1.9900\nbest mean reward: 152.1500\ncurrent episode reward: 0.0000\nepisodes: 7416\nexploration: 0.03138\nlearning_rate: 0.00006\nelapsed time: 17141.1 seconds (4.76 hours)\n\nTimestep: 4060000\nmean reward (100 episodes): 2.0500\nbest mean reward: 152.1500\ncurrent episode reward: 0.0000\nepisodes: 7466\nexploration: 0.03115\nlearning_rate: 0.00006\nelapsed time: 17185.8 seconds (4.77 hours)\n\nTimestep: 4070000\nmean reward (100 episodes): 2.0800\nbest mean reward: 152.1500\ncurrent episode reward: 4.0000\nepisodes: 7517\nexploration: 0.03092\nlearning_rate: 0.00006\nelapsed time: 17230.4 seconds (4.79 hours)\n\nTimestep: 4080000\nmean reward (100 episodes): 2.2000\nbest mean reward: 152.1500\ncurrent episode reward: 4.0000\nepisodes: 7566\nexploration: 0.03070\nlearning_rate: 0.00006\nelapsed time: 17274.9 seconds (4.80 hours)\n\nTimestep: 4090000\nmean reward (100 episodes): 2.4600\nbest mean reward: 152.1500\ncurrent episode reward: 1.0000\nepisodes: 7614\nexploration: 0.03048\nlearning_rate: 0.00006\nelapsed time: 17319.7 seconds (4.81 hours)\n\nTimestep: 4100000\nmean reward (100 episodes): 2.6200\nbest mean reward: 152.1500\ncurrent episode reward: 0.0000\nepisodes: 7660\nexploration: 0.03025\nlearning_rate: 0.00006\nelapsed time: 17363.8 seconds (4.82 hours)\n\nTimestep: 4110000\nmean reward (100 episodes): 2.7000\nbest mean reward: 152.1500\ncurrent episode reward: 3.0000\nepisodes: 7705\nexploration: 0.03002\nlearning_rate: 0.00006\nelapsed time: 17408.3 seconds (4.84 hours)\n\nTimestep: 4120000\nmean reward (100 episodes): 3.4100\nbest mean reward: 152.1500\ncurrent episode reward: 4.0000\nepisodes: 7740\nexploration: 0.02980\nlearning_rate: 0.00006\nelapsed time: 17452.7 seconds (4.85 hours)\n\nTimestep: 4130000\nmean reward (100 episodes): 4.0000\nbest mean reward: 152.1500\ncurrent episode reward: 5.0000\nepisodes: 7776\nexploration: 0.02958\nlearning_rate: 0.00006\nelapsed time: 17497.2 seconds (4.86 hours)\n\nTimestep: 4140000\nmean reward (100 episodes): 4.3500\nbest mean reward: 152.1500\ncurrent episode reward: 10.0000\nepisodes: 7813\nexploration: 0.02935\nlearning_rate: 0.00006\nelapsed time: 17541.5 seconds (4.87 hours)\n\nTimestep: 4150000\nmean reward (100 episodes): 4.5300\nbest mean reward: 152.1500\ncurrent episode reward: 3.0000\nepisodes: 7846\nexploration: 0.02912\nlearning_rate: 0.00006\nelapsed time: 17585.9 seconds (4.88 hours)\n\nTimestep: 4160000\nmean reward (100 episodes): 4.7600\nbest mean reward: 152.1500\ncurrent episode reward: 3.0000\nepisodes: 7879\nexploration: 0.02890\nlearning_rate: 0.00006\nelapsed time: 17630.0 seconds (4.90 hours)\n\nTimestep: 4170000\nmean reward (100 episodes): 4.9400\nbest mean reward: 152.1500\ncurrent episode reward: 3.0000\nepisodes: 7914\nexploration: 0.02867\nlearning_rate: 0.00006\nelapsed time: 17674.3 seconds (4.91 hours)\n\nTimestep: 4180000\nmean reward (100 episodes): 5.0200\nbest mean reward: 152.1500\ncurrent episode reward: 5.0000\nepisodes: 7945\nexploration: 0.02845\nlearning_rate: 0.00006\nelapsed time: 17718.5 seconds (4.92 hours)\n\nTimestep: 4190000\nmean reward (100 episodes): 5.0600\nbest mean reward: 152.1500\ncurrent episode reward: 2.0000\nepisodes: 7978\nexploration: 0.02823\nlearning_rate: 0.00006\nelapsed time: 17762.4 seconds (4.93 hours)\n\nTimestep: 4200000\nmean reward (100 episodes): 5.4800\nbest mean reward: 152.1500\ncurrent episode reward: 4.0000\nepisodes: 8007\nexploration: 0.02800\nlearning_rate: 0.00006\nelapsed time: 17808.3 seconds (4.95 hours)\n\nTimestep: 4210000\nmean reward (100 episodes): 5.9500\nbest mean reward: 152.1500\ncurrent episode reward: 5.0000\nepisodes: 8034\nexploration: 0.02777\nlearning_rate: 0.00006\nelapsed time: 17852.8 seconds (4.96 hours)\n\nTimestep: 4220000\nmean reward (100 episodes): 6.5300\nbest mean reward: 152.1500\ncurrent episode reward: 9.0000\nepisodes: 8062\nexploration: 0.02755\nlearning_rate: 0.00006\nelapsed time: 17897.3 seconds (4.97 hours)\n\nTimestep: 4230000\nmean reward (100 episodes): 7.3700\nbest mean reward: 152.1500\ncurrent episode reward: 9.0000\nepisodes: 8086\nexploration: 0.02733\nlearning_rate: 0.00006\nelapsed time: 17942.2 seconds (4.98 hours)\n\nTimestep: 4240000\nmean reward (100 episodes): 7.9100\nbest mean reward: 152.1500\ncurrent episode reward: 7.0000\nepisodes: 8109\nexploration: 0.02710\nlearning_rate: 0.00006\nelapsed time: 17987.0 seconds (5.00 hours)\n\nTimestep: 4250000\nmean reward (100 episodes): 8.5500\nbest mean reward: 152.1500\ncurrent episode reward: 6.0000\nepisodes: 8132\nexploration: 0.02687\nlearning_rate: 0.00006\nelapsed time: 18031.7 seconds (5.01 hours)\n\nTimestep: 4260000\nmean reward (100 episodes): 8.9700\nbest mean reward: 152.1500\ncurrent episode reward: 6.0000\nepisodes: 8157\nexploration: 0.02665\nlearning_rate: 0.00006\nelapsed time: 18077.2 seconds (5.02 hours)\n\nTimestep: 4270000\nmean reward (100 episodes): 9.3000\nbest mean reward: 152.1500\ncurrent episode reward: 10.0000\nepisodes: 8179\nexploration: 0.02642\nlearning_rate: 0.00006\nelapsed time: 18121.6 seconds (5.03 hours)\n\nTimestep: 4280000\nmean reward (100 episodes): 9.8300\nbest mean reward: 152.1500\ncurrent episode reward: 15.0000\nepisodes: 8199\nexploration: 0.02620\nlearning_rate: 0.00006\nelapsed time: 18166.4 seconds (5.05 hours)\n\nTimestep: 4290000\nmean reward (100 episodes): 10.2800\nbest mean reward: 152.1500\ncurrent episode reward: 11.0000\nepisodes: 8220\nexploration: 0.02597\nlearning_rate: 0.00006\nelapsed time: 18210.5 seconds (5.06 hours)\n\nTimestep: 4300000\nmean reward (100 episodes): 10.4500\nbest mean reward: 152.1500\ncurrent episode reward: 10.0000\nepisodes: 8241\nexploration: 0.02575\nlearning_rate: 0.00006\nelapsed time: 18255.5 seconds (5.07 hours)\n\nTimestep: 4310000\nmean reward (100 episodes): 11.1400\nbest mean reward: 152.1500\ncurrent episode reward: 23.0000\nepisodes: 8261\nexploration: 0.02552\nlearning_rate: 0.00006\nelapsed time: 18299.0 seconds (5.08 hours)\n\nTimestep: 4320000\nmean reward (100 episodes): 11.4900\nbest mean reward: 152.1500\ncurrent episode reward: 9.0000\nepisodes: 8280\nexploration: 0.02530\nlearning_rate: 0.00006\nelapsed time: 18343.3 seconds (5.10 hours)\n\nTimestep: 4330000\nmean reward (100 episodes): 11.6600\nbest mean reward: 152.1500\ncurrent episode reward: 9.0000\nepisodes: 8299\nexploration: 0.02508\nlearning_rate: 0.00006\nelapsed time: 18387.6 seconds (5.11 hours)\n\nTimestep: 4340000\nmean reward (100 episodes): 12.4400\nbest mean reward: 152.1500\ncurrent episode reward: 11.0000\nepisodes: 8316\nexploration: 0.02485\nlearning_rate: 0.00006\nelapsed time: 18432.0 seconds (5.12 hours)\n\nTimestep: 4350000\nmean reward (100 episodes): 13.3900\nbest mean reward: 152.1500\ncurrent episode reward: 13.0000\nepisodes: 8334\nexploration: 0.02462\nlearning_rate: 0.00006\nelapsed time: 18475.8 seconds (5.13 hours)\n\nTimestep: 4360000\nmean reward (100 episodes): 14.4000\nbest mean reward: 152.1500\ncurrent episode reward: 15.0000\nepisodes: 8351\nexploration: 0.02440\nlearning_rate: 0.00006\nelapsed time: 18519.8 seconds (5.14 hours)\n\nTimestep: 4370000\nmean reward (100 episodes): 14.8600\nbest mean reward: 152.1500\ncurrent episode reward: 12.0000\nepisodes: 8369\nexploration: 0.02417\nlearning_rate: 0.00006\nelapsed time: 18564.1 seconds (5.16 hours)\n\nTimestep: 4380000\nmean reward (100 episodes): 15.6700\nbest mean reward: 152.1500\ncurrent episode reward: 14.0000\nepisodes: 8385\nexploration: 0.02395\nlearning_rate: 0.00006\nelapsed time: 18608.2 seconds (5.17 hours)\n\nTimestep: 4390000\nmean reward (100 episodes): 16.2300\nbest mean reward: 152.1500\ncurrent episode reward: 19.0000\nepisodes: 8402\nexploration: 0.02372\nlearning_rate: 0.00006\nelapsed time: 18652.3 seconds (5.18 hours)\n\nTimestep: 4400000\nmean reward (100 episodes): 15.8000\nbest mean reward: 152.1500\ncurrent episode reward: 18.0000\nepisodes: 8420\nexploration: 0.02350\nlearning_rate: 0.00006\nelapsed time: 18696.9 seconds (5.19 hours)\n\nTimestep: 4410000\nmean reward (100 episodes): 15.2800\nbest mean reward: 152.1500\ncurrent episode reward: 17.0000\nepisodes: 8438\nexploration: 0.02327\nlearning_rate: 0.00006\nelapsed time: 18741.3 seconds (5.21 hours)\n\nTimestep: 4420000\nmean reward (100 episodes): 15.5400\nbest mean reward: 152.1500\ncurrent episode reward: 12.0000\nepisodes: 8455\nexploration: 0.02305\nlearning_rate: 0.00006\nelapsed time: 18785.6 seconds (5.22 hours)\n\nTimestep: 4430000\nmean reward (100 episodes): 15.7200\nbest mean reward: 152.1500\ncurrent episode reward: 16.0000\nepisodes: 8471\nexploration: 0.02282\nlearning_rate: 0.00006\nelapsed time: 18830.3 seconds (5.23 hours)\n\nTimestep: 4440000\nmean reward (100 episodes): 15.5100\nbest mean reward: 152.1500\ncurrent episode reward: 19.0000\nepisodes: 8488\nexploration: 0.02260\nlearning_rate: 0.00006\nelapsed time: 18873.9 seconds (5.24 hours)\n\nTimestep: 4450000\nmean reward (100 episodes): 15.3800\nbest mean reward: 152.1500\ncurrent episode reward: 13.0000\nepisodes: 8504\nexploration: 0.02237\nlearning_rate: 0.00006\nelapsed time: 18917.4 seconds (5.25 hours)\n\nTimestep: 4460000\nmean reward (100 episodes): 15.8000\nbest mean reward: 152.1500\ncurrent episode reward: 14.0000\nepisodes: 8521\nexploration: 0.02215\nlearning_rate: 0.00006\nelapsed time: 18961.5 seconds (5.27 hours)\n\nTimestep: 4470000\nmean reward (100 episodes): 16.2800\nbest mean reward: 152.1500\ncurrent episode reward: 11.0000\nepisodes: 8538\nexploration: 0.02192\nlearning_rate: 0.00006\nelapsed time: 19006.1 seconds (5.28 hours)\n\nTimestep: 4480000\nmean reward (100 episodes): 16.2100\nbest mean reward: 152.1500\ncurrent episode reward: 12.0000\nepisodes: 8554\nexploration: 0.02170\nlearning_rate: 0.00006\nelapsed time: 19050.7 seconds (5.29 hours)\n\nTimestep: 4490000\nmean reward (100 episodes): 16.0000\nbest mean reward: 152.1500\ncurrent episode reward: 12.0000\nepisodes: 8571\nexploration: 0.02147\nlearning_rate: 0.00006\nelapsed time: 19095.4 seconds (5.30 hours)\n\nTimestep: 4500000\nmean reward (100 episodes): 16.5100\nbest mean reward: 152.1500\ncurrent episode reward: 15.0000\nepisodes: 8585\nexploration: 0.02125\nlearning_rate: 0.00006\nelapsed time: 19139.6 seconds (5.32 hours)\n\nTimestep: 4510000\nmean reward (100 episodes): 17.3600\nbest mean reward: 152.1500\ncurrent episode reward: 27.0000\nepisodes: 8599\nexploration: 0.02103\nlearning_rate: 0.00006\nelapsed time: 19183.7 seconds (5.33 hours)\n\nTimestep: 4520000\nmean reward (100 episodes): 18.3100\nbest mean reward: 152.1500\ncurrent episode reward: 11.0000\nepisodes: 8613\nexploration: 0.02080\nlearning_rate: 0.00006\nelapsed time: 19227.3 seconds (5.34 hours)\n\nTimestep: 4530000\nmean reward (100 episodes): 19.1200\nbest mean reward: 152.1500\ncurrent episode reward: 35.0000\nepisodes: 8625\nexploration: 0.02057\nlearning_rate: 0.00006\nelapsed time: 19271.6 seconds (5.35 hours)\n\nTimestep: 4540000\nmean reward (100 episodes): 20.1500\nbest mean reward: 152.1500\ncurrent episode reward: 27.0000\nepisodes: 8638\nexploration: 0.02035\nlearning_rate: 0.00006\nelapsed time: 19315.5 seconds (5.37 hours)\n\nTimestep: 4550000\nmean reward (100 episodes): 21.2000\nbest mean reward: 152.1500\ncurrent episode reward: 20.0000\nepisodes: 8650\nexploration: 0.02013\nlearning_rate: 0.00006\nelapsed time: 19360.4 seconds (5.38 hours)\n\nTimestep: 4560000\nmean reward (100 episodes): 22.4600\nbest mean reward: 152.1500\ncurrent episode reward: 32.0000\nepisodes: 8662\nexploration: 0.01990\nlearning_rate: 0.00006\nelapsed time: 19404.0 seconds (5.39 hours)\n\nTimestep: 4570000\nmean reward (100 episodes): 23.4700\nbest mean reward: 152.1500\ncurrent episode reward: 40.0000\nepisodes: 8674\nexploration: 0.01967\nlearning_rate: 0.00006\nelapsed time: 19448.0 seconds (5.40 hours)\n\nTimestep: 4580000\nmean reward (100 episodes): 25.0900\nbest mean reward: 152.1500\ncurrent episode reward: 33.0000\nepisodes: 8686\nexploration: 0.01945\nlearning_rate: 0.00006\nelapsed time: 19492.3 seconds (5.41 hours)\n\nTimestep: 4590000\nmean reward (100 episodes): 25.5200\nbest mean reward: 152.1500\ncurrent episode reward: 22.0000\nepisodes: 8698\nexploration: 0.01923\nlearning_rate: 0.00006\nelapsed time: 19536.1 seconds (5.43 hours)\n\nTimestep: 4600000\nmean reward (100 episodes): 25.5600\nbest mean reward: 152.1500\ncurrent episode reward: 32.0000\nepisodes: 8712\nexploration: 0.01900\nlearning_rate: 0.00006\nelapsed time: 19581.2 seconds (5.44 hours)\n\nTimestep: 4610000\nmean reward (100 episodes): 26.1100\nbest mean reward: 152.1500\ncurrent episode reward: 22.0000\nepisodes: 8723\nexploration: 0.01878\nlearning_rate: 0.00005\nelapsed time: 19625.8 seconds (5.45 hours)\n\nTimestep: 4620000\nmean reward (100 episodes): 26.7300\nbest mean reward: 152.1500\ncurrent episode reward: 20.0000\nepisodes: 8734\nexploration: 0.01855\nlearning_rate: 0.00005\nelapsed time: 19669.9 seconds (5.46 hours)\n\nTimestep: 4630000\nmean reward (100 episodes): 26.9600\nbest mean reward: 152.1500\ncurrent episode reward: 18.0000\nepisodes: 8745\nexploration: 0.01832\nlearning_rate: 0.00005\nelapsed time: 19714.4 seconds (5.48 hours)\n\nTimestep: 4640000\nmean reward (100 episodes): 27.5200\nbest mean reward: 152.1500\ncurrent episode reward: 46.0000\nepisodes: 8756\nexploration: 0.01810\nlearning_rate: 0.00005\nelapsed time: 19759.0 seconds (5.49 hours)\n\nTimestep: 4650000\nmean reward (100 episodes): 28.8300\nbest mean reward: 152.1500\ncurrent episode reward: 29.0000\nepisodes: 8766\nexploration: 0.01788\nlearning_rate: 0.00005\nelapsed time: 19803.9 seconds (5.50 hours)\n\nTimestep: 4660000\nmean reward (100 episodes): 29.7300\nbest mean reward: 152.1500\ncurrent episode reward: 54.0000\nepisodes: 8775\nexploration: 0.01765\nlearning_rate: 0.00005\nelapsed time: 19847.4 seconds (5.51 hours)\n\nTimestep: 4670000\nmean reward (100 episodes): 31.4900\nbest mean reward: 152.1500\ncurrent episode reward: 50.0000\nepisodes: 8784\nexploration: 0.01742\nlearning_rate: 0.00005\nelapsed time: 19891.8 seconds (5.53 hours)\n\nTimestep: 4680000\nmean reward (100 episodes): 32.0800\nbest mean reward: 152.1500\ncurrent episode reward: 38.0000\nepisodes: 8793\nexploration: 0.01720\nlearning_rate: 0.00005\nelapsed time: 19935.7 seconds (5.54 hours)\n\nTimestep: 4690000\nmean reward (100 episodes): 34.0500\nbest mean reward: 152.1500\ncurrent episode reward: 47.0000\nepisodes: 8803\nexploration: 0.01697\nlearning_rate: 0.00005\nelapsed time: 19980.5 seconds (5.55 hours)\n\nTimestep: 4700000\nmean reward (100 episodes): 36.0400\nbest mean reward: 152.1500\ncurrent episode reward: 31.0000\nepisodes: 8811\nexploration: 0.01675\nlearning_rate: 0.00005\nelapsed time: 20025.3 seconds (5.56 hours)\n\nTimestep: 4710000\nmean reward (100 episodes): 36.9800\nbest mean reward: 152.1500\ncurrent episode reward: 26.0000\nepisodes: 8821\nexploration: 0.01652\nlearning_rate: 0.00005\nelapsed time: 20069.3 seconds (5.57 hours)\n\nTimestep: 4720000\nmean reward (100 episodes): 38.0300\nbest mean reward: 152.1500\ncurrent episode reward: 70.0000\nepisodes: 8831\nexploration: 0.01630\nlearning_rate: 0.00005\nelapsed time: 20113.9 seconds (5.59 hours)\n\nTimestep: 4730000\nmean reward (100 episodes): 40.3900\nbest mean reward: 152.1500\ncurrent episode reward: 62.0000\nepisodes: 8838\nexploration: 0.01607\nlearning_rate: 0.00005\nelapsed time: 20158.3 seconds (5.60 hours)\n\nTimestep: 4740000\nmean reward (100 episodes): 42.1400\nbest mean reward: 152.1500\ncurrent episode reward: 39.0000\nepisodes: 8846\nexploration: 0.01585\nlearning_rate: 0.00005\nelapsed time: 20201.9 seconds (5.61 hours)\n\nTimestep: 4750000\nmean reward (100 episodes): 43.6500\nbest mean reward: 152.1500\ncurrent episode reward: 55.0000\nepisodes: 8854\nexploration: 0.01562\nlearning_rate: 0.00005\nelapsed time: 20246.3 seconds (5.62 hours)\n\nTimestep: 4760000\nmean reward (100 episodes): 45.4600\nbest mean reward: 152.1500\ncurrent episode reward: 67.0000\nepisodes: 8862\nexploration: 0.01540\nlearning_rate: 0.00005\nelapsed time: 20290.6 seconds (5.64 hours)\n\nTimestep: 4770000\nmean reward (100 episodes): 46.1000\nbest mean reward: 152.1500\ncurrent episode reward: 64.0000\nepisodes: 8870\nexploration: 0.01517\nlearning_rate: 0.00005\nelapsed time: 20334.9 seconds (5.65 hours)\n\nTimestep: 4780000\nmean reward (100 episodes): 46.3600\nbest mean reward: 152.1500\ncurrent episode reward: 50.0000\nepisodes: 8879\nexploration: 0.01495\nlearning_rate: 0.00005\nelapsed time: 20378.9 seconds (5.66 hours)\n\nTimestep: 4790000\nmean reward (100 episodes): 47.5600\nbest mean reward: 152.1500\ncurrent episode reward: 75.0000\nepisodes: 8886\nexploration: 0.01472\nlearning_rate: 0.00005\nelapsed time: 20422.9 seconds (5.67 hours)\n\nTimestep: 4800000\nmean reward (100 episodes): 48.5600\nbest mean reward: 152.1500\ncurrent episode reward: 88.0000\nepisodes: 8895\nexploration: 0.01450\nlearning_rate: 0.00005\nelapsed time: 20467.5 seconds (5.69 hours)\n\nTimestep: 4810000\nmean reward (100 episodes): 50.1200\nbest mean reward: 152.1500\ncurrent episode reward: 78.0000\nepisodes: 8903\nexploration: 0.01427\nlearning_rate: 0.00005\nelapsed time: 20511.8 seconds (5.70 hours)\n\nTimestep: 4820000\nmean reward (100 episodes): 51.0000\nbest mean reward: 152.1500\ncurrent episode reward: 59.0000\nepisodes: 8910\nexploration: 0.01405\nlearning_rate: 0.00005\nelapsed time: 20556.2 seconds (5.71 hours)\n\nTimestep: 4830000\nmean reward (100 episodes): 52.7100\nbest mean reward: 152.1500\ncurrent episode reward: 75.0000\nepisodes: 8919\nexploration: 0.01382\nlearning_rate: 0.00005\nelapsed time: 20600.9 seconds (5.72 hours)\n\nTimestep: 4840000\nmean reward (100 episodes): 53.4400\nbest mean reward: 152.1500\ncurrent episode reward: 37.0000\nepisodes: 8928\nexploration: 0.01360\nlearning_rate: 0.00005\nelapsed time: 20645.2 seconds (5.73 hours)\n\nTimestep: 4850000\nmean reward (100 episodes): 53.7400\nbest mean reward: 152.1500\ncurrent episode reward: 63.0000\nepisodes: 8936\nexploration: 0.01337\nlearning_rate: 0.00005\nelapsed time: 20688.7 seconds (5.75 hours)\n\nTimestep: 4860000\nmean reward (100 episodes): 53.1200\nbest mean reward: 152.1500\ncurrent episode reward: 33.0000\nepisodes: 8944\nexploration: 0.01315\nlearning_rate: 0.00005\nelapsed time: 20733.6 seconds (5.76 hours)\n\nTimestep: 4870000\nmean reward (100 episodes): 54.6400\nbest mean reward: 152.1500\ncurrent episode reward: 67.0000\nepisodes: 8952\nexploration: 0.01292\nlearning_rate: 0.00005\nelapsed time: 20777.5 seconds (5.77 hours)\n\nTimestep: 4880000\nmean reward (100 episodes): 54.1100\nbest mean reward: 152.1500\ncurrent episode reward: 43.0000\nepisodes: 8960\nexploration: 0.01270\nlearning_rate: 0.00005\nelapsed time: 20821.1 seconds (5.78 hours)\n\nTimestep: 4890000\nmean reward (100 episodes): 55.4100\nbest mean reward: 152.1500\ncurrent episode reward: 55.0000\nepisodes: 8968\nexploration: 0.01247\nlearning_rate: 0.00005\nelapsed time: 20865.3 seconds (5.80 hours)\n\nTimestep: 4900000\nmean reward (100 episodes): 56.2100\nbest mean reward: 152.1500\ncurrent episode reward: 33.0000\nepisodes: 8975\nexploration: 0.01225\nlearning_rate: 0.00005\nelapsed time: 20909.3 seconds (5.81 hours)\n\nTimestep: 4910000\nmean reward (100 episodes): 56.9700\nbest mean reward: 152.1500\ncurrent episode reward: 74.0000\nepisodes: 8983\nexploration: 0.01202\nlearning_rate: 0.00005\nelapsed time: 20954.9 seconds (5.82 hours)\n\nTimestep: 4920000\nmean reward (100 episodes): 57.3200\nbest mean reward: 152.1500\ncurrent episode reward: 68.0000\nepisodes: 8990\nexploration: 0.01180\nlearning_rate: 0.00005\nelapsed time: 20999.6 seconds (5.83 hours)\n\nTimestep: 4930000\nmean reward (100 episodes): 59.3000\nbest mean reward: 152.1500\ncurrent episode reward: 87.0000\nepisodes: 8998\nexploration: 0.01157\nlearning_rate: 0.00005\nelapsed time: 21043.8 seconds (5.85 hours)\n\nTimestep: 4940000\nmean reward (100 episodes): 59.6200\nbest mean reward: 152.1500\ncurrent episode reward: 86.0000\nepisodes: 9006\nexploration: 0.01135\nlearning_rate: 0.00005\nelapsed time: 21092.4 seconds (5.86 hours)\n\nTimestep: 4950000\nmean reward (100 episodes): 60.8600\nbest mean reward: 152.1500\ncurrent episode reward: 73.0000\nepisodes: 9013\nexploration: 0.01112\nlearning_rate: 0.00005\nelapsed time: 21136.9 seconds (5.87 hours)\n\nTimestep: 4960000\nmean reward (100 episodes): 62.0600\nbest mean reward: 152.1500\ncurrent episode reward: 110.0000\nepisodes: 9020\nexploration: 0.01090\nlearning_rate: 0.00005\nelapsed time: 21182.0 seconds (5.88 hours)\n\nTimestep: 4970000\nmean reward (100 episodes): 63.9600\nbest mean reward: 152.1500\ncurrent episode reward: 72.0000\nepisodes: 9027\nexploration: 0.01067\nlearning_rate: 0.00005\nelapsed time: 21226.2 seconds (5.90 hours)\n\nTimestep: 4980000\nmean reward (100 episodes): 66.2000\nbest mean reward: 152.1500\ncurrent episode reward: 74.0000\nepisodes: 9034\nexploration: 0.01045\nlearning_rate: 0.00005\nelapsed time: 21270.8 seconds (5.91 hours)\n\nTimestep: 4990000\nmean reward (100 episodes): 68.8800\nbest mean reward: 152.1500\ncurrent episode reward: 61.0000\nepisodes: 9041\nexploration: 0.01022\nlearning_rate: 0.00005\nelapsed time: 21315.0 seconds (5.92 hours)\n\nTimestep: 5000000\nmean reward (100 episodes): 69.1400\nbest mean reward: 152.1500\ncurrent episode reward: 83.0000\nepisodes: 9048\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21359.3 seconds (5.93 hours)\n\nTimestep: 5010000\nmean reward (100 episodes): 70.1400\nbest mean reward: 152.1500\ncurrent episode reward: 82.0000\nepisodes: 9056\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21403.8 seconds (5.95 hours)\n\nTimestep: 5020000\nmean reward (100 episodes): 71.9400\nbest mean reward: 152.1500\ncurrent episode reward: 53.0000\nepisodes: 9063\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21448.4 seconds (5.96 hours)\n\nTimestep: 5030000\nmean reward (100 episodes): 74.8400\nbest mean reward: 152.1500\ncurrent episode reward: 69.0000\nepisodes: 9070\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21492.6 seconds (5.97 hours)\n\nTimestep: 5040000\nmean reward (100 episodes): 78.0900\nbest mean reward: 152.1500\ncurrent episode reward: 109.0000\nepisodes: 9077\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21537.6 seconds (5.98 hours)\n\nTimestep: 5050000\nmean reward (100 episodes): 79.4000\nbest mean reward: 152.1500\ncurrent episode reward: 93.0000\nepisodes: 9084\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21582.7 seconds (6.00 hours)\n\nTimestep: 5060000\nmean reward (100 episodes): 78.6800\nbest mean reward: 152.1500\ncurrent episode reward: 63.0000\nepisodes: 9093\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21626.9 seconds (6.01 hours)\n\nTimestep: 5070000\nmean reward (100 episodes): 78.4400\nbest mean reward: 152.1500\ncurrent episode reward: 55.0000\nepisodes: 9101\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21670.7 seconds (6.02 hours)\n\nTimestep: 5080000\nmean reward (100 episodes): 78.2000\nbest mean reward: 152.1500\ncurrent episode reward: 80.0000\nepisodes: 9108\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21715.4 seconds (6.03 hours)\n\nTimestep: 5090000\nmean reward (100 episodes): 77.6700\nbest mean reward: 152.1500\ncurrent episode reward: 80.0000\nepisodes: 9115\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21760.4 seconds (6.04 hours)\n\nTimestep: 5100000\nmean reward (100 episodes): 78.2700\nbest mean reward: 152.1500\ncurrent episode reward: 88.0000\nepisodes: 9123\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21805.8 seconds (6.06 hours)\n\nTimestep: 5110000\nmean reward (100 episodes): 79.0500\nbest mean reward: 152.1500\ncurrent episode reward: 129.0000\nepisodes: 9130\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21851.2 seconds (6.07 hours)\n\nTimestep: 5120000\nmean reward (100 episodes): 79.6300\nbest mean reward: 152.1500\ncurrent episode reward: 66.0000\nepisodes: 9137\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21895.7 seconds (6.08 hours)\n\nTimestep: 5130000\nmean reward (100 episodes): 83.7000\nbest mean reward: 152.1500\ncurrent episode reward: 111.0000\nepisodes: 9144\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21939.9 seconds (6.09 hours)\n\nTimestep: 5140000\nmean reward (100 episodes): 84.1300\nbest mean reward: 152.1500\ncurrent episode reward: 119.0000\nepisodes: 9152\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21983.8 seconds (6.11 hours)\n\nTimestep: 5150000\nmean reward (100 episodes): 84.8700\nbest mean reward: 152.1500\ncurrent episode reward: 61.0000\nepisodes: 9159\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22028.0 seconds (6.12 hours)\n\nTimestep: 5160000\nmean reward (100 episodes): 85.6300\nbest mean reward: 152.1500\ncurrent episode reward: 88.0000\nepisodes: 9166\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22072.6 seconds (6.13 hours)\n\nTimestep: 5170000\nmean reward (100 episodes): 82.3100\nbest mean reward: 152.1500\ncurrent episode reward: 115.0000\nepisodes: 9173\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22116.8 seconds (6.14 hours)\n\nTimestep: 5180000\nmean reward (100 episodes): 84.7200\nbest mean reward: 152.1500\ncurrent episode reward: 90.0000\nepisodes: 9180\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22160.7 seconds (6.16 hours)\n\nTimestep: 5190000\nmean reward (100 episodes): 84.8200\nbest mean reward: 152.1500\ncurrent episode reward: 66.0000\nepisodes: 9187\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22205.2 seconds (6.17 hours)\n\nTimestep: 5200000\nmean reward (100 episodes): 86.0800\nbest mean reward: 152.1500\ncurrent episode reward: 77.0000\nepisodes: 9194\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22249.9 seconds (6.18 hours)\n\nTimestep: 5210000\nmean reward (100 episodes): 88.5900\nbest mean reward: 152.1500\ncurrent episode reward: 132.0000\nepisodes: 9201\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22293.5 seconds (6.19 hours)\n\nTimestep: 5220000\nmean reward (100 episodes): 91.6200\nbest mean reward: 152.1500\ncurrent episode reward: 86.0000\nepisodes: 9207\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22338.9 seconds (6.21 hours)\n\nTimestep: 5230000\nmean reward (100 episodes): 92.3900\nbest mean reward: 152.1500\ncurrent episode reward: 103.0000\nepisodes: 9214\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22383.1 seconds (6.22 hours)\n\nTimestep: 5240000\nmean reward (100 episodes): 92.5500\nbest mean reward: 152.1500\ncurrent episode reward: 122.0000\nepisodes: 9222\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22427.7 seconds (6.23 hours)\n\nTimestep: 5250000\nmean reward (100 episodes): 94.6900\nbest mean reward: 152.1500\ncurrent episode reward: 112.0000\nepisodes: 9229\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22471.6 seconds (6.24 hours)\n\nTimestep: 5260000\nmean reward (100 episodes): 96.5400\nbest mean reward: 152.1500\ncurrent episode reward: 235.0000\nepisodes: 9236\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22516.5 seconds (6.25 hours)\n\nTimestep: 5270000\nmean reward (100 episodes): 92.5100\nbest mean reward: 152.1500\ncurrent episode reward: 45.0000\nepisodes: 9244\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22561.4 seconds (6.27 hours)\n\nTimestep: 5280000\nmean reward (100 episodes): 94.3700\nbest mean reward: 152.1500\ncurrent episode reward: 75.0000\nepisodes: 9251\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22605.9 seconds (6.28 hours)\n\nTimestep: 5290000\nmean reward (100 episodes): 93.6500\nbest mean reward: 152.1500\ncurrent episode reward: 69.0000\nepisodes: 9258\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22650.9 seconds (6.29 hours)\n\nTimestep: 5300000\nmean reward (100 episodes): 97.9000\nbest mean reward: 152.1500\ncurrent episode reward: 180.0000\nepisodes: 9266\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22695.3 seconds (6.30 hours)\n\nTimestep: 5310000\nmean reward (100 episodes): 100.5300\nbest mean reward: 152.1500\ncurrent episode reward: 93.0000\nepisodes: 9272\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22740.2 seconds (6.32 hours)\n\nTimestep: 5320000\nmean reward (100 episodes): 100.2500\nbest mean reward: 152.1500\ncurrent episode reward: 130.0000\nepisodes: 9279\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22784.5 seconds (6.33 hours)\n\nTimestep: 5330000\nmean reward (100 episodes): 102.6300\nbest mean reward: 152.1500\ncurrent episode reward: 126.0000\nepisodes: 9287\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22829.3 seconds (6.34 hours)\n\nTimestep: 5340000\nmean reward (100 episodes): 106.8400\nbest mean reward: 152.1500\ncurrent episode reward: 171.0000\nepisodes: 9293\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22874.6 seconds (6.35 hours)\n\nTimestep: 5350000\nmean reward (100 episodes): 108.5500\nbest mean reward: 152.1500\ncurrent episode reward: 81.0000\nepisodes: 9300\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22919.6 seconds (6.37 hours)\n\nTimestep: 5360000\nmean reward (100 episodes): 108.0000\nbest mean reward: 152.1500\ncurrent episode reward: 94.0000\nepisodes: 9307\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22964.1 seconds (6.38 hours)\n\nTimestep: 5370000\nmean reward (100 episodes): 110.6000\nbest mean reward: 152.1500\ncurrent episode reward: 46.0000\nepisodes: 9315\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23008.3 seconds (6.39 hours)\n\nTimestep: 5380000\nmean reward (100 episodes): 110.0400\nbest mean reward: 152.1500\ncurrent episode reward: 77.0000\nepisodes: 9322\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23052.9 seconds (6.40 hours)\n\nTimestep: 5390000\nmean reward (100 episodes): 108.9100\nbest mean reward: 152.1500\ncurrent episode reward: 55.0000\nepisodes: 9328\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23097.5 seconds (6.42 hours)\n\nTimestep: 5400000\nmean reward (100 episodes): 108.3000\nbest mean reward: 152.1500\ncurrent episode reward: 192.0000\nepisodes: 9335\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23142.4 seconds (6.43 hours)\n\nTimestep: 5410000\nmean reward (100 episodes): 108.1000\nbest mean reward: 152.1500\ncurrent episode reward: 109.0000\nepisodes: 9342\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23187.0 seconds (6.44 hours)\n\nTimestep: 5420000\nmean reward (100 episodes): 109.5300\nbest mean reward: 152.1500\ncurrent episode reward: 113.0000\nepisodes: 9349\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23231.9 seconds (6.45 hours)\n\nTimestep: 5430000\nmean reward (100 episodes): 110.0900\nbest mean reward: 152.1500\ncurrent episode reward: 22.0000\nepisodes: 9357\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23276.3 seconds (6.47 hours)\n\nTimestep: 5440000\nmean reward (100 episodes): 107.2900\nbest mean reward: 152.1500\ncurrent episode reward: 104.0000\nepisodes: 9364\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23321.0 seconds (6.48 hours)\n\nTimestep: 5450000\nmean reward (100 episodes): 105.2900\nbest mean reward: 152.1500\ncurrent episode reward: 69.0000\nepisodes: 9372\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23365.2 seconds (6.49 hours)\n\nTimestep: 5460000\nmean reward (100 episodes): 106.4900\nbest mean reward: 152.1500\ncurrent episode reward: 135.0000\nepisodes: 9379\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23409.8 seconds (6.50 hours)\n\nTimestep: 5470000\nmean reward (100 episodes): 107.3300\nbest mean reward: 152.1500\ncurrent episode reward: 141.0000\nepisodes: 9385\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23454.0 seconds (6.52 hours)\n\nTimestep: 5480000\nmean reward (100 episodes): 107.5200\nbest mean reward: 152.1500\ncurrent episode reward: 96.0000\nepisodes: 9392\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23498.8 seconds (6.53 hours)\n\nTimestep: 5490000\nmean reward (100 episodes): 106.0500\nbest mean reward: 152.1500\ncurrent episode reward: 98.0000\nepisodes: 9399\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23543.6 seconds (6.54 hours)\n\nTimestep: 5500000\nmean reward (100 episodes): 107.2300\nbest mean reward: 152.1500\ncurrent episode reward: 107.0000\nepisodes: 9405\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23588.3 seconds (6.55 hours)\n\nTimestep: 5510000\nmean reward (100 episodes): 109.5500\nbest mean reward: 152.1500\ncurrent episode reward: 241.0000\nepisodes: 9412\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23633.1 seconds (6.56 hours)\n\nTimestep: 5520000\nmean reward (100 episodes): 115.6700\nbest mean reward: 152.1500\ncurrent episode reward: 189.0000\nepisodes: 9419\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23677.4 seconds (6.58 hours)\n\nTimestep: 5530000\nmean reward (100 episodes): 118.0600\nbest mean reward: 152.1500\ncurrent episode reward: 166.0000\nepisodes: 9425\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23721.5 seconds (6.59 hours)\n\nTimestep: 5540000\nmean reward (100 episodes): 120.7600\nbest mean reward: 152.1500\ncurrent episode reward: 90.0000\nepisodes: 9432\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23765.6 seconds (6.60 hours)\n\nTimestep: 5550000\nmean reward (100 episodes): 127.1300\nbest mean reward: 152.1500\ncurrent episode reward: 128.0000\nepisodes: 9438\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23810.4 seconds (6.61 hours)\n\nTimestep: 5560000\nmean reward (100 episodes): 131.6400\nbest mean reward: 152.1500\ncurrent episode reward: 147.0000\nepisodes: 9445\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23855.5 seconds (6.63 hours)\n\nTimestep: 5570000\nmean reward (100 episodes): 130.1100\nbest mean reward: 152.1500\ncurrent episode reward: 74.0000\nepisodes: 9452\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23899.7 seconds (6.64 hours)\n\nTimestep: 5580000\nmean reward (100 episodes): 134.6300\nbest mean reward: 152.1500\ncurrent episode reward: 101.0000\nepisodes: 9460\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23944.0 seconds (6.65 hours)\n\nTimestep: 5590000\nmean reward (100 episodes): 136.4100\nbest mean reward: 152.1500\ncurrent episode reward: 97.0000\nepisodes: 9466\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23988.6 seconds (6.66 hours)\n\nTimestep: 5600000\nmean reward (100 episodes): 137.1800\nbest mean reward: 152.1500\ncurrent episode reward: 62.0000\nepisodes: 9473\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24033.3 seconds (6.68 hours)\n\nTimestep: 5610000\nmean reward (100 episodes): 138.4000\nbest mean reward: 152.1500\ncurrent episode reward: 301.0000\nepisodes: 9480\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24077.2 seconds (6.69 hours)\n\nTimestep: 5620000\nmean reward (100 episodes): 135.8500\nbest mean reward: 152.1500\ncurrent episode reward: 95.0000\nepisodes: 9487\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24121.1 seconds (6.70 hours)\n\nTimestep: 5630000\nmean reward (100 episodes): 139.2600\nbest mean reward: 152.1500\ncurrent episode reward: 124.0000\nepisodes: 9493\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24166.3 seconds (6.71 hours)\n\nTimestep: 5640000\nmean reward (100 episodes): 142.3100\nbest mean reward: 152.1500\ncurrent episode reward: 150.0000\nepisodes: 9499\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24210.5 seconds (6.73 hours)\n\nTimestep: 5650000\nmean reward (100 episodes): 138.2200\nbest mean reward: 152.1500\ncurrent episode reward: 107.0000\nepisodes: 9508\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24255.3 seconds (6.74 hours)\n\nTimestep: 5660000\nmean reward (100 episodes): 132.5000\nbest mean reward: 152.1500\ncurrent episode reward: 122.0000\nepisodes: 9515\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24300.5 seconds (6.75 hours)\n\nTimestep: 5670000\nmean reward (100 episodes): 134.4900\nbest mean reward: 152.1500\ncurrent episode reward: 64.0000\nepisodes: 9522\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24345.7 seconds (6.76 hours)\n\nTimestep: 5680000\nmean reward (100 episodes): 136.7800\nbest mean reward: 152.1500\ncurrent episode reward: 130.0000\nepisodes: 9528\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24389.4 seconds (6.77 hours)\n\nTimestep: 5690000\nmean reward (100 episodes): 131.9900\nbest mean reward: 152.1500\ncurrent episode reward: 147.0000\nepisodes: 9535\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24433.9 seconds (6.79 hours)\n\nTimestep: 5700000\nmean reward (100 episodes): 131.6600\nbest mean reward: 152.1500\ncurrent episode reward: 165.0000\nepisodes: 9542\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24478.6 seconds (6.80 hours)\n\nTimestep: 5710000\nmean reward (100 episodes): 132.1300\nbest mean reward: 152.1500\ncurrent episode reward: 186.0000\nepisodes: 9548\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24524.1 seconds (6.81 hours)\n\nTimestep: 5720000\nmean reward (100 episodes): 137.0500\nbest mean reward: 152.1500\ncurrent episode reward: 168.0000\nepisodes: 9555\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24568.8 seconds (6.82 hours)\n\nTimestep: 5730000\nmean reward (100 episodes): 136.9100\nbest mean reward: 152.1500\ncurrent episode reward: 100.0000\nepisodes: 9561\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24614.4 seconds (6.84 hours)\n\nTimestep: 5740000\nmean reward (100 episodes): 135.0800\nbest mean reward: 152.1500\ncurrent episode reward: 144.0000\nepisodes: 9568\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24658.5 seconds (6.85 hours)\n\nTimestep: 5750000\nmean reward (100 episodes): 138.9100\nbest mean reward: 152.1500\ncurrent episode reward: 153.0000\nepisodes: 9575\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24702.8 seconds (6.86 hours)\n\nTimestep: 5760000\nmean reward (100 episodes): 140.4200\nbest mean reward: 152.1500\ncurrent episode reward: 61.0000\nepisodes: 9582\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24747.6 seconds (6.87 hours)\n\nTimestep: 5770000\nmean reward (100 episodes): 143.6100\nbest mean reward: 152.1500\ncurrent episode reward: 148.0000\nepisodes: 9588\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24792.4 seconds (6.89 hours)\n\nTimestep: 5780000\nmean reward (100 episodes): 138.6000\nbest mean reward: 152.1500\ncurrent episode reward: 197.0000\nepisodes: 9595\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24836.5 seconds (6.90 hours)\n\nTimestep: 5790000\nmean reward (100 episodes): 144.0600\nbest mean reward: 152.1500\ncurrent episode reward: 269.0000\nepisodes: 9601\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24881.8 seconds (6.91 hours)\n\nTimestep: 5800000\nmean reward (100 episodes): 146.9800\nbest mean reward: 152.1500\ncurrent episode reward: 176.0000\nepisodes: 9608\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24927.3 seconds (6.92 hours)\n\nTimestep: 5810000\nmean reward (100 episodes): 147.8400\nbest mean reward: 152.1500\ncurrent episode reward: 136.0000\nepisodes: 9615\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24972.0 seconds (6.94 hours)\n\nTimestep: 5820000\nmean reward (100 episodes): 146.2800\nbest mean reward: 152.1500\ncurrent episode reward: 246.0000\nepisodes: 9621\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25016.7 seconds (6.95 hours)\n\nTimestep: 5830000\nmean reward (100 episodes): 148.3900\nbest mean reward: 152.1500\ncurrent episode reward: 120.0000\nepisodes: 9628\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25061.4 seconds (6.96 hours)\n\nTimestep: 5840000\nmean reward (100 episodes): 154.3000\nbest mean reward: 154.3000\ncurrent episode reward: 324.0000\nepisodes: 9634\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25105.6 seconds (6.97 hours)\n\nTimestep: 5850000\nmean reward (100 episodes): 154.8000\nbest mean reward: 155.5100\ncurrent episode reward: 103.0000\nepisodes: 9641\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25150.2 seconds (6.99 hours)\n\nTimestep: 5860000\nmean reward (100 episodes): 157.0000\nbest mean reward: 157.0000\ncurrent episode reward: 307.0000\nepisodes: 9647\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25194.1 seconds (7.00 hours)\n\nTimestep: 5870000\nmean reward (100 episodes): 152.8200\nbest mean reward: 157.0000\ncurrent episode reward: 259.0000\nepisodes: 9655\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25238.3 seconds (7.01 hours)\n\nTimestep: 5880000\nmean reward (100 episodes): 156.0300\nbest mean reward: 157.0000\ncurrent episode reward: 102.0000\nepisodes: 9662\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25283.1 seconds (7.02 hours)\n\nTimestep: 5890000\nmean reward (100 episodes): 158.5900\nbest mean reward: 159.7700\ncurrent episode reward: 61.0000\nepisodes: 9669\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25327.7 seconds (7.04 hours)\n\nTimestep: 5900000\nmean reward (100 episodes): 159.7500\nbest mean reward: 160.7700\ncurrent episode reward: 95.0000\nepisodes: 9676\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25372.8 seconds (7.05 hours)\n\nTimestep: 5910000\nmean reward (100 episodes): 155.5200\nbest mean reward: 160.7700\ncurrent episode reward: 174.0000\nepisodes: 9683\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25418.1 seconds (7.06 hours)\n\nTimestep: 5920000\nmean reward (100 episodes): 154.4800\nbest mean reward: 160.7700\ncurrent episode reward: 204.0000\nepisodes: 9689\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25462.7 seconds (7.07 hours)\n\nTimestep: 5930000\nmean reward (100 episodes): 159.7300\nbest mean reward: 160.7700\ncurrent episode reward: 267.0000\nepisodes: 9695\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25506.9 seconds (7.09 hours)\n\nTimestep: 5940000\nmean reward (100 episodes): 159.9900\nbest mean reward: 160.7700\ncurrent episode reward: 305.0000\nepisodes: 9701\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25552.0 seconds (7.10 hours)\n\nTimestep: 5950000\nmean reward (100 episodes): 168.5300\nbest mean reward: 168.5300\ncurrent episode reward: 219.0000\nepisodes: 9707\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25597.0 seconds (7.11 hours)\n\nTimestep: 5960000\nmean reward (100 episodes): 176.2600\nbest mean reward: 176.2600\ncurrent episode reward: 300.0000\nepisodes: 9713\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25641.3 seconds (7.12 hours)\n\nTimestep: 5970000\nmean reward (100 episodes): 175.6700\nbest mean reward: 178.6700\ncurrent episode reward: 303.0000\nepisodes: 9721\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25685.5 seconds (7.13 hours)\n\nTimestep: 5980000\nmean reward (100 episodes): 172.9900\nbest mean reward: 178.6700\ncurrent episode reward: 101.0000\nepisodes: 9728\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25729.7 seconds (7.15 hours)\n\nTimestep: 5990000\nmean reward (100 episodes): 174.6800\nbest mean reward: 178.6700\ncurrent episode reward: 312.0000\nepisodes: 9734\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25774.3 seconds (7.16 hours)\n\nTimestep: 6000000\nmean reward (100 episodes): 178.1700\nbest mean reward: 178.6700\ncurrent episode reward: 255.0000\nepisodes: 9741\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25818.6 seconds (7.17 hours)\n\nTimestep: 6010000\nmean reward (100 episodes): 178.2500\nbest mean reward: 180.6000\ncurrent episode reward: 152.0000\nepisodes: 9747\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25863.5 seconds (7.18 hours)\n\nTimestep: 6020000\nmean reward (100 episodes): 183.9600\nbest mean reward: 184.3200\ncurrent episode reward: 190.0000\nepisodes: 9753\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25908.0 seconds (7.20 hours)\n\nTimestep: 6030000\nmean reward (100 episodes): 184.0500\nbest mean reward: 186.7000\ncurrent episode reward: 184.0000\nepisodes: 9760\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25952.7 seconds (7.21 hours)\n\nTimestep: 6040000\nmean reward (100 episodes): 186.5000\nbest mean reward: 187.4800\ncurrent episode reward: 128.0000\nepisodes: 9766\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25997.7 seconds (7.22 hours)\n\nTimestep: 6050000\nmean reward (100 episodes): 191.9300\nbest mean reward: 193.5900\ncurrent episode reward: 105.0000\nepisodes: 9773\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26043.2 seconds (7.23 hours)\n\nTimestep: 6060000\nmean reward (100 episodes): 198.5100\nbest mean reward: 198.5100\ncurrent episode reward: 147.0000\nepisodes: 9780\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26088.5 seconds (7.25 hours)\n\nTimestep: 6070000\nmean reward (100 episodes): 202.2200\nbest mean reward: 202.2200\ncurrent episode reward: 264.0000\nepisodes: 9787\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26132.9 seconds (7.26 hours)\n\nTimestep: 6080000\nmean reward (100 episodes): 203.0400\nbest mean reward: 203.1800\ncurrent episode reward: 315.0000\nepisodes: 9793\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26179.0 seconds (7.27 hours)\n\nTimestep: 6090000\nmean reward (100 episodes): 204.2000\nbest mean reward: 204.8600\ncurrent episode reward: 275.0000\nepisodes: 9800\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26222.9 seconds (7.28 hours)\n\nTimestep: 6100000\nmean reward (100 episodes): 203.5200\nbest mean reward: 205.2200\ncurrent episode reward: 79.0000\nepisodes: 9807\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26267.1 seconds (7.30 hours)\n\nTimestep: 6110000\nmean reward (100 episodes): 203.1800\nbest mean reward: 205.2200\ncurrent episode reward: 162.0000\nepisodes: 9812\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26311.2 seconds (7.31 hours)\n\nTimestep: 6120000\nmean reward (100 episodes): 206.2100\nbest mean reward: 206.2100\ncurrent episode reward: 180.0000\nepisodes: 9819\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26356.0 seconds (7.32 hours)\n\nTimestep: 6130000\nmean reward (100 episodes): 212.3000\nbest mean reward: 212.3000\ncurrent episode reward: 350.0000\nepisodes: 9825\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26401.1 seconds (7.33 hours)\n\nTimestep: 6140000\nmean reward (100 episodes): 219.2300\nbest mean reward: 219.2300\ncurrent episode reward: 319.0000\nepisodes: 9830\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26445.9 seconds (7.35 hours)\n\nTimestep: 6150000\nmean reward (100 episodes): 214.6000\nbest mean reward: 219.9400\ncurrent episode reward: 177.0000\nepisodes: 9837\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26490.5 seconds (7.36 hours)\n\nTimestep: 6160000\nmean reward (100 episodes): 216.1500\nbest mean reward: 219.9400\ncurrent episode reward: 192.0000\nepisodes: 9844\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26534.2 seconds (7.37 hours)\n\nTimestep: 6170000\nmean reward (100 episodes): 219.8800\nbest mean reward: 220.0300\ncurrent episode reward: 236.0000\nepisodes: 9850\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26578.6 seconds (7.38 hours)\n\nTimestep: 6180000\nmean reward (100 episodes): 217.4700\nbest mean reward: 220.0300\ncurrent episode reward: 68.0000\nepisodes: 9856\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26623.1 seconds (7.40 hours)\n\nTimestep: 6190000\nmean reward (100 episodes): 223.9700\nbest mean reward: 223.9700\ncurrent episode reward: 328.0000\nepisodes: 9862\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26668.4 seconds (7.41 hours)\n\nTimestep: 6200000\nmean reward (100 episodes): 229.2900\nbest mean reward: 229.2900\ncurrent episode reward: 319.0000\nepisodes: 9867\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26713.4 seconds (7.42 hours)\n\nTimestep: 6210000\nmean reward (100 episodes): 230.6900\nbest mean reward: 231.6900\ncurrent episode reward: 232.0000\nepisodes: 9873\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26758.0 seconds (7.43 hours)\n\nTimestep: 6220000\nmean reward (100 episodes): 229.3100\nbest mean reward: 231.6900\ncurrent episode reward: 47.0000\nepisodes: 9879\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26802.4 seconds (7.45 hours)\n\nTimestep: 6230000\nmean reward (100 episodes): 232.9000\nbest mean reward: 234.7200\ncurrent episode reward: 245.0000\nepisodes: 9886\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26846.6 seconds (7.46 hours)\n\nTimestep: 6240000\nmean reward (100 episodes): 237.1900\nbest mean reward: 237.1900\ncurrent episode reward: 374.0000\nepisodes: 9891\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26891.9 seconds (7.47 hours)\n\nTimestep: 6250000\nmean reward (100 episodes): 236.3800\nbest mean reward: 237.1900\ncurrent episode reward: 315.0000\nepisodes: 9897\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26936.7 seconds (7.48 hours)\n\nTimestep: 6260000\nmean reward (100 episodes): 238.6800\nbest mean reward: 239.1400\ncurrent episode reward: 280.0000\nepisodes: 9903\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26981.5 seconds (7.49 hours)\n\nTimestep: 6270000\nmean reward (100 episodes): 237.8900\nbest mean reward: 239.1400\ncurrent episode reward: 307.0000\nepisodes: 9909\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27025.9 seconds (7.51 hours)\n\nTimestep: 6280000\nmean reward (100 episodes): 244.3100\nbest mean reward: 244.3100\ncurrent episode reward: 382.0000\nepisodes: 9914\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27069.9 seconds (7.52 hours)\n\nTimestep: 6290000\nmean reward (100 episodes): 248.6000\nbest mean reward: 249.0900\ncurrent episode reward: 245.0000\nepisodes: 9920\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27114.7 seconds (7.53 hours)\n\nTimestep: 6300000\nmean reward (100 episodes): 246.4000\nbest mean reward: 249.0900\ncurrent episode reward: 113.0000\nepisodes: 9926\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27159.1 seconds (7.54 hours)\n\nTimestep: 6310000\nmean reward (100 episodes): 246.1800\nbest mean reward: 249.0900\ncurrent episode reward: 264.0000\nepisodes: 9932\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27202.9 seconds (7.56 hours)\n\nTimestep: 6320000\nmean reward (100 episodes): 249.0400\nbest mean reward: 251.9400\ncurrent episode reward: 98.0000\nepisodes: 9938\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27248.3 seconds (7.57 hours)\n\nTimestep: 6330000\nmean reward (100 episodes): 253.1100\nbest mean reward: 253.1100\ncurrent episode reward: 385.0000\nepisodes: 9943\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27293.0 seconds (7.58 hours)\n\nTimestep: 6340000\nmean reward (100 episodes): 252.2100\nbest mean reward: 253.3700\ncurrent episode reward: 237.0000\nepisodes: 9949\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27337.9 seconds (7.59 hours)\n\nTimestep: 6350000\nmean reward (100 episodes): 252.4500\nbest mean reward: 256.4000\ncurrent episode reward: 164.0000\nepisodes: 9955\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27383.1 seconds (7.61 hours)\n\nTimestep: 6360000\nmean reward (100 episodes): 254.0000\nbest mean reward: 256.4000\ncurrent episode reward: 312.0000\nepisodes: 9961\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27428.0 seconds (7.62 hours)\n\nTimestep: 6370000\nmean reward (100 episodes): 249.4100\nbest mean reward: 256.4000\ncurrent episode reward: 316.0000\nepisodes: 9966\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27472.7 seconds (7.63 hours)\n\nTimestep: 6380000\nmean reward (100 episodes): 254.6600\nbest mean reward: 256.4000\ncurrent episode reward: 339.0000\nepisodes: 9972\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27517.0 seconds (7.64 hours)\n\nTimestep: 6390000\nmean reward (100 episodes): 255.8100\nbest mean reward: 256.4000\ncurrent episode reward: 255.0000\nepisodes: 9978\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27561.8 seconds (7.66 hours)\n\nTimestep: 6400000\nmean reward (100 episodes): 262.1000\nbest mean reward: 262.1000\ncurrent episode reward: 336.0000\nepisodes: 9983\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27605.9 seconds (7.67 hours)\n\nTimestep: 6410000\nmean reward (100 episodes): 264.2100\nbest mean reward: 264.2100\ncurrent episode reward: 327.0000\nepisodes: 9988\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27649.4 seconds (7.68 hours)\n\nTimestep: 6420000\nmean reward (100 episodes): 267.2900\nbest mean reward: 267.2900\ncurrent episode reward: 241.0000\nepisodes: 9994\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27694.5 seconds (7.69 hours)\n\nTimestep: 6430000\nmean reward (100 episodes): 265.3400\nbest mean reward: 267.2900\ncurrent episode reward: 254.0000\nepisodes: 10000\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27741.2 seconds (7.71 hours)\n\nTimestep: 6440000\nmean reward (100 episodes): 268.3700\nbest mean reward: 268.3700\ncurrent episode reward: 204.0000\nepisodes: 10006\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27789.3 seconds (7.72 hours)\n\nTimestep: 6450000\nmean reward (100 episodes): 267.6600\nbest mean reward: 270.5800\ncurrent episode reward: 213.0000\nepisodes: 10011\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27833.8 seconds (7.73 hours)\n\nTimestep: 6460000\nmean reward (100 episodes): 267.3100\nbest mean reward: 270.5800\ncurrent episode reward: 367.0000\nepisodes: 10017\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27878.4 seconds (7.74 hours)\n\nTimestep: 6470000\nmean reward (100 episodes): 271.9000\nbest mean reward: 271.9000\ncurrent episode reward: 369.0000\nepisodes: 10022\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27923.3 seconds (7.76 hours)\n\nTimestep: 6480000\nmean reward (100 episodes): 271.9600\nbest mean reward: 273.8300\ncurrent episode reward: 354.0000\nepisodes: 10029\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27967.7 seconds (7.77 hours)\n\nTimestep: 6490000\nmean reward (100 episodes): 271.5000\nbest mean reward: 273.8300\ncurrent episode reward: 371.0000\nepisodes: 10035\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28012.2 seconds (7.78 hours)\n\nTimestep: 6500000\nmean reward (100 episodes): 272.4500\nbest mean reward: 275.0400\ncurrent episode reward: 74.0000\nepisodes: 10041\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28056.7 seconds (7.79 hours)\n\nTimestep: 6510000\nmean reward (100 episodes): 273.0200\nbest mean reward: 275.0400\ncurrent episode reward: 337.0000\nepisodes: 10046\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28101.5 seconds (7.81 hours)\n\nTimestep: 6520000\nmean reward (100 episodes): 275.3900\nbest mean reward: 275.5200\ncurrent episode reward: 364.0000\nepisodes: 10051\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28145.6 seconds (7.82 hours)\n\nTimestep: 6530000\nmean reward (100 episodes): 282.0000\nbest mean reward: 282.0000\ncurrent episode reward: 431.0000\nepisodes: 10056\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28190.1 seconds (7.83 hours)\n\nTimestep: 6540000\nmean reward (100 episodes): 280.4200\nbest mean reward: 282.6700\ncurrent episode reward: 317.0000\nepisodes: 10062\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28234.9 seconds (7.84 hours)\n\nTimestep: 6550000\nmean reward (100 episodes): 280.5700\nbest mean reward: 283.3100\ncurrent episode reward: 128.0000\nepisodes: 10068\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28279.4 seconds (7.86 hours)\n\nTimestep: 6560000\nmean reward (100 episodes): 279.8800\nbest mean reward: 283.3100\ncurrent episode reward: 250.0000\nepisodes: 10073\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28324.3 seconds (7.87 hours)\n\nTimestep: 6570000\nmean reward (100 episodes): 280.1100\nbest mean reward: 283.3100\ncurrent episode reward: 285.0000\nepisodes: 10078\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28369.0 seconds (7.88 hours)\n\nTimestep: 6580000\nmean reward (100 episodes): 280.3600\nbest mean reward: 283.3100\ncurrent episode reward: 259.0000\nepisodes: 10083\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28413.0 seconds (7.89 hours)\n\nTimestep: 6590000\nmean reward (100 episodes): 279.2300\nbest mean reward: 283.3100\ncurrent episode reward: 275.0000\nepisodes: 10089\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28457.3 seconds (7.90 hours)\n\nTimestep: 6600000\nmean reward (100 episodes): 282.1300\nbest mean reward: 283.3100\ncurrent episode reward: 213.0000\nepisodes: 10095\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28501.3 seconds (7.92 hours)\n\nTimestep: 6610000\nmean reward (100 episodes): 282.8700\nbest mean reward: 283.8100\ncurrent episode reward: 315.0000\nepisodes: 10100\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28544.9 seconds (7.93 hours)\n\nTimestep: 6620000\nmean reward (100 episodes): 285.7100\nbest mean reward: 285.7100\ncurrent episode reward: 320.0000\nepisodes: 10106\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28590.4 seconds (7.94 hours)\n\nTimestep: 6630000\nmean reward (100 episodes): 286.0700\nbest mean reward: 286.2400\ncurrent episode reward: 358.0000\nepisodes: 10111\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28634.8 seconds (7.95 hours)\n\nTimestep: 6640000\nmean reward (100 episodes): 285.1200\nbest mean reward: 288.2900\ncurrent episode reward: 299.0000\nepisodes: 10117\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28679.5 seconds (7.97 hours)\n\nTimestep: 6650000\nmean reward (100 episodes): 280.5300\nbest mean reward: 288.2900\ncurrent episode reward: 152.0000\nepisodes: 10122\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28724.5 seconds (7.98 hours)\n\nTimestep: 6660000\nmean reward (100 episodes): 287.3900\nbest mean reward: 288.2900\ncurrent episode reward: 198.0000\nepisodes: 10128\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28768.4 seconds (7.99 hours)\n\nTimestep: 6670000\nmean reward (100 episodes): 287.6600\nbest mean reward: 288.2900\ncurrent episode reward: 269.0000\nepisodes: 10134\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28813.1 seconds (8.00 hours)\n\nTimestep: 6680000\nmean reward (100 episodes): 287.4200\nbest mean reward: 288.2900\ncurrent episode reward: 331.0000\nepisodes: 10139\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28857.2 seconds (8.02 hours)\n\nTimestep: 6690000\nmean reward (100 episodes): 290.3200\nbest mean reward: 290.3200\ncurrent episode reward: 404.0000\nepisodes: 10145\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28902.2 seconds (8.03 hours)\n\nTimestep: 6700000\nmean reward (100 episodes): 289.9000\nbest mean reward: 290.3200\ncurrent episode reward: 407.0000\nepisodes: 10151\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28947.1 seconds (8.04 hours)\n\nTimestep: 6710000\nmean reward (100 episodes): 288.8600\nbest mean reward: 290.3200\ncurrent episode reward: 301.0000\nepisodes: 10156\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28991.9 seconds (8.05 hours)\n\nTimestep: 6720000\nmean reward (100 episodes): 291.4400\nbest mean reward: 291.5700\ncurrent episode reward: 359.0000\nepisodes: 10162\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29036.6 seconds (8.07 hours)\n\nTimestep: 6730000\nmean reward (100 episodes): 292.4800\nbest mean reward: 293.1400\ncurrent episode reward: 62.0000\nepisodes: 10168\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29080.1 seconds (8.08 hours)\n\nTimestep: 6740000\nmean reward (100 episodes): 291.8100\nbest mean reward: 293.1400\ncurrent episode reward: 292.0000\nepisodes: 10173\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29124.8 seconds (8.09 hours)\n\nTimestep: 6750000\nmean reward (100 episodes): 292.8300\nbest mean reward: 293.4600\ncurrent episode reward: 317.0000\nepisodes: 10179\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29169.4 seconds (8.10 hours)\n\nTimestep: 6760000\nmean reward (100 episodes): 295.5500\nbest mean reward: 295.7200\ncurrent episode reward: 319.0000\nepisodes: 10184\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29213.2 seconds (8.11 hours)\n\nTimestep: 6770000\nmean reward (100 episodes): 294.6300\nbest mean reward: 295.7200\ncurrent episode reward: 287.0000\nepisodes: 10190\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29257.1 seconds (8.13 hours)\n\nTimestep: 6780000\nmean reward (100 episodes): 295.6100\nbest mean reward: 295.7200\ncurrent episode reward: 365.0000\nepisodes: 10196\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29301.7 seconds (8.14 hours)\n\nTimestep: 6790000\nmean reward (100 episodes): 296.4600\nbest mean reward: 297.2000\ncurrent episode reward: 300.0000\nepisodes: 10201\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29345.5 seconds (8.15 hours)\n\nTimestep: 6800000\nmean reward (100 episodes): 295.6300\nbest mean reward: 297.2000\ncurrent episode reward: 377.0000\nepisodes: 10206\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29390.0 seconds (8.16 hours)\n\nTimestep: 6810000\nmean reward (100 episodes): 297.9700\nbest mean reward: 297.9700\ncurrent episode reward: 380.0000\nepisodes: 10212\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29434.5 seconds (8.18 hours)\n\nTimestep: 6820000\nmean reward (100 episodes): 298.4600\nbest mean reward: 298.7900\ncurrent episode reward: 292.0000\nepisodes: 10218\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29478.6 seconds (8.19 hours)\n\nTimestep: 6830000\nmean reward (100 episodes): 304.1100\nbest mean reward: 304.1100\ncurrent episode reward: 393.0000\nepisodes: 10222\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29523.3 seconds (8.20 hours)\n\nTimestep: 6840000\nmean reward (100 episodes): 300.4900\nbest mean reward: 304.1100\ncurrent episode reward: 205.0000\nepisodes: 10229\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29567.6 seconds (8.21 hours)\n\nTimestep: 6850000\nmean reward (100 episodes): 299.9500\nbest mean reward: 304.1100\ncurrent episode reward: 222.0000\nepisodes: 10234\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29612.0 seconds (8.23 hours)\n\nTimestep: 6860000\nmean reward (100 episodes): 301.1400\nbest mean reward: 304.1100\ncurrent episode reward: 380.0000\nepisodes: 10239\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29656.1 seconds (8.24 hours)\n\nTimestep: 6870000\nmean reward (100 episodes): 306.1700\nbest mean reward: 306.1700\ncurrent episode reward: 374.0000\nepisodes: 10244\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29700.3 seconds (8.25 hours)\n\nTimestep: 6880000\nmean reward (100 episodes): 305.4200\nbest mean reward: 306.1700\ncurrent episode reward: 355.0000\nepisodes: 10249\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29744.4 seconds (8.26 hours)\n\nTimestep: 6890000\nmean reward (100 episodes): 306.2700\nbest mean reward: 306.2700\ncurrent episode reward: 369.0000\nepisodes: 10254\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29788.4 seconds (8.27 hours)\n\nTimestep: 6900000\nmean reward (100 episodes): 305.4000\nbest mean reward: 306.2700\ncurrent episode reward: 264.0000\nepisodes: 10260\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29833.2 seconds (8.29 hours)\n\nTimestep: 6910000\nmean reward (100 episodes): 302.3800\nbest mean reward: 306.2700\ncurrent episode reward: 254.0000\nepisodes: 10265\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29877.6 seconds (8.30 hours)\n\nTimestep: 6920000\nmean reward (100 episodes): 306.2100\nbest mean reward: 306.2700\ncurrent episode reward: 256.0000\nepisodes: 10271\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29922.7 seconds (8.31 hours)\n\nTimestep: 6930000\nmean reward (100 episodes): 306.7800\nbest mean reward: 306.9500\ncurrent episode reward: 354.0000\nepisodes: 10276\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29966.8 seconds (8.32 hours)\n\nTimestep: 6940000\nmean reward (100 episodes): 308.6200\nbest mean reward: 308.6200\ncurrent episode reward: 417.0000\nepisodes: 10280\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30012.0 seconds (8.34 hours)\n\nTimestep: 6950000\nmean reward (100 episodes): 307.8700\nbest mean reward: 308.6200\ncurrent episode reward: 229.0000\nepisodes: 10285\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30056.3 seconds (8.35 hours)\n\nTimestep: 6960000\nmean reward (100 episodes): 311.6200\nbest mean reward: 311.8300\ncurrent episode reward: 317.0000\nepisodes: 10291\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30101.2 seconds (8.36 hours)\n\nTimestep: 6970000\nmean reward (100 episodes): 310.7600\nbest mean reward: 311.8300\ncurrent episode reward: 335.0000\nepisodes: 10296\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30146.1 seconds (8.37 hours)\n\nTimestep: 6980000\nmean reward (100 episodes): 312.1100\nbest mean reward: 312.8500\ncurrent episode reward: 419.0000\nepisodes: 10301\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30189.8 seconds (8.39 hours)\n\nTimestep: 6990000\nmean reward (100 episodes): 309.6200\nbest mean reward: 312.8500\ncurrent episode reward: 196.0000\nepisodes: 10306\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30234.4 seconds (8.40 hours)\n\nTimestep: 7000000\nmean reward (100 episodes): 308.5900\nbest mean reward: 312.8500\ncurrent episode reward: 306.0000\nepisodes: 10312\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30279.0 seconds (8.41 hours)\n\nTimestep: 7010000\nmean reward (100 episodes): 309.9800\nbest mean reward: 312.8500\ncurrent episode reward: 252.0000\nepisodes: 10316\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30323.4 seconds (8.42 hours)\n\nTimestep: 7020000\nmean reward (100 episodes): 302.5700\nbest mean reward: 312.8500\ncurrent episode reward: 1.0000\nepisodes: 10323\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30367.7 seconds (8.44 hours)\n\nTimestep: 7030000\nmean reward (100 episodes): 306.3100\nbest mean reward: 312.8500\ncurrent episode reward: 412.0000\nepisodes: 10328\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30412.2 seconds (8.45 hours)\n\nTimestep: 7040000\nmean reward (100 episodes): 311.4700\nbest mean reward: 312.8500\ncurrent episode reward: 374.0000\nepisodes: 10333\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30456.5 seconds (8.46 hours)\n\nTimestep: 7050000\nmean reward (100 episodes): 315.2500\nbest mean reward: 315.2500\ncurrent episode reward: 411.0000\nepisodes: 10337\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30501.6 seconds (8.47 hours)\n\nTimestep: 7060000\nmean reward (100 episodes): 317.4300\nbest mean reward: 317.4300\ncurrent episode reward: 405.0000\nepisodes: 10340\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30546.1 seconds (8.49 hours)\n\nTimestep: 7070000\nmean reward (100 episodes): 314.2800\nbest mean reward: 317.4300\ncurrent episode reward: 274.0000\nepisodes: 10345\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30590.3 seconds (8.50 hours)\n\nTimestep: 7080000\nmean reward (100 episodes): 315.7600\nbest mean reward: 317.6100\ncurrent episode reward: 371.0000\nepisodes: 10350\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30634.1 seconds (8.51 hours)\n\nTimestep: 7090000\nmean reward (100 episodes): 320.5700\nbest mean reward: 320.5700\ncurrent episode reward: 410.0000\nepisodes: 10355\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30678.9 seconds (8.52 hours)\n\nTimestep: 7100000\nmean reward (100 episodes): 320.9900\nbest mean reward: 320.9900\ncurrent episode reward: 334.0000\nepisodes: 10360\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30723.4 seconds (8.53 hours)\n\nTimestep: 7110000\nmean reward (100 episodes): 326.8100\nbest mean reward: 326.8100\ncurrent episode reward: 386.0000\nepisodes: 10365\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30767.4 seconds (8.55 hours)\n\nTimestep: 7120000\nmean reward (100 episodes): 328.1100\nbest mean reward: 328.8700\ncurrent episode reward: 345.0000\nepisodes: 10370\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30812.4 seconds (8.56 hours)\n\nTimestep: 7130000\nmean reward (100 episodes): 331.1800\nbest mean reward: 331.1800\ncurrent episode reward: 334.0000\nepisodes: 10374\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30856.3 seconds (8.57 hours)\n\nTimestep: 7140000\nmean reward (100 episodes): 333.4600\nbest mean reward: 333.4600\ncurrent episode reward: 373.0000\nepisodes: 10379\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30900.7 seconds (8.58 hours)\n\nTimestep: 7150000\nmean reward (100 episodes): 334.3200\nbest mean reward: 334.3200\ncurrent episode reward: 406.0000\nepisodes: 10384\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30945.3 seconds (8.60 hours)\n\nTimestep: 7160000\nmean reward (100 episodes): 333.9900\nbest mean reward: 335.9000\ncurrent episode reward: 389.0000\nepisodes: 10389\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30989.2 seconds (8.61 hours)\n\nTimestep: 7170000\nmean reward (100 episodes): 338.1800\nbest mean reward: 338.1800\ncurrent episode reward: 347.0000\nepisodes: 10394\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31032.8 seconds (8.62 hours)\n\nTimestep: 7180000\nmean reward (100 episodes): 337.8800\nbest mean reward: 338.1800\ncurrent episode reward: 381.0000\nepisodes: 10398\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31076.8 seconds (8.63 hours)\n\nTimestep: 7190000\nmean reward (100 episodes): 340.0600\nbest mean reward: 340.2900\ncurrent episode reward: 396.0000\nepisodes: 10401\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31121.4 seconds (8.64 hours)\n\nTimestep: 7200000\nmean reward (100 episodes): 346.9700\nbest mean reward: 346.9700\ncurrent episode reward: 402.0000\nepisodes: 10407\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31166.6 seconds (8.66 hours)\n\nTimestep: 7210000\nmean reward (100 episodes): 348.8300\nbest mean reward: 349.5300\ncurrent episode reward: 406.0000\nepisodes: 10412\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31210.8 seconds (8.67 hours)\n\nTimestep: 7220000\nmean reward (100 episodes): 350.1500\nbest mean reward: 350.1500\ncurrent episode reward: 373.0000\nepisodes: 10416\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31254.6 seconds (8.68 hours)\n\nTimestep: 7230000\nmean reward (100 episodes): 349.5800\nbest mean reward: 350.5500\ncurrent episode reward: 345.0000\nepisodes: 10420\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31299.2 seconds (8.69 hours)\n\nTimestep: 7240000\nmean reward (100 episodes): 358.1500\nbest mean reward: 359.5200\ncurrent episode reward: 241.0000\nepisodes: 10425\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31343.2 seconds (8.71 hours)\n\nTimestep: 7250000\nmean reward (100 episodes): 358.9000\nbest mean reward: 359.7000\ncurrent episode reward: 348.0000\nepisodes: 10430\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31388.9 seconds (8.72 hours)\n\nTimestep: 7260000\nmean reward (100 episodes): 358.4600\nbest mean reward: 359.7000\ncurrent episode reward: 332.0000\nepisodes: 10433\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31433.2 seconds (8.73 hours)\n\nTimestep: 7270000\nmean reward (100 episodes): 358.1500\nbest mean reward: 359.7000\ncurrent episode reward: 388.0000\nepisodes: 10437\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31477.6 seconds (8.74 hours)\n\nTimestep: 7280000\nmean reward (100 episodes): 357.0100\nbest mean reward: 359.7000\ncurrent episode reward: 338.0000\nepisodes: 10440\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31522.2 seconds (8.76 hours)\n\nTimestep: 7290000\nmean reward (100 episodes): 360.5300\nbest mean reward: 360.5300\ncurrent episode reward: 416.0000\nepisodes: 10444\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31566.5 seconds (8.77 hours)\n\nTimestep: 7300000\nmean reward (100 episodes): 363.6800\nbest mean reward: 363.6800\ncurrent episode reward: 389.0000\nepisodes: 10449\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31611.3 seconds (8.78 hours)\n\nTimestep: 7310000\nmean reward (100 episodes): 364.4600\nbest mean reward: 364.4600\ncurrent episode reward: 427.0000\nepisodes: 10454\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31656.0 seconds (8.79 hours)\n\nTimestep: 7320000\nmean reward (100 episodes): 363.0300\nbest mean reward: 364.4800\ncurrent episode reward: 404.0000\nepisodes: 10458\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31700.3 seconds (8.81 hours)\n\nTimestep: 7330000\nmean reward (100 episodes): 364.7700\nbest mean reward: 364.9300\ncurrent episode reward: 389.0000\nepisodes: 10463\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31744.5 seconds (8.82 hours)\n\nTimestep: 7340000\nmean reward (100 episodes): 366.6600\nbest mean reward: 366.6600\ncurrent episode reward: 421.0000\nepisodes: 10467\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31788.4 seconds (8.83 hours)\n\nTimestep: 7350000\nmean reward (100 episodes): 365.0900\nbest mean reward: 366.6600\ncurrent episode reward: 375.0000\nepisodes: 10471\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31832.4 seconds (8.84 hours)\n\nTimestep: 7360000\nmean reward (100 episodes): 365.8900\nbest mean reward: 366.6600\ncurrent episode reward: 407.0000\nepisodes: 10474\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31877.1 seconds (8.85 hours)\n\nTimestep: 7370000\nmean reward (100 episodes): 366.4400\nbest mean reward: 366.6600\ncurrent episode reward: 427.0000\nepisodes: 10478\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31921.6 seconds (8.87 hours)\n\nTimestep: 7380000\nmean reward (100 episodes): 368.3700\nbest mean reward: 368.3700\ncurrent episode reward: 413.0000\nepisodes: 10481\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31965.8 seconds (8.88 hours)\n\nTimestep: 7390000\nmean reward (100 episodes): 369.1500\nbest mean reward: 369.1500\ncurrent episode reward: 413.0000\nepisodes: 10484\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32009.9 seconds (8.89 hours)\n\nTimestep: 7400000\nmean reward (100 episodes): 371.0400\nbest mean reward: 371.0400\ncurrent episode reward: 324.0000\nepisodes: 10488\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32054.6 seconds (8.90 hours)\n\nTimestep: 7410000\nmean reward (100 episodes): 370.2200\nbest mean reward: 371.6700\ncurrent episode reward: 254.0000\nepisodes: 10493\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32098.9 seconds (8.92 hours)\n\nTimestep: 7420000\nmean reward (100 episodes): 370.8300\nbest mean reward: 371.6700\ncurrent episode reward: 417.0000\nepisodes: 10496\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32143.0 seconds (8.93 hours)\n\nTimestep: 7430000\nmean reward (100 episodes): 370.2800\nbest mean reward: 371.6700\ncurrent episode reward: 328.0000\nepisodes: 10499\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32187.1 seconds (8.94 hours)\n\nTimestep: 7440000\nmean reward (100 episodes): 371.4400\nbest mean reward: 371.6700\ncurrent episode reward: 395.0000\nepisodes: 10504\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32231.8 seconds (8.95 hours)\n\nTimestep: 7450000\nmean reward (100 episodes): 370.1900\nbest mean reward: 371.6700\ncurrent episode reward: 427.0000\nepisodes: 10508\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32277.2 seconds (8.97 hours)\n\nTimestep: 7460000\nmean reward (100 episodes): 369.7600\nbest mean reward: 371.6700\ncurrent episode reward: 392.0000\nepisodes: 10512\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32321.9 seconds (8.98 hours)\n\nTimestep: 7470000\nmean reward (100 episodes): 365.4300\nbest mean reward: 371.6700\ncurrent episode reward: 116.0000\nepisodes: 10516\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32366.6 seconds (8.99 hours)\n\nTimestep: 7480000\nmean reward (100 episodes): 366.0600\nbest mean reward: 371.6700\ncurrent episode reward: 420.0000\nepisodes: 10519\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32411.4 seconds (9.00 hours)\n\nTimestep: 7490000\nmean reward (100 episodes): 363.9300\nbest mean reward: 371.6700\ncurrent episode reward: 380.0000\nepisodes: 10524\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32455.8 seconds (9.02 hours)\n\nTimestep: 7500000\nmean reward (100 episodes): 364.9000\nbest mean reward: 371.6700\ncurrent episode reward: 260.0000\nepisodes: 10528\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32500.3 seconds (9.03 hours)\n\nTimestep: 7510000\nmean reward (100 episodes): 365.3900\nbest mean reward: 371.6700\ncurrent episode reward: 416.0000\nepisodes: 10531\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32545.0 seconds (9.04 hours)\n\nTimestep: 7520000\nmean reward (100 episodes): 364.2000\nbest mean reward: 371.6700\ncurrent episode reward: 265.0000\nepisodes: 10535\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32588.9 seconds (9.05 hours)\n\nTimestep: 7530000\nmean reward (100 episodes): 363.9900\nbest mean reward: 371.6700\ncurrent episode reward: 330.0000\nepisodes: 10539\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32633.2 seconds (9.06 hours)\n\nTimestep: 7540000\nmean reward (100 episodes): 360.7200\nbest mean reward: 371.6700\ncurrent episode reward: 374.0000\nepisodes: 10543\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32677.7 seconds (9.08 hours)\n\nTimestep: 7550000\nmean reward (100 episodes): 360.3800\nbest mean reward: 371.6700\ncurrent episode reward: 330.0000\nepisodes: 10548\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32721.9 seconds (9.09 hours)\n\nTimestep: 7560000\nmean reward (100 episodes): 360.6000\nbest mean reward: 371.6700\ncurrent episode reward: 400.0000\nepisodes: 10552\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32766.3 seconds (9.10 hours)\n\nTimestep: 7570000\nmean reward (100 episodes): 361.2200\nbest mean reward: 371.6700\ncurrent episode reward: 382.0000\nepisodes: 10557\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32810.3 seconds (9.11 hours)\n\nTimestep: 7580000\nmean reward (100 episodes): 360.2900\nbest mean reward: 371.6700\ncurrent episode reward: 424.0000\nepisodes: 10560\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32854.6 seconds (9.13 hours)\n\nTimestep: 7590000\nmean reward (100 episodes): 360.2800\nbest mean reward: 371.6700\ncurrent episode reward: 374.0000\nepisodes: 10565\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32899.9 seconds (9.14 hours)\n\nTimestep: 7600000\nmean reward (100 episodes): 359.4800\nbest mean reward: 371.6700\ncurrent episode reward: 397.0000\nepisodes: 10569\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32944.0 seconds (9.15 hours)\n\nTimestep: 7610000\nmean reward (100 episodes): 360.5200\nbest mean reward: 371.6700\ncurrent episode reward: 374.0000\nepisodes: 10573\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32988.6 seconds (9.16 hours)\n\nTimestep: 7620000\nmean reward (100 episodes): 361.2100\nbest mean reward: 371.6700\ncurrent episode reward: 419.0000\nepisodes: 10576\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33032.8 seconds (9.18 hours)\n\nTimestep: 7630000\nmean reward (100 episodes): 356.3200\nbest mean reward: 371.6700\ncurrent episode reward: 306.0000\nepisodes: 10580\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33077.8 seconds (9.19 hours)\n\nTimestep: 7640000\nmean reward (100 episodes): 354.1100\nbest mean reward: 371.6700\ncurrent episode reward: 359.0000\nepisodes: 10584\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33122.0 seconds (9.20 hours)\n\nTimestep: 7650000\nmean reward (100 episodes): 354.2500\nbest mean reward: 371.6700\ncurrent episode reward: 395.0000\nepisodes: 10588\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33166.7 seconds (9.21 hours)\n\nTimestep: 7660000\nmean reward (100 episodes): 352.6400\nbest mean reward: 371.6700\ncurrent episode reward: 119.0000\nepisodes: 10590\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33211.5 seconds (9.23 hours)\n\nTimestep: 7670000\nmean reward (100 episodes): 353.7700\nbest mean reward: 371.6700\ncurrent episode reward: 421.0000\nepisodes: 10594\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33255.7 seconds (9.24 hours)\n\nTimestep: 7680000\nmean reward (100 episodes): 352.5000\nbest mean reward: 371.6700\ncurrent episode reward: 296.0000\nepisodes: 10598\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33299.6 seconds (9.25 hours)\n\nTimestep: 7690000\nmean reward (100 episodes): 353.7100\nbest mean reward: 371.6700\ncurrent episode reward: 385.0000\nepisodes: 10603\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33344.1 seconds (9.26 hours)\n\nTimestep: 7700000\nmean reward (100 episodes): 354.4400\nbest mean reward: 371.6700\ncurrent episode reward: 353.0000\nepisodes: 10607\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33389.3 seconds (9.27 hours)\n\nTimestep: 7710000\nmean reward (100 episodes): 352.9500\nbest mean reward: 371.6700\ncurrent episode reward: 431.0000\nepisodes: 10610\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33434.3 seconds (9.29 hours)\n\nTimestep: 7720000\nmean reward (100 episodes): 356.1500\nbest mean reward: 371.6700\ncurrent episode reward: 426.0000\nepisodes: 10614\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33478.6 seconds (9.30 hours)\n\nTimestep: 7730000\nmean reward (100 episodes): 366.9000\nbest mean reward: 371.6700\ncurrent episode reward: 820.0000\nepisodes: 10617\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33522.9 seconds (9.31 hours)\n\nTimestep: 7740000\nmean reward (100 episodes): 370.0000\nbest mean reward: 371.6700\ncurrent episode reward: 391.0000\nepisodes: 10621\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33567.6 seconds (9.32 hours)\n\nTimestep: 7750000\nmean reward (100 episodes): 371.0200\nbest mean reward: 371.6700\ncurrent episode reward: 345.0000\nepisodes: 10625\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33612.3 seconds (9.34 hours)\n\nTimestep: 7760000\nmean reward (100 episodes): 370.6500\nbest mean reward: 371.6700\ncurrent episode reward: 349.0000\nepisodes: 10630\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33657.0 seconds (9.35 hours)\n\nTimestep: 7770000\nmean reward (100 episodes): 368.2600\nbest mean reward: 371.6700\ncurrent episode reward: 424.0000\nepisodes: 10634\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33701.2 seconds (9.36 hours)\n\nTimestep: 7780000\nmean reward (100 episodes): 367.3600\nbest mean reward: 371.6700\ncurrent episode reward: 337.0000\nepisodes: 10638\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33746.1 seconds (9.37 hours)\n\nTimestep: 7790000\nmean reward (100 episodes): 371.4700\nbest mean reward: 371.6700\ncurrent episode reward: 401.0000\nepisodes: 10643\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33790.4 seconds (9.39 hours)\n\nTimestep: 7800000\nmean reward (100 episodes): 369.3200\nbest mean reward: 372.9000\ncurrent episode reward: 53.0000\nepisodes: 10646\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33836.3 seconds (9.40 hours)\n\nTimestep: 7810000\nmean reward (100 episodes): 363.8900\nbest mean reward: 372.9000\ncurrent episode reward: 202.0000\nepisodes: 10651\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33880.3 seconds (9.41 hours)\n\nTimestep: 7820000\nmean reward (100 episodes): 364.5200\nbest mean reward: 372.9000\ncurrent episode reward: 393.0000\nepisodes: 10656\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33924.7 seconds (9.42 hours)\n\nTimestep: 7830000\nmean reward (100 episodes): 365.2700\nbest mean reward: 372.9000\ncurrent episode reward: 376.0000\nepisodes: 10658\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33969.2 seconds (9.44 hours)\n\nTimestep: 7840000\nmean reward (100 episodes): 363.5600\nbest mean reward: 372.9000\ncurrent episode reward: 424.0000\nepisodes: 10663\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34013.3 seconds (9.45 hours)\n\nTimestep: 7850000\nmean reward (100 episodes): 365.7600\nbest mean reward: 372.9000\ncurrent episode reward: 388.0000\nepisodes: 10667\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34057.4 seconds (9.46 hours)\n\nTimestep: 7860000\nmean reward (100 episodes): 362.9800\nbest mean reward: 372.9000\ncurrent episode reward: 374.0000\nepisodes: 10673\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34101.2 seconds (9.47 hours)\n\nTimestep: 7870000\nmean reward (100 episodes): 365.0600\nbest mean reward: 372.9000\ncurrent episode reward: 409.0000\nepisodes: 10677\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34146.2 seconds (9.49 hours)\n\nTimestep: 7880000\nmean reward (100 episodes): 368.2200\nbest mean reward: 372.9000\ncurrent episode reward: 367.0000\nepisodes: 10681\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34190.1 seconds (9.50 hours)\n\nTimestep: 7890000\nmean reward (100 episodes): 363.1700\nbest mean reward: 372.9000\ncurrent episode reward: 420.0000\nepisodes: 10686\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34235.3 seconds (9.51 hours)\n\nTimestep: 7900000\nmean reward (100 episodes): 365.3300\nbest mean reward: 372.9000\ncurrent episode reward: 384.0000\nepisodes: 10691\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34279.2 seconds (9.52 hours)\n\nTimestep: 7910000\nmean reward (100 episodes): 366.7100\nbest mean reward: 372.9000\ncurrent episode reward: 335.0000\nepisodes: 10696\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34323.9 seconds (9.53 hours)\n\nTimestep: 7920000\nmean reward (100 episodes): 364.4200\nbest mean reward: 372.9000\ncurrent episode reward: 289.0000\nepisodes: 10699\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34368.1 seconds (9.55 hours)\n\nTimestep: 7930000\nmean reward (100 episodes): 362.9700\nbest mean reward: 372.9000\ncurrent episode reward: 402.0000\nepisodes: 10703\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34413.4 seconds (9.56 hours)\n\nTimestep: 7940000\nmean reward (100 episodes): 364.9900\nbest mean reward: 372.9000\ncurrent episode reward: 410.0000\nepisodes: 10707\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34457.5 seconds (9.57 hours)\n\nTimestep: 7950000\nmean reward (100 episodes): 364.7700\nbest mean reward: 372.9000\ncurrent episode reward: 413.0000\nepisodes: 10711\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34502.8 seconds (9.58 hours)\n\nTimestep: 7960000\nmean reward (100 episodes): 363.6500\nbest mean reward: 372.9000\ncurrent episode reward: 386.0000\nepisodes: 10715\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34547.4 seconds (9.60 hours)\n\nTimestep: 7970000\nmean reward (100 episodes): 358.2900\nbest mean reward: 372.9000\ncurrent episode reward: 321.0000\nepisodes: 10718\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34591.9 seconds (9.61 hours)\n\nTimestep: 7980000\nmean reward (100 episodes): 356.6700\nbest mean reward: 372.9000\ncurrent episode reward: 291.0000\nepisodes: 10723\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34636.1 seconds (9.62 hours)\n\nTimestep: 7990000\nmean reward (100 episodes): 358.0800\nbest mean reward: 372.9000\ncurrent episode reward: 436.0000\nepisodes: 10726\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34681.4 seconds (9.63 hours)\n\nTimestep: 8000000\nmean reward (100 episodes): 354.2400\nbest mean reward: 372.9000\ncurrent episode reward: 264.0000\nepisodes: 10731\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34726.5 seconds (9.65 hours)\n\nTimestep: 8010000\nmean reward (100 episodes): 358.0800\nbest mean reward: 372.9000\ncurrent episode reward: 420.0000\nepisodes: 10735\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34770.4 seconds (9.66 hours)\n\nTimestep: 8020000\nmean reward (100 episodes): 357.6300\nbest mean reward: 372.9000\ncurrent episode reward: 336.0000\nepisodes: 10739\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34814.3 seconds (9.67 hours)\n\nTimestep: 8030000\nmean reward (100 episodes): 357.3000\nbest mean reward: 372.9000\ncurrent episode reward: 351.0000\nepisodes: 10742\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34858.1 seconds (9.68 hours)\n\nTimestep: 8040000\nmean reward (100 episodes): 359.8400\nbest mean reward: 372.9000\ncurrent episode reward: 377.0000\nepisodes: 10746\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34902.2 seconds (9.70 hours)\n\nTimestep: 8050000\nmean reward (100 episodes): 364.0300\nbest mean reward: 372.9000\ncurrent episode reward: 419.0000\nepisodes: 10751\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34946.7 seconds (9.71 hours)\n\nTimestep: 8060000\nmean reward (100 episodes): 363.0700\nbest mean reward: 372.9000\ncurrent episode reward: 351.0000\nepisodes: 10755\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34991.4 seconds (9.72 hours)\n\nTimestep: 8070000\nmean reward (100 episodes): 357.0600\nbest mean reward: 372.9000\ncurrent episode reward: 279.0000\nepisodes: 10760\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35036.2 seconds (9.73 hours)\n\nTimestep: 8080000\nmean reward (100 episodes): 355.7700\nbest mean reward: 372.9000\ncurrent episode reward: 325.0000\nepisodes: 10764\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35081.2 seconds (9.74 hours)\n\nTimestep: 8090000\nmean reward (100 episodes): 356.6600\nbest mean reward: 372.9000\ncurrent episode reward: 304.0000\nepisodes: 10769\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35126.0 seconds (9.76 hours)\n\nTimestep: 8100000\nmean reward (100 episodes): 356.7800\nbest mean reward: 372.9000\ncurrent episode reward: 404.0000\nepisodes: 10774\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35170.4 seconds (9.77 hours)\n\nTimestep: 8110000\nmean reward (100 episodes): 351.0500\nbest mean reward: 372.9000\ncurrent episode reward: 402.0000\nepisodes: 10779\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35214.7 seconds (9.78 hours)\n\nTimestep: 8120000\nmean reward (100 episodes): 349.5900\nbest mean reward: 372.9000\ncurrent episode reward: 416.0000\nepisodes: 10783\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35258.9 seconds (9.79 hours)\n\nTimestep: 8130000\nmean reward (100 episodes): 349.3900\nbest mean reward: 372.9000\ncurrent episode reward: 372.0000\nepisodes: 10787\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35304.3 seconds (9.81 hours)\n\nTimestep: 8140000\nmean reward (100 episodes): 350.5600\nbest mean reward: 372.9000\ncurrent episode reward: 413.0000\nepisodes: 10790\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35348.5 seconds (9.82 hours)\n\nTimestep: 8150000\nmean reward (100 episodes): 349.0700\nbest mean reward: 372.9000\ncurrent episode reward: 292.0000\nepisodes: 10795\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35392.7 seconds (9.83 hours)\n\nTimestep: 8160000\nmean reward (100 episodes): 350.2500\nbest mean reward: 372.9000\ncurrent episode reward: 395.0000\nepisodes: 10798\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35437.4 seconds (9.84 hours)\n\nTimestep: 8170000\nmean reward (100 episodes): 351.2000\nbest mean reward: 372.9000\ncurrent episode reward: 350.0000\nepisodes: 10801\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35481.5 seconds (9.86 hours)\n\nTimestep: 8180000\nmean reward (100 episodes): 349.0600\nbest mean reward: 372.9000\ncurrent episode reward: 316.0000\nepisodes: 10806\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35526.1 seconds (9.87 hours)\n\nTimestep: 8190000\nmean reward (100 episodes): 349.8900\nbest mean reward: 372.9000\ncurrent episode reward: 387.0000\nepisodes: 10810\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35570.0 seconds (9.88 hours)\n\nTimestep: 8200000\nmean reward (100 episodes): 348.9500\nbest mean reward: 372.9000\ncurrent episode reward: 358.0000\nepisodes: 10814\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35614.7 seconds (9.89 hours)\n\nTimestep: 8210000\nmean reward (100 episodes): 348.9700\nbest mean reward: 372.9000\ncurrent episode reward: 409.0000\nepisodes: 10818\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35659.0 seconds (9.91 hours)\n\nTimestep: 8220000\nmean reward (100 episodes): 345.1000\nbest mean reward: 372.9000\ncurrent episode reward: 71.0000\nepisodes: 10823\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35703.8 seconds (9.92 hours)\n\nTimestep: 8230000\nmean reward (100 episodes): 341.4800\nbest mean reward: 372.9000\ncurrent episode reward: 396.0000\nepisodes: 10828\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35748.2 seconds (9.93 hours)\n\nTimestep: 8240000\nmean reward (100 episodes): 340.2500\nbest mean reward: 372.9000\ncurrent episode reward: 384.0000\nepisodes: 10833\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35793.2 seconds (9.94 hours)\n\nTimestep: 8250000\nmean reward (100 episodes): 339.6300\nbest mean reward: 372.9000\ncurrent episode reward: 371.0000\nepisodes: 10836\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35837.6 seconds (9.95 hours)\n\nTimestep: 8260000\nmean reward (100 episodes): 334.8000\nbest mean reward: 372.9000\ncurrent episode reward: 243.0000\nepisodes: 10841\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35882.8 seconds (9.97 hours)\n\nTimestep: 8270000\nmean reward (100 episodes): 328.4700\nbest mean reward: 372.9000\ncurrent episode reward: 51.0000\nepisodes: 10846\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35927.5 seconds (9.98 hours)\n\nTimestep: 8280000\nmean reward (100 episodes): 330.9200\nbest mean reward: 372.9000\ncurrent episode reward: 407.0000\nepisodes: 10850\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35972.3 seconds (9.99 hours)\n\nTimestep: 8290000\nmean reward (100 episodes): 333.1900\nbest mean reward: 372.9000\ncurrent episode reward: 431.0000\nepisodes: 10854\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36015.6 seconds (10.00 hours)\n\nTimestep: 8300000\nmean reward (100 episodes): 338.7700\nbest mean reward: 372.9000\ncurrent episode reward: 420.0000\nepisodes: 10858\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36058.1 seconds (10.02 hours)\n\nTimestep: 8310000\nmean reward (100 episodes): 339.5800\nbest mean reward: 372.9000\ncurrent episode reward: 358.0000\nepisodes: 10862\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36103.1 seconds (10.03 hours)\n\nTimestep: 8320000\nmean reward (100 episodes): 336.7500\nbest mean reward: 372.9000\ncurrent episode reward: 215.0000\nepisodes: 10867\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36147.5 seconds (10.04 hours)\n\nTimestep: 8330000\nmean reward (100 episodes): 336.9800\nbest mean reward: 372.9000\ncurrent episode reward: 413.0000\nepisodes: 10872\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36192.1 seconds (10.05 hours)\n\nTimestep: 8340000\nmean reward (100 episodes): 336.8500\nbest mean reward: 372.9000\ncurrent episode reward: 415.0000\nepisodes: 10873\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36236.8 seconds (10.07 hours)\n\nTimestep: 8350000\nmean reward (100 episodes): 343.5800\nbest mean reward: 372.9000\ncurrent episode reward: 385.0000\nepisodes: 10876\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36281.3 seconds (10.08 hours)\n\nTimestep: 8360000\nmean reward (100 episodes): 347.0000\nbest mean reward: 372.9000\ncurrent episode reward: 408.0000\nepisodes: 10880\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36325.9 seconds (10.09 hours)\n\nTimestep: 8370000\nmean reward (100 episodes): 352.3600\nbest mean reward: 372.9000\ncurrent episode reward: 385.0000\nepisodes: 10884\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36370.3 seconds (10.10 hours)\n\nTimestep: 8380000\nmean reward (100 episodes): 353.9400\nbest mean reward: 372.9000\ncurrent episode reward: 416.0000\nepisodes: 10888\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36414.9 seconds (10.12 hours)\n\nTimestep: 8390000\nmean reward (100 episodes): 354.0000\nbest mean reward: 372.9000\ncurrent episode reward: 418.0000\nepisodes: 10892\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36460.1 seconds (10.13 hours)\n\nTimestep: 8400000\nmean reward (100 episodes): 356.6100\nbest mean reward: 372.9000\ncurrent episode reward: 404.0000\nepisodes: 10896\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36504.4 seconds (10.14 hours)\n\nTimestep: 8410000\nmean reward (100 episodes): 357.3000\nbest mean reward: 372.9000\ncurrent episode reward: 420.0000\nepisodes: 10900\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36548.6 seconds (10.15 hours)\n\nTimestep: 8420000\nmean reward (100 episodes): 358.5200\nbest mean reward: 372.9000\ncurrent episode reward: 431.0000\nepisodes: 10905\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36593.3 seconds (10.16 hours)\n\nTimestep: 8430000\nmean reward (100 episodes): 357.5900\nbest mean reward: 372.9000\ncurrent episode reward: 415.0000\nepisodes: 10907\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36638.2 seconds (10.18 hours)\n\nTimestep: 8440000\nmean reward (100 episodes): 357.8300\nbest mean reward: 372.9000\ncurrent episode reward: 407.0000\nepisodes: 10910\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36682.6 seconds (10.19 hours)\n\nTimestep: 8450000\nmean reward (100 episodes): 358.3400\nbest mean reward: 372.9000\ncurrent episode reward: 397.0000\nepisodes: 10914\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36726.3 seconds (10.20 hours)\n\nTimestep: 8460000\nmean reward (100 episodes): 359.2200\nbest mean reward: 372.9000\ncurrent episode reward: 333.0000\nepisodes: 10917\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36770.9 seconds (10.21 hours)\n\nTimestep: 8470000\nmean reward (100 episodes): 358.8900\nbest mean reward: 372.9000\ncurrent episode reward: 401.0000\nepisodes: 10921\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36814.9 seconds (10.23 hours)\n\nTimestep: 8480000\nmean reward (100 episodes): 360.1700\nbest mean reward: 372.9000\ncurrent episode reward: 424.0000\nepisodes: 10925\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36858.9 seconds (10.24 hours)\n\nTimestep: 8490000\nmean reward (100 episodes): 367.1800\nbest mean reward: 372.9000\ncurrent episode reward: 795.0000\nepisodes: 10928\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36903.1 seconds (10.25 hours)\n\nTimestep: 8500000\nmean reward (100 episodes): 368.3500\nbest mean reward: 372.9000\ncurrent episode reward: 421.0000\nepisodes: 10932\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36948.3 seconds (10.26 hours)\n\nTimestep: 8510000\nmean reward (100 episodes): 369.3700\nbest mean reward: 372.9000\ncurrent episode reward: 399.0000\nepisodes: 10935\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36993.0 seconds (10.28 hours)\n\nTimestep: 8520000\nmean reward (100 episodes): 369.3000\nbest mean reward: 372.9000\ncurrent episode reward: 402.0000\nepisodes: 10939\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37037.7 seconds (10.29 hours)\n\nTimestep: 8530000\nmean reward (100 episodes): 374.6500\nbest mean reward: 374.7300\ncurrent episode reward: 362.0000\nepisodes: 10942\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37082.0 seconds (10.30 hours)\n\nTimestep: 8540000\nmean reward (100 episodes): 381.8400\nbest mean reward: 381.8400\ncurrent episode reward: 404.0000\nepisodes: 10946\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37126.2 seconds (10.31 hours)\n\nTimestep: 8550000\nmean reward (100 episodes): 381.7900\nbest mean reward: 382.0500\ncurrent episode reward: 381.0000\nepisodes: 10950\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37170.5 seconds (10.33 hours)\n\nTimestep: 8560000\nmean reward (100 episodes): 381.2100\nbest mean reward: 382.0500\ncurrent episode reward: 334.0000\nepisodes: 10953\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37215.0 seconds (10.34 hours)\n\nTimestep: 8570000\nmean reward (100 episodes): 379.5400\nbest mean reward: 382.0500\ncurrent episode reward: 122.0000\nepisodes: 10957\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37259.0 seconds (10.35 hours)\n\nTimestep: 8580000\nmean reward (100 episodes): 385.2100\nbest mean reward: 385.2100\ncurrent episode reward: 433.0000\nepisodes: 10960\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37303.5 seconds (10.36 hours)\n\nTimestep: 8590000\nmean reward (100 episodes): 387.2700\nbest mean reward: 387.2700\ncurrent episode reward: 262.0000\nepisodes: 10964\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37347.3 seconds (10.37 hours)\n\nTimestep: 8600000\nmean reward (100 episodes): 385.4800\nbest mean reward: 387.6300\ncurrent episode reward: 177.0000\nepisodes: 10969\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37391.3 seconds (10.39 hours)\n\nTimestep: 8610000\nmean reward (100 episodes): 386.3400\nbest mean reward: 387.6300\ncurrent episode reward: 412.0000\nepisodes: 10972\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37436.8 seconds (10.40 hours)\n\nTimestep: 8620000\nmean reward (100 episodes): 380.6600\nbest mean reward: 387.6300\ncurrent episode reward: 221.0000\nepisodes: 10976\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37481.0 seconds (10.41 hours)\n\nTimestep: 8630000\nmean reward (100 episodes): 379.9500\nbest mean reward: 387.6300\ncurrent episode reward: 424.0000\nepisodes: 10980\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37525.9 seconds (10.42 hours)\n\nTimestep: 8640000\nmean reward (100 episodes): 376.8500\nbest mean reward: 387.6300\ncurrent episode reward: 283.0000\nepisodes: 10984\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37571.1 seconds (10.44 hours)\n\nTimestep: 8650000\nmean reward (100 episodes): 376.9200\nbest mean reward: 387.6300\ncurrent episode reward: 398.0000\nepisodes: 10988\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37615.6 seconds (10.45 hours)\n\nTimestep: 8660000\nmean reward (100 episodes): 376.8400\nbest mean reward: 387.6300\ncurrent episode reward: 388.0000\nepisodes: 10990\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37660.8 seconds (10.46 hours)\n\nTimestep: 8670000\nmean reward (100 episodes): 377.1600\nbest mean reward: 387.6300\ncurrent episode reward: 428.0000\nepisodes: 10993\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37705.1 seconds (10.47 hours)\n\nTimestep: 8680000\nmean reward (100 episodes): 375.7600\nbest mean reward: 387.6300\ncurrent episode reward: 297.0000\nepisodes: 10995\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37749.6 seconds (10.49 hours)\n\nTimestep: 8690000\nmean reward (100 episodes): 375.6800\nbest mean reward: 387.6300\ncurrent episode reward: 418.0000\nepisodes: 10998\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37793.9 seconds (10.50 hours)\n\nTimestep: 8700000\nmean reward (100 episodes): 377.7600\nbest mean reward: 387.6300\ncurrent episode reward: 400.0000\nepisodes: 11002\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37845.6 seconds (10.51 hours)\n\nTimestep: 8710000\nmean reward (100 episodes): 377.0700\nbest mean reward: 387.6300\ncurrent episode reward: 441.0000\nepisodes: 11005\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37889.8 seconds (10.52 hours)\n\nTimestep: 8720000\nmean reward (100 episodes): 377.9300\nbest mean reward: 387.6300\ncurrent episode reward: 378.0000\nepisodes: 11009\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37934.4 seconds (10.54 hours)\n\nTimestep: 8730000\nmean reward (100 episodes): 377.9700\nbest mean reward: 387.6300\ncurrent episode reward: 419.0000\nepisodes: 11013\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37978.8 seconds (10.55 hours)\n\nTimestep: 8740000\nmean reward (100 episodes): 378.4000\nbest mean reward: 387.6300\ncurrent episode reward: 414.0000\nepisodes: 11016\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38022.7 seconds (10.56 hours)\n\nTimestep: 8750000\nmean reward (100 episodes): 377.9200\nbest mean reward: 387.6300\ncurrent episode reward: 293.0000\nepisodes: 11021\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38067.7 seconds (10.57 hours)\n\nTimestep: 8760000\nmean reward (100 episodes): 381.2800\nbest mean reward: 387.6300\ncurrent episode reward: 374.0000\nepisodes: 11025\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38113.0 seconds (10.59 hours)\n\nTimestep: 8770000\nmean reward (100 episodes): 376.6900\nbest mean reward: 387.6300\ncurrent episode reward: 357.0000\nepisodes: 11029\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38157.2 seconds (10.60 hours)\n\nTimestep: 8780000\nmean reward (100 episodes): 379.9800\nbest mean reward: 387.6300\ncurrent episode reward: 427.0000\nepisodes: 11033\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38202.1 seconds (10.61 hours)\n\nTimestep: 8790000\nmean reward (100 episodes): 379.2900\nbest mean reward: 387.6300\ncurrent episode reward: 300.0000\nepisodes: 11037\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38247.2 seconds (10.62 hours)\n\nTimestep: 8800000\nmean reward (100 episodes): 377.3900\nbest mean reward: 387.6300\ncurrent episode reward: 150.0000\nepisodes: 11042\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38291.9 seconds (10.64 hours)\n\nTimestep: 8810000\nmean reward (100 episodes): 375.1100\nbest mean reward: 387.6300\ncurrent episode reward: 120.0000\nepisodes: 11046\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38337.1 seconds (10.65 hours)\n\nTimestep: 8820000\nmean reward (100 episodes): 375.7000\nbest mean reward: 387.6300\ncurrent episode reward: 428.0000\nepisodes: 11049\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38382.7 seconds (10.66 hours)\n\nTimestep: 8830000\nmean reward (100 episodes): 371.4100\nbest mean reward: 387.6300\ncurrent episode reward: 280.0000\nepisodes: 11054\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38428.0 seconds (10.67 hours)\n\nTimestep: 8840000\nmean reward (100 episodes): 374.2200\nbest mean reward: 387.6300\ncurrent episode reward: 425.0000\nepisodes: 11057\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38473.2 seconds (10.69 hours)\n\nTimestep: 8850000\nmean reward (100 episodes): 369.5500\nbest mean reward: 387.6300\ncurrent episode reward: 377.0000\nepisodes: 11062\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38517.3 seconds (10.70 hours)\n\nTimestep: 8860000\nmean reward (100 episodes): 372.1200\nbest mean reward: 387.6300\ncurrent episode reward: 277.0000\nepisodes: 11066\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38561.9 seconds (10.71 hours)\n\nTimestep: 8870000\nmean reward (100 episodes): 372.2600\nbest mean reward: 387.6300\ncurrent episode reward: 383.0000\nepisodes: 11068\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38606.3 seconds (10.72 hours)\n\nTimestep: 8880000\nmean reward (100 episodes): 373.6700\nbest mean reward: 387.6300\ncurrent episode reward: 337.0000\nepisodes: 11071\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38650.4 seconds (10.74 hours)\n\nTimestep: 8890000\nmean reward (100 episodes): 376.2600\nbest mean reward: 387.6300\ncurrent episode reward: 416.0000\nepisodes: 11075\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38694.4 seconds (10.75 hours)\n\nTimestep: 8900000\nmean reward (100 episodes): 376.7500\nbest mean reward: 387.6300\ncurrent episode reward: 345.0000\nepisodes: 11080\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38737.9 seconds (10.76 hours)\n\nTimestep: 8910000\nmean reward (100 episodes): 379.8200\nbest mean reward: 387.6300\ncurrent episode reward: 399.0000\nepisodes: 11083\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38782.7 seconds (10.77 hours)\n\nTimestep: 8920000\nmean reward (100 episodes): 381.0400\nbest mean reward: 387.6300\ncurrent episode reward: 390.0000\nepisodes: 11087\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38826.8 seconds (10.79 hours)\n\nTimestep: 8930000\nmean reward (100 episodes): 379.9800\nbest mean reward: 387.6300\ncurrent episode reward: 392.0000\nepisodes: 11090\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38871.5 seconds (10.80 hours)\n\nTimestep: 8940000\nmean reward (100 episodes): 379.9300\nbest mean reward: 387.6300\ncurrent episode reward: 399.0000\nepisodes: 11093\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38916.4 seconds (10.81 hours)\n\nTimestep: 8950000\nmean reward (100 episodes): 381.4200\nbest mean reward: 387.6300\ncurrent episode reward: 406.0000\nepisodes: 11095\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38960.3 seconds (10.82 hours)\n\nTimestep: 8960000\nmean reward (100 episodes): 383.2000\nbest mean reward: 387.6300\ncurrent episode reward: 367.0000\nepisodes: 11099\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39004.6 seconds (10.83 hours)\n\nTimestep: 8970000\nmean reward (100 episodes): 382.8000\nbest mean reward: 387.6300\ncurrent episode reward: 427.0000\nepisodes: 11102\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39049.8 seconds (10.85 hours)\n\nTimestep: 8980000\nmean reward (100 episodes): 380.7000\nbest mean reward: 387.6300\ncurrent episode reward: 409.0000\nepisodes: 11107\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39093.5 seconds (10.86 hours)\n\nTimestep: 8990000\nmean reward (100 episodes): 380.9500\nbest mean reward: 387.6300\ncurrent episode reward: 270.0000\nepisodes: 11110\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39138.7 seconds (10.87 hours)\n\nTimestep: 9000000\nmean reward (100 episodes): 380.7800\nbest mean reward: 387.6300\ncurrent episode reward: 395.0000\nepisodes: 11113\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39182.8 seconds (10.88 hours)\n\nTimestep: 9010000\nmean reward (100 episodes): 380.7000\nbest mean reward: 387.6300\ncurrent episode reward: 424.0000\nepisodes: 11116\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39227.0 seconds (10.90 hours)\n\nTimestep: 9020000\nmean reward (100 episodes): 380.9700\nbest mean reward: 387.6300\ncurrent episode reward: 394.0000\nepisodes: 11119\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39271.5 seconds (10.91 hours)\n\nTimestep: 9030000\nmean reward (100 episodes): 381.6100\nbest mean reward: 387.6300\ncurrent episode reward: 371.0000\nepisodes: 11122\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39316.4 seconds (10.92 hours)\n\nTimestep: 9040000\nmean reward (100 episodes): 383.3800\nbest mean reward: 387.6300\ncurrent episode reward: 419.0000\nepisodes: 11125\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39361.3 seconds (10.93 hours)\n\nTimestep: 9050000\nmean reward (100 episodes): 384.5000\nbest mean reward: 387.6300\ncurrent episode reward: 399.0000\nepisodes: 11129\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39405.9 seconds (10.95 hours)\n\nTimestep: 9060000\nmean reward (100 episodes): 382.4800\nbest mean reward: 387.6300\ncurrent episode reward: 420.0000\nepisodes: 11133\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39450.6 seconds (10.96 hours)\n\nTimestep: 9070000\nmean reward (100 episodes): 381.4500\nbest mean reward: 387.6300\ncurrent episode reward: 411.0000\nepisodes: 11137\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39494.7 seconds (10.97 hours)\n\nTimestep: 9080000\nmean reward (100 episodes): 381.7400\nbest mean reward: 387.6300\ncurrent episode reward: 431.0000\nepisodes: 11141\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39539.4 seconds (10.98 hours)\n\nTimestep: 9090000\nmean reward (100 episodes): 384.1500\nbest mean reward: 387.6300\ncurrent episode reward: 384.0000\nepisodes: 11143\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39583.8 seconds (11.00 hours)\n\nTimestep: 9100000\nmean reward (100 episodes): 382.7000\nbest mean reward: 387.6300\ncurrent episode reward: 294.0000\nepisodes: 11149\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39628.6 seconds (11.01 hours)\n\nTimestep: 9110000\nmean reward (100 episodes): 386.8300\nbest mean reward: 387.6300\ncurrent episode reward: 293.0000\nepisodes: 11152\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39672.5 seconds (11.02 hours)\n\nTimestep: 9120000\nmean reward (100 episodes): 385.7800\nbest mean reward: 388.4400\ncurrent episode reward: 162.0000\nepisodes: 11155\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39716.3 seconds (11.03 hours)\n\nTimestep: 9130000\nmean reward (100 episodes): 382.1700\nbest mean reward: 388.4400\ncurrent episode reward: 379.0000\nepisodes: 11158\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39761.3 seconds (11.04 hours)\n\nTimestep: 9140000\nmean reward (100 episodes): 383.1600\nbest mean reward: 388.4400\ncurrent episode reward: 417.0000\nepisodes: 11160\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39805.9 seconds (11.06 hours)\n\nTimestep: 9150000\nmean reward (100 episodes): 383.8800\nbest mean reward: 388.4400\ncurrent episode reward: 412.0000\nepisodes: 11164\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39851.0 seconds (11.07 hours)\n\nTimestep: 9160000\nmean reward (100 episodes): 385.1000\nbest mean reward: 388.4400\ncurrent episode reward: 320.0000\nepisodes: 11167\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39895.8 seconds (11.08 hours)\n\nTimestep: 9170000\nmean reward (100 episodes): 384.7100\nbest mean reward: 388.4400\ncurrent episode reward: 303.0000\nepisodes: 11171\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39940.3 seconds (11.09 hours)\n\nTimestep: 9180000\nmean reward (100 episodes): 381.7300\nbest mean reward: 388.4400\ncurrent episode reward: 417.0000\nepisodes: 11175\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39984.5 seconds (11.11 hours)\n\nTimestep: 9190000\nmean reward (100 episodes): 383.1700\nbest mean reward: 388.4400\ncurrent episode reward: 432.0000\nepisodes: 11178\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40029.4 seconds (11.12 hours)\n\nTimestep: 9200000\nmean reward (100 episodes): 381.7900\nbest mean reward: 388.4400\ncurrent episode reward: 260.0000\nepisodes: 11182\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40073.9 seconds (11.13 hours)\n\nTimestep: 9210000\nmean reward (100 episodes): 381.5100\nbest mean reward: 388.4400\ncurrent episode reward: 412.0000\nepisodes: 11185\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40118.7 seconds (11.14 hours)\n\nTimestep: 9220000\nmean reward (100 episodes): 378.3200\nbest mean reward: 388.4400\ncurrent episode reward: 301.0000\nepisodes: 11188\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40163.4 seconds (11.16 hours)\n\nTimestep: 9230000\nmean reward (100 episodes): 375.4700\nbest mean reward: 388.4400\ncurrent episode reward: 387.0000\nepisodes: 11193\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40208.5 seconds (11.17 hours)\n\nTimestep: 9240000\nmean reward (100 episodes): 375.2100\nbest mean reward: 388.4400\ncurrent episode reward: 417.0000\nepisodes: 11195\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40253.3 seconds (11.18 hours)\n\nTimestep: 9250000\nmean reward (100 episodes): 373.3800\nbest mean reward: 388.4400\ncurrent episode reward: 393.0000\nepisodes: 11198\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40298.1 seconds (11.19 hours)\n\nTimestep: 9260000\nmean reward (100 episodes): 373.2700\nbest mean reward: 388.4400\ncurrent episode reward: 381.0000\nepisodes: 11202\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40342.5 seconds (11.21 hours)\n\nTimestep: 9270000\nmean reward (100 episodes): 371.1300\nbest mean reward: 388.4400\ncurrent episode reward: 342.0000\nepisodes: 11207\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40387.1 seconds (11.22 hours)\n\nTimestep: 9280000\nmean reward (100 episodes): 372.3600\nbest mean reward: 388.4400\ncurrent episode reward: 421.0000\nepisodes: 11211\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40431.7 seconds (11.23 hours)\n\nTimestep: 9290000\nmean reward (100 episodes): 372.6800\nbest mean reward: 388.4400\ncurrent episode reward: 399.0000\nepisodes: 11215\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40476.0 seconds (11.24 hours)\n\nTimestep: 9300000\nmean reward (100 episodes): 371.9000\nbest mean reward: 388.4400\ncurrent episode reward: 374.0000\nepisodes: 11218\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40520.6 seconds (11.26 hours)\n\nTimestep: 9310000\nmean reward (100 episodes): 369.9800\nbest mean reward: 388.4400\ncurrent episode reward: 383.0000\nepisodes: 11222\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40564.4 seconds (11.27 hours)\n\nTimestep: 9320000\nmean reward (100 episodes): 368.5400\nbest mean reward: 388.4400\ncurrent episode reward: 382.0000\nepisodes: 11226\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40609.5 seconds (11.28 hours)\n\nTimestep: 9330000\nmean reward (100 episodes): 370.6500\nbest mean reward: 388.4400\ncurrent episode reward: 341.0000\nepisodes: 11231\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40653.9 seconds (11.29 hours)\n\nTimestep: 9340000\nmean reward (100 episodes): 370.6700\nbest mean reward: 388.4400\ncurrent episode reward: 403.0000\nepisodes: 11233\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40698.8 seconds (11.31 hours)\n\nTimestep: 9350000\nmean reward (100 episodes): 373.1900\nbest mean reward: 388.4400\ncurrent episode reward: 399.0000\nepisodes: 11236\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40742.8 seconds (11.32 hours)\n\nTimestep: 9360000\nmean reward (100 episodes): 367.0400\nbest mean reward: 388.4400\ncurrent episode reward: 84.0000\nepisodes: 11242\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40788.4 seconds (11.33 hours)\n\nTimestep: 9370000\nmean reward (100 episodes): 367.6200\nbest mean reward: 388.4400\ncurrent episode reward: 422.0000\nepisodes: 11246\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40833.3 seconds (11.34 hours)\n\nTimestep: 9380000\nmean reward (100 episodes): 372.7200\nbest mean reward: 388.4400\ncurrent episode reward: 413.0000\nepisodes: 11249\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40877.9 seconds (11.35 hours)\n\nTimestep: 9390000\nmean reward (100 episodes): 369.4800\nbest mean reward: 388.4400\ncurrent episode reward: 408.0000\nepisodes: 11254\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40923.3 seconds (11.37 hours)\n\nTimestep: 9400000\nmean reward (100 episodes): 374.6900\nbest mean reward: 388.4400\ncurrent episode reward: 406.0000\nepisodes: 11258\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40968.9 seconds (11.38 hours)\n\nTimestep: 9410000\nmean reward (100 episodes): 373.8400\nbest mean reward: 388.4400\ncurrent episode reward: 423.0000\nepisodes: 11262\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41013.6 seconds (11.39 hours)\n\nTimestep: 9420000\nmean reward (100 episodes): 374.3000\nbest mean reward: 388.4400\ncurrent episode reward: 425.0000\nepisodes: 11265\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41057.7 seconds (11.40 hours)\n\nTimestep: 9430000\nmean reward (100 episodes): 372.7300\nbest mean reward: 388.4400\ncurrent episode reward: 224.0000\nepisodes: 11268\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41102.1 seconds (11.42 hours)\n\nTimestep: 9440000\nmean reward (100 episodes): 372.6600\nbest mean reward: 388.4400\ncurrent episode reward: 406.0000\nepisodes: 11272\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41146.4 seconds (11.43 hours)\n\nTimestep: 9450000\nmean reward (100 episodes): 373.4700\nbest mean reward: 388.4400\ncurrent episode reward: 411.0000\nepisodes: 11274\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41189.8 seconds (11.44 hours)\n\nTimestep: 9460000\nmean reward (100 episodes): 372.1000\nbest mean reward: 388.4400\ncurrent episode reward: 406.0000\nepisodes: 11278\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41234.5 seconds (11.45 hours)\n\nTimestep: 9470000\nmean reward (100 episodes): 372.6800\nbest mean reward: 388.4400\ncurrent episode reward: 232.0000\nepisodes: 11282\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41278.4 seconds (11.47 hours)\n\nTimestep: 9480000\nmean reward (100 episodes): 372.3000\nbest mean reward: 388.4400\ncurrent episode reward: 382.0000\nepisodes: 11285\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41322.8 seconds (11.48 hours)\n\nTimestep: 9490000\nmean reward (100 episodes): 375.1200\nbest mean reward: 388.4400\ncurrent episode reward: 346.0000\nepisodes: 11288\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41367.6 seconds (11.49 hours)\n\nTimestep: 9500000\nmean reward (100 episodes): 377.9900\nbest mean reward: 388.4400\ncurrent episode reward: 421.0000\nepisodes: 11291\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41412.0 seconds (11.50 hours)\n\nTimestep: 9510000\nmean reward (100 episodes): 378.9500\nbest mean reward: 388.4400\ncurrent episode reward: 410.0000\nepisodes: 11294\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41456.1 seconds (11.52 hours)\n\nTimestep: 9520000\nmean reward (100 episodes): 377.5800\nbest mean reward: 388.4400\ncurrent episode reward: 393.0000\nepisodes: 11299\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41500.7 seconds (11.53 hours)\n\nTimestep: 9530000\nmean reward (100 episodes): 378.0900\nbest mean reward: 388.4400\ncurrent episode reward: 404.0000\nepisodes: 11302\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41545.3 seconds (11.54 hours)\n\nTimestep: 9540000\nmean reward (100 episodes): 379.0600\nbest mean reward: 388.4400\ncurrent episode reward: 433.0000\nepisodes: 11304\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41589.5 seconds (11.55 hours)\n\nTimestep: 9550000\nmean reward (100 episodes): 380.7800\nbest mean reward: 388.4400\ncurrent episode reward: 246.0000\nepisodes: 11308\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41634.4 seconds (11.57 hours)\n\nTimestep: 9560000\nmean reward (100 episodes): 379.5600\nbest mean reward: 388.4400\ncurrent episode reward: 334.0000\nepisodes: 11312\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41679.0 seconds (11.58 hours)\n\nTimestep: 9570000\nmean reward (100 episodes): 375.7000\nbest mean reward: 388.4400\ncurrent episode reward: 410.0000\nepisodes: 11316\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41723.4 seconds (11.59 hours)\n\nTimestep: 9580000\nmean reward (100 episodes): 375.3700\nbest mean reward: 388.4400\ncurrent episode reward: 401.0000\nepisodes: 11319\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41768.2 seconds (11.60 hours)\n\nTimestep: 9590000\nmean reward (100 episodes): 377.5300\nbest mean reward: 388.4400\ncurrent episode reward: 354.0000\nepisodes: 11323\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41812.9 seconds (11.61 hours)\n\nTimestep: 9600000\nmean reward (100 episodes): 379.3700\nbest mean reward: 388.4400\ncurrent episode reward: 408.0000\nepisodes: 11325\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41856.8 seconds (11.63 hours)\n\nTimestep: 9610000\nmean reward (100 episodes): 379.5900\nbest mean reward: 388.4400\ncurrent episode reward: 424.0000\nepisodes: 11329\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41901.0 seconds (11.64 hours)\n\nTimestep: 9620000\nmean reward (100 episodes): 378.7900\nbest mean reward: 388.4400\ncurrent episode reward: 346.0000\nepisodes: 11332\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41945.0 seconds (11.65 hours)\n\nTimestep: 9630000\nmean reward (100 episodes): 374.1400\nbest mean reward: 388.4400\ncurrent episode reward: 113.0000\nepisodes: 11336\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41990.6 seconds (11.66 hours)\n\nTimestep: 9640000\nmean reward (100 episodes): 376.0700\nbest mean reward: 388.4400\ncurrent episode reward: 424.0000\nepisodes: 11340\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42034.9 seconds (11.68 hours)\n\nTimestep: 9650000\nmean reward (100 episodes): 379.8300\nbest mean reward: 388.4400\ncurrent episode reward: 413.0000\nepisodes: 11343\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42079.6 seconds (11.69 hours)\n\nTimestep: 9660000\nmean reward (100 episodes): 378.7500\nbest mean reward: 388.4400\ncurrent episode reward: 350.0000\nepisodes: 11347\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42124.2 seconds (11.70 hours)\n\nTimestep: 9670000\nmean reward (100 episodes): 379.2200\nbest mean reward: 388.4400\ncurrent episode reward: 423.0000\nepisodes: 11350\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42168.7 seconds (11.71 hours)\n\nTimestep: 9680000\nmean reward (100 episodes): 378.4500\nbest mean reward: 388.4400\ncurrent episode reward: 180.0000\nepisodes: 11354\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42212.7 seconds (11.73 hours)\n\nTimestep: 9684338\nmean reward (100 episodes): 378.3600\nbest mean reward: 388.4400\ncurrent episode reward: 343.0000\nepisodes: 11356\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42232.3 seconds (11.73 hours)\n"
  },
  {
    "path": "dqn/logs_text/Enduro_s001.text",
    "content": "('AVAILABLE GPUS: ', [u'device: 0, name: TITAN X (Pascal), pci bus id: 0000:01:00.0'])\ntask = Task<env_id=EnduroNoFrameskip-v3 trials=2 max_timesteps=40000000 max_seconds=None reward_floor=0.0 reward_ceiling=5000.0>\n\nTimestep: 60000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 18\nexploration: 0.94600\nlearning_rate: 0.00010\nelapsed time: 100.9 seconds (0.03 hours)\n\nTimestep: 70000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 21\nexploration: 0.93700\nlearning_rate: 0.00010\nelapsed time: 134.7 seconds (0.04 hours)\n\nTimestep: 80000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 24\nexploration: 0.92800\nlearning_rate: 0.00010\nelapsed time: 168.5 seconds (0.05 hours)\n\nTimestep: 90000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 27\nexploration: 0.91900\nlearning_rate: 0.00010\nelapsed time: 203.3 seconds (0.06 hours)\n\nTimestep: 100000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 30\nexploration: 0.91000\nlearning_rate: 0.00010\nelapsed time: 240.6 seconds (0.07 hours)\n\nTimestep: 110000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 33\nexploration: 0.90100\nlearning_rate: 0.00010\nelapsed time: 275.1 seconds (0.08 hours)\n\nTimestep: 120000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 36\nexploration: 0.89200\nlearning_rate: 0.00010\nelapsed time: 309.8 seconds (0.09 hours)\n\nTimestep: 130000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 39\nexploration: 0.88300\nlearning_rate: 0.00010\nelapsed time: 344.6 seconds (0.10 hours)\n\nTimestep: 140000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 42\nexploration: 0.87400\nlearning_rate: 0.00010\nelapsed time: 379.4 seconds (0.11 hours)\n\nTimestep: 150000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 45\nexploration: 0.86500\nlearning_rate: 0.00010\nelapsed time: 414.3 seconds (0.12 hours)\n\nTimestep: 160000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 48\nexploration: 0.85600\nlearning_rate: 0.00010\nelapsed time: 449.3 seconds (0.12 hours)\n\nTimestep: 170000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 51\nexploration: 0.84700\nlearning_rate: 0.00010\nelapsed time: 484.5 seconds (0.13 hours)\n\nTimestep: 180000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 54\nexploration: 0.83800\nlearning_rate: 0.00010\nelapsed time: 519.9 seconds (0.14 hours)\n\nTimestep: 190000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 57\nexploration: 0.82900\nlearning_rate: 0.00010\nelapsed time: 555.4 seconds (0.15 hours)\n\nTimestep: 200000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 60\nexploration: 0.82000\nlearning_rate: 0.00010\nelapsed time: 591.0 seconds (0.16 hours)\n\nTimestep: 210000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 63\nexploration: 0.81100\nlearning_rate: 0.00010\nelapsed time: 626.9 seconds (0.17 hours)\n\nTimestep: 220000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 66\nexploration: 0.80200\nlearning_rate: 0.00010\nelapsed time: 665.6 seconds (0.18 hours)\n\nTimestep: 230000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 69\nexploration: 0.79300\nlearning_rate: 0.00010\nelapsed time: 701.5 seconds (0.19 hours)\n\nTimestep: 240000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 72\nexploration: 0.78400\nlearning_rate: 0.00010\nelapsed time: 737.6 seconds (0.20 hours)\n\nTimestep: 250000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 75\nexploration: 0.77500\nlearning_rate: 0.00010\nelapsed time: 773.9 seconds (0.21 hours)\n\nTimestep: 260000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 78\nexploration: 0.76600\nlearning_rate: 0.00010\nelapsed time: 810.8 seconds (0.23 hours)\n\nTimestep: 270000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 81\nexploration: 0.75700\nlearning_rate: 0.00010\nelapsed time: 847.4 seconds (0.24 hours)\n\nTimestep: 280000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 84\nexploration: 0.74800\nlearning_rate: 0.00010\nelapsed time: 883.8 seconds (0.25 hours)\n\nTimestep: 290000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 87\nexploration: 0.73900\nlearning_rate: 0.00010\nelapsed time: 921.0 seconds (0.26 hours)\n\nTimestep: 300000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 90\nexploration: 0.73000\nlearning_rate: 0.00010\nelapsed time: 958.3 seconds (0.27 hours)\n\nTimestep: 310000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 93\nexploration: 0.72100\nlearning_rate: 0.00010\nelapsed time: 995.8 seconds (0.28 hours)\n\nTimestep: 320000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 96\nexploration: 0.71200\nlearning_rate: 0.00010\nelapsed time: 1033.7 seconds (0.29 hours)\n\nTimestep: 330000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 99\nexploration: 0.70300\nlearning_rate: 0.00010\nelapsed time: 1071.6 seconds (0.30 hours)\n\nTimestep: 340000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 102\nexploration: 0.69400\nlearning_rate: 0.00010\nelapsed time: 1109.5 seconds (0.31 hours)\n\nTimestep: 350000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 105\nexploration: 0.68500\nlearning_rate: 0.00010\nelapsed time: 1147.4 seconds (0.32 hours)\n\nTimestep: 360000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 108\nexploration: 0.67600\nlearning_rate: 0.00010\nelapsed time: 1185.4 seconds (0.33 hours)\n\nTimestep: 370000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 111\nexploration: 0.66700\nlearning_rate: 0.00010\nelapsed time: 1223.8 seconds (0.34 hours)\n\nTimestep: 380000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 114\nexploration: 0.65800\nlearning_rate: 0.00010\nelapsed time: 1261.3 seconds (0.35 hours)\n\nTimestep: 390000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 117\nexploration: 0.64900\nlearning_rate: 0.00010\nelapsed time: 1299.5 seconds (0.36 hours)\n\nTimestep: 400000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 120\nexploration: 0.64000\nlearning_rate: 0.00010\nelapsed time: 1338.5 seconds (0.37 hours)\n\nTimestep: 410000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 123\nexploration: 0.63100\nlearning_rate: 0.00010\nelapsed time: 1376.9 seconds (0.38 hours)\n\nTimestep: 420000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 126\nexploration: 0.62200\nlearning_rate: 0.00010\nelapsed time: 1418.0 seconds (0.39 hours)\n\nTimestep: 430000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 129\nexploration: 0.61300\nlearning_rate: 0.00010\nelapsed time: 1457.1 seconds (0.40 hours)\n\nTimestep: 440000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 132\nexploration: 0.60400\nlearning_rate: 0.00010\nelapsed time: 1496.1 seconds (0.42 hours)\n\nTimestep: 450000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 135\nexploration: 0.59500\nlearning_rate: 0.00010\nelapsed time: 1534.7 seconds (0.43 hours)\n\nTimestep: 460000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 138\nexploration: 0.58600\nlearning_rate: 0.00010\nelapsed time: 1574.2 seconds (0.44 hours)\n\nTimestep: 470000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 141\nexploration: 0.57700\nlearning_rate: 0.00010\nelapsed time: 1613.7 seconds (0.45 hours)\n\nTimestep: 480000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 144\nexploration: 0.56800\nlearning_rate: 0.00010\nelapsed time: 1653.0 seconds (0.46 hours)\n\nTimestep: 490000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 147\nexploration: 0.55900\nlearning_rate: 0.00010\nelapsed time: 1693.6 seconds (0.47 hours)\n\nTimestep: 500000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 150\nexploration: 0.55000\nlearning_rate: 0.00010\nelapsed time: 1733.2 seconds (0.48 hours)\n\nTimestep: 510000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 153\nexploration: 0.54100\nlearning_rate: 0.00010\nelapsed time: 1773.4 seconds (0.49 hours)\n\nTimestep: 520000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 156\nexploration: 0.53200\nlearning_rate: 0.00010\nelapsed time: 1814.4 seconds (0.50 hours)\n\nTimestep: 530000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 159\nexploration: 0.52300\nlearning_rate: 0.00010\nelapsed time: 1854.9 seconds (0.52 hours)\n\nTimestep: 540000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 162\nexploration: 0.51400\nlearning_rate: 0.00010\nelapsed time: 1895.0 seconds (0.53 hours)\n\nTimestep: 550000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 165\nexploration: 0.50500\nlearning_rate: 0.00010\nelapsed time: 1935.9 seconds (0.54 hours)\n\nTimestep: 560000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 168\nexploration: 0.49600\nlearning_rate: 0.00010\nelapsed time: 1976.6 seconds (0.55 hours)\n\nTimestep: 570000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 171\nexploration: 0.48700\nlearning_rate: 0.00010\nelapsed time: 2017.5 seconds (0.56 hours)\n\nTimestep: 580000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 174\nexploration: 0.47800\nlearning_rate: 0.00010\nelapsed time: 2058.5 seconds (0.57 hours)\n\nTimestep: 590000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 177\nexploration: 0.46900\nlearning_rate: 0.00010\nelapsed time: 2099.3 seconds (0.58 hours)\n\nTimestep: 600000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 180\nexploration: 0.46000\nlearning_rate: 0.00010\nelapsed time: 2140.3 seconds (0.59 hours)\n\nTimestep: 610000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 183\nexploration: 0.45100\nlearning_rate: 0.00010\nelapsed time: 2181.6 seconds (0.61 hours)\n\nTimestep: 620000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 186\nexploration: 0.44200\nlearning_rate: 0.00010\nelapsed time: 2222.9 seconds (0.62 hours)\n\nTimestep: 630000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 189\nexploration: 0.43300\nlearning_rate: 0.00010\nelapsed time: 2264.8 seconds (0.63 hours)\n\nTimestep: 640000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 192\nexploration: 0.42400\nlearning_rate: 0.00010\nelapsed time: 2306.5 seconds (0.64 hours)\n\nTimestep: 650000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 195\nexploration: 0.41500\nlearning_rate: 0.00010\nelapsed time: 2347.3 seconds (0.65 hours)\n\nTimestep: 660000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 198\nexploration: 0.40600\nlearning_rate: 0.00010\nelapsed time: 2389.0 seconds (0.66 hours)\n\nTimestep: 670000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 201\nexploration: 0.39700\nlearning_rate: 0.00010\nelapsed time: 2430.8 seconds (0.68 hours)\n\nTimestep: 680000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 204\nexploration: 0.38800\nlearning_rate: 0.00010\nelapsed time: 2472.8 seconds (0.69 hours)\n\nTimestep: 690000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0300\ncurrent episode reward: 0.0000\nepisodes: 207\nexploration: 0.37900\nlearning_rate: 0.00010\nelapsed time: 2514.9 seconds (0.70 hours)\n\nTimestep: 700000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0400\ncurrent episode reward: 1.0000\nepisodes: 210\nexploration: 0.37000\nlearning_rate: 0.00010\nelapsed time: 2557.8 seconds (0.71 hours)\n\nTimestep: 710000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0400\ncurrent episode reward: 0.0000\nepisodes: 213\nexploration: 0.36100\nlearning_rate: 0.00010\nelapsed time: 2600.9 seconds (0.72 hours)\n\nTimestep: 720000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0400\ncurrent episode reward: 0.0000\nepisodes: 216\nexploration: 0.35200\nlearning_rate: 0.00010\nelapsed time: 2644.7 seconds (0.73 hours)\n\nTimestep: 730000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0400\ncurrent episode reward: 0.0000\nepisodes: 219\nexploration: 0.34300\nlearning_rate: 0.00010\nelapsed time: 2688.2 seconds (0.75 hours)\n\nTimestep: 740000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0400\ncurrent episode reward: 0.0000\nepisodes: 222\nexploration: 0.33400\nlearning_rate: 0.00010\nelapsed time: 2731.1 seconds (0.76 hours)\n\nTimestep: 750000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0400\ncurrent episode reward: 0.0000\nepisodes: 225\nexploration: 0.32500\nlearning_rate: 0.00010\nelapsed time: 2773.8 seconds (0.77 hours)\n\nTimestep: 760000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0400\ncurrent episode reward: 0.0000\nepisodes: 228\nexploration: 0.31600\nlearning_rate: 0.00010\nelapsed time: 2816.0 seconds (0.78 hours)\n\nTimestep: 770000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0400\ncurrent episode reward: 0.0000\nepisodes: 231\nexploration: 0.30700\nlearning_rate: 0.00010\nelapsed time: 2859.0 seconds (0.79 hours)\n\nTimestep: 780000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0400\ncurrent episode reward: 0.0000\nepisodes: 234\nexploration: 0.29800\nlearning_rate: 0.00010\nelapsed time: 2902.1 seconds (0.81 hours)\n\nTimestep: 790000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0400\ncurrent episode reward: 0.0000\nepisodes: 237\nexploration: 0.28900\nlearning_rate: 0.00010\nelapsed time: 2945.3 seconds (0.82 hours)\n\nTimestep: 800000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0400\ncurrent episode reward: 0.0000\nepisodes: 240\nexploration: 0.28000\nlearning_rate: 0.00010\nelapsed time: 2988.4 seconds (0.83 hours)\n\nTimestep: 810000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0400\ncurrent episode reward: 0.0000\nepisodes: 243\nexploration: 0.27100\nlearning_rate: 0.00010\nelapsed time: 3031.9 seconds (0.84 hours)\n\nTimestep: 820000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0400\ncurrent episode reward: 0.0000\nepisodes: 246\nexploration: 0.26200\nlearning_rate: 0.00010\nelapsed time: 3075.5 seconds (0.85 hours)\n\nTimestep: 830000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0400\ncurrent episode reward: 0.0000\nepisodes: 249\nexploration: 0.25300\nlearning_rate: 0.00010\nelapsed time: 3119.4 seconds (0.87 hours)\n\nTimestep: 840000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0400\ncurrent episode reward: 0.0000\nepisodes: 252\nexploration: 0.24400\nlearning_rate: 0.00010\nelapsed time: 3163.0 seconds (0.88 hours)\n\nTimestep: 850000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0400\ncurrent episode reward: 1.0000\nepisodes: 255\nexploration: 0.23500\nlearning_rate: 0.00010\nelapsed time: 3207.1 seconds (0.89 hours)\n\nTimestep: 860000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0400\ncurrent episode reward: 0.0000\nepisodes: 258\nexploration: 0.22600\nlearning_rate: 0.00010\nelapsed time: 3251.6 seconds (0.90 hours)\n\nTimestep: 870000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0400\ncurrent episode reward: 0.0000\nepisodes: 261\nexploration: 0.21700\nlearning_rate: 0.00010\nelapsed time: 3295.4 seconds (0.92 hours)\n\nTimestep: 880000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0400\ncurrent episode reward: 0.0000\nepisodes: 264\nexploration: 0.20800\nlearning_rate: 0.00010\nelapsed time: 3339.9 seconds (0.93 hours)\n\nTimestep: 890000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0400\ncurrent episode reward: 0.0000\nepisodes: 267\nexploration: 0.19900\nlearning_rate: 0.00010\nelapsed time: 3384.5 seconds (0.94 hours)\n\nTimestep: 900000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 270\nexploration: 0.19000\nlearning_rate: 0.00010\nelapsed time: 3429.2 seconds (0.95 hours)\n\nTimestep: 910000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 273\nexploration: 0.18100\nlearning_rate: 0.00010\nelapsed time: 3473.8 seconds (0.96 hours)\n\nTimestep: 920000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 276\nexploration: 0.17200\nlearning_rate: 0.00010\nelapsed time: 3519.0 seconds (0.98 hours)\n\nTimestep: 930000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 279\nexploration: 0.16300\nlearning_rate: 0.00010\nelapsed time: 3564.4 seconds (0.99 hours)\n\nTimestep: 940000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 282\nexploration: 0.15400\nlearning_rate: 0.00010\nelapsed time: 3609.3 seconds (1.00 hours)\n\nTimestep: 950000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 285\nexploration: 0.14500\nlearning_rate: 0.00010\nelapsed time: 3655.1 seconds (1.02 hours)\n\nTimestep: 960000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 288\nexploration: 0.13600\nlearning_rate: 0.00010\nelapsed time: 3699.8 seconds (1.03 hours)\n\nTimestep: 970000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 291\nexploration: 0.12700\nlearning_rate: 0.00010\nelapsed time: 3745.2 seconds (1.04 hours)\n\nTimestep: 980000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 294\nexploration: 0.11800\nlearning_rate: 0.00010\nelapsed time: 3790.3 seconds (1.05 hours)\n\nTimestep: 990000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 297\nexploration: 0.10900\nlearning_rate: 0.00010\nelapsed time: 3835.2 seconds (1.07 hours)\n\nTimestep: 1000000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 300\nexploration: 0.10000\nlearning_rate: 0.00010\nelapsed time: 3880.8 seconds (1.08 hours)\n\nTimestep: 1010000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 303\nexploration: 0.09978\nlearning_rate: 0.00010\nelapsed time: 3926.9 seconds (1.09 hours)\n\nTimestep: 1020000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 307\nexploration: 0.09955\nlearning_rate: 0.00010\nelapsed time: 3971.9 seconds (1.10 hours)\n\nTimestep: 1030000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 310\nexploration: 0.09933\nlearning_rate: 0.00010\nelapsed time: 4017.7 seconds (1.12 hours)\n\nTimestep: 1040000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 313\nexploration: 0.09910\nlearning_rate: 0.00010\nelapsed time: 4063.0 seconds (1.13 hours)\n\nTimestep: 1050000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 316\nexploration: 0.09888\nlearning_rate: 0.00010\nelapsed time: 4108.3 seconds (1.14 hours)\n\nTimestep: 1060000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 319\nexploration: 0.09865\nlearning_rate: 0.00010\nelapsed time: 4153.6 seconds (1.15 hours)\n\nTimestep: 1070000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 322\nexploration: 0.09842\nlearning_rate: 0.00010\nelapsed time: 4200.0 seconds (1.17 hours)\n\nTimestep: 1080000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 325\nexploration: 0.09820\nlearning_rate: 0.00010\nelapsed time: 4245.9 seconds (1.18 hours)\n\nTimestep: 1090000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 328\nexploration: 0.09798\nlearning_rate: 0.00010\nelapsed time: 4292.1 seconds (1.19 hours)\n\nTimestep: 1100000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 331\nexploration: 0.09775\nlearning_rate: 0.00010\nelapsed time: 4337.7 seconds (1.20 hours)\n\nTimestep: 1110000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 334\nexploration: 0.09753\nlearning_rate: 0.00010\nelapsed time: 4382.6 seconds (1.22 hours)\n\nTimestep: 1120000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 337\nexploration: 0.09730\nlearning_rate: 0.00010\nelapsed time: 4428.1 seconds (1.23 hours)\n\nTimestep: 1130000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 340\nexploration: 0.09708\nlearning_rate: 0.00010\nelapsed time: 4474.0 seconds (1.24 hours)\n\nTimestep: 1140000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 343\nexploration: 0.09685\nlearning_rate: 0.00010\nelapsed time: 4520.1 seconds (1.26 hours)\n\nTimestep: 1150000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 346\nexploration: 0.09663\nlearning_rate: 0.00010\nelapsed time: 4565.9 seconds (1.27 hours)\n\nTimestep: 1160000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 349\nexploration: 0.09640\nlearning_rate: 0.00010\nelapsed time: 4611.0 seconds (1.28 hours)\n\nTimestep: 1170000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 352\nexploration: 0.09618\nlearning_rate: 0.00010\nelapsed time: 4656.4 seconds (1.29 hours)\n\nTimestep: 1180000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 355\nexploration: 0.09595\nlearning_rate: 0.00010\nelapsed time: 4702.1 seconds (1.31 hours)\n\nTimestep: 1190000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 358\nexploration: 0.09573\nlearning_rate: 0.00010\nelapsed time: 4748.2 seconds (1.32 hours)\n\nTimestep: 1200000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 361\nexploration: 0.09550\nlearning_rate: 0.00010\nelapsed time: 4794.3 seconds (1.33 hours)\n\nTimestep: 1210000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 364\nexploration: 0.09527\nlearning_rate: 0.00010\nelapsed time: 4839.8 seconds (1.34 hours)\n\nTimestep: 1220000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.0600\ncurrent episode reward: 1.0000\nepisodes: 367\nexploration: 0.09505\nlearning_rate: 0.00010\nelapsed time: 4885.7 seconds (1.36 hours)\n\nTimestep: 1230000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 370\nexploration: 0.09483\nlearning_rate: 0.00010\nelapsed time: 4931.2 seconds (1.37 hours)\n\nTimestep: 1240000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 373\nexploration: 0.09460\nlearning_rate: 0.00010\nelapsed time: 4977.0 seconds (1.38 hours)\n\nTimestep: 1250000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 376\nexploration: 0.09438\nlearning_rate: 0.00010\nelapsed time: 5022.7 seconds (1.40 hours)\n\nTimestep: 1260000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 379\nexploration: 0.09415\nlearning_rate: 0.00010\nelapsed time: 5068.7 seconds (1.41 hours)\n\nTimestep: 1270000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 382\nexploration: 0.09393\nlearning_rate: 0.00010\nelapsed time: 5115.0 seconds (1.42 hours)\n\nTimestep: 1280000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 385\nexploration: 0.09370\nlearning_rate: 0.00010\nelapsed time: 5160.9 seconds (1.43 hours)\n\nTimestep: 1290000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 388\nexploration: 0.09348\nlearning_rate: 0.00010\nelapsed time: 5206.6 seconds (1.45 hours)\n\nTimestep: 1300000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 391\nexploration: 0.09325\nlearning_rate: 0.00010\nelapsed time: 5253.3 seconds (1.46 hours)\n\nTimestep: 1310000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 394\nexploration: 0.09303\nlearning_rate: 0.00010\nelapsed time: 5297.8 seconds (1.47 hours)\n\nTimestep: 1320000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 397\nexploration: 0.09280\nlearning_rate: 0.00010\nelapsed time: 5342.7 seconds (1.48 hours)\n\nTimestep: 1330000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 400\nexploration: 0.09258\nlearning_rate: 0.00010\nelapsed time: 5388.6 seconds (1.50 hours)\n\nTimestep: 1340000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 403\nexploration: 0.09235\nlearning_rate: 0.00010\nelapsed time: 5434.5 seconds (1.51 hours)\n\nTimestep: 1350000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 406\nexploration: 0.09213\nlearning_rate: 0.00010\nelapsed time: 5479.9 seconds (1.52 hours)\n\nTimestep: 1360000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 409\nexploration: 0.09190\nlearning_rate: 0.00010\nelapsed time: 5525.6 seconds (1.53 hours)\n\nTimestep: 1370000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 412\nexploration: 0.09168\nlearning_rate: 0.00010\nelapsed time: 5570.6 seconds (1.55 hours)\n\nTimestep: 1380000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 415\nexploration: 0.09145\nlearning_rate: 0.00010\nelapsed time: 5615.8 seconds (1.56 hours)\n\nTimestep: 1390000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 418\nexploration: 0.09123\nlearning_rate: 0.00010\nelapsed time: 5661.9 seconds (1.57 hours)\n\nTimestep: 1400000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 421\nexploration: 0.09100\nlearning_rate: 0.00010\nelapsed time: 5707.6 seconds (1.59 hours)\n\nTimestep: 1410000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 424\nexploration: 0.09078\nlearning_rate: 0.00009\nelapsed time: 5753.3 seconds (1.60 hours)\n\nTimestep: 1420000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 1.0000\nepisodes: 427\nexploration: 0.09055\nlearning_rate: 0.00009\nelapsed time: 5798.6 seconds (1.61 hours)\n\nTimestep: 1430000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 430\nexploration: 0.09033\nlearning_rate: 0.00009\nelapsed time: 5843.9 seconds (1.62 hours)\n\nTimestep: 1440000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 433\nexploration: 0.09010\nlearning_rate: 0.00009\nelapsed time: 5890.8 seconds (1.64 hours)\n\nTimestep: 1450000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 436\nexploration: 0.08988\nlearning_rate: 0.00009\nelapsed time: 5937.4 seconds (1.65 hours)\n\nTimestep: 1460000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 439\nexploration: 0.08965\nlearning_rate: 0.00009\nelapsed time: 5983.0 seconds (1.66 hours)\n\nTimestep: 1470000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 442\nexploration: 0.08943\nlearning_rate: 0.00009\nelapsed time: 6029.4 seconds (1.67 hours)\n\nTimestep: 1480000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 445\nexploration: 0.08920\nlearning_rate: 0.00009\nelapsed time: 6075.0 seconds (1.69 hours)\n\nTimestep: 1490000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 448\nexploration: 0.08897\nlearning_rate: 0.00009\nelapsed time: 6120.9 seconds (1.70 hours)\n\nTimestep: 1500000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 451\nexploration: 0.08875\nlearning_rate: 0.00009\nelapsed time: 6166.4 seconds (1.71 hours)\n\nTimestep: 1510000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 454\nexploration: 0.08853\nlearning_rate: 0.00009\nelapsed time: 6211.8 seconds (1.73 hours)\n\nTimestep: 1520000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 457\nexploration: 0.08830\nlearning_rate: 0.00009\nelapsed time: 6257.2 seconds (1.74 hours)\n\nTimestep: 1530000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 460\nexploration: 0.08808\nlearning_rate: 0.00009\nelapsed time: 6303.0 seconds (1.75 hours)\n\nTimestep: 1540000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 463\nexploration: 0.08785\nlearning_rate: 0.00009\nelapsed time: 6347.7 seconds (1.76 hours)\n\nTimestep: 1550000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 466\nexploration: 0.08763\nlearning_rate: 0.00009\nelapsed time: 6392.6 seconds (1.78 hours)\n\nTimestep: 1560000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 469\nexploration: 0.08740\nlearning_rate: 0.00009\nelapsed time: 6437.4 seconds (1.79 hours)\n\nTimestep: 1570000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 472\nexploration: 0.08718\nlearning_rate: 0.00009\nelapsed time: 6482.8 seconds (1.80 hours)\n\nTimestep: 1580000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 475\nexploration: 0.08695\nlearning_rate: 0.00009\nelapsed time: 6527.8 seconds (1.81 hours)\n\nTimestep: 1590000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 478\nexploration: 0.08673\nlearning_rate: 0.00009\nelapsed time: 6573.7 seconds (1.83 hours)\n\nTimestep: 1600000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 481\nexploration: 0.08650\nlearning_rate: 0.00009\nelapsed time: 6620.2 seconds (1.84 hours)\n\nTimestep: 1610000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 484\nexploration: 0.08628\nlearning_rate: 0.00009\nelapsed time: 6665.1 seconds (1.85 hours)\n\nTimestep: 1620000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 487\nexploration: 0.08605\nlearning_rate: 0.00009\nelapsed time: 6710.7 seconds (1.86 hours)\n\nTimestep: 1630000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 490\nexploration: 0.08582\nlearning_rate: 0.00009\nelapsed time: 6756.4 seconds (1.88 hours)\n\nTimestep: 1640000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 493\nexploration: 0.08560\nlearning_rate: 0.00009\nelapsed time: 6802.0 seconds (1.89 hours)\n\nTimestep: 1650000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 496\nexploration: 0.08538\nlearning_rate: 0.00009\nelapsed time: 6847.8 seconds (1.90 hours)\n\nTimestep: 1660000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 499\nexploration: 0.08515\nlearning_rate: 0.00009\nelapsed time: 6893.2 seconds (1.91 hours)\n\nTimestep: 1670000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 502\nexploration: 0.08493\nlearning_rate: 0.00009\nelapsed time: 6939.2 seconds (1.93 hours)\n\nTimestep: 1680000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 505\nexploration: 0.08470\nlearning_rate: 0.00009\nelapsed time: 6984.4 seconds (1.94 hours)\n\nTimestep: 1690000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 508\nexploration: 0.08448\nlearning_rate: 0.00009\nelapsed time: 7030.1 seconds (1.95 hours)\n\nTimestep: 1700000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 511\nexploration: 0.08425\nlearning_rate: 0.00009\nelapsed time: 7076.7 seconds (1.97 hours)\n\nTimestep: 1710000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 514\nexploration: 0.08403\nlearning_rate: 0.00009\nelapsed time: 7123.0 seconds (1.98 hours)\n\nTimestep: 1720000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 517\nexploration: 0.08380\nlearning_rate: 0.00009\nelapsed time: 7168.3 seconds (1.99 hours)\n\nTimestep: 1730000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 520\nexploration: 0.08358\nlearning_rate: 0.00009\nelapsed time: 7214.2 seconds (2.00 hours)\n\nTimestep: 1740000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 523\nexploration: 0.08335\nlearning_rate: 0.00009\nelapsed time: 7260.3 seconds (2.02 hours)\n\nTimestep: 1750000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 526\nexploration: 0.08313\nlearning_rate: 0.00009\nelapsed time: 7305.7 seconds (2.03 hours)\n\nTimestep: 1760000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 529\nexploration: 0.08290\nlearning_rate: 0.00009\nelapsed time: 7351.8 seconds (2.04 hours)\n\nTimestep: 1770000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 532\nexploration: 0.08267\nlearning_rate: 0.00009\nelapsed time: 7397.7 seconds (2.05 hours)\n\nTimestep: 1780000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 535\nexploration: 0.08245\nlearning_rate: 0.00009\nelapsed time: 7444.2 seconds (2.07 hours)\n\nTimestep: 1790000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 538\nexploration: 0.08223\nlearning_rate: 0.00009\nelapsed time: 7490.4 seconds (2.08 hours)\n\nTimestep: 1800000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 541\nexploration: 0.08200\nlearning_rate: 0.00009\nelapsed time: 7536.2 seconds (2.09 hours)\n\nTimestep: 1810000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 544\nexploration: 0.08178\nlearning_rate: 0.00009\nelapsed time: 7580.8 seconds (2.11 hours)\n\nTimestep: 1820000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 547\nexploration: 0.08155\nlearning_rate: 0.00009\nelapsed time: 7626.7 seconds (2.12 hours)\n\nTimestep: 1830000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 550\nexploration: 0.08133\nlearning_rate: 0.00009\nelapsed time: 7672.4 seconds (2.13 hours)\n\nTimestep: 1840000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 553\nexploration: 0.08110\nlearning_rate: 0.00009\nelapsed time: 7717.8 seconds (2.14 hours)\n\nTimestep: 1850000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 556\nexploration: 0.08088\nlearning_rate: 0.00009\nelapsed time: 7764.1 seconds (2.16 hours)\n\nTimestep: 1860000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 559\nexploration: 0.08065\nlearning_rate: 0.00009\nelapsed time: 7810.0 seconds (2.17 hours)\n\nTimestep: 1870000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 562\nexploration: 0.08042\nlearning_rate: 0.00009\nelapsed time: 7855.5 seconds (2.18 hours)\n\nTimestep: 1880000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 565\nexploration: 0.08020\nlearning_rate: 0.00009\nelapsed time: 7901.2 seconds (2.19 hours)\n\nTimestep: 1890000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 568\nexploration: 0.07998\nlearning_rate: 0.00009\nelapsed time: 7946.8 seconds (2.21 hours)\n\nTimestep: 1900000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 571\nexploration: 0.07975\nlearning_rate: 0.00009\nelapsed time: 7992.7 seconds (2.22 hours)\n\nTimestep: 1910000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 574\nexploration: 0.07952\nlearning_rate: 0.00009\nelapsed time: 8038.0 seconds (2.23 hours)\n\nTimestep: 1920000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 577\nexploration: 0.07930\nlearning_rate: 0.00009\nelapsed time: 8083.6 seconds (2.25 hours)\n\nTimestep: 1930000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 580\nexploration: 0.07908\nlearning_rate: 0.00009\nelapsed time: 8128.7 seconds (2.26 hours)\n\nTimestep: 1940000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 583\nexploration: 0.07885\nlearning_rate: 0.00009\nelapsed time: 8173.6 seconds (2.27 hours)\n\nTimestep: 1950000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 586\nexploration: 0.07863\nlearning_rate: 0.00009\nelapsed time: 8218.7 seconds (2.28 hours)\n\nTimestep: 1960000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 589\nexploration: 0.07840\nlearning_rate: 0.00009\nelapsed time: 8263.9 seconds (2.30 hours)\n\nTimestep: 1970000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 592\nexploration: 0.07818\nlearning_rate: 0.00009\nelapsed time: 8309.7 seconds (2.31 hours)\n\nTimestep: 1980000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 595\nexploration: 0.07795\nlearning_rate: 0.00009\nelapsed time: 8355.1 seconds (2.32 hours)\n\nTimestep: 1990000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 598\nexploration: 0.07773\nlearning_rate: 0.00009\nelapsed time: 8401.3 seconds (2.33 hours)\n\nTimestep: 2000000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0600\ncurrent episode reward: 0.0000\nepisodes: 601\nexploration: 0.07750\nlearning_rate: 0.00009\nelapsed time: 8446.5 seconds (2.35 hours)\n\nTimestep: 2010000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.0700\ncurrent episode reward: 2.0000\nepisodes: 604\nexploration: 0.07728\nlearning_rate: 0.00009\nelapsed time: 8491.9 seconds (2.36 hours)\n\nTimestep: 2020000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.0700\ncurrent episode reward: 0.0000\nepisodes: 607\nexploration: 0.07705\nlearning_rate: 0.00009\nelapsed time: 8537.8 seconds (2.37 hours)\n\nTimestep: 2030000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.0800\ncurrent episode reward: 1.0000\nepisodes: 610\nexploration: 0.07683\nlearning_rate: 0.00009\nelapsed time: 8584.0 seconds (2.38 hours)\n\nTimestep: 2040000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.0800\ncurrent episode reward: 0.0000\nepisodes: 614\nexploration: 0.07660\nlearning_rate: 0.00009\nelapsed time: 8630.1 seconds (2.40 hours)\n\nTimestep: 2050000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.0900\ncurrent episode reward: 1.0000\nepisodes: 617\nexploration: 0.07637\nlearning_rate: 0.00009\nelapsed time: 8675.8 seconds (2.41 hours)\n\nTimestep: 2060000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 620\nexploration: 0.07615\nlearning_rate: 0.00009\nelapsed time: 8720.9 seconds (2.42 hours)\n\nTimestep: 2070000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 623\nexploration: 0.07593\nlearning_rate: 0.00009\nelapsed time: 8766.4 seconds (2.44 hours)\n\nTimestep: 2080000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 626\nexploration: 0.07570\nlearning_rate: 0.00009\nelapsed time: 8812.4 seconds (2.45 hours)\n\nTimestep: 2090000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 629\nexploration: 0.07548\nlearning_rate: 0.00009\nelapsed time: 8858.3 seconds (2.46 hours)\n\nTimestep: 2100000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 632\nexploration: 0.07525\nlearning_rate: 0.00009\nelapsed time: 8903.9 seconds (2.47 hours)\n\nTimestep: 2110000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 635\nexploration: 0.07503\nlearning_rate: 0.00009\nelapsed time: 8949.8 seconds (2.49 hours)\n\nTimestep: 2120000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 638\nexploration: 0.07480\nlearning_rate: 0.00009\nelapsed time: 8996.2 seconds (2.50 hours)\n\nTimestep: 2130000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 641\nexploration: 0.07458\nlearning_rate: 0.00009\nelapsed time: 9042.0 seconds (2.51 hours)\n\nTimestep: 2140000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 644\nexploration: 0.07435\nlearning_rate: 0.00009\nelapsed time: 9088.3 seconds (2.52 hours)\n\nTimestep: 2150000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.0900\ncurrent episode reward: 1.0000\nepisodes: 647\nexploration: 0.07412\nlearning_rate: 0.00009\nelapsed time: 9133.9 seconds (2.54 hours)\n\nTimestep: 2160000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 650\nexploration: 0.07390\nlearning_rate: 0.00009\nelapsed time: 9179.9 seconds (2.55 hours)\n\nTimestep: 2170000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 653\nexploration: 0.07368\nlearning_rate: 0.00009\nelapsed time: 9225.9 seconds (2.56 hours)\n\nTimestep: 2180000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 656\nexploration: 0.07345\nlearning_rate: 0.00009\nelapsed time: 9271.7 seconds (2.58 hours)\n\nTimestep: 2190000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 659\nexploration: 0.07322\nlearning_rate: 0.00009\nelapsed time: 9317.0 seconds (2.59 hours)\n\nTimestep: 2200000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 662\nexploration: 0.07300\nlearning_rate: 0.00009\nelapsed time: 9363.2 seconds (2.60 hours)\n\nTimestep: 2210000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 665\nexploration: 0.07278\nlearning_rate: 0.00008\nelapsed time: 9408.1 seconds (2.61 hours)\n\nTimestep: 2220000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 668\nexploration: 0.07255\nlearning_rate: 0.00008\nelapsed time: 9453.2 seconds (2.63 hours)\n\nTimestep: 2230000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 671\nexploration: 0.07233\nlearning_rate: 0.00008\nelapsed time: 9498.2 seconds (2.64 hours)\n\nTimestep: 2240000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 674\nexploration: 0.07210\nlearning_rate: 0.00008\nelapsed time: 9543.3 seconds (2.65 hours)\n\nTimestep: 2250000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 677\nexploration: 0.07187\nlearning_rate: 0.00008\nelapsed time: 9589.0 seconds (2.66 hours)\n\nTimestep: 2260000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.0900\ncurrent episode reward: 0.0000\nepisodes: 680\nexploration: 0.07165\nlearning_rate: 0.00008\nelapsed time: 9635.3 seconds (2.68 hours)\n\nTimestep: 2270000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 683\nexploration: 0.07143\nlearning_rate: 0.00008\nelapsed time: 9681.5 seconds (2.69 hours)\n\nTimestep: 2280000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 686\nexploration: 0.07120\nlearning_rate: 0.00008\nelapsed time: 9727.8 seconds (2.70 hours)\n\nTimestep: 2290000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 689\nexploration: 0.07097\nlearning_rate: 0.00008\nelapsed time: 9773.5 seconds (2.71 hours)\n\nTimestep: 2300000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 692\nexploration: 0.07075\nlearning_rate: 0.00008\nelapsed time: 9819.2 seconds (2.73 hours)\n\nTimestep: 2310000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 695\nexploration: 0.07053\nlearning_rate: 0.00008\nelapsed time: 9864.4 seconds (2.74 hours)\n\nTimestep: 2320000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 698\nexploration: 0.07030\nlearning_rate: 0.00008\nelapsed time: 9910.5 seconds (2.75 hours)\n\nTimestep: 2330000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.1000\ncurrent episode reward: 1.0000\nepisodes: 701\nexploration: 0.07007\nlearning_rate: 0.00008\nelapsed time: 9956.1 seconds (2.77 hours)\n\nTimestep: 2340000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 704\nexploration: 0.06985\nlearning_rate: 0.00008\nelapsed time: 10002.5 seconds (2.78 hours)\n\nTimestep: 2350000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 707\nexploration: 0.06962\nlearning_rate: 0.00008\nelapsed time: 10048.1 seconds (2.79 hours)\n\nTimestep: 2360000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 710\nexploration: 0.06940\nlearning_rate: 0.00008\nelapsed time: 10093.0 seconds (2.80 hours)\n\nTimestep: 2370000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 713\nexploration: 0.06918\nlearning_rate: 0.00008\nelapsed time: 10138.7 seconds (2.82 hours)\n\nTimestep: 2380000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 716\nexploration: 0.06895\nlearning_rate: 0.00008\nelapsed time: 10184.7 seconds (2.83 hours)\n\nTimestep: 2390000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 719\nexploration: 0.06873\nlearning_rate: 0.00008\nelapsed time: 10230.7 seconds (2.84 hours)\n\nTimestep: 2400000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 722\nexploration: 0.06850\nlearning_rate: 0.00008\nelapsed time: 10277.0 seconds (2.85 hours)\n\nTimestep: 2410000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 725\nexploration: 0.06828\nlearning_rate: 0.00008\nelapsed time: 10323.3 seconds (2.87 hours)\n\nTimestep: 2420000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 728\nexploration: 0.06805\nlearning_rate: 0.00008\nelapsed time: 10368.8 seconds (2.88 hours)\n\nTimestep: 2430000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 731\nexploration: 0.06782\nlearning_rate: 0.00008\nelapsed time: 10415.1 seconds (2.89 hours)\n\nTimestep: 2440000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 734\nexploration: 0.06760\nlearning_rate: 0.00008\nelapsed time: 10461.0 seconds (2.91 hours)\n\nTimestep: 2450000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 737\nexploration: 0.06738\nlearning_rate: 0.00008\nelapsed time: 10507.1 seconds (2.92 hours)\n\nTimestep: 2460000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 740\nexploration: 0.06715\nlearning_rate: 0.00008\nelapsed time: 10553.4 seconds (2.93 hours)\n\nTimestep: 2470000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 743\nexploration: 0.06693\nlearning_rate: 0.00008\nelapsed time: 10599.4 seconds (2.94 hours)\n\nTimestep: 2480000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 746\nexploration: 0.06670\nlearning_rate: 0.00008\nelapsed time: 10645.0 seconds (2.96 hours)\n\nTimestep: 2490000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.1000\ncurrent episode reward: 1.0000\nepisodes: 749\nexploration: 0.06648\nlearning_rate: 0.00008\nelapsed time: 10690.5 seconds (2.97 hours)\n\nTimestep: 2500000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 752\nexploration: 0.06625\nlearning_rate: 0.00008\nelapsed time: 10736.4 seconds (2.98 hours)\n\nTimestep: 2510000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 755\nexploration: 0.06603\nlearning_rate: 0.00008\nelapsed time: 10782.5 seconds (3.00 hours)\n\nTimestep: 2520000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 758\nexploration: 0.06580\nlearning_rate: 0.00008\nelapsed time: 10828.7 seconds (3.01 hours)\n\nTimestep: 2530000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 761\nexploration: 0.06557\nlearning_rate: 0.00008\nelapsed time: 10874.1 seconds (3.02 hours)\n\nTimestep: 2540000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 764\nexploration: 0.06535\nlearning_rate: 0.00008\nelapsed time: 10919.5 seconds (3.03 hours)\n\nTimestep: 2550000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 767\nexploration: 0.06513\nlearning_rate: 0.00008\nelapsed time: 10964.2 seconds (3.05 hours)\n\nTimestep: 2560000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 770\nexploration: 0.06490\nlearning_rate: 0.00008\nelapsed time: 11009.9 seconds (3.06 hours)\n\nTimestep: 2570000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 773\nexploration: 0.06468\nlearning_rate: 0.00008\nelapsed time: 11056.9 seconds (3.07 hours)\n\nTimestep: 2580000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 776\nexploration: 0.06445\nlearning_rate: 0.00008\nelapsed time: 11102.9 seconds (3.08 hours)\n\nTimestep: 2590000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 779\nexploration: 0.06423\nlearning_rate: 0.00008\nelapsed time: 11149.3 seconds (3.10 hours)\n\nTimestep: 2600000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 782\nexploration: 0.06400\nlearning_rate: 0.00008\nelapsed time: 11194.5 seconds (3.11 hours)\n\nTimestep: 2610000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 785\nexploration: 0.06377\nlearning_rate: 0.00008\nelapsed time: 11240.4 seconds (3.12 hours)\n\nTimestep: 2620000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 788\nexploration: 0.06355\nlearning_rate: 0.00008\nelapsed time: 11287.0 seconds (3.14 hours)\n\nTimestep: 2630000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 791\nexploration: 0.06333\nlearning_rate: 0.00008\nelapsed time: 11332.5 seconds (3.15 hours)\n\nTimestep: 2640000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 794\nexploration: 0.06310\nlearning_rate: 0.00008\nelapsed time: 11379.0 seconds (3.16 hours)\n\nTimestep: 2650000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.1000\ncurrent episode reward: 2.0000\nepisodes: 797\nexploration: 0.06288\nlearning_rate: 0.00008\nelapsed time: 11425.1 seconds (3.17 hours)\n\nTimestep: 2660000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 800\nexploration: 0.06265\nlearning_rate: 0.00008\nelapsed time: 11471.0 seconds (3.19 hours)\n\nTimestep: 2670000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.1000\ncurrent episode reward: 1.0000\nepisodes: 803\nexploration: 0.06243\nlearning_rate: 0.00008\nelapsed time: 11517.7 seconds (3.20 hours)\n\nTimestep: 2680000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 806\nexploration: 0.06220\nlearning_rate: 0.00008\nelapsed time: 11563.6 seconds (3.21 hours)\n\nTimestep: 2690000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 809\nexploration: 0.06198\nlearning_rate: 0.00008\nelapsed time: 11609.5 seconds (3.22 hours)\n\nTimestep: 2700000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 812\nexploration: 0.06175\nlearning_rate: 0.00008\nelapsed time: 11655.2 seconds (3.24 hours)\n\nTimestep: 2710000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 815\nexploration: 0.06153\nlearning_rate: 0.00008\nelapsed time: 11701.0 seconds (3.25 hours)\n\nTimestep: 2720000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 818\nexploration: 0.06130\nlearning_rate: 0.00008\nelapsed time: 11747.1 seconds (3.26 hours)\n\nTimestep: 2730000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 821\nexploration: 0.06108\nlearning_rate: 0.00008\nelapsed time: 11793.2 seconds (3.28 hours)\n\nTimestep: 2740000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 824\nexploration: 0.06085\nlearning_rate: 0.00008\nelapsed time: 11839.6 seconds (3.29 hours)\n\nTimestep: 2750000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 827\nexploration: 0.06062\nlearning_rate: 0.00008\nelapsed time: 11885.3 seconds (3.30 hours)\n\nTimestep: 2760000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 830\nexploration: 0.06040\nlearning_rate: 0.00008\nelapsed time: 11931.1 seconds (3.31 hours)\n\nTimestep: 2770000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 833\nexploration: 0.06017\nlearning_rate: 0.00008\nelapsed time: 11977.8 seconds (3.33 hours)\n\nTimestep: 2780000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 836\nexploration: 0.05995\nlearning_rate: 0.00008\nelapsed time: 12024.2 seconds (3.34 hours)\n\nTimestep: 2790000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 839\nexploration: 0.05973\nlearning_rate: 0.00008\nelapsed time: 12069.9 seconds (3.35 hours)\n\nTimestep: 2800000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 842\nexploration: 0.05950\nlearning_rate: 0.00008\nelapsed time: 12116.0 seconds (3.37 hours)\n\nTimestep: 2810000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 845\nexploration: 0.05928\nlearning_rate: 0.00008\nelapsed time: 12162.3 seconds (3.38 hours)\n\nTimestep: 2820000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.1000\ncurrent episode reward: 3.0000\nepisodes: 848\nexploration: 0.05905\nlearning_rate: 0.00008\nelapsed time: 12208.5 seconds (3.39 hours)\n\nTimestep: 2830000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 851\nexploration: 0.05883\nlearning_rate: 0.00008\nelapsed time: 12254.1 seconds (3.40 hours)\n\nTimestep: 2840000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 854\nexploration: 0.05860\nlearning_rate: 0.00008\nelapsed time: 12299.7 seconds (3.42 hours)\n\nTimestep: 2850000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 857\nexploration: 0.05837\nlearning_rate: 0.00008\nelapsed time: 12345.2 seconds (3.43 hours)\n\nTimestep: 2860000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 860\nexploration: 0.05815\nlearning_rate: 0.00008\nelapsed time: 12391.3 seconds (3.44 hours)\n\nTimestep: 2870000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 863\nexploration: 0.05792\nlearning_rate: 0.00008\nelapsed time: 12437.0 seconds (3.45 hours)\n\nTimestep: 2880000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 866\nexploration: 0.05770\nlearning_rate: 0.00008\nelapsed time: 12483.5 seconds (3.47 hours)\n\nTimestep: 2890000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 869\nexploration: 0.05748\nlearning_rate: 0.00008\nelapsed time: 12529.1 seconds (3.48 hours)\n\nTimestep: 2900000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 872\nexploration: 0.05725\nlearning_rate: 0.00008\nelapsed time: 12574.8 seconds (3.49 hours)\n\nTimestep: 2910000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 875\nexploration: 0.05702\nlearning_rate: 0.00008\nelapsed time: 12621.8 seconds (3.51 hours)\n\nTimestep: 2920000\nmean reward (100 episodes): 0.1200\nbest mean reward: 0.1200\ncurrent episode reward: 0.0000\nepisodes: 878\nexploration: 0.05680\nlearning_rate: 0.00008\nelapsed time: 12668.2 seconds (3.52 hours)\n\nTimestep: 2930000\nmean reward (100 episodes): 0.1200\nbest mean reward: 0.1200\ncurrent episode reward: 0.0000\nepisodes: 881\nexploration: 0.05658\nlearning_rate: 0.00008\nelapsed time: 12714.2 seconds (3.53 hours)\n\nTimestep: 2940000\nmean reward (100 episodes): 0.1300\nbest mean reward: 0.1300\ncurrent episode reward: 1.0000\nepisodes: 884\nexploration: 0.05635\nlearning_rate: 0.00008\nelapsed time: 12759.6 seconds (3.54 hours)\n\nTimestep: 2950000\nmean reward (100 episodes): 0.1300\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 887\nexploration: 0.05613\nlearning_rate: 0.00008\nelapsed time: 12806.5 seconds (3.56 hours)\n\nTimestep: 2960000\nmean reward (100 episodes): 0.1300\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 890\nexploration: 0.05590\nlearning_rate: 0.00008\nelapsed time: 12852.5 seconds (3.57 hours)\n\nTimestep: 2970000\nmean reward (100 episodes): 0.1300\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 893\nexploration: 0.05568\nlearning_rate: 0.00008\nelapsed time: 12898.6 seconds (3.58 hours)\n\nTimestep: 2980000\nmean reward (100 episodes): 0.1300\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 896\nexploration: 0.05545\nlearning_rate: 0.00008\nelapsed time: 12944.1 seconds (3.60 hours)\n\nTimestep: 2990000\nmean reward (100 episodes): 0.1300\nbest mean reward: 0.1300\ncurrent episode reward: 1.0000\nepisodes: 899\nexploration: 0.05523\nlearning_rate: 0.00008\nelapsed time: 12989.8 seconds (3.61 hours)\n\nTimestep: 3000000\nmean reward (100 episodes): 0.1200\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 902\nexploration: 0.05500\nlearning_rate: 0.00008\nelapsed time: 13035.6 seconds (3.62 hours)\n\nTimestep: 3010000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 905\nexploration: 0.05478\nlearning_rate: 0.00007\nelapsed time: 13081.5 seconds (3.63 hours)\n\nTimestep: 3020000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 908\nexploration: 0.05455\nlearning_rate: 0.00007\nelapsed time: 13127.1 seconds (3.65 hours)\n\nTimestep: 3030000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 911\nexploration: 0.05433\nlearning_rate: 0.00007\nelapsed time: 13173.7 seconds (3.66 hours)\n\nTimestep: 3040000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 914\nexploration: 0.05410\nlearning_rate: 0.00007\nelapsed time: 13220.8 seconds (3.67 hours)\n\nTimestep: 3050000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 917\nexploration: 0.05388\nlearning_rate: 0.00007\nelapsed time: 13266.8 seconds (3.69 hours)\n\nTimestep: 3060000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 920\nexploration: 0.05365\nlearning_rate: 0.00007\nelapsed time: 13313.4 seconds (3.70 hours)\n\nTimestep: 3070000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 924\nexploration: 0.05343\nlearning_rate: 0.00007\nelapsed time: 13358.3 seconds (3.71 hours)\n\nTimestep: 3080000\nmean reward (100 episodes): 0.1200\nbest mean reward: 0.1300\ncurrent episode reward: 1.0000\nepisodes: 927\nexploration: 0.05320\nlearning_rate: 0.00007\nelapsed time: 13404.7 seconds (3.72 hours)\n\nTimestep: 3090000\nmean reward (100 episodes): 0.1200\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 930\nexploration: 0.05298\nlearning_rate: 0.00007\nelapsed time: 13450.3 seconds (3.74 hours)\n\nTimestep: 3100000\nmean reward (100 episodes): 0.1200\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 933\nexploration: 0.05275\nlearning_rate: 0.00007\nelapsed time: 13495.6 seconds (3.75 hours)\n\nTimestep: 3110000\nmean reward (100 episodes): 0.1200\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 936\nexploration: 0.05253\nlearning_rate: 0.00007\nelapsed time: 13541.4 seconds (3.76 hours)\n\nTimestep: 3120000\nmean reward (100 episodes): 0.1200\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 939\nexploration: 0.05230\nlearning_rate: 0.00007\nelapsed time: 13586.8 seconds (3.77 hours)\n\nTimestep: 3130000\nmean reward (100 episodes): 0.1200\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 942\nexploration: 0.05208\nlearning_rate: 0.00007\nelapsed time: 13632.5 seconds (3.79 hours)\n\nTimestep: 3140000\nmean reward (100 episodes): 0.1200\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 945\nexploration: 0.05185\nlearning_rate: 0.00007\nelapsed time: 13679.3 seconds (3.80 hours)\n\nTimestep: 3150000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 948\nexploration: 0.05163\nlearning_rate: 0.00007\nelapsed time: 13725.4 seconds (3.81 hours)\n\nTimestep: 3160000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.1300\ncurrent episode reward: 1.0000\nepisodes: 951\nexploration: 0.05140\nlearning_rate: 0.00007\nelapsed time: 13771.8 seconds (3.83 hours)\n\nTimestep: 3170000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 954\nexploration: 0.05117\nlearning_rate: 0.00007\nelapsed time: 13818.4 seconds (3.84 hours)\n\nTimestep: 3180000\nmean reward (100 episodes): 0.1200\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 957\nexploration: 0.05095\nlearning_rate: 0.00007\nelapsed time: 13864.7 seconds (3.85 hours)\n\nTimestep: 3190000\nmean reward (100 episodes): 0.1200\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 960\nexploration: 0.05072\nlearning_rate: 0.00007\nelapsed time: 13910.8 seconds (3.86 hours)\n\nTimestep: 3200000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 963\nexploration: 0.05050\nlearning_rate: 0.00007\nelapsed time: 13956.6 seconds (3.88 hours)\n\nTimestep: 3210000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 966\nexploration: 0.05028\nlearning_rate: 0.00007\nelapsed time: 14002.1 seconds (3.89 hours)\n\nTimestep: 3220000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 969\nexploration: 0.05005\nlearning_rate: 0.00007\nelapsed time: 14047.8 seconds (3.90 hours)\n\nTimestep: 3230000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 972\nexploration: 0.04983\nlearning_rate: 0.00007\nelapsed time: 14093.2 seconds (3.91 hours)\n\nTimestep: 3240000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 975\nexploration: 0.04960\nlearning_rate: 0.00007\nelapsed time: 14138.6 seconds (3.93 hours)\n\nTimestep: 3250000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 978\nexploration: 0.04938\nlearning_rate: 0.00007\nelapsed time: 14185.3 seconds (3.94 hours)\n\nTimestep: 3260000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 981\nexploration: 0.04915\nlearning_rate: 0.00007\nelapsed time: 14231.1 seconds (3.95 hours)\n\nTimestep: 3270000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 984\nexploration: 0.04892\nlearning_rate: 0.00007\nelapsed time: 14277.9 seconds (3.97 hours)\n\nTimestep: 3280000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 987\nexploration: 0.04870\nlearning_rate: 0.00007\nelapsed time: 14323.7 seconds (3.98 hours)\n\nTimestep: 3290000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 990\nexploration: 0.04847\nlearning_rate: 0.00007\nelapsed time: 14369.5 seconds (3.99 hours)\n\nTimestep: 3300000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 993\nexploration: 0.04825\nlearning_rate: 0.00007\nelapsed time: 14415.2 seconds (4.00 hours)\n\nTimestep: 3310000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 996\nexploration: 0.04802\nlearning_rate: 0.00007\nelapsed time: 14460.7 seconds (4.02 hours)\n\nTimestep: 3320000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 999\nexploration: 0.04780\nlearning_rate: 0.00007\nelapsed time: 14506.4 seconds (4.03 hours)\n\nTimestep: 3330000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 1002\nexploration: 0.04757\nlearning_rate: 0.00007\nelapsed time: 14553.2 seconds (4.04 hours)\n\nTimestep: 3340000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 1005\nexploration: 0.04735\nlearning_rate: 0.00007\nelapsed time: 14599.9 seconds (4.06 hours)\n\nTimestep: 3350000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 1008\nexploration: 0.04713\nlearning_rate: 0.00007\nelapsed time: 14646.2 seconds (4.07 hours)\n\nTimestep: 3360000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 1011\nexploration: 0.04690\nlearning_rate: 0.00007\nelapsed time: 14692.6 seconds (4.08 hours)\n\nTimestep: 3370000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 1014\nexploration: 0.04667\nlearning_rate: 0.00007\nelapsed time: 14738.7 seconds (4.09 hours)\n\nTimestep: 3380000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.1300\ncurrent episode reward: 1.0000\nepisodes: 1017\nexploration: 0.04645\nlearning_rate: 0.00007\nelapsed time: 14785.6 seconds (4.11 hours)\n\nTimestep: 3390000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 1020\nexploration: 0.04622\nlearning_rate: 0.00007\nelapsed time: 14831.4 seconds (4.12 hours)\n\nTimestep: 3400000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 1023\nexploration: 0.04600\nlearning_rate: 0.00007\nelapsed time: 14877.3 seconds (4.13 hours)\n\nTimestep: 3410000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 1026\nexploration: 0.04577\nlearning_rate: 0.00007\nelapsed time: 14923.3 seconds (4.15 hours)\n\nTimestep: 3420000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 1029\nexploration: 0.04555\nlearning_rate: 0.00007\nelapsed time: 14969.4 seconds (4.16 hours)\n\nTimestep: 3430000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 1032\nexploration: 0.04532\nlearning_rate: 0.00007\nelapsed time: 15015.9 seconds (4.17 hours)\n\nTimestep: 3440000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.1300\ncurrent episode reward: 1.0000\nepisodes: 1035\nexploration: 0.04510\nlearning_rate: 0.00007\nelapsed time: 15063.2 seconds (4.18 hours)\n\nTimestep: 3450000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 1038\nexploration: 0.04487\nlearning_rate: 0.00007\nelapsed time: 15109.1 seconds (4.20 hours)\n\nTimestep: 3460000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 1041\nexploration: 0.04465\nlearning_rate: 0.00007\nelapsed time: 15155.3 seconds (4.21 hours)\n\nTimestep: 3470000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 1044\nexploration: 0.04442\nlearning_rate: 0.00007\nelapsed time: 15201.6 seconds (4.22 hours)\n\nTimestep: 3480000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1300\ncurrent episode reward: 0.0000\nepisodes: 1047\nexploration: 0.04420\nlearning_rate: 0.00007\nelapsed time: 15247.6 seconds (4.24 hours)\n\nTimestep: 3490000\nmean reward (100 episodes): 0.1400\nbest mean reward: 0.1400\ncurrent episode reward: 0.0000\nepisodes: 1050\nexploration: 0.04397\nlearning_rate: 0.00007\nelapsed time: 15293.8 seconds (4.25 hours)\n\nTimestep: 3500000\nmean reward (100 episodes): 0.1300\nbest mean reward: 0.1400\ncurrent episode reward: 0.0000\nepisodes: 1053\nexploration: 0.04375\nlearning_rate: 0.00007\nelapsed time: 15340.6 seconds (4.26 hours)\n\nTimestep: 3510000\nmean reward (100 episodes): 0.1200\nbest mean reward: 0.1400\ncurrent episode reward: 0.0000\nepisodes: 1056\nexploration: 0.04353\nlearning_rate: 0.00007\nelapsed time: 15386.7 seconds (4.27 hours)\n\nTimestep: 3520000\nmean reward (100 episodes): 0.1200\nbest mean reward: 0.1400\ncurrent episode reward: 0.0000\nepisodes: 1059\nexploration: 0.04330\nlearning_rate: 0.00007\nelapsed time: 15432.6 seconds (4.29 hours)\n\nTimestep: 3530000\nmean reward (100 episodes): 0.1600\nbest mean reward: 0.1600\ncurrent episode reward: 0.0000\nepisodes: 1062\nexploration: 0.04308\nlearning_rate: 0.00007\nelapsed time: 15478.5 seconds (4.30 hours)\n\nTimestep: 3540000\nmean reward (100 episodes): 0.1600\nbest mean reward: 0.1600\ncurrent episode reward: 0.0000\nepisodes: 1065\nexploration: 0.04285\nlearning_rate: 0.00007\nelapsed time: 15525.3 seconds (4.31 hours)\n\nTimestep: 3550000\nmean reward (100 episodes): 0.1600\nbest mean reward: 0.1600\ncurrent episode reward: 0.0000\nepisodes: 1068\nexploration: 0.04263\nlearning_rate: 0.00007\nelapsed time: 15571.7 seconds (4.33 hours)\n\nTimestep: 3560000\nmean reward (100 episodes): 0.1600\nbest mean reward: 0.1600\ncurrent episode reward: 0.0000\nepisodes: 1071\nexploration: 0.04240\nlearning_rate: 0.00007\nelapsed time: 15618.4 seconds (4.34 hours)\n\nTimestep: 3570000\nmean reward (100 episodes): 0.2000\nbest mean reward: 0.2000\ncurrent episode reward: 2.0000\nepisodes: 1074\nexploration: 0.04218\nlearning_rate: 0.00007\nelapsed time: 15664.5 seconds (4.35 hours)\n\nTimestep: 3580000\nmean reward (100 episodes): 0.2000\nbest mean reward: 0.2000\ncurrent episode reward: 0.0000\nepisodes: 1077\nexploration: 0.04195\nlearning_rate: 0.00007\nelapsed time: 15711.1 seconds (4.36 hours)\n\nTimestep: 3590000\nmean reward (100 episodes): 0.2000\nbest mean reward: 0.2000\ncurrent episode reward: 0.0000\nepisodes: 1080\nexploration: 0.04173\nlearning_rate: 0.00007\nelapsed time: 15757.3 seconds (4.38 hours)\n\nTimestep: 3600000\nmean reward (100 episodes): 0.2000\nbest mean reward: 0.2000\ncurrent episode reward: 0.0000\nepisodes: 1083\nexploration: 0.04150\nlearning_rate: 0.00007\nelapsed time: 15803.1 seconds (4.39 hours)\n\nTimestep: 3610000\nmean reward (100 episodes): 0.2100\nbest mean reward: 0.2100\ncurrent episode reward: 0.0000\nepisodes: 1086\nexploration: 0.04127\nlearning_rate: 0.00007\nelapsed time: 15849.0 seconds (4.40 hours)\n\nTimestep: 3620000\nmean reward (100 episodes): 0.2100\nbest mean reward: 0.2100\ncurrent episode reward: 0.0000\nepisodes: 1089\nexploration: 0.04105\nlearning_rate: 0.00007\nelapsed time: 15895.0 seconds (4.42 hours)\n\nTimestep: 3630000\nmean reward (100 episodes): 0.2100\nbest mean reward: 0.2100\ncurrent episode reward: 0.0000\nepisodes: 1092\nexploration: 0.04083\nlearning_rate: 0.00007\nelapsed time: 15940.5 seconds (4.43 hours)\n\nTimestep: 3640000\nmean reward (100 episodes): 0.2100\nbest mean reward: 0.2100\ncurrent episode reward: 0.0000\nepisodes: 1095\nexploration: 0.04060\nlearning_rate: 0.00007\nelapsed time: 15986.8 seconds (4.44 hours)\n\nTimestep: 3650000\nmean reward (100 episodes): 0.2100\nbest mean reward: 0.2100\ncurrent episode reward: 0.0000\nepisodes: 1098\nexploration: 0.04038\nlearning_rate: 0.00007\nelapsed time: 16032.5 seconds (4.45 hours)\n\nTimestep: 3660000\nmean reward (100 episodes): 0.2100\nbest mean reward: 0.2100\ncurrent episode reward: 0.0000\nepisodes: 1101\nexploration: 0.04015\nlearning_rate: 0.00007\nelapsed time: 16078.6 seconds (4.47 hours)\n\nTimestep: 3670000\nmean reward (100 episodes): 0.2300\nbest mean reward: 0.2300\ncurrent episode reward: 0.0000\nepisodes: 1104\nexploration: 0.03993\nlearning_rate: 0.00007\nelapsed time: 16125.3 seconds (4.48 hours)\n\nTimestep: 3680000\nmean reward (100 episodes): 0.2300\nbest mean reward: 0.2300\ncurrent episode reward: 0.0000\nepisodes: 1107\nexploration: 0.03970\nlearning_rate: 0.00007\nelapsed time: 16171.9 seconds (4.49 hours)\n\nTimestep: 3690000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2400\ncurrent episode reward: 1.0000\nepisodes: 1110\nexploration: 0.03947\nlearning_rate: 0.00007\nelapsed time: 16217.8 seconds (4.50 hours)\n\nTimestep: 3700000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2400\ncurrent episode reward: 0.0000\nepisodes: 1113\nexploration: 0.03925\nlearning_rate: 0.00007\nelapsed time: 16263.9 seconds (4.52 hours)\n\nTimestep: 3710000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2400\ncurrent episode reward: 0.0000\nepisodes: 1116\nexploration: 0.03902\nlearning_rate: 0.00007\nelapsed time: 16309.7 seconds (4.53 hours)\n\nTimestep: 3720000\nmean reward (100 episodes): 0.2300\nbest mean reward: 0.2400\ncurrent episode reward: 0.0000\nepisodes: 1119\nexploration: 0.03880\nlearning_rate: 0.00007\nelapsed time: 16355.8 seconds (4.54 hours)\n\nTimestep: 3730000\nmean reward (100 episodes): 0.2300\nbest mean reward: 0.2400\ncurrent episode reward: 0.0000\nepisodes: 1122\nexploration: 0.03857\nlearning_rate: 0.00007\nelapsed time: 16402.5 seconds (4.56 hours)\n\nTimestep: 3740000\nmean reward (100 episodes): 0.2300\nbest mean reward: 0.2400\ncurrent episode reward: 0.0000\nepisodes: 1125\nexploration: 0.03835\nlearning_rate: 0.00007\nelapsed time: 16448.8 seconds (4.57 hours)\n\nTimestep: 3750000\nmean reward (100 episodes): 0.2600\nbest mean reward: 0.2600\ncurrent episode reward: 3.0000\nepisodes: 1128\nexploration: 0.03812\nlearning_rate: 0.00007\nelapsed time: 16494.9 seconds (4.58 hours)\n\nTimestep: 3760000\nmean reward (100 episodes): 0.2600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1131\nexploration: 0.03790\nlearning_rate: 0.00007\nelapsed time: 16540.1 seconds (4.59 hours)\n\nTimestep: 3770000\nmean reward (100 episodes): 0.2600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1134\nexploration: 0.03768\nlearning_rate: 0.00007\nelapsed time: 16586.6 seconds (4.61 hours)\n\nTimestep: 3780000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1137\nexploration: 0.03745\nlearning_rate: 0.00007\nelapsed time: 16633.7 seconds (4.62 hours)\n\nTimestep: 3790000\nmean reward (100 episodes): 0.2200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1140\nexploration: 0.03722\nlearning_rate: 0.00007\nelapsed time: 16680.4 seconds (4.63 hours)\n\nTimestep: 3800000\nmean reward (100 episodes): 0.1900\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1143\nexploration: 0.03700\nlearning_rate: 0.00007\nelapsed time: 16727.0 seconds (4.65 hours)\n\nTimestep: 3810000\nmean reward (100 episodes): 0.2100\nbest mean reward: 0.2600\ncurrent episode reward: 2.0000\nepisodes: 1146\nexploration: 0.03678\nlearning_rate: 0.00006\nelapsed time: 16773.5 seconds (4.66 hours)\n\nTimestep: 3820000\nmean reward (100 episodes): 0.1800\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1149\nexploration: 0.03655\nlearning_rate: 0.00006\nelapsed time: 16820.3 seconds (4.67 hours)\n\nTimestep: 3830000\nmean reward (100 episodes): 0.2100\nbest mean reward: 0.2600\ncurrent episode reward: 3.0000\nepisodes: 1152\nexploration: 0.03632\nlearning_rate: 0.00006\nelapsed time: 16866.7 seconds (4.69 hours)\n\nTimestep: 3840000\nmean reward (100 episodes): 0.2100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1155\nexploration: 0.03610\nlearning_rate: 0.00006\nelapsed time: 16912.7 seconds (4.70 hours)\n\nTimestep: 3850000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1158\nexploration: 0.03587\nlearning_rate: 0.00006\nelapsed time: 16959.1 seconds (4.71 hours)\n\nTimestep: 3860000\nmean reward (100 episodes): 0.2000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1161\nexploration: 0.03565\nlearning_rate: 0.00006\nelapsed time: 17006.6 seconds (4.72 hours)\n\nTimestep: 3870000\nmean reward (100 episodes): 0.2100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1164\nexploration: 0.03542\nlearning_rate: 0.00006\nelapsed time: 17052.2 seconds (4.74 hours)\n\nTimestep: 3880000\nmean reward (100 episodes): 0.2200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1167\nexploration: 0.03520\nlearning_rate: 0.00006\nelapsed time: 17098.3 seconds (4.75 hours)\n\nTimestep: 3890000\nmean reward (100 episodes): 0.2300\nbest mean reward: 0.2600\ncurrent episode reward: 1.0000\nepisodes: 1170\nexploration: 0.03497\nlearning_rate: 0.00006\nelapsed time: 17144.5 seconds (4.76 hours)\n\nTimestep: 3900000\nmean reward (100 episodes): 0.2200\nbest mean reward: 0.2600\ncurrent episode reward: 1.0000\nepisodes: 1173\nexploration: 0.03475\nlearning_rate: 0.00006\nelapsed time: 17191.0 seconds (4.78 hours)\n\nTimestep: 3910000\nmean reward (100 episodes): 0.2000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1176\nexploration: 0.03453\nlearning_rate: 0.00006\nelapsed time: 17236.5 seconds (4.79 hours)\n\nTimestep: 3920000\nmean reward (100 episodes): 0.2100\nbest mean reward: 0.2600\ncurrent episode reward: 1.0000\nepisodes: 1179\nexploration: 0.03430\nlearning_rate: 0.00006\nelapsed time: 17282.0 seconds (4.80 hours)\n\nTimestep: 3930000\nmean reward (100 episodes): 0.2100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1182\nexploration: 0.03407\nlearning_rate: 0.00006\nelapsed time: 17327.9 seconds (4.81 hours)\n\nTimestep: 3940000\nmean reward (100 episodes): 0.2200\nbest mean reward: 0.2600\ncurrent episode reward: 2.0000\nepisodes: 1185\nexploration: 0.03385\nlearning_rate: 0.00006\nelapsed time: 17374.7 seconds (4.83 hours)\n\nTimestep: 3950000\nmean reward (100 episodes): 0.2300\nbest mean reward: 0.2600\ncurrent episode reward: 1.0000\nepisodes: 1188\nexploration: 0.03362\nlearning_rate: 0.00006\nelapsed time: 17421.1 seconds (4.84 hours)\n\nTimestep: 3960000\nmean reward (100 episodes): 0.2300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1191\nexploration: 0.03340\nlearning_rate: 0.00006\nelapsed time: 17467.4 seconds (4.85 hours)\n\nTimestep: 3970000\nmean reward (100 episodes): 0.2500\nbest mean reward: 0.2600\ncurrent episode reward: 2.0000\nepisodes: 1194\nexploration: 0.03317\nlearning_rate: 0.00006\nelapsed time: 17514.3 seconds (4.87 hours)\n\nTimestep: 3980000\nmean reward (100 episodes): 0.2500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1197\nexploration: 0.03295\nlearning_rate: 0.00006\nelapsed time: 17560.3 seconds (4.88 hours)\n\nTimestep: 3990000\nmean reward (100 episodes): 0.2500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1200\nexploration: 0.03272\nlearning_rate: 0.00006\nelapsed time: 17607.1 seconds (4.89 hours)\n\nTimestep: 4000000\nmean reward (100 episodes): 0.2300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1203\nexploration: 0.03250\nlearning_rate: 0.00006\nelapsed time: 17653.2 seconds (4.90 hours)\n\nTimestep: 4010000\nmean reward (100 episodes): 0.2300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1206\nexploration: 0.03227\nlearning_rate: 0.00006\nelapsed time: 17699.8 seconds (4.92 hours)\n\nTimestep: 4020000\nmean reward (100 episodes): 0.2300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1209\nexploration: 0.03205\nlearning_rate: 0.00006\nelapsed time: 17746.7 seconds (4.93 hours)\n\nTimestep: 4030000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1212\nexploration: 0.03183\nlearning_rate: 0.00006\nelapsed time: 17793.2 seconds (4.94 hours)\n\nTimestep: 4040000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1215\nexploration: 0.03160\nlearning_rate: 0.00006\nelapsed time: 17839.5 seconds (4.96 hours)\n\nTimestep: 4050000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1218\nexploration: 0.03138\nlearning_rate: 0.00006\nelapsed time: 17885.4 seconds (4.97 hours)\n\nTimestep: 4060000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1221\nexploration: 0.03115\nlearning_rate: 0.00006\nelapsed time: 17931.6 seconds (4.98 hours)\n\nTimestep: 4070000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1224\nexploration: 0.03092\nlearning_rate: 0.00006\nelapsed time: 17977.7 seconds (4.99 hours)\n\nTimestep: 4080000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1227\nexploration: 0.03070\nlearning_rate: 0.00006\nelapsed time: 18024.1 seconds (5.01 hours)\n\nTimestep: 4090000\nmean reward (100 episodes): 0.2500\nbest mean reward: 0.2600\ncurrent episode reward: 4.0000\nepisodes: 1230\nexploration: 0.03048\nlearning_rate: 0.00006\nelapsed time: 18070.3 seconds (5.02 hours)\n\nTimestep: 4100000\nmean reward (100 episodes): 0.2700\nbest mean reward: 0.2700\ncurrent episode reward: 0.0000\nepisodes: 1234\nexploration: 0.03025\nlearning_rate: 0.00006\nelapsed time: 18116.8 seconds (5.03 hours)\n\nTimestep: 4110000\nmean reward (100 episodes): 0.2700\nbest mean reward: 0.2700\ncurrent episode reward: 0.0000\nepisodes: 1237\nexploration: 0.03002\nlearning_rate: 0.00006\nelapsed time: 18162.9 seconds (5.05 hours)\n\nTimestep: 4120000\nmean reward (100 episodes): 0.2900\nbest mean reward: 0.2900\ncurrent episode reward: 2.0000\nepisodes: 1240\nexploration: 0.02980\nlearning_rate: 0.00006\nelapsed time: 18210.1 seconds (5.06 hours)\n\nTimestep: 4130000\nmean reward (100 episodes): 0.2900\nbest mean reward: 0.2900\ncurrent episode reward: 0.0000\nepisodes: 1243\nexploration: 0.02958\nlearning_rate: 0.00006\nelapsed time: 18256.3 seconds (5.07 hours)\n\nTimestep: 4140000\nmean reward (100 episodes): 0.2700\nbest mean reward: 0.2900\ncurrent episode reward: 0.0000\nepisodes: 1246\nexploration: 0.02935\nlearning_rate: 0.00006\nelapsed time: 18303.7 seconds (5.08 hours)\n\nTimestep: 4150000\nmean reward (100 episodes): 0.2800\nbest mean reward: 0.2900\ncurrent episode reward: 0.0000\nepisodes: 1249\nexploration: 0.02912\nlearning_rate: 0.00006\nelapsed time: 18349.9 seconds (5.10 hours)\n\nTimestep: 4160000\nmean reward (100 episodes): 0.2500\nbest mean reward: 0.2900\ncurrent episode reward: 0.0000\nepisodes: 1252\nexploration: 0.02890\nlearning_rate: 0.00006\nelapsed time: 18396.2 seconds (5.11 hours)\n\nTimestep: 4170000\nmean reward (100 episodes): 0.2800\nbest mean reward: 0.2900\ncurrent episode reward: 4.0000\nepisodes: 1255\nexploration: 0.02867\nlearning_rate: 0.00006\nelapsed time: 18442.6 seconds (5.12 hours)\n\nTimestep: 4180000\nmean reward (100 episodes): 0.2500\nbest mean reward: 0.2900\ncurrent episode reward: 0.0000\nepisodes: 1258\nexploration: 0.02845\nlearning_rate: 0.00006\nelapsed time: 18488.9 seconds (5.14 hours)\n\nTimestep: 4190000\nmean reward (100 episodes): 0.2500\nbest mean reward: 0.2900\ncurrent episode reward: 0.0000\nepisodes: 1261\nexploration: 0.02823\nlearning_rate: 0.00006\nelapsed time: 18535.9 seconds (5.15 hours)\n\nTimestep: 4200000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2900\ncurrent episode reward: 0.0000\nepisodes: 1264\nexploration: 0.02800\nlearning_rate: 0.00006\nelapsed time: 18582.5 seconds (5.16 hours)\n\nTimestep: 4210000\nmean reward (100 episodes): 0.2300\nbest mean reward: 0.2900\ncurrent episode reward: 0.0000\nepisodes: 1267\nexploration: 0.02777\nlearning_rate: 0.00006\nelapsed time: 18627.9 seconds (5.17 hours)\n\nTimestep: 4220000\nmean reward (100 episodes): 0.2200\nbest mean reward: 0.2900\ncurrent episode reward: 0.0000\nepisodes: 1270\nexploration: 0.02755\nlearning_rate: 0.00006\nelapsed time: 18673.6 seconds (5.19 hours)\n\nTimestep: 4230000\nmean reward (100 episodes): 0.2300\nbest mean reward: 0.2900\ncurrent episode reward: 0.0000\nepisodes: 1273\nexploration: 0.02733\nlearning_rate: 0.00006\nelapsed time: 18719.6 seconds (5.20 hours)\n\nTimestep: 4240000\nmean reward (100 episodes): 0.2700\nbest mean reward: 0.2900\ncurrent episode reward: 4.0000\nepisodes: 1276\nexploration: 0.02710\nlearning_rate: 0.00006\nelapsed time: 18766.0 seconds (5.21 hours)\n\nTimestep: 4250000\nmean reward (100 episodes): 0.2600\nbest mean reward: 0.2900\ncurrent episode reward: 0.0000\nepisodes: 1279\nexploration: 0.02687\nlearning_rate: 0.00006\nelapsed time: 18813.0 seconds (5.23 hours)\n\nTimestep: 4260000\nmean reward (100 episodes): 0.2800\nbest mean reward: 0.2900\ncurrent episode reward: 0.0000\nepisodes: 1282\nexploration: 0.02665\nlearning_rate: 0.00006\nelapsed time: 18859.5 seconds (5.24 hours)\n\nTimestep: 4270000\nmean reward (100 episodes): 0.2600\nbest mean reward: 0.2900\ncurrent episode reward: 0.0000\nepisodes: 1285\nexploration: 0.02642\nlearning_rate: 0.00006\nelapsed time: 18905.7 seconds (5.25 hours)\n\nTimestep: 4280000\nmean reward (100 episodes): 0.3000\nbest mean reward: 0.3000\ncurrent episode reward: 3.0000\nepisodes: 1288\nexploration: 0.02620\nlearning_rate: 0.00006\nelapsed time: 18952.0 seconds (5.26 hours)\n\nTimestep: 4290000\nmean reward (100 episodes): 0.5500\nbest mean reward: 0.5500\ncurrent episode reward: 3.0000\nepisodes: 1291\nexploration: 0.02597\nlearning_rate: 0.00006\nelapsed time: 18997.5 seconds (5.28 hours)\n\nTimestep: 4300000\nmean reward (100 episodes): 0.5300\nbest mean reward: 0.5500\ncurrent episode reward: 0.0000\nepisodes: 1294\nexploration: 0.02575\nlearning_rate: 0.00006\nelapsed time: 19043.5 seconds (5.29 hours)\n\nTimestep: 4310000\nmean reward (100 episodes): 0.5300\nbest mean reward: 0.5500\ncurrent episode reward: 0.0000\nepisodes: 1297\nexploration: 0.02552\nlearning_rate: 0.00006\nelapsed time: 19089.5 seconds (5.30 hours)\n\nTimestep: 4320000\nmean reward (100 episodes): 0.5400\nbest mean reward: 0.5500\ncurrent episode reward: 0.0000\nepisodes: 1300\nexploration: 0.02530\nlearning_rate: 0.00006\nelapsed time: 19136.3 seconds (5.32 hours)\n\nTimestep: 4330000\nmean reward (100 episodes): 0.5400\nbest mean reward: 0.5500\ncurrent episode reward: 0.0000\nepisodes: 1303\nexploration: 0.02508\nlearning_rate: 0.00006\nelapsed time: 19181.9 seconds (5.33 hours)\n\nTimestep: 4340000\nmean reward (100 episodes): 0.6200\nbest mean reward: 0.6200\ncurrent episode reward: 3.0000\nepisodes: 1306\nexploration: 0.02485\nlearning_rate: 0.00006\nelapsed time: 19228.3 seconds (5.34 hours)\n\nTimestep: 4350000\nmean reward (100 episodes): 0.6500\nbest mean reward: 0.6500\ncurrent episode reward: 3.0000\nepisodes: 1309\nexploration: 0.02462\nlearning_rate: 0.00006\nelapsed time: 19275.8 seconds (5.35 hours)\n\nTimestep: 4360000\nmean reward (100 episodes): 0.6400\nbest mean reward: 0.6500\ncurrent episode reward: 1.0000\nepisodes: 1312\nexploration: 0.02440\nlearning_rate: 0.00006\nelapsed time: 19322.1 seconds (5.37 hours)\n\nTimestep: 4370000\nmean reward (100 episodes): 0.6700\nbest mean reward: 0.6700\ncurrent episode reward: 0.0000\nepisodes: 1315\nexploration: 0.02417\nlearning_rate: 0.00006\nelapsed time: 19368.0 seconds (5.38 hours)\n\nTimestep: 4380000\nmean reward (100 episodes): 1.0000\nbest mean reward: 1.0000\ncurrent episode reward: 21.0000\nepisodes: 1318\nexploration: 0.02395\nlearning_rate: 0.00006\nelapsed time: 19414.2 seconds (5.39 hours)\n\nTimestep: 4390000\nmean reward (100 episodes): 1.1200\nbest mean reward: 1.1200\ncurrent episode reward: 0.0000\nepisodes: 1321\nexploration: 0.02372\nlearning_rate: 0.00006\nelapsed time: 19460.6 seconds (5.41 hours)\n\nTimestep: 4400000\nmean reward (100 episodes): 1.1200\nbest mean reward: 1.1200\ncurrent episode reward: 0.0000\nepisodes: 1324\nexploration: 0.02350\nlearning_rate: 0.00006\nelapsed time: 19507.5 seconds (5.42 hours)\n\nTimestep: 4410000\nmean reward (100 episodes): 1.1900\nbest mean reward: 1.1900\ncurrent episode reward: 3.0000\nepisodes: 1327\nexploration: 0.02327\nlearning_rate: 0.00006\nelapsed time: 19554.6 seconds (5.43 hours)\n\nTimestep: 4420000\nmean reward (100 episodes): 1.1800\nbest mean reward: 1.2200\ncurrent episode reward: 0.0000\nepisodes: 1330\nexploration: 0.02305\nlearning_rate: 0.00006\nelapsed time: 19601.9 seconds (5.44 hours)\n\nTimestep: 4430000\nmean reward (100 episodes): 1.3000\nbest mean reward: 1.3000\ncurrent episode reward: 5.0000\nepisodes: 1333\nexploration: 0.02282\nlearning_rate: 0.00006\nelapsed time: 19647.8 seconds (5.46 hours)\n\nTimestep: 4440000\nmean reward (100 episodes): 1.3500\nbest mean reward: 1.3500\ncurrent episode reward: 0.0000\nepisodes: 1336\nexploration: 0.02260\nlearning_rate: 0.00006\nelapsed time: 19694.3 seconds (5.47 hours)\n\nTimestep: 4450000\nmean reward (100 episodes): 1.3500\nbest mean reward: 1.3500\ncurrent episode reward: 0.0000\nepisodes: 1339\nexploration: 0.02237\nlearning_rate: 0.00006\nelapsed time: 19740.7 seconds (5.48 hours)\n\nTimestep: 4460000\nmean reward (100 episodes): 1.3400\nbest mean reward: 1.3500\ncurrent episode reward: 1.0000\nepisodes: 1342\nexploration: 0.02215\nlearning_rate: 0.00006\nelapsed time: 19787.0 seconds (5.50 hours)\n\nTimestep: 4470000\nmean reward (100 episodes): 1.3800\nbest mean reward: 1.3800\ncurrent episode reward: 1.0000\nepisodes: 1345\nexploration: 0.02192\nlearning_rate: 0.00006\nelapsed time: 19833.2 seconds (5.51 hours)\n\nTimestep: 4480000\nmean reward (100 episodes): 1.4400\nbest mean reward: 1.4400\ncurrent episode reward: 1.0000\nepisodes: 1348\nexploration: 0.02170\nlearning_rate: 0.00006\nelapsed time: 19879.1 seconds (5.52 hours)\n\nTimestep: 4490000\nmean reward (100 episodes): 1.6300\nbest mean reward: 1.6300\ncurrent episode reward: 3.0000\nepisodes: 1351\nexploration: 0.02147\nlearning_rate: 0.00006\nelapsed time: 19926.5 seconds (5.54 hours)\n\nTimestep: 4500000\nmean reward (100 episodes): 1.6600\nbest mean reward: 1.6600\ncurrent episode reward: 0.0000\nepisodes: 1354\nexploration: 0.02125\nlearning_rate: 0.00006\nelapsed time: 19973.2 seconds (5.55 hours)\n\nTimestep: 4510000\nmean reward (100 episodes): 1.6400\nbest mean reward: 1.6600\ncurrent episode reward: 1.0000\nepisodes: 1357\nexploration: 0.02103\nlearning_rate: 0.00006\nelapsed time: 20019.8 seconds (5.56 hours)\n\nTimestep: 4520000\nmean reward (100 episodes): 1.7300\nbest mean reward: 1.7300\ncurrent episode reward: 7.0000\nepisodes: 1360\nexploration: 0.02080\nlearning_rate: 0.00006\nelapsed time: 20066.3 seconds (5.57 hours)\n\nTimestep: 4530000\nmean reward (100 episodes): 1.9200\nbest mean reward: 1.9200\ncurrent episode reward: 0.0000\nepisodes: 1363\nexploration: 0.02057\nlearning_rate: 0.00006\nelapsed time: 20112.7 seconds (5.59 hours)\n\nTimestep: 4540000\nmean reward (100 episodes): 1.9500\nbest mean reward: 1.9500\ncurrent episode reward: 2.0000\nepisodes: 1366\nexploration: 0.02035\nlearning_rate: 0.00006\nelapsed time: 20158.6 seconds (5.60 hours)\n\nTimestep: 4550000\nmean reward (100 episodes): 2.2200\nbest mean reward: 2.2200\ncurrent episode reward: 9.0000\nepisodes: 1369\nexploration: 0.02013\nlearning_rate: 0.00006\nelapsed time: 20204.4 seconds (5.61 hours)\n\nTimestep: 4560000\nmean reward (100 episodes): 2.2500\nbest mean reward: 2.2500\ncurrent episode reward: 3.0000\nepisodes: 1372\nexploration: 0.01990\nlearning_rate: 0.00006\nelapsed time: 20250.2 seconds (5.63 hours)\n\nTimestep: 4570000\nmean reward (100 episodes): 2.2700\nbest mean reward: 2.2700\ncurrent episode reward: 0.0000\nepisodes: 1375\nexploration: 0.01967\nlearning_rate: 0.00006\nelapsed time: 20296.1 seconds (5.64 hours)\n\nTimestep: 4580000\nmean reward (100 episodes): 2.3900\nbest mean reward: 2.3900\ncurrent episode reward: 0.0000\nepisodes: 1378\nexploration: 0.01945\nlearning_rate: 0.00006\nelapsed time: 20343.0 seconds (5.65 hours)\n\nTimestep: 4590000\nmean reward (100 episodes): 2.3900\nbest mean reward: 2.4000\ncurrent episode reward: 1.0000\nepisodes: 1381\nexploration: 0.01923\nlearning_rate: 0.00006\nelapsed time: 20390.0 seconds (5.66 hours)\n\nTimestep: 4600000\nmean reward (100 episodes): 2.4500\nbest mean reward: 2.4500\ncurrent episode reward: 0.0000\nepisodes: 1384\nexploration: 0.01900\nlearning_rate: 0.00006\nelapsed time: 20436.6 seconds (5.68 hours)\n\nTimestep: 4610000\nmean reward (100 episodes): 2.4300\nbest mean reward: 2.4500\ncurrent episode reward: 0.0000\nepisodes: 1387\nexploration: 0.01878\nlearning_rate: 0.00005\nelapsed time: 20482.6 seconds (5.69 hours)\n\nTimestep: 4620000\nmean reward (100 episodes): 2.2100\nbest mean reward: 2.4500\ncurrent episode reward: 1.0000\nepisodes: 1390\nexploration: 0.01855\nlearning_rate: 0.00005\nelapsed time: 20528.9 seconds (5.70 hours)\n\nTimestep: 4630000\nmean reward (100 episodes): 2.2100\nbest mean reward: 2.4500\ncurrent episode reward: 3.0000\nepisodes: 1393\nexploration: 0.01832\nlearning_rate: 0.00005\nelapsed time: 20574.5 seconds (5.72 hours)\n\nTimestep: 4640000\nmean reward (100 episodes): 2.2900\nbest mean reward: 2.4500\ncurrent episode reward: 1.0000\nepisodes: 1396\nexploration: 0.01810\nlearning_rate: 0.00005\nelapsed time: 20621.5 seconds (5.73 hours)\n\nTimestep: 4650000\nmean reward (100 episodes): 2.2900\nbest mean reward: 2.4500\ncurrent episode reward: 0.0000\nepisodes: 1399\nexploration: 0.01788\nlearning_rate: 0.00005\nelapsed time: 20667.3 seconds (5.74 hours)\n\nTimestep: 4660000\nmean reward (100 episodes): 2.3000\nbest mean reward: 2.4500\ncurrent episode reward: 0.0000\nepisodes: 1402\nexploration: 0.01765\nlearning_rate: 0.00005\nelapsed time: 20713.3 seconds (5.75 hours)\n\nTimestep: 4670000\nmean reward (100 episodes): 2.2500\nbest mean reward: 2.4500\ncurrent episode reward: 0.0000\nepisodes: 1405\nexploration: 0.01742\nlearning_rate: 0.00005\nelapsed time: 20760.0 seconds (5.77 hours)\n\nTimestep: 4680000\nmean reward (100 episodes): 2.2700\nbest mean reward: 2.4500\ncurrent episode reward: 0.0000\nepisodes: 1408\nexploration: 0.01720\nlearning_rate: 0.00005\nelapsed time: 20805.6 seconds (5.78 hours)\n\nTimestep: 4690000\nmean reward (100 episodes): 2.2800\nbest mean reward: 2.4500\ncurrent episode reward: 4.0000\nepisodes: 1411\nexploration: 0.01697\nlearning_rate: 0.00005\nelapsed time: 20851.8 seconds (5.79 hours)\n\nTimestep: 4700000\nmean reward (100 episodes): 2.2400\nbest mean reward: 2.4500\ncurrent episode reward: 0.0000\nepisodes: 1414\nexploration: 0.01675\nlearning_rate: 0.00005\nelapsed time: 20897.0 seconds (5.80 hours)\n\nTimestep: 4710000\nmean reward (100 episodes): 2.1300\nbest mean reward: 2.4500\ncurrent episode reward: 0.0000\nepisodes: 1417\nexploration: 0.01652\nlearning_rate: 0.00005\nelapsed time: 20943.2 seconds (5.82 hours)\n\nTimestep: 4720000\nmean reward (100 episodes): 1.8500\nbest mean reward: 2.4500\ncurrent episode reward: 0.0000\nepisodes: 1420\nexploration: 0.01630\nlearning_rate: 0.00005\nelapsed time: 20990.0 seconds (5.83 hours)\n\nTimestep: 4730000\nmean reward (100 episodes): 2.0000\nbest mean reward: 2.4500\ncurrent episode reward: 14.0000\nepisodes: 1423\nexploration: 0.01607\nlearning_rate: 0.00005\nelapsed time: 21036.3 seconds (5.84 hours)\n\nTimestep: 4740000\nmean reward (100 episodes): 2.1300\nbest mean reward: 2.4500\ncurrent episode reward: 6.0000\nepisodes: 1426\nexploration: 0.01585\nlearning_rate: 0.00005\nelapsed time: 21082.5 seconds (5.86 hours)\n\nTimestep: 4750000\nmean reward (100 episodes): 2.3700\nbest mean reward: 2.4500\ncurrent episode reward: 0.0000\nepisodes: 1429\nexploration: 0.01562\nlearning_rate: 0.00005\nelapsed time: 21128.9 seconds (5.87 hours)\n\nTimestep: 4760000\nmean reward (100 episodes): 2.3600\nbest mean reward: 2.4500\ncurrent episode reward: 7.0000\nepisodes: 1432\nexploration: 0.01540\nlearning_rate: 0.00005\nelapsed time: 21176.3 seconds (5.88 hours)\n\nTimestep: 4770000\nmean reward (100 episodes): 2.3700\nbest mean reward: 2.4500\ncurrent episode reward: 1.0000\nepisodes: 1435\nexploration: 0.01517\nlearning_rate: 0.00005\nelapsed time: 21222.4 seconds (5.90 hours)\n\nTimestep: 4780000\nmean reward (100 episodes): 2.5700\nbest mean reward: 2.5700\ncurrent episode reward: 5.0000\nepisodes: 1438\nexploration: 0.01495\nlearning_rate: 0.00005\nelapsed time: 21269.1 seconds (5.91 hours)\n\nTimestep: 4790000\nmean reward (100 episodes): 2.8000\nbest mean reward: 2.8000\ncurrent episode reward: 23.0000\nepisodes: 1441\nexploration: 0.01472\nlearning_rate: 0.00005\nelapsed time: 21315.0 seconds (5.92 hours)\n\nTimestep: 4800000\nmean reward (100 episodes): 2.8800\nbest mean reward: 2.8800\ncurrent episode reward: 12.0000\nepisodes: 1444\nexploration: 0.01450\nlearning_rate: 0.00005\nelapsed time: 21361.9 seconds (5.93 hours)\n\nTimestep: 4810000\nmean reward (100 episodes): 2.9600\nbest mean reward: 2.9600\ncurrent episode reward: 1.0000\nepisodes: 1447\nexploration: 0.01427\nlearning_rate: 0.00005\nelapsed time: 21409.0 seconds (5.95 hours)\n\nTimestep: 4820000\nmean reward (100 episodes): 2.8000\nbest mean reward: 2.9600\ncurrent episode reward: 0.0000\nepisodes: 1450\nexploration: 0.01405\nlearning_rate: 0.00005\nelapsed time: 21455.5 seconds (5.96 hours)\n\nTimestep: 4830000\nmean reward (100 episodes): 3.0200\nbest mean reward: 3.0200\ncurrent episode reward: 0.0000\nepisodes: 1453\nexploration: 0.01382\nlearning_rate: 0.00005\nelapsed time: 21502.5 seconds (5.97 hours)\n\nTimestep: 4840000\nmean reward (100 episodes): 3.5000\nbest mean reward: 3.5100\ncurrent episode reward: 0.0000\nepisodes: 1456\nexploration: 0.01360\nlearning_rate: 0.00005\nelapsed time: 21549.4 seconds (5.99 hours)\n\nTimestep: 4850000\nmean reward (100 episodes): 3.9400\nbest mean reward: 3.9400\ncurrent episode reward: 15.0000\nepisodes: 1459\nexploration: 0.01337\nlearning_rate: 0.00005\nelapsed time: 21596.7 seconds (6.00 hours)\n\nTimestep: 4860000\nmean reward (100 episodes): 3.7700\nbest mean reward: 3.9600\ncurrent episode reward: 0.0000\nepisodes: 1462\nexploration: 0.01315\nlearning_rate: 0.00005\nelapsed time: 21643.2 seconds (6.01 hours)\n\nTimestep: 4870000\nmean reward (100 episodes): 3.8500\nbest mean reward: 3.9600\ncurrent episode reward: 0.0000\nepisodes: 1465\nexploration: 0.01292\nlearning_rate: 0.00005\nelapsed time: 21689.6 seconds (6.02 hours)\n\nTimestep: 4880000\nmean reward (100 episodes): 3.6900\nbest mean reward: 3.9600\ncurrent episode reward: 2.0000\nepisodes: 1468\nexploration: 0.01270\nlearning_rate: 0.00005\nelapsed time: 21734.9 seconds (6.04 hours)\n\nTimestep: 4890000\nmean reward (100 episodes): 3.8400\nbest mean reward: 3.9600\ncurrent episode reward: 17.0000\nepisodes: 1471\nexploration: 0.01247\nlearning_rate: 0.00005\nelapsed time: 21780.3 seconds (6.05 hours)\n\nTimestep: 4900000\nmean reward (100 episodes): 3.8300\nbest mean reward: 3.9600\ncurrent episode reward: 0.0000\nepisodes: 1474\nexploration: 0.01225\nlearning_rate: 0.00005\nelapsed time: 21825.8 seconds (6.06 hours)\n\nTimestep: 4910000\nmean reward (100 episodes): 3.8800\nbest mean reward: 3.9600\ncurrent episode reward: 8.0000\nepisodes: 1477\nexploration: 0.01202\nlearning_rate: 0.00005\nelapsed time: 21871.4 seconds (6.08 hours)\n\nTimestep: 4920000\nmean reward (100 episodes): 3.9000\nbest mean reward: 3.9600\ncurrent episode reward: 0.0000\nepisodes: 1480\nexploration: 0.01180\nlearning_rate: 0.00005\nelapsed time: 21916.8 seconds (6.09 hours)\n\nTimestep: 4930000\nmean reward (100 episodes): 3.8700\nbest mean reward: 3.9600\ncurrent episode reward: 4.0000\nepisodes: 1483\nexploration: 0.01157\nlearning_rate: 0.00005\nelapsed time: 21963.6 seconds (6.10 hours)\n\nTimestep: 4940000\nmean reward (100 episodes): 3.9100\nbest mean reward: 3.9600\ncurrent episode reward: 0.0000\nepisodes: 1486\nexploration: 0.01135\nlearning_rate: 0.00005\nelapsed time: 22009.7 seconds (6.11 hours)\n\nTimestep: 4950000\nmean reward (100 episodes): 4.2700\nbest mean reward: 4.2700\ncurrent episode reward: 0.0000\nepisodes: 1489\nexploration: 0.01112\nlearning_rate: 0.00005\nelapsed time: 22056.4 seconds (6.13 hours)\n\nTimestep: 4960000\nmean reward (100 episodes): 4.7500\nbest mean reward: 4.7500\ncurrent episode reward: 9.0000\nepisodes: 1492\nexploration: 0.01090\nlearning_rate: 0.00005\nelapsed time: 22103.2 seconds (6.14 hours)\n\nTimestep: 4970000\nmean reward (100 episodes): 5.1300\nbest mean reward: 5.1300\ncurrent episode reward: 13.0000\nepisodes: 1495\nexploration: 0.01067\nlearning_rate: 0.00005\nelapsed time: 22150.1 seconds (6.15 hours)\n\nTimestep: 4980000\nmean reward (100 episodes): 5.4800\nbest mean reward: 5.4800\ncurrent episode reward: 0.0000\nepisodes: 1498\nexploration: 0.01045\nlearning_rate: 0.00005\nelapsed time: 22196.1 seconds (6.17 hours)\n\nTimestep: 4990000\nmean reward (100 episodes): 5.6200\nbest mean reward: 5.6200\ncurrent episode reward: 13.0000\nepisodes: 1501\nexploration: 0.01022\nlearning_rate: 0.00005\nelapsed time: 22242.2 seconds (6.18 hours)\n\nTimestep: 5000000\nmean reward (100 episodes): 6.6600\nbest mean reward: 6.6600\ncurrent episode reward: 67.0000\nepisodes: 1504\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22288.5 seconds (6.19 hours)\n\nTimestep: 5010000\nmean reward (100 episodes): 7.6600\nbest mean reward: 7.6600\ncurrent episode reward: 28.0000\nepisodes: 1507\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22335.4 seconds (6.20 hours)\n\nTimestep: 5020000\nmean reward (100 episodes): 8.4400\nbest mean reward: 8.4400\ncurrent episode reward: 33.0000\nepisodes: 1510\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22382.4 seconds (6.22 hours)\n\nTimestep: 5030000\nmean reward (100 episodes): 8.7100\nbest mean reward: 8.7100\ncurrent episode reward: 0.0000\nepisodes: 1513\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22428.8 seconds (6.23 hours)\n\nTimestep: 5040000\nmean reward (100 episodes): 9.5200\nbest mean reward: 9.5200\ncurrent episode reward: 2.0000\nepisodes: 1516\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22475.5 seconds (6.24 hours)\n\nTimestep: 5050000\nmean reward (100 episodes): 10.4400\nbest mean reward: 10.4400\ncurrent episode reward: 59.0000\nepisodes: 1519\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22522.3 seconds (6.26 hours)\n\nTimestep: 5060000\nmean reward (100 episodes): 11.3500\nbest mean reward: 11.3500\ncurrent episode reward: 13.0000\nepisodes: 1522\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22568.4 seconds (6.27 hours)\n\nTimestep: 5070000\nmean reward (100 episodes): 11.8200\nbest mean reward: 11.8200\ncurrent episode reward: 15.0000\nepisodes: 1525\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22614.8 seconds (6.28 hours)\n\nTimestep: 5080000\nmean reward (100 episodes): 13.1100\nbest mean reward: 13.1100\ncurrent episode reward: 40.0000\nepisodes: 1528\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22661.8 seconds (6.29 hours)\n\nTimestep: 5090000\nmean reward (100 episodes): 13.6900\nbest mean reward: 13.6900\ncurrent episode reward: 34.0000\nepisodes: 1531\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22708.6 seconds (6.31 hours)\n\nTimestep: 5100000\nmean reward (100 episodes): 14.8800\nbest mean reward: 14.8800\ncurrent episode reward: 72.0000\nepisodes: 1534\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22755.4 seconds (6.32 hours)\n\nTimestep: 5110000\nmean reward (100 episodes): 16.0800\nbest mean reward: 16.0800\ncurrent episode reward: 42.0000\nepisodes: 1537\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22802.2 seconds (6.33 hours)\n\nTimestep: 5120000\nmean reward (100 episodes): 17.3600\nbest mean reward: 17.3600\ncurrent episode reward: 87.0000\nepisodes: 1540\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22849.3 seconds (6.35 hours)\n\nTimestep: 5130000\nmean reward (100 episodes): 19.1600\nbest mean reward: 19.1600\ncurrent episode reward: 63.0000\nepisodes: 1543\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22896.4 seconds (6.36 hours)\n\nTimestep: 5140000\nmean reward (100 episodes): 19.8000\nbest mean reward: 19.8000\ncurrent episode reward: 30.0000\nepisodes: 1547\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22942.6 seconds (6.37 hours)\n\nTimestep: 5150000\nmean reward (100 episodes): 22.2400\nbest mean reward: 22.2400\ncurrent episode reward: 77.0000\nepisodes: 1550\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22989.7 seconds (6.39 hours)\n\nTimestep: 5160000\nmean reward (100 episodes): 23.6500\nbest mean reward: 23.6500\ncurrent episode reward: 44.0000\nepisodes: 1553\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23035.4 seconds (6.40 hours)\n\nTimestep: 5170000\nmean reward (100 episodes): 25.3600\nbest mean reward: 25.3600\ncurrent episode reward: 51.0000\nepisodes: 1556\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23081.6 seconds (6.41 hours)\n\nTimestep: 5180000\nmean reward (100 episodes): 26.8100\nbest mean reward: 26.8100\ncurrent episode reward: 115.0000\nepisodes: 1559\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23128.7 seconds (6.42 hours)\n\nTimestep: 5190000\nmean reward (100 episodes): 28.0500\nbest mean reward: 28.0500\ncurrent episode reward: 33.0000\nepisodes: 1562\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23174.7 seconds (6.44 hours)\n\nTimestep: 5200000\nmean reward (100 episodes): 29.8700\nbest mean reward: 29.8700\ncurrent episode reward: 27.0000\nepisodes: 1565\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23221.2 seconds (6.45 hours)\n\nTimestep: 5210000\nmean reward (100 episodes): 31.9400\nbest mean reward: 31.9400\ncurrent episode reward: 84.0000\nepisodes: 1568\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23268.1 seconds (6.46 hours)\n\nTimestep: 5220000\nmean reward (100 episodes): 33.5500\nbest mean reward: 33.5500\ncurrent episode reward: 76.0000\nepisodes: 1571\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23315.6 seconds (6.48 hours)\n\nTimestep: 5230000\nmean reward (100 episodes): 35.7200\nbest mean reward: 35.7200\ncurrent episode reward: 75.0000\nepisodes: 1574\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23362.8 seconds (6.49 hours)\n\nTimestep: 5240000\nmean reward (100 episodes): 36.6300\nbest mean reward: 36.6300\ncurrent episode reward: 30.0000\nepisodes: 1577\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23409.5 seconds (6.50 hours)\n\nTimestep: 5250000\nmean reward (100 episodes): 38.5000\nbest mean reward: 38.5000\ncurrent episode reward: 93.0000\nepisodes: 1580\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23456.7 seconds (6.52 hours)\n\nTimestep: 5260000\nmean reward (100 episodes): 39.7000\nbest mean reward: 39.7000\ncurrent episode reward: 48.0000\nepisodes: 1583\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23503.2 seconds (6.53 hours)\n\nTimestep: 5270000\nmean reward (100 episodes): 40.7900\nbest mean reward: 40.7900\ncurrent episode reward: 51.0000\nepisodes: 1586\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23549.9 seconds (6.54 hours)\n\nTimestep: 5280000\nmean reward (100 episodes): 42.5700\nbest mean reward: 42.5700\ncurrent episode reward: 66.0000\nepisodes: 1589\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23596.9 seconds (6.55 hours)\n\nTimestep: 5290000\nmean reward (100 episodes): 44.2100\nbest mean reward: 44.2100\ncurrent episode reward: 82.0000\nepisodes: 1592\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23644.0 seconds (6.57 hours)\n\nTimestep: 5300000\nmean reward (100 episodes): 46.0200\nbest mean reward: 46.0200\ncurrent episode reward: 111.0000\nepisodes: 1595\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23691.2 seconds (6.58 hours)\n\nTimestep: 5310000\nmean reward (100 episodes): 47.1700\nbest mean reward: 47.1700\ncurrent episode reward: 39.0000\nepisodes: 1598\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23737.6 seconds (6.59 hours)\n\nTimestep: 5320000\nmean reward (100 episodes): 49.6700\nbest mean reward: 49.6700\ncurrent episode reward: 74.0000\nepisodes: 1601\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23784.2 seconds (6.61 hours)\n\nTimestep: 5330000\nmean reward (100 episodes): 50.8400\nbest mean reward: 50.8400\ncurrent episode reward: 106.0000\nepisodes: 1604\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23830.3 seconds (6.62 hours)\n\nTimestep: 5340000\nmean reward (100 episodes): 52.5100\nbest mean reward: 52.5100\ncurrent episode reward: 80.0000\nepisodes: 1607\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23877.0 seconds (6.63 hours)\n\nTimestep: 5350000\nmean reward (100 episodes): 53.8000\nbest mean reward: 53.8000\ncurrent episode reward: 68.0000\nepisodes: 1610\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23923.2 seconds (6.65 hours)\n\nTimestep: 5360000\nmean reward (100 episodes): 55.7100\nbest mean reward: 55.7100\ncurrent episode reward: 47.0000\nepisodes: 1613\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23969.7 seconds (6.66 hours)\n\nTimestep: 5370000\nmean reward (100 episodes): 57.1100\nbest mean reward: 57.1100\ncurrent episode reward: 48.0000\nepisodes: 1616\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24017.0 seconds (6.67 hours)\n\nTimestep: 5380000\nmean reward (100 episodes): 59.0800\nbest mean reward: 59.0800\ncurrent episode reward: 108.0000\nepisodes: 1619\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24064.7 seconds (6.68 hours)\n\nTimestep: 5390000\nmean reward (100 episodes): 60.7600\nbest mean reward: 60.7600\ncurrent episode reward: 103.0000\nepisodes: 1622\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24111.1 seconds (6.70 hours)\n\nTimestep: 5400000\nmean reward (100 episodes): 61.6100\nbest mean reward: 61.6100\ncurrent episode reward: 58.0000\nepisodes: 1625\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24156.6 seconds (6.71 hours)\n\nTimestep: 5410000\nmean reward (100 episodes): 62.6700\nbest mean reward: 62.6700\ncurrent episode reward: 90.0000\nepisodes: 1628\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24203.2 seconds (6.72 hours)\n\nTimestep: 5420000\nmean reward (100 episodes): 64.8800\nbest mean reward: 64.8800\ncurrent episode reward: 93.0000\nepisodes: 1631\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24250.6 seconds (6.74 hours)\n\nTimestep: 5430000\nmean reward (100 episodes): 65.2200\nbest mean reward: 65.2500\ncurrent episode reward: 92.0000\nepisodes: 1634\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24296.9 seconds (6.75 hours)\n\nTimestep: 5440000\nmean reward (100 episodes): 64.5100\nbest mean reward: 65.3700\ncurrent episode reward: 2.0000\nepisodes: 1637\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24342.9 seconds (6.76 hours)\n\nTimestep: 5450000\nmean reward (100 episodes): 64.7700\nbest mean reward: 65.3700\ncurrent episode reward: 102.0000\nepisodes: 1640\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24389.4 seconds (6.77 hours)\n\nTimestep: 5460000\nmean reward (100 episodes): 64.5000\nbest mean reward: 65.3700\ncurrent episode reward: 28.0000\nepisodes: 1643\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24436.6 seconds (6.79 hours)\n\nTimestep: 5470000\nmean reward (100 episodes): 65.3200\nbest mean reward: 65.3700\ncurrent episode reward: 29.0000\nepisodes: 1646\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24483.0 seconds (6.80 hours)\n\nTimestep: 5480000\nmean reward (100 episodes): 66.2600\nbest mean reward: 66.2600\ncurrent episode reward: 93.0000\nepisodes: 1649\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24529.0 seconds (6.81 hours)\n\nTimestep: 5490000\nmean reward (100 episodes): 65.8300\nbest mean reward: 66.2600\ncurrent episode reward: 83.0000\nepisodes: 1652\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24575.0 seconds (6.83 hours)\n\nTimestep: 5500000\nmean reward (100 episodes): 65.9900\nbest mean reward: 66.2600\ncurrent episode reward: 72.0000\nepisodes: 1655\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24621.2 seconds (6.84 hours)\n\nTimestep: 5510000\nmean reward (100 episodes): 67.0000\nbest mean reward: 67.0000\ncurrent episode reward: 132.0000\nepisodes: 1658\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24667.6 seconds (6.85 hours)\n\nTimestep: 5520000\nmean reward (100 episodes): 67.1100\nbest mean reward: 67.1100\ncurrent episode reward: 94.0000\nepisodes: 1661\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24714.3 seconds (6.87 hours)\n\nTimestep: 5530000\nmean reward (100 episodes): 67.8800\nbest mean reward: 67.8800\ncurrent episode reward: 111.0000\nepisodes: 1664\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24761.0 seconds (6.88 hours)\n\nTimestep: 5540000\nmean reward (100 episodes): 68.2000\nbest mean reward: 68.2800\ncurrent episode reward: 51.0000\nepisodes: 1667\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24807.5 seconds (6.89 hours)\n\nTimestep: 5550000\nmean reward (100 episodes): 68.3300\nbest mean reward: 68.3300\ncurrent episode reward: 91.0000\nepisodes: 1670\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24854.1 seconds (6.90 hours)\n\nTimestep: 5560000\nmean reward (100 episodes): 69.7800\nbest mean reward: 69.7800\ncurrent episode reward: 105.0000\nepisodes: 1673\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24900.8 seconds (6.92 hours)\n\nTimestep: 5570000\nmean reward (100 episodes): 71.0700\nbest mean reward: 71.0700\ncurrent episode reward: 81.0000\nepisodes: 1676\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24947.0 seconds (6.93 hours)\n\nTimestep: 5580000\nmean reward (100 episodes): 72.5600\nbest mean reward: 72.5600\ncurrent episode reward: 73.0000\nepisodes: 1679\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24993.4 seconds (6.94 hours)\n\nTimestep: 5590000\nmean reward (100 episodes): 73.4700\nbest mean reward: 73.4700\ncurrent episode reward: 50.0000\nepisodes: 1682\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25039.1 seconds (6.96 hours)\n\nTimestep: 5600000\nmean reward (100 episodes): 74.8500\nbest mean reward: 74.8500\ncurrent episode reward: 88.0000\nepisodes: 1685\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25084.9 seconds (6.97 hours)\n\nTimestep: 5610000\nmean reward (100 episodes): 76.3400\nbest mean reward: 76.3400\ncurrent episode reward: 115.0000\nepisodes: 1688\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25131.1 seconds (6.98 hours)\n\nTimestep: 5620000\nmean reward (100 episodes): 77.5000\nbest mean reward: 77.5000\ncurrent episode reward: 105.0000\nepisodes: 1691\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25177.6 seconds (6.99 hours)\n\nTimestep: 5630000\nmean reward (100 episodes): 78.6100\nbest mean reward: 78.6100\ncurrent episode reward: 111.0000\nepisodes: 1694\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25224.3 seconds (7.01 hours)\n\nTimestep: 5640000\nmean reward (100 episodes): 79.0600\nbest mean reward: 79.0600\ncurrent episode reward: 103.0000\nepisodes: 1697\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25270.8 seconds (7.02 hours)\n\nTimestep: 5650000\nmean reward (100 episodes): 79.3900\nbest mean reward: 79.8400\ncurrent episode reward: 104.0000\nepisodes: 1700\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25316.5 seconds (7.03 hours)\n\nTimestep: 5660000\nmean reward (100 episodes): 80.8400\nbest mean reward: 80.8400\ncurrent episode reward: 116.0000\nepisodes: 1703\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25363.2 seconds (7.05 hours)\n\nTimestep: 5670000\nmean reward (100 episodes): 79.9500\nbest mean reward: 80.8400\ncurrent episode reward: 41.0000\nepisodes: 1706\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25408.8 seconds (7.06 hours)\n\nTimestep: 5680000\nmean reward (100 episodes): 81.4600\nbest mean reward: 81.4600\ncurrent episode reward: 97.0000\nepisodes: 1709\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25455.4 seconds (7.07 hours)\n\nTimestep: 5690000\nmean reward (100 episodes): 81.9300\nbest mean reward: 82.0100\ncurrent episode reward: 94.0000\nepisodes: 1712\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25501.7 seconds (7.08 hours)\n\nTimestep: 5700000\nmean reward (100 episodes): 81.9800\nbest mean reward: 82.4200\ncurrent episode reward: 30.0000\nepisodes: 1715\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25547.1 seconds (7.10 hours)\n\nTimestep: 5710000\nmean reward (100 episodes): 82.5100\nbest mean reward: 82.5500\ncurrent episode reward: 116.0000\nepisodes: 1718\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25593.5 seconds (7.11 hours)\n\nTimestep: 5720000\nmean reward (100 episodes): 82.2100\nbest mean reward: 82.5500\ncurrent episode reward: 126.0000\nepisodes: 1721\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25640.7 seconds (7.12 hours)\n\nTimestep: 5730000\nmean reward (100 episodes): 82.0700\nbest mean reward: 82.5500\ncurrent episode reward: 8.0000\nepisodes: 1724\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25687.3 seconds (7.14 hours)\n\nTimestep: 5740000\nmean reward (100 episodes): 82.1900\nbest mean reward: 82.5500\ncurrent episode reward: 100.0000\nepisodes: 1727\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25733.7 seconds (7.15 hours)\n\nTimestep: 5750000\nmean reward (100 episodes): 81.8300\nbest mean reward: 82.5500\ncurrent episode reward: 98.0000\nepisodes: 1730\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25780.9 seconds (7.16 hours)\n\nTimestep: 5760000\nmean reward (100 episodes): 82.5400\nbest mean reward: 82.5500\ncurrent episode reward: 117.0000\nepisodes: 1733\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25827.7 seconds (7.17 hours)\n\nTimestep: 5770000\nmean reward (100 episodes): 83.2700\nbest mean reward: 83.2700\ncurrent episode reward: 90.0000\nepisodes: 1736\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25873.4 seconds (7.19 hours)\n\nTimestep: 5780000\nmean reward (100 episodes): 84.9900\nbest mean reward: 84.9900\ncurrent episode reward: 56.0000\nepisodes: 1739\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25920.6 seconds (7.20 hours)\n\nTimestep: 5790000\nmean reward (100 episodes): 85.4700\nbest mean reward: 86.2300\ncurrent episode reward: 28.0000\nepisodes: 1742\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25966.7 seconds (7.21 hours)\n\nTimestep: 5800000\nmean reward (100 episodes): 87.5200\nbest mean reward: 87.5200\ncurrent episode reward: 105.0000\nepisodes: 1745\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26012.5 seconds (7.23 hours)\n\nTimestep: 5810000\nmean reward (100 episodes): 88.6100\nbest mean reward: 88.6100\ncurrent episode reward: 132.0000\nepisodes: 1748\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26059.6 seconds (7.24 hours)\n\nTimestep: 5820000\nmean reward (100 episodes): 88.7200\nbest mean reward: 89.3400\ncurrent episode reward: 0.0000\nepisodes: 1751\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26106.7 seconds (7.25 hours)\n\nTimestep: 5830000\nmean reward (100 episodes): 88.4600\nbest mean reward: 89.3400\ncurrent episode reward: 32.0000\nepisodes: 1754\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26153.5 seconds (7.26 hours)\n\nTimestep: 5840000\nmean reward (100 episodes): 88.7200\nbest mean reward: 89.3400\ncurrent episode reward: 23.0000\nepisodes: 1757\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26200.4 seconds (7.28 hours)\n\nTimestep: 5850000\nmean reward (100 episodes): 88.5800\nbest mean reward: 89.3400\ncurrent episode reward: 23.0000\nepisodes: 1760\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26247.2 seconds (7.29 hours)\n\nTimestep: 5860000\nmean reward (100 episodes): 88.8900\nbest mean reward: 89.3400\ncurrent episode reward: 83.0000\nepisodes: 1763\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26292.9 seconds (7.30 hours)\n\nTimestep: 5870000\nmean reward (100 episodes): 89.3100\nbest mean reward: 89.3400\ncurrent episode reward: 92.0000\nepisodes: 1766\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26339.3 seconds (7.32 hours)\n\nTimestep: 5880000\nmean reward (100 episodes): 90.8800\nbest mean reward: 90.8800\ncurrent episode reward: 106.0000\nepisodes: 1769\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26386.4 seconds (7.33 hours)\n\nTimestep: 5890000\nmean reward (100 episodes): 90.7100\nbest mean reward: 90.9900\ncurrent episode reward: 106.0000\nepisodes: 1772\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26432.2 seconds (7.34 hours)\n\nTimestep: 5900000\nmean reward (100 episodes): 90.5300\nbest mean reward: 91.0700\ncurrent episode reward: 52.0000\nepisodes: 1775\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26479.0 seconds (7.36 hours)\n\nTimestep: 5910000\nmean reward (100 episodes): 91.5300\nbest mean reward: 91.5300\ncurrent episode reward: 140.0000\nepisodes: 1778\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26524.7 seconds (7.37 hours)\n\nTimestep: 5920000\nmean reward (100 episodes): 91.9200\nbest mean reward: 92.2800\ncurrent episode reward: 128.0000\nepisodes: 1781\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26570.7 seconds (7.38 hours)\n\nTimestep: 5930000\nmean reward (100 episodes): 93.6200\nbest mean reward: 93.6200\ncurrent episode reward: 116.0000\nepisodes: 1784\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26617.5 seconds (7.39 hours)\n\nTimestep: 5940000\nmean reward (100 episodes): 94.5000\nbest mean reward: 94.5000\ncurrent episode reward: 138.0000\nepisodes: 1787\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26663.9 seconds (7.41 hours)\n\nTimestep: 5950000\nmean reward (100 episodes): 94.3400\nbest mean reward: 94.7200\ncurrent episode reward: 75.0000\nepisodes: 1790\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26710.7 seconds (7.42 hours)\n\nTimestep: 5960000\nmean reward (100 episodes): 94.3500\nbest mean reward: 94.7200\ncurrent episode reward: 77.0000\nepisodes: 1793\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26757.4 seconds (7.43 hours)\n\nTimestep: 5970000\nmean reward (100 episodes): 95.5000\nbest mean reward: 95.5000\ncurrent episode reward: 189.0000\nepisodes: 1796\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26804.0 seconds (7.45 hours)\n\nTimestep: 5980000\nmean reward (100 episodes): 96.3100\nbest mean reward: 96.3100\ncurrent episode reward: 104.0000\nepisodes: 1799\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26849.9 seconds (7.46 hours)\n\nTimestep: 5990000\nmean reward (100 episodes): 97.0400\nbest mean reward: 97.0600\ncurrent episode reward: 109.0000\nepisodes: 1802\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26896.0 seconds (7.47 hours)\n\nTimestep: 6000000\nmean reward (100 episodes): 96.9700\nbest mean reward: 97.0600\ncurrent episode reward: 108.0000\nepisodes: 1805\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26942.8 seconds (7.48 hours)\n\nTimestep: 6010000\nmean reward (100 episodes): 96.4700\nbest mean reward: 97.7200\ncurrent episode reward: 49.0000\nepisodes: 1808\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26989.2 seconds (7.50 hours)\n\nTimestep: 6020000\nmean reward (100 episodes): 94.7600\nbest mean reward: 97.7200\ncurrent episode reward: 39.0000\nepisodes: 1811\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27035.7 seconds (7.51 hours)\n\nTimestep: 6030000\nmean reward (100 episodes): 94.8600\nbest mean reward: 97.7200\ncurrent episode reward: 129.0000\nepisodes: 1814\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27082.7 seconds (7.52 hours)\n\nTimestep: 6040000\nmean reward (100 episodes): 95.0300\nbest mean reward: 97.7200\ncurrent episode reward: 2.0000\nepisodes: 1817\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27129.5 seconds (7.54 hours)\n\nTimestep: 6050000\nmean reward (100 episodes): 95.6000\nbest mean reward: 97.7200\ncurrent episode reward: 158.0000\nepisodes: 1820\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27176.0 seconds (7.55 hours)\n\nTimestep: 6060000\nmean reward (100 episodes): 95.4100\nbest mean reward: 97.7200\ncurrent episode reward: 135.0000\nepisodes: 1823\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27222.9 seconds (7.56 hours)\n\nTimestep: 6070000\nmean reward (100 episodes): 97.2300\nbest mean reward: 97.7200\ncurrent episode reward: 103.0000\nepisodes: 1826\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27268.5 seconds (7.57 hours)\n\nTimestep: 6080000\nmean reward (100 episodes): 97.5200\nbest mean reward: 97.7200\ncurrent episode reward: 106.0000\nepisodes: 1829\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27315.0 seconds (7.59 hours)\n\nTimestep: 6090000\nmean reward (100 episodes): 98.5700\nbest mean reward: 98.5700\ncurrent episode reward: 82.0000\nepisodes: 1832\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27361.8 seconds (7.60 hours)\n\nTimestep: 6100000\nmean reward (100 episodes): 98.3000\nbest mean reward: 98.5700\ncurrent episode reward: 79.0000\nepisodes: 1835\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27407.8 seconds (7.61 hours)\n\nTimestep: 6110000\nmean reward (100 episodes): 99.0200\nbest mean reward: 99.0200\ncurrent episode reward: 107.0000\nepisodes: 1838\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27454.1 seconds (7.63 hours)\n\nTimestep: 6120000\nmean reward (100 episodes): 98.4000\nbest mean reward: 99.1500\ncurrent episode reward: 66.0000\nepisodes: 1841\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27500.6 seconds (7.64 hours)\n\nTimestep: 6130000\nmean reward (100 episodes): 98.4400\nbest mean reward: 99.1500\ncurrent episode reward: 93.0000\nepisodes: 1844\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27546.8 seconds (7.65 hours)\n\nTimestep: 6140000\nmean reward (100 episodes): 98.5400\nbest mean reward: 99.1500\ncurrent episode reward: 62.0000\nepisodes: 1847\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27592.9 seconds (7.66 hours)\n\nTimestep: 6150000\nmean reward (100 episodes): 99.2000\nbest mean reward: 99.2000\ncurrent episode reward: 56.0000\nepisodes: 1851\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27639.7 seconds (7.68 hours)\n\nTimestep: 6160000\nmean reward (100 episodes): 99.2600\nbest mean reward: 99.2600\ncurrent episode reward: 149.0000\nepisodes: 1854\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27686.0 seconds (7.69 hours)\n\nTimestep: 6170000\nmean reward (100 episodes): 101.3800\nbest mean reward: 101.3800\ncurrent episode reward: 111.0000\nepisodes: 1857\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27732.1 seconds (7.70 hours)\n\nTimestep: 6180000\nmean reward (100 episodes): 102.4600\nbest mean reward: 102.4600\ncurrent episode reward: 129.0000\nepisodes: 1860\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27778.9 seconds (7.72 hours)\n\nTimestep: 6190000\nmean reward (100 episodes): 103.0100\nbest mean reward: 103.0100\ncurrent episode reward: 130.0000\nepisodes: 1863\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27826.2 seconds (7.73 hours)\n\nTimestep: 6200000\nmean reward (100 episodes): 104.0400\nbest mean reward: 104.0400\ncurrent episode reward: 160.0000\nepisodes: 1866\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27872.5 seconds (7.74 hours)\n\nTimestep: 6210000\nmean reward (100 episodes): 103.5400\nbest mean reward: 104.1600\ncurrent episode reward: 99.0000\nepisodes: 1869\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27919.3 seconds (7.76 hours)\n\nTimestep: 6220000\nmean reward (100 episodes): 103.8200\nbest mean reward: 104.1600\ncurrent episode reward: 96.0000\nepisodes: 1872\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27965.9 seconds (7.77 hours)\n\nTimestep: 6230000\nmean reward (100 episodes): 100.9800\nbest mean reward: 104.1600\ncurrent episode reward: 7.0000\nepisodes: 1875\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28012.5 seconds (7.78 hours)\n\nTimestep: 6240000\nmean reward (100 episodes): 99.4100\nbest mean reward: 104.1600\ncurrent episode reward: 104.0000\nepisodes: 1878\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28058.6 seconds (7.79 hours)\n\nTimestep: 6250000\nmean reward (100 episodes): 99.5400\nbest mean reward: 104.1600\ncurrent episode reward: 131.0000\nepisodes: 1881\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28105.0 seconds (7.81 hours)\n\nTimestep: 6260000\nmean reward (100 episodes): 99.2400\nbest mean reward: 104.1600\ncurrent episode reward: 102.0000\nepisodes: 1884\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28151.1 seconds (7.82 hours)\n\nTimestep: 6270000\nmean reward (100 episodes): 98.9200\nbest mean reward: 104.1600\ncurrent episode reward: 94.0000\nepisodes: 1887\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28197.1 seconds (7.83 hours)\n\nTimestep: 6280000\nmean reward (100 episodes): 99.1800\nbest mean reward: 104.1600\ncurrent episode reward: 99.0000\nepisodes: 1890\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28243.2 seconds (7.85 hours)\n\nTimestep: 6290000\nmean reward (100 episodes): 98.4000\nbest mean reward: 104.1600\ncurrent episode reward: 63.0000\nepisodes: 1893\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28289.6 seconds (7.86 hours)\n\nTimestep: 6300000\nmean reward (100 episodes): 99.8600\nbest mean reward: 104.1600\ncurrent episode reward: 173.0000\nepisodes: 1896\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28335.5 seconds (7.87 hours)\n\nTimestep: 6310000\nmean reward (100 episodes): 100.2000\nbest mean reward: 104.1600\ncurrent episode reward: 111.0000\nepisodes: 1899\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28382.2 seconds (7.88 hours)\n\nTimestep: 6320000\nmean reward (100 episodes): 99.9700\nbest mean reward: 104.1600\ncurrent episode reward: 113.0000\nepisodes: 1902\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28428.3 seconds (7.90 hours)\n\nTimestep: 6330000\nmean reward (100 episodes): 100.3500\nbest mean reward: 104.1600\ncurrent episode reward: 118.0000\nepisodes: 1905\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28474.1 seconds (7.91 hours)\n\nTimestep: 6340000\nmean reward (100 episodes): 100.8200\nbest mean reward: 104.1600\ncurrent episode reward: 119.0000\nepisodes: 1908\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28520.1 seconds (7.92 hours)\n\nTimestep: 6350000\nmean reward (100 episodes): 103.4200\nbest mean reward: 104.1600\ncurrent episode reward: 82.0000\nepisodes: 1911\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28567.0 seconds (7.94 hours)\n\nTimestep: 6360000\nmean reward (100 episodes): 103.8500\nbest mean reward: 104.1600\ncurrent episode reward: 166.0000\nepisodes: 1914\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28614.5 seconds (7.95 hours)\n\nTimestep: 6370000\nmean reward (100 episodes): 106.0200\nbest mean reward: 106.0200\ncurrent episode reward: 132.0000\nepisodes: 1917\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28660.8 seconds (7.96 hours)\n\nTimestep: 6380000\nmean reward (100 episodes): 107.9400\nbest mean reward: 107.9400\ncurrent episode reward: 174.0000\nepisodes: 1920\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28707.9 seconds (7.97 hours)\n\nTimestep: 6390000\nmean reward (100 episodes): 109.1600\nbest mean reward: 109.2400\ncurrent episode reward: 127.0000\nepisodes: 1923\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28754.2 seconds (7.99 hours)\n\nTimestep: 6400000\nmean reward (100 episodes): 109.2100\nbest mean reward: 109.2400\ncurrent episode reward: 129.0000\nepisodes: 1926\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28800.7 seconds (8.00 hours)\n\nTimestep: 6410000\nmean reward (100 episodes): 110.6000\nbest mean reward: 110.6000\ncurrent episode reward: 110.0000\nepisodes: 1929\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28846.4 seconds (8.01 hours)\n\nTimestep: 6420000\nmean reward (100 episodes): 112.1400\nbest mean reward: 112.1400\ncurrent episode reward: 172.0000\nepisodes: 1932\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28892.3 seconds (8.03 hours)\n\nTimestep: 6430000\nmean reward (100 episodes): 113.5000\nbest mean reward: 113.5000\ncurrent episode reward: 123.0000\nepisodes: 1935\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28938.5 seconds (8.04 hours)\n\nTimestep: 6440000\nmean reward (100 episodes): 114.6600\nbest mean reward: 114.6600\ncurrent episode reward: 175.0000\nepisodes: 1938\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28984.3 seconds (8.05 hours)\n\nTimestep: 6450000\nmean reward (100 episodes): 116.5300\nbest mean reward: 116.5300\ncurrent episode reward: 140.0000\nepisodes: 1941\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29031.0 seconds (8.06 hours)\n\nTimestep: 6460000\nmean reward (100 episodes): 117.6400\nbest mean reward: 117.6400\ncurrent episode reward: 109.0000\nepisodes: 1944\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29077.2 seconds (8.08 hours)\n\nTimestep: 6470000\nmean reward (100 episodes): 119.3900\nbest mean reward: 119.3900\ncurrent episode reward: 185.0000\nepisodes: 1947\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29123.7 seconds (8.09 hours)\n\nTimestep: 6480000\nmean reward (100 episodes): 120.4600\nbest mean reward: 120.4600\ncurrent episode reward: 175.0000\nepisodes: 1950\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29170.1 seconds (8.10 hours)\n\nTimestep: 6490000\nmean reward (100 episodes): 123.8500\nbest mean reward: 123.8500\ncurrent episode reward: 174.0000\nepisodes: 1953\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29216.6 seconds (8.12 hours)\n\nTimestep: 6500000\nmean reward (100 episodes): 123.7900\nbest mean reward: 123.9000\ncurrent episode reward: 139.0000\nepisodes: 1956\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29264.2 seconds (8.13 hours)\n\nTimestep: 6510000\nmean reward (100 episodes): 124.7600\nbest mean reward: 124.7600\ncurrent episode reward: 165.0000\nepisodes: 1959\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29310.1 seconds (8.14 hours)\n\nTimestep: 6520000\nmean reward (100 episodes): 126.8800\nbest mean reward: 126.8800\ncurrent episode reward: 166.0000\nepisodes: 1962\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29356.8 seconds (8.15 hours)\n\nTimestep: 6530000\nmean reward (100 episodes): 128.2500\nbest mean reward: 128.2500\ncurrent episode reward: 272.0000\nepisodes: 1964\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29403.5 seconds (8.17 hours)\n\nTimestep: 6540000\nmean reward (100 episodes): 130.6600\nbest mean reward: 130.8900\ncurrent episode reward: 137.0000\nepisodes: 1966\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29450.1 seconds (8.18 hours)\n\nTimestep: 6550000\nmean reward (100 episodes): 133.9100\nbest mean reward: 133.9100\ncurrent episode reward: 351.0000\nepisodes: 1968\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29497.0 seconds (8.19 hours)\n\nTimestep: 6560000\nmean reward (100 episodes): 134.9000\nbest mean reward: 134.9000\ncurrent episode reward: 153.0000\nepisodes: 1970\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29543.1 seconds (8.21 hours)\n\nTimestep: 6570000\nmean reward (100 episodes): 138.8800\nbest mean reward: 138.8800\ncurrent episode reward: 180.0000\nepisodes: 1973\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29590.1 seconds (8.22 hours)\n\nTimestep: 6580000\nmean reward (100 episodes): 143.5300\nbest mean reward: 143.5300\ncurrent episode reward: 196.0000\nepisodes: 1976\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29636.3 seconds (8.23 hours)\n\nTimestep: 6590000\nmean reward (100 episodes): 145.9900\nbest mean reward: 145.9900\ncurrent episode reward: 199.0000\nepisodes: 1979\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29682.5 seconds (8.25 hours)\n\nTimestep: 6600000\nmean reward (100 episodes): 144.5900\nbest mean reward: 145.9900\ncurrent episode reward: 153.0000\nepisodes: 1982\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29729.7 seconds (8.26 hours)\n\nTimestep: 6610000\nmean reward (100 episodes): 146.3600\nbest mean reward: 146.3600\ncurrent episode reward: 136.0000\nepisodes: 1984\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29776.9 seconds (8.27 hours)\n\nTimestep: 6620000\nmean reward (100 episodes): 147.8200\nbest mean reward: 147.8700\ncurrent episode reward: 174.0000\nepisodes: 1986\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29822.6 seconds (8.28 hours)\n\nTimestep: 6630000\nmean reward (100 episodes): 148.9400\nbest mean reward: 148.9400\ncurrent episode reward: 157.0000\nepisodes: 1989\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29869.8 seconds (8.30 hours)\n\nTimestep: 6640000\nmean reward (100 episodes): 151.5900\nbest mean reward: 151.5900\ncurrent episode reward: 364.0000\nepisodes: 1990\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29916.2 seconds (8.31 hours)\n\nTimestep: 6650000\nmean reward (100 episodes): 156.0400\nbest mean reward: 156.0400\ncurrent episode reward: 313.0000\nepisodes: 1992\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29963.1 seconds (8.32 hours)\n\nTimestep: 6660000\nmean reward (100 episodes): 159.0600\nbest mean reward: 159.0600\ncurrent episode reward: 187.0000\nepisodes: 1994\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30010.1 seconds (8.34 hours)\n\nTimestep: 6670000\nmean reward (100 episodes): 158.1700\nbest mean reward: 159.0700\ncurrent episode reward: 83.0000\nepisodes: 1996\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30056.5 seconds (8.35 hours)\n\nTimestep: 6680000\nmean reward (100 episodes): 160.0000\nbest mean reward: 160.0000\ncurrent episode reward: 171.0000\nepisodes: 1998\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30103.2 seconds (8.36 hours)\n\nTimestep: 6690000\nmean reward (100 episodes): 162.5900\nbest mean reward: 162.5900\ncurrent episode reward: 120.0000\nepisodes: 2001\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30150.3 seconds (8.38 hours)\n\nTimestep: 6700000\nmean reward (100 episodes): 165.6800\nbest mean reward: 165.6800\ncurrent episode reward: 325.0000\nepisodes: 2003\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30196.6 seconds (8.39 hours)\n\nTimestep: 6710000\nmean reward (100 episodes): 168.7100\nbest mean reward: 168.7100\ncurrent episode reward: 407.0000\nepisodes: 2005\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30244.2 seconds (8.40 hours)\n\nTimestep: 6720000\nmean reward (100 episodes): 172.5900\nbest mean reward: 172.5900\ncurrent episode reward: 385.0000\nepisodes: 2007\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30290.8 seconds (8.41 hours)\n\nTimestep: 6730000\nmean reward (100 episodes): 173.5000\nbest mean reward: 173.5000\ncurrent episode reward: 150.0000\nepisodes: 2009\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30337.2 seconds (8.43 hours)\n\nTimestep: 6740000\nmean reward (100 episodes): 175.5200\nbest mean reward: 175.5200\ncurrent episode reward: 179.0000\nepisodes: 2011\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30383.4 seconds (8.44 hours)\n\nTimestep: 6750000\nmean reward (100 episodes): 175.2200\nbest mean reward: 177.1800\ncurrent episode reward: 84.0000\nepisodes: 2014\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30429.6 seconds (8.45 hours)\n\nTimestep: 6760000\nmean reward (100 episodes): 174.9500\nbest mean reward: 177.1800\ncurrent episode reward: 165.0000\nepisodes: 2017\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30477.0 seconds (8.47 hours)\n\nTimestep: 6770000\nmean reward (100 episodes): 177.1300\nbest mean reward: 177.1800\ncurrent episode reward: 356.0000\nepisodes: 2019\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30523.1 seconds (8.48 hours)\n\nTimestep: 6780000\nmean reward (100 episodes): 179.1100\nbest mean reward: 179.1100\ncurrent episode reward: 405.0000\nepisodes: 2021\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30569.8 seconds (8.49 hours)\n\nTimestep: 6790000\nmean reward (100 episodes): 182.0300\nbest mean reward: 182.0300\ncurrent episode reward: 172.0000\nepisodes: 2023\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30615.5 seconds (8.50 hours)\n\nTimestep: 6800000\nmean reward (100 episodes): 183.9800\nbest mean reward: 183.9800\ncurrent episode reward: 270.0000\nepisodes: 2025\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30662.0 seconds (8.52 hours)\n\nTimestep: 6810000\nmean reward (100 episodes): 186.4800\nbest mean reward: 186.4800\ncurrent episode reward: 181.0000\nepisodes: 2027\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30708.6 seconds (8.53 hours)\n\nTimestep: 6820000\nmean reward (100 episodes): 188.5100\nbest mean reward: 188.5100\ncurrent episode reward: 128.0000\nepisodes: 2029\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30754.7 seconds (8.54 hours)\n\nTimestep: 6830000\nmean reward (100 episodes): 189.7800\nbest mean reward: 190.3300\ncurrent episode reward: 120.0000\nepisodes: 2031\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30800.7 seconds (8.56 hours)\n\nTimestep: 6840000\nmean reward (100 episodes): 190.4300\nbest mean reward: 190.4300\ncurrent episode reward: 170.0000\nepisodes: 2034\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30847.2 seconds (8.57 hours)\n\nTimestep: 6850000\nmean reward (100 episodes): 192.8000\nbest mean reward: 192.8000\ncurrent episode reward: 197.0000\nepisodes: 2036\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30893.8 seconds (8.58 hours)\n\nTimestep: 6860000\nmean reward (100 episodes): 195.4100\nbest mean reward: 195.4900\ncurrent episode reward: 167.0000\nepisodes: 2038\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30940.9 seconds (8.59 hours)\n\nTimestep: 6870000\nmean reward (100 episodes): 197.0100\nbest mean reward: 197.0100\ncurrent episode reward: 345.0000\nepisodes: 2039\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30987.7 seconds (8.61 hours)\n\nTimestep: 6880000\nmean reward (100 episodes): 199.7600\nbest mean reward: 199.7600\ncurrent episode reward: 174.0000\nepisodes: 2041\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31034.2 seconds (8.62 hours)\n\nTimestep: 6890000\nmean reward (100 episodes): 202.8200\nbest mean reward: 202.8200\ncurrent episode reward: 150.0000\nepisodes: 2044\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31081.0 seconds (8.63 hours)\n\nTimestep: 6900000\nmean reward (100 episodes): 204.4600\nbest mean reward: 204.4600\ncurrent episode reward: 164.0000\nepisodes: 2046\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31127.4 seconds (8.65 hours)\n\nTimestep: 6910000\nmean reward (100 episodes): 205.1200\nbest mean reward: 205.1200\ncurrent episode reward: 251.0000\nepisodes: 2047\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31174.4 seconds (8.66 hours)\n\nTimestep: 6920000\nmean reward (100 episodes): 209.4200\nbest mean reward: 209.4200\ncurrent episode reward: 270.0000\nepisodes: 2049\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31221.3 seconds (8.67 hours)\n\nTimestep: 6930000\nmean reward (100 episodes): 211.9400\nbest mean reward: 211.9400\ncurrent episode reward: 155.0000\nepisodes: 2051\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31267.5 seconds (8.69 hours)\n\nTimestep: 6940000\nmean reward (100 episodes): 212.5700\nbest mean reward: 212.5700\ncurrent episode reward: 175.0000\nepisodes: 2054\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31314.6 seconds (8.70 hours)\n\nTimestep: 6950000\nmean reward (100 episodes): 215.0900\nbest mean reward: 215.0900\ncurrent episode reward: 368.0000\nepisodes: 2056\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31361.3 seconds (8.71 hours)\n\nTimestep: 6960000\nmean reward (100 episodes): 216.7700\nbest mean reward: 216.7700\ncurrent episode reward: 159.0000\nepisodes: 2058\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31407.9 seconds (8.72 hours)\n\nTimestep: 6970000\nmean reward (100 episodes): 216.4500\nbest mean reward: 217.1100\ncurrent episode reward: 177.0000\nepisodes: 2061\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31453.5 seconds (8.74 hours)\n\nTimestep: 6980000\nmean reward (100 episodes): 215.9800\nbest mean reward: 217.1100\ncurrent episode reward: 134.0000\nepisodes: 2063\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31499.9 seconds (8.75 hours)\n\nTimestep: 6990000\nmean reward (100 episodes): 214.3000\nbest mean reward: 217.1100\ncurrent episode reward: 114.0000\nepisodes: 2066\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31546.2 seconds (8.76 hours)\n\nTimestep: 7000000\nmean reward (100 episodes): 214.3700\nbest mean reward: 217.1100\ncurrent episode reward: 160.0000\nepisodes: 2068\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31593.1 seconds (8.78 hours)\n\nTimestep: 7010000\nmean reward (100 episodes): 217.7600\nbest mean reward: 217.7600\ncurrent episode reward: 477.0000\nepisodes: 2069\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31640.1 seconds (8.79 hours)\n\nTimestep: 7020000\nmean reward (100 episodes): 218.3000\nbest mean reward: 220.0800\ncurrent episode reward: 168.0000\nepisodes: 2072\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31686.3 seconds (8.80 hours)\n\nTimestep: 7030000\nmean reward (100 episodes): 217.8400\nbest mean reward: 220.0800\ncurrent episode reward: 188.0000\nepisodes: 2074\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31733.0 seconds (8.81 hours)\n\nTimestep: 7040000\nmean reward (100 episodes): 221.2200\nbest mean reward: 221.2200\ncurrent episode reward: 330.0000\nepisodes: 2076\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31779.6 seconds (8.83 hours)\n\nTimestep: 7050000\nmean reward (100 episodes): 223.0900\nbest mean reward: 223.0900\ncurrent episode reward: 353.0000\nepisodes: 2077\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31826.1 seconds (8.84 hours)\n\nTimestep: 7060000\nmean reward (100 episodes): 228.5900\nbest mean reward: 228.5900\ncurrent episode reward: 424.0000\nepisodes: 2079\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31872.4 seconds (8.85 hours)\n\nTimestep: 7070000\nmean reward (100 episodes): 232.0700\nbest mean reward: 232.0700\ncurrent episode reward: 376.0000\nepisodes: 2080\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31919.4 seconds (8.87 hours)\n\nTimestep: 7080000\nmean reward (100 episodes): 235.0800\nbest mean reward: 235.0800\ncurrent episode reward: 180.0000\nepisodes: 2082\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31966.6 seconds (8.88 hours)\n\nTimestep: 7090000\nmean reward (100 episodes): 235.8800\nbest mean reward: 236.5400\ncurrent episode reward: 191.0000\nepisodes: 2085\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32012.8 seconds (8.89 hours)\n\nTimestep: 7100000\nmean reward (100 episodes): 238.0600\nbest mean reward: 238.0600\ncurrent episode reward: 381.0000\nepisodes: 2087\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32059.5 seconds (8.91 hours)\n\nTimestep: 7110000\nmean reward (100 episodes): 240.5500\nbest mean reward: 240.5500\ncurrent episode reward: 358.0000\nepisodes: 2088\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32106.6 seconds (8.92 hours)\n\nTimestep: 7120000\nmean reward (100 episodes): 243.8000\nbest mean reward: 243.8000\ncurrent episode reward: 450.0000\nepisodes: 2090\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32154.0 seconds (8.93 hours)\n\nTimestep: 7130000\nmean reward (100 episodes): 242.8900\nbest mean reward: 243.8000\ncurrent episode reward: 360.0000\nepisodes: 2092\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32201.5 seconds (8.94 hours)\n\nTimestep: 7140000\nmean reward (100 episodes): 243.6400\nbest mean reward: 243.8200\ncurrent episode reward: 169.0000\nepisodes: 2094\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32247.8 seconds (8.96 hours)\n\nTimestep: 7150000\nmean reward (100 episodes): 243.4600\nbest mean reward: 244.4000\ncurrent episode reward: 184.0000\nepisodes: 2097\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32293.8 seconds (8.97 hours)\n\nTimestep: 7160000\nmean reward (100 episodes): 244.9300\nbest mean reward: 244.9300\ncurrent episode reward: 318.0000\nepisodes: 2098\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32340.7 seconds (8.98 hours)\n\nTimestep: 7170000\nmean reward (100 episodes): 245.3900\nbest mean reward: 245.3900\ncurrent episode reward: 193.0000\nepisodes: 2100\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32386.5 seconds (9.00 hours)\n\nTimestep: 7180000\nmean reward (100 episodes): 247.9400\nbest mean reward: 248.1000\ncurrent episode reward: 158.0000\nepisodes: 2102\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32432.8 seconds (9.01 hours)\n\nTimestep: 7190000\nmean reward (100 episodes): 249.3000\nbest mean reward: 249.3000\ncurrent episode reward: 175.0000\nepisodes: 2104\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32480.0 seconds (9.02 hours)\n\nTimestep: 7200000\nmean reward (100 episodes): 251.7500\nbest mean reward: 251.7500\ncurrent episode reward: 465.0000\nepisodes: 2106\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32526.3 seconds (9.04 hours)\n\nTimestep: 7210000\nmean reward (100 episodes): 252.3800\nbest mean reward: 252.4200\ncurrent episode reward: 179.0000\nepisodes: 2108\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32572.4 seconds (9.05 hours)\n\nTimestep: 7220000\nmean reward (100 episodes): 253.6000\nbest mean reward: 253.6000\ncurrent episode reward: 388.0000\nepisodes: 2110\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32619.3 seconds (9.06 hours)\n\nTimestep: 7230000\nmean reward (100 episodes): 254.7300\nbest mean reward: 254.7300\ncurrent episode reward: 292.0000\nepisodes: 2111\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32665.3 seconds (9.07 hours)\n\nTimestep: 7240000\nmean reward (100 episodes): 259.0500\nbest mean reward: 259.0500\ncurrent episode reward: 287.0000\nepisodes: 2113\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32711.9 seconds (9.09 hours)\n\nTimestep: 7250000\nmean reward (100 episodes): 263.0900\nbest mean reward: 263.0900\ncurrent episode reward: 428.0000\nepisodes: 2115\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32758.7 seconds (9.10 hours)\n\nTimestep: 7260000\nmean reward (100 episodes): 265.8700\nbest mean reward: 265.8700\ncurrent episode reward: 387.0000\nepisodes: 2116\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32805.9 seconds (9.11 hours)\n\nTimestep: 7270000\nmean reward (100 episodes): 270.8100\nbest mean reward: 270.8100\ncurrent episode reward: 383.0000\nepisodes: 2118\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32853.1 seconds (9.13 hours)\n\nTimestep: 7280000\nmean reward (100 episodes): 271.2200\nbest mean reward: 271.2200\ncurrent episode reward: 186.0000\nepisodes: 2120\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32900.1 seconds (9.14 hours)\n\nTimestep: 7290000\nmean reward (100 episodes): 271.5400\nbest mean reward: 271.5400\ncurrent episode reward: 437.0000\nepisodes: 2121\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32946.5 seconds (9.15 hours)\n\nTimestep: 7300000\nmean reward (100 episodes): 273.7300\nbest mean reward: 273.7300\ncurrent episode reward: 356.0000\nepisodes: 2124\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32992.9 seconds (9.16 hours)\n\nTimestep: 7310000\nmean reward (100 episodes): 273.8300\nbest mean reward: 273.8300\ncurrent episode reward: 457.0000\nepisodes: 2126\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33039.0 seconds (9.18 hours)\n\nTimestep: 7320000\nmean reward (100 episodes): 275.7700\nbest mean reward: 275.7700\ncurrent episode reward: 375.0000\nepisodes: 2127\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33085.7 seconds (9.19 hours)\n\nTimestep: 7330000\nmean reward (100 episodes): 275.5200\nbest mean reward: 275.7700\ncurrent episode reward: 139.0000\nepisodes: 2129\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33131.6 seconds (9.20 hours)\n\nTimestep: 7340000\nmean reward (100 episodes): 278.8400\nbest mean reward: 278.8400\ncurrent episode reward: 377.0000\nepisodes: 2131\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33178.0 seconds (9.22 hours)\n\nTimestep: 7350000\nmean reward (100 episodes): 281.4200\nbest mean reward: 281.4200\ncurrent episode reward: 374.0000\nepisodes: 2132\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33224.9 seconds (9.23 hours)\n\nTimestep: 7360000\nmean reward (100 episodes): 283.0500\nbest mean reward: 283.2400\ncurrent episode reward: 151.0000\nepisodes: 2134\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33272.0 seconds (9.24 hours)\n\nTimestep: 7370000\nmean reward (100 episodes): 285.7100\nbest mean reward: 285.7100\ncurrent episode reward: 355.0000\nepisodes: 2136\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33318.9 seconds (9.26 hours)\n\nTimestep: 7380000\nmean reward (100 episodes): 284.5600\nbest mean reward: 285.7100\ncurrent episode reward: 289.0000\nepisodes: 2137\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33365.1 seconds (9.27 hours)\n\nTimestep: 7390000\nmean reward (100 episodes): 287.0600\nbest mean reward: 287.0600\ncurrent episode reward: 373.0000\nepisodes: 2139\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33411.6 seconds (9.28 hours)\n\nTimestep: 7400000\nmean reward (100 episodes): 287.4600\nbest mean reward: 287.4600\ncurrent episode reward: 407.0000\nepisodes: 2140\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33458.4 seconds (9.29 hours)\n\nTimestep: 7410000\nmean reward (100 episodes): 288.2300\nbest mean reward: 289.9700\ncurrent episode reward: 185.0000\nepisodes: 2142\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33505.6 seconds (9.31 hours)\n\nTimestep: 7420000\nmean reward (100 episodes): 292.5800\nbest mean reward: 292.5800\ncurrent episode reward: 382.0000\nepisodes: 2144\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33552.3 seconds (9.32 hours)\n\nTimestep: 7430000\nmean reward (100 episodes): 294.0700\nbest mean reward: 294.0700\ncurrent episode reward: 450.0000\nepisodes: 2146\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33599.0 seconds (9.33 hours)\n\nTimestep: 7440000\nmean reward (100 episodes): 294.7700\nbest mean reward: 294.7700\ncurrent episode reward: 321.0000\nepisodes: 2147\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33645.8 seconds (9.35 hours)\n\nTimestep: 7450000\nmean reward (100 episodes): 294.3600\nbest mean reward: 295.1900\ncurrent episode reward: 187.0000\nepisodes: 2149\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33691.7 seconds (9.36 hours)\n\nTimestep: 7460000\nmean reward (100 episodes): 294.0000\nbest mean reward: 295.1900\ncurrent episode reward: 108.0000\nepisodes: 2151\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33738.3 seconds (9.37 hours)\n\nTimestep: 7470000\nmean reward (100 episodes): 298.5200\nbest mean reward: 298.5200\ncurrent episode reward: 443.0000\nepisodes: 2153\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33784.4 seconds (9.38 hours)\n\nTimestep: 7480000\nmean reward (100 episodes): 300.9400\nbest mean reward: 300.9400\ncurrent episode reward: 417.0000\nepisodes: 2154\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33831.3 seconds (9.40 hours)\n\nTimestep: 7490000\nmean reward (100 episodes): 303.1600\nbest mean reward: 303.4300\ncurrent episode reward: 341.0000\nepisodes: 2156\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33878.1 seconds (9.41 hours)\n\nTimestep: 7500000\nmean reward (100 episodes): 302.4200\nbest mean reward: 303.4300\ncurrent episode reward: 185.0000\nepisodes: 2158\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33925.4 seconds (9.42 hours)\n\nTimestep: 7510000\nmean reward (100 episodes): 305.8000\nbest mean reward: 305.8000\ncurrent episode reward: 199.0000\nepisodes: 2160\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33971.6 seconds (9.44 hours)\n\nTimestep: 7520000\nmean reward (100 episodes): 311.0300\nbest mean reward: 311.0300\ncurrent episode reward: 447.0000\nepisodes: 2162\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34018.8 seconds (9.45 hours)\n\nTimestep: 7530000\nmean reward (100 episodes): 313.3100\nbest mean reward: 313.3100\ncurrent episode reward: 362.0000\nepisodes: 2163\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34065.5 seconds (9.46 hours)\n\nTimestep: 7540000\nmean reward (100 episodes): 314.5600\nbest mean reward: 314.5600\ncurrent episode reward: 195.0000\nepisodes: 2165\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34112.2 seconds (9.48 hours)\n\nTimestep: 7550000\nmean reward (100 episodes): 316.5300\nbest mean reward: 318.0700\ncurrent episode reward: 194.0000\nepisodes: 2167\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34159.4 seconds (9.49 hours)\n\nTimestep: 7560000\nmean reward (100 episodes): 317.2600\nbest mean reward: 318.8000\ncurrent episode reward: 323.0000\nepisodes: 2169\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34206.8 seconds (9.50 hours)\n\nTimestep: 7570000\nmean reward (100 episodes): 317.2100\nbest mean reward: 318.8000\ncurrent episode reward: 146.0000\nepisodes: 2171\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34252.5 seconds (9.51 hours)\n\nTimestep: 7580000\nmean reward (100 episodes): 320.5900\nbest mean reward: 320.5900\ncurrent episode reward: 432.0000\nepisodes: 2173\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34298.5 seconds (9.53 hours)\n\nTimestep: 7590000\nmean reward (100 episodes): 318.7800\nbest mean reward: 320.7000\ncurrent episode reward: 148.0000\nepisodes: 2175\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34345.2 seconds (9.54 hours)\n\nTimestep: 7600000\nmean reward (100 episodes): 313.8000\nbest mean reward: 320.7000\ncurrent episode reward: 169.0000\nepisodes: 2178\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34391.5 seconds (9.55 hours)\n\nTimestep: 7610000\nmean reward (100 episodes): 311.6300\nbest mean reward: 320.7000\ncurrent episode reward: 185.0000\nepisodes: 2180\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34437.7 seconds (9.57 hours)\n\nTimestep: 7620000\nmean reward (100 episodes): 312.0900\nbest mean reward: 320.7000\ncurrent episode reward: 392.0000\nepisodes: 2181\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34483.9 seconds (9.58 hours)\n\nTimestep: 7630000\nmean reward (100 episodes): 314.2700\nbest mean reward: 320.7000\ncurrent episode reward: 414.0000\nepisodes: 2183\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34530.7 seconds (9.59 hours)\n\nTimestep: 7640000\nmean reward (100 episodes): 317.5400\nbest mean reward: 320.7000\ncurrent episode reward: 483.0000\nepisodes: 2184\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34576.8 seconds (9.60 hours)\n\nTimestep: 7650000\nmean reward (100 episodes): 320.3700\nbest mean reward: 320.7000\ncurrent episode reward: 474.0000\nepisodes: 2185\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34623.1 seconds (9.62 hours)\n\nTimestep: 7660000\nmean reward (100 episodes): 323.1600\nbest mean reward: 325.3400\ncurrent episode reward: 163.0000\nepisodes: 2187\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34669.8 seconds (9.63 hours)\n\nTimestep: 7670000\nmean reward (100 episodes): 324.3500\nbest mean reward: 325.3400\ncurrent episode reward: 438.0000\nepisodes: 2189\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34715.4 seconds (9.64 hours)\n\nTimestep: 7680000\nmean reward (100 episodes): 318.2900\nbest mean reward: 325.3400\ncurrent episode reward: 183.0000\nepisodes: 2192\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34761.4 seconds (9.66 hours)\n\nTimestep: 7690000\nmean reward (100 episodes): 317.7300\nbest mean reward: 325.3400\ncurrent episode reward: 391.0000\nepisodes: 2194\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34807.3 seconds (9.67 hours)\n\nTimestep: 7700000\nmean reward (100 episodes): 319.1300\nbest mean reward: 325.3400\ncurrent episode reward: 188.0000\nepisodes: 2196\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34854.1 seconds (9.68 hours)\n\nTimestep: 7710000\nmean reward (100 episodes): 320.0100\nbest mean reward: 325.3400\ncurrent episode reward: 195.0000\nepisodes: 2198\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34901.2 seconds (9.69 hours)\n\nTimestep: 7720000\nmean reward (100 episodes): 320.1900\nbest mean reward: 325.3400\ncurrent episode reward: 380.0000\nepisodes: 2199\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34947.1 seconds (9.71 hours)\n\nTimestep: 7730000\nmean reward (100 episodes): 320.2800\nbest mean reward: 325.3400\ncurrent episode reward: 176.0000\nepisodes: 2202\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34993.9 seconds (9.72 hours)\n\nTimestep: 7740000\nmean reward (100 episodes): 319.7600\nbest mean reward: 325.3400\ncurrent episode reward: 368.0000\nepisodes: 2203\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35041.0 seconds (9.73 hours)\n\nTimestep: 7750000\nmean reward (100 episodes): 322.8600\nbest mean reward: 325.3400\ncurrent episode reward: 397.0000\nepisodes: 2205\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35088.3 seconds (9.75 hours)\n\nTimestep: 7760000\nmean reward (100 episodes): 322.4100\nbest mean reward: 325.3400\ncurrent episode reward: 420.0000\nepisodes: 2206\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35134.9 seconds (9.76 hours)\n\nTimestep: 7770000\nmean reward (100 episodes): 323.9100\nbest mean reward: 325.3400\ncurrent episode reward: 385.0000\nepisodes: 2208\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35181.9 seconds (9.77 hours)\n\nTimestep: 7780000\nmean reward (100 episodes): 324.1000\nbest mean reward: 325.3400\ncurrent episode reward: 185.0000\nepisodes: 2209\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35228.9 seconds (9.79 hours)\n\nTimestep: 7790000\nmean reward (100 episodes): 328.1000\nbest mean reward: 328.1000\ncurrent episode reward: 396.0000\nepisodes: 2211\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35276.6 seconds (9.80 hours)\n\nTimestep: 7800000\nmean reward (100 episodes): 324.8100\nbest mean reward: 328.1000\ncurrent episode reward: 161.0000\nepisodes: 2214\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35322.4 seconds (9.81 hours)\n\nTimestep: 7810000\nmean reward (100 episodes): 324.8400\nbest mean reward: 328.1000\ncurrent episode reward: 431.0000\nepisodes: 2215\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35369.6 seconds (9.82 hours)\n\nTimestep: 7820000\nmean reward (100 episodes): 325.0200\nbest mean reward: 328.1000\ncurrent episode reward: 411.0000\nepisodes: 2217\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35416.0 seconds (9.84 hours)\n\nTimestep: 7830000\nmean reward (100 episodes): 325.7500\nbest mean reward: 328.1000\ncurrent episode reward: 456.0000\nepisodes: 2218\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35462.6 seconds (9.85 hours)\n\nTimestep: 7840000\nmean reward (100 episodes): 324.6600\nbest mean reward: 328.1000\ncurrent episode reward: 170.0000\nepisodes: 2221\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35508.8 seconds (9.86 hours)\n\nTimestep: 7850000\nmean reward (100 episodes): 324.4900\nbest mean reward: 328.1000\ncurrent episode reward: 325.0000\nepisodes: 2223\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35555.7 seconds (9.88 hours)\n\nTimestep: 7860000\nmean reward (100 episodes): 318.4700\nbest mean reward: 328.1000\ncurrent episode reward: 153.0000\nepisodes: 2226\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35601.8 seconds (9.89 hours)\n\nTimestep: 7870000\nmean reward (100 episodes): 315.4300\nbest mean reward: 328.1000\ncurrent episode reward: 128.0000\nepisodes: 2229\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35648.3 seconds (9.90 hours)\n\nTimestep: 7880000\nmean reward (100 episodes): 315.1000\nbest mean reward: 328.1000\ncurrent episode reward: 359.0000\nepisodes: 2230\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35695.2 seconds (9.92 hours)\n\nTimestep: 7890000\nmean reward (100 episodes): 313.4600\nbest mean reward: 328.1000\ncurrent episode reward: 189.0000\nepisodes: 2232\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35742.7 seconds (9.93 hours)\n\nTimestep: 7900000\nmean reward (100 episodes): 316.4500\nbest mean reward: 328.1000\ncurrent episode reward: 424.0000\nepisodes: 2234\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35789.4 seconds (9.94 hours)\n\nTimestep: 7910000\nmean reward (100 episodes): 311.1200\nbest mean reward: 328.1000\ncurrent episode reward: 193.0000\nepisodes: 2237\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35836.0 seconds (9.95 hours)\n\nTimestep: 7920000\nmean reward (100 episodes): 312.1800\nbest mean reward: 328.1000\ncurrent episode reward: 495.0000\nepisodes: 2238\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35882.3 seconds (9.97 hours)\n\nTimestep: 7930000\nmean reward (100 episodes): 314.7200\nbest mean reward: 328.1000\ncurrent episode reward: 627.0000\nepisodes: 2239\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35929.7 seconds (9.98 hours)\n\nTimestep: 7940000\nmean reward (100 episodes): 315.1100\nbest mean reward: 328.1000\ncurrent episode reward: 413.0000\nepisodes: 2241\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35976.3 seconds (9.99 hours)\n\nTimestep: 7950000\nmean reward (100 episodes): 314.7000\nbest mean reward: 328.1000\ncurrent episode reward: 348.0000\nepisodes: 2243\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36022.7 seconds (10.01 hours)\n\nTimestep: 7960000\nmean reward (100 episodes): 311.7500\nbest mean reward: 328.1000\ncurrent episode reward: 111.0000\nepisodes: 2245\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36069.8 seconds (10.02 hours)\n\nTimestep: 7970000\nmean reward (100 episodes): 312.7900\nbest mean reward: 328.1000\ncurrent episode reward: 403.0000\nepisodes: 2247\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36116.4 seconds (10.03 hours)\n\nTimestep: 7980000\nmean reward (100 episodes): 311.7400\nbest mean reward: 328.1000\ncurrent episode reward: 351.0000\nepisodes: 2248\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36163.0 seconds (10.05 hours)\n\nTimestep: 7990000\nmean reward (100 episodes): 314.6200\nbest mean reward: 328.1000\ncurrent episode reward: 461.0000\nepisodes: 2250\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36209.0 seconds (10.06 hours)\n\nTimestep: 8000000\nmean reward (100 episodes): 317.2400\nbest mean reward: 328.1000\ncurrent episode reward: 370.0000\nepisodes: 2251\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36256.0 seconds (10.07 hours)\n\nTimestep: 8010000\nmean reward (100 episodes): 316.7700\nbest mean reward: 328.1000\ncurrent episode reward: 401.0000\nepisodes: 2253\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36302.6 seconds (10.08 hours)\n\nTimestep: 8020000\nmean reward (100 episodes): 316.9000\nbest mean reward: 328.1000\ncurrent episode reward: 430.0000\nepisodes: 2254\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36348.9 seconds (10.10 hours)\n\nTimestep: 8030000\nmean reward (100 episodes): 317.1100\nbest mean reward: 328.1000\ncurrent episode reward: 341.0000\nepisodes: 2256\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36395.2 seconds (10.11 hours)\n\nTimestep: 8040000\nmean reward (100 episodes): 319.3800\nbest mean reward: 328.1000\ncurrent episode reward: 408.0000\nepisodes: 2257\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36442.2 seconds (10.12 hours)\n\nTimestep: 8050000\nmean reward (100 episodes): 321.2600\nbest mean reward: 328.1000\ncurrent episode reward: 436.0000\nepisodes: 2259\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36488.8 seconds (10.14 hours)\n\nTimestep: 8060000\nmean reward (100 episodes): 325.9400\nbest mean reward: 328.1000\ncurrent episode reward: 667.0000\nepisodes: 2260\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36535.9 seconds (10.15 hours)\n\nTimestep: 8070000\nmean reward (100 episodes): 325.8700\nbest mean reward: 328.1000\ncurrent episode reward: 387.0000\nepisodes: 2261\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36582.5 seconds (10.16 hours)\n\nTimestep: 8080000\nmean reward (100 episodes): 326.7500\nbest mean reward: 328.1000\ncurrent episode reward: 407.0000\nepisodes: 2263\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36629.0 seconds (10.17 hours)\n\nTimestep: 8090000\nmean reward (100 episodes): 324.7600\nbest mean reward: 328.1000\ncurrent episode reward: 192.0000\nepisodes: 2264\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36676.3 seconds (10.19 hours)\n\nTimestep: 8100000\nmean reward (100 episodes): 329.4000\nbest mean reward: 329.4000\ncurrent episode reward: 481.0000\nepisodes: 2266\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36723.8 seconds (10.20 hours)\n\nTimestep: 8110000\nmean reward (100 episodes): 332.4000\nbest mean reward: 332.4000\ncurrent episode reward: 494.0000\nepisodes: 2267\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36771.6 seconds (10.21 hours)\n\nTimestep: 8120000\nmean reward (100 episodes): 331.2400\nbest mean reward: 332.5200\ncurrent episode reward: 195.0000\nepisodes: 2269\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36818.1 seconds (10.23 hours)\n\nTimestep: 8130000\nmean reward (100 episodes): 334.3000\nbest mean reward: 334.3000\ncurrent episode reward: 353.0000\nepisodes: 2271\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36865.0 seconds (10.24 hours)\n\nTimestep: 8140000\nmean reward (100 episodes): 334.1900\nbest mean reward: 334.3000\ncurrent episode reward: 441.0000\nepisodes: 2273\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36912.0 seconds (10.25 hours)\n\nTimestep: 8150000\nmean reward (100 episodes): 336.6900\nbest mean reward: 336.6900\ncurrent episode reward: 449.0000\nepisodes: 2274\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36958.9 seconds (10.27 hours)\n\nTimestep: 8160000\nmean reward (100 episodes): 340.6500\nbest mean reward: 340.6500\ncurrent episode reward: 394.0000\nepisodes: 2276\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37004.9 seconds (10.28 hours)\n\nTimestep: 8170000\nmean reward (100 episodes): 343.0400\nbest mean reward: 343.0400\ncurrent episode reward: 409.0000\nepisodes: 2277\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37051.8 seconds (10.29 hours)\n\nTimestep: 8180000\nmean reward (100 episodes): 344.0100\nbest mean reward: 346.3000\ncurrent episode reward: 155.0000\nepisodes: 2280\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37098.7 seconds (10.31 hours)\n\nTimestep: 8190000\nmean reward (100 episodes): 342.1900\nbest mean reward: 346.3000\ncurrent episode reward: 196.0000\nepisodes: 2282\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37145.8 seconds (10.32 hours)\n\nTimestep: 8200000\nmean reward (100 episodes): 336.8600\nbest mean reward: 346.3000\ncurrent episode reward: 177.0000\nepisodes: 2284\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37192.5 seconds (10.33 hours)\n\nTimestep: 8210000\nmean reward (100 episodes): 333.1600\nbest mean reward: 346.3000\ncurrent episode reward: 383.0000\nepisodes: 2286\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37238.5 seconds (10.34 hours)\n\nTimestep: 8220000\nmean reward (100 episodes): 338.3600\nbest mean reward: 346.3000\ncurrent episode reward: 683.0000\nepisodes: 2287\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37284.8 seconds (10.36 hours)\n\nTimestep: 8230000\nmean reward (100 episodes): 341.2200\nbest mean reward: 346.3000\ncurrent episode reward: 721.0000\nepisodes: 2288\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37331.8 seconds (10.37 hours)\n\nTimestep: 8240000\nmean reward (100 episodes): 342.1500\nbest mean reward: 346.3000\ncurrent episode reward: 410.0000\nepisodes: 2290\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37377.8 seconds (10.38 hours)\n\nTimestep: 8250000\nmean reward (100 episodes): 345.4200\nbest mean reward: 346.3000\ncurrent episode reward: 446.0000\nepisodes: 2291\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37424.7 seconds (10.40 hours)\n\nTimestep: 8260000\nmean reward (100 episodes): 351.1400\nbest mean reward: 351.1400\ncurrent episode reward: 453.0000\nepisodes: 2293\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37471.7 seconds (10.41 hours)\n\nTimestep: 8270000\nmean reward (100 episodes): 351.6800\nbest mean reward: 351.6800\ncurrent episode reward: 445.0000\nepisodes: 2294\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37517.8 seconds (10.42 hours)\n\nTimestep: 8280000\nmean reward (100 episodes): 355.2100\nbest mean reward: 355.2100\ncurrent episode reward: 384.0000\nepisodes: 2296\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37564.4 seconds (10.43 hours)\n\nTimestep: 8290000\nmean reward (100 episodes): 355.0000\nbest mean reward: 355.2100\ncurrent episode reward: 374.0000\nepisodes: 2297\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37611.4 seconds (10.45 hours)\n\nTimestep: 8300000\nmean reward (100 episodes): 358.2300\nbest mean reward: 358.2300\ncurrent episode reward: 490.0000\nepisodes: 2299\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37658.3 seconds (10.46 hours)\n\nTimestep: 8310000\nmean reward (100 episodes): 358.3100\nbest mean reward: 358.3100\ncurrent episode reward: 194.0000\nepisodes: 2301\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37704.7 seconds (10.47 hours)\n\nTimestep: 8320000\nmean reward (100 episodes): 356.6500\nbest mean reward: 358.9600\ncurrent episode reward: 137.0000\nepisodes: 2303\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37751.2 seconds (10.49 hours)\n\nTimestep: 8330000\nmean reward (100 episodes): 353.5300\nbest mean reward: 358.9600\ncurrent episode reward: 377.0000\nepisodes: 2305\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37798.2 seconds (10.50 hours)\n\nTimestep: 8340000\nmean reward (100 episodes): 348.8400\nbest mean reward: 358.9600\ncurrent episode reward: 197.0000\nepisodes: 2307\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37845.2 seconds (10.51 hours)\n\nTimestep: 8350000\nmean reward (100 episodes): 349.0400\nbest mean reward: 358.9600\ncurrent episode reward: 166.0000\nepisodes: 2309\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37891.7 seconds (10.53 hours)\n\nTimestep: 8360000\nmean reward (100 episodes): 344.2000\nbest mean reward: 358.9600\ncurrent episode reward: 161.0000\nepisodes: 2311\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37938.3 seconds (10.54 hours)\n\nTimestep: 8370000\nmean reward (100 episodes): 348.1100\nbest mean reward: 358.9600\ncurrent episode reward: 377.0000\nepisodes: 2313\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37984.8 seconds (10.55 hours)\n\nTimestep: 8380000\nmean reward (100 episodes): 350.5100\nbest mean reward: 358.9600\ncurrent episode reward: 401.0000\nepisodes: 2314\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38031.2 seconds (10.56 hours)\n\nTimestep: 8390000\nmean reward (100 episodes): 346.3100\nbest mean reward: 358.9600\ncurrent episode reward: 197.0000\nepisodes: 2316\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38077.6 seconds (10.58 hours)\n\nTimestep: 8400000\nmean reward (100 episodes): 346.6300\nbest mean reward: 358.9600\ncurrent episode reward: 443.0000\nepisodes: 2317\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38123.9 seconds (10.59 hours)\n\nTimestep: 8410000\nmean reward (100 episodes): 348.9500\nbest mean reward: 358.9600\ncurrent episode reward: 490.0000\nepisodes: 2319\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38171.5 seconds (10.60 hours)\n\nTimestep: 8420000\nmean reward (100 episodes): 351.0600\nbest mean reward: 358.9600\ncurrent episode reward: 404.0000\nepisodes: 2320\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38218.6 seconds (10.62 hours)\n\nTimestep: 8430000\nmean reward (100 episodes): 355.0000\nbest mean reward: 358.9600\ncurrent episode reward: 164.0000\nepisodes: 2322\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38265.3 seconds (10.63 hours)\n\nTimestep: 8440000\nmean reward (100 episodes): 358.5800\nbest mean reward: 358.9600\ncurrent episode reward: 683.0000\nepisodes: 2323\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38312.0 seconds (10.64 hours)\n\nTimestep: 8450000\nmean reward (100 episodes): 362.4000\nbest mean reward: 362.4000\ncurrent episode reward: 164.0000\nepisodes: 2325\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38358.6 seconds (10.66 hours)\n\nTimestep: 8460000\nmean reward (100 episodes): 362.0200\nbest mean reward: 362.6800\ncurrent episode reward: 186.0000\nepisodes: 2328\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38405.5 seconds (10.67 hours)\n\nTimestep: 8470000\nmean reward (100 episodes): 364.2200\nbest mean reward: 364.2200\ncurrent episode reward: 348.0000\nepisodes: 2329\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38451.4 seconds (10.68 hours)\n\nTimestep: 8480000\nmean reward (100 episodes): 364.9500\nbest mean reward: 364.9500\ncurrent episode reward: 406.0000\nepisodes: 2331\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38498.5 seconds (10.69 hours)\n\nTimestep: 8490000\nmean reward (100 episodes): 366.9600\nbest mean reward: 366.9600\ncurrent episode reward: 390.0000\nepisodes: 2332\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38545.2 seconds (10.71 hours)\n\nTimestep: 8500000\nmean reward (100 episodes): 369.4600\nbest mean reward: 369.4600\ncurrent episode reward: 650.0000\nepisodes: 2333\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38591.6 seconds (10.72 hours)\n\nTimestep: 8510000\nmean reward (100 episodes): 371.7500\nbest mean reward: 371.7500\ncurrent episode reward: 349.0000\nepisodes: 2335\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38638.1 seconds (10.73 hours)\n\nTimestep: 8520000\nmean reward (100 episodes): 374.2700\nbest mean reward: 374.2700\ncurrent episode reward: 446.0000\nepisodes: 2336\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38685.2 seconds (10.75 hours)\n\nTimestep: 8530000\nmean reward (100 episodes): 375.8200\nbest mean reward: 377.0900\ncurrent episode reward: 368.0000\nepisodes: 2338\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38731.6 seconds (10.76 hours)\n\nTimestep: 8540000\nmean reward (100 episodes): 371.5800\nbest mean reward: 377.0900\ncurrent episode reward: 469.0000\nepisodes: 2340\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38777.9 seconds (10.77 hours)\n\nTimestep: 8550000\nmean reward (100 episodes): 372.2600\nbest mean reward: 377.0900\ncurrent episode reward: 470.0000\nepisodes: 2342\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38824.2 seconds (10.78 hours)\n\nTimestep: 8560000\nmean reward (100 episodes): 372.9700\nbest mean reward: 377.0900\ncurrent episode reward: 419.0000\nepisodes: 2343\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38870.5 seconds (10.80 hours)\n\nTimestep: 8570000\nmean reward (100 episodes): 379.6600\nbest mean reward: 379.6600\ncurrent episode reward: 438.0000\nepisodes: 2345\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38917.4 seconds (10.81 hours)\n\nTimestep: 8580000\nmean reward (100 episodes): 375.9000\nbest mean reward: 379.6600\ncurrent episode reward: 158.0000\nepisodes: 2347\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38964.1 seconds (10.82 hours)\n\nTimestep: 8590000\nmean reward (100 episodes): 376.9700\nbest mean reward: 379.6600\ncurrent episode reward: 458.0000\nepisodes: 2348\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39010.7 seconds (10.84 hours)\n\nTimestep: 8600000\nmean reward (100 episodes): 380.6100\nbest mean reward: 380.6100\ncurrent episode reward: 786.0000\nepisodes: 2349\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39057.5 seconds (10.85 hours)\n\nTimestep: 8610000\nmean reward (100 episodes): 378.5300\nbest mean reward: 380.6100\ncurrent episode reward: 197.0000\nepisodes: 2351\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39104.0 seconds (10.86 hours)\n\nTimestep: 8620000\nmean reward (100 episodes): 379.1000\nbest mean reward: 380.6100\ncurrent episode reward: 367.0000\nepisodes: 2353\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39150.6 seconds (10.88 hours)\n\nTimestep: 8630000\nmean reward (100 episodes): 381.7700\nbest mean reward: 381.7700\ncurrent episode reward: 697.0000\nepisodes: 2354\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39197.3 seconds (10.89 hours)\n\nTimestep: 8640000\nmean reward (100 episodes): 382.0800\nbest mean reward: 382.0800\ncurrent episode reward: 470.0000\nepisodes: 2355\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39243.3 seconds (10.90 hours)\n\nTimestep: 8650000\nmean reward (100 episodes): 383.5400\nbest mean reward: 385.7900\ncurrent episode reward: 183.0000\nepisodes: 2357\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39289.7 seconds (10.91 hours)\n\nTimestep: 8660000\nmean reward (100 episodes): 380.9800\nbest mean reward: 385.7900\ncurrent episode reward: 192.0000\nepisodes: 2359\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39336.5 seconds (10.93 hours)\n\nTimestep: 8670000\nmean reward (100 episodes): 380.2200\nbest mean reward: 385.7900\ncurrent episode reward: 591.0000\nepisodes: 2360\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39382.5 seconds (10.94 hours)\n\nTimestep: 8680000\nmean reward (100 episodes): 379.8900\nbest mean reward: 385.7900\ncurrent episode reward: 411.0000\nepisodes: 2362\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39428.9 seconds (10.95 hours)\n\nTimestep: 8690000\nmean reward (100 episodes): 380.2600\nbest mean reward: 385.7900\ncurrent episode reward: 444.0000\nepisodes: 2363\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39476.4 seconds (10.97 hours)\n\nTimestep: 8700000\nmean reward (100 episodes): 380.7100\nbest mean reward: 385.7900\ncurrent episode reward: 413.0000\nepisodes: 2365\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39522.7 seconds (10.98 hours)\n\nTimestep: 8710000\nmean reward (100 episodes): 376.4400\nbest mean reward: 385.7900\ncurrent episode reward: 185.0000\nepisodes: 2367\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39569.7 seconds (10.99 hours)\n\nTimestep: 8720000\nmean reward (100 episodes): 370.9500\nbest mean reward: 385.7900\ncurrent episode reward: 146.0000\nepisodes: 2370\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39615.7 seconds (11.00 hours)\n\nTimestep: 8730000\nmean reward (100 episodes): 372.2200\nbest mean reward: 385.7900\ncurrent episode reward: 475.0000\nepisodes: 2372\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39661.3 seconds (11.02 hours)\n\nTimestep: 8740000\nmean reward (100 episodes): 369.9400\nbest mean reward: 385.7900\ncurrent episode reward: 479.0000\nepisodes: 2374\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39707.7 seconds (11.03 hours)\n\nTimestep: 8750000\nmean reward (100 episodes): 369.8900\nbest mean reward: 385.7900\ncurrent episode reward: 434.0000\nepisodes: 2375\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39754.0 seconds (11.04 hours)\n\nTimestep: 8760000\nmean reward (100 episodes): 364.7000\nbest mean reward: 385.7900\ncurrent episode reward: 186.0000\nepisodes: 2378\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39799.9 seconds (11.06 hours)\n\nTimestep: 8770000\nmean reward (100 episodes): 367.0600\nbest mean reward: 385.7900\ncurrent episode reward: 435.0000\nepisodes: 2379\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39846.4 seconds (11.07 hours)\n\nTimestep: 8780000\nmean reward (100 episodes): 370.9800\nbest mean reward: 385.7900\ncurrent episode reward: 471.0000\nepisodes: 2381\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39893.4 seconds (11.08 hours)\n\nTimestep: 8790000\nmean reward (100 episodes): 376.0100\nbest mean reward: 385.7900\ncurrent episode reward: 699.0000\nepisodes: 2382\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39940.0 seconds (11.09 hours)\n\nTimestep: 8800000\nmean reward (100 episodes): 378.1800\nbest mean reward: 385.7900\ncurrent episode reward: 404.0000\nepisodes: 2383\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39987.1 seconds (11.11 hours)\n\nTimestep: 8810000\nmean reward (100 episodes): 380.7400\nbest mean reward: 385.7900\ncurrent episode reward: 373.0000\nepisodes: 2385\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40034.5 seconds (11.12 hours)\n\nTimestep: 8820000\nmean reward (100 episodes): 381.0000\nbest mean reward: 385.7900\ncurrent episode reward: 409.0000\nepisodes: 2386\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40081.5 seconds (11.13 hours)\n\nTimestep: 8830000\nmean reward (100 episodes): 381.4300\nbest mean reward: 385.7900\ncurrent episode reward: 726.0000\nepisodes: 2387\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40129.2 seconds (11.15 hours)\n\nTimestep: 8840000\nmean reward (100 episodes): 381.4800\nbest mean reward: 385.7900\ncurrent episode reward: 477.0000\nepisodes: 2389\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40175.4 seconds (11.16 hours)\n\nTimestep: 8850000\nmean reward (100 episodes): 382.2000\nbest mean reward: 385.7900\ncurrent episode reward: 482.0000\nepisodes: 2390\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40222.2 seconds (11.17 hours)\n\nTimestep: 8860000\nmean reward (100 episodes): 379.3300\nbest mean reward: 385.7900\ncurrent episode reward: 162.0000\nepisodes: 2392\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40268.7 seconds (11.19 hours)\n\nTimestep: 8870000\nmean reward (100 episodes): 377.1100\nbest mean reward: 385.7900\ncurrent episode reward: 192.0000\nepisodes: 2394\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40315.0 seconds (11.20 hours)\n\nTimestep: 8880000\nmean reward (100 episodes): 379.0100\nbest mean reward: 385.7900\ncurrent episode reward: 653.0000\nepisodes: 2395\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40361.3 seconds (11.21 hours)\n\nTimestep: 8890000\nmean reward (100 episodes): 380.7400\nbest mean reward: 385.7900\ncurrent episode reward: 495.0000\nepisodes: 2397\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40407.3 seconds (11.22 hours)\n\nTimestep: 8900000\nmean reward (100 episodes): 377.6700\nbest mean reward: 385.7900\ncurrent episode reward: 187.0000\nepisodes: 2399\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40453.9 seconds (11.24 hours)\n\nTimestep: 8910000\nmean reward (100 episodes): 378.5800\nbest mean reward: 385.7900\ncurrent episode reward: 480.0000\nepisodes: 2400\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40501.1 seconds (11.25 hours)\n\nTimestep: 8920000\nmean reward (100 episodes): 382.5200\nbest mean reward: 385.7900\ncurrent episode reward: 408.0000\nepisodes: 2402\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40547.5 seconds (11.26 hours)\n\nTimestep: 8930000\nmean reward (100 episodes): 386.1100\nbest mean reward: 386.1100\ncurrent episode reward: 479.0000\nepisodes: 2404\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40593.1 seconds (11.28 hours)\n\nTimestep: 8940000\nmean reward (100 episodes): 387.1200\nbest mean reward: 387.1200\ncurrent episode reward: 195.0000\nepisodes: 2406\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40638.6 seconds (11.29 hours)\n\nTimestep: 8950000\nmean reward (100 episodes): 389.6100\nbest mean reward: 389.6100\ncurrent episode reward: 446.0000\nepisodes: 2407\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40685.9 seconds (11.30 hours)\n\nTimestep: 8960000\nmean reward (100 episodes): 393.0800\nbest mean reward: 393.0800\ncurrent episode reward: 479.0000\nepisodes: 2409\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40732.5 seconds (11.31 hours)\n\nTimestep: 8970000\nmean reward (100 episodes): 392.7000\nbest mean reward: 393.0800\ncurrent episode reward: 397.0000\nepisodes: 2410\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40779.3 seconds (11.33 hours)\n\nTimestep: 8980000\nmean reward (100 episodes): 396.3400\nbest mean reward: 396.3400\ncurrent episode reward: 490.0000\nepisodes: 2412\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40825.4 seconds (11.34 hours)\n\nTimestep: 8990000\nmean reward (100 episodes): 395.3600\nbest mean reward: 397.4600\ncurrent episode reward: 191.0000\nepisodes: 2414\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40871.1 seconds (11.35 hours)\n\nTimestep: 9000000\nmean reward (100 episodes): 397.2500\nbest mean reward: 397.4600\ncurrent episode reward: 435.0000\nepisodes: 2415\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40917.2 seconds (11.37 hours)\n\nTimestep: 9010000\nmean reward (100 episodes): 399.4600\nbest mean reward: 399.4600\ncurrent episode reward: 446.0000\nepisodes: 2417\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40964.6 seconds (11.38 hours)\n\nTimestep: 9020000\nmean reward (100 episodes): 397.5100\nbest mean reward: 399.4600\ncurrent episode reward: 499.0000\nepisodes: 2418\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41011.1 seconds (11.39 hours)\n\nTimestep: 9030000\nmean reward (100 episodes): 397.1700\nbest mean reward: 399.4600\ncurrent episode reward: 424.0000\nepisodes: 2420\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41057.1 seconds (11.40 hours)\n\nTimestep: 9040000\nmean reward (100 episodes): 398.2900\nbest mean reward: 399.4600\ncurrent episode reward: 709.0000\nepisodes: 2421\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41103.7 seconds (11.42 hours)\n\nTimestep: 9050000\nmean reward (100 episodes): 396.4000\nbest mean reward: 401.4000\ncurrent episode reward: 183.0000\nepisodes: 2423\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41150.5 seconds (11.43 hours)\n\nTimestep: 9060000\nmean reward (100 episodes): 396.6600\nbest mean reward: 401.4000\ncurrent episode reward: 466.0000\nepisodes: 2424\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41197.0 seconds (11.44 hours)\n\nTimestep: 9070000\nmean reward (100 episodes): 402.2800\nbest mean reward: 402.2800\ncurrent episode reward: 417.0000\nepisodes: 2426\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41243.8 seconds (11.46 hours)\n\nTimestep: 9080000\nmean reward (100 episodes): 405.3100\nbest mean reward: 405.3100\ncurrent episode reward: 440.0000\nepisodes: 2427\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41290.5 seconds (11.47 hours)\n\nTimestep: 9090000\nmean reward (100 episodes): 409.8500\nbest mean reward: 409.8500\ncurrent episode reward: 640.0000\nepisodes: 2428\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41337.1 seconds (11.48 hours)\n\nTimestep: 9100000\nmean reward (100 episodes): 410.0100\nbest mean reward: 410.5100\ncurrent episode reward: 374.0000\nepisodes: 2430\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41384.1 seconds (11.50 hours)\n\nTimestep: 9110000\nmean reward (100 episodes): 410.7900\nbest mean reward: 410.7900\ncurrent episode reward: 484.0000\nepisodes: 2431\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41430.4 seconds (11.51 hours)\n\nTimestep: 9120000\nmean reward (100 episodes): 408.6200\nbest mean reward: 413.1900\ncurrent episode reward: 193.0000\nepisodes: 2433\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41477.0 seconds (11.52 hours)\n\nTimestep: 9130000\nmean reward (100 episodes): 408.1700\nbest mean reward: 413.1900\ncurrent episode reward: 397.0000\nepisodes: 2434\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41523.2 seconds (11.53 hours)\n\nTimestep: 9140000\nmean reward (100 episodes): 406.1200\nbest mean reward: 413.1900\ncurrent episode reward: 189.0000\nepisodes: 2436\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41569.6 seconds (11.55 hours)\n\nTimestep: 9150000\nmean reward (100 episodes): 407.3400\nbest mean reward: 413.1900\ncurrent episode reward: 482.0000\nepisodes: 2438\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41616.1 seconds (11.56 hours)\n\nTimestep: 9160000\nmean reward (100 episodes): 411.5200\nbest mean reward: 413.1900\ncurrent episode reward: 610.0000\nepisodes: 2439\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41662.7 seconds (11.57 hours)\n\nTimestep: 9170000\nmean reward (100 episodes): 411.6400\nbest mean reward: 413.1900\ncurrent episode reward: 189.0000\nepisodes: 2441\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41709.4 seconds (11.59 hours)\n\nTimestep: 9180000\nmean reward (100 episodes): 410.9700\nbest mean reward: 413.1900\ncurrent episode reward: 403.0000\nepisodes: 2442\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41756.5 seconds (11.60 hours)\n\nTimestep: 9190000\nmean reward (100 episodes): 411.1000\nbest mean reward: 413.1900\ncurrent episode reward: 473.0000\nepisodes: 2444\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41803.3 seconds (11.61 hours)\n\nTimestep: 9200000\nmean reward (100 episodes): 411.6800\nbest mean reward: 413.1900\ncurrent episode reward: 496.0000\nepisodes: 2445\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41850.4 seconds (11.63 hours)\n\nTimestep: 9210000\nmean reward (100 episodes): 412.9900\nbest mean reward: 413.1900\ncurrent episode reward: 188.0000\nepisodes: 2447\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41897.2 seconds (11.64 hours)\n\nTimestep: 9220000\nmean reward (100 episodes): 410.0800\nbest mean reward: 413.1900\ncurrent episode reward: 478.0000\nepisodes: 2449\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41942.9 seconds (11.65 hours)\n\nTimestep: 9230000\nmean reward (100 episodes): 411.4500\nbest mean reward: 413.1900\ncurrent episode reward: 563.0000\nepisodes: 2450\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41989.1 seconds (11.66 hours)\n\nTimestep: 9240000\nmean reward (100 episodes): 410.7700\nbest mean reward: 413.1900\ncurrent episode reward: 416.0000\nepisodes: 2452\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42034.4 seconds (11.68 hours)\n\nTimestep: 9250000\nmean reward (100 episodes): 401.1100\nbest mean reward: 413.1900\ncurrent episode reward: 187.0000\nepisodes: 2455\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42081.1 seconds (11.69 hours)\n\nTimestep: 9260000\nmean reward (100 episodes): 398.7800\nbest mean reward: 413.1900\ncurrent episode reward: 479.0000\nepisodes: 2456\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42127.5 seconds (11.70 hours)\n\nTimestep: 9270000\nmean reward (100 episodes): 403.4100\nbest mean reward: 413.1900\ncurrent episode reward: 646.0000\nepisodes: 2457\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42173.8 seconds (11.71 hours)\n\nTimestep: 9280000\nmean reward (100 episodes): 404.2000\nbest mean reward: 413.1900\ncurrent episode reward: 193.0000\nepisodes: 2459\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42220.7 seconds (11.73 hours)\n\nTimestep: 9290000\nmean reward (100 episodes): 402.7400\nbest mean reward: 413.1900\ncurrent episode reward: 493.0000\nepisodes: 2461\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42266.7 seconds (11.74 hours)\n\nTimestep: 9300000\nmean reward (100 episodes): 400.7800\nbest mean reward: 413.1900\ncurrent episode reward: 486.0000\nepisodes: 2463\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42312.9 seconds (11.75 hours)\n\nTimestep: 9310000\nmean reward (100 episodes): 400.6000\nbest mean reward: 413.1900\ncurrent episode reward: 449.0000\nepisodes: 2464\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42359.5 seconds (11.77 hours)\n\nTimestep: 9320000\nmean reward (100 episodes): 401.7700\nbest mean reward: 413.1900\ncurrent episode reward: 478.0000\nepisodes: 2466\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42405.9 seconds (11.78 hours)\n\nTimestep: 9330000\nmean reward (100 episodes): 403.9400\nbest mean reward: 413.1900\ncurrent episode reward: 402.0000\nepisodes: 2467\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42452.9 seconds (11.79 hours)\n\nTimestep: 9340000\nmean reward (100 episodes): 409.3000\nbest mean reward: 413.1900\ncurrent episode reward: 461.0000\nepisodes: 2469\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42499.4 seconds (11.81 hours)\n\nTimestep: 9350000\nmean reward (100 episodes): 412.1300\nbest mean reward: 413.1900\ncurrent episode reward: 429.0000\nepisodes: 2470\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42546.1 seconds (11.82 hours)\n\nTimestep: 9360000\nmean reward (100 episodes): 415.0100\nbest mean reward: 415.0100\ncurrent episode reward: 472.0000\nepisodes: 2471\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42592.5 seconds (11.83 hours)\n\nTimestep: 9370000\nmean reward (100 episodes): 420.3500\nbest mean reward: 420.3500\ncurrent episode reward: 464.0000\nepisodes: 2473\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42638.5 seconds (11.84 hours)\n\nTimestep: 9380000\nmean reward (100 episodes): 420.1100\nbest mean reward: 420.3500\ncurrent episode reward: 455.0000\nepisodes: 2474\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42684.8 seconds (11.86 hours)\n\nTimestep: 9390000\nmean reward (100 episodes): 422.7000\nbest mean reward: 422.7000\ncurrent episode reward: 693.0000\nepisodes: 2475\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42731.3 seconds (11.87 hours)\n\nTimestep: 9400000\nmean reward (100 episodes): 425.3800\nbest mean reward: 425.3800\ncurrent episode reward: 671.0000\nepisodes: 2476\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42778.6 seconds (11.88 hours)\n\nTimestep: 9410000\nmean reward (100 episodes): 429.9900\nbest mean reward: 429.9900\ncurrent episode reward: 407.0000\nepisodes: 2478\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42824.5 seconds (11.90 hours)\n\nTimestep: 9420000\nmean reward (100 episodes): 430.4000\nbest mean reward: 430.4000\ncurrent episode reward: 476.0000\nepisodes: 2479\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42870.8 seconds (11.91 hours)\n\nTimestep: 9430000\nmean reward (100 episodes): 429.7700\nbest mean reward: 430.4000\ncurrent episode reward: 420.0000\nepisodes: 2481\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42917.4 seconds (11.92 hours)\n\nTimestep: 9440000\nmean reward (100 episodes): 427.2100\nbest mean reward: 430.4000\ncurrent episode reward: 443.0000\nepisodes: 2482\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42963.8 seconds (11.93 hours)\n\nTimestep: 9450000\nmean reward (100 episodes): 430.3300\nbest mean reward: 430.4000\ncurrent episode reward: 716.0000\nepisodes: 2483\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43010.3 seconds (11.95 hours)\n\nTimestep: 9460000\nmean reward (100 episodes): 431.5700\nbest mean reward: 433.3900\ncurrent episode reward: 191.0000\nepisodes: 2485\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43056.8 seconds (11.96 hours)\n\nTimestep: 9470000\nmean reward (100 episodes): 432.3000\nbest mean reward: 433.3900\ncurrent episode reward: 482.0000\nepisodes: 2486\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43103.5 seconds (11.97 hours)\n\nTimestep: 9480000\nmean reward (100 episodes): 429.4800\nbest mean reward: 433.3900\ncurrent episode reward: 450.0000\nepisodes: 2488\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43150.3 seconds (11.99 hours)\n\nTimestep: 9490000\nmean reward (100 episodes): 424.8200\nbest mean reward: 433.3900\ncurrent episode reward: 174.0000\nepisodes: 2490\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43196.5 seconds (12.00 hours)\n\nTimestep: 9500000\nmean reward (100 episodes): 425.1100\nbest mean reward: 433.3900\ncurrent episode reward: 492.0000\nepisodes: 2491\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43243.6 seconds (12.01 hours)\n\nTimestep: 9510000\nmean reward (100 episodes): 430.6300\nbest mean reward: 433.3900\ncurrent episode reward: 714.0000\nepisodes: 2492\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43289.6 seconds (12.02 hours)\n\nTimestep: 9520000\nmean reward (100 episodes): 432.9000\nbest mean reward: 433.3900\ncurrent episode reward: 491.0000\nepisodes: 2494\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43335.8 seconds (12.04 hours)\n\nTimestep: 9530000\nmean reward (100 episodes): 427.0800\nbest mean reward: 433.3900\ncurrent episode reward: 60.0000\nepisodes: 2496\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43381.6 seconds (12.05 hours)\n\nTimestep: 9540000\nmean reward (100 episodes): 426.6400\nbest mean reward: 433.3900\ncurrent episode reward: 451.0000\nepisodes: 2497\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43427.8 seconds (12.06 hours)\n\nTimestep: 9550000\nmean reward (100 episodes): 426.7500\nbest mean reward: 433.3900\ncurrent episode reward: 415.0000\nepisodes: 2498\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43474.2 seconds (12.08 hours)\n\nTimestep: 9560000\nmean reward (100 episodes): 428.3800\nbest mean reward: 433.3900\ncurrent episode reward: 191.0000\nepisodes: 2500\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43521.5 seconds (12.09 hours)\n\nTimestep: 9570000\nmean reward (100 episodes): 428.8900\nbest mean reward: 433.3900\ncurrent episode reward: 427.0000\nepisodes: 2502\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43567.6 seconds (12.10 hours)\n\nTimestep: 9580000\nmean reward (100 episodes): 428.7800\nbest mean reward: 433.3900\ncurrent episode reward: 466.0000\nepisodes: 2504\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43613.5 seconds (12.11 hours)\n\nTimestep: 9590000\nmean reward (100 episodes): 428.7800\nbest mean reward: 433.3900\ncurrent episode reward: 466.0000\nepisodes: 2504\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43660.9 seconds (12.13 hours)\n\nTimestep: 9600000\nmean reward (100 episodes): 435.8900\nbest mean reward: 435.8900\ncurrent episode reward: 450.0000\nepisodes: 2506\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43707.1 seconds (12.14 hours)\n\nTimestep: 9610000\nmean reward (100 episodes): 433.3000\nbest mean reward: 435.8900\ncurrent episode reward: 491.0000\nepisodes: 2508\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43753.3 seconds (12.15 hours)\n\nTimestep: 9620000\nmean reward (100 episodes): 430.3400\nbest mean reward: 435.8900\ncurrent episode reward: 183.0000\nepisodes: 2509\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43799.1 seconds (12.17 hours)\n\nTimestep: 9630000\nmean reward (100 episodes): 431.1000\nbest mean reward: 435.8900\ncurrent episode reward: 174.0000\nepisodes: 2511\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43845.5 seconds (12.18 hours)\n\nTimestep: 9640000\nmean reward (100 episodes): 434.0200\nbest mean reward: 435.8900\ncurrent episode reward: 782.0000\nepisodes: 2512\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43892.7 seconds (12.19 hours)\n\nTimestep: 9650000\nmean reward (100 episodes): 428.8700\nbest mean reward: 435.8900\ncurrent episode reward: 31.0000\nepisodes: 2515\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43939.2 seconds (12.21 hours)\n\nTimestep: 9660000\nmean reward (100 episodes): 423.1000\nbest mean reward: 435.8900\ncurrent episode reward: 197.0000\nepisodes: 2517\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43985.8 seconds (12.22 hours)\n\nTimestep: 9670000\nmean reward (100 episodes): 423.0900\nbest mean reward: 435.8900\ncurrent episode reward: 447.0000\nepisodes: 2519\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44031.9 seconds (12.23 hours)\n\nTimestep: 9680000\nmean reward (100 episodes): 414.4000\nbest mean reward: 435.8900\ncurrent episode reward: 64.0000\nepisodes: 2521\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44077.8 seconds (12.24 hours)\n\nTimestep: 9690000\nmean reward (100 episodes): 407.6100\nbest mean reward: 435.8900\ncurrent episode reward: 173.0000\nepisodes: 2524\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44124.5 seconds (12.26 hours)\n\nTimestep: 9700000\nmean reward (100 episodes): 402.1700\nbest mean reward: 435.8900\ncurrent episode reward: 173.0000\nepisodes: 2526\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44171.6 seconds (12.27 hours)\n\nTimestep: 9710000\nmean reward (100 episodes): 394.9200\nbest mean reward: 435.8900\ncurrent episode reward: 64.0000\nepisodes: 2528\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44217.7 seconds (12.28 hours)\n\nTimestep: 9720000\nmean reward (100 episodes): 395.1600\nbest mean reward: 435.8900\ncurrent episode reward: 428.0000\nepisodes: 2530\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44263.7 seconds (12.30 hours)\n\nTimestep: 9730000\nmean reward (100 episodes): 388.5700\nbest mean reward: 435.8900\ncurrent episode reward: 290.0000\nepisodes: 2532\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44310.0 seconds (12.31 hours)\n\nTimestep: 9740000\nmean reward (100 episodes): 388.4900\nbest mean reward: 435.8900\ncurrent episode reward: 189.0000\nepisodes: 2534\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44357.3 seconds (12.32 hours)\n\nTimestep: 9750000\nmean reward (100 episodes): 388.9300\nbest mean reward: 435.8900\ncurrent episode reward: 445.0000\nepisodes: 2535\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44403.4 seconds (12.33 hours)\n\nTimestep: 9760000\nmean reward (100 episodes): 384.3100\nbest mean reward: 435.8900\ncurrent episode reward: 195.0000\nepisodes: 2538\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44450.5 seconds (12.35 hours)\n\nTimestep: 9770000\nmean reward (100 episodes): 380.1100\nbest mean reward: 435.8900\ncurrent episode reward: 190.0000\nepisodes: 2539\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44497.6 seconds (12.36 hours)\n\nTimestep: 9780000\nmean reward (100 episodes): 384.6900\nbest mean reward: 435.8900\ncurrent episode reward: 414.0000\nepisodes: 2541\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44544.9 seconds (12.37 hours)\n\nTimestep: 9790000\nmean reward (100 episodes): 385.5000\nbest mean reward: 435.8900\ncurrent episode reward: 484.0000\nepisodes: 2542\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44591.1 seconds (12.39 hours)\n\nTimestep: 9800000\nmean reward (100 episodes): 385.7700\nbest mean reward: 435.8900\ncurrent episode reward: 454.0000\nepisodes: 2544\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44637.3 seconds (12.40 hours)\n\nTimestep: 9810000\nmean reward (100 episodes): 385.2800\nbest mean reward: 435.8900\ncurrent episode reward: 447.0000\nepisodes: 2545\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44684.5 seconds (12.41 hours)\n\nTimestep: 9820000\nmean reward (100 episodes): 388.4700\nbest mean reward: 435.8900\ncurrent episode reward: 489.0000\nepisodes: 2547\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44730.5 seconds (12.43 hours)\n\nTimestep: 9830000\nmean reward (100 episodes): 377.2600\nbest mean reward: 435.8900\ncurrent episode reward: 30.0000\nepisodes: 2550\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44776.3 seconds (12.44 hours)\n\nTimestep: 9840000\nmean reward (100 episodes): 373.9000\nbest mean reward: 435.8900\ncurrent episode reward: 192.0000\nepisodes: 2553\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44822.7 seconds (12.45 hours)\n\nTimestep: 9850000\nmean reward (100 episodes): 376.0500\nbest mean reward: 435.8900\ncurrent episode reward: 396.0000\nepisodes: 2555\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44869.3 seconds (12.46 hours)\n\nTimestep: 9860000\nmean reward (100 episodes): 370.7100\nbest mean reward: 435.8900\ncurrent episode reward: 157.0000\nepisodes: 2557\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44915.5 seconds (12.48 hours)\n\nTimestep: 9870000\nmean reward (100 episodes): 370.1300\nbest mean reward: 435.8900\ncurrent episode reward: 188.0000\nepisodes: 2559\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44961.5 seconds (12.49 hours)\n\nTimestep: 9880000\nmean reward (100 episodes): 364.8900\nbest mean reward: 435.8900\ncurrent episode reward: 160.0000\nepisodes: 2562\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45007.6 seconds (12.50 hours)\n\nTimestep: 9890000\nmean reward (100 episodes): 367.9600\nbest mean reward: 435.8900\ncurrent episode reward: 793.0000\nepisodes: 2563\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45053.8 seconds (12.51 hours)\n\nTimestep: 9900000\nmean reward (100 episodes): 370.5500\nbest mean reward: 435.8900\ncurrent episode reward: 708.0000\nepisodes: 2564\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45100.4 seconds (12.53 hours)\n\nTimestep: 9910000\nmean reward (100 episodes): 368.2700\nbest mean reward: 435.8900\ncurrent episode reward: 187.0000\nepisodes: 2565\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45146.8 seconds (12.54 hours)\n\nTimestep: 9920000\nmean reward (100 episodes): 371.2700\nbest mean reward: 435.8900\ncurrent episode reward: 492.0000\nepisodes: 2567\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45193.4 seconds (12.55 hours)\n\nTimestep: 9930000\nmean reward (100 episodes): 371.2500\nbest mean reward: 435.8900\ncurrent episode reward: 448.0000\nepisodes: 2568\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45240.4 seconds (12.57 hours)\n\nTimestep: 9940000\nmean reward (100 episodes): 373.5700\nbest mean reward: 435.8900\ncurrent episode reward: 693.0000\nepisodes: 2569\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45286.9 seconds (12.58 hours)\n\nTimestep: 9950000\nmean reward (100 episodes): 373.8200\nbest mean reward: 435.8900\ncurrent episode reward: 496.0000\nepisodes: 2571\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45333.7 seconds (12.59 hours)\n\nTimestep: 9960000\nmean reward (100 episodes): 371.4300\nbest mean reward: 435.8900\ncurrent episode reward: 489.0000\nepisodes: 2572\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45380.2 seconds (12.61 hours)\n\nTimestep: 9970000\nmean reward (100 episodes): 370.9500\nbest mean reward: 435.8900\ncurrent episode reward: 197.0000\nepisodes: 2574\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45426.3 seconds (12.62 hours)\n\nTimestep: 9980000\nmean reward (100 episodes): 363.4900\nbest mean reward: 435.8900\ncurrent episode reward: 193.0000\nepisodes: 2576\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45473.5 seconds (12.63 hours)\n\nTimestep: 9985964\nmean reward (100 episodes): 363.4900\nbest mean reward: 435.8900\ncurrent episode reward: 193.0000\nepisodes: 2576\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45501.3 seconds (12.64 hours)\n"
  },
  {
    "path": "dqn/logs_text/Enduro_s002.text",
    "content": "('AVAILABLE GPUS: ', [u'device: 0, name: TITAN X (Pascal), pci bus id: 0000:01:00.0'])\ntask = Task<env_id=EnduroNoFrameskip-v3 trials=2 max_timesteps=40000000 max_seconds=None reward_floor=0.0 reward_ceiling=5000.0>\n\nTimestep: 60000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 18\nexploration: 0.94600\nlearning_rate: 0.00010\nelapsed time: 101.6 seconds (0.03 hours)\n\nTimestep: 70000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 21\nexploration: 0.93700\nlearning_rate: 0.00010\nelapsed time: 135.5 seconds (0.04 hours)\n\nTimestep: 80000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 24\nexploration: 0.92800\nlearning_rate: 0.00010\nelapsed time: 169.5 seconds (0.05 hours)\n\nTimestep: 90000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 27\nexploration: 0.91900\nlearning_rate: 0.00010\nelapsed time: 204.0 seconds (0.06 hours)\n\nTimestep: 100000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 30\nexploration: 0.91000\nlearning_rate: 0.00010\nelapsed time: 241.1 seconds (0.07 hours)\n\nTimestep: 110000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 33\nexploration: 0.90100\nlearning_rate: 0.00010\nelapsed time: 275.7 seconds (0.08 hours)\n\nTimestep: 120000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 36\nexploration: 0.89200\nlearning_rate: 0.00010\nelapsed time: 310.4 seconds (0.09 hours)\n\nTimestep: 130000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 39\nexploration: 0.88300\nlearning_rate: 0.00010\nelapsed time: 345.1 seconds (0.10 hours)\n\nTimestep: 140000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 42\nexploration: 0.87400\nlearning_rate: 0.00010\nelapsed time: 380.0 seconds (0.11 hours)\n\nTimestep: 150000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 45\nexploration: 0.86500\nlearning_rate: 0.00010\nelapsed time: 414.9 seconds (0.12 hours)\n\nTimestep: 160000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 48\nexploration: 0.85600\nlearning_rate: 0.00010\nelapsed time: 449.7 seconds (0.12 hours)\n\nTimestep: 170000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 51\nexploration: 0.84700\nlearning_rate: 0.00010\nelapsed time: 485.1 seconds (0.13 hours)\n\nTimestep: 180000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 54\nexploration: 0.83800\nlearning_rate: 0.00010\nelapsed time: 520.4 seconds (0.14 hours)\n\nTimestep: 190000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 57\nexploration: 0.82900\nlearning_rate: 0.00010\nelapsed time: 556.0 seconds (0.15 hours)\n\nTimestep: 200000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 60\nexploration: 0.82000\nlearning_rate: 0.00010\nelapsed time: 591.7 seconds (0.16 hours)\n\nTimestep: 210000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 63\nexploration: 0.81100\nlearning_rate: 0.00010\nelapsed time: 627.7 seconds (0.17 hours)\n\nTimestep: 220000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 66\nexploration: 0.80200\nlearning_rate: 0.00010\nelapsed time: 666.3 seconds (0.19 hours)\n\nTimestep: 230000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 69\nexploration: 0.79300\nlearning_rate: 0.00010\nelapsed time: 702.5 seconds (0.20 hours)\n\nTimestep: 240000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 72\nexploration: 0.78400\nlearning_rate: 0.00010\nelapsed time: 739.2 seconds (0.21 hours)\n\nTimestep: 250000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 75\nexploration: 0.77500\nlearning_rate: 0.00010\nelapsed time: 775.9 seconds (0.22 hours)\n\nTimestep: 260000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 78\nexploration: 0.76600\nlearning_rate: 0.00010\nelapsed time: 812.9 seconds (0.23 hours)\n\nTimestep: 270000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 81\nexploration: 0.75700\nlearning_rate: 0.00010\nelapsed time: 849.5 seconds (0.24 hours)\n\nTimestep: 280000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 84\nexploration: 0.74800\nlearning_rate: 0.00010\nelapsed time: 886.8 seconds (0.25 hours)\n\nTimestep: 290000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 87\nexploration: 0.73900\nlearning_rate: 0.00010\nelapsed time: 924.0 seconds (0.26 hours)\n\nTimestep: 300000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 90\nexploration: 0.73000\nlearning_rate: 0.00010\nelapsed time: 961.4 seconds (0.27 hours)\n\nTimestep: 310000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 93\nexploration: 0.72100\nlearning_rate: 0.00010\nelapsed time: 998.6 seconds (0.28 hours)\n\nTimestep: 320000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 96\nexploration: 0.71200\nlearning_rate: 0.00010\nelapsed time: 1035.8 seconds (0.29 hours)\n\nTimestep: 330000\nmean reward (100 episodes): 0.0000\nbest mean reward: -inf\ncurrent episode reward: 0.0000\nepisodes: 99\nexploration: 0.70300\nlearning_rate: 0.00010\nelapsed time: 1073.8 seconds (0.30 hours)\n\nTimestep: 340000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 102\nexploration: 0.69400\nlearning_rate: 0.00010\nelapsed time: 1111.1 seconds (0.31 hours)\n\nTimestep: 350000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 105\nexploration: 0.68500\nlearning_rate: 0.00010\nelapsed time: 1148.8 seconds (0.32 hours)\n\nTimestep: 360000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 108\nexploration: 0.67600\nlearning_rate: 0.00010\nelapsed time: 1186.6 seconds (0.33 hours)\n\nTimestep: 370000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 111\nexploration: 0.66700\nlearning_rate: 0.00010\nelapsed time: 1224.0 seconds (0.34 hours)\n\nTimestep: 380000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 114\nexploration: 0.65800\nlearning_rate: 0.00010\nelapsed time: 1261.6 seconds (0.35 hours)\n\nTimestep: 390000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 117\nexploration: 0.64900\nlearning_rate: 0.00010\nelapsed time: 1300.3 seconds (0.36 hours)\n\nTimestep: 400000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 120\nexploration: 0.64000\nlearning_rate: 0.00010\nelapsed time: 1338.9 seconds (0.37 hours)\n\nTimestep: 410000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 123\nexploration: 0.63100\nlearning_rate: 0.00010\nelapsed time: 1377.2 seconds (0.38 hours)\n\nTimestep: 420000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 126\nexploration: 0.62200\nlearning_rate: 0.00010\nelapsed time: 1418.2 seconds (0.39 hours)\n\nTimestep: 430000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 129\nexploration: 0.61300\nlearning_rate: 0.00010\nelapsed time: 1457.4 seconds (0.40 hours)\n\nTimestep: 440000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 132\nexploration: 0.60400\nlearning_rate: 0.00010\nelapsed time: 1496.4 seconds (0.42 hours)\n\nTimestep: 450000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 135\nexploration: 0.59500\nlearning_rate: 0.00010\nelapsed time: 1535.6 seconds (0.43 hours)\n\nTimestep: 460000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 138\nexploration: 0.58600\nlearning_rate: 0.00010\nelapsed time: 1574.9 seconds (0.44 hours)\n\nTimestep: 470000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 141\nexploration: 0.57700\nlearning_rate: 0.00010\nelapsed time: 1614.1 seconds (0.45 hours)\n\nTimestep: 480000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 144\nexploration: 0.56800\nlearning_rate: 0.00010\nelapsed time: 1653.5 seconds (0.46 hours)\n\nTimestep: 490000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 147\nexploration: 0.55900\nlearning_rate: 0.00010\nelapsed time: 1693.6 seconds (0.47 hours)\n\nTimestep: 500000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 150\nexploration: 0.55000\nlearning_rate: 0.00010\nelapsed time: 1732.8 seconds (0.48 hours)\n\nTimestep: 510000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 153\nexploration: 0.54100\nlearning_rate: 0.00010\nelapsed time: 1772.4 seconds (0.49 hours)\n\nTimestep: 520000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 156\nexploration: 0.53200\nlearning_rate: 0.00010\nelapsed time: 1812.6 seconds (0.50 hours)\n\nTimestep: 530000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 159\nexploration: 0.52300\nlearning_rate: 0.00010\nelapsed time: 1852.1 seconds (0.51 hours)\n\nTimestep: 540000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 162\nexploration: 0.51400\nlearning_rate: 0.00010\nelapsed time: 1892.2 seconds (0.53 hours)\n\nTimestep: 550000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 165\nexploration: 0.50500\nlearning_rate: 0.00010\nelapsed time: 1932.5 seconds (0.54 hours)\n\nTimestep: 560000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 168\nexploration: 0.49600\nlearning_rate: 0.00010\nelapsed time: 1973.0 seconds (0.55 hours)\n\nTimestep: 570000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 171\nexploration: 0.48700\nlearning_rate: 0.00010\nelapsed time: 2013.3 seconds (0.56 hours)\n\nTimestep: 580000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 174\nexploration: 0.47800\nlearning_rate: 0.00010\nelapsed time: 2053.7 seconds (0.57 hours)\n\nTimestep: 590000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 177\nexploration: 0.46900\nlearning_rate: 0.00010\nelapsed time: 2095.2 seconds (0.58 hours)\n\nTimestep: 600000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 180\nexploration: 0.46000\nlearning_rate: 0.00010\nelapsed time: 2136.3 seconds (0.59 hours)\n\nTimestep: 610000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 183\nexploration: 0.45100\nlearning_rate: 0.00010\nelapsed time: 2178.1 seconds (0.61 hours)\n\nTimestep: 620000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 186\nexploration: 0.44200\nlearning_rate: 0.00010\nelapsed time: 2219.1 seconds (0.62 hours)\n\nTimestep: 630000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 189\nexploration: 0.43300\nlearning_rate: 0.00010\nelapsed time: 2260.8 seconds (0.63 hours)\n\nTimestep: 640000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 192\nexploration: 0.42400\nlearning_rate: 0.00010\nelapsed time: 2302.4 seconds (0.64 hours)\n\nTimestep: 650000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.0000\ncurrent episode reward: 0.0000\nepisodes: 195\nexploration: 0.41500\nlearning_rate: 0.00010\nelapsed time: 2344.8 seconds (0.65 hours)\n\nTimestep: 660000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 198\nexploration: 0.40600\nlearning_rate: 0.00010\nelapsed time: 2387.1 seconds (0.66 hours)\n\nTimestep: 670000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 201\nexploration: 0.39700\nlearning_rate: 0.00010\nelapsed time: 2430.0 seconds (0.67 hours)\n\nTimestep: 680000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 204\nexploration: 0.38800\nlearning_rate: 0.00010\nelapsed time: 2471.2 seconds (0.69 hours)\n\nTimestep: 690000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 207\nexploration: 0.37900\nlearning_rate: 0.00010\nelapsed time: 2513.2 seconds (0.70 hours)\n\nTimestep: 700000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 210\nexploration: 0.37000\nlearning_rate: 0.00010\nelapsed time: 2555.0 seconds (0.71 hours)\n\nTimestep: 710000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 213\nexploration: 0.36100\nlearning_rate: 0.00010\nelapsed time: 2597.4 seconds (0.72 hours)\n\nTimestep: 720000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 216\nexploration: 0.35200\nlearning_rate: 0.00010\nelapsed time: 2640.8 seconds (0.73 hours)\n\nTimestep: 730000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 219\nexploration: 0.34300\nlearning_rate: 0.00010\nelapsed time: 2683.8 seconds (0.75 hours)\n\nTimestep: 740000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 222\nexploration: 0.33400\nlearning_rate: 0.00010\nelapsed time: 2726.6 seconds (0.76 hours)\n\nTimestep: 750000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 225\nexploration: 0.32500\nlearning_rate: 0.00010\nelapsed time: 2769.0 seconds (0.77 hours)\n\nTimestep: 760000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 228\nexploration: 0.31600\nlearning_rate: 0.00010\nelapsed time: 2813.2 seconds (0.78 hours)\n\nTimestep: 770000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 231\nexploration: 0.30700\nlearning_rate: 0.00010\nelapsed time: 2856.4 seconds (0.79 hours)\n\nTimestep: 780000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 234\nexploration: 0.29800\nlearning_rate: 0.00010\nelapsed time: 2900.3 seconds (0.81 hours)\n\nTimestep: 790000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 237\nexploration: 0.28900\nlearning_rate: 0.00010\nelapsed time: 2943.8 seconds (0.82 hours)\n\nTimestep: 800000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 240\nexploration: 0.28000\nlearning_rate: 0.00010\nelapsed time: 2988.3 seconds (0.83 hours)\n\nTimestep: 810000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 243\nexploration: 0.27100\nlearning_rate: 0.00010\nelapsed time: 3033.2 seconds (0.84 hours)\n\nTimestep: 820000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 246\nexploration: 0.26200\nlearning_rate: 0.00010\nelapsed time: 3076.8 seconds (0.85 hours)\n\nTimestep: 830000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 249\nexploration: 0.25300\nlearning_rate: 0.00010\nelapsed time: 3120.1 seconds (0.87 hours)\n\nTimestep: 840000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 252\nexploration: 0.24400\nlearning_rate: 0.00010\nelapsed time: 3164.0 seconds (0.88 hours)\n\nTimestep: 850000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.0100\ncurrent episode reward: 0.0000\nepisodes: 255\nexploration: 0.23500\nlearning_rate: 0.00010\nelapsed time: 3207.8 seconds (0.89 hours)\n\nTimestep: 860000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0500\ncurrent episode reward: 4.0000\nepisodes: 258\nexploration: 0.22600\nlearning_rate: 0.00010\nelapsed time: 3251.8 seconds (0.90 hours)\n\nTimestep: 870000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 261\nexploration: 0.21700\nlearning_rate: 0.00010\nelapsed time: 3296.4 seconds (0.92 hours)\n\nTimestep: 880000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.0500\ncurrent episode reward: 0.0000\nepisodes: 264\nexploration: 0.20800\nlearning_rate: 0.00010\nelapsed time: 3340.1 seconds (0.93 hours)\n\nTimestep: 890000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.1000\ncurrent episode reward: 0.0000\nepisodes: 267\nexploration: 0.19900\nlearning_rate: 0.00010\nelapsed time: 3384.4 seconds (0.94 hours)\n\nTimestep: 900000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1100\ncurrent episode reward: 0.0000\nepisodes: 270\nexploration: 0.19000\nlearning_rate: 0.00010\nelapsed time: 3428.9 seconds (0.95 hours)\n\nTimestep: 910000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1100\ncurrent episode reward: 0.0000\nepisodes: 273\nexploration: 0.18100\nlearning_rate: 0.00010\nelapsed time: 3472.8 seconds (0.96 hours)\n\nTimestep: 920000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1100\ncurrent episode reward: 0.0000\nepisodes: 276\nexploration: 0.17200\nlearning_rate: 0.00010\nelapsed time: 3517.8 seconds (0.98 hours)\n\nTimestep: 930000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1100\ncurrent episode reward: 0.0000\nepisodes: 279\nexploration: 0.16300\nlearning_rate: 0.00010\nelapsed time: 3563.0 seconds (0.99 hours)\n\nTimestep: 940000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1100\ncurrent episode reward: 0.0000\nepisodes: 282\nexploration: 0.15400\nlearning_rate: 0.00010\nelapsed time: 3607.6 seconds (1.00 hours)\n\nTimestep: 950000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1100\ncurrent episode reward: 0.0000\nepisodes: 285\nexploration: 0.14500\nlearning_rate: 0.00010\nelapsed time: 3653.0 seconds (1.01 hours)\n\nTimestep: 960000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1100\ncurrent episode reward: 0.0000\nepisodes: 288\nexploration: 0.13600\nlearning_rate: 0.00010\nelapsed time: 3698.3 seconds (1.03 hours)\n\nTimestep: 970000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.1100\ncurrent episode reward: 0.0000\nepisodes: 291\nexploration: 0.12700\nlearning_rate: 0.00010\nelapsed time: 3742.7 seconds (1.04 hours)\n\nTimestep: 980000\nmean reward (100 episodes): 0.1400\nbest mean reward: 0.1400\ncurrent episode reward: 0.0000\nepisodes: 294\nexploration: 0.11800\nlearning_rate: 0.00010\nelapsed time: 3788.0 seconds (1.05 hours)\n\nTimestep: 990000\nmean reward (100 episodes): 0.1400\nbest mean reward: 0.1500\ncurrent episode reward: 0.0000\nepisodes: 297\nexploration: 0.10900\nlearning_rate: 0.00010\nelapsed time: 3833.8 seconds (1.06 hours)\n\nTimestep: 1000000\nmean reward (100 episodes): 0.1400\nbest mean reward: 0.1500\ncurrent episode reward: 0.0000\nepisodes: 300\nexploration: 0.10000\nlearning_rate: 0.00010\nelapsed time: 3878.9 seconds (1.08 hours)\n\nTimestep: 1010000\nmean reward (100 episodes): 0.1400\nbest mean reward: 0.1500\ncurrent episode reward: 0.0000\nepisodes: 303\nexploration: 0.09978\nlearning_rate: 0.00010\nelapsed time: 3924.3 seconds (1.09 hours)\n\nTimestep: 1020000\nmean reward (100 episodes): 0.1500\nbest mean reward: 0.1500\ncurrent episode reward: 0.0000\nepisodes: 307\nexploration: 0.09955\nlearning_rate: 0.00010\nelapsed time: 3969.6 seconds (1.10 hours)\n\nTimestep: 1030000\nmean reward (100 episodes): 0.1500\nbest mean reward: 0.1500\ncurrent episode reward: 0.0000\nepisodes: 310\nexploration: 0.09933\nlearning_rate: 0.00010\nelapsed time: 4016.8 seconds (1.12 hours)\n\nTimestep: 1040000\nmean reward (100 episodes): 0.1900\nbest mean reward: 0.1900\ncurrent episode reward: 0.0000\nepisodes: 313\nexploration: 0.09910\nlearning_rate: 0.00010\nelapsed time: 4062.4 seconds (1.13 hours)\n\nTimestep: 1050000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2400\ncurrent episode reward: 0.0000\nepisodes: 316\nexploration: 0.09888\nlearning_rate: 0.00010\nelapsed time: 4107.2 seconds (1.14 hours)\n\nTimestep: 1060000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2400\ncurrent episode reward: 0.0000\nepisodes: 319\nexploration: 0.09865\nlearning_rate: 0.00010\nelapsed time: 4153.0 seconds (1.15 hours)\n\nTimestep: 1070000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2400\ncurrent episode reward: 0.0000\nepisodes: 322\nexploration: 0.09842\nlearning_rate: 0.00010\nelapsed time: 4199.6 seconds (1.17 hours)\n\nTimestep: 1080000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2400\ncurrent episode reward: 0.0000\nepisodes: 325\nexploration: 0.09820\nlearning_rate: 0.00010\nelapsed time: 4245.3 seconds (1.18 hours)\n\nTimestep: 1090000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2400\ncurrent episode reward: 0.0000\nepisodes: 328\nexploration: 0.09798\nlearning_rate: 0.00010\nelapsed time: 4290.6 seconds (1.19 hours)\n\nTimestep: 1100000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2400\ncurrent episode reward: 0.0000\nepisodes: 331\nexploration: 0.09775\nlearning_rate: 0.00010\nelapsed time: 4336.2 seconds (1.20 hours)\n\nTimestep: 1110000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2400\ncurrent episode reward: 0.0000\nepisodes: 334\nexploration: 0.09753\nlearning_rate: 0.00010\nelapsed time: 4381.4 seconds (1.22 hours)\n\nTimestep: 1120000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2400\ncurrent episode reward: 0.0000\nepisodes: 337\nexploration: 0.09730\nlearning_rate: 0.00010\nelapsed time: 4427.6 seconds (1.23 hours)\n\nTimestep: 1130000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2400\ncurrent episode reward: 0.0000\nepisodes: 340\nexploration: 0.09708\nlearning_rate: 0.00010\nelapsed time: 4473.6 seconds (1.24 hours)\n\nTimestep: 1140000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2400\ncurrent episode reward: 0.0000\nepisodes: 343\nexploration: 0.09685\nlearning_rate: 0.00010\nelapsed time: 4519.5 seconds (1.26 hours)\n\nTimestep: 1150000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2400\ncurrent episode reward: 0.0000\nepisodes: 346\nexploration: 0.09663\nlearning_rate: 0.00010\nelapsed time: 4565.9 seconds (1.27 hours)\n\nTimestep: 1160000\nmean reward (100 episodes): 0.2400\nbest mean reward: 0.2400\ncurrent episode reward: 0.0000\nepisodes: 349\nexploration: 0.09640\nlearning_rate: 0.00010\nelapsed time: 4611.0 seconds (1.28 hours)\n\nTimestep: 1170000\nmean reward (100 episodes): 0.2600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 352\nexploration: 0.09618\nlearning_rate: 0.00010\nelapsed time: 4656.4 seconds (1.29 hours)\n\nTimestep: 1180000\nmean reward (100 episodes): 0.2600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 355\nexploration: 0.09595\nlearning_rate: 0.00010\nelapsed time: 4701.5 seconds (1.31 hours)\n\nTimestep: 1190000\nmean reward (100 episodes): 0.2200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 358\nexploration: 0.09573\nlearning_rate: 0.00010\nelapsed time: 4747.5 seconds (1.32 hours)\n\nTimestep: 1200000\nmean reward (100 episodes): 0.2200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 361\nexploration: 0.09550\nlearning_rate: 0.00010\nelapsed time: 4793.1 seconds (1.33 hours)\n\nTimestep: 1210000\nmean reward (100 episodes): 0.2200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 364\nexploration: 0.09527\nlearning_rate: 0.00010\nelapsed time: 4838.7 seconds (1.34 hours)\n\nTimestep: 1220000\nmean reward (100 episodes): 0.1700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 367\nexploration: 0.09505\nlearning_rate: 0.00010\nelapsed time: 4884.1 seconds (1.36 hours)\n\nTimestep: 1230000\nmean reward (100 episodes): 0.1600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 370\nexploration: 0.09483\nlearning_rate: 0.00010\nelapsed time: 4929.6 seconds (1.37 hours)\n\nTimestep: 1240000\nmean reward (100 episodes): 0.1600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 373\nexploration: 0.09460\nlearning_rate: 0.00010\nelapsed time: 4975.0 seconds (1.38 hours)\n\nTimestep: 1250000\nmean reward (100 episodes): 0.1600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 376\nexploration: 0.09438\nlearning_rate: 0.00010\nelapsed time: 5019.5 seconds (1.39 hours)\n\nTimestep: 1260000\nmean reward (100 episodes): 0.1700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 379\nexploration: 0.09415\nlearning_rate: 0.00010\nelapsed time: 5064.7 seconds (1.41 hours)\n\nTimestep: 1270000\nmean reward (100 episodes): 0.1700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 382\nexploration: 0.09393\nlearning_rate: 0.00010\nelapsed time: 5110.1 seconds (1.42 hours)\n\nTimestep: 1280000\nmean reward (100 episodes): 0.1700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 385\nexploration: 0.09370\nlearning_rate: 0.00010\nelapsed time: 5155.8 seconds (1.43 hours)\n\nTimestep: 1290000\nmean reward (100 episodes): 0.1700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 388\nexploration: 0.09348\nlearning_rate: 0.00010\nelapsed time: 5200.7 seconds (1.44 hours)\n\nTimestep: 1300000\nmean reward (100 episodes): 0.1700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 391\nexploration: 0.09325\nlearning_rate: 0.00010\nelapsed time: 5246.8 seconds (1.46 hours)\n\nTimestep: 1310000\nmean reward (100 episodes): 0.1400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 394\nexploration: 0.09303\nlearning_rate: 0.00010\nelapsed time: 5292.7 seconds (1.47 hours)\n\nTimestep: 1320000\nmean reward (100 episodes): 0.1300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 397\nexploration: 0.09280\nlearning_rate: 0.00010\nelapsed time: 5338.8 seconds (1.48 hours)\n\nTimestep: 1330000\nmean reward (100 episodes): 0.1400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 400\nexploration: 0.09258\nlearning_rate: 0.00010\nelapsed time: 5383.9 seconds (1.50 hours)\n\nTimestep: 1340000\nmean reward (100 episodes): 0.1400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 403\nexploration: 0.09235\nlearning_rate: 0.00010\nelapsed time: 5430.2 seconds (1.51 hours)\n\nTimestep: 1350000\nmean reward (100 episodes): 0.1300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 406\nexploration: 0.09213\nlearning_rate: 0.00010\nelapsed time: 5476.2 seconds (1.52 hours)\n\nTimestep: 1360000\nmean reward (100 episodes): 0.1300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 409\nexploration: 0.09190\nlearning_rate: 0.00010\nelapsed time: 5521.1 seconds (1.53 hours)\n\nTimestep: 1370000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 412\nexploration: 0.09168\nlearning_rate: 0.00010\nelapsed time: 5566.5 seconds (1.55 hours)\n\nTimestep: 1380000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 415\nexploration: 0.09145\nlearning_rate: 0.00010\nelapsed time: 5612.2 seconds (1.56 hours)\n\nTimestep: 1390000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 418\nexploration: 0.09123\nlearning_rate: 0.00010\nelapsed time: 5657.4 seconds (1.57 hours)\n\nTimestep: 1400000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 421\nexploration: 0.09100\nlearning_rate: 0.00010\nelapsed time: 5702.6 seconds (1.58 hours)\n\nTimestep: 1410000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 424\nexploration: 0.09078\nlearning_rate: 0.00009\nelapsed time: 5747.8 seconds (1.60 hours)\n\nTimestep: 1420000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 427\nexploration: 0.09055\nlearning_rate: 0.00009\nelapsed time: 5793.7 seconds (1.61 hours)\n\nTimestep: 1430000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 430\nexploration: 0.09033\nlearning_rate: 0.00009\nelapsed time: 5839.3 seconds (1.62 hours)\n\nTimestep: 1440000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 433\nexploration: 0.09010\nlearning_rate: 0.00009\nelapsed time: 5885.3 seconds (1.63 hours)\n\nTimestep: 1450000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 436\nexploration: 0.08988\nlearning_rate: 0.00009\nelapsed time: 5930.4 seconds (1.65 hours)\n\nTimestep: 1460000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 1.0000\nepisodes: 439\nexploration: 0.08965\nlearning_rate: 0.00009\nelapsed time: 5975.4 seconds (1.66 hours)\n\nTimestep: 1470000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 442\nexploration: 0.08943\nlearning_rate: 0.00009\nelapsed time: 6020.8 seconds (1.67 hours)\n\nTimestep: 1480000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 445\nexploration: 0.08920\nlearning_rate: 0.00009\nelapsed time: 6066.1 seconds (1.69 hours)\n\nTimestep: 1490000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 448\nexploration: 0.08897\nlearning_rate: 0.00009\nelapsed time: 6112.0 seconds (1.70 hours)\n\nTimestep: 1500000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 451\nexploration: 0.08875\nlearning_rate: 0.00009\nelapsed time: 6157.2 seconds (1.71 hours)\n\nTimestep: 1510000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 454\nexploration: 0.08853\nlearning_rate: 0.00009\nelapsed time: 6202.2 seconds (1.72 hours)\n\nTimestep: 1520000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 457\nexploration: 0.08830\nlearning_rate: 0.00009\nelapsed time: 6247.6 seconds (1.74 hours)\n\nTimestep: 1530000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 460\nexploration: 0.08808\nlearning_rate: 0.00009\nelapsed time: 6293.0 seconds (1.75 hours)\n\nTimestep: 1540000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 463\nexploration: 0.08785\nlearning_rate: 0.00009\nelapsed time: 6338.6 seconds (1.76 hours)\n\nTimestep: 1550000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 466\nexploration: 0.08763\nlearning_rate: 0.00009\nelapsed time: 6384.6 seconds (1.77 hours)\n\nTimestep: 1560000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 469\nexploration: 0.08740\nlearning_rate: 0.00009\nelapsed time: 6430.7 seconds (1.79 hours)\n\nTimestep: 1570000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 472\nexploration: 0.08718\nlearning_rate: 0.00009\nelapsed time: 6475.9 seconds (1.80 hours)\n\nTimestep: 1580000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 475\nexploration: 0.08695\nlearning_rate: 0.00009\nelapsed time: 6521.1 seconds (1.81 hours)\n\nTimestep: 1590000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 478\nexploration: 0.08673\nlearning_rate: 0.00009\nelapsed time: 6566.3 seconds (1.82 hours)\n\nTimestep: 1600000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 481\nexploration: 0.08650\nlearning_rate: 0.00009\nelapsed time: 6611.6 seconds (1.84 hours)\n\nTimestep: 1610000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 484\nexploration: 0.08628\nlearning_rate: 0.00009\nelapsed time: 6656.9 seconds (1.85 hours)\n\nTimestep: 1620000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 487\nexploration: 0.08605\nlearning_rate: 0.00009\nelapsed time: 6702.4 seconds (1.86 hours)\n\nTimestep: 1630000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 490\nexploration: 0.08582\nlearning_rate: 0.00009\nelapsed time: 6748.0 seconds (1.87 hours)\n\nTimestep: 1640000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 493\nexploration: 0.08560\nlearning_rate: 0.00009\nelapsed time: 6793.4 seconds (1.89 hours)\n\nTimestep: 1650000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 496\nexploration: 0.08538\nlearning_rate: 0.00009\nelapsed time: 6839.6 seconds (1.90 hours)\n\nTimestep: 1660000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 499\nexploration: 0.08515\nlearning_rate: 0.00009\nelapsed time: 6884.9 seconds (1.91 hours)\n\nTimestep: 1670000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 502\nexploration: 0.08493\nlearning_rate: 0.00009\nelapsed time: 6930.5 seconds (1.93 hours)\n\nTimestep: 1680000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 505\nexploration: 0.08470\nlearning_rate: 0.00009\nelapsed time: 6976.5 seconds (1.94 hours)\n\nTimestep: 1690000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 508\nexploration: 0.08448\nlearning_rate: 0.00009\nelapsed time: 7022.2 seconds (1.95 hours)\n\nTimestep: 1700000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 511\nexploration: 0.08425\nlearning_rate: 0.00009\nelapsed time: 7068.4 seconds (1.96 hours)\n\nTimestep: 1710000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 514\nexploration: 0.08403\nlearning_rate: 0.00009\nelapsed time: 7115.4 seconds (1.98 hours)\n\nTimestep: 1720000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 517\nexploration: 0.08380\nlearning_rate: 0.00009\nelapsed time: 7160.8 seconds (1.99 hours)\n\nTimestep: 1730000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 520\nexploration: 0.08358\nlearning_rate: 0.00009\nelapsed time: 7206.0 seconds (2.00 hours)\n\nTimestep: 1740000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 523\nexploration: 0.08335\nlearning_rate: 0.00009\nelapsed time: 7252.2 seconds (2.01 hours)\n\nTimestep: 1750000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 526\nexploration: 0.08313\nlearning_rate: 0.00009\nelapsed time: 7297.9 seconds (2.03 hours)\n\nTimestep: 1760000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 529\nexploration: 0.08290\nlearning_rate: 0.00009\nelapsed time: 7343.7 seconds (2.04 hours)\n\nTimestep: 1770000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 532\nexploration: 0.08267\nlearning_rate: 0.00009\nelapsed time: 7389.9 seconds (2.05 hours)\n\nTimestep: 1780000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 535\nexploration: 0.08245\nlearning_rate: 0.00009\nelapsed time: 7435.9 seconds (2.07 hours)\n\nTimestep: 1790000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 538\nexploration: 0.08223\nlearning_rate: 0.00009\nelapsed time: 7482.2 seconds (2.08 hours)\n\nTimestep: 1800000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 541\nexploration: 0.08200\nlearning_rate: 0.00009\nelapsed time: 7528.1 seconds (2.09 hours)\n\nTimestep: 1810000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 544\nexploration: 0.08178\nlearning_rate: 0.00009\nelapsed time: 7573.9 seconds (2.10 hours)\n\nTimestep: 1820000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 547\nexploration: 0.08155\nlearning_rate: 0.00009\nelapsed time: 7619.4 seconds (2.12 hours)\n\nTimestep: 1830000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 550\nexploration: 0.08133\nlearning_rate: 0.00009\nelapsed time: 7664.6 seconds (2.13 hours)\n\nTimestep: 1840000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 553\nexploration: 0.08110\nlearning_rate: 0.00009\nelapsed time: 7709.7 seconds (2.14 hours)\n\nTimestep: 1850000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 556\nexploration: 0.08088\nlearning_rate: 0.00009\nelapsed time: 7754.8 seconds (2.15 hours)\n\nTimestep: 1860000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 559\nexploration: 0.08065\nlearning_rate: 0.00009\nelapsed time: 7800.0 seconds (2.17 hours)\n\nTimestep: 1870000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 562\nexploration: 0.08042\nlearning_rate: 0.00009\nelapsed time: 7846.0 seconds (2.18 hours)\n\nTimestep: 1880000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 565\nexploration: 0.08020\nlearning_rate: 0.00009\nelapsed time: 7892.0 seconds (2.19 hours)\n\nTimestep: 1890000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 568\nexploration: 0.07998\nlearning_rate: 0.00009\nelapsed time: 7936.8 seconds (2.20 hours)\n\nTimestep: 1900000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 571\nexploration: 0.07975\nlearning_rate: 0.00009\nelapsed time: 7981.9 seconds (2.22 hours)\n\nTimestep: 1910000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 1.0000\nepisodes: 574\nexploration: 0.07952\nlearning_rate: 0.00009\nelapsed time: 8028.4 seconds (2.23 hours)\n\nTimestep: 1920000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 577\nexploration: 0.07930\nlearning_rate: 0.00009\nelapsed time: 8073.7 seconds (2.24 hours)\n\nTimestep: 1930000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 580\nexploration: 0.07908\nlearning_rate: 0.00009\nelapsed time: 8119.4 seconds (2.26 hours)\n\nTimestep: 1940000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 583\nexploration: 0.07885\nlearning_rate: 0.00009\nelapsed time: 8165.5 seconds (2.27 hours)\n\nTimestep: 1950000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 586\nexploration: 0.07863\nlearning_rate: 0.00009\nelapsed time: 8211.3 seconds (2.28 hours)\n\nTimestep: 1960000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 589\nexploration: 0.07840\nlearning_rate: 0.00009\nelapsed time: 8257.0 seconds (2.29 hours)\n\nTimestep: 1970000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 592\nexploration: 0.07818\nlearning_rate: 0.00009\nelapsed time: 8302.9 seconds (2.31 hours)\n\nTimestep: 1980000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 595\nexploration: 0.07795\nlearning_rate: 0.00009\nelapsed time: 8348.2 seconds (2.32 hours)\n\nTimestep: 1990000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 598\nexploration: 0.07773\nlearning_rate: 0.00009\nelapsed time: 8393.7 seconds (2.33 hours)\n\nTimestep: 2000000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 601\nexploration: 0.07750\nlearning_rate: 0.00009\nelapsed time: 8439.2 seconds (2.34 hours)\n\nTimestep: 2010000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 604\nexploration: 0.07728\nlearning_rate: 0.00009\nelapsed time: 8483.9 seconds (2.36 hours)\n\nTimestep: 2020000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.2600\ncurrent episode reward: 1.0000\nepisodes: 607\nexploration: 0.07705\nlearning_rate: 0.00009\nelapsed time: 8529.9 seconds (2.37 hours)\n\nTimestep: 2030000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 610\nexploration: 0.07683\nlearning_rate: 0.00009\nelapsed time: 8575.4 seconds (2.38 hours)\n\nTimestep: 2040000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 614\nexploration: 0.07660\nlearning_rate: 0.00009\nelapsed time: 8620.6 seconds (2.39 hours)\n\nTimestep: 2050000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.2600\ncurrent episode reward: 1.0000\nepisodes: 617\nexploration: 0.07637\nlearning_rate: 0.00009\nelapsed time: 8666.0 seconds (2.41 hours)\n\nTimestep: 2060000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 620\nexploration: 0.07615\nlearning_rate: 0.00009\nelapsed time: 8711.8 seconds (2.42 hours)\n\nTimestep: 2070000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 623\nexploration: 0.07593\nlearning_rate: 0.00009\nelapsed time: 8757.7 seconds (2.43 hours)\n\nTimestep: 2080000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 626\nexploration: 0.07570\nlearning_rate: 0.00009\nelapsed time: 8802.9 seconds (2.45 hours)\n\nTimestep: 2090000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 629\nexploration: 0.07548\nlearning_rate: 0.00009\nelapsed time: 8848.0 seconds (2.46 hours)\n\nTimestep: 2100000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 632\nexploration: 0.07525\nlearning_rate: 0.00009\nelapsed time: 8893.8 seconds (2.47 hours)\n\nTimestep: 2110000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 635\nexploration: 0.07503\nlearning_rate: 0.00009\nelapsed time: 8939.9 seconds (2.48 hours)\n\nTimestep: 2120000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 638\nexploration: 0.07480\nlearning_rate: 0.00009\nelapsed time: 8985.6 seconds (2.50 hours)\n\nTimestep: 2130000\nmean reward (100 episodes): 0.1200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 641\nexploration: 0.07458\nlearning_rate: 0.00009\nelapsed time: 9031.6 seconds (2.51 hours)\n\nTimestep: 2140000\nmean reward (100 episodes): 0.1200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 644\nexploration: 0.07435\nlearning_rate: 0.00009\nelapsed time: 9077.0 seconds (2.52 hours)\n\nTimestep: 2150000\nmean reward (100 episodes): 0.1200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 647\nexploration: 0.07412\nlearning_rate: 0.00009\nelapsed time: 9122.3 seconds (2.53 hours)\n\nTimestep: 2160000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.2600\ncurrent episode reward: 1.0000\nepisodes: 650\nexploration: 0.07390\nlearning_rate: 0.00009\nelapsed time: 9167.8 seconds (2.55 hours)\n\nTimestep: 2170000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 653\nexploration: 0.07368\nlearning_rate: 0.00009\nelapsed time: 9214.7 seconds (2.56 hours)\n\nTimestep: 2180000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 656\nexploration: 0.07345\nlearning_rate: 0.00009\nelapsed time: 9260.8 seconds (2.57 hours)\n\nTimestep: 2190000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 659\nexploration: 0.07322\nlearning_rate: 0.00009\nelapsed time: 9307.1 seconds (2.59 hours)\n\nTimestep: 2200000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 662\nexploration: 0.07300\nlearning_rate: 0.00009\nelapsed time: 9353.1 seconds (2.60 hours)\n\nTimestep: 2210000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 665\nexploration: 0.07278\nlearning_rate: 0.00008\nelapsed time: 9399.3 seconds (2.61 hours)\n\nTimestep: 2220000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 668\nexploration: 0.07255\nlearning_rate: 0.00008\nelapsed time: 9444.3 seconds (2.62 hours)\n\nTimestep: 2230000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 671\nexploration: 0.07233\nlearning_rate: 0.00008\nelapsed time: 9490.3 seconds (2.64 hours)\n\nTimestep: 2240000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 674\nexploration: 0.07210\nlearning_rate: 0.00008\nelapsed time: 9536.7 seconds (2.65 hours)\n\nTimestep: 2250000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 677\nexploration: 0.07187\nlearning_rate: 0.00008\nelapsed time: 9582.5 seconds (2.66 hours)\n\nTimestep: 2260000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 680\nexploration: 0.07165\nlearning_rate: 0.00008\nelapsed time: 9628.6 seconds (2.67 hours)\n\nTimestep: 2270000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 683\nexploration: 0.07143\nlearning_rate: 0.00008\nelapsed time: 9674.3 seconds (2.69 hours)\n\nTimestep: 2280000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 686\nexploration: 0.07120\nlearning_rate: 0.00008\nelapsed time: 9719.9 seconds (2.70 hours)\n\nTimestep: 2290000\nmean reward (100 episodes): 0.1100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 689\nexploration: 0.07097\nlearning_rate: 0.00008\nelapsed time: 9765.7 seconds (2.71 hours)\n\nTimestep: 2300000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 692\nexploration: 0.07075\nlearning_rate: 0.00008\nelapsed time: 9811.7 seconds (2.73 hours)\n\nTimestep: 2310000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 695\nexploration: 0.07053\nlearning_rate: 0.00008\nelapsed time: 9857.1 seconds (2.74 hours)\n\nTimestep: 2320000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 698\nexploration: 0.07030\nlearning_rate: 0.00008\nelapsed time: 9902.5 seconds (2.75 hours)\n\nTimestep: 2330000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 701\nexploration: 0.07007\nlearning_rate: 0.00008\nelapsed time: 9948.5 seconds (2.76 hours)\n\nTimestep: 2340000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 704\nexploration: 0.06985\nlearning_rate: 0.00008\nelapsed time: 9994.2 seconds (2.78 hours)\n\nTimestep: 2350000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 707\nexploration: 0.06962\nlearning_rate: 0.00008\nelapsed time: 10040.5 seconds (2.79 hours)\n\nTimestep: 2360000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.2600\ncurrent episode reward: 1.0000\nepisodes: 710\nexploration: 0.06940\nlearning_rate: 0.00008\nelapsed time: 10087.4 seconds (2.80 hours)\n\nTimestep: 2370000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 713\nexploration: 0.06918\nlearning_rate: 0.00008\nelapsed time: 10133.3 seconds (2.81 hours)\n\nTimestep: 2380000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 716\nexploration: 0.06895\nlearning_rate: 0.00008\nelapsed time: 10179.4 seconds (2.83 hours)\n\nTimestep: 2390000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 719\nexploration: 0.06873\nlearning_rate: 0.00008\nelapsed time: 10225.9 seconds (2.84 hours)\n\nTimestep: 2400000\nmean reward (100 episodes): 0.0900\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 722\nexploration: 0.06850\nlearning_rate: 0.00008\nelapsed time: 10272.0 seconds (2.85 hours)\n\nTimestep: 2410000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 725\nexploration: 0.06828\nlearning_rate: 0.00008\nelapsed time: 10317.7 seconds (2.87 hours)\n\nTimestep: 2420000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 728\nexploration: 0.06805\nlearning_rate: 0.00008\nelapsed time: 10362.8 seconds (2.88 hours)\n\nTimestep: 2430000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 731\nexploration: 0.06782\nlearning_rate: 0.00008\nelapsed time: 10409.6 seconds (2.89 hours)\n\nTimestep: 2440000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 734\nexploration: 0.06760\nlearning_rate: 0.00008\nelapsed time: 10455.5 seconds (2.90 hours)\n\nTimestep: 2450000\nmean reward (100 episodes): 0.1000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 737\nexploration: 0.06738\nlearning_rate: 0.00008\nelapsed time: 10501.5 seconds (2.92 hours)\n\nTimestep: 2460000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 740\nexploration: 0.06715\nlearning_rate: 0.00008\nelapsed time: 10547.8 seconds (2.93 hours)\n\nTimestep: 2470000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 743\nexploration: 0.06693\nlearning_rate: 0.00008\nelapsed time: 10594.3 seconds (2.94 hours)\n\nTimestep: 2480000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 746\nexploration: 0.06670\nlearning_rate: 0.00008\nelapsed time: 10640.2 seconds (2.96 hours)\n\nTimestep: 2490000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 749\nexploration: 0.06648\nlearning_rate: 0.00008\nelapsed time: 10687.0 seconds (2.97 hours)\n\nTimestep: 2500000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 752\nexploration: 0.06625\nlearning_rate: 0.00008\nelapsed time: 10733.3 seconds (2.98 hours)\n\nTimestep: 2510000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 755\nexploration: 0.06603\nlearning_rate: 0.00008\nelapsed time: 10779.0 seconds (2.99 hours)\n\nTimestep: 2520000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 758\nexploration: 0.06580\nlearning_rate: 0.00008\nelapsed time: 10824.9 seconds (3.01 hours)\n\nTimestep: 2530000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 761\nexploration: 0.06557\nlearning_rate: 0.00008\nelapsed time: 10871.1 seconds (3.02 hours)\n\nTimestep: 2540000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 764\nexploration: 0.06535\nlearning_rate: 0.00008\nelapsed time: 10917.4 seconds (3.03 hours)\n\nTimestep: 2550000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 767\nexploration: 0.06513\nlearning_rate: 0.00008\nelapsed time: 10963.7 seconds (3.05 hours)\n\nTimestep: 2560000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 770\nexploration: 0.06490\nlearning_rate: 0.00008\nelapsed time: 11009.9 seconds (3.06 hours)\n\nTimestep: 2570000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 773\nexploration: 0.06468\nlearning_rate: 0.00008\nelapsed time: 11056.2 seconds (3.07 hours)\n\nTimestep: 2580000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 776\nexploration: 0.06445\nlearning_rate: 0.00008\nelapsed time: 11102.7 seconds (3.08 hours)\n\nTimestep: 2590000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 1.0000\nepisodes: 779\nexploration: 0.06423\nlearning_rate: 0.00008\nelapsed time: 11148.5 seconds (3.10 hours)\n\nTimestep: 2600000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 782\nexploration: 0.06400\nlearning_rate: 0.00008\nelapsed time: 11194.0 seconds (3.11 hours)\n\nTimestep: 2610000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 785\nexploration: 0.06377\nlearning_rate: 0.00008\nelapsed time: 11240.0 seconds (3.12 hours)\n\nTimestep: 2620000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 788\nexploration: 0.06355\nlearning_rate: 0.00008\nelapsed time: 11285.2 seconds (3.13 hours)\n\nTimestep: 2630000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 791\nexploration: 0.06333\nlearning_rate: 0.00008\nelapsed time: 11330.8 seconds (3.15 hours)\n\nTimestep: 2640000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 794\nexploration: 0.06310\nlearning_rate: 0.00008\nelapsed time: 11376.3 seconds (3.16 hours)\n\nTimestep: 2650000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 797\nexploration: 0.06288\nlearning_rate: 0.00008\nelapsed time: 11422.1 seconds (3.17 hours)\n\nTimestep: 2660000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 800\nexploration: 0.06265\nlearning_rate: 0.00008\nelapsed time: 11467.8 seconds (3.19 hours)\n\nTimestep: 2670000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 803\nexploration: 0.06243\nlearning_rate: 0.00008\nelapsed time: 11513.9 seconds (3.20 hours)\n\nTimestep: 2680000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 806\nexploration: 0.06220\nlearning_rate: 0.00008\nelapsed time: 11560.4 seconds (3.21 hours)\n\nTimestep: 2690000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 809\nexploration: 0.06198\nlearning_rate: 0.00008\nelapsed time: 11606.7 seconds (3.22 hours)\n\nTimestep: 2700000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 812\nexploration: 0.06175\nlearning_rate: 0.00008\nelapsed time: 11652.7 seconds (3.24 hours)\n\nTimestep: 2710000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 815\nexploration: 0.06153\nlearning_rate: 0.00008\nelapsed time: 11699.5 seconds (3.25 hours)\n\nTimestep: 2720000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 818\nexploration: 0.06130\nlearning_rate: 0.00008\nelapsed time: 11745.4 seconds (3.26 hours)\n\nTimestep: 2730000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 821\nexploration: 0.06108\nlearning_rate: 0.00008\nelapsed time: 11790.4 seconds (3.28 hours)\n\nTimestep: 2740000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 824\nexploration: 0.06085\nlearning_rate: 0.00008\nelapsed time: 11836.6 seconds (3.29 hours)\n\nTimestep: 2750000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 827\nexploration: 0.06062\nlearning_rate: 0.00008\nelapsed time: 11881.5 seconds (3.30 hours)\n\nTimestep: 2760000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 830\nexploration: 0.06040\nlearning_rate: 0.00008\nelapsed time: 11927.5 seconds (3.31 hours)\n\nTimestep: 2770000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 833\nexploration: 0.06017\nlearning_rate: 0.00008\nelapsed time: 11973.6 seconds (3.33 hours)\n\nTimestep: 2780000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 836\nexploration: 0.05995\nlearning_rate: 0.00008\nelapsed time: 12019.6 seconds (3.34 hours)\n\nTimestep: 2790000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 839\nexploration: 0.05973\nlearning_rate: 0.00008\nelapsed time: 12065.1 seconds (3.35 hours)\n\nTimestep: 2800000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 1.0000\nepisodes: 842\nexploration: 0.05950\nlearning_rate: 0.00008\nelapsed time: 12111.2 seconds (3.36 hours)\n\nTimestep: 2810000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 845\nexploration: 0.05928\nlearning_rate: 0.00008\nelapsed time: 12156.6 seconds (3.38 hours)\n\nTimestep: 2820000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 848\nexploration: 0.05905\nlearning_rate: 0.00008\nelapsed time: 12201.7 seconds (3.39 hours)\n\nTimestep: 2830000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 851\nexploration: 0.05883\nlearning_rate: 0.00008\nelapsed time: 12247.2 seconds (3.40 hours)\n\nTimestep: 2840000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 854\nexploration: 0.05860\nlearning_rate: 0.00008\nelapsed time: 12293.1 seconds (3.41 hours)\n\nTimestep: 2850000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 857\nexploration: 0.05837\nlearning_rate: 0.00008\nelapsed time: 12338.9 seconds (3.43 hours)\n\nTimestep: 2860000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 860\nexploration: 0.05815\nlearning_rate: 0.00008\nelapsed time: 12385.2 seconds (3.44 hours)\n\nTimestep: 2870000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 863\nexploration: 0.05792\nlearning_rate: 0.00008\nelapsed time: 12431.0 seconds (3.45 hours)\n\nTimestep: 2880000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 866\nexploration: 0.05770\nlearning_rate: 0.00008\nelapsed time: 12477.1 seconds (3.47 hours)\n\nTimestep: 2890000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 869\nexploration: 0.05748\nlearning_rate: 0.00008\nelapsed time: 12523.2 seconds (3.48 hours)\n\nTimestep: 2900000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 1.0000\nepisodes: 872\nexploration: 0.05725\nlearning_rate: 0.00008\nelapsed time: 12569.2 seconds (3.49 hours)\n\nTimestep: 2910000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 875\nexploration: 0.05702\nlearning_rate: 0.00008\nelapsed time: 12615.2 seconds (3.50 hours)\n\nTimestep: 2920000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 878\nexploration: 0.05680\nlearning_rate: 0.00008\nelapsed time: 12660.8 seconds (3.52 hours)\n\nTimestep: 2930000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 881\nexploration: 0.05658\nlearning_rate: 0.00008\nelapsed time: 12707.2 seconds (3.53 hours)\n\nTimestep: 2940000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 884\nexploration: 0.05635\nlearning_rate: 0.00008\nelapsed time: 12753.5 seconds (3.54 hours)\n\nTimestep: 2950000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 1.0000\nepisodes: 887\nexploration: 0.05613\nlearning_rate: 0.00008\nelapsed time: 12798.8 seconds (3.56 hours)\n\nTimestep: 2960000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 890\nexploration: 0.05590\nlearning_rate: 0.00008\nelapsed time: 12844.7 seconds (3.57 hours)\n\nTimestep: 2970000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 893\nexploration: 0.05568\nlearning_rate: 0.00008\nelapsed time: 12890.7 seconds (3.58 hours)\n\nTimestep: 2980000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 896\nexploration: 0.05545\nlearning_rate: 0.00008\nelapsed time: 12936.4 seconds (3.59 hours)\n\nTimestep: 2990000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 899\nexploration: 0.05523\nlearning_rate: 0.00008\nelapsed time: 12982.3 seconds (3.61 hours)\n\nTimestep: 3000000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 902\nexploration: 0.05500\nlearning_rate: 0.00008\nelapsed time: 13028.3 seconds (3.62 hours)\n\nTimestep: 3010000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 905\nexploration: 0.05478\nlearning_rate: 0.00007\nelapsed time: 13074.6 seconds (3.63 hours)\n\nTimestep: 3020000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 908\nexploration: 0.05455\nlearning_rate: 0.00007\nelapsed time: 13121.2 seconds (3.64 hours)\n\nTimestep: 3030000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 911\nexploration: 0.05433\nlearning_rate: 0.00007\nelapsed time: 13167.6 seconds (3.66 hours)\n\nTimestep: 3040000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 914\nexploration: 0.05410\nlearning_rate: 0.00007\nelapsed time: 13213.4 seconds (3.67 hours)\n\nTimestep: 3050000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 917\nexploration: 0.05388\nlearning_rate: 0.00007\nelapsed time: 13260.0 seconds (3.68 hours)\n\nTimestep: 3060000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 921\nexploration: 0.05365\nlearning_rate: 0.00007\nelapsed time: 13305.8 seconds (3.70 hours)\n\nTimestep: 3070000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 924\nexploration: 0.05343\nlearning_rate: 0.00007\nelapsed time: 13352.2 seconds (3.71 hours)\n\nTimestep: 3080000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 927\nexploration: 0.05320\nlearning_rate: 0.00007\nelapsed time: 13397.6 seconds (3.72 hours)\n\nTimestep: 3090000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 930\nexploration: 0.05298\nlearning_rate: 0.00007\nelapsed time: 13443.1 seconds (3.73 hours)\n\nTimestep: 3100000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 933\nexploration: 0.05275\nlearning_rate: 0.00007\nelapsed time: 13489.0 seconds (3.75 hours)\n\nTimestep: 3110000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 2.0000\nepisodes: 936\nexploration: 0.05253\nlearning_rate: 0.00007\nelapsed time: 13535.0 seconds (3.76 hours)\n\nTimestep: 3120000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 939\nexploration: 0.05230\nlearning_rate: 0.00007\nelapsed time: 13581.1 seconds (3.77 hours)\n\nTimestep: 3130000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 942\nexploration: 0.05208\nlearning_rate: 0.00007\nelapsed time: 13628.0 seconds (3.79 hours)\n\nTimestep: 3140000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 945\nexploration: 0.05185\nlearning_rate: 0.00007\nelapsed time: 13673.4 seconds (3.80 hours)\n\nTimestep: 3150000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 948\nexploration: 0.05163\nlearning_rate: 0.00007\nelapsed time: 13719.0 seconds (3.81 hours)\n\nTimestep: 3160000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 951\nexploration: 0.05140\nlearning_rate: 0.00007\nelapsed time: 13765.1 seconds (3.82 hours)\n\nTimestep: 3170000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 954\nexploration: 0.05117\nlearning_rate: 0.00007\nelapsed time: 13811.1 seconds (3.84 hours)\n\nTimestep: 3180000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 957\nexploration: 0.05095\nlearning_rate: 0.00007\nelapsed time: 13857.5 seconds (3.85 hours)\n\nTimestep: 3190000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 960\nexploration: 0.05072\nlearning_rate: 0.00007\nelapsed time: 13902.8 seconds (3.86 hours)\n\nTimestep: 3200000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 963\nexploration: 0.05050\nlearning_rate: 0.00007\nelapsed time: 13948.8 seconds (3.87 hours)\n\nTimestep: 3210000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 966\nexploration: 0.05028\nlearning_rate: 0.00007\nelapsed time: 13995.1 seconds (3.89 hours)\n\nTimestep: 3220000\nmean reward (100 episodes): 0.0700\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 969\nexploration: 0.05005\nlearning_rate: 0.00007\nelapsed time: 14040.4 seconds (3.90 hours)\n\nTimestep: 3230000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 972\nexploration: 0.04983\nlearning_rate: 0.00007\nelapsed time: 14085.9 seconds (3.91 hours)\n\nTimestep: 3240000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 975\nexploration: 0.04960\nlearning_rate: 0.00007\nelapsed time: 14131.6 seconds (3.93 hours)\n\nTimestep: 3250000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 978\nexploration: 0.04938\nlearning_rate: 0.00007\nelapsed time: 14177.3 seconds (3.94 hours)\n\nTimestep: 3260000\nmean reward (100 episodes): 0.0600\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 981\nexploration: 0.04915\nlearning_rate: 0.00007\nelapsed time: 14223.4 seconds (3.95 hours)\n\nTimestep: 3270000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 984\nexploration: 0.04892\nlearning_rate: 0.00007\nelapsed time: 14270.0 seconds (3.96 hours)\n\nTimestep: 3280000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 987\nexploration: 0.04870\nlearning_rate: 0.00007\nelapsed time: 14316.2 seconds (3.98 hours)\n\nTimestep: 3290000\nmean reward (100 episodes): 0.0400\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 990\nexploration: 0.04847\nlearning_rate: 0.00007\nelapsed time: 14361.7 seconds (3.99 hours)\n\nTimestep: 3300000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 1.0000\nepisodes: 993\nexploration: 0.04825\nlearning_rate: 0.00007\nelapsed time: 14408.2 seconds (4.00 hours)\n\nTimestep: 3310000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 996\nexploration: 0.04802\nlearning_rate: 0.00007\nelapsed time: 14453.3 seconds (4.01 hours)\n\nTimestep: 3320000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 999\nexploration: 0.04780\nlearning_rate: 0.00007\nelapsed time: 14499.3 seconds (4.03 hours)\n\nTimestep: 3330000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1002\nexploration: 0.04757\nlearning_rate: 0.00007\nelapsed time: 14546.0 seconds (4.04 hours)\n\nTimestep: 3340000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1005\nexploration: 0.04735\nlearning_rate: 0.00007\nelapsed time: 14592.3 seconds (4.05 hours)\n\nTimestep: 3350000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1008\nexploration: 0.04713\nlearning_rate: 0.00007\nelapsed time: 14638.1 seconds (4.07 hours)\n\nTimestep: 3360000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1011\nexploration: 0.04690\nlearning_rate: 0.00007\nelapsed time: 14684.3 seconds (4.08 hours)\n\nTimestep: 3370000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1014\nexploration: 0.04667\nlearning_rate: 0.00007\nelapsed time: 14729.9 seconds (4.09 hours)\n\nTimestep: 3380000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1017\nexploration: 0.04645\nlearning_rate: 0.00007\nelapsed time: 14775.4 seconds (4.10 hours)\n\nTimestep: 3390000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1020\nexploration: 0.04622\nlearning_rate: 0.00007\nelapsed time: 14820.8 seconds (4.12 hours)\n\nTimestep: 3400000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1023\nexploration: 0.04600\nlearning_rate: 0.00007\nelapsed time: 14866.9 seconds (4.13 hours)\n\nTimestep: 3410000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1026\nexploration: 0.04577\nlearning_rate: 0.00007\nelapsed time: 14912.5 seconds (4.14 hours)\n\nTimestep: 3420000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1029\nexploration: 0.04555\nlearning_rate: 0.00007\nelapsed time: 14959.0 seconds (4.16 hours)\n\nTimestep: 3430000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1032\nexploration: 0.04532\nlearning_rate: 0.00007\nelapsed time: 15005.0 seconds (4.17 hours)\n\nTimestep: 3440000\nmean reward (100 episodes): 0.0500\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1035\nexploration: 0.04510\nlearning_rate: 0.00007\nelapsed time: 15050.7 seconds (4.18 hours)\n\nTimestep: 3450000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1038\nexploration: 0.04487\nlearning_rate: 0.00007\nelapsed time: 15096.2 seconds (4.19 hours)\n\nTimestep: 3460000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1041\nexploration: 0.04465\nlearning_rate: 0.00007\nelapsed time: 15141.9 seconds (4.21 hours)\n\nTimestep: 3470000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1044\nexploration: 0.04442\nlearning_rate: 0.00007\nelapsed time: 15187.6 seconds (4.22 hours)\n\nTimestep: 3480000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1047\nexploration: 0.04420\nlearning_rate: 0.00007\nelapsed time: 15233.0 seconds (4.23 hours)\n\nTimestep: 3490000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1050\nexploration: 0.04397\nlearning_rate: 0.00007\nelapsed time: 15279.4 seconds (4.24 hours)\n\nTimestep: 3500000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1053\nexploration: 0.04375\nlearning_rate: 0.00007\nelapsed time: 15325.7 seconds (4.26 hours)\n\nTimestep: 3510000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1056\nexploration: 0.04353\nlearning_rate: 0.00007\nelapsed time: 15371.9 seconds (4.27 hours)\n\nTimestep: 3520000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1059\nexploration: 0.04330\nlearning_rate: 0.00007\nelapsed time: 15417.7 seconds (4.28 hours)\n\nTimestep: 3530000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1062\nexploration: 0.04308\nlearning_rate: 0.00007\nelapsed time: 15463.3 seconds (4.30 hours)\n\nTimestep: 3540000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1065\nexploration: 0.04285\nlearning_rate: 0.00007\nelapsed time: 15509.1 seconds (4.31 hours)\n\nTimestep: 3550000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1068\nexploration: 0.04263\nlearning_rate: 0.00007\nelapsed time: 15554.8 seconds (4.32 hours)\n\nTimestep: 3560000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1071\nexploration: 0.04240\nlearning_rate: 0.00007\nelapsed time: 15601.3 seconds (4.33 hours)\n\nTimestep: 3570000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1074\nexploration: 0.04218\nlearning_rate: 0.00007\nelapsed time: 15647.4 seconds (4.35 hours)\n\nTimestep: 3580000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1077\nexploration: 0.04195\nlearning_rate: 0.00007\nelapsed time: 15693.1 seconds (4.36 hours)\n\nTimestep: 3590000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1080\nexploration: 0.04173\nlearning_rate: 0.00007\nelapsed time: 15738.8 seconds (4.37 hours)\n\nTimestep: 3600000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1083\nexploration: 0.04150\nlearning_rate: 0.00007\nelapsed time: 15784.8 seconds (4.38 hours)\n\nTimestep: 3610000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1086\nexploration: 0.04127\nlearning_rate: 0.00007\nelapsed time: 15830.6 seconds (4.40 hours)\n\nTimestep: 3620000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1089\nexploration: 0.04105\nlearning_rate: 0.00007\nelapsed time: 15875.8 seconds (4.41 hours)\n\nTimestep: 3630000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1092\nexploration: 0.04083\nlearning_rate: 0.00007\nelapsed time: 15922.5 seconds (4.42 hours)\n\nTimestep: 3640000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1095\nexploration: 0.04060\nlearning_rate: 0.00007\nelapsed time: 15968.0 seconds (4.44 hours)\n\nTimestep: 3650000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1098\nexploration: 0.04038\nlearning_rate: 0.00007\nelapsed time: 16014.8 seconds (4.45 hours)\n\nTimestep: 3660000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1101\nexploration: 0.04015\nlearning_rate: 0.00007\nelapsed time: 16060.6 seconds (4.46 hours)\n\nTimestep: 3670000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1104\nexploration: 0.03993\nlearning_rate: 0.00007\nelapsed time: 16105.8 seconds (4.47 hours)\n\nTimestep: 3680000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1107\nexploration: 0.03970\nlearning_rate: 0.00007\nelapsed time: 16151.6 seconds (4.49 hours)\n\nTimestep: 3690000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1110\nexploration: 0.03947\nlearning_rate: 0.00007\nelapsed time: 16197.7 seconds (4.50 hours)\n\nTimestep: 3700000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1113\nexploration: 0.03925\nlearning_rate: 0.00007\nelapsed time: 16243.3 seconds (4.51 hours)\n\nTimestep: 3710000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1116\nexploration: 0.03902\nlearning_rate: 0.00007\nelapsed time: 16288.7 seconds (4.52 hours)\n\nTimestep: 3720000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1119\nexploration: 0.03880\nlearning_rate: 0.00007\nelapsed time: 16334.3 seconds (4.54 hours)\n\nTimestep: 3730000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1122\nexploration: 0.03857\nlearning_rate: 0.00007\nelapsed time: 16381.0 seconds (4.55 hours)\n\nTimestep: 3740000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1125\nexploration: 0.03835\nlearning_rate: 0.00007\nelapsed time: 16426.5 seconds (4.56 hours)\n\nTimestep: 3750000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1128\nexploration: 0.03812\nlearning_rate: 0.00007\nelapsed time: 16472.5 seconds (4.58 hours)\n\nTimestep: 3760000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1131\nexploration: 0.03790\nlearning_rate: 0.00007\nelapsed time: 16518.8 seconds (4.59 hours)\n\nTimestep: 3770000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1134\nexploration: 0.03768\nlearning_rate: 0.00007\nelapsed time: 16565.0 seconds (4.60 hours)\n\nTimestep: 3780000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1137\nexploration: 0.03745\nlearning_rate: 0.00007\nelapsed time: 16610.7 seconds (4.61 hours)\n\nTimestep: 3790000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1140\nexploration: 0.03722\nlearning_rate: 0.00007\nelapsed time: 16656.8 seconds (4.63 hours)\n\nTimestep: 3800000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1143\nexploration: 0.03700\nlearning_rate: 0.00007\nelapsed time: 16703.1 seconds (4.64 hours)\n\nTimestep: 3810000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1146\nexploration: 0.03678\nlearning_rate: 0.00006\nelapsed time: 16749.4 seconds (4.65 hours)\n\nTimestep: 3820000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1149\nexploration: 0.03655\nlearning_rate: 0.00006\nelapsed time: 16795.8 seconds (4.67 hours)\n\nTimestep: 3830000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1152\nexploration: 0.03632\nlearning_rate: 0.00006\nelapsed time: 16841.6 seconds (4.68 hours)\n\nTimestep: 3840000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1155\nexploration: 0.03610\nlearning_rate: 0.00006\nelapsed time: 16887.8 seconds (4.69 hours)\n\nTimestep: 3850000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1158\nexploration: 0.03587\nlearning_rate: 0.00006\nelapsed time: 16932.8 seconds (4.70 hours)\n\nTimestep: 3860000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1161\nexploration: 0.03565\nlearning_rate: 0.00006\nelapsed time: 16979.9 seconds (4.72 hours)\n\nTimestep: 3870000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1164\nexploration: 0.03542\nlearning_rate: 0.00006\nelapsed time: 17026.7 seconds (4.73 hours)\n\nTimestep: 3880000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1167\nexploration: 0.03520\nlearning_rate: 0.00006\nelapsed time: 17072.9 seconds (4.74 hours)\n\nTimestep: 3890000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1170\nexploration: 0.03497\nlearning_rate: 0.00006\nelapsed time: 17119.4 seconds (4.76 hours)\n\nTimestep: 3900000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1173\nexploration: 0.03475\nlearning_rate: 0.00006\nelapsed time: 17165.4 seconds (4.77 hours)\n\nTimestep: 3910000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1176\nexploration: 0.03453\nlearning_rate: 0.00006\nelapsed time: 17211.3 seconds (4.78 hours)\n\nTimestep: 3920000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1179\nexploration: 0.03430\nlearning_rate: 0.00006\nelapsed time: 17257.1 seconds (4.79 hours)\n\nTimestep: 3930000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1182\nexploration: 0.03407\nlearning_rate: 0.00006\nelapsed time: 17302.6 seconds (4.81 hours)\n\nTimestep: 3940000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 2.0000\nepisodes: 1185\nexploration: 0.03385\nlearning_rate: 0.00006\nelapsed time: 17348.8 seconds (4.82 hours)\n\nTimestep: 3950000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1188\nexploration: 0.03362\nlearning_rate: 0.00006\nelapsed time: 17394.4 seconds (4.83 hours)\n\nTimestep: 3960000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1191\nexploration: 0.03340\nlearning_rate: 0.00006\nelapsed time: 17440.8 seconds (4.84 hours)\n\nTimestep: 3970000\nmean reward (100 episodes): 0.0200\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1194\nexploration: 0.03317\nlearning_rate: 0.00006\nelapsed time: 17487.6 seconds (4.86 hours)\n\nTimestep: 3980000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1197\nexploration: 0.03295\nlearning_rate: 0.00006\nelapsed time: 17533.3 seconds (4.87 hours)\n\nTimestep: 3990000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1200\nexploration: 0.03272\nlearning_rate: 0.00006\nelapsed time: 17579.2 seconds (4.88 hours)\n\nTimestep: 4000000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1203\nexploration: 0.03250\nlearning_rate: 0.00006\nelapsed time: 17625.3 seconds (4.90 hours)\n\nTimestep: 4010000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1206\nexploration: 0.03227\nlearning_rate: 0.00006\nelapsed time: 17671.7 seconds (4.91 hours)\n\nTimestep: 4020000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1209\nexploration: 0.03205\nlearning_rate: 0.00006\nelapsed time: 17717.9 seconds (4.92 hours)\n\nTimestep: 4030000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1212\nexploration: 0.03183\nlearning_rate: 0.00006\nelapsed time: 17763.5 seconds (4.93 hours)\n\nTimestep: 4040000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1215\nexploration: 0.03160\nlearning_rate: 0.00006\nelapsed time: 17810.1 seconds (4.95 hours)\n\nTimestep: 4050000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1218\nexploration: 0.03138\nlearning_rate: 0.00006\nelapsed time: 17856.2 seconds (4.96 hours)\n\nTimestep: 4060000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1221\nexploration: 0.03115\nlearning_rate: 0.00006\nelapsed time: 17903.2 seconds (4.97 hours)\n\nTimestep: 4070000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1224\nexploration: 0.03092\nlearning_rate: 0.00006\nelapsed time: 17949.2 seconds (4.99 hours)\n\nTimestep: 4080000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1227\nexploration: 0.03070\nlearning_rate: 0.00006\nelapsed time: 17995.6 seconds (5.00 hours)\n\nTimestep: 4090000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1231\nexploration: 0.03048\nlearning_rate: 0.00006\nelapsed time: 18042.0 seconds (5.01 hours)\n\nTimestep: 4100000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1234\nexploration: 0.03025\nlearning_rate: 0.00006\nelapsed time: 18087.6 seconds (5.02 hours)\n\nTimestep: 4110000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1237\nexploration: 0.03002\nlearning_rate: 0.00006\nelapsed time: 18134.3 seconds (5.04 hours)\n\nTimestep: 4120000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1240\nexploration: 0.02980\nlearning_rate: 0.00006\nelapsed time: 18179.8 seconds (5.05 hours)\n\nTimestep: 4130000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1243\nexploration: 0.02958\nlearning_rate: 0.00006\nelapsed time: 18225.7 seconds (5.06 hours)\n\nTimestep: 4140000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1246\nexploration: 0.02935\nlearning_rate: 0.00006\nelapsed time: 18271.9 seconds (5.08 hours)\n\nTimestep: 4150000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1249\nexploration: 0.02912\nlearning_rate: 0.00006\nelapsed time: 18317.8 seconds (5.09 hours)\n\nTimestep: 4160000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1252\nexploration: 0.02890\nlearning_rate: 0.00006\nelapsed time: 18364.1 seconds (5.10 hours)\n\nTimestep: 4170000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1255\nexploration: 0.02867\nlearning_rate: 0.00006\nelapsed time: 18410.5 seconds (5.11 hours)\n\nTimestep: 4180000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1258\nexploration: 0.02845\nlearning_rate: 0.00006\nelapsed time: 18456.0 seconds (5.13 hours)\n\nTimestep: 4190000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1261\nexploration: 0.02823\nlearning_rate: 0.00006\nelapsed time: 18502.1 seconds (5.14 hours)\n\nTimestep: 4200000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1264\nexploration: 0.02800\nlearning_rate: 0.00006\nelapsed time: 18548.4 seconds (5.15 hours)\n\nTimestep: 4210000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1267\nexploration: 0.02777\nlearning_rate: 0.00006\nelapsed time: 18594.3 seconds (5.17 hours)\n\nTimestep: 4220000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1270\nexploration: 0.02755\nlearning_rate: 0.00006\nelapsed time: 18640.5 seconds (5.18 hours)\n\nTimestep: 4230000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1273\nexploration: 0.02733\nlearning_rate: 0.00006\nelapsed time: 18686.8 seconds (5.19 hours)\n\nTimestep: 4240000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1276\nexploration: 0.02710\nlearning_rate: 0.00006\nelapsed time: 18733.5 seconds (5.20 hours)\n\nTimestep: 4250000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1279\nexploration: 0.02687\nlearning_rate: 0.00006\nelapsed time: 18779.4 seconds (5.22 hours)\n\nTimestep: 4260000\nmean reward (100 episodes): 0.0300\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1282\nexploration: 0.02665\nlearning_rate: 0.00006\nelapsed time: 18825.6 seconds (5.23 hours)\n\nTimestep: 4270000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1285\nexploration: 0.02642\nlearning_rate: 0.00006\nelapsed time: 18871.1 seconds (5.24 hours)\n\nTimestep: 4280000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1288\nexploration: 0.02620\nlearning_rate: 0.00006\nelapsed time: 18917.3 seconds (5.25 hours)\n\nTimestep: 4290000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1291\nexploration: 0.02597\nlearning_rate: 0.00006\nelapsed time: 18962.8 seconds (5.27 hours)\n\nTimestep: 4300000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1294\nexploration: 0.02575\nlearning_rate: 0.00006\nelapsed time: 19009.1 seconds (5.28 hours)\n\nTimestep: 4310000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1297\nexploration: 0.02552\nlearning_rate: 0.00006\nelapsed time: 19055.4 seconds (5.29 hours)\n\nTimestep: 4320000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1300\nexploration: 0.02530\nlearning_rate: 0.00006\nelapsed time: 19101.3 seconds (5.31 hours)\n\nTimestep: 4330000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1303\nexploration: 0.02508\nlearning_rate: 0.00006\nelapsed time: 19147.0 seconds (5.32 hours)\n\nTimestep: 4340000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1306\nexploration: 0.02485\nlearning_rate: 0.00006\nelapsed time: 19192.6 seconds (5.33 hours)\n\nTimestep: 4350000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1309\nexploration: 0.02462\nlearning_rate: 0.00006\nelapsed time: 19238.0 seconds (5.34 hours)\n\nTimestep: 4360000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1312\nexploration: 0.02440\nlearning_rate: 0.00006\nelapsed time: 19283.9 seconds (5.36 hours)\n\nTimestep: 4370000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1315\nexploration: 0.02417\nlearning_rate: 0.00006\nelapsed time: 19331.2 seconds (5.37 hours)\n\nTimestep: 4380000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1318\nexploration: 0.02395\nlearning_rate: 0.00006\nelapsed time: 19376.8 seconds (5.38 hours)\n\nTimestep: 4390000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1321\nexploration: 0.02372\nlearning_rate: 0.00006\nelapsed time: 19422.9 seconds (5.40 hours)\n\nTimestep: 4400000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1324\nexploration: 0.02350\nlearning_rate: 0.00006\nelapsed time: 19468.9 seconds (5.41 hours)\n\nTimestep: 4410000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1327\nexploration: 0.02327\nlearning_rate: 0.00006\nelapsed time: 19515.3 seconds (5.42 hours)\n\nTimestep: 4420000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1330\nexploration: 0.02305\nlearning_rate: 0.00006\nelapsed time: 19561.3 seconds (5.43 hours)\n\nTimestep: 4430000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1333\nexploration: 0.02282\nlearning_rate: 0.00006\nelapsed time: 19606.7 seconds (5.45 hours)\n\nTimestep: 4440000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1336\nexploration: 0.02260\nlearning_rate: 0.00006\nelapsed time: 19652.7 seconds (5.46 hours)\n\nTimestep: 4450000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1339\nexploration: 0.02237\nlearning_rate: 0.00006\nelapsed time: 19698.9 seconds (5.47 hours)\n\nTimestep: 4460000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1342\nexploration: 0.02215\nlearning_rate: 0.00006\nelapsed time: 19745.2 seconds (5.48 hours)\n\nTimestep: 4470000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1345\nexploration: 0.02192\nlearning_rate: 0.00006\nelapsed time: 19791.2 seconds (5.50 hours)\n\nTimestep: 4480000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1348\nexploration: 0.02170\nlearning_rate: 0.00006\nelapsed time: 19837.2 seconds (5.51 hours)\n\nTimestep: 4490000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1351\nexploration: 0.02147\nlearning_rate: 0.00006\nelapsed time: 19883.7 seconds (5.52 hours)\n\nTimestep: 4500000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1354\nexploration: 0.02125\nlearning_rate: 0.00006\nelapsed time: 19929.2 seconds (5.54 hours)\n\nTimestep: 4510000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1357\nexploration: 0.02103\nlearning_rate: 0.00006\nelapsed time: 19975.7 seconds (5.55 hours)\n\nTimestep: 4520000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1360\nexploration: 0.02080\nlearning_rate: 0.00006\nelapsed time: 20021.5 seconds (5.56 hours)\n\nTimestep: 4530000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1363\nexploration: 0.02057\nlearning_rate: 0.00006\nelapsed time: 20067.2 seconds (5.57 hours)\n\nTimestep: 4540000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1366\nexploration: 0.02035\nlearning_rate: 0.00006\nelapsed time: 20113.3 seconds (5.59 hours)\n\nTimestep: 4550000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1369\nexploration: 0.02013\nlearning_rate: 0.00006\nelapsed time: 20158.9 seconds (5.60 hours)\n\nTimestep: 4560000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1372\nexploration: 0.01990\nlearning_rate: 0.00006\nelapsed time: 20205.2 seconds (5.61 hours)\n\nTimestep: 4570000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1375\nexploration: 0.01967\nlearning_rate: 0.00006\nelapsed time: 20251.3 seconds (5.63 hours)\n\nTimestep: 4580000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1378\nexploration: 0.01945\nlearning_rate: 0.00006\nelapsed time: 20297.3 seconds (5.64 hours)\n\nTimestep: 4590000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1381\nexploration: 0.01923\nlearning_rate: 0.00006\nelapsed time: 20343.8 seconds (5.65 hours)\n\nTimestep: 4600000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1384\nexploration: 0.01900\nlearning_rate: 0.00006\nelapsed time: 20389.9 seconds (5.66 hours)\n\nTimestep: 4610000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1387\nexploration: 0.01878\nlearning_rate: 0.00005\nelapsed time: 20436.1 seconds (5.68 hours)\n\nTimestep: 4620000\nmean reward (100 episodes): 0.0000\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1390\nexploration: 0.01855\nlearning_rate: 0.00005\nelapsed time: 20482.5 seconds (5.69 hours)\n\nTimestep: 4630000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1393\nexploration: 0.01832\nlearning_rate: 0.00005\nelapsed time: 20528.5 seconds (5.70 hours)\n\nTimestep: 4640000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1396\nexploration: 0.01810\nlearning_rate: 0.00005\nelapsed time: 20574.4 seconds (5.72 hours)\n\nTimestep: 4650000\nmean reward (100 episodes): 0.0100\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1399\nexploration: 0.01788\nlearning_rate: 0.00005\nelapsed time: 20620.0 seconds (5.73 hours)\n\nTimestep: 4660000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.2600\ncurrent episode reward: 5.0000\nepisodes: 1402\nexploration: 0.01765\nlearning_rate: 0.00005\nelapsed time: 20667.1 seconds (5.74 hours)\n\nTimestep: 4670000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1405\nexploration: 0.01742\nlearning_rate: 0.00005\nelapsed time: 20713.4 seconds (5.75 hours)\n\nTimestep: 4680000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1408\nexploration: 0.01720\nlearning_rate: 0.00005\nelapsed time: 20760.2 seconds (5.77 hours)\n\nTimestep: 4690000\nmean reward (100 episodes): 0.0800\nbest mean reward: 0.2600\ncurrent episode reward: 0.0000\nepisodes: 1411\nexploration: 0.01697\nlearning_rate: 0.00005\nelapsed time: 20807.3 seconds (5.78 hours)\n\nTimestep: 4700000\nmean reward (100 episodes): 0.6800\nbest mean reward: 0.6800\ncurrent episode reward: 42.0000\nepisodes: 1414\nexploration: 0.01675\nlearning_rate: 0.00005\nelapsed time: 20853.6 seconds (5.79 hours)\n\nTimestep: 4710000\nmean reward (100 episodes): 1.4700\nbest mean reward: 1.4700\ncurrent episode reward: 25.0000\nepisodes: 1417\nexploration: 0.01652\nlearning_rate: 0.00005\nelapsed time: 20899.2 seconds (5.81 hours)\n\nTimestep: 4720000\nmean reward (100 episodes): 1.8900\nbest mean reward: 1.8900\ncurrent episode reward: 21.0000\nepisodes: 1420\nexploration: 0.01630\nlearning_rate: 0.00005\nelapsed time: 20946.5 seconds (5.82 hours)\n\nTimestep: 4730000\nmean reward (100 episodes): 2.7100\nbest mean reward: 2.7100\ncurrent episode reward: 29.0000\nepisodes: 1423\nexploration: 0.01607\nlearning_rate: 0.00005\nelapsed time: 20992.7 seconds (5.83 hours)\n\nTimestep: 4740000\nmean reward (100 episodes): 3.7300\nbest mean reward: 3.7300\ncurrent episode reward: 30.0000\nepisodes: 1426\nexploration: 0.01585\nlearning_rate: 0.00005\nelapsed time: 21039.3 seconds (5.84 hours)\n\nTimestep: 4750000\nmean reward (100 episodes): 4.4400\nbest mean reward: 4.4400\ncurrent episode reward: 26.0000\nepisodes: 1429\nexploration: 0.01562\nlearning_rate: 0.00005\nelapsed time: 21086.0 seconds (5.86 hours)\n\nTimestep: 4760000\nmean reward (100 episodes): 5.4000\nbest mean reward: 5.4000\ncurrent episode reward: 31.0000\nepisodes: 1432\nexploration: 0.01540\nlearning_rate: 0.00005\nelapsed time: 21132.6 seconds (5.87 hours)\n\nTimestep: 4770000\nmean reward (100 episodes): 6.1500\nbest mean reward: 6.1500\ncurrent episode reward: 12.0000\nepisodes: 1435\nexploration: 0.01517\nlearning_rate: 0.00005\nelapsed time: 21178.9 seconds (5.88 hours)\n\nTimestep: 4780000\nmean reward (100 episodes): 7.2200\nbest mean reward: 7.2200\ncurrent episode reward: 38.0000\nepisodes: 1438\nexploration: 0.01495\nlearning_rate: 0.00005\nelapsed time: 21224.4 seconds (5.90 hours)\n\nTimestep: 4790000\nmean reward (100 episodes): 8.0800\nbest mean reward: 8.0800\ncurrent episode reward: 39.0000\nepisodes: 1441\nexploration: 0.01472\nlearning_rate: 0.00005\nelapsed time: 21270.6 seconds (5.91 hours)\n\nTimestep: 4800000\nmean reward (100 episodes): 8.4700\nbest mean reward: 8.4700\ncurrent episode reward: 18.0000\nepisodes: 1444\nexploration: 0.01450\nlearning_rate: 0.00005\nelapsed time: 21316.8 seconds (5.92 hours)\n\nTimestep: 4810000\nmean reward (100 episodes): 9.5000\nbest mean reward: 9.5000\ncurrent episode reward: 41.0000\nepisodes: 1447\nexploration: 0.01427\nlearning_rate: 0.00005\nelapsed time: 21362.7 seconds (5.93 hours)\n\nTimestep: 4820000\nmean reward (100 episodes): 10.1100\nbest mean reward: 10.1100\ncurrent episode reward: 5.0000\nepisodes: 1450\nexploration: 0.01405\nlearning_rate: 0.00005\nelapsed time: 21408.6 seconds (5.95 hours)\n\nTimestep: 4830000\nmean reward (100 episodes): 10.8100\nbest mean reward: 10.8100\ncurrent episode reward: 32.0000\nepisodes: 1453\nexploration: 0.01382\nlearning_rate: 0.00005\nelapsed time: 21455.3 seconds (5.96 hours)\n\nTimestep: 4840000\nmean reward (100 episodes): 11.9200\nbest mean reward: 11.9200\ncurrent episode reward: 26.0000\nepisodes: 1456\nexploration: 0.01360\nlearning_rate: 0.00005\nelapsed time: 21501.2 seconds (5.97 hours)\n\nTimestep: 4850000\nmean reward (100 episodes): 13.5100\nbest mean reward: 13.5100\ncurrent episode reward: 41.0000\nepisodes: 1459\nexploration: 0.01337\nlearning_rate: 0.00005\nelapsed time: 21548.2 seconds (5.99 hours)\n\nTimestep: 4860000\nmean reward (100 episodes): 14.6300\nbest mean reward: 14.6300\ncurrent episode reward: 30.0000\nepisodes: 1462\nexploration: 0.01315\nlearning_rate: 0.00005\nelapsed time: 21595.0 seconds (6.00 hours)\n\nTimestep: 4870000\nmean reward (100 episodes): 15.1100\nbest mean reward: 15.1100\ncurrent episode reward: 26.0000\nepisodes: 1465\nexploration: 0.01292\nlearning_rate: 0.00005\nelapsed time: 21640.8 seconds (6.01 hours)\n\nTimestep: 4880000\nmean reward (100 episodes): 15.7500\nbest mean reward: 15.7500\ncurrent episode reward: 19.0000\nepisodes: 1468\nexploration: 0.01270\nlearning_rate: 0.00005\nelapsed time: 21687.4 seconds (6.02 hours)\n\nTimestep: 4890000\nmean reward (100 episodes): 16.5600\nbest mean reward: 16.5600\ncurrent episode reward: 21.0000\nepisodes: 1471\nexploration: 0.01247\nlearning_rate: 0.00005\nelapsed time: 21733.7 seconds (6.04 hours)\n\nTimestep: 4900000\nmean reward (100 episodes): 17.3400\nbest mean reward: 17.3400\ncurrent episode reward: 45.0000\nepisodes: 1474\nexploration: 0.01225\nlearning_rate: 0.00005\nelapsed time: 21779.1 seconds (6.05 hours)\n\nTimestep: 4910000\nmean reward (100 episodes): 17.8700\nbest mean reward: 17.8700\ncurrent episode reward: 10.0000\nepisodes: 1477\nexploration: 0.01202\nlearning_rate: 0.00005\nelapsed time: 21825.6 seconds (6.06 hours)\n\nTimestep: 4920000\nmean reward (100 episodes): 18.7700\nbest mean reward: 18.7700\ncurrent episode reward: 18.0000\nepisodes: 1480\nexploration: 0.01180\nlearning_rate: 0.00005\nelapsed time: 21871.8 seconds (6.08 hours)\n\nTimestep: 4930000\nmean reward (100 episodes): 19.3600\nbest mean reward: 19.3600\ncurrent episode reward: 36.0000\nepisodes: 1483\nexploration: 0.01157\nlearning_rate: 0.00005\nelapsed time: 21918.1 seconds (6.09 hours)\n\nTimestep: 4940000\nmean reward (100 episodes): 20.0000\nbest mean reward: 20.0000\ncurrent episode reward: 25.0000\nepisodes: 1486\nexploration: 0.01135\nlearning_rate: 0.00005\nelapsed time: 21964.4 seconds (6.10 hours)\n\nTimestep: 4950000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8000\ncurrent episode reward: 7.0000\nepisodes: 1489\nexploration: 0.01112\nlearning_rate: 0.00005\nelapsed time: 22010.1 seconds (6.11 hours)\n\nTimestep: 4960000\nmean reward (100 episodes): 21.3100\nbest mean reward: 21.3200\ncurrent episode reward: 0.0000\nepisodes: 1492\nexploration: 0.01090\nlearning_rate: 0.00005\nelapsed time: 22057.4 seconds (6.13 hours)\n\nTimestep: 4970000\nmean reward (100 episodes): 22.1200\nbest mean reward: 22.1200\ncurrent episode reward: 26.0000\nepisodes: 1495\nexploration: 0.01067\nlearning_rate: 0.00005\nelapsed time: 22103.5 seconds (6.14 hours)\n\nTimestep: 4980000\nmean reward (100 episodes): 22.7500\nbest mean reward: 22.7500\ncurrent episode reward: 34.0000\nepisodes: 1498\nexploration: 0.01045\nlearning_rate: 0.00005\nelapsed time: 22149.5 seconds (6.15 hours)\n\nTimestep: 4990000\nmean reward (100 episodes): 23.3700\nbest mean reward: 23.3700\ncurrent episode reward: 32.0000\nepisodes: 1501\nexploration: 0.01022\nlearning_rate: 0.00005\nelapsed time: 22196.3 seconds (6.17 hours)\n\nTimestep: 5000000\nmean reward (100 episodes): 23.7900\nbest mean reward: 23.7900\ncurrent episode reward: 6.0000\nepisodes: 1504\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22242.8 seconds (6.18 hours)\n\nTimestep: 5010000\nmean reward (100 episodes): 24.5900\nbest mean reward: 24.5900\ncurrent episode reward: 29.0000\nepisodes: 1507\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22289.3 seconds (6.19 hours)\n\nTimestep: 5020000\nmean reward (100 episodes): 25.3900\nbest mean reward: 25.3900\ncurrent episode reward: 27.0000\nepisodes: 1510\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22336.7 seconds (6.20 hours)\n\nTimestep: 5030000\nmean reward (100 episodes): 25.7300\nbest mean reward: 25.7300\ncurrent episode reward: 25.0000\nepisodes: 1513\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22383.4 seconds (6.22 hours)\n\nTimestep: 5040000\nmean reward (100 episodes): 25.7900\nbest mean reward: 25.7900\ncurrent episode reward: 31.0000\nepisodes: 1516\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22430.0 seconds (6.23 hours)\n\nTimestep: 5050000\nmean reward (100 episodes): 26.1000\nbest mean reward: 26.1000\ncurrent episode reward: 43.0000\nepisodes: 1519\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22476.0 seconds (6.24 hours)\n\nTimestep: 5060000\nmean reward (100 episodes): 26.0800\nbest mean reward: 26.1000\ncurrent episode reward: 18.0000\nepisodes: 1522\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22522.2 seconds (6.26 hours)\n\nTimestep: 5070000\nmean reward (100 episodes): 25.8900\nbest mean reward: 26.2000\ncurrent episode reward: 6.0000\nepisodes: 1525\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22568.6 seconds (6.27 hours)\n\nTimestep: 5080000\nmean reward (100 episodes): 26.1100\nbest mean reward: 26.2000\ncurrent episode reward: 35.0000\nepisodes: 1528\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22615.6 seconds (6.28 hours)\n\nTimestep: 5090000\nmean reward (100 episodes): 26.0600\nbest mean reward: 26.2000\ncurrent episode reward: 22.0000\nepisodes: 1531\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22661.6 seconds (6.29 hours)\n\nTimestep: 5100000\nmean reward (100 episodes): 25.7500\nbest mean reward: 26.2000\ncurrent episode reward: 10.0000\nepisodes: 1534\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22707.9 seconds (6.31 hours)\n\nTimestep: 5110000\nmean reward (100 episodes): 25.6100\nbest mean reward: 26.2000\ncurrent episode reward: 31.0000\nepisodes: 1537\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22754.4 seconds (6.32 hours)\n\nTimestep: 5120000\nmean reward (100 episodes): 25.1400\nbest mean reward: 26.2000\ncurrent episode reward: 23.0000\nepisodes: 1541\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22799.8 seconds (6.33 hours)\n\nTimestep: 5130000\nmean reward (100 episodes): 25.5100\nbest mean reward: 26.2000\ncurrent episode reward: 25.0000\nepisodes: 1544\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22845.4 seconds (6.35 hours)\n\nTimestep: 5140000\nmean reward (100 episodes): 24.8100\nbest mean reward: 26.2000\ncurrent episode reward: 1.0000\nepisodes: 1547\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22891.0 seconds (6.36 hours)\n\nTimestep: 5150000\nmean reward (100 episodes): 24.8100\nbest mean reward: 26.2000\ncurrent episode reward: 13.0000\nepisodes: 1550\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22936.1 seconds (6.37 hours)\n\nTimestep: 5160000\nmean reward (100 episodes): 24.7000\nbest mean reward: 26.2000\ncurrent episode reward: 18.0000\nepisodes: 1553\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22982.1 seconds (6.38 hours)\n\nTimestep: 5170000\nmean reward (100 episodes): 24.3700\nbest mean reward: 26.2000\ncurrent episode reward: 37.0000\nepisodes: 1556\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23028.3 seconds (6.40 hours)\n\nTimestep: 5180000\nmean reward (100 episodes): 23.8500\nbest mean reward: 26.2000\ncurrent episode reward: 36.0000\nepisodes: 1559\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23074.7 seconds (6.41 hours)\n\nTimestep: 5190000\nmean reward (100 episodes): 23.2600\nbest mean reward: 26.2000\ncurrent episode reward: 13.0000\nepisodes: 1562\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23121.0 seconds (6.42 hours)\n\nTimestep: 5200000\nmean reward (100 episodes): 23.7800\nbest mean reward: 26.2000\ncurrent episode reward: 34.0000\nepisodes: 1565\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23166.9 seconds (6.44 hours)\n\nTimestep: 5210000\nmean reward (100 episodes): 24.0300\nbest mean reward: 26.2000\ncurrent episode reward: 33.0000\nepisodes: 1568\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23212.9 seconds (6.45 hours)\n\nTimestep: 5220000\nmean reward (100 episodes): 24.1000\nbest mean reward: 26.2000\ncurrent episode reward: 27.0000\nepisodes: 1571\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23258.8 seconds (6.46 hours)\n\nTimestep: 5230000\nmean reward (100 episodes): 23.7800\nbest mean reward: 26.2000\ncurrent episode reward: 22.0000\nepisodes: 1574\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23305.1 seconds (6.47 hours)\n\nTimestep: 5240000\nmean reward (100 episodes): 23.9300\nbest mean reward: 26.2000\ncurrent episode reward: 19.0000\nepisodes: 1577\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23350.6 seconds (6.49 hours)\n\nTimestep: 5250000\nmean reward (100 episodes): 23.8600\nbest mean reward: 26.2000\ncurrent episode reward: 33.0000\nepisodes: 1580\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23396.6 seconds (6.50 hours)\n\nTimestep: 5260000\nmean reward (100 episodes): 24.2400\nbest mean reward: 26.2000\ncurrent episode reward: 11.0000\nepisodes: 1583\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23442.8 seconds (6.51 hours)\n\nTimestep: 5270000\nmean reward (100 episodes): 23.9400\nbest mean reward: 26.2000\ncurrent episode reward: 34.0000\nepisodes: 1586\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23488.9 seconds (6.52 hours)\n\nTimestep: 5280000\nmean reward (100 episodes): 23.8800\nbest mean reward: 26.2000\ncurrent episode reward: 13.0000\nepisodes: 1589\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23535.5 seconds (6.54 hours)\n\nTimestep: 5290000\nmean reward (100 episodes): 24.3200\nbest mean reward: 26.2000\ncurrent episode reward: 36.0000\nepisodes: 1592\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23581.8 seconds (6.55 hours)\n\nTimestep: 5300000\nmean reward (100 episodes): 24.3700\nbest mean reward: 26.2000\ncurrent episode reward: 29.0000\nepisodes: 1595\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23628.9 seconds (6.56 hours)\n\nTimestep: 5310000\nmean reward (100 episodes): 24.5500\nbest mean reward: 26.2000\ncurrent episode reward: 22.0000\nepisodes: 1598\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23674.6 seconds (6.58 hours)\n\nTimestep: 5320000\nmean reward (100 episodes): 24.0400\nbest mean reward: 26.2000\ncurrent episode reward: 4.0000\nepisodes: 1601\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23721.5 seconds (6.59 hours)\n\nTimestep: 5330000\nmean reward (100 episodes): 24.2100\nbest mean reward: 26.2000\ncurrent episode reward: 20.0000\nepisodes: 1604\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23768.2 seconds (6.60 hours)\n\nTimestep: 5340000\nmean reward (100 episodes): 23.9600\nbest mean reward: 26.2000\ncurrent episode reward: 26.0000\nepisodes: 1607\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23814.7 seconds (6.62 hours)\n\nTimestep: 5350000\nmean reward (100 episodes): 23.8700\nbest mean reward: 26.2000\ncurrent episode reward: 2.0000\nepisodes: 1610\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23859.7 seconds (6.63 hours)\n\nTimestep: 5360000\nmean reward (100 episodes): 24.2000\nbest mean reward: 26.2000\ncurrent episode reward: 25.0000\nepisodes: 1613\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23905.5 seconds (6.64 hours)\n\nTimestep: 5370000\nmean reward (100 episodes): 24.1300\nbest mean reward: 26.2000\ncurrent episode reward: 36.0000\nepisodes: 1616\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23951.8 seconds (6.65 hours)\n\nTimestep: 5380000\nmean reward (100 episodes): 24.2000\nbest mean reward: 26.2000\ncurrent episode reward: 11.0000\nepisodes: 1619\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23998.2 seconds (6.67 hours)\n\nTimestep: 5390000\nmean reward (100 episodes): 24.2400\nbest mean reward: 26.2000\ncurrent episode reward: 34.0000\nepisodes: 1622\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24044.5 seconds (6.68 hours)\n\nTimestep: 5400000\nmean reward (100 episodes): 24.1700\nbest mean reward: 26.2000\ncurrent episode reward: 41.0000\nepisodes: 1625\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24090.7 seconds (6.69 hours)\n\nTimestep: 5410000\nmean reward (100 episodes): 23.8000\nbest mean reward: 26.2000\ncurrent episode reward: 32.0000\nepisodes: 1628\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24136.1 seconds (6.70 hours)\n\nTimestep: 5420000\nmean reward (100 episodes): 23.5600\nbest mean reward: 26.2000\ncurrent episode reward: 34.0000\nepisodes: 1631\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24182.6 seconds (6.72 hours)\n\nTimestep: 5430000\nmean reward (100 episodes): 23.1000\nbest mean reward: 26.2000\ncurrent episode reward: 3.0000\nepisodes: 1634\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24228.5 seconds (6.73 hours)\n\nTimestep: 5440000\nmean reward (100 episodes): 22.9900\nbest mean reward: 26.2000\ncurrent episode reward: 28.0000\nepisodes: 1637\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24274.8 seconds (6.74 hours)\n\nTimestep: 5450000\nmean reward (100 episodes): 22.8700\nbest mean reward: 26.2000\ncurrent episode reward: 42.0000\nepisodes: 1640\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24321.3 seconds (6.76 hours)\n\nTimestep: 5460000\nmean reward (100 episodes): 23.0200\nbest mean reward: 26.2000\ncurrent episode reward: 32.0000\nepisodes: 1643\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24367.8 seconds (6.77 hours)\n\nTimestep: 5470000\nmean reward (100 episodes): 22.8700\nbest mean reward: 26.2000\ncurrent episode reward: 7.0000\nepisodes: 1646\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24414.1 seconds (6.78 hours)\n\nTimestep: 5480000\nmean reward (100 episodes): 23.1000\nbest mean reward: 26.2000\ncurrent episode reward: 38.0000\nepisodes: 1649\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24459.9 seconds (6.79 hours)\n\nTimestep: 5490000\nmean reward (100 episodes): 23.4500\nbest mean reward: 26.2000\ncurrent episode reward: 28.0000\nepisodes: 1652\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24506.0 seconds (6.81 hours)\n\nTimestep: 5500000\nmean reward (100 episodes): 23.4000\nbest mean reward: 26.2000\ncurrent episode reward: 33.0000\nepisodes: 1655\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24551.7 seconds (6.82 hours)\n\nTimestep: 5510000\nmean reward (100 episodes): 23.1500\nbest mean reward: 26.2000\ncurrent episode reward: 32.0000\nepisodes: 1658\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24597.6 seconds (6.83 hours)\n\nTimestep: 5520000\nmean reward (100 episodes): 23.2400\nbest mean reward: 26.2000\ncurrent episode reward: 44.0000\nepisodes: 1661\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24643.5 seconds (6.85 hours)\n\nTimestep: 5530000\nmean reward (100 episodes): 22.5600\nbest mean reward: 26.2000\ncurrent episode reward: 6.0000\nepisodes: 1664\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24690.0 seconds (6.86 hours)\n\nTimestep: 5540000\nmean reward (100 episodes): 22.3800\nbest mean reward: 26.2000\ncurrent episode reward: 21.0000\nepisodes: 1667\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24736.0 seconds (6.87 hours)\n\nTimestep: 5550000\nmean reward (100 episodes): 22.0400\nbest mean reward: 26.2000\ncurrent episode reward: 25.0000\nepisodes: 1670\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24782.5 seconds (6.88 hours)\n\nTimestep: 5560000\nmean reward (100 episodes): 22.4500\nbest mean reward: 26.2000\ncurrent episode reward: 38.0000\nepisodes: 1673\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24828.6 seconds (6.90 hours)\n\nTimestep: 5570000\nmean reward (100 episodes): 22.7700\nbest mean reward: 26.2000\ncurrent episode reward: 37.0000\nepisodes: 1676\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24875.3 seconds (6.91 hours)\n\nTimestep: 5580000\nmean reward (100 episodes): 22.4800\nbest mean reward: 26.2000\ncurrent episode reward: 28.0000\nepisodes: 1679\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24922.2 seconds (6.92 hours)\n\nTimestep: 5590000\nmean reward (100 episodes): 21.8900\nbest mean reward: 26.2000\ncurrent episode reward: 33.0000\nepisodes: 1682\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24968.2 seconds (6.94 hours)\n\nTimestep: 5600000\nmean reward (100 episodes): 22.5100\nbest mean reward: 26.2000\ncurrent episode reward: 31.0000\nepisodes: 1685\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25014.5 seconds (6.95 hours)\n\nTimestep: 5610000\nmean reward (100 episodes): 21.9300\nbest mean reward: 26.2000\ncurrent episode reward: 3.0000\nepisodes: 1688\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25061.0 seconds (6.96 hours)\n\nTimestep: 5620000\nmean reward (100 episodes): 22.0400\nbest mean reward: 26.2000\ncurrent episode reward: 23.0000\nepisodes: 1691\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25107.5 seconds (6.97 hours)\n\nTimestep: 5630000\nmean reward (100 episodes): 21.1100\nbest mean reward: 26.2000\ncurrent episode reward: 0.0000\nepisodes: 1694\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25154.5 seconds (6.99 hours)\n\nTimestep: 5640000\nmean reward (100 episodes): 20.5900\nbest mean reward: 26.2000\ncurrent episode reward: 11.0000\nepisodes: 1697\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25201.1 seconds (7.00 hours)\n\nTimestep: 5650000\nmean reward (100 episodes): 20.9900\nbest mean reward: 26.2000\ncurrent episode reward: 33.0000\nepisodes: 1700\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25248.2 seconds (7.01 hours)\n\nTimestep: 5660000\nmean reward (100 episodes): 20.5500\nbest mean reward: 26.2000\ncurrent episode reward: 0.0000\nepisodes: 1703\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25294.5 seconds (7.03 hours)\n\nTimestep: 5670000\nmean reward (100 episodes): 20.0600\nbest mean reward: 26.2000\ncurrent episode reward: 0.0000\nepisodes: 1706\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25340.6 seconds (7.04 hours)\n\nTimestep: 5680000\nmean reward (100 episodes): 19.1100\nbest mean reward: 26.2000\ncurrent episode reward: 0.0000\nepisodes: 1709\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25387.4 seconds (7.05 hours)\n\nTimestep: 5690000\nmean reward (100 episodes): 19.3700\nbest mean reward: 26.2000\ncurrent episode reward: 35.0000\nepisodes: 1712\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25434.0 seconds (7.06 hours)\n\nTimestep: 5700000\nmean reward (100 episodes): 19.1400\nbest mean reward: 26.2000\ncurrent episode reward: 21.0000\nepisodes: 1715\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25480.4 seconds (7.08 hours)\n\nTimestep: 5710000\nmean reward (100 episodes): 18.4900\nbest mean reward: 26.2000\ncurrent episode reward: 9.0000\nepisodes: 1718\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25527.1 seconds (7.09 hours)\n\nTimestep: 5720000\nmean reward (100 episodes): 18.3100\nbest mean reward: 26.2000\ncurrent episode reward: 23.0000\nepisodes: 1721\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25573.3 seconds (7.10 hours)\n\nTimestep: 5730000\nmean reward (100 episodes): 18.7500\nbest mean reward: 26.2000\ncurrent episode reward: 35.0000\nepisodes: 1724\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25619.1 seconds (7.12 hours)\n\nTimestep: 5740000\nmean reward (100 episodes): 18.7200\nbest mean reward: 26.2000\ncurrent episode reward: 31.0000\nepisodes: 1727\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25665.6 seconds (7.13 hours)\n\nTimestep: 5750000\nmean reward (100 episodes): 18.5100\nbest mean reward: 26.2000\ncurrent episode reward: 0.0000\nepisodes: 1730\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25712.2 seconds (7.14 hours)\n\nTimestep: 5760000\nmean reward (100 episodes): 18.0700\nbest mean reward: 26.2000\ncurrent episode reward: 4.0000\nepisodes: 1733\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25758.1 seconds (7.16 hours)\n\nTimestep: 5770000\nmean reward (100 episodes): 18.3900\nbest mean reward: 26.2000\ncurrent episode reward: 14.0000\nepisodes: 1736\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25803.9 seconds (7.17 hours)\n\nTimestep: 5780000\nmean reward (100 episodes): 18.9700\nbest mean reward: 26.2000\ncurrent episode reward: 16.0000\nepisodes: 1739\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25850.6 seconds (7.18 hours)\n\nTimestep: 5790000\nmean reward (100 episodes): 19.2700\nbest mean reward: 26.2000\ncurrent episode reward: 39.0000\nepisodes: 1742\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25897.4 seconds (7.19 hours)\n\nTimestep: 5800000\nmean reward (100 episodes): 19.6100\nbest mean reward: 26.2000\ncurrent episode reward: 24.0000\nepisodes: 1745\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25943.9 seconds (7.21 hours)\n\nTimestep: 5810000\nmean reward (100 episodes): 20.3300\nbest mean reward: 26.2000\ncurrent episode reward: 35.0000\nepisodes: 1748\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25989.6 seconds (7.22 hours)\n\nTimestep: 5820000\nmean reward (100 episodes): 20.2400\nbest mean reward: 26.2000\ncurrent episode reward: 36.0000\nepisodes: 1751\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26036.0 seconds (7.23 hours)\n\nTimestep: 5830000\nmean reward (100 episodes): 20.3900\nbest mean reward: 26.2000\ncurrent episode reward: 32.0000\nepisodes: 1754\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26082.5 seconds (7.25 hours)\n\nTimestep: 5840000\nmean reward (100 episodes): 20.3500\nbest mean reward: 26.2000\ncurrent episode reward: 42.0000\nepisodes: 1757\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26128.7 seconds (7.26 hours)\n\nTimestep: 5850000\nmean reward (100 episodes): 20.6300\nbest mean reward: 26.2000\ncurrent episode reward: 45.0000\nepisodes: 1760\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26174.7 seconds (7.27 hours)\n\nTimestep: 5860000\nmean reward (100 episodes): 20.8200\nbest mean reward: 26.2000\ncurrent episode reward: 19.0000\nepisodes: 1763\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26221.3 seconds (7.28 hours)\n\nTimestep: 5870000\nmean reward (100 episodes): 21.0000\nbest mean reward: 26.2000\ncurrent episode reward: 36.0000\nepisodes: 1766\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26267.4 seconds (7.30 hours)\n\nTimestep: 5880000\nmean reward (100 episodes): 21.1000\nbest mean reward: 26.2000\ncurrent episode reward: 33.0000\nepisodes: 1769\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26313.5 seconds (7.31 hours)\n\nTimestep: 5890000\nmean reward (100 episodes): 20.6700\nbest mean reward: 26.2000\ncurrent episode reward: 0.0000\nepisodes: 1772\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26359.7 seconds (7.32 hours)\n\nTimestep: 5900000\nmean reward (100 episodes): 20.6000\nbest mean reward: 26.2000\ncurrent episode reward: 36.0000\nepisodes: 1775\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26405.8 seconds (7.33 hours)\n\nTimestep: 5910000\nmean reward (100 episodes): 21.0000\nbest mean reward: 26.2000\ncurrent episode reward: 30.0000\nepisodes: 1778\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26452.4 seconds (7.35 hours)\n\nTimestep: 5920000\nmean reward (100 episodes): 21.2100\nbest mean reward: 26.2000\ncurrent episode reward: 41.0000\nepisodes: 1781\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26499.1 seconds (7.36 hours)\n\nTimestep: 5930000\nmean reward (100 episodes): 21.3200\nbest mean reward: 26.2000\ncurrent episode reward: 46.0000\nepisodes: 1784\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26544.9 seconds (7.37 hours)\n\nTimestep: 5940000\nmean reward (100 episodes): 21.4100\nbest mean reward: 26.2000\ncurrent episode reward: 24.0000\nepisodes: 1787\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26591.8 seconds (7.39 hours)\n\nTimestep: 5950000\nmean reward (100 episodes): 21.3300\nbest mean reward: 26.2000\ncurrent episode reward: 26.0000\nepisodes: 1790\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26638.0 seconds (7.40 hours)\n\nTimestep: 5960000\nmean reward (100 episodes): 22.3200\nbest mean reward: 26.2000\ncurrent episode reward: 30.0000\nepisodes: 1793\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26684.9 seconds (7.41 hours)\n\nTimestep: 5970000\nmean reward (100 episodes): 22.6000\nbest mean reward: 26.2000\ncurrent episode reward: 30.0000\nepisodes: 1796\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26730.7 seconds (7.43 hours)\n\nTimestep: 5980000\nmean reward (100 episodes): 23.1200\nbest mean reward: 26.2000\ncurrent episode reward: 40.0000\nepisodes: 1799\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26777.0 seconds (7.44 hours)\n\nTimestep: 5990000\nmean reward (100 episodes): 23.2500\nbest mean reward: 26.2000\ncurrent episode reward: 8.0000\nepisodes: 1802\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26823.4 seconds (7.45 hours)\n\nTimestep: 6000000\nmean reward (100 episodes): 24.0500\nbest mean reward: 26.2000\ncurrent episode reward: 26.0000\nepisodes: 1805\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26869.7 seconds (7.46 hours)\n\nTimestep: 6010000\nmean reward (100 episodes): 24.9900\nbest mean reward: 26.2000\ncurrent episode reward: 22.0000\nepisodes: 1808\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26916.2 seconds (7.48 hours)\n\nTimestep: 6020000\nmean reward (100 episodes): 25.1900\nbest mean reward: 26.2000\ncurrent episode reward: 27.0000\nepisodes: 1811\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26963.4 seconds (7.49 hours)\n\nTimestep: 6030000\nmean reward (100 episodes): 25.2700\nbest mean reward: 26.2000\ncurrent episode reward: 32.0000\nepisodes: 1814\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27009.9 seconds (7.50 hours)\n\nTimestep: 6040000\nmean reward (100 episodes): 25.2800\nbest mean reward: 26.2000\ncurrent episode reward: 19.0000\nepisodes: 1817\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27055.9 seconds (7.52 hours)\n\nTimestep: 6050000\nmean reward (100 episodes): 26.1100\nbest mean reward: 26.2000\ncurrent episode reward: 28.0000\nepisodes: 1820\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27102.7 seconds (7.53 hours)\n\nTimestep: 6060000\nmean reward (100 episodes): 25.7700\nbest mean reward: 26.2000\ncurrent episode reward: 17.0000\nepisodes: 1823\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27148.6 seconds (7.54 hours)\n\nTimestep: 6070000\nmean reward (100 episodes): 25.7600\nbest mean reward: 26.2000\ncurrent episode reward: 24.0000\nepisodes: 1826\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27196.2 seconds (7.55 hours)\n\nTimestep: 6080000\nmean reward (100 episodes): 25.7100\nbest mean reward: 26.2000\ncurrent episode reward: 8.0000\nepisodes: 1829\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27242.3 seconds (7.57 hours)\n\nTimestep: 6090000\nmean reward (100 episodes): 26.5500\nbest mean reward: 26.5500\ncurrent episode reward: 24.0000\nepisodes: 1832\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27289.0 seconds (7.58 hours)\n\nTimestep: 6100000\nmean reward (100 episodes): 26.6000\nbest mean reward: 26.6000\ncurrent episode reward: 21.0000\nepisodes: 1835\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27335.1 seconds (7.59 hours)\n\nTimestep: 6110000\nmean reward (100 episodes): 26.5900\nbest mean reward: 26.6100\ncurrent episode reward: 43.0000\nepisodes: 1838\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27381.3 seconds (7.61 hours)\n\nTimestep: 6120000\nmean reward (100 episodes): 26.1400\nbest mean reward: 26.6600\ncurrent episode reward: 13.0000\nepisodes: 1841\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27426.5 seconds (7.62 hours)\n\nTimestep: 6130000\nmean reward (100 episodes): 25.6100\nbest mean reward: 26.6600\ncurrent episode reward: 16.0000\nepisodes: 1844\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27473.7 seconds (7.63 hours)\n\nTimestep: 6140000\nmean reward (100 episodes): 25.6200\nbest mean reward: 26.6600\ncurrent episode reward: 29.0000\nepisodes: 1848\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27520.0 seconds (7.64 hours)\n\nTimestep: 6150000\nmean reward (100 episodes): 25.2000\nbest mean reward: 26.6600\ncurrent episode reward: 25.0000\nepisodes: 1851\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27566.4 seconds (7.66 hours)\n\nTimestep: 6160000\nmean reward (100 episodes): 25.2100\nbest mean reward: 26.6600\ncurrent episode reward: 22.0000\nepisodes: 1854\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27613.5 seconds (7.67 hours)\n\nTimestep: 6170000\nmean reward (100 episodes): 25.4300\nbest mean reward: 26.6600\ncurrent episode reward: 23.0000\nepisodes: 1857\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27659.8 seconds (7.68 hours)\n\nTimestep: 6180000\nmean reward (100 episodes): 25.3700\nbest mean reward: 26.6600\ncurrent episode reward: 30.0000\nepisodes: 1860\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27707.1 seconds (7.70 hours)\n\nTimestep: 6190000\nmean reward (100 episodes): 25.2800\nbest mean reward: 26.6600\ncurrent episode reward: 17.0000\nepisodes: 1863\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27753.7 seconds (7.71 hours)\n\nTimestep: 6200000\nmean reward (100 episodes): 25.7300\nbest mean reward: 26.6600\ncurrent episode reward: 33.0000\nepisodes: 1866\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27800.1 seconds (7.72 hours)\n\nTimestep: 6210000\nmean reward (100 episodes): 25.8300\nbest mean reward: 26.6600\ncurrent episode reward: 17.0000\nepisodes: 1869\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27846.5 seconds (7.74 hours)\n\nTimestep: 6220000\nmean reward (100 episodes): 26.0300\nbest mean reward: 26.6600\ncurrent episode reward: 6.0000\nepisodes: 1872\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27892.6 seconds (7.75 hours)\n\nTimestep: 6230000\nmean reward (100 episodes): 26.4300\nbest mean reward: 26.6600\ncurrent episode reward: 29.0000\nepisodes: 1875\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27938.8 seconds (7.76 hours)\n\nTimestep: 6240000\nmean reward (100 episodes): 26.0500\nbest mean reward: 26.6600\ncurrent episode reward: 19.0000\nepisodes: 1878\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27984.5 seconds (7.77 hours)\n\nTimestep: 6250000\nmean reward (100 episodes): 26.1500\nbest mean reward: 26.6600\ncurrent episode reward: 33.0000\nepisodes: 1881\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28030.8 seconds (7.79 hours)\n\nTimestep: 6260000\nmean reward (100 episodes): 25.8500\nbest mean reward: 26.6600\ncurrent episode reward: 12.0000\nepisodes: 1884\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28077.5 seconds (7.80 hours)\n\nTimestep: 6270000\nmean reward (100 episodes): 25.8900\nbest mean reward: 26.6600\ncurrent episode reward: 9.0000\nepisodes: 1887\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28124.1 seconds (7.81 hours)\n\nTimestep: 6280000\nmean reward (100 episodes): 25.8100\nbest mean reward: 26.6600\ncurrent episode reward: 25.0000\nepisodes: 1890\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28170.8 seconds (7.83 hours)\n\nTimestep: 6290000\nmean reward (100 episodes): 25.4800\nbest mean reward: 26.6600\ncurrent episode reward: 64.0000\nepisodes: 1893\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28216.5 seconds (7.84 hours)\n\nTimestep: 6300000\nmean reward (100 episodes): 26.0700\nbest mean reward: 26.6600\ncurrent episode reward: 41.0000\nepisodes: 1896\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28262.7 seconds (7.85 hours)\n\nTimestep: 6310000\nmean reward (100 episodes): 25.6600\nbest mean reward: 26.6600\ncurrent episode reward: 29.0000\nepisodes: 1899\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28308.4 seconds (7.86 hours)\n\nTimestep: 6320000\nmean reward (100 episodes): 26.3000\nbest mean reward: 26.6600\ncurrent episode reward: 71.0000\nepisodes: 1902\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28355.0 seconds (7.88 hours)\n\nTimestep: 6330000\nmean reward (100 episodes): 26.6900\nbest mean reward: 26.6900\ncurrent episode reward: 42.0000\nepisodes: 1905\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28401.3 seconds (7.89 hours)\n\nTimestep: 6340000\nmean reward (100 episodes): 26.4800\nbest mean reward: 26.6900\ncurrent episode reward: 17.0000\nepisodes: 1908\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28447.5 seconds (7.90 hours)\n\nTimestep: 6350000\nmean reward (100 episodes): 26.1400\nbest mean reward: 26.6900\ncurrent episode reward: 25.0000\nepisodes: 1911\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28493.5 seconds (7.91 hours)\n\nTimestep: 6360000\nmean reward (100 episodes): 26.0700\nbest mean reward: 26.6900\ncurrent episode reward: 27.0000\nepisodes: 1914\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28540.3 seconds (7.93 hours)\n\nTimestep: 6370000\nmean reward (100 episodes): 26.5700\nbest mean reward: 26.6900\ncurrent episode reward: 48.0000\nepisodes: 1917\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28586.7 seconds (7.94 hours)\n\nTimestep: 6380000\nmean reward (100 episodes): 26.2800\nbest mean reward: 26.6900\ncurrent episode reward: 31.0000\nepisodes: 1920\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28632.9 seconds (7.95 hours)\n\nTimestep: 6390000\nmean reward (100 episodes): 26.6700\nbest mean reward: 26.6900\ncurrent episode reward: 53.0000\nepisodes: 1923\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28679.3 seconds (7.97 hours)\n\nTimestep: 6400000\nmean reward (100 episodes): 26.7600\nbest mean reward: 26.8300\ncurrent episode reward: 28.0000\nepisodes: 1926\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28725.3 seconds (7.98 hours)\n\nTimestep: 6410000\nmean reward (100 episodes): 27.2700\nbest mean reward: 27.2700\ncurrent episode reward: 51.0000\nepisodes: 1929\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28772.3 seconds (7.99 hours)\n\nTimestep: 6420000\nmean reward (100 episodes): 27.7900\nbest mean reward: 27.7900\ncurrent episode reward: 26.0000\nepisodes: 1932\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28819.0 seconds (8.01 hours)\n\nTimestep: 6430000\nmean reward (100 episodes): 27.7200\nbest mean reward: 27.9300\ncurrent episode reward: 22.0000\nepisodes: 1935\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28865.0 seconds (8.02 hours)\n\nTimestep: 6440000\nmean reward (100 episodes): 27.4600\nbest mean reward: 27.9300\ncurrent episode reward: 19.0000\nepisodes: 1938\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28910.1 seconds (8.03 hours)\n\nTimestep: 6450000\nmean reward (100 episodes): 27.6300\nbest mean reward: 27.9300\ncurrent episode reward: 24.0000\nepisodes: 1941\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28956.1 seconds (8.04 hours)\n\nTimestep: 6460000\nmean reward (100 episodes): 27.6800\nbest mean reward: 27.9300\ncurrent episode reward: 16.0000\nepisodes: 1944\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29002.7 seconds (8.06 hours)\n\nTimestep: 6470000\nmean reward (100 episodes): 27.4900\nbest mean reward: 27.9300\ncurrent episode reward: 33.0000\nepisodes: 1947\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29049.1 seconds (8.07 hours)\n\nTimestep: 6480000\nmean reward (100 episodes): 27.7700\nbest mean reward: 27.9300\ncurrent episode reward: 32.0000\nepisodes: 1950\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29095.4 seconds (8.08 hours)\n\nTimestep: 6490000\nmean reward (100 episodes): 27.9900\nbest mean reward: 28.0200\ncurrent episode reward: 40.0000\nepisodes: 1953\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29141.3 seconds (8.09 hours)\n\nTimestep: 6500000\nmean reward (100 episodes): 27.6200\nbest mean reward: 28.0600\ncurrent episode reward: 21.0000\nepisodes: 1956\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29188.0 seconds (8.11 hours)\n\nTimestep: 6510000\nmean reward (100 episodes): 27.6200\nbest mean reward: 28.0600\ncurrent episode reward: 36.0000\nepisodes: 1959\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29234.6 seconds (8.12 hours)\n\nTimestep: 6520000\nmean reward (100 episodes): 27.5600\nbest mean reward: 28.0600\ncurrent episode reward: 37.0000\nepisodes: 1962\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29280.9 seconds (8.13 hours)\n\nTimestep: 6530000\nmean reward (100 episodes): 26.6100\nbest mean reward: 28.0600\ncurrent episode reward: 5.0000\nepisodes: 1965\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29327.1 seconds (8.15 hours)\n\nTimestep: 6540000\nmean reward (100 episodes): 26.3400\nbest mean reward: 28.0600\ncurrent episode reward: 45.0000\nepisodes: 1968\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29374.5 seconds (8.16 hours)\n\nTimestep: 6550000\nmean reward (100 episodes): 26.2200\nbest mean reward: 28.0600\ncurrent episode reward: 31.0000\nepisodes: 1971\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29421.3 seconds (8.17 hours)\n\nTimestep: 6560000\nmean reward (100 episodes): 25.8600\nbest mean reward: 28.0600\ncurrent episode reward: 23.0000\nepisodes: 1974\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29468.3 seconds (8.19 hours)\n\nTimestep: 6570000\nmean reward (100 episodes): 26.0900\nbest mean reward: 28.0600\ncurrent episode reward: 43.0000\nepisodes: 1977\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29514.8 seconds (8.20 hours)\n\nTimestep: 6580000\nmean reward (100 episodes): 26.1400\nbest mean reward: 28.0600\ncurrent episode reward: 30.0000\nepisodes: 1980\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29561.0 seconds (8.21 hours)\n\nTimestep: 6590000\nmean reward (100 episodes): 26.1400\nbest mean reward: 28.0600\ncurrent episode reward: 24.0000\nepisodes: 1983\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29607.2 seconds (8.22 hours)\n\nTimestep: 6600000\nmean reward (100 episodes): 25.9200\nbest mean reward: 28.0600\ncurrent episode reward: 31.0000\nepisodes: 1986\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29653.5 seconds (8.24 hours)\n\nTimestep: 6610000\nmean reward (100 episodes): 26.3300\nbest mean reward: 28.0600\ncurrent episode reward: 22.0000\nepisodes: 1989\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29699.6 seconds (8.25 hours)\n\nTimestep: 6620000\nmean reward (100 episodes): 26.3200\nbest mean reward: 28.0600\ncurrent episode reward: 2.0000\nepisodes: 1992\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29746.1 seconds (8.26 hours)\n\nTimestep: 6630000\nmean reward (100 episodes): 25.6600\nbest mean reward: 28.0600\ncurrent episode reward: 3.0000\nepisodes: 1995\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29792.5 seconds (8.28 hours)\n\nTimestep: 6640000\nmean reward (100 episodes): 25.5100\nbest mean reward: 28.0600\ncurrent episode reward: 48.0000\nepisodes: 1998\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29837.9 seconds (8.29 hours)\n\nTimestep: 6650000\nmean reward (100 episodes): 25.7500\nbest mean reward: 28.0600\ncurrent episode reward: 6.0000\nepisodes: 2001\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29885.4 seconds (8.30 hours)\n\nTimestep: 6660000\nmean reward (100 episodes): 24.9400\nbest mean reward: 28.0600\ncurrent episode reward: 27.0000\nepisodes: 2004\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29932.3 seconds (8.31 hours)\n\nTimestep: 6670000\nmean reward (100 episodes): 24.7000\nbest mean reward: 28.0600\ncurrent episode reward: 27.0000\nepisodes: 2007\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29979.2 seconds (8.33 hours)\n\nTimestep: 6680000\nmean reward (100 episodes): 24.4700\nbest mean reward: 28.0600\ncurrent episode reward: 0.0000\nepisodes: 2010\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30025.1 seconds (8.34 hours)\n\nTimestep: 6690000\nmean reward (100 episodes): 23.8500\nbest mean reward: 28.0600\ncurrent episode reward: 11.0000\nepisodes: 2013\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30071.4 seconds (8.35 hours)\n\nTimestep: 6700000\nmean reward (100 episodes): 23.5500\nbest mean reward: 28.0600\ncurrent episode reward: 25.0000\nepisodes: 2016\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30118.2 seconds (8.37 hours)\n\nTimestep: 6710000\nmean reward (100 episodes): 23.2500\nbest mean reward: 28.0600\ncurrent episode reward: 27.0000\nepisodes: 2019\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30163.7 seconds (8.38 hours)\n\nTimestep: 6720000\nmean reward (100 episodes): 23.4700\nbest mean reward: 28.0600\ncurrent episode reward: 27.0000\nepisodes: 2022\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30210.3 seconds (8.39 hours)\n\nTimestep: 6730000\nmean reward (100 episodes): 22.9800\nbest mean reward: 28.0600\ncurrent episode reward: 10.0000\nepisodes: 2025\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30256.8 seconds (8.40 hours)\n\nTimestep: 6740000\nmean reward (100 episodes): 22.3100\nbest mean reward: 28.0600\ncurrent episode reward: 15.0000\nepisodes: 2028\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30303.2 seconds (8.42 hours)\n\nTimestep: 6750000\nmean reward (100 episodes): 21.8600\nbest mean reward: 28.0600\ncurrent episode reward: 54.0000\nepisodes: 2031\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30349.6 seconds (8.43 hours)\n\nTimestep: 6760000\nmean reward (100 episodes): 21.7400\nbest mean reward: 28.0600\ncurrent episode reward: 0.0000\nepisodes: 2034\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30395.5 seconds (8.44 hours)\n\nTimestep: 6770000\nmean reward (100 episodes): 21.2500\nbest mean reward: 28.0600\ncurrent episode reward: 11.0000\nepisodes: 2037\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30441.9 seconds (8.46 hours)\n\nTimestep: 6780000\nmean reward (100 episodes): 21.1500\nbest mean reward: 28.0600\ncurrent episode reward: 33.0000\nepisodes: 2040\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30489.2 seconds (8.47 hours)\n\nTimestep: 6790000\nmean reward (100 episodes): 20.8600\nbest mean reward: 28.0600\ncurrent episode reward: 0.0000\nepisodes: 2043\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30535.9 seconds (8.48 hours)\n\nTimestep: 6800000\nmean reward (100 episodes): 20.7700\nbest mean reward: 28.0600\ncurrent episode reward: 18.0000\nepisodes: 2046\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30581.7 seconds (8.49 hours)\n\nTimestep: 6810000\nmean reward (100 episodes): 21.0800\nbest mean reward: 28.0600\ncurrent episode reward: 13.0000\nepisodes: 2049\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30628.0 seconds (8.51 hours)\n\nTimestep: 6820000\nmean reward (100 episodes): 21.3400\nbest mean reward: 28.0600\ncurrent episode reward: 28.0000\nepisodes: 2052\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30674.0 seconds (8.52 hours)\n\nTimestep: 6830000\nmean reward (100 episodes): 21.0100\nbest mean reward: 28.0600\ncurrent episode reward: 2.0000\nepisodes: 2055\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30720.6 seconds (8.53 hours)\n\nTimestep: 6840000\nmean reward (100 episodes): 21.1100\nbest mean reward: 28.0600\ncurrent episode reward: 29.0000\nepisodes: 2058\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30767.6 seconds (8.55 hours)\n\nTimestep: 6850000\nmean reward (100 episodes): 21.3100\nbest mean reward: 28.0600\ncurrent episode reward: 33.0000\nepisodes: 2061\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30814.3 seconds (8.56 hours)\n\nTimestep: 6860000\nmean reward (100 episodes): 21.6900\nbest mean reward: 28.0600\ncurrent episode reward: 39.0000\nepisodes: 2064\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30861.4 seconds (8.57 hours)\n\nTimestep: 6870000\nmean reward (100 episodes): 22.1700\nbest mean reward: 28.0600\ncurrent episode reward: 28.0000\nepisodes: 2067\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30907.9 seconds (8.59 hours)\n\nTimestep: 6880000\nmean reward (100 episodes): 22.2900\nbest mean reward: 28.0600\ncurrent episode reward: 41.0000\nepisodes: 2070\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30953.9 seconds (8.60 hours)\n\nTimestep: 6890000\nmean reward (100 episodes): 22.1100\nbest mean reward: 28.0600\ncurrent episode reward: 34.0000\nepisodes: 2073\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31000.0 seconds (8.61 hours)\n\nTimestep: 6900000\nmean reward (100 episodes): 22.5500\nbest mean reward: 28.0600\ncurrent episode reward: 44.0000\nepisodes: 2076\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31046.8 seconds (8.62 hours)\n\nTimestep: 6910000\nmean reward (100 episodes): 22.7100\nbest mean reward: 28.0600\ncurrent episode reward: 36.0000\nepisodes: 2079\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31092.5 seconds (8.64 hours)\n\nTimestep: 6920000\nmean reward (100 episodes): 22.7400\nbest mean reward: 28.0600\ncurrent episode reward: 30.0000\nepisodes: 2082\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31139.5 seconds (8.65 hours)\n\nTimestep: 6930000\nmean reward (100 episodes): 23.2100\nbest mean reward: 28.0600\ncurrent episode reward: 27.0000\nepisodes: 2085\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31185.5 seconds (8.66 hours)\n\nTimestep: 6940000\nmean reward (100 episodes): 23.4400\nbest mean reward: 28.0600\ncurrent episode reward: 34.0000\nepisodes: 2088\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31232.2 seconds (8.68 hours)\n\nTimestep: 6950000\nmean reward (100 episodes): 23.3500\nbest mean reward: 28.0600\ncurrent episode reward: 31.0000\nepisodes: 2091\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31278.3 seconds (8.69 hours)\n\nTimestep: 6960000\nmean reward (100 episodes): 23.8100\nbest mean reward: 28.0600\ncurrent episode reward: 49.0000\nepisodes: 2094\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31324.7 seconds (8.70 hours)\n\nTimestep: 6970000\nmean reward (100 episodes): 24.4300\nbest mean reward: 28.0600\ncurrent episode reward: 29.0000\nepisodes: 2097\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31371.5 seconds (8.71 hours)\n\nTimestep: 6980000\nmean reward (100 episodes): 23.7800\nbest mean reward: 28.0600\ncurrent episode reward: 28.0000\nepisodes: 2100\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31417.9 seconds (8.73 hours)\n\nTimestep: 6990000\nmean reward (100 episodes): 23.9300\nbest mean reward: 28.0600\ncurrent episode reward: 13.0000\nepisodes: 2103\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31465.1 seconds (8.74 hours)\n\nTimestep: 7000000\nmean reward (100 episodes): 24.1800\nbest mean reward: 28.0600\ncurrent episode reward: 23.0000\nepisodes: 2106\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31512.0 seconds (8.75 hours)\n\nTimestep: 7010000\nmean reward (100 episodes): 24.3600\nbest mean reward: 28.0600\ncurrent episode reward: 17.0000\nepisodes: 2109\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31558.4 seconds (8.77 hours)\n\nTimestep: 7020000\nmean reward (100 episodes): 25.0700\nbest mean reward: 28.0600\ncurrent episode reward: 34.0000\nepisodes: 2112\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31604.4 seconds (8.78 hours)\n\nTimestep: 7030000\nmean reward (100 episodes): 25.5800\nbest mean reward: 28.0600\ncurrent episode reward: 19.0000\nepisodes: 2115\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31650.4 seconds (8.79 hours)\n\nTimestep: 7040000\nmean reward (100 episodes): 25.6400\nbest mean reward: 28.0600\ncurrent episode reward: 6.0000\nepisodes: 2118\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31696.7 seconds (8.80 hours)\n\nTimestep: 7050000\nmean reward (100 episodes): 25.2100\nbest mean reward: 28.0600\ncurrent episode reward: 9.0000\nepisodes: 2121\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31743.0 seconds (8.82 hours)\n\nTimestep: 7060000\nmean reward (100 episodes): 25.3400\nbest mean reward: 28.0600\ncurrent episode reward: 46.0000\nepisodes: 2124\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31789.8 seconds (8.83 hours)\n\nTimestep: 7070000\nmean reward (100 episodes): 25.3700\nbest mean reward: 28.0600\ncurrent episode reward: 7.0000\nepisodes: 2127\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31836.5 seconds (8.84 hours)\n\nTimestep: 7080000\nmean reward (100 episodes): 25.1600\nbest mean reward: 28.0600\ncurrent episode reward: 29.0000\nepisodes: 2130\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31882.5 seconds (8.86 hours)\n\nTimestep: 7090000\nmean reward (100 episodes): 24.7900\nbest mean reward: 28.0600\ncurrent episode reward: 16.0000\nepisodes: 2133\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31929.5 seconds (8.87 hours)\n\nTimestep: 7100000\nmean reward (100 episodes): 25.1800\nbest mean reward: 28.0600\ncurrent episode reward: 1.0000\nepisodes: 2136\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31975.6 seconds (8.88 hours)\n\nTimestep: 7110000\nmean reward (100 episodes): 25.5900\nbest mean reward: 28.0600\ncurrent episode reward: 35.0000\nepisodes: 2139\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32022.4 seconds (8.90 hours)\n\nTimestep: 7120000\nmean reward (100 episodes): 25.5700\nbest mean reward: 28.0600\ncurrent episode reward: 22.0000\nepisodes: 2142\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32069.0 seconds (8.91 hours)\n\nTimestep: 7130000\nmean reward (100 episodes): 25.7100\nbest mean reward: 28.0600\ncurrent episode reward: 9.0000\nepisodes: 2145\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32116.1 seconds (8.92 hours)\n\nTimestep: 7140000\nmean reward (100 episodes): 25.3400\nbest mean reward: 28.0600\ncurrent episode reward: 12.0000\nepisodes: 2149\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32162.6 seconds (8.93 hours)\n\nTimestep: 7150000\nmean reward (100 episodes): 24.7700\nbest mean reward: 28.0600\ncurrent episode reward: 7.0000\nepisodes: 2152\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32208.8 seconds (8.95 hours)\n\nTimestep: 7160000\nmean reward (100 episodes): 25.2400\nbest mean reward: 28.0600\ncurrent episode reward: 32.0000\nepisodes: 2155\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32255.5 seconds (8.96 hours)\n\nTimestep: 7170000\nmean reward (100 episodes): 25.2700\nbest mean reward: 28.0600\ncurrent episode reward: 37.0000\nepisodes: 2158\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32302.7 seconds (8.97 hours)\n\nTimestep: 7180000\nmean reward (100 episodes): 25.2100\nbest mean reward: 28.0600\ncurrent episode reward: 36.0000\nepisodes: 2161\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32348.9 seconds (8.99 hours)\n\nTimestep: 7190000\nmean reward (100 episodes): 25.3000\nbest mean reward: 28.0600\ncurrent episode reward: 28.0000\nepisodes: 2164\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32395.0 seconds (9.00 hours)\n\nTimestep: 7200000\nmean reward (100 episodes): 25.3200\nbest mean reward: 28.0600\ncurrent episode reward: 29.0000\nepisodes: 2167\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32441.0 seconds (9.01 hours)\n\nTimestep: 7210000\nmean reward (100 episodes): 25.0700\nbest mean reward: 28.0600\ncurrent episode reward: 20.0000\nepisodes: 2170\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32487.9 seconds (9.02 hours)\n\nTimestep: 7220000\nmean reward (100 episodes): 25.2200\nbest mean reward: 28.0600\ncurrent episode reward: 13.0000\nepisodes: 2173\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32534.3 seconds (9.04 hours)\n\nTimestep: 7230000\nmean reward (100 episodes): 24.9200\nbest mean reward: 28.0600\ncurrent episode reward: 26.0000\nepisodes: 2176\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32580.9 seconds (9.05 hours)\n\nTimestep: 7240000\nmean reward (100 episodes): 24.2600\nbest mean reward: 28.0600\ncurrent episode reward: 15.0000\nepisodes: 2179\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32627.9 seconds (9.06 hours)\n\nTimestep: 7250000\nmean reward (100 episodes): 24.1900\nbest mean reward: 28.0600\ncurrent episode reward: 6.0000\nepisodes: 2182\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32675.0 seconds (9.08 hours)\n\nTimestep: 7260000\nmean reward (100 episodes): 23.5300\nbest mean reward: 28.0600\ncurrent episode reward: 1.0000\nepisodes: 2185\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32720.9 seconds (9.09 hours)\n\nTimestep: 7270000\nmean reward (100 episodes): 23.0600\nbest mean reward: 28.0600\ncurrent episode reward: 15.0000\nepisodes: 2188\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32767.8 seconds (9.10 hours)\n\nTimestep: 7280000\nmean reward (100 episodes): 23.4400\nbest mean reward: 28.0600\ncurrent episode reward: 32.0000\nepisodes: 2191\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32814.3 seconds (9.12 hours)\n\nTimestep: 7290000\nmean reward (100 episodes): 22.4900\nbest mean reward: 28.0600\ncurrent episode reward: 13.0000\nepisodes: 2194\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32860.2 seconds (9.13 hours)\n\nTimestep: 7300000\nmean reward (100 episodes): 22.4600\nbest mean reward: 28.0600\ncurrent episode reward: 27.0000\nepisodes: 2197\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32906.9 seconds (9.14 hours)\n\nTimestep: 7310000\nmean reward (100 episodes): 22.5200\nbest mean reward: 28.0600\ncurrent episode reward: 31.0000\nepisodes: 2200\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32952.8 seconds (9.15 hours)\n\nTimestep: 7320000\nmean reward (100 episodes): 22.2100\nbest mean reward: 28.0600\ncurrent episode reward: 13.0000\nepisodes: 2203\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32998.2 seconds (9.17 hours)\n\nTimestep: 7330000\nmean reward (100 episodes): 22.0400\nbest mean reward: 28.0600\ncurrent episode reward: 31.0000\nepisodes: 2206\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33045.2 seconds (9.18 hours)\n\nTimestep: 7340000\nmean reward (100 episodes): 22.2000\nbest mean reward: 28.0600\ncurrent episode reward: 11.0000\nepisodes: 2209\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33091.5 seconds (9.19 hours)\n\nTimestep: 7350000\nmean reward (100 episodes): 22.0600\nbest mean reward: 28.0600\ncurrent episode reward: 23.0000\nepisodes: 2212\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33137.7 seconds (9.20 hours)\n\nTimestep: 7360000\nmean reward (100 episodes): 21.4900\nbest mean reward: 28.0600\ncurrent episode reward: 12.0000\nepisodes: 2215\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33184.6 seconds (9.22 hours)\n\nTimestep: 7370000\nmean reward (100 episodes): 21.3900\nbest mean reward: 28.0600\ncurrent episode reward: 25.0000\nepisodes: 2218\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33231.2 seconds (9.23 hours)\n\nTimestep: 7380000\nmean reward (100 episodes): 21.5400\nbest mean reward: 28.0600\ncurrent episode reward: 11.0000\nepisodes: 2221\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33277.2 seconds (9.24 hours)\n\nTimestep: 7390000\nmean reward (100 episodes): 21.5100\nbest mean reward: 28.0600\ncurrent episode reward: 2.0000\nepisodes: 2224\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33323.9 seconds (9.26 hours)\n\nTimestep: 7400000\nmean reward (100 episodes): 22.1300\nbest mean reward: 28.0600\ncurrent episode reward: 31.0000\nepisodes: 2227\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33370.3 seconds (9.27 hours)\n\nTimestep: 7410000\nmean reward (100 episodes): 22.2300\nbest mean reward: 28.0600\ncurrent episode reward: 14.0000\nepisodes: 2230\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33417.2 seconds (9.28 hours)\n\nTimestep: 7420000\nmean reward (100 episodes): 22.8000\nbest mean reward: 28.0600\ncurrent episode reward: 30.0000\nepisodes: 2233\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33463.9 seconds (9.30 hours)\n\nTimestep: 7430000\nmean reward (100 episodes): 22.7200\nbest mean reward: 28.0600\ncurrent episode reward: 26.0000\nepisodes: 2236\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33509.8 seconds (9.31 hours)\n\nTimestep: 7440000\nmean reward (100 episodes): 22.1600\nbest mean reward: 28.0600\ncurrent episode reward: 0.0000\nepisodes: 2239\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33556.4 seconds (9.32 hours)\n\nTimestep: 7450000\nmean reward (100 episodes): 21.8600\nbest mean reward: 28.0600\ncurrent episode reward: 32.0000\nepisodes: 2242\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33602.6 seconds (9.33 hours)\n\nTimestep: 7460000\nmean reward (100 episodes): 22.2400\nbest mean reward: 28.0600\ncurrent episode reward: 26.0000\nepisodes: 2245\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33649.0 seconds (9.35 hours)\n\nTimestep: 7470000\nmean reward (100 episodes): 22.3700\nbest mean reward: 28.0600\ncurrent episode reward: 28.0000\nepisodes: 2248\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33695.9 seconds (9.36 hours)\n\nTimestep: 7480000\nmean reward (100 episodes): 22.7300\nbest mean reward: 28.0600\ncurrent episode reward: 46.0000\nepisodes: 2251\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33742.1 seconds (9.37 hours)\n\nTimestep: 7490000\nmean reward (100 episodes): 22.8900\nbest mean reward: 28.0600\ncurrent episode reward: 22.0000\nepisodes: 2254\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33788.8 seconds (9.39 hours)\n\nTimestep: 7500000\nmean reward (100 episodes): 22.7900\nbest mean reward: 28.0600\ncurrent episode reward: 19.0000\nepisodes: 2257\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33836.1 seconds (9.40 hours)\n\nTimestep: 7510000\nmean reward (100 episodes): 22.6900\nbest mean reward: 28.0600\ncurrent episode reward: 36.0000\nepisodes: 2260\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33882.0 seconds (9.41 hours)\n\nTimestep: 7520000\nmean reward (100 episodes): 22.5400\nbest mean reward: 28.0600\ncurrent episode reward: 20.0000\nepisodes: 2263\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33927.4 seconds (9.42 hours)\n\nTimestep: 7530000\nmean reward (100 episodes): 22.3800\nbest mean reward: 28.0600\ncurrent episode reward: 39.0000\nepisodes: 2266\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 33973.6 seconds (9.44 hours)\n\nTimestep: 7540000\nmean reward (100 episodes): 22.8900\nbest mean reward: 28.0600\ncurrent episode reward: 77.0000\nepisodes: 2269\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34020.6 seconds (9.45 hours)\n\nTimestep: 7550000\nmean reward (100 episodes): 22.7400\nbest mean reward: 28.0600\ncurrent episode reward: 8.0000\nepisodes: 2272\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34067.6 seconds (9.46 hours)\n\nTimestep: 7560000\nmean reward (100 episodes): 22.8100\nbest mean reward: 28.0600\ncurrent episode reward: 36.0000\nepisodes: 2275\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34114.3 seconds (9.48 hours)\n\nTimestep: 7570000\nmean reward (100 episodes): 23.1900\nbest mean reward: 28.0600\ncurrent episode reward: 34.0000\nepisodes: 2278\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34161.5 seconds (9.49 hours)\n\nTimestep: 7580000\nmean reward (100 episodes): 23.1300\nbest mean reward: 28.0600\ncurrent episode reward: 23.0000\nepisodes: 2281\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34208.1 seconds (9.50 hours)\n\nTimestep: 7590000\nmean reward (100 episodes): 23.5300\nbest mean reward: 28.0600\ncurrent episode reward: 12.0000\nepisodes: 2284\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34253.9 seconds (9.51 hours)\n\nTimestep: 7600000\nmean reward (100 episodes): 23.9100\nbest mean reward: 28.0600\ncurrent episode reward: 48.0000\nepisodes: 2287\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34300.5 seconds (9.53 hours)\n\nTimestep: 7610000\nmean reward (100 episodes): 23.7200\nbest mean reward: 28.0600\ncurrent episode reward: 13.0000\nepisodes: 2290\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34347.3 seconds (9.54 hours)\n\nTimestep: 7620000\nmean reward (100 episodes): 23.8400\nbest mean reward: 28.0600\ncurrent episode reward: 16.0000\nepisodes: 2293\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34393.8 seconds (9.55 hours)\n\nTimestep: 7630000\nmean reward (100 episodes): 23.7200\nbest mean reward: 28.0600\ncurrent episode reward: 3.0000\nepisodes: 2296\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34440.7 seconds (9.57 hours)\n\nTimestep: 7640000\nmean reward (100 episodes): 23.6100\nbest mean reward: 28.0600\ncurrent episode reward: 25.0000\nepisodes: 2299\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34486.8 seconds (9.58 hours)\n\nTimestep: 7650000\nmean reward (100 episodes): 23.7600\nbest mean reward: 28.0600\ncurrent episode reward: 15.0000\nepisodes: 2302\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34532.9 seconds (9.59 hours)\n\nTimestep: 7660000\nmean reward (100 episodes): 23.9200\nbest mean reward: 28.0600\ncurrent episode reward: 18.0000\nepisodes: 2305\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34578.9 seconds (9.61 hours)\n\nTimestep: 7670000\nmean reward (100 episodes): 23.9800\nbest mean reward: 28.0600\ncurrent episode reward: 34.0000\nepisodes: 2308\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34625.1 seconds (9.62 hours)\n\nTimestep: 7680000\nmean reward (100 episodes): 24.9700\nbest mean reward: 28.0600\ncurrent episode reward: 10.0000\nepisodes: 2311\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34671.3 seconds (9.63 hours)\n\nTimestep: 7690000\nmean reward (100 episodes): 25.4800\nbest mean reward: 28.0600\ncurrent episode reward: 26.0000\nepisodes: 2314\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34717.1 seconds (9.64 hours)\n\nTimestep: 7700000\nmean reward (100 episodes): 25.9300\nbest mean reward: 28.0600\ncurrent episode reward: 29.0000\nepisodes: 2317\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34763.0 seconds (9.66 hours)\n\nTimestep: 7710000\nmean reward (100 episodes): 25.9400\nbest mean reward: 28.0600\ncurrent episode reward: 24.0000\nepisodes: 2320\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34809.3 seconds (9.67 hours)\n\nTimestep: 7720000\nmean reward (100 episodes): 25.9700\nbest mean reward: 28.0600\ncurrent episode reward: 27.0000\nepisodes: 2323\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34855.6 seconds (9.68 hours)\n\nTimestep: 7730000\nmean reward (100 episodes): 26.2100\nbest mean reward: 28.0600\ncurrent episode reward: 25.0000\nepisodes: 2326\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34902.2 seconds (9.70 hours)\n\nTimestep: 7740000\nmean reward (100 episodes): 26.4200\nbest mean reward: 28.0600\ncurrent episode reward: 30.0000\nepisodes: 2329\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34948.4 seconds (9.71 hours)\n\nTimestep: 7750000\nmean reward (100 episodes): 26.1700\nbest mean reward: 28.0600\ncurrent episode reward: 31.0000\nepisodes: 2332\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 34993.8 seconds (9.72 hours)\n\nTimestep: 7760000\nmean reward (100 episodes): 26.8300\nbest mean reward: 28.0600\ncurrent episode reward: 29.0000\nepisodes: 2335\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35040.0 seconds (9.73 hours)\n\nTimestep: 7770000\nmean reward (100 episodes): 26.7700\nbest mean reward: 28.0600\ncurrent episode reward: 31.0000\nepisodes: 2338\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35086.9 seconds (9.75 hours)\n\nTimestep: 7780000\nmean reward (100 episodes): 27.2600\nbest mean reward: 28.0600\ncurrent episode reward: 3.0000\nepisodes: 2341\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35133.8 seconds (9.76 hours)\n\nTimestep: 7790000\nmean reward (100 episodes): 27.0100\nbest mean reward: 28.0600\ncurrent episode reward: 22.0000\nepisodes: 2344\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35179.6 seconds (9.77 hours)\n\nTimestep: 7800000\nmean reward (100 episodes): 27.2300\nbest mean reward: 28.0600\ncurrent episode reward: 35.0000\nepisodes: 2347\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35226.3 seconds (9.79 hours)\n\nTimestep: 7810000\nmean reward (100 episodes): 27.0700\nbest mean reward: 28.0600\ncurrent episode reward: 14.0000\nepisodes: 2350\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35273.7 seconds (9.80 hours)\n\nTimestep: 7820000\nmean reward (100 episodes): 27.0000\nbest mean reward: 28.0600\ncurrent episode reward: 44.0000\nepisodes: 2353\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35320.3 seconds (9.81 hours)\n\nTimestep: 7830000\nmean reward (100 episodes): 27.2000\nbest mean reward: 28.0600\ncurrent episode reward: 5.0000\nepisodes: 2356\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35366.6 seconds (9.82 hours)\n\nTimestep: 7840000\nmean reward (100 episodes): 27.4800\nbest mean reward: 28.0600\ncurrent episode reward: 8.0000\nepisodes: 2359\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35412.9 seconds (9.84 hours)\n\nTimestep: 7850000\nmean reward (100 episodes): 27.7000\nbest mean reward: 28.0600\ncurrent episode reward: 32.0000\nepisodes: 2362\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35458.7 seconds (9.85 hours)\n\nTimestep: 7860000\nmean reward (100 episodes): 28.2100\nbest mean reward: 28.2100\ncurrent episode reward: 23.0000\nepisodes: 2365\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35504.7 seconds (9.86 hours)\n\nTimestep: 7870000\nmean reward (100 episodes): 27.9800\nbest mean reward: 28.2100\ncurrent episode reward: 14.0000\nepisodes: 2368\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35550.3 seconds (9.88 hours)\n\nTimestep: 7880000\nmean reward (100 episodes): 27.3300\nbest mean reward: 28.2100\ncurrent episode reward: 14.0000\nepisodes: 2371\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35596.4 seconds (9.89 hours)\n\nTimestep: 7890000\nmean reward (100 episodes): 27.8800\nbest mean reward: 28.2100\ncurrent episode reward: 29.0000\nepisodes: 2374\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35642.6 seconds (9.90 hours)\n\nTimestep: 7900000\nmean reward (100 episodes): 27.9300\nbest mean reward: 28.2100\ncurrent episode reward: 40.0000\nepisodes: 2377\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35689.3 seconds (9.91 hours)\n\nTimestep: 7910000\nmean reward (100 episodes): 27.9700\nbest mean reward: 28.2100\ncurrent episode reward: 17.0000\nepisodes: 2380\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35734.7 seconds (9.93 hours)\n\nTimestep: 7920000\nmean reward (100 episodes): 27.9700\nbest mean reward: 28.2100\ncurrent episode reward: 29.0000\nepisodes: 2383\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35781.6 seconds (9.94 hours)\n\nTimestep: 7930000\nmean reward (100 episodes): 27.9700\nbest mean reward: 28.2100\ncurrent episode reward: 5.0000\nepisodes: 2386\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35827.7 seconds (9.95 hours)\n\nTimestep: 7940000\nmean reward (100 episodes): 27.2000\nbest mean reward: 28.2100\ncurrent episode reward: 12.0000\nepisodes: 2389\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35873.9 seconds (9.96 hours)\n\nTimestep: 7950000\nmean reward (100 episodes): 27.8200\nbest mean reward: 28.2100\ncurrent episode reward: 39.0000\nepisodes: 2392\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35918.9 seconds (9.98 hours)\n\nTimestep: 7960000\nmean reward (100 episodes): 27.8500\nbest mean reward: 28.2100\ncurrent episode reward: 3.0000\nepisodes: 2395\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 35965.4 seconds (9.99 hours)\n\nTimestep: 7970000\nmean reward (100 episodes): 28.8700\nbest mean reward: 28.8700\ncurrent episode reward: 93.0000\nepisodes: 2398\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36012.2 seconds (10.00 hours)\n\nTimestep: 7980000\nmean reward (100 episodes): 29.0100\nbest mean reward: 29.0100\ncurrent episode reward: 35.0000\nepisodes: 2401\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36058.9 seconds (10.02 hours)\n\nTimestep: 7990000\nmean reward (100 episodes): 29.0900\nbest mean reward: 29.0900\ncurrent episode reward: 36.0000\nepisodes: 2404\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36105.9 seconds (10.03 hours)\n\nTimestep: 8000000\nmean reward (100 episodes): 29.1500\nbest mean reward: 29.2100\ncurrent episode reward: 55.0000\nepisodes: 2407\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36152.4 seconds (10.04 hours)\n\nTimestep: 8010000\nmean reward (100 episodes): 27.7200\nbest mean reward: 29.2100\ncurrent episode reward: 16.0000\nepisodes: 2410\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36198.9 seconds (10.06 hours)\n\nTimestep: 8020000\nmean reward (100 episodes): 27.7300\nbest mean reward: 29.2100\ncurrent episode reward: 45.0000\nepisodes: 2413\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36246.1 seconds (10.07 hours)\n\nTimestep: 8030000\nmean reward (100 episodes): 28.0700\nbest mean reward: 29.2100\ncurrent episode reward: 52.0000\nepisodes: 2416\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36292.6 seconds (10.08 hours)\n\nTimestep: 8040000\nmean reward (100 episodes): 27.5000\nbest mean reward: 29.2100\ncurrent episode reward: 11.0000\nepisodes: 2419\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36339.1 seconds (10.09 hours)\n\nTimestep: 8050000\nmean reward (100 episodes): 27.5600\nbest mean reward: 29.2100\ncurrent episode reward: 45.0000\nepisodes: 2422\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36385.7 seconds (10.11 hours)\n\nTimestep: 8060000\nmean reward (100 episodes): 27.4300\nbest mean reward: 29.2100\ncurrent episode reward: 29.0000\nepisodes: 2425\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36431.7 seconds (10.12 hours)\n\nTimestep: 8070000\nmean reward (100 episodes): 27.6800\nbest mean reward: 29.2100\ncurrent episode reward: 41.0000\nepisodes: 2428\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36478.3 seconds (10.13 hours)\n\nTimestep: 8080000\nmean reward (100 episodes): 27.5300\nbest mean reward: 29.2100\ncurrent episode reward: 16.0000\nepisodes: 2431\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36523.9 seconds (10.15 hours)\n\nTimestep: 8090000\nmean reward (100 episodes): 27.0700\nbest mean reward: 29.2100\ncurrent episode reward: 11.0000\nepisodes: 2434\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36570.4 seconds (10.16 hours)\n\nTimestep: 8100000\nmean reward (100 episodes): 27.5800\nbest mean reward: 29.2100\ncurrent episode reward: 46.0000\nepisodes: 2437\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36616.7 seconds (10.17 hours)\n\nTimestep: 8110000\nmean reward (100 episodes): 27.4000\nbest mean reward: 29.2100\ncurrent episode reward: 13.0000\nepisodes: 2440\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36663.1 seconds (10.18 hours)\n\nTimestep: 8120000\nmean reward (100 episodes): 27.4900\nbest mean reward: 29.2100\ncurrent episode reward: 29.0000\nepisodes: 2443\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36709.4 seconds (10.20 hours)\n\nTimestep: 8130000\nmean reward (100 episodes): 27.1500\nbest mean reward: 29.2100\ncurrent episode reward: 38.0000\nepisodes: 2446\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36755.8 seconds (10.21 hours)\n\nTimestep: 8140000\nmean reward (100 episodes): 26.9800\nbest mean reward: 29.2100\ncurrent episode reward: 38.0000\nepisodes: 2449\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36802.3 seconds (10.22 hours)\n\nTimestep: 8150000\nmean reward (100 episodes): 26.9100\nbest mean reward: 29.2100\ncurrent episode reward: 32.0000\nepisodes: 2453\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36848.9 seconds (10.24 hours)\n\nTimestep: 8160000\nmean reward (100 episodes): 26.8500\nbest mean reward: 29.2100\ncurrent episode reward: 25.0000\nepisodes: 2456\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36895.4 seconds (10.25 hours)\n\nTimestep: 8170000\nmean reward (100 episodes): 26.7200\nbest mean reward: 29.2100\ncurrent episode reward: 29.0000\nepisodes: 2459\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36942.4 seconds (10.26 hours)\n\nTimestep: 8180000\nmean reward (100 episodes): 26.6400\nbest mean reward: 29.2100\ncurrent episode reward: 66.0000\nepisodes: 2462\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 36989.3 seconds (10.27 hours)\n\nTimestep: 8190000\nmean reward (100 episodes): 26.3300\nbest mean reward: 29.2100\ncurrent episode reward: 20.0000\nepisodes: 2465\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37035.1 seconds (10.29 hours)\n\nTimestep: 8200000\nmean reward (100 episodes): 27.0600\nbest mean reward: 29.2100\ncurrent episode reward: 40.0000\nepisodes: 2468\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37081.5 seconds (10.30 hours)\n\nTimestep: 8210000\nmean reward (100 episodes): 26.9600\nbest mean reward: 29.2100\ncurrent episode reward: 9.0000\nepisodes: 2471\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37127.5 seconds (10.31 hours)\n\nTimestep: 8220000\nmean reward (100 episodes): 26.4000\nbest mean reward: 29.2100\ncurrent episode reward: 8.0000\nepisodes: 2474\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37173.4 seconds (10.33 hours)\n\nTimestep: 8230000\nmean reward (100 episodes): 26.3500\nbest mean reward: 29.2100\ncurrent episode reward: 30.0000\nepisodes: 2477\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37219.7 seconds (10.34 hours)\n\nTimestep: 8240000\nmean reward (100 episodes): 26.0400\nbest mean reward: 29.2100\ncurrent episode reward: 13.0000\nepisodes: 2480\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37266.1 seconds (10.35 hours)\n\nTimestep: 8250000\nmean reward (100 episodes): 26.5200\nbest mean reward: 29.2100\ncurrent episode reward: 84.0000\nepisodes: 2483\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37313.7 seconds (10.36 hours)\n\nTimestep: 8260000\nmean reward (100 episodes): 26.8000\nbest mean reward: 29.2100\ncurrent episode reward: 42.0000\nepisodes: 2486\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37360.2 seconds (10.38 hours)\n\nTimestep: 8270000\nmean reward (100 episodes): 27.0100\nbest mean reward: 29.2100\ncurrent episode reward: 9.0000\nepisodes: 2489\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37407.4 seconds (10.39 hours)\n\nTimestep: 8280000\nmean reward (100 episodes): 26.6800\nbest mean reward: 29.2100\ncurrent episode reward: 24.0000\nepisodes: 2492\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37454.1 seconds (10.40 hours)\n\nTimestep: 8290000\nmean reward (100 episodes): 26.7000\nbest mean reward: 29.2100\ncurrent episode reward: 14.0000\nepisodes: 2495\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37500.6 seconds (10.42 hours)\n\nTimestep: 8300000\nmean reward (100 episodes): 25.9400\nbest mean reward: 29.2100\ncurrent episode reward: 31.0000\nepisodes: 2498\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37547.3 seconds (10.43 hours)\n\nTimestep: 8310000\nmean reward (100 episodes): 26.1500\nbest mean reward: 29.2100\ncurrent episode reward: 52.0000\nepisodes: 2501\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37593.3 seconds (10.44 hours)\n\nTimestep: 8320000\nmean reward (100 episodes): 26.3700\nbest mean reward: 29.2100\ncurrent episode reward: 27.0000\nepisodes: 2504\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37640.2 seconds (10.46 hours)\n\nTimestep: 8330000\nmean reward (100 episodes): 26.5600\nbest mean reward: 29.2100\ncurrent episode reward: 38.0000\nepisodes: 2507\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37686.2 seconds (10.47 hours)\n\nTimestep: 8340000\nmean reward (100 episodes): 26.8200\nbest mean reward: 29.2100\ncurrent episode reward: 14.0000\nepisodes: 2510\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37732.6 seconds (10.48 hours)\n\nTimestep: 8350000\nmean reward (100 episodes): 26.6700\nbest mean reward: 29.2100\ncurrent episode reward: 8.0000\nepisodes: 2513\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37779.7 seconds (10.49 hours)\n\nTimestep: 8360000\nmean reward (100 episodes): 26.3300\nbest mean reward: 29.2100\ncurrent episode reward: 41.0000\nepisodes: 2516\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37825.9 seconds (10.51 hours)\n\nTimestep: 8370000\nmean reward (100 episodes): 26.5500\nbest mean reward: 29.2100\ncurrent episode reward: 18.0000\nepisodes: 2519\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37872.6 seconds (10.52 hours)\n\nTimestep: 8380000\nmean reward (100 episodes): 26.4700\nbest mean reward: 29.2100\ncurrent episode reward: 14.0000\nepisodes: 2522\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37918.5 seconds (10.53 hours)\n\nTimestep: 8390000\nmean reward (100 episodes): 26.0300\nbest mean reward: 29.2100\ncurrent episode reward: 8.0000\nepisodes: 2525\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 37964.6 seconds (10.55 hours)\n\nTimestep: 8400000\nmean reward (100 episodes): 25.6100\nbest mean reward: 29.2100\ncurrent episode reward: 3.0000\nepisodes: 2528\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38010.2 seconds (10.56 hours)\n\nTimestep: 8410000\nmean reward (100 episodes): 26.2800\nbest mean reward: 29.2100\ncurrent episode reward: 92.0000\nepisodes: 2531\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38057.1 seconds (10.57 hours)\n\nTimestep: 8420000\nmean reward (100 episodes): 26.6000\nbest mean reward: 29.2100\ncurrent episode reward: 39.0000\nepisodes: 2534\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38104.1 seconds (10.58 hours)\n\nTimestep: 8430000\nmean reward (100 episodes): 26.0600\nbest mean reward: 29.2100\ncurrent episode reward: 7.0000\nepisodes: 2537\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38150.1 seconds (10.60 hours)\n\nTimestep: 8440000\nmean reward (100 episodes): 25.9800\nbest mean reward: 29.2100\ncurrent episode reward: 8.0000\nepisodes: 2540\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38195.5 seconds (10.61 hours)\n\nTimestep: 8450000\nmean reward (100 episodes): 25.9700\nbest mean reward: 29.2100\ncurrent episode reward: 16.0000\nepisodes: 2543\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38242.3 seconds (10.62 hours)\n\nTimestep: 8460000\nmean reward (100 episodes): 26.0000\nbest mean reward: 29.2100\ncurrent episode reward: 23.0000\nepisodes: 2546\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38288.1 seconds (10.64 hours)\n\nTimestep: 8470000\nmean reward (100 episodes): 25.6800\nbest mean reward: 29.2100\ncurrent episode reward: 21.0000\nepisodes: 2549\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38334.4 seconds (10.65 hours)\n\nTimestep: 8480000\nmean reward (100 episodes): 25.5000\nbest mean reward: 29.2100\ncurrent episode reward: 0.0000\nepisodes: 2552\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38381.0 seconds (10.66 hours)\n\nTimestep: 8490000\nmean reward (100 episodes): 25.4700\nbest mean reward: 29.2100\ncurrent episode reward: 21.0000\nepisodes: 2555\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38426.9 seconds (10.67 hours)\n\nTimestep: 8500000\nmean reward (100 episodes): 25.8700\nbest mean reward: 29.2100\ncurrent episode reward: 43.0000\nepisodes: 2558\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38474.0 seconds (10.69 hours)\n\nTimestep: 8510000\nmean reward (100 episodes): 25.7800\nbest mean reward: 29.2100\ncurrent episode reward: 20.0000\nepisodes: 2561\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38520.3 seconds (10.70 hours)\n\nTimestep: 8520000\nmean reward (100 episodes): 25.8300\nbest mean reward: 29.2100\ncurrent episode reward: 55.0000\nepisodes: 2564\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38566.7 seconds (10.71 hours)\n\nTimestep: 8530000\nmean reward (100 episodes): 25.9200\nbest mean reward: 29.2100\ncurrent episode reward: 37.0000\nepisodes: 2567\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38613.1 seconds (10.73 hours)\n\nTimestep: 8540000\nmean reward (100 episodes): 25.6700\nbest mean reward: 29.2100\ncurrent episode reward: 16.0000\nepisodes: 2570\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38659.7 seconds (10.74 hours)\n\nTimestep: 8550000\nmean reward (100 episodes): 26.4600\nbest mean reward: 29.2100\ncurrent episode reward: 1.0000\nepisodes: 2573\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38706.2 seconds (10.75 hours)\n\nTimestep: 8560000\nmean reward (100 episodes): 25.8300\nbest mean reward: 29.2100\ncurrent episode reward: 5.0000\nepisodes: 2576\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38752.6 seconds (10.76 hours)\n\nTimestep: 8570000\nmean reward (100 episodes): 26.3100\nbest mean reward: 29.2100\ncurrent episode reward: 76.0000\nepisodes: 2579\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38799.6 seconds (10.78 hours)\n\nTimestep: 8580000\nmean reward (100 episodes): 26.1800\nbest mean reward: 29.2100\ncurrent episode reward: 37.0000\nepisodes: 2582\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38845.3 seconds (10.79 hours)\n\nTimestep: 8590000\nmean reward (100 episodes): 25.6000\nbest mean reward: 29.2100\ncurrent episode reward: 22.0000\nepisodes: 2585\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38891.9 seconds (10.80 hours)\n\nTimestep: 8600000\nmean reward (100 episodes): 25.6500\nbest mean reward: 29.2100\ncurrent episode reward: 23.0000\nepisodes: 2588\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38938.0 seconds (10.82 hours)\n\nTimestep: 8610000\nmean reward (100 episodes): 25.9400\nbest mean reward: 29.2100\ncurrent episode reward: 25.0000\nepisodes: 2591\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 38984.3 seconds (10.83 hours)\n\nTimestep: 8620000\nmean reward (100 episodes): 26.3800\nbest mean reward: 29.2100\ncurrent episode reward: 42.0000\nepisodes: 2594\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39030.5 seconds (10.84 hours)\n\nTimestep: 8630000\nmean reward (100 episodes): 26.9200\nbest mean reward: 29.2100\ncurrent episode reward: 25.0000\nepisodes: 2597\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39076.7 seconds (10.85 hours)\n\nTimestep: 8640000\nmean reward (100 episodes): 26.8300\nbest mean reward: 29.2100\ncurrent episode reward: 10.0000\nepisodes: 2600\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39122.7 seconds (10.87 hours)\n\nTimestep: 8650000\nmean reward (100 episodes): 26.5200\nbest mean reward: 29.2100\ncurrent episode reward: 38.0000\nepisodes: 2603\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39169.2 seconds (10.88 hours)\n\nTimestep: 8660000\nmean reward (100 episodes): 26.3500\nbest mean reward: 29.2100\ncurrent episode reward: 29.0000\nepisodes: 2606\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39215.9 seconds (10.89 hours)\n\nTimestep: 8670000\nmean reward (100 episodes): 26.6600\nbest mean reward: 29.2100\ncurrent episode reward: 48.0000\nepisodes: 2609\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39262.9 seconds (10.91 hours)\n\nTimestep: 8680000\nmean reward (100 episodes): 26.4500\nbest mean reward: 29.2100\ncurrent episode reward: 9.0000\nepisodes: 2612\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39309.2 seconds (10.92 hours)\n\nTimestep: 8690000\nmean reward (100 episodes): 26.6400\nbest mean reward: 29.2100\ncurrent episode reward: 1.0000\nepisodes: 2615\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39355.2 seconds (10.93 hours)\n\nTimestep: 8700000\nmean reward (100 episodes): 26.7000\nbest mean reward: 29.2100\ncurrent episode reward: 22.0000\nepisodes: 2618\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39401.8 seconds (10.94 hours)\n\nTimestep: 8710000\nmean reward (100 episodes): 25.9900\nbest mean reward: 29.2100\ncurrent episode reward: 10.0000\nepisodes: 2621\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39447.6 seconds (10.96 hours)\n\nTimestep: 8720000\nmean reward (100 episodes): 26.6500\nbest mean reward: 29.2100\ncurrent episode reward: 24.0000\nepisodes: 2624\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39494.9 seconds (10.97 hours)\n\nTimestep: 8730000\nmean reward (100 episodes): 26.8700\nbest mean reward: 29.2100\ncurrent episode reward: 30.0000\nepisodes: 2627\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39540.6 seconds (10.98 hours)\n\nTimestep: 8740000\nmean reward (100 episodes): 27.7500\nbest mean reward: 29.2100\ncurrent episode reward: 24.0000\nepisodes: 2630\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39587.2 seconds (11.00 hours)\n\nTimestep: 8750000\nmean reward (100 episodes): 26.9300\nbest mean reward: 29.2100\ncurrent episode reward: 20.0000\nepisodes: 2633\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39633.3 seconds (11.01 hours)\n\nTimestep: 8760000\nmean reward (100 episodes): 27.1000\nbest mean reward: 29.2100\ncurrent episode reward: 27.0000\nepisodes: 2636\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39679.8 seconds (11.02 hours)\n\nTimestep: 8770000\nmean reward (100 episodes): 26.8600\nbest mean reward: 29.2100\ncurrent episode reward: 37.0000\nepisodes: 2639\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39725.6 seconds (11.03 hours)\n\nTimestep: 8780000\nmean reward (100 episodes): 27.2600\nbest mean reward: 29.2100\ncurrent episode reward: 39.0000\nepisodes: 2642\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39772.4 seconds (11.05 hours)\n\nTimestep: 8790000\nmean reward (100 episodes): 27.3000\nbest mean reward: 29.2100\ncurrent episode reward: 25.0000\nepisodes: 2645\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39819.0 seconds (11.06 hours)\n\nTimestep: 8800000\nmean reward (100 episodes): 27.7300\nbest mean reward: 29.2100\ncurrent episode reward: 29.0000\nepisodes: 2648\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39865.2 seconds (11.07 hours)\n\nTimestep: 8810000\nmean reward (100 episodes): 27.7600\nbest mean reward: 29.2100\ncurrent episode reward: 7.0000\nepisodes: 2651\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39911.1 seconds (11.09 hours)\n\nTimestep: 8820000\nmean reward (100 episodes): 28.0100\nbest mean reward: 29.2100\ncurrent episode reward: 15.0000\nepisodes: 2654\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 39957.6 seconds (11.10 hours)\n\nTimestep: 8830000\nmean reward (100 episodes): 27.7700\nbest mean reward: 29.2100\ncurrent episode reward: 26.0000\nepisodes: 2657\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40003.7 seconds (11.11 hours)\n\nTimestep: 8840000\nmean reward (100 episodes): 27.2800\nbest mean reward: 29.2100\ncurrent episode reward: 21.0000\nepisodes: 2660\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40050.2 seconds (11.13 hours)\n\nTimestep: 8850000\nmean reward (100 episodes): 27.4000\nbest mean reward: 29.2100\ncurrent episode reward: 43.0000\nepisodes: 2663\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40096.5 seconds (11.14 hours)\n\nTimestep: 8860000\nmean reward (100 episodes): 26.7100\nbest mean reward: 29.2100\ncurrent episode reward: 16.0000\nepisodes: 2666\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40142.4 seconds (11.15 hours)\n\nTimestep: 8870000\nmean reward (100 episodes): 26.4000\nbest mean reward: 29.2100\ncurrent episode reward: 28.0000\nepisodes: 2669\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40188.2 seconds (11.16 hours)\n\nTimestep: 8880000\nmean reward (100 episodes): 25.7200\nbest mean reward: 29.2100\ncurrent episode reward: 12.0000\nepisodes: 2672\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40233.9 seconds (11.18 hours)\n\nTimestep: 8890000\nmean reward (100 episodes): 26.5700\nbest mean reward: 29.2100\ncurrent episode reward: 17.0000\nepisodes: 2675\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40280.8 seconds (11.19 hours)\n\nTimestep: 8900000\nmean reward (100 episodes): 26.6500\nbest mean reward: 29.2100\ncurrent episode reward: 18.0000\nepisodes: 2678\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40326.9 seconds (11.20 hours)\n\nTimestep: 8910000\nmean reward (100 episodes): 26.5900\nbest mean reward: 29.2100\ncurrent episode reward: 30.0000\nepisodes: 2681\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40373.6 seconds (11.21 hours)\n\nTimestep: 8920000\nmean reward (100 episodes): 26.8400\nbest mean reward: 29.2100\ncurrent episode reward: 14.0000\nepisodes: 2684\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40419.7 seconds (11.23 hours)\n\nTimestep: 8930000\nmean reward (100 episodes): 27.0800\nbest mean reward: 29.2100\ncurrent episode reward: 38.0000\nepisodes: 2687\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40466.2 seconds (11.24 hours)\n\nTimestep: 8940000\nmean reward (100 episodes): 27.1300\nbest mean reward: 29.2100\ncurrent episode reward: 30.0000\nepisodes: 2690\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40512.3 seconds (11.25 hours)\n\nTimestep: 8950000\nmean reward (100 episodes): 27.2900\nbest mean reward: 29.2100\ncurrent episode reward: 41.0000\nepisodes: 2693\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40558.7 seconds (11.27 hours)\n\nTimestep: 8960000\nmean reward (100 episodes): 27.1900\nbest mean reward: 29.2100\ncurrent episode reward: 38.0000\nepisodes: 2696\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40604.6 seconds (11.28 hours)\n\nTimestep: 8970000\nmean reward (100 episodes): 27.4800\nbest mean reward: 29.2100\ncurrent episode reward: 43.0000\nepisodes: 2699\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40651.0 seconds (11.29 hours)\n\nTimestep: 8980000\nmean reward (100 episodes): 27.3100\nbest mean reward: 29.2100\ncurrent episode reward: 26.0000\nepisodes: 2702\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40697.1 seconds (11.30 hours)\n\nTimestep: 8990000\nmean reward (100 episodes): 26.9900\nbest mean reward: 29.2100\ncurrent episode reward: 18.0000\nepisodes: 2705\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40744.0 seconds (11.32 hours)\n\nTimestep: 9000000\nmean reward (100 episodes): 27.0300\nbest mean reward: 29.2100\ncurrent episode reward: 36.0000\nepisodes: 2708\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40790.7 seconds (11.33 hours)\n\nTimestep: 9010000\nmean reward (100 episodes): 26.8100\nbest mean reward: 29.2100\ncurrent episode reward: 36.0000\nepisodes: 2711\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40837.2 seconds (11.34 hours)\n\nTimestep: 9020000\nmean reward (100 episodes): 26.9300\nbest mean reward: 29.2100\ncurrent episode reward: 18.0000\nepisodes: 2714\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40883.6 seconds (11.36 hours)\n\nTimestep: 9030000\nmean reward (100 episodes): 27.1200\nbest mean reward: 29.2100\ncurrent episode reward: 21.0000\nepisodes: 2717\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40930.3 seconds (11.37 hours)\n\nTimestep: 9040000\nmean reward (100 episodes): 27.6600\nbest mean reward: 29.2100\ncurrent episode reward: 17.0000\nepisodes: 2720\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 40977.5 seconds (11.38 hours)\n\nTimestep: 9050000\nmean reward (100 episodes): 27.3600\nbest mean reward: 29.2100\ncurrent episode reward: 44.0000\nepisodes: 2723\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41024.8 seconds (11.40 hours)\n\nTimestep: 9060000\nmean reward (100 episodes): 27.2400\nbest mean reward: 29.2100\ncurrent episode reward: 33.0000\nepisodes: 2726\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41071.6 seconds (11.41 hours)\n\nTimestep: 9070000\nmean reward (100 episodes): 26.4000\nbest mean reward: 29.2100\ncurrent episode reward: 28.0000\nepisodes: 2729\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41118.5 seconds (11.42 hours)\n\nTimestep: 9080000\nmean reward (100 episodes): 26.6600\nbest mean reward: 29.2100\ncurrent episode reward: 16.0000\nepisodes: 2732\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41165.1 seconds (11.43 hours)\n\nTimestep: 9090000\nmean reward (100 episodes): 26.4600\nbest mean reward: 29.2100\ncurrent episode reward: 18.0000\nepisodes: 2735\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41211.5 seconds (11.45 hours)\n\nTimestep: 9100000\nmean reward (100 episodes): 26.9600\nbest mean reward: 29.2100\ncurrent episode reward: 33.0000\nepisodes: 2738\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41258.4 seconds (11.46 hours)\n\nTimestep: 9110000\nmean reward (100 episodes): 26.6900\nbest mean reward: 29.2100\ncurrent episode reward: 29.0000\nepisodes: 2741\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41303.7 seconds (11.47 hours)\n\nTimestep: 9120000\nmean reward (100 episodes): 26.4000\nbest mean reward: 29.2100\ncurrent episode reward: 23.0000\nepisodes: 2744\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41349.3 seconds (11.49 hours)\n\nTimestep: 9130000\nmean reward (100 episodes): 26.4700\nbest mean reward: 29.2100\ncurrent episode reward: 30.0000\nepisodes: 2747\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41395.1 seconds (11.50 hours)\n\nTimestep: 9140000\nmean reward (100 episodes): 26.0100\nbest mean reward: 29.2100\ncurrent episode reward: 28.0000\nepisodes: 2750\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41441.9 seconds (11.51 hours)\n\nTimestep: 9150000\nmean reward (100 episodes): 25.9700\nbest mean reward: 29.2100\ncurrent episode reward: 26.0000\nepisodes: 2753\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41488.3 seconds (11.52 hours)\n\nTimestep: 9160000\nmean reward (100 episodes): 25.9100\nbest mean reward: 29.2100\ncurrent episode reward: 3.0000\nepisodes: 2757\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41533.6 seconds (11.54 hours)\n\nTimestep: 9170000\nmean reward (100 episodes): 26.6900\nbest mean reward: 29.2100\ncurrent episode reward: 54.0000\nepisodes: 2760\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41579.8 seconds (11.55 hours)\n\nTimestep: 9180000\nmean reward (100 episodes): 26.6700\nbest mean reward: 29.2100\ncurrent episode reward: 20.0000\nepisodes: 2763\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41626.9 seconds (11.56 hours)\n\nTimestep: 9190000\nmean reward (100 episodes): 26.8700\nbest mean reward: 29.2100\ncurrent episode reward: 30.0000\nepisodes: 2766\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41672.8 seconds (11.58 hours)\n\nTimestep: 9200000\nmean reward (100 episodes): 26.9500\nbest mean reward: 29.2100\ncurrent episode reward: 28.0000\nepisodes: 2769\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41718.9 seconds (11.59 hours)\n\nTimestep: 9210000\nmean reward (100 episodes): 26.9100\nbest mean reward: 29.2100\ncurrent episode reward: 27.0000\nepisodes: 2772\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41764.6 seconds (11.60 hours)\n\nTimestep: 9220000\nmean reward (100 episodes): 26.7800\nbest mean reward: 29.2100\ncurrent episode reward: 33.0000\nepisodes: 2775\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41811.5 seconds (11.61 hours)\n\nTimestep: 9230000\nmean reward (100 episodes): 26.6800\nbest mean reward: 29.2100\ncurrent episode reward: 17.0000\nepisodes: 2778\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41858.8 seconds (11.63 hours)\n\nTimestep: 9240000\nmean reward (100 episodes): 26.4200\nbest mean reward: 29.2100\ncurrent episode reward: 30.0000\nepisodes: 2781\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41905.6 seconds (11.64 hours)\n\nTimestep: 9250000\nmean reward (100 episodes): 26.1700\nbest mean reward: 29.2100\ncurrent episode reward: 29.0000\nepisodes: 2784\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41951.6 seconds (11.65 hours)\n\nTimestep: 9260000\nmean reward (100 episodes): 25.7900\nbest mean reward: 29.2100\ncurrent episode reward: 6.0000\nepisodes: 2787\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 41998.2 seconds (11.67 hours)\n\nTimestep: 9270000\nmean reward (100 episodes): 25.4900\nbest mean reward: 29.2100\ncurrent episode reward: 15.0000\nepisodes: 2790\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42044.2 seconds (11.68 hours)\n\nTimestep: 9280000\nmean reward (100 episodes): 25.1300\nbest mean reward: 29.2100\ncurrent episode reward: 9.0000\nepisodes: 2793\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42090.6 seconds (11.69 hours)\n\nTimestep: 9290000\nmean reward (100 episodes): 24.5100\nbest mean reward: 29.2100\ncurrent episode reward: 9.0000\nepisodes: 2796\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42137.2 seconds (11.70 hours)\n\nTimestep: 9300000\nmean reward (100 episodes): 24.0000\nbest mean reward: 29.2100\ncurrent episode reward: 23.0000\nepisodes: 2799\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42183.8 seconds (11.72 hours)\n\nTimestep: 9310000\nmean reward (100 episodes): 24.2100\nbest mean reward: 29.2100\ncurrent episode reward: 19.0000\nepisodes: 2802\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42230.2 seconds (11.73 hours)\n\nTimestep: 9320000\nmean reward (100 episodes): 24.3400\nbest mean reward: 29.2100\ncurrent episode reward: 1.0000\nepisodes: 2805\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42276.1 seconds (11.74 hours)\n\nTimestep: 9330000\nmean reward (100 episodes): 24.0900\nbest mean reward: 29.2100\ncurrent episode reward: 26.0000\nepisodes: 2808\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42323.4 seconds (11.76 hours)\n\nTimestep: 9340000\nmean reward (100 episodes): 23.9900\nbest mean reward: 29.2100\ncurrent episode reward: 14.0000\nepisodes: 2811\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42369.5 seconds (11.77 hours)\n\nTimestep: 9350000\nmean reward (100 episodes): 23.3700\nbest mean reward: 29.2100\ncurrent episode reward: 6.0000\nepisodes: 2814\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42415.5 seconds (11.78 hours)\n\nTimestep: 9360000\nmean reward (100 episodes): 23.3200\nbest mean reward: 29.2100\ncurrent episode reward: 29.0000\nepisodes: 2817\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42462.2 seconds (11.80 hours)\n\nTimestep: 9370000\nmean reward (100 episodes): 23.7700\nbest mean reward: 29.2100\ncurrent episode reward: 50.0000\nepisodes: 2820\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42509.0 seconds (11.81 hours)\n\nTimestep: 9380000\nmean reward (100 episodes): 23.8000\nbest mean reward: 29.2100\ncurrent episode reward: 3.0000\nepisodes: 2823\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42555.1 seconds (11.82 hours)\n\nTimestep: 9390000\nmean reward (100 episodes): 23.6900\nbest mean reward: 29.2100\ncurrent episode reward: 34.0000\nepisodes: 2826\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42601.0 seconds (11.83 hours)\n\nTimestep: 9400000\nmean reward (100 episodes): 23.9500\nbest mean reward: 29.2100\ncurrent episode reward: 31.0000\nepisodes: 2829\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42647.3 seconds (11.85 hours)\n\nTimestep: 9410000\nmean reward (100 episodes): 23.7600\nbest mean reward: 29.2100\ncurrent episode reward: 25.0000\nepisodes: 2832\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42693.4 seconds (11.86 hours)\n\nTimestep: 9420000\nmean reward (100 episodes): 24.0600\nbest mean reward: 29.2100\ncurrent episode reward: 33.0000\nepisodes: 2835\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42739.8 seconds (11.87 hours)\n\nTimestep: 9430000\nmean reward (100 episodes): 24.0600\nbest mean reward: 29.2100\ncurrent episode reward: 27.0000\nepisodes: 2838\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42785.9 seconds (11.88 hours)\n\nTimestep: 9440000\nmean reward (100 episodes): 23.8700\nbest mean reward: 29.2100\ncurrent episode reward: 26.0000\nepisodes: 2841\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42832.5 seconds (11.90 hours)\n\nTimestep: 9450000\nmean reward (100 episodes): 24.1700\nbest mean reward: 29.2100\ncurrent episode reward: 12.0000\nepisodes: 2844\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42879.2 seconds (11.91 hours)\n\nTimestep: 9460000\nmean reward (100 episodes): 24.3300\nbest mean reward: 29.2100\ncurrent episode reward: 35.0000\nepisodes: 2847\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42925.7 seconds (11.92 hours)\n\nTimestep: 9470000\nmean reward (100 episodes): 24.5100\nbest mean reward: 29.2100\ncurrent episode reward: 32.0000\nepisodes: 2850\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 42971.6 seconds (11.94 hours)\n\nTimestep: 9480000\nmean reward (100 episodes): 24.5800\nbest mean reward: 29.2100\ncurrent episode reward: 23.0000\nepisodes: 2853\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43017.8 seconds (11.95 hours)\n\nTimestep: 9490000\nmean reward (100 episodes): 24.7000\nbest mean reward: 29.2100\ncurrent episode reward: 35.0000\nepisodes: 2856\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43063.4 seconds (11.96 hours)\n\nTimestep: 9500000\nmean reward (100 episodes): 24.8900\nbest mean reward: 29.2100\ncurrent episode reward: 31.0000\nepisodes: 2859\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43110.6 seconds (11.98 hours)\n\nTimestep: 9510000\nmean reward (100 episodes): 24.1000\nbest mean reward: 29.2100\ncurrent episode reward: 0.0000\nepisodes: 2862\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43157.1 seconds (11.99 hours)\n\nTimestep: 9520000\nmean reward (100 episodes): 24.2300\nbest mean reward: 29.2100\ncurrent episode reward: 46.0000\nepisodes: 2865\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43203.5 seconds (12.00 hours)\n\nTimestep: 9530000\nmean reward (100 episodes): 24.1900\nbest mean reward: 29.2100\ncurrent episode reward: 15.0000\nepisodes: 2868\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43249.7 seconds (12.01 hours)\n\nTimestep: 9540000\nmean reward (100 episodes): 23.8400\nbest mean reward: 29.2100\ncurrent episode reward: 8.0000\nepisodes: 2871\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43296.2 seconds (12.03 hours)\n\nTimestep: 9550000\nmean reward (100 episodes): 23.8900\nbest mean reward: 29.2100\ncurrent episode reward: 31.0000\nepisodes: 2874\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43342.7 seconds (12.04 hours)\n\nTimestep: 9560000\nmean reward (100 episodes): 24.3900\nbest mean reward: 29.2100\ncurrent episode reward: 37.0000\nepisodes: 2877\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43389.3 seconds (12.05 hours)\n\nTimestep: 9570000\nmean reward (100 episodes): 24.5400\nbest mean reward: 29.2100\ncurrent episode reward: 4.0000\nepisodes: 2880\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43436.4 seconds (12.07 hours)\n\nTimestep: 9580000\nmean reward (100 episodes): 24.6300\nbest mean reward: 29.2100\ncurrent episode reward: 38.0000\nepisodes: 2883\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43483.5 seconds (12.08 hours)\n\nTimestep: 9590000\nmean reward (100 episodes): 24.6500\nbest mean reward: 29.2100\ncurrent episode reward: 26.0000\nepisodes: 2886\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43530.4 seconds (12.09 hours)\n\nTimestep: 9600000\nmean reward (100 episodes): 24.9500\nbest mean reward: 29.2100\ncurrent episode reward: 20.0000\nepisodes: 2889\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43576.4 seconds (12.10 hours)\n\nTimestep: 9610000\nmean reward (100 episodes): 24.5300\nbest mean reward: 29.2100\ncurrent episode reward: 24.0000\nepisodes: 2892\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43622.5 seconds (12.12 hours)\n\nTimestep: 9620000\nmean reward (100 episodes): 24.4900\nbest mean reward: 29.2100\ncurrent episode reward: 0.0000\nepisodes: 2895\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43668.9 seconds (12.13 hours)\n\nTimestep: 9630000\nmean reward (100 episodes): 24.5300\nbest mean reward: 29.2100\ncurrent episode reward: 0.0000\nepisodes: 2898\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43714.8 seconds (12.14 hours)\n\nTimestep: 9640000\nmean reward (100 episodes): 24.4500\nbest mean reward: 29.2100\ncurrent episode reward: 50.0000\nepisodes: 2901\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43760.6 seconds (12.16 hours)\n\nTimestep: 9650000\nmean reward (100 episodes): 24.4100\nbest mean reward: 29.2100\ncurrent episode reward: 24.0000\nepisodes: 2904\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43806.5 seconds (12.17 hours)\n\nTimestep: 9660000\nmean reward (100 episodes): 24.3400\nbest mean reward: 29.2100\ncurrent episode reward: 9.0000\nepisodes: 2907\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43853.5 seconds (12.18 hours)\n\nTimestep: 9670000\nmean reward (100 episodes): 23.9000\nbest mean reward: 29.2100\ncurrent episode reward: 24.0000\nepisodes: 2910\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43899.6 seconds (12.19 hours)\n\nTimestep: 9680000\nmean reward (100 episodes): 24.4600\nbest mean reward: 29.2100\ncurrent episode reward: 40.0000\nepisodes: 2913\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43945.5 seconds (12.21 hours)\n\nTimestep: 9690000\nmean reward (100 episodes): 24.8700\nbest mean reward: 29.2100\ncurrent episode reward: 33.0000\nepisodes: 2916\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 43991.8 seconds (12.22 hours)\n\nTimestep: 9700000\nmean reward (100 episodes): 24.8100\nbest mean reward: 29.2100\ncurrent episode reward: 32.0000\nepisodes: 2919\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44038.1 seconds (12.23 hours)\n\nTimestep: 9710000\nmean reward (100 episodes): 24.7500\nbest mean reward: 29.2100\ncurrent episode reward: 32.0000\nepisodes: 2922\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44083.9 seconds (12.25 hours)\n\nTimestep: 9720000\nmean reward (100 episodes): 24.4900\nbest mean reward: 29.2100\ncurrent episode reward: 23.0000\nepisodes: 2925\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44129.5 seconds (12.26 hours)\n\nTimestep: 9730000\nmean reward (100 episodes): 24.2200\nbest mean reward: 29.2100\ncurrent episode reward: 14.0000\nepisodes: 2928\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44175.9 seconds (12.27 hours)\n\nTimestep: 9740000\nmean reward (100 episodes): 24.2100\nbest mean reward: 29.2100\ncurrent episode reward: 21.0000\nepisodes: 2931\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44221.5 seconds (12.28 hours)\n\nTimestep: 9750000\nmean reward (100 episodes): 24.4100\nbest mean reward: 29.2100\ncurrent episode reward: 36.0000\nepisodes: 2934\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44268.3 seconds (12.30 hours)\n\nTimestep: 9760000\nmean reward (100 episodes): 23.8400\nbest mean reward: 29.2100\ncurrent episode reward: 7.0000\nepisodes: 2937\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44314.1 seconds (12.31 hours)\n\nTimestep: 9770000\nmean reward (100 episodes): 23.7100\nbest mean reward: 29.2100\ncurrent episode reward: 22.0000\nepisodes: 2940\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44360.9 seconds (12.32 hours)\n\nTimestep: 9780000\nmean reward (100 episodes): 23.4500\nbest mean reward: 29.2100\ncurrent episode reward: 14.0000\nepisodes: 2943\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44406.8 seconds (12.34 hours)\n\nTimestep: 9790000\nmean reward (100 episodes): 23.2200\nbest mean reward: 29.2100\ncurrent episode reward: 1.0000\nepisodes: 2946\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44453.3 seconds (12.35 hours)\n\nTimestep: 9800000\nmean reward (100 episodes): 23.0400\nbest mean reward: 29.2100\ncurrent episode reward: 17.0000\nepisodes: 2949\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44499.6 seconds (12.36 hours)\n\nTimestep: 9810000\nmean reward (100 episodes): 22.7900\nbest mean reward: 29.2100\ncurrent episode reward: 24.0000\nepisodes: 2952\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44546.5 seconds (12.37 hours)\n\nTimestep: 9820000\nmean reward (100 episodes): 23.3700\nbest mean reward: 29.2100\ncurrent episode reward: 40.0000\nepisodes: 2955\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44593.2 seconds (12.39 hours)\n\nTimestep: 9830000\nmean reward (100 episodes): 23.1500\nbest mean reward: 29.2100\ncurrent episode reward: 26.0000\nepisodes: 2958\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44640.2 seconds (12.40 hours)\n\nTimestep: 9840000\nmean reward (100 episodes): 22.6100\nbest mean reward: 29.2100\ncurrent episode reward: 0.0000\nepisodes: 2961\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44686.0 seconds (12.41 hours)\n\nTimestep: 9850000\nmean reward (100 episodes): 22.4000\nbest mean reward: 29.2100\ncurrent episode reward: 18.0000\nepisodes: 2964\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44731.4 seconds (12.43 hours)\n\nTimestep: 9860000\nmean reward (100 episodes): 21.7700\nbest mean reward: 29.2100\ncurrent episode reward: 0.0000\nepisodes: 2967\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44777.0 seconds (12.44 hours)\n\nTimestep: 9870000\nmean reward (100 episodes): 21.7400\nbest mean reward: 29.2100\ncurrent episode reward: 22.0000\nepisodes: 2970\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44824.0 seconds (12.45 hours)\n\nTimestep: 9880000\nmean reward (100 episodes): 22.4000\nbest mean reward: 29.2100\ncurrent episode reward: 26.0000\nepisodes: 2973\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44869.9 seconds (12.46 hours)\n\nTimestep: 9890000\nmean reward (100 episodes): 21.8800\nbest mean reward: 29.2100\ncurrent episode reward: 24.0000\nepisodes: 2976\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44916.2 seconds (12.48 hours)\n\nTimestep: 9900000\nmean reward (100 episodes): 21.0700\nbest mean reward: 29.2100\ncurrent episode reward: 14.0000\nepisodes: 2979\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 44962.6 seconds (12.49 hours)\n\nTimestep: 9910000\nmean reward (100 episodes): 21.3100\nbest mean reward: 29.2100\ncurrent episode reward: 18.0000\nepisodes: 2982\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45008.9 seconds (12.50 hours)\n\nTimestep: 9920000\nmean reward (100 episodes): 20.8500\nbest mean reward: 29.2100\ncurrent episode reward: 18.0000\nepisodes: 2985\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45054.7 seconds (12.52 hours)\n\nTimestep: 9930000\nmean reward (100 episodes): 20.4600\nbest mean reward: 29.2100\ncurrent episode reward: 19.0000\nepisodes: 2988\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45101.0 seconds (12.53 hours)\n\nTimestep: 9940000\nmean reward (100 episodes): 20.7900\nbest mean reward: 29.2100\ncurrent episode reward: 29.0000\nepisodes: 2991\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45147.8 seconds (12.54 hours)\n\nTimestep: 9950000\nmean reward (100 episodes): 20.9000\nbest mean reward: 29.2100\ncurrent episode reward: 36.0000\nepisodes: 2994\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45193.9 seconds (12.55 hours)\n\nTimestep: 9960000\nmean reward (100 episodes): 21.1000\nbest mean reward: 29.2100\ncurrent episode reward: 38.0000\nepisodes: 2997\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45239.9 seconds (12.57 hours)\n\nTimestep: 9970000\nmean reward (100 episodes): 21.4500\nbest mean reward: 29.2100\ncurrent episode reward: 5.0000\nepisodes: 3000\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45286.7 seconds (12.58 hours)\n\nTimestep: 9980000\nmean reward (100 episodes): 20.6700\nbest mean reward: 29.2100\ncurrent episode reward: 5.0000\nepisodes: 3003\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45333.4 seconds (12.59 hours)\n\nTimestep: 9983323\nmean reward (100 episodes): 20.4300\nbest mean reward: 29.2100\ncurrent episode reward: 0.0000\nepisodes: 3004\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 45348.9 seconds (12.60 hours)\n"
  },
  {
    "path": "dqn/logs_text/Pong_s001.text",
    "content": "('AVAILABLE GPUS: ', [u'device: 0, name: TITAN X (Pascal), pci bus id: 0000:01:00.0'])\ntask = Task<env_id=PongNoFrameskip-v3 trials=2 max_timesteps=40000000 max_seconds=None reward_floor=-20.7 reward_ceiling=21.0>\n\nTimestep: 60000\nmean reward (100 episodes): -20.2615\nbest mean reward: -inf\ncurrent episode reward: -20.0000\nepisodes: 65\nexploration: 0.94600\nlearning_rate: 0.00010\nelapsed time: 98.4 seconds (0.03 hours)\n\nTimestep: 70000\nmean reward (100 episodes): -20.2400\nbest mean reward: -inf\ncurrent episode reward: -21.0000\nepisodes: 75\nexploration: 0.93700\nlearning_rate: 0.00010\nelapsed time: 130.4 seconds (0.04 hours)\n\nTimestep: 80000\nmean reward (100 episodes): -20.2558\nbest mean reward: -inf\ncurrent episode reward: -20.0000\nepisodes: 86\nexploration: 0.92800\nlearning_rate: 0.00010\nelapsed time: 162.7 seconds (0.05 hours)\n\nTimestep: 90000\nmean reward (100 episodes): -20.2292\nbest mean reward: -inf\ncurrent episode reward: -20.0000\nepisodes: 96\nexploration: 0.91900\nlearning_rate: 0.00010\nelapsed time: 194.9 seconds (0.05 hours)\n\nTimestep: 100000\nmean reward (100 episodes): -20.2200\nbest mean reward: -20.1900\ncurrent episode reward: -21.0000\nepisodes: 107\nexploration: 0.91000\nlearning_rate: 0.00010\nelapsed time: 227.1 seconds (0.06 hours)\n\nTimestep: 110000\nmean reward (100 episodes): -20.2500\nbest mean reward: -20.1900\ncurrent episode reward: -21.0000\nepisodes: 118\nexploration: 0.90100\nlearning_rate: 0.00010\nelapsed time: 259.4 seconds (0.07 hours)\n\nTimestep: 120000\nmean reward (100 episodes): -20.2200\nbest mean reward: -20.1900\ncurrent episode reward: -21.0000\nepisodes: 129\nexploration: 0.89200\nlearning_rate: 0.00010\nelapsed time: 294.7 seconds (0.08 hours)\n\nTimestep: 130000\nmean reward (100 episodes): -20.2800\nbest mean reward: -20.1900\ncurrent episode reward: -20.0000\nepisodes: 140\nexploration: 0.88300\nlearning_rate: 0.00010\nelapsed time: 327.8 seconds (0.09 hours)\n\nTimestep: 140000\nmean reward (100 episodes): -20.2700\nbest mean reward: -20.1900\ncurrent episode reward: -20.0000\nepisodes: 151\nexploration: 0.87400\nlearning_rate: 0.00010\nelapsed time: 361.2 seconds (0.10 hours)\n\nTimestep: 150000\nmean reward (100 episodes): -20.2700\nbest mean reward: -20.1900\ncurrent episode reward: -19.0000\nepisodes: 161\nexploration: 0.86500\nlearning_rate: 0.00010\nelapsed time: 394.5 seconds (0.11 hours)\n\nTimestep: 160000\nmean reward (100 episodes): -20.3400\nbest mean reward: -20.1900\ncurrent episode reward: -20.0000\nepisodes: 172\nexploration: 0.85600\nlearning_rate: 0.00010\nelapsed time: 427.9 seconds (0.12 hours)\n\nTimestep: 170000\nmean reward (100 episodes): -20.2500\nbest mean reward: -20.1900\ncurrent episode reward: -20.0000\nepisodes: 183\nexploration: 0.84700\nlearning_rate: 0.00010\nelapsed time: 461.6 seconds (0.13 hours)\n\nTimestep: 180000\nmean reward (100 episodes): -20.3000\nbest mean reward: -20.1900\ncurrent episode reward: -21.0000\nepisodes: 194\nexploration: 0.83800\nlearning_rate: 0.00010\nelapsed time: 494.9 seconds (0.14 hours)\n\nTimestep: 190000\nmean reward (100 episodes): -20.2900\nbest mean reward: -20.1900\ncurrent episode reward: -19.0000\nepisodes: 204\nexploration: 0.82900\nlearning_rate: 0.00010\nelapsed time: 528.8 seconds (0.15 hours)\n\nTimestep: 200000\nmean reward (100 episodes): -20.2700\nbest mean reward: -20.1900\ncurrent episode reward: -21.0000\nepisodes: 215\nexploration: 0.82000\nlearning_rate: 0.00010\nelapsed time: 562.7 seconds (0.16 hours)\n\nTimestep: 210000\nmean reward (100 episodes): -20.2000\nbest mean reward: -20.1900\ncurrent episode reward: -21.0000\nepisodes: 226\nexploration: 0.81100\nlearning_rate: 0.00010\nelapsed time: 600.2 seconds (0.17 hours)\n\nTimestep: 220000\nmean reward (100 episodes): -20.1800\nbest mean reward: -20.1800\ncurrent episode reward: -21.0000\nepisodes: 238\nexploration: 0.80200\nlearning_rate: 0.00010\nelapsed time: 634.5 seconds (0.18 hours)\n\nTimestep: 230000\nmean reward (100 episodes): -20.1600\nbest mean reward: -20.1600\ncurrent episode reward: -21.0000\nepisodes: 248\nexploration: 0.79300\nlearning_rate: 0.00010\nelapsed time: 669.0 seconds (0.19 hours)\n\nTimestep: 240000\nmean reward (100 episodes): -20.1700\nbest mean reward: -20.1400\ncurrent episode reward: -20.0000\nepisodes: 259\nexploration: 0.78400\nlearning_rate: 0.00010\nelapsed time: 703.7 seconds (0.20 hours)\n\nTimestep: 250000\nmean reward (100 episodes): -20.1800\nbest mean reward: -20.1400\ncurrent episode reward: -21.0000\nepisodes: 269\nexploration: 0.77500\nlearning_rate: 0.00010\nelapsed time: 738.1 seconds (0.21 hours)\n\nTimestep: 260000\nmean reward (100 episodes): -20.1700\nbest mean reward: -20.1400\ncurrent episode reward: -21.0000\nepisodes: 280\nexploration: 0.76600\nlearning_rate: 0.00010\nelapsed time: 772.9 seconds (0.21 hours)\n\nTimestep: 270000\nmean reward (100 episodes): -20.2300\nbest mean reward: -20.1400\ncurrent episode reward: -21.0000\nepisodes: 291\nexploration: 0.75700\nlearning_rate: 0.00010\nelapsed time: 808.1 seconds (0.22 hours)\n\nTimestep: 280000\nmean reward (100 episodes): -20.2200\nbest mean reward: -20.1400\ncurrent episode reward: -20.0000\nepisodes: 302\nexploration: 0.74800\nlearning_rate: 0.00010\nelapsed time: 842.9 seconds (0.23 hours)\n\nTimestep: 290000\nmean reward (100 episodes): -20.2700\nbest mean reward: -20.1400\ncurrent episode reward: -21.0000\nepisodes: 314\nexploration: 0.73900\nlearning_rate: 0.00010\nelapsed time: 877.7 seconds (0.24 hours)\n\nTimestep: 300000\nmean reward (100 episodes): -20.2800\nbest mean reward: -20.1400\ncurrent episode reward: -20.0000\nepisodes: 324\nexploration: 0.73000\nlearning_rate: 0.00010\nelapsed time: 913.2 seconds (0.25 hours)\n\nTimestep: 310000\nmean reward (100 episodes): -20.2900\nbest mean reward: -20.1400\ncurrent episode reward: -20.0000\nepisodes: 335\nexploration: 0.72100\nlearning_rate: 0.00010\nelapsed time: 948.4 seconds (0.26 hours)\n\nTimestep: 320000\nmean reward (100 episodes): -20.3300\nbest mean reward: -20.1400\ncurrent episode reward: -21.0000\nepisodes: 346\nexploration: 0.71200\nlearning_rate: 0.00010\nelapsed time: 986.9 seconds (0.27 hours)\n\nTimestep: 330000\nmean reward (100 episodes): -20.2800\nbest mean reward: -20.1400\ncurrent episode reward: -17.0000\nepisodes: 356\nexploration: 0.70300\nlearning_rate: 0.00010\nelapsed time: 1023.1 seconds (0.28 hours)\n\nTimestep: 340000\nmean reward (100 episodes): -20.3000\nbest mean reward: -20.1400\ncurrent episode reward: -21.0000\nepisodes: 368\nexploration: 0.69400\nlearning_rate: 0.00010\nelapsed time: 1059.3 seconds (0.29 hours)\n\nTimestep: 350000\nmean reward (100 episodes): -20.3700\nbest mean reward: -20.1400\ncurrent episode reward: -21.0000\nepisodes: 379\nexploration: 0.68500\nlearning_rate: 0.00010\nelapsed time: 1095.2 seconds (0.30 hours)\n\nTimestep: 360000\nmean reward (100 episodes): -20.3500\nbest mean reward: -20.1400\ncurrent episode reward: -21.0000\nepisodes: 390\nexploration: 0.67600\nlearning_rate: 0.00010\nelapsed time: 1131.1 seconds (0.31 hours)\n\nTimestep: 370000\nmean reward (100 episodes): -20.3200\nbest mean reward: -20.1400\ncurrent episode reward: -20.0000\nepisodes: 401\nexploration: 0.66700\nlearning_rate: 0.00010\nelapsed time: 1167.6 seconds (0.32 hours)\n\nTimestep: 380000\nmean reward (100 episodes): -20.3400\nbest mean reward: -20.1400\ncurrent episode reward: -21.0000\nepisodes: 412\nexploration: 0.65800\nlearning_rate: 0.00010\nelapsed time: 1203.7 seconds (0.33 hours)\n\nTimestep: 390000\nmean reward (100 episodes): -20.3400\nbest mean reward: -20.1400\ncurrent episode reward: -19.0000\nepisodes: 423\nexploration: 0.64900\nlearning_rate: 0.00010\nelapsed time: 1240.2 seconds (0.34 hours)\n\nTimestep: 400000\nmean reward (100 episodes): -20.3300\nbest mean reward: -20.1400\ncurrent episode reward: -20.0000\nepisodes: 433\nexploration: 0.64000\nlearning_rate: 0.00010\nelapsed time: 1276.6 seconds (0.35 hours)\n\nTimestep: 410000\nmean reward (100 episodes): -20.2900\nbest mean reward: -20.1400\ncurrent episode reward: -20.0000\nepisodes: 442\nexploration: 0.63100\nlearning_rate: 0.00010\nelapsed time: 1313.2 seconds (0.36 hours)\n\nTimestep: 420000\nmean reward (100 episodes): -20.2500\nbest mean reward: -20.1400\ncurrent episode reward: -21.0000\nepisodes: 451\nexploration: 0.62200\nlearning_rate: 0.00010\nelapsed time: 1349.3 seconds (0.37 hours)\n\nTimestep: 430000\nmean reward (100 episodes): -20.1000\nbest mean reward: -20.1000\ncurrent episode reward: -16.0000\nepisodes: 459\nexploration: 0.61300\nlearning_rate: 0.00010\nelapsed time: 1386.0 seconds (0.38 hours)\n\nTimestep: 440000\nmean reward (100 episodes): -19.9700\nbest mean reward: -19.9700\ncurrent episode reward: -18.0000\nepisodes: 468\nexploration: 0.60400\nlearning_rate: 0.00010\nelapsed time: 1423.3 seconds (0.40 hours)\n\nTimestep: 450000\nmean reward (100 episodes): -19.8700\nbest mean reward: -19.8700\ncurrent episode reward: -20.0000\nepisodes: 476\nexploration: 0.59500\nlearning_rate: 0.00010\nelapsed time: 1460.4 seconds (0.41 hours)\n\nTimestep: 460000\nmean reward (100 episodes): -19.6200\nbest mean reward: -19.6200\ncurrent episode reward: -20.0000\nepisodes: 484\nexploration: 0.58600\nlearning_rate: 0.00010\nelapsed time: 1497.6 seconds (0.42 hours)\n\nTimestep: 470000\nmean reward (100 episodes): -19.4500\nbest mean reward: -19.4500\ncurrent episode reward: -18.0000\nepisodes: 491\nexploration: 0.57700\nlearning_rate: 0.00010\nelapsed time: 1535.5 seconds (0.43 hours)\n\nTimestep: 480000\nmean reward (100 episodes): -19.3100\nbest mean reward: -19.3100\ncurrent episode reward: -20.0000\nepisodes: 498\nexploration: 0.56800\nlearning_rate: 0.00010\nelapsed time: 1572.5 seconds (0.44 hours)\n\nTimestep: 490000\nmean reward (100 episodes): -19.2200\nbest mean reward: -19.2200\ncurrent episode reward: -18.0000\nepisodes: 505\nexploration: 0.55900\nlearning_rate: 0.00010\nelapsed time: 1609.6 seconds (0.45 hours)\n\nTimestep: 500000\nmean reward (100 episodes): -19.0300\nbest mean reward: -19.0300\ncurrent episode reward: -16.0000\nepisodes: 512\nexploration: 0.55000\nlearning_rate: 0.00010\nelapsed time: 1650.4 seconds (0.46 hours)\n\nTimestep: 510000\nmean reward (100 episodes): -18.9200\nbest mean reward: -18.9200\ncurrent episode reward: -16.0000\nepisodes: 519\nexploration: 0.54100\nlearning_rate: 0.00010\nelapsed time: 1690.2 seconds (0.47 hours)\n\nTimestep: 520000\nmean reward (100 episodes): -18.7500\nbest mean reward: -18.7500\ncurrent episode reward: -15.0000\nepisodes: 526\nexploration: 0.53200\nlearning_rate: 0.00010\nelapsed time: 1728.6 seconds (0.48 hours)\n\nTimestep: 530000\nmean reward (100 episodes): -18.5600\nbest mean reward: -18.5600\ncurrent episode reward: -18.0000\nepisodes: 533\nexploration: 0.52300\nlearning_rate: 0.00010\nelapsed time: 1766.9 seconds (0.49 hours)\n\nTimestep: 540000\nmean reward (100 episodes): -18.4100\nbest mean reward: -18.4100\ncurrent episode reward: -15.0000\nepisodes: 540\nexploration: 0.51400\nlearning_rate: 0.00010\nelapsed time: 1805.1 seconds (0.50 hours)\n\nTimestep: 550000\nmean reward (100 episodes): -18.2500\nbest mean reward: -18.2500\ncurrent episode reward: -18.0000\nepisodes: 546\nexploration: 0.50500\nlearning_rate: 0.00010\nelapsed time: 1844.0 seconds (0.51 hours)\n\nTimestep: 560000\nmean reward (100 episodes): -18.0900\nbest mean reward: -18.0900\ncurrent episode reward: -18.0000\nepisodes: 553\nexploration: 0.49600\nlearning_rate: 0.00010\nelapsed time: 1882.6 seconds (0.52 hours)\n\nTimestep: 570000\nmean reward (100 episodes): -18.0600\nbest mean reward: -18.0600\ncurrent episode reward: -15.0000\nepisodes: 559\nexploration: 0.48700\nlearning_rate: 0.00010\nelapsed time: 1921.0 seconds (0.53 hours)\n\nTimestep: 580000\nmean reward (100 episodes): -17.9000\nbest mean reward: -17.9000\ncurrent episode reward: -15.0000\nepisodes: 565\nexploration: 0.47800\nlearning_rate: 0.00010\nelapsed time: 1960.6 seconds (0.54 hours)\n\nTimestep: 590000\nmean reward (100 episodes): -17.8300\nbest mean reward: -17.8000\ncurrent episode reward: -20.0000\nepisodes: 571\nexploration: 0.46900\nlearning_rate: 0.00010\nelapsed time: 2000.0 seconds (0.56 hours)\n\nTimestep: 600000\nmean reward (100 episodes): -17.6700\nbest mean reward: -17.6700\ncurrent episode reward: -17.0000\nepisodes: 577\nexploration: 0.46000\nlearning_rate: 0.00010\nelapsed time: 2039.2 seconds (0.57 hours)\n\nTimestep: 610000\nmean reward (100 episodes): -17.7300\nbest mean reward: -17.6500\ncurrent episode reward: -21.0000\nepisodes: 584\nexploration: 0.45100\nlearning_rate: 0.00010\nelapsed time: 2078.7 seconds (0.58 hours)\n\nTimestep: 620000\nmean reward (100 episodes): -17.7000\nbest mean reward: -17.6500\ncurrent episode reward: -19.0000\nepisodes: 590\nexploration: 0.44200\nlearning_rate: 0.00010\nelapsed time: 2118.7 seconds (0.59 hours)\n\nTimestep: 630000\nmean reward (100 episodes): -17.6400\nbest mean reward: -17.6300\ncurrent episode reward: -19.0000\nepisodes: 595\nexploration: 0.43300\nlearning_rate: 0.00010\nelapsed time: 2157.7 seconds (0.60 hours)\n\nTimestep: 640000\nmean reward (100 episodes): -17.5000\nbest mean reward: -17.5000\ncurrent episode reward: -16.0000\nepisodes: 600\nexploration: 0.42400\nlearning_rate: 0.00010\nelapsed time: 2197.3 seconds (0.61 hours)\n\nTimestep: 650000\nmean reward (100 episodes): -17.4200\nbest mean reward: -17.4100\ncurrent episode reward: -19.0000\nepisodes: 605\nexploration: 0.41500\nlearning_rate: 0.00010\nelapsed time: 2237.1 seconds (0.62 hours)\n\nTimestep: 660000\nmean reward (100 episodes): -17.3800\nbest mean reward: -17.3600\ncurrent episode reward: -20.0000\nepisodes: 611\nexploration: 0.40600\nlearning_rate: 0.00010\nelapsed time: 2276.6 seconds (0.63 hours)\n\nTimestep: 670000\nmean reward (100 episodes): -17.3400\nbest mean reward: -17.3400\ncurrent episode reward: -18.0000\nepisodes: 617\nexploration: 0.39700\nlearning_rate: 0.00010\nelapsed time: 2316.7 seconds (0.64 hours)\n\nTimestep: 680000\nmean reward (100 episodes): -17.2900\nbest mean reward: -17.2900\ncurrent episode reward: -18.0000\nepisodes: 623\nexploration: 0.38800\nlearning_rate: 0.00010\nelapsed time: 2356.8 seconds (0.65 hours)\n\nTimestep: 690000\nmean reward (100 episodes): -17.3300\nbest mean reward: -17.2900\ncurrent episode reward: -17.0000\nepisodes: 628\nexploration: 0.37900\nlearning_rate: 0.00010\nelapsed time: 2396.9 seconds (0.67 hours)\n\nTimestep: 700000\nmean reward (100 episodes): -17.2600\nbest mean reward: -17.2600\ncurrent episode reward: -15.0000\nepisodes: 634\nexploration: 0.37000\nlearning_rate: 0.00010\nelapsed time: 2437.1 seconds (0.68 hours)\n\nTimestep: 710000\nmean reward (100 episodes): -17.2200\nbest mean reward: -17.2200\ncurrent episode reward: -19.0000\nepisodes: 639\nexploration: 0.36100\nlearning_rate: 0.00010\nelapsed time: 2477.0 seconds (0.69 hours)\n\nTimestep: 720000\nmean reward (100 episodes): -17.1900\nbest mean reward: -17.1900\ncurrent episode reward: -16.0000\nepisodes: 643\nexploration: 0.35200\nlearning_rate: 0.00010\nelapsed time: 2518.1 seconds (0.70 hours)\n\nTimestep: 730000\nmean reward (100 episodes): -17.0600\nbest mean reward: -17.0600\ncurrent episode reward: -14.0000\nepisodes: 648\nexploration: 0.34300\nlearning_rate: 0.00010\nelapsed time: 2558.4 seconds (0.71 hours)\n\nTimestep: 740000\nmean reward (100 episodes): -17.0600\nbest mean reward: -17.0400\ncurrent episode reward: -16.0000\nepisodes: 654\nexploration: 0.33400\nlearning_rate: 0.00010\nelapsed time: 2598.7 seconds (0.72 hours)\n\nTimestep: 750000\nmean reward (100 episodes): -17.0000\nbest mean reward: -16.9800\ncurrent episode reward: -14.0000\nepisodes: 659\nexploration: 0.32500\nlearning_rate: 0.00010\nelapsed time: 2640.3 seconds (0.73 hours)\n\nTimestep: 760000\nmean reward (100 episodes): -16.9100\nbest mean reward: -16.9100\ncurrent episode reward: -14.0000\nepisodes: 663\nexploration: 0.31600\nlearning_rate: 0.00010\nelapsed time: 2682.0 seconds (0.74 hours)\n\nTimestep: 770000\nmean reward (100 episodes): -16.7600\nbest mean reward: -16.7500\ncurrent episode reward: -19.0000\nepisodes: 668\nexploration: 0.30700\nlearning_rate: 0.00010\nelapsed time: 2722.9 seconds (0.76 hours)\n\nTimestep: 780000\nmean reward (100 episodes): -16.6200\nbest mean reward: -16.6200\ncurrent episode reward: -11.0000\nepisodes: 673\nexploration: 0.29800\nlearning_rate: 0.00010\nelapsed time: 2764.8 seconds (0.77 hours)\n\nTimestep: 790000\nmean reward (100 episodes): -16.5900\nbest mean reward: -16.5900\ncurrent episode reward: -13.0000\nepisodes: 678\nexploration: 0.28900\nlearning_rate: 0.00010\nelapsed time: 2806.1 seconds (0.78 hours)\n\nTimestep: 800000\nmean reward (100 episodes): -16.4800\nbest mean reward: -16.4800\ncurrent episode reward: -18.0000\nepisodes: 682\nexploration: 0.28000\nlearning_rate: 0.00010\nelapsed time: 2847.9 seconds (0.79 hours)\n\nTimestep: 810000\nmean reward (100 episodes): -16.3700\nbest mean reward: -16.3600\ncurrent episode reward: -17.0000\nepisodes: 687\nexploration: 0.27100\nlearning_rate: 0.00010\nelapsed time: 2889.8 seconds (0.80 hours)\n\nTimestep: 820000\nmean reward (100 episodes): -16.3800\nbest mean reward: -16.3600\ncurrent episode reward: -18.0000\nepisodes: 692\nexploration: 0.26200\nlearning_rate: 0.00010\nelapsed time: 2931.4 seconds (0.81 hours)\n\nTimestep: 830000\nmean reward (100 episodes): -16.3100\nbest mean reward: -16.3100\ncurrent episode reward: -14.0000\nepisodes: 696\nexploration: 0.25300\nlearning_rate: 0.00010\nelapsed time: 2973.4 seconds (0.83 hours)\n\nTimestep: 840000\nmean reward (100 episodes): -16.1900\nbest mean reward: -16.1900\ncurrent episode reward: -16.0000\nepisodes: 700\nexploration: 0.24400\nlearning_rate: 0.00010\nelapsed time: 3014.4 seconds (0.84 hours)\n\nTimestep: 850000\nmean reward (100 episodes): -16.0900\nbest mean reward: -16.0900\ncurrent episode reward: -15.0000\nepisodes: 705\nexploration: 0.23500\nlearning_rate: 0.00010\nelapsed time: 3056.5 seconds (0.85 hours)\n\nTimestep: 860000\nmean reward (100 episodes): -15.9200\nbest mean reward: -15.9200\ncurrent episode reward: -11.0000\nepisodes: 708\nexploration: 0.22600\nlearning_rate: 0.00010\nelapsed time: 3098.8 seconds (0.86 hours)\n\nTimestep: 870000\nmean reward (100 episodes): -15.7400\nbest mean reward: -15.7400\ncurrent episode reward: -13.0000\nepisodes: 713\nexploration: 0.21700\nlearning_rate: 0.00010\nelapsed time: 3140.5 seconds (0.87 hours)\n\nTimestep: 880000\nmean reward (100 episodes): -15.6300\nbest mean reward: -15.6300\ncurrent episode reward: -13.0000\nepisodes: 716\nexploration: 0.20800\nlearning_rate: 0.00010\nelapsed time: 3182.4 seconds (0.88 hours)\n\nTimestep: 890000\nmean reward (100 episodes): -15.5100\nbest mean reward: -15.5100\ncurrent episode reward: -18.0000\nepisodes: 721\nexploration: 0.19900\nlearning_rate: 0.00010\nelapsed time: 3224.9 seconds (0.90 hours)\n\nTimestep: 900000\nmean reward (100 episodes): -15.3100\nbest mean reward: -15.3100\ncurrent episode reward: -11.0000\nepisodes: 724\nexploration: 0.19000\nlearning_rate: 0.00010\nelapsed time: 3266.8 seconds (0.91 hours)\n\nTimestep: 910000\nmean reward (100 episodes): -15.1100\nbest mean reward: -15.1100\ncurrent episode reward: -12.0000\nepisodes: 729\nexploration: 0.18100\nlearning_rate: 0.00010\nelapsed time: 3311.2 seconds (0.92 hours)\n\nTimestep: 920000\nmean reward (100 episodes): -15.0200\nbest mean reward: -15.0200\ncurrent episode reward: -13.0000\nepisodes: 732\nexploration: 0.17200\nlearning_rate: 0.00010\nelapsed time: 3359.3 seconds (0.93 hours)\n\nTimestep: 930000\nmean reward (100 episodes): -14.8900\nbest mean reward: -14.8900\ncurrent episode reward: -15.0000\nepisodes: 736\nexploration: 0.16300\nlearning_rate: 0.00010\nelapsed time: 3402.5 seconds (0.95 hours)\n\nTimestep: 940000\nmean reward (100 episodes): -14.5900\nbest mean reward: -14.5900\ncurrent episode reward: -15.0000\nepisodes: 739\nexploration: 0.15400\nlearning_rate: 0.00010\nelapsed time: 3445.6 seconds (0.96 hours)\n\nTimestep: 950000\nmean reward (100 episodes): -14.4800\nbest mean reward: -14.4800\ncurrent episode reward: -14.0000\nepisodes: 743\nexploration: 0.14500\nlearning_rate: 0.00010\nelapsed time: 3489.1 seconds (0.97 hours)\n\nTimestep: 960000\nmean reward (100 episodes): -14.4100\nbest mean reward: -14.4100\ncurrent episode reward: -12.0000\nepisodes: 746\nexploration: 0.13600\nlearning_rate: 0.00010\nelapsed time: 3533.8 seconds (0.98 hours)\n\nTimestep: 970000\nmean reward (100 episodes): -14.2600\nbest mean reward: -14.2600\ncurrent episode reward: -7.0000\nepisodes: 750\nexploration: 0.12700\nlearning_rate: 0.00010\nelapsed time: 3578.1 seconds (0.99 hours)\n\nTimestep: 980000\nmean reward (100 episodes): -14.1300\nbest mean reward: -14.1100\ncurrent episode reward: -18.0000\nepisodes: 754\nexploration: 0.11800\nlearning_rate: 0.00010\nelapsed time: 3622.3 seconds (1.01 hours)\n\nTimestep: 990000\nmean reward (100 episodes): -13.8400\nbest mean reward: -13.8400\ncurrent episode reward: -6.0000\nepisodes: 757\nexploration: 0.10900\nlearning_rate: 0.00010\nelapsed time: 3666.4 seconds (1.02 hours)\n\nTimestep: 1000000\nmean reward (100 episodes): -13.6200\nbest mean reward: -13.6200\ncurrent episode reward: -8.0000\nepisodes: 760\nexploration: 0.10000\nlearning_rate: 0.00010\nelapsed time: 3710.5 seconds (1.03 hours)\n\nTimestep: 1010000\nmean reward (100 episodes): -13.5500\nbest mean reward: -13.5500\ncurrent episode reward: -8.0000\nepisodes: 764\nexploration: 0.09967\nlearning_rate: 0.00010\nelapsed time: 3754.1 seconds (1.04 hours)\n\nTimestep: 1020000\nmean reward (100 episodes): -13.4800\nbest mean reward: -13.4100\ncurrent episode reward: -16.0000\nepisodes: 767\nexploration: 0.09935\nlearning_rate: 0.00010\nelapsed time: 3797.2 seconds (1.05 hours)\n\nTimestep: 1030000\nmean reward (100 episodes): -13.2500\nbest mean reward: -13.2500\ncurrent episode reward: -13.0000\nepisodes: 771\nexploration: 0.09902\nlearning_rate: 0.00010\nelapsed time: 3840.5 seconds (1.07 hours)\n\nTimestep: 1040000\nmean reward (100 episodes): -13.1700\nbest mean reward: -13.1700\ncurrent episode reward: -10.0000\nepisodes: 774\nexploration: 0.09869\nlearning_rate: 0.00010\nelapsed time: 3884.7 seconds (1.08 hours)\n\nTimestep: 1050000\nmean reward (100 episodes): -12.8800\nbest mean reward: -12.8800\ncurrent episode reward: -7.0000\nepisodes: 777\nexploration: 0.09836\nlearning_rate: 0.00010\nelapsed time: 3929.2 seconds (1.09 hours)\n\nTimestep: 1060000\nmean reward (100 episodes): -12.7500\nbest mean reward: -12.7500\ncurrent episode reward: -7.0000\nepisodes: 781\nexploration: 0.09804\nlearning_rate: 0.00009\nelapsed time: 3972.4 seconds (1.10 hours)\n\nTimestep: 1070000\nmean reward (100 episodes): -12.5600\nbest mean reward: -12.5600\ncurrent episode reward: -10.0000\nepisodes: 784\nexploration: 0.09771\nlearning_rate: 0.00009\nelapsed time: 4015.6 seconds (1.12 hours)\n\nTimestep: 1080000\nmean reward (100 episodes): -12.3900\nbest mean reward: -12.3900\ncurrent episode reward: -5.0000\nepisodes: 788\nexploration: 0.09738\nlearning_rate: 0.00009\nelapsed time: 4060.2 seconds (1.13 hours)\n\nTimestep: 1090000\nmean reward (100 episodes): -12.1000\nbest mean reward: -12.1000\ncurrent episode reward: -7.0000\nepisodes: 790\nexploration: 0.09705\nlearning_rate: 0.00009\nelapsed time: 4104.7 seconds (1.14 hours)\n\nTimestep: 1100000\nmean reward (100 episodes): -12.1100\nbest mean reward: -12.0200\ncurrent episode reward: -17.0000\nepisodes: 794\nexploration: 0.09673\nlearning_rate: 0.00009\nelapsed time: 4148.5 seconds (1.15 hours)\n\nTimestep: 1110000\nmean reward (100 episodes): -11.9500\nbest mean reward: -11.9500\ncurrent episode reward: -15.0000\nepisodes: 797\nexploration: 0.09640\nlearning_rate: 0.00009\nelapsed time: 4192.9 seconds (1.16 hours)\n\nTimestep: 1120000\nmean reward (100 episodes): -11.6800\nbest mean reward: -11.6800\ncurrent episode reward: -13.0000\nepisodes: 801\nexploration: 0.09607\nlearning_rate: 0.00009\nelapsed time: 4236.7 seconds (1.18 hours)\n\nTimestep: 1130000\nmean reward (100 episodes): -11.5200\nbest mean reward: -11.5200\ncurrent episode reward: -9.0000\nepisodes: 804\nexploration: 0.09575\nlearning_rate: 0.00009\nelapsed time: 4281.1 seconds (1.19 hours)\n\nTimestep: 1140000\nmean reward (100 episodes): -11.4200\nbest mean reward: -11.4100\ncurrent episode reward: -12.0000\nepisodes: 808\nexploration: 0.09542\nlearning_rate: 0.00009\nelapsed time: 4325.7 seconds (1.20 hours)\n\nTimestep: 1150000\nmean reward (100 episodes): -11.2700\nbest mean reward: -11.2300\ncurrent episode reward: -13.0000\nepisodes: 811\nexploration: 0.09509\nlearning_rate: 0.00009\nelapsed time: 4369.6 seconds (1.21 hours)\n\nTimestep: 1160000\nmean reward (100 episodes): -10.9600\nbest mean reward: -10.9600\ncurrent episode reward: -14.0000\nepisodes: 815\nexploration: 0.09476\nlearning_rate: 0.00009\nelapsed time: 4413.2 seconds (1.23 hours)\n\nTimestep: 1170000\nmean reward (100 episodes): -10.7600\nbest mean reward: -10.7600\ncurrent episode reward: -10.0000\nepisodes: 818\nexploration: 0.09444\nlearning_rate: 0.00009\nelapsed time: 4457.1 seconds (1.24 hours)\n\nTimestep: 1180000\nmean reward (100 episodes): -10.3600\nbest mean reward: -10.3600\ncurrent episode reward: -6.0000\nepisodes: 821\nexploration: 0.09411\nlearning_rate: 0.00009\nelapsed time: 4501.9 seconds (1.25 hours)\n\nTimestep: 1190000\nmean reward (100 episodes): -10.2300\nbest mean reward: -10.2300\ncurrent episode reward: -9.0000\nepisodes: 824\nexploration: 0.09378\nlearning_rate: 0.00009\nelapsed time: 4545.4 seconds (1.26 hours)\n\nTimestep: 1200000\nmean reward (100 episodes): -10.0500\nbest mean reward: -10.0500\ncurrent episode reward: -10.0000\nepisodes: 827\nexploration: 0.09345\nlearning_rate: 0.00009\nelapsed time: 4589.3 seconds (1.27 hours)\n\nTimestep: 1210000\nmean reward (100 episodes): -9.6900\nbest mean reward: -9.6900\ncurrent episode reward: -6.0000\nepisodes: 830\nexploration: 0.09313\nlearning_rate: 0.00009\nelapsed time: 4633.0 seconds (1.29 hours)\n\nTimestep: 1220000\nmean reward (100 episodes): -9.5100\nbest mean reward: -9.5100\ncurrent episode reward: -8.0000\nepisodes: 833\nexploration: 0.09280\nlearning_rate: 0.00009\nelapsed time: 4677.2 seconds (1.30 hours)\n\nTimestep: 1230000\nmean reward (100 episodes): -9.1200\nbest mean reward: -9.1200\ncurrent episode reward: -4.0000\nepisodes: 836\nexploration: 0.09247\nlearning_rate: 0.00009\nelapsed time: 4721.1 seconds (1.31 hours)\n\nTimestep: 1240000\nmean reward (100 episodes): -9.0700\nbest mean reward: -9.0700\ncurrent episode reward: -9.0000\nepisodes: 839\nexploration: 0.09215\nlearning_rate: 0.00009\nelapsed time: 4765.0 seconds (1.32 hours)\n\nTimestep: 1250000\nmean reward (100 episodes): -8.8200\nbest mean reward: -8.8200\ncurrent episode reward: -4.0000\nepisodes: 842\nexploration: 0.09182\nlearning_rate: 0.00009\nelapsed time: 4809.2 seconds (1.34 hours)\n\nTimestep: 1260000\nmean reward (100 episodes): -8.5100\nbest mean reward: -8.5100\ncurrent episode reward: -4.0000\nepisodes: 845\nexploration: 0.09149\nlearning_rate: 0.00009\nelapsed time: 4853.6 seconds (1.35 hours)\n\nTimestep: 1270000\nmean reward (100 episodes): -8.1100\nbest mean reward: -8.1100\ncurrent episode reward: -4.0000\nepisodes: 848\nexploration: 0.09116\nlearning_rate: 0.00009\nelapsed time: 4898.0 seconds (1.36 hours)\n\nTimestep: 1280000\nmean reward (100 episodes): -8.0200\nbest mean reward: -7.9900\ncurrent episode reward: -8.0000\nepisodes: 851\nexploration: 0.09084\nlearning_rate: 0.00009\nelapsed time: 4942.5 seconds (1.37 hours)\n\nTimestep: 1290000\nmean reward (100 episodes): -7.6800\nbest mean reward: -7.6800\ncurrent episode reward: -9.0000\nepisodes: 855\nexploration: 0.09051\nlearning_rate: 0.00009\nelapsed time: 4986.8 seconds (1.39 hours)\n\nTimestep: 1300000\nmean reward (100 episodes): -7.5000\nbest mean reward: -7.5000\ncurrent episode reward: -1.0000\nepisodes: 858\nexploration: 0.09018\nlearning_rate: 0.00009\nelapsed time: 5030.8 seconds (1.40 hours)\n\nTimestep: 1310000\nmean reward (100 episodes): -7.2400\nbest mean reward: -7.2400\ncurrent episode reward: 2.0000\nepisodes: 861\nexploration: 0.08985\nlearning_rate: 0.00009\nelapsed time: 5074.7 seconds (1.41 hours)\n\nTimestep: 1320000\nmean reward (100 episodes): -6.9200\nbest mean reward: -6.9200\ncurrent episode reward: -8.0000\nepisodes: 864\nexploration: 0.08953\nlearning_rate: 0.00009\nelapsed time: 5118.6 seconds (1.42 hours)\n\nTimestep: 1330000\nmean reward (100 episodes): -6.6400\nbest mean reward: -6.6400\ncurrent episode reward: 2.0000\nepisodes: 866\nexploration: 0.08920\nlearning_rate: 0.00009\nelapsed time: 5162.3 seconds (1.43 hours)\n\nTimestep: 1340000\nmean reward (100 episodes): -6.3500\nbest mean reward: -6.3500\ncurrent episode reward: 3.0000\nepisodes: 869\nexploration: 0.08887\nlearning_rate: 0.00009\nelapsed time: 5205.3 seconds (1.45 hours)\n\nTimestep: 1350000\nmean reward (100 episodes): -5.9900\nbest mean reward: -5.9900\ncurrent episode reward: -6.0000\nepisodes: 872\nexploration: 0.08855\nlearning_rate: 0.00009\nelapsed time: 5249.1 seconds (1.46 hours)\n\nTimestep: 1360000\nmean reward (100 episodes): -5.6800\nbest mean reward: -5.6800\ncurrent episode reward: -1.0000\nepisodes: 875\nexploration: 0.08822\nlearning_rate: 0.00009\nelapsed time: 5292.9 seconds (1.47 hours)\n\nTimestep: 1370000\nmean reward (100 episodes): -5.5100\nbest mean reward: -5.5100\ncurrent episode reward: -3.0000\nepisodes: 878\nexploration: 0.08789\nlearning_rate: 0.00009\nelapsed time: 5336.1 seconds (1.48 hours)\n\nTimestep: 1380000\nmean reward (100 episodes): -5.0900\nbest mean reward: -5.0900\ncurrent episode reward: 3.0000\nepisodes: 881\nexploration: 0.08756\nlearning_rate: 0.00009\nelapsed time: 5380.3 seconds (1.49 hours)\n\nTimestep: 1390000\nmean reward (100 episodes): -4.8900\nbest mean reward: -4.8900\ncurrent episode reward: 2.0000\nepisodes: 883\nexploration: 0.08724\nlearning_rate: 0.00009\nelapsed time: 5425.3 seconds (1.51 hours)\n\nTimestep: 1400000\nmean reward (100 episodes): -4.6300\nbest mean reward: -4.6300\ncurrent episode reward: -6.0000\nepisodes: 886\nexploration: 0.08691\nlearning_rate: 0.00009\nelapsed time: 5469.4 seconds (1.52 hours)\n\nTimestep: 1410000\nmean reward (100 episodes): -4.4200\nbest mean reward: -4.4200\ncurrent episode reward: 5.0000\nepisodes: 889\nexploration: 0.08658\nlearning_rate: 0.00009\nelapsed time: 5513.0 seconds (1.53 hours)\n\nTimestep: 1420000\nmean reward (100 episodes): -3.9400\nbest mean reward: -3.9400\ncurrent episode reward: 4.0000\nepisodes: 892\nexploration: 0.08625\nlearning_rate: 0.00009\nelapsed time: 5556.7 seconds (1.54 hours)\n\nTimestep: 1430000\nmean reward (100 episodes): -3.3400\nbest mean reward: -3.3400\ncurrent episode reward: 2.0000\nepisodes: 895\nexploration: 0.08593\nlearning_rate: 0.00009\nelapsed time: 5601.0 seconds (1.56 hours)\n\nTimestep: 1440000\nmean reward (100 episodes): -3.0100\nbest mean reward: -3.0100\ncurrent episode reward: 4.0000\nepisodes: 897\nexploration: 0.08560\nlearning_rate: 0.00009\nelapsed time: 5644.1 seconds (1.57 hours)\n\nTimestep: 1450000\nmean reward (100 episodes): -2.9500\nbest mean reward: -2.9500\ncurrent episode reward: -5.0000\nepisodes: 900\nexploration: 0.08527\nlearning_rate: 0.00009\nelapsed time: 5687.8 seconds (1.58 hours)\n\nTimestep: 1460000\nmean reward (100 episodes): -2.5100\nbest mean reward: -2.5100\ncurrent episode reward: 1.0000\nepisodes: 903\nexploration: 0.08495\nlearning_rate: 0.00009\nelapsed time: 5732.0 seconds (1.59 hours)\n\nTimestep: 1470000\nmean reward (100 episodes): -2.0500\nbest mean reward: -2.0500\ncurrent episode reward: 2.0000\nepisodes: 906\nexploration: 0.08462\nlearning_rate: 0.00009\nelapsed time: 5775.9 seconds (1.60 hours)\n\nTimestep: 1480000\nmean reward (100 episodes): -1.5900\nbest mean reward: -1.5900\ncurrent episode reward: 4.0000\nepisodes: 909\nexploration: 0.08429\nlearning_rate: 0.00009\nelapsed time: 5819.8 seconds (1.62 hours)\n\nTimestep: 1490000\nmean reward (100 episodes): -1.1600\nbest mean reward: -1.1600\ncurrent episode reward: 5.0000\nepisodes: 912\nexploration: 0.08396\nlearning_rate: 0.00009\nelapsed time: 5863.7 seconds (1.63 hours)\n\nTimestep: 1500000\nmean reward (100 episodes): -0.7200\nbest mean reward: -0.7200\ncurrent episode reward: 8.0000\nepisodes: 915\nexploration: 0.08364\nlearning_rate: 0.00009\nelapsed time: 5907.2 seconds (1.64 hours)\n\nTimestep: 1510000\nmean reward (100 episodes): -0.1000\nbest mean reward: -0.1000\ncurrent episode reward: 8.0000\nepisodes: 919\nexploration: 0.08331\nlearning_rate: 0.00009\nelapsed time: 5951.1 seconds (1.65 hours)\n\nTimestep: 1520000\nmean reward (100 episodes): 0.3800\nbest mean reward: 0.3800\ncurrent episode reward: 8.0000\nepisodes: 922\nexploration: 0.08298\nlearning_rate: 0.00009\nelapsed time: 5995.1 seconds (1.67 hours)\n\nTimestep: 1530000\nmean reward (100 episodes): 0.8000\nbest mean reward: 0.8000\ncurrent episode reward: 9.0000\nepisodes: 926\nexploration: 0.08265\nlearning_rate: 0.00009\nelapsed time: 6038.7 seconds (1.68 hours)\n\nTimestep: 1540000\nmean reward (100 episodes): 1.0400\nbest mean reward: 1.0400\ncurrent episode reward: 8.0000\nepisodes: 929\nexploration: 0.08233\nlearning_rate: 0.00009\nelapsed time: 6082.0 seconds (1.69 hours)\n\nTimestep: 1550000\nmean reward (100 episodes): 1.3500\nbest mean reward: 1.3500\ncurrent episode reward: 6.0000\nepisodes: 932\nexploration: 0.08200\nlearning_rate: 0.00009\nelapsed time: 6125.9 seconds (1.70 hours)\n\nTimestep: 1560000\nmean reward (100 episodes): 1.6700\nbest mean reward: 1.6700\ncurrent episode reward: 8.0000\nepisodes: 936\nexploration: 0.08167\nlearning_rate: 0.00009\nelapsed time: 6170.6 seconds (1.71 hours)\n\nTimestep: 1570000\nmean reward (100 episodes): 2.1200\nbest mean reward: 2.1200\ncurrent episode reward: 9.0000\nepisodes: 939\nexploration: 0.08135\nlearning_rate: 0.00009\nelapsed time: 6213.6 seconds (1.73 hours)\n\nTimestep: 1580000\nmean reward (100 episodes): 2.6800\nbest mean reward: 2.6800\ncurrent episode reward: 9.0000\nepisodes: 943\nexploration: 0.08102\nlearning_rate: 0.00009\nelapsed time: 6256.8 seconds (1.74 hours)\n\nTimestep: 1590000\nmean reward (100 episodes): 3.1300\nbest mean reward: 3.1300\ncurrent episode reward: 12.0000\nepisodes: 946\nexploration: 0.08069\nlearning_rate: 0.00009\nelapsed time: 6300.1 seconds (1.75 hours)\n\nTimestep: 1600000\nmean reward (100 episodes): 3.7400\nbest mean reward: 3.7400\ncurrent episode reward: 15.0000\nepisodes: 950\nexploration: 0.08036\nlearning_rate: 0.00009\nelapsed time: 6343.8 seconds (1.76 hours)\n\nTimestep: 1610000\nmean reward (100 episodes): 4.5100\nbest mean reward: 4.5100\ncurrent episode reward: 18.0000\nepisodes: 954\nexploration: 0.08004\nlearning_rate: 0.00009\nelapsed time: 6387.9 seconds (1.77 hours)\n\nTimestep: 1620000\nmean reward (100 episodes): 5.1300\nbest mean reward: 5.1300\ncurrent episode reward: 19.0000\nepisodes: 958\nexploration: 0.07971\nlearning_rate: 0.00009\nelapsed time: 6432.3 seconds (1.79 hours)\n\nTimestep: 1630000\nmean reward (100 episodes): 5.6500\nbest mean reward: 5.6500\ncurrent episode reward: 12.0000\nepisodes: 962\nexploration: 0.07938\nlearning_rate: 0.00009\nelapsed time: 6476.4 seconds (1.80 hours)\n\nTimestep: 1640000\nmean reward (100 episodes): 6.0700\nbest mean reward: 6.0700\ncurrent episode reward: 13.0000\nepisodes: 966\nexploration: 0.07905\nlearning_rate: 0.00009\nelapsed time: 6519.6 seconds (1.81 hours)\n\nTimestep: 1650000\nmean reward (100 episodes): 6.6500\nbest mean reward: 6.6500\ncurrent episode reward: 13.0000\nepisodes: 970\nexploration: 0.07873\nlearning_rate: 0.00009\nelapsed time: 6563.3 seconds (1.82 hours)\n\nTimestep: 1660000\nmean reward (100 episodes): 7.2700\nbest mean reward: 7.2700\ncurrent episode reward: 14.0000\nepisodes: 974\nexploration: 0.07840\nlearning_rate: 0.00008\nelapsed time: 6607.0 seconds (1.84 hours)\n\nTimestep: 1670000\nmean reward (100 episodes): 8.2200\nbest mean reward: 8.2200\ncurrent episode reward: 19.0000\nepisodes: 979\nexploration: 0.07807\nlearning_rate: 0.00008\nelapsed time: 6650.6 seconds (1.85 hours)\n\nTimestep: 1680000\nmean reward (100 episodes): 8.7300\nbest mean reward: 8.7300\ncurrent episode reward: 16.0000\nepisodes: 983\nexploration: 0.07775\nlearning_rate: 0.00008\nelapsed time: 6694.5 seconds (1.86 hours)\n\nTimestep: 1690000\nmean reward (100 episodes): 9.3600\nbest mean reward: 9.3600\ncurrent episode reward: 15.0000\nepisodes: 987\nexploration: 0.07742\nlearning_rate: 0.00008\nelapsed time: 6738.8 seconds (1.87 hours)\n\nTimestep: 1700000\nmean reward (100 episodes): 9.9300\nbest mean reward: 9.9300\ncurrent episode reward: 17.0000\nepisodes: 991\nexploration: 0.07709\nlearning_rate: 0.00008\nelapsed time: 6782.7 seconds (1.88 hours)\n\nTimestep: 1710000\nmean reward (100 episodes): 10.4600\nbest mean reward: 10.4600\ncurrent episode reward: 16.0000\nepisodes: 996\nexploration: 0.07676\nlearning_rate: 0.00008\nelapsed time: 6827.5 seconds (1.90 hours)\n\nTimestep: 1720000\nmean reward (100 episodes): 11.0900\nbest mean reward: 11.0900\ncurrent episode reward: 16.0000\nepisodes: 1000\nexploration: 0.07644\nlearning_rate: 0.00008\nelapsed time: 6875.3 seconds (1.91 hours)\n\nTimestep: 1730000\nmean reward (100 episodes): 11.7200\nbest mean reward: 11.7200\ncurrent episode reward: 21.0000\nepisodes: 1005\nexploration: 0.07611\nlearning_rate: 0.00008\nelapsed time: 6921.5 seconds (1.92 hours)\n\nTimestep: 1740000\nmean reward (100 episodes): 12.2400\nbest mean reward: 12.2400\ncurrent episode reward: 18.0000\nepisodes: 1010\nexploration: 0.07578\nlearning_rate: 0.00008\nelapsed time: 6964.8 seconds (1.93 hours)\n\nTimestep: 1750000\nmean reward (100 episodes): 12.6400\nbest mean reward: 12.6400\ncurrent episode reward: 17.0000\nepisodes: 1014\nexploration: 0.07545\nlearning_rate: 0.00008\nelapsed time: 7008.9 seconds (1.95 hours)\n\nTimestep: 1760000\nmean reward (100 episodes): 13.0700\nbest mean reward: 13.0700\ncurrent episode reward: 18.0000\nepisodes: 1019\nexploration: 0.07513\nlearning_rate: 0.00008\nelapsed time: 7052.6 seconds (1.96 hours)\n\nTimestep: 1770000\nmean reward (100 episodes): 13.4000\nbest mean reward: 13.4000\ncurrent episode reward: 20.0000\nepisodes: 1024\nexploration: 0.07480\nlearning_rate: 0.00008\nelapsed time: 7097.0 seconds (1.97 hours)\n\nTimestep: 1780000\nmean reward (100 episodes): 14.0200\nbest mean reward: 14.0200\ncurrent episode reward: 17.0000\nepisodes: 1029\nexploration: 0.07447\nlearning_rate: 0.00008\nelapsed time: 7141.5 seconds (1.98 hours)\n\nTimestep: 1790000\nmean reward (100 episodes): 14.4700\nbest mean reward: 14.4700\ncurrent episode reward: 17.0000\nepisodes: 1033\nexploration: 0.07415\nlearning_rate: 0.00008\nelapsed time: 7185.3 seconds (2.00 hours)\n\nTimestep: 1800000\nmean reward (100 episodes): 14.9800\nbest mean reward: 14.9800\ncurrent episode reward: 17.0000\nepisodes: 1037\nexploration: 0.07382\nlearning_rate: 0.00008\nelapsed time: 7229.3 seconds (2.01 hours)\n\nTimestep: 1810000\nmean reward (100 episodes): 15.1800\nbest mean reward: 15.1800\ncurrent episode reward: 18.0000\nepisodes: 1042\nexploration: 0.07349\nlearning_rate: 0.00008\nelapsed time: 7273.8 seconds (2.02 hours)\n\nTimestep: 1820000\nmean reward (100 episodes): 15.5700\nbest mean reward: 15.5700\ncurrent episode reward: 19.0000\nepisodes: 1047\nexploration: 0.07316\nlearning_rate: 0.00008\nelapsed time: 7317.2 seconds (2.03 hours)\n\nTimestep: 1830000\nmean reward (100 episodes): 15.7400\nbest mean reward: 15.7400\ncurrent episode reward: 19.0000\nepisodes: 1052\nexploration: 0.07284\nlearning_rate: 0.00008\nelapsed time: 7360.9 seconds (2.04 hours)\n\nTimestep: 1840000\nmean reward (100 episodes): 15.9700\nbest mean reward: 15.9700\ncurrent episode reward: 14.0000\nepisodes: 1057\nexploration: 0.07251\nlearning_rate: 0.00008\nelapsed time: 7404.4 seconds (2.06 hours)\n\nTimestep: 1850000\nmean reward (100 episodes): 16.1900\nbest mean reward: 16.1900\ncurrent episode reward: 18.0000\nepisodes: 1062\nexploration: 0.07218\nlearning_rate: 0.00008\nelapsed time: 7448.8 seconds (2.07 hours)\n\nTimestep: 1860000\nmean reward (100 episodes): 16.4000\nbest mean reward: 16.4000\ncurrent episode reward: 18.0000\nepisodes: 1067\nexploration: 0.07185\nlearning_rate: 0.00008\nelapsed time: 7492.2 seconds (2.08 hours)\n\nTimestep: 1870000\nmean reward (100 episodes): 16.5000\nbest mean reward: 16.5300\ncurrent episode reward: 14.0000\nepisodes: 1072\nexploration: 0.07153\nlearning_rate: 0.00008\nelapsed time: 7535.8 seconds (2.09 hours)\n\nTimestep: 1880000\nmean reward (100 episodes): 16.4900\nbest mean reward: 16.5300\ncurrent episode reward: 17.0000\nepisodes: 1076\nexploration: 0.07120\nlearning_rate: 0.00008\nelapsed time: 7579.6 seconds (2.11 hours)\n\nTimestep: 1890000\nmean reward (100 episodes): 16.4700\nbest mean reward: 16.5300\ncurrent episode reward: 19.0000\nepisodes: 1081\nexploration: 0.07087\nlearning_rate: 0.00008\nelapsed time: 7623.7 seconds (2.12 hours)\n\nTimestep: 1900000\nmean reward (100 episodes): 16.5900\nbest mean reward: 16.5900\ncurrent episode reward: 19.0000\nepisodes: 1086\nexploration: 0.07055\nlearning_rate: 0.00008\nelapsed time: 7667.5 seconds (2.13 hours)\n\nTimestep: 1910000\nmean reward (100 episodes): 16.6700\nbest mean reward: 16.6700\ncurrent episode reward: 15.0000\nepisodes: 1090\nexploration: 0.07022\nlearning_rate: 0.00008\nelapsed time: 7711.2 seconds (2.14 hours)\n\nTimestep: 1920000\nmean reward (100 episodes): 16.6300\nbest mean reward: 16.6700\ncurrent episode reward: 16.0000\nepisodes: 1095\nexploration: 0.06989\nlearning_rate: 0.00008\nelapsed time: 7754.2 seconds (2.15 hours)\n\nTimestep: 1930000\nmean reward (100 episodes): 16.6500\nbest mean reward: 16.7400\ncurrent episode reward: 18.0000\nepisodes: 1100\nexploration: 0.06956\nlearning_rate: 0.00008\nelapsed time: 7798.1 seconds (2.17 hours)\n\nTimestep: 1940000\nmean reward (100 episodes): 16.0500\nbest mean reward: 16.7400\ncurrent episode reward: -9.0000\nepisodes: 1105\nexploration: 0.06924\nlearning_rate: 0.00008\nelapsed time: 7842.2 seconds (2.18 hours)\n\nTimestep: 1950000\nmean reward (100 episodes): 16.1000\nbest mean reward: 16.7400\ncurrent episode reward: 17.0000\nepisodes: 1110\nexploration: 0.06891\nlearning_rate: 0.00008\nelapsed time: 7886.2 seconds (2.19 hours)\n\nTimestep: 1960000\nmean reward (100 episodes): 16.1100\nbest mean reward: 16.7400\ncurrent episode reward: 14.0000\nepisodes: 1115\nexploration: 0.06858\nlearning_rate: 0.00008\nelapsed time: 7930.1 seconds (2.20 hours)\n\nTimestep: 1970000\nmean reward (100 episodes): 16.1500\nbest mean reward: 16.7400\ncurrent episode reward: 19.0000\nepisodes: 1119\nexploration: 0.06825\nlearning_rate: 0.00008\nelapsed time: 7974.4 seconds (2.22 hours)\n\nTimestep: 1980000\nmean reward (100 episodes): 16.0600\nbest mean reward: 16.7400\ncurrent episode reward: 17.0000\nepisodes: 1124\nexploration: 0.06793\nlearning_rate: 0.00008\nelapsed time: 8019.4 seconds (2.23 hours)\n\nTimestep: 1990000\nmean reward (100 episodes): 16.2200\nbest mean reward: 16.7400\ncurrent episode reward: 19.0000\nepisodes: 1129\nexploration: 0.06760\nlearning_rate: 0.00008\nelapsed time: 8063.1 seconds (2.24 hours)\n\nTimestep: 2000000\nmean reward (100 episodes): 16.3100\nbest mean reward: 16.7400\ncurrent episode reward: 18.0000\nepisodes: 1134\nexploration: 0.06727\nlearning_rate: 0.00008\nelapsed time: 8107.2 seconds (2.25 hours)\n\nTimestep: 2010000\nmean reward (100 episodes): 16.4100\nbest mean reward: 16.7400\ncurrent episode reward: 18.0000\nepisodes: 1139\nexploration: 0.06695\nlearning_rate: 0.00008\nelapsed time: 8151.3 seconds (2.26 hours)\n\nTimestep: 2020000\nmean reward (100 episodes): 16.4500\nbest mean reward: 16.7400\ncurrent episode reward: 18.0000\nepisodes: 1144\nexploration: 0.06662\nlearning_rate: 0.00008\nelapsed time: 8195.9 seconds (2.28 hours)\n\nTimestep: 2030000\nmean reward (100 episodes): 16.3600\nbest mean reward: 16.7400\ncurrent episode reward: 11.0000\nepisodes: 1149\nexploration: 0.06629\nlearning_rate: 0.00008\nelapsed time: 8239.9 seconds (2.29 hours)\n\nTimestep: 2040000\nmean reward (100 episodes): 16.4600\nbest mean reward: 16.7400\ncurrent episode reward: 20.0000\nepisodes: 1154\nexploration: 0.06596\nlearning_rate: 0.00008\nelapsed time: 8283.5 seconds (2.30 hours)\n\nTimestep: 2050000\nmean reward (100 episodes): 16.4700\nbest mean reward: 16.7400\ncurrent episode reward: 16.0000\nepisodes: 1158\nexploration: 0.06564\nlearning_rate: 0.00008\nelapsed time: 8327.2 seconds (2.31 hours)\n\nTimestep: 2060000\nmean reward (100 episodes): 16.4300\nbest mean reward: 16.7400\ncurrent episode reward: 15.0000\nepisodes: 1163\nexploration: 0.06531\nlearning_rate: 0.00008\nelapsed time: 8371.8 seconds (2.33 hours)\n\nTimestep: 2070000\nmean reward (100 episodes): 16.3900\nbest mean reward: 16.7400\ncurrent episode reward: 19.0000\nepisodes: 1168\nexploration: 0.06498\nlearning_rate: 0.00008\nelapsed time: 8415.3 seconds (2.34 hours)\n\nTimestep: 2080000\nmean reward (100 episodes): 16.4500\nbest mean reward: 16.7400\ncurrent episode reward: 17.0000\nepisodes: 1173\nexploration: 0.06465\nlearning_rate: 0.00008\nelapsed time: 8459.2 seconds (2.35 hours)\n\nTimestep: 2090000\nmean reward (100 episodes): 15.6600\nbest mean reward: 16.7400\ncurrent episode reward: 20.0000\nepisodes: 1178\nexploration: 0.06433\nlearning_rate: 0.00008\nelapsed time: 8503.1 seconds (2.36 hours)\n\nTimestep: 2100000\nmean reward (100 episodes): 15.7600\nbest mean reward: 16.7400\ncurrent episode reward: 18.0000\nepisodes: 1184\nexploration: 0.06400\nlearning_rate: 0.00008\nelapsed time: 8546.9 seconds (2.37 hours)\n\nTimestep: 2110000\nmean reward (100 episodes): 15.8100\nbest mean reward: 16.7400\ncurrent episode reward: 20.0000\nepisodes: 1189\nexploration: 0.06367\nlearning_rate: 0.00008\nelapsed time: 8590.7 seconds (2.39 hours)\n\nTimestep: 2120000\nmean reward (100 episodes): 15.8800\nbest mean reward: 16.7400\ncurrent episode reward: 18.0000\nepisodes: 1193\nexploration: 0.06335\nlearning_rate: 0.00008\nelapsed time: 8634.8 seconds (2.40 hours)\n\nTimestep: 2130000\nmean reward (100 episodes): 15.8000\nbest mean reward: 16.7400\ncurrent episode reward: 20.0000\nepisodes: 1198\nexploration: 0.06302\nlearning_rate: 0.00008\nelapsed time: 8678.6 seconds (2.41 hours)\n\nTimestep: 2140000\nmean reward (100 episodes): 16.1800\nbest mean reward: 16.7400\ncurrent episode reward: 19.0000\nepisodes: 1203\nexploration: 0.06269\nlearning_rate: 0.00008\nelapsed time: 8722.8 seconds (2.42 hours)\n\nTimestep: 2150000\nmean reward (100 episodes): 16.5200\nbest mean reward: 16.7400\ncurrent episode reward: 18.0000\nepisodes: 1207\nexploration: 0.06236\nlearning_rate: 0.00008\nelapsed time: 8766.5 seconds (2.44 hours)\n\nTimestep: 2160000\nmean reward (100 episodes): 16.4800\nbest mean reward: 16.7400\ncurrent episode reward: 17.0000\nepisodes: 1212\nexploration: 0.06204\nlearning_rate: 0.00008\nelapsed time: 8810.3 seconds (2.45 hours)\n\nTimestep: 2170000\nmean reward (100 episodes): 16.5300\nbest mean reward: 16.7400\ncurrent episode reward: 16.0000\nepisodes: 1217\nexploration: 0.06171\nlearning_rate: 0.00008\nelapsed time: 8854.2 seconds (2.46 hours)\n\nTimestep: 2180000\nmean reward (100 episodes): 16.5800\nbest mean reward: 16.7400\ncurrent episode reward: 18.0000\nepisodes: 1222\nexploration: 0.06138\nlearning_rate: 0.00008\nelapsed time: 8898.3 seconds (2.47 hours)\n\nTimestep: 2190000\nmean reward (100 episodes): 16.4700\nbest mean reward: 16.7400\ncurrent episode reward: 14.0000\nepisodes: 1227\nexploration: 0.06105\nlearning_rate: 0.00008\nelapsed time: 8942.1 seconds (2.48 hours)\n\nTimestep: 2200000\nmean reward (100 episodes): 16.3500\nbest mean reward: 16.7400\ncurrent episode reward: 5.0000\nepisodes: 1231\nexploration: 0.06073\nlearning_rate: 0.00008\nelapsed time: 8986.0 seconds (2.50 hours)\n\nTimestep: 2210000\nmean reward (100 episodes): 16.3300\nbest mean reward: 16.7400\ncurrent episode reward: 20.0000\nepisodes: 1236\nexploration: 0.06040\nlearning_rate: 0.00008\nelapsed time: 9029.8 seconds (2.51 hours)\n\nTimestep: 2220000\nmean reward (100 episodes): 16.3200\nbest mean reward: 16.7400\ncurrent episode reward: 18.0000\nepisodes: 1241\nexploration: 0.06007\nlearning_rate: 0.00008\nelapsed time: 9073.3 seconds (2.52 hours)\n\nTimestep: 2230000\nmean reward (100 episodes): 16.3700\nbest mean reward: 16.7400\ncurrent episode reward: 17.0000\nepisodes: 1245\nexploration: 0.05975\nlearning_rate: 0.00008\nelapsed time: 9117.2 seconds (2.53 hours)\n\nTimestep: 2240000\nmean reward (100 episodes): 16.3900\nbest mean reward: 16.7400\ncurrent episode reward: 17.0000\nepisodes: 1250\nexploration: 0.05942\nlearning_rate: 0.00008\nelapsed time: 9161.0 seconds (2.54 hours)\n\nTimestep: 2250000\nmean reward (100 episodes): 16.3700\nbest mean reward: 16.7400\ncurrent episode reward: 19.0000\nepisodes: 1255\nexploration: 0.05909\nlearning_rate: 0.00008\nelapsed time: 9205.4 seconds (2.56 hours)\n\nTimestep: 2260000\nmean reward (100 episodes): 16.4300\nbest mean reward: 16.7400\ncurrent episode reward: 18.0000\nepisodes: 1260\nexploration: 0.05876\nlearning_rate: 0.00007\nelapsed time: 9249.3 seconds (2.57 hours)\n\nTimestep: 2270000\nmean reward (100 episodes): 16.5400\nbest mean reward: 16.7400\ncurrent episode reward: 18.0000\nepisodes: 1265\nexploration: 0.05844\nlearning_rate: 0.00007\nelapsed time: 9293.2 seconds (2.58 hours)\n\nTimestep: 2280000\nmean reward (100 episodes): 16.5300\nbest mean reward: 16.7400\ncurrent episode reward: 17.0000\nepisodes: 1270\nexploration: 0.05811\nlearning_rate: 0.00007\nelapsed time: 9336.7 seconds (2.59 hours)\n\nTimestep: 2290000\nmean reward (100 episodes): 16.8100\nbest mean reward: 16.8100\ncurrent episode reward: 18.0000\nepisodes: 1275\nexploration: 0.05778\nlearning_rate: 0.00007\nelapsed time: 9380.9 seconds (2.61 hours)\n\nTimestep: 2300000\nmean reward (100 episodes): 17.3800\nbest mean reward: 17.4500\ncurrent episode reward: 13.0000\nepisodes: 1279\nexploration: 0.05745\nlearning_rate: 0.00007\nelapsed time: 9425.0 seconds (2.62 hours)\n\nTimestep: 2310000\nmean reward (100 episodes): 17.3100\nbest mean reward: 17.4500\ncurrent episode reward: 19.0000\nepisodes: 1284\nexploration: 0.05713\nlearning_rate: 0.00007\nelapsed time: 9470.1 seconds (2.63 hours)\n\nTimestep: 2320000\nmean reward (100 episodes): 17.3000\nbest mean reward: 17.4500\ncurrent episode reward: 18.0000\nepisodes: 1289\nexploration: 0.05680\nlearning_rate: 0.00007\nelapsed time: 9514.3 seconds (2.64 hours)\n\nTimestep: 2330000\nmean reward (100 episodes): 17.3400\nbest mean reward: 17.4500\ncurrent episode reward: 18.0000\nepisodes: 1294\nexploration: 0.05647\nlearning_rate: 0.00007\nelapsed time: 9558.5 seconds (2.66 hours)\n\nTimestep: 2340000\nmean reward (100 episodes): 17.3700\nbest mean reward: 17.4500\ncurrent episode reward: 18.0000\nepisodes: 1299\nexploration: 0.05615\nlearning_rate: 0.00007\nelapsed time: 9602.5 seconds (2.67 hours)\n\nTimestep: 2350000\nmean reward (100 episodes): 17.3900\nbest mean reward: 17.4500\ncurrent episode reward: 18.0000\nepisodes: 1304\nexploration: 0.05582\nlearning_rate: 0.00007\nelapsed time: 9646.1 seconds (2.68 hours)\n\nTimestep: 2360000\nmean reward (100 episodes): 17.4900\nbest mean reward: 17.4900\ncurrent episode reward: 19.0000\nepisodes: 1309\nexploration: 0.05549\nlearning_rate: 0.00007\nelapsed time: 9690.9 seconds (2.69 hours)\n\nTimestep: 2370000\nmean reward (100 episodes): 17.5700\nbest mean reward: 17.5700\ncurrent episode reward: 20.0000\nepisodes: 1314\nexploration: 0.05516\nlearning_rate: 0.00007\nelapsed time: 9735.3 seconds (2.70 hours)\n\nTimestep: 2380000\nmean reward (100 episodes): 17.6900\nbest mean reward: 17.6900\ncurrent episode reward: 18.0000\nepisodes: 1320\nexploration: 0.05484\nlearning_rate: 0.00007\nelapsed time: 9779.2 seconds (2.72 hours)\n\nTimestep: 2390000\nmean reward (100 episodes): 17.7500\nbest mean reward: 17.8000\ncurrent episode reward: 16.0000\nepisodes: 1324\nexploration: 0.05451\nlearning_rate: 0.00007\nelapsed time: 9823.7 seconds (2.73 hours)\n\nTimestep: 2400000\nmean reward (100 episodes): 17.7700\nbest mean reward: 17.8000\ncurrent episode reward: 18.0000\nepisodes: 1329\nexploration: 0.05418\nlearning_rate: 0.00007\nelapsed time: 9867.8 seconds (2.74 hours)\n\nTimestep: 2410000\nmean reward (100 episodes): 17.9200\nbest mean reward: 17.9200\ncurrent episode reward: 19.0000\nepisodes: 1334\nexploration: 0.05385\nlearning_rate: 0.00007\nelapsed time: 9912.1 seconds (2.75 hours)\n\nTimestep: 2420000\nmean reward (100 episodes): 17.8200\nbest mean reward: 17.9200\ncurrent episode reward: 15.0000\nepisodes: 1339\nexploration: 0.05353\nlearning_rate: 0.00007\nelapsed time: 9955.9 seconds (2.77 hours)\n\nTimestep: 2430000\nmean reward (100 episodes): 17.9000\nbest mean reward: 17.9200\ncurrent episode reward: 21.0000\nepisodes: 1344\nexploration: 0.05320\nlearning_rate: 0.00007\nelapsed time: 9999.8 seconds (2.78 hours)\n\nTimestep: 2440000\nmean reward (100 episodes): 17.9200\nbest mean reward: 17.9400\ncurrent episode reward: 17.0000\nepisodes: 1348\nexploration: 0.05287\nlearning_rate: 0.00007\nelapsed time: 10043.7 seconds (2.79 hours)\n\nTimestep: 2450000\nmean reward (100 episodes): 17.8700\nbest mean reward: 17.9400\ncurrent episode reward: 20.0000\nepisodes: 1353\nexploration: 0.05255\nlearning_rate: 0.00007\nelapsed time: 10087.6 seconds (2.80 hours)\n\nTimestep: 2460000\nmean reward (100 episodes): 17.8600\nbest mean reward: 17.9400\ncurrent episode reward: 18.0000\nepisodes: 1358\nexploration: 0.05222\nlearning_rate: 0.00007\nelapsed time: 10131.9 seconds (2.81 hours)\n\nTimestep: 2470000\nmean reward (100 episodes): 17.9100\nbest mean reward: 17.9400\ncurrent episode reward: 18.0000\nepisodes: 1363\nexploration: 0.05189\nlearning_rate: 0.00007\nelapsed time: 10176.0 seconds (2.83 hours)\n\nTimestep: 2480000\nmean reward (100 episodes): 17.9800\nbest mean reward: 17.9800\ncurrent episode reward: 20.0000\nepisodes: 1368\nexploration: 0.05156\nlearning_rate: 0.00007\nelapsed time: 10220.0 seconds (2.84 hours)\n\nTimestep: 2490000\nmean reward (100 episodes): 17.9700\nbest mean reward: 18.0000\ncurrent episode reward: 18.0000\nepisodes: 1373\nexploration: 0.05124\nlearning_rate: 0.00007\nelapsed time: 10265.0 seconds (2.85 hours)\n\nTimestep: 2500000\nmean reward (100 episodes): 17.9500\nbest mean reward: 18.0000\ncurrent episode reward: 18.0000\nepisodes: 1378\nexploration: 0.05091\nlearning_rate: 0.00007\nelapsed time: 10309.2 seconds (2.86 hours)\n\nTimestep: 2510000\nmean reward (100 episodes): 18.0600\nbest mean reward: 18.1200\ncurrent episode reward: 17.0000\nepisodes: 1383\nexploration: 0.05058\nlearning_rate: 0.00007\nelapsed time: 10353.5 seconds (2.88 hours)\n\nTimestep: 2520000\nmean reward (100 episodes): 18.0300\nbest mean reward: 18.1200\ncurrent episode reward: 20.0000\nepisodes: 1388\nexploration: 0.05025\nlearning_rate: 0.00007\nelapsed time: 10397.8 seconds (2.89 hours)\n\nTimestep: 2530000\nmean reward (100 episodes): 18.0700\nbest mean reward: 18.1200\ncurrent episode reward: 20.0000\nepisodes: 1393\nexploration: 0.04993\nlearning_rate: 0.00007\nelapsed time: 10441.3 seconds (2.90 hours)\n\nTimestep: 2540000\nmean reward (100 episodes): 17.7100\nbest mean reward: 18.1200\ncurrent episode reward: 19.0000\nepisodes: 1398\nexploration: 0.04960\nlearning_rate: 0.00007\nelapsed time: 10485.3 seconds (2.91 hours)\n\nTimestep: 2550000\nmean reward (100 episodes): 17.3600\nbest mean reward: 18.1200\ncurrent episode reward: -18.0000\nepisodes: 1404\nexploration: 0.04927\nlearning_rate: 0.00007\nelapsed time: 10529.0 seconds (2.92 hours)\n\nTimestep: 2560000\nmean reward (100 episodes): 17.1000\nbest mean reward: 18.1200\ncurrent episode reward: 20.0000\nepisodes: 1409\nexploration: 0.04895\nlearning_rate: 0.00007\nelapsed time: 10572.4 seconds (2.94 hours)\n\nTimestep: 2570000\nmean reward (100 episodes): 17.0600\nbest mean reward: 18.1200\ncurrent episode reward: 19.0000\nepisodes: 1413\nexploration: 0.04862\nlearning_rate: 0.00007\nelapsed time: 10616.1 seconds (2.95 hours)\n\nTimestep: 2580000\nmean reward (100 episodes): 16.9500\nbest mean reward: 18.1200\ncurrent episode reward: 16.0000\nepisodes: 1418\nexploration: 0.04829\nlearning_rate: 0.00007\nelapsed time: 10660.0 seconds (2.96 hours)\n\nTimestep: 2590000\nmean reward (100 episodes): 16.9700\nbest mean reward: 18.1200\ncurrent episode reward: 19.0000\nepisodes: 1423\nexploration: 0.04796\nlearning_rate: 0.00007\nelapsed time: 10704.1 seconds (2.97 hours)\n\nTimestep: 2600000\nmean reward (100 episodes): 17.0300\nbest mean reward: 18.1200\ncurrent episode reward: 14.0000\nepisodes: 1428\nexploration: 0.04764\nlearning_rate: 0.00007\nelapsed time: 10749.0 seconds (2.99 hours)\n\nTimestep: 2610000\nmean reward (100 episodes): 17.0700\nbest mean reward: 18.1200\ncurrent episode reward: 19.0000\nepisodes: 1433\nexploration: 0.04731\nlearning_rate: 0.00007\nelapsed time: 10793.7 seconds (3.00 hours)\n\nTimestep: 2620000\nmean reward (100 episodes): 17.1900\nbest mean reward: 18.1200\ncurrent episode reward: 20.0000\nepisodes: 1439\nexploration: 0.04698\nlearning_rate: 0.00007\nelapsed time: 10837.1 seconds (3.01 hours)\n\nTimestep: 2630000\nmean reward (100 episodes): 17.1500\nbest mean reward: 18.1200\ncurrent episode reward: 18.0000\nepisodes: 1444\nexploration: 0.04665\nlearning_rate: 0.00007\nelapsed time: 10881.7 seconds (3.02 hours)\n\nTimestep: 2640000\nmean reward (100 episodes): 17.1600\nbest mean reward: 18.1200\ncurrent episode reward: 17.0000\nepisodes: 1448\nexploration: 0.04633\nlearning_rate: 0.00007\nelapsed time: 10926.3 seconds (3.04 hours)\n\nTimestep: 2650000\nmean reward (100 episodes): 17.1400\nbest mean reward: 18.1200\ncurrent episode reward: 17.0000\nepisodes: 1453\nexploration: 0.04600\nlearning_rate: 0.00007\nelapsed time: 10970.6 seconds (3.05 hours)\n\nTimestep: 2660000\nmean reward (100 episodes): 17.1400\nbest mean reward: 18.1200\ncurrent episode reward: 19.0000\nepisodes: 1459\nexploration: 0.04567\nlearning_rate: 0.00007\nelapsed time: 11014.3 seconds (3.06 hours)\n\nTimestep: 2670000\nmean reward (100 episodes): 17.1200\nbest mean reward: 18.1200\ncurrent episode reward: 21.0000\nepisodes: 1464\nexploration: 0.04535\nlearning_rate: 0.00007\nelapsed time: 11057.9 seconds (3.07 hours)\n\nTimestep: 2680000\nmean reward (100 episodes): 17.0300\nbest mean reward: 18.1200\ncurrent episode reward: 21.0000\nepisodes: 1469\nexploration: 0.04502\nlearning_rate: 0.00007\nelapsed time: 11102.8 seconds (3.08 hours)\n\nTimestep: 2690000\nmean reward (100 episodes): 17.0400\nbest mean reward: 18.1200\ncurrent episode reward: 20.0000\nepisodes: 1474\nexploration: 0.04469\nlearning_rate: 0.00007\nelapsed time: 11146.9 seconds (3.10 hours)\n\nTimestep: 2700000\nmean reward (100 episodes): 17.1300\nbest mean reward: 18.1200\ncurrent episode reward: 19.0000\nepisodes: 1479\nexploration: 0.04436\nlearning_rate: 0.00007\nelapsed time: 11190.9 seconds (3.11 hours)\n\nTimestep: 2710000\nmean reward (100 episodes): 17.1800\nbest mean reward: 18.1200\ncurrent episode reward: 18.0000\nepisodes: 1484\nexploration: 0.04404\nlearning_rate: 0.00007\nelapsed time: 11235.2 seconds (3.12 hours)\n\nTimestep: 2720000\nmean reward (100 episodes): 17.2000\nbest mean reward: 18.1200\ncurrent episode reward: 20.0000\nepisodes: 1489\nexploration: 0.04371\nlearning_rate: 0.00007\nelapsed time: 11279.3 seconds (3.13 hours)\n\nTimestep: 2730000\nmean reward (100 episodes): 17.3200\nbest mean reward: 18.1200\ncurrent episode reward: 20.0000\nepisodes: 1495\nexploration: 0.04338\nlearning_rate: 0.00007\nelapsed time: 11323.9 seconds (3.15 hours)\n\nTimestep: 2740000\nmean reward (100 episodes): 17.7100\nbest mean reward: 18.1200\ncurrent episode reward: 18.0000\nepisodes: 1499\nexploration: 0.04305\nlearning_rate: 0.00007\nelapsed time: 11368.2 seconds (3.16 hours)\n\nTimestep: 2750000\nmean reward (100 episodes): 18.0800\nbest mean reward: 18.1200\ncurrent episode reward: 18.0000\nepisodes: 1504\nexploration: 0.04273\nlearning_rate: 0.00007\nelapsed time: 11412.8 seconds (3.17 hours)\n\nTimestep: 2760000\nmean reward (100 episodes): 18.3500\nbest mean reward: 18.3800\ncurrent episode reward: 19.0000\nepisodes: 1509\nexploration: 0.04240\nlearning_rate: 0.00007\nelapsed time: 11457.3 seconds (3.18 hours)\n\nTimestep: 2770000\nmean reward (100 episodes): 18.4200\nbest mean reward: 18.4200\ncurrent episode reward: 20.0000\nepisodes: 1514\nexploration: 0.04207\nlearning_rate: 0.00007\nelapsed time: 11501.4 seconds (3.19 hours)\n\nTimestep: 2780000\nmean reward (100 episodes): 18.4200\nbest mean reward: 18.4300\ncurrent episode reward: 17.0000\nepisodes: 1519\nexploration: 0.04175\nlearning_rate: 0.00007\nelapsed time: 11545.5 seconds (3.21 hours)\n\nTimestep: 2790000\nmean reward (100 episodes): 18.3800\nbest mean reward: 18.4300\ncurrent episode reward: 19.0000\nepisodes: 1524\nexploration: 0.04142\nlearning_rate: 0.00007\nelapsed time: 11590.0 seconds (3.22 hours)\n\nTimestep: 2800000\nmean reward (100 episodes): 18.4000\nbest mean reward: 18.4400\ncurrent episode reward: 17.0000\nepisodes: 1529\nexploration: 0.04109\nlearning_rate: 0.00007\nelapsed time: 11633.7 seconds (3.23 hours)\n\nTimestep: 2810000\nmean reward (100 episodes): 18.4500\nbest mean reward: 18.4700\ncurrent episode reward: 18.0000\nepisodes: 1535\nexploration: 0.04076\nlearning_rate: 0.00007\nelapsed time: 11677.6 seconds (3.24 hours)\n\nTimestep: 2820000\nmean reward (100 episodes): 18.4500\nbest mean reward: 18.4700\ncurrent episode reward: 19.0000\nepisodes: 1540\nexploration: 0.04044\nlearning_rate: 0.00007\nelapsed time: 11722.1 seconds (3.26 hours)\n\nTimestep: 2830000\nmean reward (100 episodes): 18.4800\nbest mean reward: 18.4800\ncurrent episode reward: 20.0000\nepisodes: 1545\nexploration: 0.04011\nlearning_rate: 0.00007\nelapsed time: 11765.7 seconds (3.27 hours)\n\nTimestep: 2840000\nmean reward (100 episodes): 18.6200\nbest mean reward: 18.6300\ncurrent episode reward: 18.0000\nepisodes: 1550\nexploration: 0.03978\nlearning_rate: 0.00007\nelapsed time: 11809.6 seconds (3.28 hours)\n\nTimestep: 2850000\nmean reward (100 episodes): 18.6700\nbest mean reward: 18.6900\ncurrent episode reward: 17.0000\nepisodes: 1556\nexploration: 0.03945\nlearning_rate: 0.00007\nelapsed time: 11853.7 seconds (3.29 hours)\n\nTimestep: 2860000\nmean reward (100 episodes): 18.6400\nbest mean reward: 18.6900\ncurrent episode reward: 19.0000\nepisodes: 1561\nexploration: 0.03913\nlearning_rate: 0.00006\nelapsed time: 11897.6 seconds (3.30 hours)\n\nTimestep: 2870000\nmean reward (100 episodes): 18.6500\nbest mean reward: 18.6900\ncurrent episode reward: 15.0000\nepisodes: 1566\nexploration: 0.03880\nlearning_rate: 0.00006\nelapsed time: 11941.6 seconds (3.32 hours)\n\nTimestep: 2880000\nmean reward (100 episodes): 18.7000\nbest mean reward: 18.7300\ncurrent episode reward: 16.0000\nepisodes: 1571\nexploration: 0.03847\nlearning_rate: 0.00006\nelapsed time: 11986.0 seconds (3.33 hours)\n\nTimestep: 2890000\nmean reward (100 episodes): 18.7300\nbest mean reward: 18.7300\ncurrent episode reward: 19.0000\nepisodes: 1575\nexploration: 0.03815\nlearning_rate: 0.00006\nelapsed time: 12030.3 seconds (3.34 hours)\n\nTimestep: 2900000\nmean reward (100 episodes): 18.7200\nbest mean reward: 18.7300\ncurrent episode reward: 19.0000\nepisodes: 1581\nexploration: 0.03782\nlearning_rate: 0.00006\nelapsed time: 12074.7 seconds (3.35 hours)\n\nTimestep: 2910000\nmean reward (100 episodes): 18.7400\nbest mean reward: 18.7500\ncurrent episode reward: 18.0000\nepisodes: 1586\nexploration: 0.03749\nlearning_rate: 0.00006\nelapsed time: 12119.5 seconds (3.37 hours)\n\nTimestep: 2920000\nmean reward (100 episodes): 18.6500\nbest mean reward: 18.7500\ncurrent episode reward: 21.0000\nepisodes: 1591\nexploration: 0.03716\nlearning_rate: 0.00006\nelapsed time: 12163.8 seconds (3.38 hours)\n\nTimestep: 2930000\nmean reward (100 episodes): 18.6000\nbest mean reward: 18.7500\ncurrent episode reward: 19.0000\nepisodes: 1596\nexploration: 0.03684\nlearning_rate: 0.00006\nelapsed time: 12208.1 seconds (3.39 hours)\n\nTimestep: 2940000\nmean reward (100 episodes): 18.6700\nbest mean reward: 18.7500\ncurrent episode reward: 19.0000\nepisodes: 1602\nexploration: 0.03651\nlearning_rate: 0.00006\nelapsed time: 12251.6 seconds (3.40 hours)\n\nTimestep: 2950000\nmean reward (100 episodes): 18.6300\nbest mean reward: 18.7500\ncurrent episode reward: 18.0000\nepisodes: 1606\nexploration: 0.03618\nlearning_rate: 0.00006\nelapsed time: 12295.4 seconds (3.42 hours)\n\nTimestep: 2960000\nmean reward (100 episodes): 18.7000\nbest mean reward: 18.7500\ncurrent episode reward: 20.0000\nepisodes: 1612\nexploration: 0.03585\nlearning_rate: 0.00006\nelapsed time: 12339.5 seconds (3.43 hours)\n\nTimestep: 2970000\nmean reward (100 episodes): 18.7100\nbest mean reward: 18.7500\ncurrent episode reward: 21.0000\nepisodes: 1617\nexploration: 0.03553\nlearning_rate: 0.00006\nelapsed time: 12383.7 seconds (3.44 hours)\n\nTimestep: 2980000\nmean reward (100 episodes): 18.7400\nbest mean reward: 18.7500\ncurrent episode reward: 18.0000\nepisodes: 1622\nexploration: 0.03520\nlearning_rate: 0.00006\nelapsed time: 12427.8 seconds (3.45 hours)\n\nTimestep: 2990000\nmean reward (100 episodes): 18.7700\nbest mean reward: 18.7800\ncurrent episode reward: 20.0000\nepisodes: 1628\nexploration: 0.03487\nlearning_rate: 0.00006\nelapsed time: 12472.3 seconds (3.46 hours)\n\nTimestep: 3000000\nmean reward (100 episodes): 18.7300\nbest mean reward: 18.8100\ncurrent episode reward: 19.0000\nepisodes: 1633\nexploration: 0.03455\nlearning_rate: 0.00006\nelapsed time: 12516.2 seconds (3.48 hours)\n\nTimestep: 3010000\nmean reward (100 episodes): 18.7100\nbest mean reward: 18.8100\ncurrent episode reward: 21.0000\nepisodes: 1638\nexploration: 0.03422\nlearning_rate: 0.00006\nelapsed time: 12561.1 seconds (3.49 hours)\n\nTimestep: 3020000\nmean reward (100 episodes): 18.7400\nbest mean reward: 18.8100\ncurrent episode reward: 19.0000\nepisodes: 1644\nexploration: 0.03389\nlearning_rate: 0.00006\nelapsed time: 12605.2 seconds (3.50 hours)\n\nTimestep: 3030000\nmean reward (100 episodes): 18.6700\nbest mean reward: 18.8100\ncurrent episode reward: 19.0000\nepisodes: 1649\nexploration: 0.03356\nlearning_rate: 0.00006\nelapsed time: 12649.5 seconds (3.51 hours)\n\nTimestep: 3040000\nmean reward (100 episodes): 18.7500\nbest mean reward: 18.8100\ncurrent episode reward: 20.0000\nepisodes: 1654\nexploration: 0.03324\nlearning_rate: 0.00006\nelapsed time: 12694.4 seconds (3.53 hours)\n\nTimestep: 3050000\nmean reward (100 episodes): 18.7400\nbest mean reward: 18.8100\ncurrent episode reward: 16.0000\nepisodes: 1659\nexploration: 0.03291\nlearning_rate: 0.00006\nelapsed time: 12738.4 seconds (3.54 hours)\n\nTimestep: 3060000\nmean reward (100 episodes): 18.7600\nbest mean reward: 18.8100\ncurrent episode reward: 20.0000\nepisodes: 1664\nexploration: 0.03258\nlearning_rate: 0.00006\nelapsed time: 12782.6 seconds (3.55 hours)\n\nTimestep: 3070000\nmean reward (100 episodes): 18.8900\nbest mean reward: 18.8900\ncurrent episode reward: 21.0000\nepisodes: 1670\nexploration: 0.03225\nlearning_rate: 0.00006\nelapsed time: 12827.3 seconds (3.56 hours)\n\nTimestep: 3080000\nmean reward (100 episodes): 18.9600\nbest mean reward: 18.9600\ncurrent episode reward: 20.0000\nepisodes: 1675\nexploration: 0.03193\nlearning_rate: 0.00006\nelapsed time: 12870.0 seconds (3.58 hours)\n\nTimestep: 3090000\nmean reward (100 episodes): 18.9700\nbest mean reward: 19.0000\ncurrent episode reward: 20.0000\nepisodes: 1680\nexploration: 0.03160\nlearning_rate: 0.00006\nelapsed time: 12914.4 seconds (3.59 hours)\n\nTimestep: 3100000\nmean reward (100 episodes): 19.0000\nbest mean reward: 19.0000\ncurrent episode reward: 18.0000\nepisodes: 1686\nexploration: 0.03127\nlearning_rate: 0.00006\nelapsed time: 12958.3 seconds (3.60 hours)\n\nTimestep: 3110000\nmean reward (100 episodes): 19.0700\nbest mean reward: 19.1200\ncurrent episode reward: 21.0000\nepisodes: 1691\nexploration: 0.03095\nlearning_rate: 0.00006\nelapsed time: 13002.8 seconds (3.61 hours)\n\nTimestep: 3120000\nmean reward (100 episodes): 18.9600\nbest mean reward: 19.1200\ncurrent episode reward: 4.0000\nepisodes: 1696\nexploration: 0.03062\nlearning_rate: 0.00006\nelapsed time: 13047.2 seconds (3.62 hours)\n\nTimestep: 3130000\nmean reward (100 episodes): 18.9900\nbest mean reward: 19.1200\ncurrent episode reward: 17.0000\nepisodes: 1702\nexploration: 0.03029\nlearning_rate: 0.00006\nelapsed time: 13090.2 seconds (3.64 hours)\n\nTimestep: 3140000\nmean reward (100 episodes): 18.9800\nbest mean reward: 19.1200\ncurrent episode reward: 18.0000\nepisodes: 1707\nexploration: 0.02996\nlearning_rate: 0.00006\nelapsed time: 13134.6 seconds (3.65 hours)\n\nTimestep: 3150000\nmean reward (100 episodes): 18.9900\nbest mean reward: 19.1200\ncurrent episode reward: 19.0000\nepisodes: 1712\nexploration: 0.02964\nlearning_rate: 0.00006\nelapsed time: 13178.8 seconds (3.66 hours)\n\nTimestep: 3160000\nmean reward (100 episodes): 19.0700\nbest mean reward: 19.1200\ncurrent episode reward: 20.0000\nepisodes: 1718\nexploration: 0.02931\nlearning_rate: 0.00006\nelapsed time: 13224.1 seconds (3.67 hours)\n\nTimestep: 3170000\nmean reward (100 episodes): 19.1100\nbest mean reward: 19.1200\ncurrent episode reward: 20.0000\nepisodes: 1723\nexploration: 0.02898\nlearning_rate: 0.00006\nelapsed time: 13267.8 seconds (3.69 hours)\n\nTimestep: 3180000\nmean reward (100 episodes): 19.1100\nbest mean reward: 19.1500\ncurrent episode reward: 18.0000\nepisodes: 1729\nexploration: 0.02865\nlearning_rate: 0.00006\nelapsed time: 13313.1 seconds (3.70 hours)\n\nTimestep: 3190000\nmean reward (100 episodes): 19.1900\nbest mean reward: 19.1900\ncurrent episode reward: 20.0000\nepisodes: 1734\nexploration: 0.02833\nlearning_rate: 0.00006\nelapsed time: 13357.6 seconds (3.71 hours)\n\nTimestep: 3200000\nmean reward (100 episodes): 19.1900\nbest mean reward: 19.2400\ncurrent episode reward: 18.0000\nepisodes: 1739\nexploration: 0.02800\nlearning_rate: 0.00006\nelapsed time: 13401.9 seconds (3.72 hours)\n\nTimestep: 3210000\nmean reward (100 episodes): 19.1500\nbest mean reward: 19.2400\ncurrent episode reward: 19.0000\nepisodes: 1745\nexploration: 0.02767\nlearning_rate: 0.00006\nelapsed time: 13446.0 seconds (3.74 hours)\n\nTimestep: 3220000\nmean reward (100 episodes): 19.1900\nbest mean reward: 19.2400\ncurrent episode reward: 18.0000\nepisodes: 1750\nexploration: 0.02735\nlearning_rate: 0.00006\nelapsed time: 13490.6 seconds (3.75 hours)\n\nTimestep: 3230000\nmean reward (100 episodes): 19.1900\nbest mean reward: 19.2400\ncurrent episode reward: 21.0000\nepisodes: 1756\nexploration: 0.02702\nlearning_rate: 0.00006\nelapsed time: 13534.7 seconds (3.76 hours)\n\nTimestep: 3240000\nmean reward (100 episodes): 19.3000\nbest mean reward: 19.3000\ncurrent episode reward: 20.0000\nepisodes: 1761\nexploration: 0.02669\nlearning_rate: 0.00006\nelapsed time: 13580.0 seconds (3.77 hours)\n\nTimestep: 3250000\nmean reward (100 episodes): 19.3100\nbest mean reward: 19.3600\ncurrent episode reward: 18.0000\nepisodes: 1767\nexploration: 0.02636\nlearning_rate: 0.00006\nelapsed time: 13624.5 seconds (3.78 hours)\n\nTimestep: 3260000\nmean reward (100 episodes): 19.2900\nbest mean reward: 19.3600\ncurrent episode reward: 20.0000\nepisodes: 1772\nexploration: 0.02604\nlearning_rate: 0.00006\nelapsed time: 13668.8 seconds (3.80 hours)\n\nTimestep: 3270000\nmean reward (100 episodes): 19.2900\nbest mean reward: 19.3600\ncurrent episode reward: 21.0000\nepisodes: 1777\nexploration: 0.02571\nlearning_rate: 0.00006\nelapsed time: 13713.4 seconds (3.81 hours)\n\nTimestep: 3280000\nmean reward (100 episodes): 19.2700\nbest mean reward: 19.3600\ncurrent episode reward: 19.0000\nepisodes: 1783\nexploration: 0.02538\nlearning_rate: 0.00006\nelapsed time: 13757.0 seconds (3.82 hours)\n\nTimestep: 3290000\nmean reward (100 episodes): 19.3800\nbest mean reward: 19.3800\ncurrent episode reward: 20.0000\nepisodes: 1788\nexploration: 0.02505\nlearning_rate: 0.00006\nelapsed time: 13801.3 seconds (3.83 hours)\n\nTimestep: 3300000\nmean reward (100 episodes): 19.3500\nbest mean reward: 19.3800\ncurrent episode reward: 18.0000\nepisodes: 1794\nexploration: 0.02473\nlearning_rate: 0.00006\nelapsed time: 13846.0 seconds (3.85 hours)\n\nTimestep: 3310000\nmean reward (100 episodes): 19.5100\nbest mean reward: 19.5300\ncurrent episode reward: 20.0000\nepisodes: 1799\nexploration: 0.02440\nlearning_rate: 0.00006\nelapsed time: 13890.2 seconds (3.86 hours)\n\nTimestep: 3320000\nmean reward (100 episodes): 19.5500\nbest mean reward: 19.5500\ncurrent episode reward: 21.0000\nepisodes: 1805\nexploration: 0.02407\nlearning_rate: 0.00006\nelapsed time: 13934.0 seconds (3.87 hours)\n\nTimestep: 3330000\nmean reward (100 episodes): 19.6000\nbest mean reward: 19.6400\ncurrent episode reward: 21.0000\nepisodes: 1810\nexploration: 0.02375\nlearning_rate: 0.00006\nelapsed time: 13978.3 seconds (3.88 hours)\n\nTimestep: 3340000\nmean reward (100 episodes): 19.6200\nbest mean reward: 19.6400\ncurrent episode reward: 21.0000\nepisodes: 1816\nexploration: 0.02342\nlearning_rate: 0.00006\nelapsed time: 14022.1 seconds (3.90 hours)\n\nTimestep: 3350000\nmean reward (100 episodes): 19.6000\nbest mean reward: 19.6400\ncurrent episode reward: 20.0000\nepisodes: 1821\nexploration: 0.02309\nlearning_rate: 0.00006\nelapsed time: 14066.2 seconds (3.91 hours)\n\nTimestep: 3360000\nmean reward (100 episodes): 19.5700\nbest mean reward: 19.6400\ncurrent episode reward: 19.0000\nepisodes: 1827\nexploration: 0.02276\nlearning_rate: 0.00006\nelapsed time: 14110.4 seconds (3.92 hours)\n\nTimestep: 3370000\nmean reward (100 episodes): 19.6100\nbest mean reward: 19.6400\ncurrent episode reward: 21.0000\nepisodes: 1832\nexploration: 0.02244\nlearning_rate: 0.00006\nelapsed time: 14155.0 seconds (3.93 hours)\n\nTimestep: 3380000\nmean reward (100 episodes): 19.6100\nbest mean reward: 19.6400\ncurrent episode reward: 20.0000\nepisodes: 1837\nexploration: 0.02211\nlearning_rate: 0.00006\nelapsed time: 14199.4 seconds (3.94 hours)\n\nTimestep: 3390000\nmean reward (100 episodes): 19.7600\nbest mean reward: 19.7600\ncurrent episode reward: 21.0000\nepisodes: 1843\nexploration: 0.02178\nlearning_rate: 0.00006\nelapsed time: 14243.7 seconds (3.96 hours)\n\nTimestep: 3400000\nmean reward (100 episodes): 19.7600\nbest mean reward: 19.7700\ncurrent episode reward: 19.0000\nepisodes: 1848\nexploration: 0.02145\nlearning_rate: 0.00006\nelapsed time: 14288.7 seconds (3.97 hours)\n\nTimestep: 3410000\nmean reward (100 episodes): 19.7800\nbest mean reward: 19.8000\ncurrent episode reward: 19.0000\nepisodes: 1854\nexploration: 0.02113\nlearning_rate: 0.00006\nelapsed time: 14333.8 seconds (3.98 hours)\n\nTimestep: 3420000\nmean reward (100 episodes): 19.7600\nbest mean reward: 19.8000\ncurrent episode reward: 21.0000\nepisodes: 1860\nexploration: 0.02080\nlearning_rate: 0.00006\nelapsed time: 14378.6 seconds (3.99 hours)\n\nTimestep: 3430000\nmean reward (100 episodes): 19.7200\nbest mean reward: 19.8000\ncurrent episode reward: 15.0000\nepisodes: 1865\nexploration: 0.02047\nlearning_rate: 0.00006\nelapsed time: 14422.5 seconds (4.01 hours)\n\nTimestep: 3440000\nmean reward (100 episodes): 19.7700\nbest mean reward: 19.8000\ncurrent episode reward: 19.0000\nepisodes: 1870\nexploration: 0.02015\nlearning_rate: 0.00006\nelapsed time: 14467.1 seconds (4.02 hours)\n\nTimestep: 3450000\nmean reward (100 episodes): 19.7500\nbest mean reward: 19.8000\ncurrent episode reward: 21.0000\nepisodes: 1876\nexploration: 0.01982\nlearning_rate: 0.00006\nelapsed time: 14511.1 seconds (4.03 hours)\n\nTimestep: 3460000\nmean reward (100 episodes): 19.5500\nbest mean reward: 19.8000\ncurrent episode reward: 15.0000\nepisodes: 1881\nexploration: 0.01949\nlearning_rate: 0.00005\nelapsed time: 14555.3 seconds (4.04 hours)\n\nTimestep: 3470000\nmean reward (100 episodes): 19.6000\nbest mean reward: 19.8000\ncurrent episode reward: 21.0000\nepisodes: 1887\nexploration: 0.01916\nlearning_rate: 0.00005\nelapsed time: 14599.6 seconds (4.06 hours)\n\nTimestep: 3480000\nmean reward (100 episodes): 19.5700\nbest mean reward: 19.8000\ncurrent episode reward: 21.0000\nepisodes: 1892\nexploration: 0.01884\nlearning_rate: 0.00005\nelapsed time: 14642.8 seconds (4.07 hours)\n\nTimestep: 3490000\nmean reward (100 episodes): 19.5600\nbest mean reward: 19.8000\ncurrent episode reward: 21.0000\nepisodes: 1897\nexploration: 0.01851\nlearning_rate: 0.00005\nelapsed time: 14686.7 seconds (4.08 hours)\n\nTimestep: 3500000\nmean reward (100 episodes): 19.5900\nbest mean reward: 19.8000\ncurrent episode reward: 21.0000\nepisodes: 1903\nexploration: 0.01818\nlearning_rate: 0.00005\nelapsed time: 14731.2 seconds (4.09 hours)\n\nTimestep: 3510000\nmean reward (100 episodes): 19.6400\nbest mean reward: 19.8000\ncurrent episode reward: 19.0000\nepisodes: 1909\nexploration: 0.01785\nlearning_rate: 0.00005\nelapsed time: 14775.8 seconds (4.10 hours)\n\nTimestep: 3520000\nmean reward (100 episodes): 19.6100\nbest mean reward: 19.8000\ncurrent episode reward: 18.0000\nepisodes: 1914\nexploration: 0.01753\nlearning_rate: 0.00005\nelapsed time: 14820.3 seconds (4.12 hours)\n\nTimestep: 3530000\nmean reward (100 episodes): 19.6500\nbest mean reward: 19.8000\ncurrent episode reward: 20.0000\nepisodes: 1920\nexploration: 0.01720\nlearning_rate: 0.00005\nelapsed time: 14864.7 seconds (4.13 hours)\n\nTimestep: 3540000\nmean reward (100 episodes): 19.6300\nbest mean reward: 19.8000\ncurrent episode reward: 21.0000\nepisodes: 1924\nexploration: 0.01687\nlearning_rate: 0.00005\nelapsed time: 14908.6 seconds (4.14 hours)\n\nTimestep: 3550000\nmean reward (100 episodes): 19.6600\nbest mean reward: 19.8000\ncurrent episode reward: 21.0000\nepisodes: 1930\nexploration: 0.01655\nlearning_rate: 0.00005\nelapsed time: 14953.4 seconds (4.15 hours)\n\nTimestep: 3560000\nmean reward (100 episodes): 19.7300\nbest mean reward: 19.8000\ncurrent episode reward: 21.0000\nepisodes: 1936\nexploration: 0.01622\nlearning_rate: 0.00005\nelapsed time: 14997.7 seconds (4.17 hours)\n\nTimestep: 3570000\nmean reward (100 episodes): 19.7500\nbest mean reward: 19.8000\ncurrent episode reward: 20.0000\nepisodes: 1942\nexploration: 0.01589\nlearning_rate: 0.00005\nelapsed time: 15041.5 seconds (4.18 hours)\n\nTimestep: 3580000\nmean reward (100 episodes): 19.7700\nbest mean reward: 19.8000\ncurrent episode reward: 21.0000\nepisodes: 1947\nexploration: 0.01556\nlearning_rate: 0.00005\nelapsed time: 15085.5 seconds (4.19 hours)\n\nTimestep: 3590000\nmean reward (100 episodes): 19.8000\nbest mean reward: 19.8000\ncurrent episode reward: 20.0000\nepisodes: 1953\nexploration: 0.01524\nlearning_rate: 0.00005\nelapsed time: 15129.9 seconds (4.20 hours)\n\nTimestep: 3600000\nmean reward (100 episodes): 19.8400\nbest mean reward: 19.8400\ncurrent episode reward: 21.0000\nepisodes: 1959\nexploration: 0.01491\nlearning_rate: 0.00005\nelapsed time: 15174.5 seconds (4.22 hours)\n\nTimestep: 3610000\nmean reward (100 episodes): 19.8700\nbest mean reward: 19.8700\ncurrent episode reward: 17.0000\nepisodes: 1965\nexploration: 0.01458\nlearning_rate: 0.00005\nelapsed time: 15218.5 seconds (4.23 hours)\n\nTimestep: 3620000\nmean reward (100 episodes): 19.9600\nbest mean reward: 19.9600\ncurrent episode reward: 20.0000\nepisodes: 1971\nexploration: 0.01425\nlearning_rate: 0.00005\nelapsed time: 15263.0 seconds (4.24 hours)\n\nTimestep: 3630000\nmean reward (100 episodes): 19.9900\nbest mean reward: 19.9900\ncurrent episode reward: 21.0000\nepisodes: 1976\nexploration: 0.01393\nlearning_rate: 0.00005\nelapsed time: 15308.1 seconds (4.25 hours)\n\nTimestep: 3640000\nmean reward (100 episodes): 20.2400\nbest mean reward: 20.2400\ncurrent episode reward: 21.0000\nepisodes: 1982\nexploration: 0.01360\nlearning_rate: 0.00005\nelapsed time: 15352.2 seconds (4.26 hours)\n\nTimestep: 3650000\nmean reward (100 episodes): 20.2500\nbest mean reward: 20.2500\ncurrent episode reward: 21.0000\nepisodes: 1988\nexploration: 0.01327\nlearning_rate: 0.00005\nelapsed time: 15396.5 seconds (4.28 hours)\n\nTimestep: 3660000\nmean reward (100 episodes): 20.2400\nbest mean reward: 20.2700\ncurrent episode reward: 20.0000\nepisodes: 1993\nexploration: 0.01295\nlearning_rate: 0.00005\nelapsed time: 15442.2 seconds (4.29 hours)\n\nTimestep: 3670000\nmean reward (100 episodes): 20.2600\nbest mean reward: 20.2700\ncurrent episode reward: 21.0000\nepisodes: 1999\nexploration: 0.01262\nlearning_rate: 0.00005\nelapsed time: 15486.6 seconds (4.30 hours)\n\nTimestep: 3680000\nmean reward (100 episodes): 20.2800\nbest mean reward: 20.2800\ncurrent episode reward: 21.0000\nepisodes: 2005\nexploration: 0.01229\nlearning_rate: 0.00005\nelapsed time: 15535.0 seconds (4.32 hours)\n\nTimestep: 3690000\nmean reward (100 episodes): 20.2800\nbest mean reward: 20.2800\ncurrent episode reward: 21.0000\nepisodes: 2011\nexploration: 0.01196\nlearning_rate: 0.00005\nelapsed time: 15579.6 seconds (4.33 hours)\n\nTimestep: 3700000\nmean reward (100 episodes): 20.3500\nbest mean reward: 20.3500\ncurrent episode reward: 21.0000\nepisodes: 2017\nexploration: 0.01164\nlearning_rate: 0.00005\nelapsed time: 15623.8 seconds (4.34 hours)\n\nTimestep: 3710000\nmean reward (100 episodes): 20.3800\nbest mean reward: 20.3800\ncurrent episode reward: 21.0000\nepisodes: 2022\nexploration: 0.01131\nlearning_rate: 0.00005\nelapsed time: 15667.9 seconds (4.35 hours)\n\nTimestep: 3720000\nmean reward (100 episodes): 20.4400\nbest mean reward: 20.4400\ncurrent episode reward: 21.0000\nepisodes: 2029\nexploration: 0.01098\nlearning_rate: 0.00005\nelapsed time: 15712.0 seconds (4.36 hours)\n\nTimestep: 3730000\nmean reward (100 episodes): 20.3800\nbest mean reward: 20.4400\ncurrent episode reward: 18.0000\nepisodes: 2034\nexploration: 0.01065\nlearning_rate: 0.00005\nelapsed time: 15756.1 seconds (4.38 hours)\n\nTimestep: 3740000\nmean reward (100 episodes): 20.3300\nbest mean reward: 20.4400\ncurrent episode reward: 21.0000\nepisodes: 2040\nexploration: 0.01033\nlearning_rate: 0.00005\nelapsed time: 15800.6 seconds (4.39 hours)\n\nTimestep: 3750000\nmean reward (100 episodes): 20.3700\nbest mean reward: 20.4400\ncurrent episode reward: 21.0000\nepisodes: 2046\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 15845.5 seconds (4.40 hours)\n\nTimestep: 3760000\nmean reward (100 episodes): 20.3800\nbest mean reward: 20.4400\ncurrent episode reward: 20.0000\nepisodes: 2052\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 15890.6 seconds (4.41 hours)\n\nTimestep: 3770000\nmean reward (100 episodes): 20.4100\nbest mean reward: 20.4400\ncurrent episode reward: 21.0000\nepisodes: 2058\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 15934.7 seconds (4.43 hours)\n\nTimestep: 3780000\nmean reward (100 episodes): 20.3900\nbest mean reward: 20.4400\ncurrent episode reward: 21.0000\nepisodes: 2063\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 15979.9 seconds (4.44 hours)\n\nTimestep: 3790000\nmean reward (100 episodes): 20.4200\nbest mean reward: 20.4400\ncurrent episode reward: 21.0000\nepisodes: 2069\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16024.6 seconds (4.45 hours)\n\nTimestep: 3800000\nmean reward (100 episodes): 20.4200\nbest mean reward: 20.4400\ncurrent episode reward: 21.0000\nepisodes: 2075\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16069.1 seconds (4.46 hours)\n\nTimestep: 3810000\nmean reward (100 episodes): 20.4000\nbest mean reward: 20.4400\ncurrent episode reward: 20.0000\nepisodes: 2081\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16113.2 seconds (4.48 hours)\n\nTimestep: 3820000\nmean reward (100 episodes): 20.4200\nbest mean reward: 20.4400\ncurrent episode reward: 21.0000\nepisodes: 2087\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16157.5 seconds (4.49 hours)\n\nTimestep: 3830000\nmean reward (100 episodes): 20.4400\nbest mean reward: 20.4400\ncurrent episode reward: 19.0000\nepisodes: 2092\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16202.8 seconds (4.50 hours)\n\nTimestep: 3840000\nmean reward (100 episodes): 20.4700\nbest mean reward: 20.4800\ncurrent episode reward: 21.0000\nepisodes: 2098\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16247.5 seconds (4.51 hours)\n\nTimestep: 3850000\nmean reward (100 episodes): 20.4500\nbest mean reward: 20.4800\ncurrent episode reward: 21.0000\nepisodes: 2104\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16292.0 seconds (4.53 hours)\n\nTimestep: 3860000\nmean reward (100 episodes): 20.4700\nbest mean reward: 20.4800\ncurrent episode reward: 20.0000\nepisodes: 2110\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16337.5 seconds (4.54 hours)\n\nTimestep: 3870000\nmean reward (100 episodes): 20.4400\nbest mean reward: 20.4800\ncurrent episode reward: 19.0000\nepisodes: 2115\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16382.0 seconds (4.55 hours)\n\nTimestep: 3880000\nmean reward (100 episodes): 20.4600\nbest mean reward: 20.4800\ncurrent episode reward: 21.0000\nepisodes: 2121\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16427.1 seconds (4.56 hours)\n\nTimestep: 3890000\nmean reward (100 episodes): 20.4300\nbest mean reward: 20.4800\ncurrent episode reward: 20.0000\nepisodes: 2126\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16471.2 seconds (4.58 hours)\n\nTimestep: 3900000\nmean reward (100 episodes): 20.4500\nbest mean reward: 20.4800\ncurrent episode reward: 21.0000\nepisodes: 2132\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16516.1 seconds (4.59 hours)\n\nTimestep: 3910000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2138\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16560.2 seconds (4.60 hours)\n\nTimestep: 3920000\nmean reward (100 episodes): 20.5000\nbest mean reward: 20.5200\ncurrent episode reward: 19.0000\nepisodes: 2144\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16604.7 seconds (4.61 hours)\n\nTimestep: 3930000\nmean reward (100 episodes): 20.4100\nbest mean reward: 20.5200\ncurrent episode reward: 19.0000\nepisodes: 2149\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16649.0 seconds (4.62 hours)\n\nTimestep: 3940000\nmean reward (100 episodes): 20.4100\nbest mean reward: 20.5200\ncurrent episode reward: 20.0000\nepisodes: 2155\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16693.1 seconds (4.64 hours)\n\nTimestep: 3950000\nmean reward (100 episodes): 20.4100\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2161\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16737.1 seconds (4.65 hours)\n\nTimestep: 3960000\nmean reward (100 episodes): 20.4400\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2167\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16781.3 seconds (4.66 hours)\n\nTimestep: 3970000\nmean reward (100 episodes): 20.4000\nbest mean reward: 20.5200\ncurrent episode reward: 19.0000\nepisodes: 2173\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16825.5 seconds (4.67 hours)\n\nTimestep: 3980000\nmean reward (100 episodes): 20.3900\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2178\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16869.9 seconds (4.69 hours)\n\nTimestep: 3990000\nmean reward (100 episodes): 20.4300\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2184\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16914.6 seconds (4.70 hours)\n\nTimestep: 4000000\nmean reward (100 episodes): 20.3800\nbest mean reward: 20.5200\ncurrent episode reward: 20.0000\nepisodes: 2190\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16958.8 seconds (4.71 hours)\n\nTimestep: 4010000\nmean reward (100 episodes): 20.3900\nbest mean reward: 20.5200\ncurrent episode reward: 20.0000\nepisodes: 2195\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17003.2 seconds (4.72 hours)\n\nTimestep: 4020000\nmean reward (100 episodes): 20.3900\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2201\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17047.5 seconds (4.74 hours)\n\nTimestep: 4030000\nmean reward (100 episodes): 20.3900\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2207\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17092.7 seconds (4.75 hours)\n\nTimestep: 4040000\nmean reward (100 episodes): 20.4000\nbest mean reward: 20.5200\ncurrent episode reward: 20.0000\nepisodes: 2213\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17137.4 seconds (4.76 hours)\n\nTimestep: 4050000\nmean reward (100 episodes): 20.4300\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2219\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17181.9 seconds (4.77 hours)\n\nTimestep: 4060000\nmean reward (100 episodes): 20.4300\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2224\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17226.5 seconds (4.79 hours)\n\nTimestep: 4070000\nmean reward (100 episodes): 20.4100\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2230\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17270.5 seconds (4.80 hours)\n\nTimestep: 4080000\nmean reward (100 episodes): 20.4000\nbest mean reward: 20.5200\ncurrent episode reward: 20.0000\nepisodes: 2236\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17314.7 seconds (4.81 hours)\n\nTimestep: 4090000\nmean reward (100 episodes): 20.3900\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2242\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17359.2 seconds (4.82 hours)\n\nTimestep: 4100000\nmean reward (100 episodes): 20.4500\nbest mean reward: 20.5200\ncurrent episode reward: 20.0000\nepisodes: 2247\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17403.9 seconds (4.83 hours)\n\nTimestep: 4110000\nmean reward (100 episodes): 20.4700\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2253\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17448.1 seconds (4.85 hours)\n\nTimestep: 4120000\nmean reward (100 episodes): 20.4800\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2259\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17492.8 seconds (4.86 hours)\n\nTimestep: 4130000\nmean reward (100 episodes): 20.4600\nbest mean reward: 20.5200\ncurrent episode reward: 20.0000\nepisodes: 2265\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17536.4 seconds (4.87 hours)\n\nTimestep: 4140000\nmean reward (100 episodes): 20.4500\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2271\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17580.9 seconds (4.88 hours)\n\nTimestep: 4150000\nmean reward (100 episodes): 20.4800\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2277\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17625.1 seconds (4.90 hours)\n\nTimestep: 4160000\nmean reward (100 episodes): 20.4700\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2282\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17669.0 seconds (4.91 hours)\n\nTimestep: 4170000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2288\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17713.4 seconds (4.92 hours)\n\nTimestep: 4180000\nmean reward (100 episodes): 20.5400\nbest mean reward: 20.5400\ncurrent episode reward: 21.0000\nepisodes: 2294\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17757.8 seconds (4.93 hours)\n\nTimestep: 4190000\nmean reward (100 episodes): 20.5800\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2300\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17802.2 seconds (4.95 hours)\n\nTimestep: 4200000\nmean reward (100 episodes): 20.5800\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2306\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17847.1 seconds (4.96 hours)\n\nTimestep: 4210000\nmean reward (100 episodes): 20.5900\nbest mean reward: 20.5900\ncurrent episode reward: 21.0000\nepisodes: 2312\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17891.0 seconds (4.97 hours)\n\nTimestep: 4220000\nmean reward (100 episodes): 20.5900\nbest mean reward: 20.6000\ncurrent episode reward: 20.0000\nepisodes: 2318\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17934.9 seconds (4.98 hours)\n\nTimestep: 4230000\nmean reward (100 episodes): 20.6100\nbest mean reward: 20.6100\ncurrent episode reward: 21.0000\nepisodes: 2324\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17979.9 seconds (4.99 hours)\n\nTimestep: 4240000\nmean reward (100 episodes): 20.6400\nbest mean reward: 20.6400\ncurrent episode reward: 21.0000\nepisodes: 2330\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18024.7 seconds (5.01 hours)\n\nTimestep: 4250000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 2336\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18069.6 seconds (5.02 hours)\n\nTimestep: 4260000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.6900\ncurrent episode reward: 21.0000\nepisodes: 2342\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18114.6 seconds (5.03 hours)\n\nTimestep: 4270000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.7100\ncurrent episode reward: 21.0000\nepisodes: 2347\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18159.2 seconds (5.04 hours)\n\nTimestep: 4280000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.7100\ncurrent episode reward: 21.0000\nepisodes: 2353\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18204.1 seconds (5.06 hours)\n\nTimestep: 4290000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.7100\ncurrent episode reward: 21.0000\nepisodes: 2359\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18247.9 seconds (5.07 hours)\n\nTimestep: 4300000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.7400\ncurrent episode reward: 21.0000\nepisodes: 2365\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18292.7 seconds (5.08 hours)\n\nTimestep: 4310000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.7600\ncurrent episode reward: 20.0000\nepisodes: 2371\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18336.7 seconds (5.09 hours)\n\nTimestep: 4320000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.7600\ncurrent episode reward: 20.0000\nepisodes: 2377\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18380.8 seconds (5.11 hours)\n\nTimestep: 4330000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.7700\ncurrent episode reward: 20.0000\nepisodes: 2383\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18424.9 seconds (5.12 hours)\n\nTimestep: 4340000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2389\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18469.5 seconds (5.13 hours)\n\nTimestep: 4350000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2395\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18512.9 seconds (5.14 hours)\n\nTimestep: 4360000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2400\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18557.5 seconds (5.15 hours)\n\nTimestep: 4370000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.7700\ncurrent episode reward: 20.0000\nepisodes: 2406\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18603.0 seconds (5.17 hours)\n\nTimestep: 4380000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2412\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18647.8 seconds (5.18 hours)\n\nTimestep: 4390000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2418\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18692.3 seconds (5.19 hours)\n\nTimestep: 4400000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2424\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18737.0 seconds (5.20 hours)\n\nTimestep: 4410000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2430\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18782.1 seconds (5.22 hours)\n\nTimestep: 4420000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2435\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18827.1 seconds (5.23 hours)\n\nTimestep: 4430000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2441\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18871.1 seconds (5.24 hours)\n\nTimestep: 4440000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2447\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18916.1 seconds (5.25 hours)\n\nTimestep: 4450000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2453\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18960.1 seconds (5.27 hours)\n\nTimestep: 4460000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.7700\ncurrent episode reward: 20.0000\nepisodes: 2459\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19003.8 seconds (5.28 hours)\n\nTimestep: 4470000\nmean reward (100 episodes): 20.6400\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2465\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19048.3 seconds (5.29 hours)\n\nTimestep: 4480000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2471\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19092.6 seconds (5.30 hours)\n\nTimestep: 4490000\nmean reward (100 episodes): 20.6500\nbest mean reward: 20.7700\ncurrent episode reward: 20.0000\nepisodes: 2477\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19137.0 seconds (5.32 hours)\n\nTimestep: 4500000\nmean reward (100 episodes): 20.6200\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2483\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19181.6 seconds (5.33 hours)\n\nTimestep: 4510000\nmean reward (100 episodes): 20.6500\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2489\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19226.7 seconds (5.34 hours)\n\nTimestep: 4520000\nmean reward (100 episodes): 20.6500\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2495\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19271.3 seconds (5.35 hours)\n\nTimestep: 4530000\nmean reward (100 episodes): 20.6300\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2500\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19315.9 seconds (5.37 hours)\n\nTimestep: 4540000\nmean reward (100 episodes): 20.6500\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2506\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19359.7 seconds (5.38 hours)\n\nTimestep: 4550000\nmean reward (100 episodes): 20.6200\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2512\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19404.7 seconds (5.39 hours)\n\nTimestep: 4560000\nmean reward (100 episodes): 20.6200\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2518\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19449.0 seconds (5.40 hours)\n\nTimestep: 4570000\nmean reward (100 episodes): 20.6200\nbest mean reward: 20.7700\ncurrent episode reward: 20.0000\nepisodes: 2524\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19493.7 seconds (5.41 hours)\n\nTimestep: 4580000\nmean reward (100 episodes): 20.6200\nbest mean reward: 20.7700\ncurrent episode reward: 20.0000\nepisodes: 2530\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19537.8 seconds (5.43 hours)\n\nTimestep: 4590000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2536\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19582.3 seconds (5.44 hours)\n\nTimestep: 4600000\nmean reward (100 episodes): 20.6300\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2541\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19627.3 seconds (5.45 hours)\n\nTimestep: 4610000\nmean reward (100 episodes): 20.6100\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2547\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19672.4 seconds (5.46 hours)\n\nTimestep: 4620000\nmean reward (100 episodes): 20.6100\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2553\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19717.6 seconds (5.48 hours)\n\nTimestep: 4630000\nmean reward (100 episodes): 20.6100\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2559\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19762.0 seconds (5.49 hours)\n\nTimestep: 4640000\nmean reward (100 episodes): 20.6000\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2565\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19806.8 seconds (5.50 hours)\n\nTimestep: 4650000\nmean reward (100 episodes): 20.5800\nbest mean reward: 20.7700\ncurrent episode reward: 20.0000\nepisodes: 2571\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19851.8 seconds (5.51 hours)\n\nTimestep: 4660000\nmean reward (100 episodes): 20.6000\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2576\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19897.4 seconds (5.53 hours)\n\nTimestep: 4670000\nmean reward (100 episodes): 20.6200\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2582\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19941.2 seconds (5.54 hours)\n\nTimestep: 4680000\nmean reward (100 episodes): 20.5800\nbest mean reward: 20.7700\ncurrent episode reward: 20.0000\nepisodes: 2588\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19985.1 seconds (5.55 hours)\n\nTimestep: 4690000\nmean reward (100 episodes): 20.5800\nbest mean reward: 20.7700\ncurrent episode reward: 20.0000\nepisodes: 2594\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20028.8 seconds (5.56 hours)\n\nTimestep: 4700000\nmean reward (100 episodes): 20.5700\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2600\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20073.0 seconds (5.58 hours)\n\nTimestep: 4710000\nmean reward (100 episodes): 20.5500\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2606\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20117.4 seconds (5.59 hours)\n\nTimestep: 4720000\nmean reward (100 episodes): 20.5700\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2612\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20162.0 seconds (5.60 hours)\n\nTimestep: 4730000\nmean reward (100 episodes): 20.5500\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2618\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20206.6 seconds (5.61 hours)\n\nTimestep: 4740000\nmean reward (100 episodes): 20.5700\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2624\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20250.8 seconds (5.63 hours)\n\nTimestep: 4750000\nmean reward (100 episodes): 20.5800\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2629\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20295.0 seconds (5.64 hours)\n\nTimestep: 4760000\nmean reward (100 episodes): 20.5800\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2635\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20340.1 seconds (5.65 hours)\n\nTimestep: 4770000\nmean reward (100 episodes): 20.6000\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2641\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20384.8 seconds (5.66 hours)\n\nTimestep: 4780000\nmean reward (100 episodes): 20.6200\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2647\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20430.2 seconds (5.68 hours)\n\nTimestep: 4790000\nmean reward (100 episodes): 20.6300\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2653\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20474.9 seconds (5.69 hours)\n\nTimestep: 4800000\nmean reward (100 episodes): 20.6400\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2659\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20519.6 seconds (5.70 hours)\n\nTimestep: 4810000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2665\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20563.7 seconds (5.71 hours)\n\nTimestep: 4820000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2671\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20607.8 seconds (5.72 hours)\n\nTimestep: 4830000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2677\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20652.3 seconds (5.74 hours)\n\nTimestep: 4840000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2682\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20696.6 seconds (5.75 hours)\n\nTimestep: 4850000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2688\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20741.1 seconds (5.76 hours)\n\nTimestep: 4860000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.7700\ncurrent episode reward: 20.0000\nepisodes: 2694\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20785.9 seconds (5.77 hours)\n\nTimestep: 4870000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.7700\ncurrent episode reward: 20.0000\nepisodes: 2700\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20830.6 seconds (5.79 hours)\n\nTimestep: 4880000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2706\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20875.4 seconds (5.80 hours)\n\nTimestep: 4890000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2712\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20919.7 seconds (5.81 hours)\n\nTimestep: 4900000\nmean reward (100 episodes): 20.6400\nbest mean reward: 20.7700\ncurrent episode reward: 13.0000\nepisodes: 2718\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20964.0 seconds (5.82 hours)\n\nTimestep: 4910000\nmean reward (100 episodes): 20.6300\nbest mean reward: 20.7700\ncurrent episode reward: 20.0000\nepisodes: 2723\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21008.1 seconds (5.84 hours)\n\nTimestep: 4920000\nmean reward (100 episodes): 20.6200\nbest mean reward: 20.7700\ncurrent episode reward: 20.0000\nepisodes: 2729\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21052.4 seconds (5.85 hours)\n\nTimestep: 4930000\nmean reward (100 episodes): 20.6100\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2735\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21096.3 seconds (5.86 hours)\n\nTimestep: 4940000\nmean reward (100 episodes): 20.6300\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2741\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21140.4 seconds (5.87 hours)\n\nTimestep: 4950000\nmean reward (100 episodes): 20.6200\nbest mean reward: 20.7700\ncurrent episode reward: 20.0000\nepisodes: 2747\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21184.2 seconds (5.88 hours)\n\nTimestep: 4960000\nmean reward (100 episodes): 20.6200\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2753\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21228.5 seconds (5.90 hours)\n\nTimestep: 4970000\nmean reward (100 episodes): 20.6100\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2759\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21273.4 seconds (5.91 hours)\n\nTimestep: 4980000\nmean reward (100 episodes): 20.6100\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2765\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21318.1 seconds (5.92 hours)\n\nTimestep: 4990000\nmean reward (100 episodes): 20.6200\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2770\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21361.9 seconds (5.93 hours)\n\nTimestep: 5000000\nmean reward (100 episodes): 20.5700\nbest mean reward: 20.7700\ncurrent episode reward: 19.0000\nepisodes: 2776\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21406.0 seconds (5.95 hours)\n\nTimestep: 5010000\nmean reward (100 episodes): 20.5900\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2782\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21450.2 seconds (5.96 hours)\n\nTimestep: 5020000\nmean reward (100 episodes): 20.6000\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2788\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21494.8 seconds (5.97 hours)\n\nTimestep: 5030000\nmean reward (100 episodes): 20.5900\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2793\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21540.0 seconds (5.98 hours)\n\nTimestep: 5040000\nmean reward (100 episodes): 20.5900\nbest mean reward: 20.7700\ncurrent episode reward: 20.0000\nepisodes: 2799\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21584.2 seconds (6.00 hours)\n\nTimestep: 5050000\nmean reward (100 episodes): 20.6000\nbest mean reward: 20.7700\ncurrent episode reward: 20.0000\nepisodes: 2805\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21629.1 seconds (6.01 hours)\n\nTimestep: 5060000\nmean reward (100 episodes): 20.5800\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2811\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21673.1 seconds (6.02 hours)\n\nTimestep: 5070000\nmean reward (100 episodes): 20.5900\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2817\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21717.2 seconds (6.03 hours)\n\nTimestep: 5080000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2823\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21762.0 seconds (6.05 hours)\n\nTimestep: 5090000\nmean reward (100 episodes): 20.6400\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2829\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21806.2 seconds (6.06 hours)\n\nTimestep: 5100000\nmean reward (100 episodes): 20.6500\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2835\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21850.8 seconds (6.07 hours)\n\nTimestep: 5110000\nmean reward (100 episodes): 20.6500\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2840\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21895.7 seconds (6.08 hours)\n\nTimestep: 5120000\nmean reward (100 episodes): 20.6500\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2846\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21940.6 seconds (6.09 hours)\n\nTimestep: 5130000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2852\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21985.5 seconds (6.11 hours)\n\nTimestep: 5140000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2858\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22029.7 seconds (6.12 hours)\n\nTimestep: 5150000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2864\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22074.2 seconds (6.13 hours)\n\nTimestep: 5160000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2870\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22118.9 seconds (6.14 hours)\n\nTimestep: 5170000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2876\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22162.8 seconds (6.16 hours)\n\nTimestep: 5180000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 2882\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22207.0 seconds (6.17 hours)\n\nTimestep: 5190000\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.7800\ncurrent episode reward: 20.0000\nepisodes: 2888\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22251.0 seconds (6.18 hours)\n\nTimestep: 5200000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.7800\ncurrent episode reward: 21.0000\nepisodes: 2893\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22295.2 seconds (6.19 hours)\n\nTimestep: 5210000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.7800\ncurrent episode reward: 21.0000\nepisodes: 2899\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22338.5 seconds (6.21 hours)\n\nTimestep: 5220000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.7800\ncurrent episode reward: 21.0000\nepisodes: 2905\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22382.4 seconds (6.22 hours)\n\nTimestep: 5230000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.7800\ncurrent episode reward: 21.0000\nepisodes: 2911\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22427.3 seconds (6.23 hours)\n\nTimestep: 5240000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.7800\ncurrent episode reward: 21.0000\nepisodes: 2917\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22471.9 seconds (6.24 hours)\n\nTimestep: 5250000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.7800\ncurrent episode reward: 20.0000\nepisodes: 2923\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22517.5 seconds (6.25 hours)\n\nTimestep: 5260000\nmean reward (100 episodes): 20.7900\nbest mean reward: 20.8000\ncurrent episode reward: 20.0000\nepisodes: 2929\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22562.0 seconds (6.27 hours)\n\nTimestep: 5270000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8100\ncurrent episode reward: 20.0000\nepisodes: 2935\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22606.1 seconds (6.28 hours)\n\nTimestep: 5280000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8100\ncurrent episode reward: 21.0000\nepisodes: 2941\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22650.6 seconds (6.29 hours)\n\nTimestep: 5290000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8100\ncurrent episode reward: 21.0000\nepisodes: 2947\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22695.1 seconds (6.30 hours)\n\nTimestep: 5300000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8100\ncurrent episode reward: 21.0000\nepisodes: 2953\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22739.2 seconds (6.32 hours)\n\nTimestep: 5310000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 2958\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22783.3 seconds (6.33 hours)\n\nTimestep: 5320000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 2964\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22827.9 seconds (6.34 hours)\n\nTimestep: 5330000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 2970\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22873.0 seconds (6.35 hours)\n\nTimestep: 5340000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 2976\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22917.5 seconds (6.37 hours)\n\nTimestep: 5350000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 2982\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22961.9 seconds (6.38 hours)\n\nTimestep: 5360000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 2988\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23006.2 seconds (6.39 hours)\n\nTimestep: 5370000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 2994\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23050.9 seconds (6.40 hours)\n\nTimestep: 5380000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3000\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23098.1 seconds (6.42 hours)\n\nTimestep: 5390000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.8200\ncurrent episode reward: 19.0000\nepisodes: 3006\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23145.0 seconds (6.43 hours)\n\nTimestep: 5400000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3012\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23190.2 seconds (6.44 hours)\n\nTimestep: 5410000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3018\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23234.9 seconds (6.45 hours)\n\nTimestep: 5420000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3024\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23279.1 seconds (6.47 hours)\n\nTimestep: 5430000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3030\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23322.6 seconds (6.48 hours)\n\nTimestep: 5440000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3035\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23367.2 seconds (6.49 hours)\n\nTimestep: 5450000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3041\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23411.6 seconds (6.50 hours)\n\nTimestep: 5460000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3047\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23455.9 seconds (6.52 hours)\n\nTimestep: 5470000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3053\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23500.6 seconds (6.53 hours)\n\nTimestep: 5480000\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3059\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23545.2 seconds (6.54 hours)\n\nTimestep: 5490000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3065\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23589.4 seconds (6.55 hours)\n\nTimestep: 5500000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.8200\ncurrent episode reward: 18.0000\nepisodes: 3071\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23634.0 seconds (6.57 hours)\n\nTimestep: 5510000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3077\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23677.6 seconds (6.58 hours)\n\nTimestep: 5520000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3083\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23722.5 seconds (6.59 hours)\n\nTimestep: 5530000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3089\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23767.1 seconds (6.60 hours)\n\nTimestep: 5540000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3094\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23811.9 seconds (6.61 hours)\n\nTimestep: 5550000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3100\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23856.5 seconds (6.63 hours)\n\nTimestep: 5560000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3106\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23901.2 seconds (6.64 hours)\n\nTimestep: 5570000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3112\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23945.0 seconds (6.65 hours)\n\nTimestep: 5580000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3118\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23989.6 seconds (6.66 hours)\n\nTimestep: 5590000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3124\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24033.6 seconds (6.68 hours)\n\nTimestep: 5600000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3130\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24077.7 seconds (6.69 hours)\n\nTimestep: 5610000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3136\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24121.9 seconds (6.70 hours)\n\nTimestep: 5620000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3142\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24166.7 seconds (6.71 hours)\n\nTimestep: 5630000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3148\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24210.9 seconds (6.73 hours)\n\nTimestep: 5640000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3154\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24255.8 seconds (6.74 hours)\n\nTimestep: 5650000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3160\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24301.2 seconds (6.75 hours)\n\nTimestep: 5660000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3166\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24345.6 seconds (6.76 hours)\n\nTimestep: 5670000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3172\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24389.6 seconds (6.77 hours)\n\nTimestep: 5680000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3178\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24434.2 seconds (6.79 hours)\n\nTimestep: 5690000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3183\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24478.8 seconds (6.80 hours)\n\nTimestep: 5700000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3189\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24522.7 seconds (6.81 hours)\n\nTimestep: 5710000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3195\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24567.6 seconds (6.82 hours)\n\nTimestep: 5720000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3201\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24613.4 seconds (6.84 hours)\n\nTimestep: 5730000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3207\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24658.2 seconds (6.85 hours)\n\nTimestep: 5740000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3213\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24702.6 seconds (6.86 hours)\n\nTimestep: 5750000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3219\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24746.9 seconds (6.87 hours)\n\nTimestep: 5760000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3225\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24791.4 seconds (6.89 hours)\n\nTimestep: 5770000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3231\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24835.4 seconds (6.90 hours)\n\nTimestep: 5780000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3237\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24879.2 seconds (6.91 hours)\n\nTimestep: 5790000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3243\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24923.4 seconds (6.92 hours)\n\nTimestep: 5800000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3248\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24967.8 seconds (6.94 hours)\n\nTimestep: 5810000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3254\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25012.3 seconds (6.95 hours)\n\nTimestep: 5820000\nmean reward (100 episodes): 20.6300\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3260\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25057.1 seconds (6.96 hours)\n\nTimestep: 5830000\nmean reward (100 episodes): 20.6300\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3266\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25102.3 seconds (6.97 hours)\n\nTimestep: 5840000\nmean reward (100 episodes): 20.6100\nbest mean reward: 20.8200\ncurrent episode reward: 18.0000\nepisodes: 3272\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25146.8 seconds (6.99 hours)\n\nTimestep: 5850000\nmean reward (100 episodes): 20.6200\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3278\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25191.7 seconds (7.00 hours)\n\nTimestep: 5860000\nmean reward (100 episodes): 20.6200\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3284\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25235.8 seconds (7.01 hours)\n\nTimestep: 5870000\nmean reward (100 episodes): 20.6300\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3290\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25280.9 seconds (7.02 hours)\n\nTimestep: 5880000\nmean reward (100 episodes): 20.6200\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3296\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25325.4 seconds (7.03 hours)\n\nTimestep: 5890000\nmean reward (100 episodes): 20.6300\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3301\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25369.3 seconds (7.05 hours)\n\nTimestep: 5900000\nmean reward (100 episodes): 20.6300\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3308\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25414.1 seconds (7.06 hours)\n\nTimestep: 5910000\nmean reward (100 episodes): 20.6500\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3314\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25459.0 seconds (7.07 hours)\n\nTimestep: 5920000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3320\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25503.0 seconds (7.08 hours)\n\nTimestep: 5930000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3325\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25547.3 seconds (7.10 hours)\n\nTimestep: 5940000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3332\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25591.6 seconds (7.11 hours)\n\nTimestep: 5950000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3337\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25635.8 seconds (7.12 hours)\n\nTimestep: 5960000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3343\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25679.9 seconds (7.13 hours)\n\nTimestep: 5970000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3349\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25723.5 seconds (7.15 hours)\n\nTimestep: 5980000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3355\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25768.2 seconds (7.16 hours)\n\nTimestep: 5990000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3361\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25812.2 seconds (7.17 hours)\n\nTimestep: 6000000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3367\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25857.4 seconds (7.18 hours)\n\nTimestep: 6010000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3373\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25902.1 seconds (7.20 hours)\n\nTimestep: 6020000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3379\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25946.7 seconds (7.21 hours)\n\nTimestep: 6030000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3385\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25991.7 seconds (7.22 hours)\n\nTimestep: 6040000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3391\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26036.9 seconds (7.23 hours)\n\nTimestep: 6050000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3397\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26081.5 seconds (7.24 hours)\n\nTimestep: 6060000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3403\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26126.1 seconds (7.26 hours)\n\nTimestep: 6070000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3409\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26170.6 seconds (7.27 hours)\n\nTimestep: 6080000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3415\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26215.6 seconds (7.28 hours)\n\nTimestep: 6090000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3421\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26260.1 seconds (7.29 hours)\n\nTimestep: 6100000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3427\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26304.8 seconds (7.31 hours)\n\nTimestep: 6110000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3433\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26349.1 seconds (7.32 hours)\n\nTimestep: 6120000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3438\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26393.3 seconds (7.33 hours)\n\nTimestep: 6130000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3444\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26437.5 seconds (7.34 hours)\n\nTimestep: 6140000\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3450\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26482.4 seconds (7.36 hours)\n\nTimestep: 6150000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8200\ncurrent episode reward: 19.0000\nepisodes: 3456\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26527.0 seconds (7.37 hours)\n\nTimestep: 6160000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3462\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26571.0 seconds (7.38 hours)\n\nTimestep: 6170000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3468\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26615.7 seconds (7.39 hours)\n\nTimestep: 6180000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3474\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26660.2 seconds (7.41 hours)\n\nTimestep: 6190000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3480\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26705.0 seconds (7.42 hours)\n\nTimestep: 6200000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3486\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26749.7 seconds (7.43 hours)\n\nTimestep: 6210000\nmean reward (100 episodes): 20.7900\nbest mean reward: 20.8200\ncurrent episode reward: 20.0000\nepisodes: 3492\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26793.9 seconds (7.44 hours)\n\nTimestep: 6220000\nmean reward (100 episodes): 20.8200\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3498\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26838.9 seconds (7.46 hours)\n\nTimestep: 6230000\nmean reward (100 episodes): 20.8300\nbest mean reward: 20.8300\ncurrent episode reward: 21.0000\nepisodes: 3504\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26882.6 seconds (7.47 hours)\n\nTimestep: 6240000\nmean reward (100 episodes): 20.8200\nbest mean reward: 20.8300\ncurrent episode reward: 21.0000\nepisodes: 3510\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26927.2 seconds (7.48 hours)\n\nTimestep: 6250000\nmean reward (100 episodes): 20.8200\nbest mean reward: 20.8300\ncurrent episode reward: 21.0000\nepisodes: 3516\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26972.4 seconds (7.49 hours)\n\nTimestep: 6260000\nmean reward (100 episodes): 20.8400\nbest mean reward: 20.8400\ncurrent episode reward: 21.0000\nepisodes: 3522\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27016.9 seconds (7.50 hours)\n\nTimestep: 6270000\nmean reward (100 episodes): 20.8400\nbest mean reward: 20.8400\ncurrent episode reward: 21.0000\nepisodes: 3528\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27060.9 seconds (7.52 hours)\n\nTimestep: 6280000\nmean reward (100 episodes): 20.8200\nbest mean reward: 20.8500\ncurrent episode reward: 20.0000\nepisodes: 3534\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27105.0 seconds (7.53 hours)\n\nTimestep: 6290000\nmean reward (100 episodes): 20.8500\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 3540\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27148.9 seconds (7.54 hours)\n\nTimestep: 6300000\nmean reward (100 episodes): 20.8600\nbest mean reward: 20.8600\ncurrent episode reward: 21.0000\nepisodes: 3546\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27193.3 seconds (7.55 hours)\n\nTimestep: 6310000\nmean reward (100 episodes): 20.8500\nbest mean reward: 20.8600\ncurrent episode reward: 20.0000\nepisodes: 3552\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27237.3 seconds (7.57 hours)\n\nTimestep: 6320000\nmean reward (100 episodes): 20.8600\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3558\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27281.9 seconds (7.58 hours)\n\nTimestep: 6330000\nmean reward (100 episodes): 20.8400\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3564\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27325.7 seconds (7.59 hours)\n\nTimestep: 6340000\nmean reward (100 episodes): 20.8300\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3570\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27369.8 seconds (7.60 hours)\n\nTimestep: 6350000\nmean reward (100 episodes): 20.8100\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3576\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27414.4 seconds (7.62 hours)\n\nTimestep: 6360000\nmean reward (100 episodes): 20.8100\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 3582\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27458.4 seconds (7.63 hours)\n\nTimestep: 6370000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3588\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27503.4 seconds (7.64 hours)\n\nTimestep: 6380000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 3594\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27548.3 seconds (7.65 hours)\n\nTimestep: 6390000\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3600\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27592.7 seconds (7.66 hours)\n\nTimestep: 6400000\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3606\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27637.4 seconds (7.68 hours)\n\nTimestep: 6410000\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3612\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27681.7 seconds (7.69 hours)\n\nTimestep: 6420000\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3618\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27726.0 seconds (7.70 hours)\n\nTimestep: 6430000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3624\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27770.6 seconds (7.71 hours)\n\nTimestep: 6440000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3630\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27814.8 seconds (7.73 hours)\n\nTimestep: 6450000\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3636\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27858.8 seconds (7.74 hours)\n\nTimestep: 6460000\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3642\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27903.0 seconds (7.75 hours)\n\nTimestep: 6470000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3648\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27948.0 seconds (7.76 hours)\n\nTimestep: 6480000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3654\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27991.2 seconds (7.78 hours)\n\nTimestep: 6490000\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3660\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28035.5 seconds (7.79 hours)\n\nTimestep: 6500000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3665\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28079.4 seconds (7.80 hours)\n\nTimestep: 6510000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3671\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28124.1 seconds (7.81 hours)\n\nTimestep: 6520000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3677\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28168.6 seconds (7.82 hours)\n\nTimestep: 6530000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3683\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28212.7 seconds (7.84 hours)\n\nTimestep: 6540000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 3689\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28257.4 seconds (7.85 hours)\n\nTimestep: 6550000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3695\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28302.2 seconds (7.86 hours)\n\nTimestep: 6560000\nmean reward (100 episodes): 20.7900\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3701\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28346.2 seconds (7.87 hours)\n\nTimestep: 6570000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3707\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28390.1 seconds (7.89 hours)\n\nTimestep: 6580000\nmean reward (100 episodes): 20.7900\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3713\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28435.2 seconds (7.90 hours)\n\nTimestep: 6590000\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 3719\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28479.8 seconds (7.91 hours)\n\nTimestep: 6600000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3725\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28524.6 seconds (7.92 hours)\n\nTimestep: 6610000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3730\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28568.7 seconds (7.94 hours)\n\nTimestep: 6620000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3736\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28613.6 seconds (7.95 hours)\n\nTimestep: 6630000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3742\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28657.6 seconds (7.96 hours)\n\nTimestep: 6640000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3748\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28702.7 seconds (7.97 hours)\n\nTimestep: 6650000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3754\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28747.4 seconds (7.99 hours)\n\nTimestep: 6660000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3760\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28791.7 seconds (8.00 hours)\n\nTimestep: 6670000\nmean reward (100 episodes): 20.8100\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3766\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28835.6 seconds (8.01 hours)\n\nTimestep: 6680000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 3772\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28880.1 seconds (8.02 hours)\n\nTimestep: 6690000\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 3778\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28924.9 seconds (8.03 hours)\n\nTimestep: 6700000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3784\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28969.0 seconds (8.05 hours)\n\nTimestep: 6710000\nmean reward (100 episodes): 20.7900\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3790\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29012.3 seconds (8.06 hours)\n\nTimestep: 6720000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 3796\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29057.1 seconds (8.07 hours)\n\nTimestep: 6730000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3802\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29101.8 seconds (8.08 hours)\n\nTimestep: 6740000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3808\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29145.9 seconds (8.10 hours)\n\nTimestep: 6750000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3814\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29190.6 seconds (8.11 hours)\n\nTimestep: 6760000\nmean reward (100 episodes): 20.8200\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3820\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29234.1 seconds (8.12 hours)\n\nTimestep: 6770000\nmean reward (100 episodes): 20.8200\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 3826\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29278.9 seconds (8.13 hours)\n\nTimestep: 6780000\nmean reward (100 episodes): 20.8100\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 3832\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29323.3 seconds (8.15 hours)\n\nTimestep: 6790000\nmean reward (100 episodes): 20.8200\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 3838\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29367.1 seconds (8.16 hours)\n\nTimestep: 6800000\nmean reward (100 episodes): 20.8100\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3844\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29411.2 seconds (8.17 hours)\n\nTimestep: 6810000\nmean reward (100 episodes): 20.8100\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 3850\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29455.8 seconds (8.18 hours)\n\nTimestep: 6820000\nmean reward (100 episodes): 20.8100\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3856\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29500.3 seconds (8.19 hours)\n\nTimestep: 6830000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3862\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29545.0 seconds (8.21 hours)\n\nTimestep: 6840000\nmean reward (100 episodes): 20.7900\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3868\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29588.2 seconds (8.22 hours)\n\nTimestep: 6850000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3874\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29632.6 seconds (8.23 hours)\n\nTimestep: 6860000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 3880\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29677.2 seconds (8.24 hours)\n\nTimestep: 6870000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3886\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29721.4 seconds (8.26 hours)\n\nTimestep: 6880000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3892\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29766.7 seconds (8.27 hours)\n\nTimestep: 6890000\nmean reward (100 episodes): 20.8200\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3898\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29811.1 seconds (8.28 hours)\n\nTimestep: 6900000\nmean reward (100 episodes): 20.8200\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3904\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29854.5 seconds (8.29 hours)\n\nTimestep: 6910000\nmean reward (100 episodes): 20.7900\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3909\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29899.6 seconds (8.31 hours)\n\nTimestep: 6920000\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3915\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29944.3 seconds (8.32 hours)\n\nTimestep: 6930000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 3921\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29988.9 seconds (8.33 hours)\n\nTimestep: 6940000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3927\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30033.7 seconds (8.34 hours)\n\nTimestep: 6950000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3933\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30077.9 seconds (8.35 hours)\n\nTimestep: 6960000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3939\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30122.4 seconds (8.37 hours)\n\nTimestep: 6970000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3945\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30167.2 seconds (8.38 hours)\n\nTimestep: 6980000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3951\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30211.4 seconds (8.39 hours)\n\nTimestep: 6990000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3957\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30256.2 seconds (8.40 hours)\n\nTimestep: 7000000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3963\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30301.3 seconds (8.42 hours)\n\nTimestep: 7010000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3969\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30345.6 seconds (8.43 hours)\n\nTimestep: 7020000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3975\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30390.7 seconds (8.44 hours)\n\nTimestep: 7030000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 3981\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30435.9 seconds (8.45 hours)\n\nTimestep: 7040000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3987\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30480.3 seconds (8.47 hours)\n\nTimestep: 7050000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 3992\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30524.6 seconds (8.48 hours)\n\nTimestep: 7060000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 3998\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30568.8 seconds (8.49 hours)\n\nTimestep: 7070000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4004\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30617.8 seconds (8.50 hours)\n\nTimestep: 7080000\nmean reward (100 episodes): 20.6500\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 4010\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30662.3 seconds (8.52 hours)\n\nTimestep: 7090000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4016\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30706.8 seconds (8.53 hours)\n\nTimestep: 7100000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4022\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30750.7 seconds (8.54 hours)\n\nTimestep: 7110000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 4028\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30795.1 seconds (8.55 hours)\n\nTimestep: 7120000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4034\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30839.1 seconds (8.57 hours)\n\nTimestep: 7130000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4040\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30883.6 seconds (8.58 hours)\n\nTimestep: 7140000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4046\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30927.6 seconds (8.59 hours)\n\nTimestep: 7150000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4052\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30972.7 seconds (8.60 hours)\n\nTimestep: 7160000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4058\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31017.1 seconds (8.62 hours)\n\nTimestep: 7170000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 4064\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31061.5 seconds (8.63 hours)\n\nTimestep: 7180000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 4070\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31106.0 seconds (8.64 hours)\n\nTimestep: 7190000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4076\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31150.1 seconds (8.65 hours)\n\nTimestep: 7200000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4082\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31194.2 seconds (8.67 hours)\n\nTimestep: 7210000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4088\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31238.7 seconds (8.68 hours)\n\nTimestep: 7220000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4094\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31283.2 seconds (8.69 hours)\n\nTimestep: 7230000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4100\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31328.0 seconds (8.70 hours)\n\nTimestep: 7240000\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.8700\ncurrent episode reward: 20.0000\nepisodes: 4106\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31372.2 seconds (8.71 hours)\n\nTimestep: 7250000\nmean reward (100 episodes): 20.7900\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4111\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31416.0 seconds (8.73 hours)\n\nTimestep: 7260000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4117\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31460.2 seconds (8.74 hours)\n\nTimestep: 7270000\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4123\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31504.4 seconds (8.75 hours)\n\nTimestep: 7280000\nmean reward (100 episodes): 20.7900\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4129\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31548.3 seconds (8.76 hours)\n\nTimestep: 7290000\nmean reward (100 episodes): 20.7900\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4135\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31593.1 seconds (8.78 hours)\n\nTimestep: 7300000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4141\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31637.1 seconds (8.79 hours)\n\nTimestep: 7310000\nmean reward (100 episodes): 20.7900\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4147\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31681.2 seconds (8.80 hours)\n\nTimestep: 7320000\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4153\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31725.8 seconds (8.81 hours)\n\nTimestep: 7330000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4159\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31770.0 seconds (8.83 hours)\n\nTimestep: 7340000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4165\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31813.6 seconds (8.84 hours)\n\nTimestep: 7350000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4171\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31858.6 seconds (8.85 hours)\n\nTimestep: 7360000\nmean reward (100 episodes): 20.7900\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4177\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31903.2 seconds (8.86 hours)\n\nTimestep: 7370000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4183\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31947.3 seconds (8.87 hours)\n\nTimestep: 7380000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4189\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31992.0 seconds (8.89 hours)\n\nTimestep: 7390000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4194\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32036.5 seconds (8.90 hours)\n\nTimestep: 7400000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4200\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32081.0 seconds (8.91 hours)\n\nTimestep: 7410000\nmean reward (100 episodes): 20.7900\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4206\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32124.9 seconds (8.92 hours)\n\nTimestep: 7420000\nmean reward (100 episodes): 20.8100\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4212\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32168.9 seconds (8.94 hours)\n\nTimestep: 7430000\nmean reward (100 episodes): 20.8400\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4218\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32213.5 seconds (8.95 hours)\n\nTimestep: 7440000\nmean reward (100 episodes): 20.8500\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4225\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32257.8 seconds (8.96 hours)\n\nTimestep: 7450000\nmean reward (100 episodes): 20.8400\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4230\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32302.0 seconds (8.97 hours)\n\nTimestep: 7460000\nmean reward (100 episodes): 20.8200\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4236\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32346.4 seconds (8.99 hours)\n\nTimestep: 7470000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4242\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32390.3 seconds (9.00 hours)\n\nTimestep: 7476493\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.8700\ncurrent episode reward: 21.0000\nepisodes: 4246\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32419.2 seconds (9.01 hours)\n"
  },
  {
    "path": "dqn/logs_text/Pong_s002.text",
    "content": "('AVAILABLE GPUS: ', [u'device: 0, name: TITAN X (Pascal), pci bus id: 0000:01:00.0'])\ntask = Task<env_id=PongNoFrameskip-v3 trials=2 max_timesteps=40000000 max_seconds=None reward_floor=-20.7 reward_ceiling=21.0>\n\nTimestep: 60000\nmean reward (100 episodes): -20.2698\nbest mean reward: -inf\ncurrent episode reward: -19.0000\nepisodes: 63\nexploration: 0.94600\nlearning_rate: 0.00010\nelapsed time: 94.9 seconds (0.03 hours)\n\nTimestep: 70000\nmean reward (100 episodes): -20.3200\nbest mean reward: -inf\ncurrent episode reward: -20.0000\nepisodes: 75\nexploration: 0.93700\nlearning_rate: 0.00010\nelapsed time: 129.6 seconds (0.04 hours)\n\nTimestep: 80000\nmean reward (100 episodes): -20.3372\nbest mean reward: -inf\ncurrent episode reward: -20.0000\nepisodes: 86\nexploration: 0.92800\nlearning_rate: 0.00010\nelapsed time: 161.8 seconds (0.04 hours)\n\nTimestep: 90000\nmean reward (100 episodes): -20.2917\nbest mean reward: -inf\ncurrent episode reward: -19.0000\nepisodes: 96\nexploration: 0.91900\nlearning_rate: 0.00010\nelapsed time: 193.8 seconds (0.05 hours)\n\nTimestep: 100000\nmean reward (100 episodes): -20.2700\nbest mean reward: -20.2500\ncurrent episode reward: -21.0000\nepisodes: 107\nexploration: 0.91000\nlearning_rate: 0.00010\nelapsed time: 226.2 seconds (0.06 hours)\n\nTimestep: 110000\nmean reward (100 episodes): -20.2300\nbest mean reward: -20.2300\ncurrent episode reward: -21.0000\nepisodes: 118\nexploration: 0.90100\nlearning_rate: 0.00010\nelapsed time: 258.8 seconds (0.07 hours)\n\nTimestep: 120000\nmean reward (100 episodes): -20.2600\nbest mean reward: -20.2300\ncurrent episode reward: -19.0000\nepisodes: 129\nexploration: 0.89200\nlearning_rate: 0.00010\nelapsed time: 293.9 seconds (0.08 hours)\n\nTimestep: 130000\nmean reward (100 episodes): -20.2300\nbest mean reward: -20.2300\ncurrent episode reward: -19.0000\nepisodes: 139\nexploration: 0.88300\nlearning_rate: 0.00010\nelapsed time: 327.3 seconds (0.09 hours)\n\nTimestep: 140000\nmean reward (100 episodes): -20.2600\nbest mean reward: -20.2200\ncurrent episode reward: -21.0000\nepisodes: 150\nexploration: 0.87400\nlearning_rate: 0.00010\nelapsed time: 360.2 seconds (0.10 hours)\n\nTimestep: 150000\nmean reward (100 episodes): -20.2800\nbest mean reward: -20.2200\ncurrent episode reward: -21.0000\nepisodes: 160\nexploration: 0.86500\nlearning_rate: 0.00010\nelapsed time: 393.3 seconds (0.11 hours)\n\nTimestep: 160000\nmean reward (100 episodes): -20.3200\nbest mean reward: -20.2200\ncurrent episode reward: -20.0000\nepisodes: 170\nexploration: 0.85600\nlearning_rate: 0.00010\nelapsed time: 426.0 seconds (0.12 hours)\n\nTimestep: 170000\nmean reward (100 episodes): -20.2500\nbest mean reward: -20.2200\ncurrent episode reward: -20.0000\nepisodes: 181\nexploration: 0.84700\nlearning_rate: 0.00010\nelapsed time: 459.4 seconds (0.13 hours)\n\nTimestep: 180000\nmean reward (100 episodes): -20.2900\nbest mean reward: -20.2200\ncurrent episode reward: -21.0000\nepisodes: 192\nexploration: 0.83800\nlearning_rate: 0.00010\nelapsed time: 492.5 seconds (0.14 hours)\n\nTimestep: 190000\nmean reward (100 episodes): -20.3400\nbest mean reward: -20.2200\ncurrent episode reward: -21.0000\nepisodes: 203\nexploration: 0.82900\nlearning_rate: 0.00010\nelapsed time: 526.1 seconds (0.15 hours)\n\nTimestep: 200000\nmean reward (100 episodes): -20.3200\nbest mean reward: -20.2200\ncurrent episode reward: -21.0000\nepisodes: 214\nexploration: 0.82000\nlearning_rate: 0.00010\nelapsed time: 559.4 seconds (0.16 hours)\n\nTimestep: 210000\nmean reward (100 episodes): -20.3300\nbest mean reward: -20.2200\ncurrent episode reward: -19.0000\nepisodes: 225\nexploration: 0.81100\nlearning_rate: 0.00010\nelapsed time: 596.1 seconds (0.17 hours)\n\nTimestep: 220000\nmean reward (100 episodes): -20.3400\nbest mean reward: -20.2200\ncurrent episode reward: -20.0000\nepisodes: 235\nexploration: 0.80200\nlearning_rate: 0.00010\nelapsed time: 630.7 seconds (0.18 hours)\n\nTimestep: 230000\nmean reward (100 episodes): -20.3300\nbest mean reward: -20.2200\ncurrent episode reward: -20.0000\nepisodes: 247\nexploration: 0.79300\nlearning_rate: 0.00010\nelapsed time: 664.8 seconds (0.18 hours)\n\nTimestep: 240000\nmean reward (100 episodes): -20.3100\nbest mean reward: -20.2200\ncurrent episode reward: -20.0000\nepisodes: 257\nexploration: 0.78400\nlearning_rate: 0.00010\nelapsed time: 698.7 seconds (0.19 hours)\n\nTimestep: 250000\nmean reward (100 episodes): -20.2600\nbest mean reward: -20.2200\ncurrent episode reward: -18.0000\nepisodes: 268\nexploration: 0.77500\nlearning_rate: 0.00010\nelapsed time: 733.0 seconds (0.20 hours)\n\nTimestep: 260000\nmean reward (100 episodes): -20.2700\nbest mean reward: -20.2200\ncurrent episode reward: -21.0000\nepisodes: 278\nexploration: 0.76600\nlearning_rate: 0.00010\nelapsed time: 767.2 seconds (0.21 hours)\n\nTimestep: 270000\nmean reward (100 episodes): -20.2400\nbest mean reward: -20.2200\ncurrent episode reward: -20.0000\nepisodes: 289\nexploration: 0.75700\nlearning_rate: 0.00010\nelapsed time: 802.2 seconds (0.22 hours)\n\nTimestep: 280000\nmean reward (100 episodes): -20.2500\nbest mean reward: -20.2200\ncurrent episode reward: -20.0000\nepisodes: 300\nexploration: 0.74800\nlearning_rate: 0.00010\nelapsed time: 836.9 seconds (0.23 hours)\n\nTimestep: 290000\nmean reward (100 episodes): -20.2100\nbest mean reward: -20.2000\ncurrent episode reward: -20.0000\nepisodes: 310\nexploration: 0.73900\nlearning_rate: 0.00010\nelapsed time: 871.8 seconds (0.24 hours)\n\nTimestep: 300000\nmean reward (100 episodes): -20.1600\nbest mean reward: -20.1600\ncurrent episode reward: -17.0000\nepisodes: 321\nexploration: 0.73000\nlearning_rate: 0.00010\nelapsed time: 907.2 seconds (0.25 hours)\n\nTimestep: 310000\nmean reward (100 episodes): -20.2200\nbest mean reward: -20.1600\ncurrent episode reward: -21.0000\nepisodes: 332\nexploration: 0.72100\nlearning_rate: 0.00010\nelapsed time: 942.4 seconds (0.26 hours)\n\nTimestep: 320000\nmean reward (100 episodes): -20.1900\nbest mean reward: -20.1600\ncurrent episode reward: -20.0000\nepisodes: 343\nexploration: 0.71200\nlearning_rate: 0.00010\nelapsed time: 979.5 seconds (0.27 hours)\n\nTimestep: 330000\nmean reward (100 episodes): -20.2600\nbest mean reward: -20.1600\ncurrent episode reward: -20.0000\nepisodes: 354\nexploration: 0.70300\nlearning_rate: 0.00010\nelapsed time: 1016.4 seconds (0.28 hours)\n\nTimestep: 340000\nmean reward (100 episodes): -20.2100\nbest mean reward: -20.1600\ncurrent episode reward: -21.0000\nepisodes: 364\nexploration: 0.69400\nlearning_rate: 0.00010\nelapsed time: 1052.1 seconds (0.29 hours)\n\nTimestep: 350000\nmean reward (100 episodes): -20.2600\nbest mean reward: -20.1600\ncurrent episode reward: -21.0000\nepisodes: 373\nexploration: 0.68500\nlearning_rate: 0.00010\nelapsed time: 1088.3 seconds (0.30 hours)\n\nTimestep: 360000\nmean reward (100 episodes): -20.1700\nbest mean reward: -20.1600\ncurrent episode reward: -19.0000\nepisodes: 383\nexploration: 0.67600\nlearning_rate: 0.00010\nelapsed time: 1124.8 seconds (0.31 hours)\n\nTimestep: 370000\nmean reward (100 episodes): -20.0700\nbest mean reward: -20.0700\ncurrent episode reward: -19.0000\nepisodes: 392\nexploration: 0.66700\nlearning_rate: 0.00010\nelapsed time: 1160.2 seconds (0.32 hours)\n\nTimestep: 380000\nmean reward (100 episodes): -20.0500\nbest mean reward: -20.0400\ncurrent episode reward: -19.0000\nepisodes: 402\nexploration: 0.65800\nlearning_rate: 0.00010\nelapsed time: 1196.5 seconds (0.33 hours)\n\nTimestep: 390000\nmean reward (100 episodes): -20.0100\nbest mean reward: -20.0100\ncurrent episode reward: -19.0000\nepisodes: 411\nexploration: 0.64900\nlearning_rate: 0.00010\nelapsed time: 1232.8 seconds (0.34 hours)\n\nTimestep: 400000\nmean reward (100 episodes): -19.9100\nbest mean reward: -19.9100\ncurrent episode reward: -18.0000\nepisodes: 419\nexploration: 0.64000\nlearning_rate: 0.00010\nelapsed time: 1268.4 seconds (0.35 hours)\n\nTimestep: 410000\nmean reward (100 episodes): -19.8200\nbest mean reward: -19.8200\ncurrent episode reward: -19.0000\nepisodes: 427\nexploration: 0.63100\nlearning_rate: 0.00010\nelapsed time: 1305.2 seconds (0.36 hours)\n\nTimestep: 420000\nmean reward (100 episodes): -19.6600\nbest mean reward: -19.6600\ncurrent episode reward: -20.0000\nepisodes: 435\nexploration: 0.62200\nlearning_rate: 0.00010\nelapsed time: 1342.3 seconds (0.37 hours)\n\nTimestep: 430000\nmean reward (100 episodes): -19.5600\nbest mean reward: -19.5600\ncurrent episode reward: -15.0000\nepisodes: 442\nexploration: 0.61300\nlearning_rate: 0.00010\nelapsed time: 1379.1 seconds (0.38 hours)\n\nTimestep: 440000\nmean reward (100 episodes): -19.3700\nbest mean reward: -19.3700\ncurrent episode reward: -17.0000\nepisodes: 450\nexploration: 0.60400\nlearning_rate: 0.00010\nelapsed time: 1416.0 seconds (0.39 hours)\n\nTimestep: 450000\nmean reward (100 episodes): -19.1800\nbest mean reward: -19.1800\ncurrent episode reward: -19.0000\nepisodes: 457\nexploration: 0.59500\nlearning_rate: 0.00010\nelapsed time: 1452.7 seconds (0.40 hours)\n\nTimestep: 460000\nmean reward (100 episodes): -19.0900\nbest mean reward: -19.0900\ncurrent episode reward: -19.0000\nepisodes: 464\nexploration: 0.58600\nlearning_rate: 0.00010\nelapsed time: 1489.6 seconds (0.41 hours)\n\nTimestep: 470000\nmean reward (100 episodes): -18.9000\nbest mean reward: -18.8900\ncurrent episode reward: -20.0000\nepisodes: 471\nexploration: 0.57700\nlearning_rate: 0.00010\nelapsed time: 1527.1 seconds (0.42 hours)\n\nTimestep: 480000\nmean reward (100 episodes): -18.7800\nbest mean reward: -18.7800\ncurrent episode reward: -18.0000\nepisodes: 478\nexploration: 0.56800\nlearning_rate: 0.00010\nelapsed time: 1564.7 seconds (0.43 hours)\n\nTimestep: 490000\nmean reward (100 episodes): -18.7200\nbest mean reward: -18.7100\ncurrent episode reward: -19.0000\nepisodes: 484\nexploration: 0.55900\nlearning_rate: 0.00010\nelapsed time: 1602.2 seconds (0.45 hours)\n\nTimestep: 500000\nmean reward (100 episodes): -18.5100\nbest mean reward: -18.5100\ncurrent episode reward: -17.0000\nepisodes: 491\nexploration: 0.55000\nlearning_rate: 0.00010\nelapsed time: 1639.9 seconds (0.46 hours)\n\nTimestep: 510000\nmean reward (100 episodes): -18.4400\nbest mean reward: -18.4400\ncurrent episode reward: -21.0000\nepisodes: 497\nexploration: 0.54100\nlearning_rate: 0.00010\nelapsed time: 1677.4 seconds (0.47 hours)\n\nTimestep: 520000\nmean reward (100 episodes): -18.1800\nbest mean reward: -18.1800\ncurrent episode reward: -14.0000\nepisodes: 504\nexploration: 0.53200\nlearning_rate: 0.00010\nelapsed time: 1715.6 seconds (0.48 hours)\n\nTimestep: 530000\nmean reward (100 episodes): -18.0500\nbest mean reward: -18.0500\ncurrent episode reward: -19.0000\nepisodes: 510\nexploration: 0.52300\nlearning_rate: 0.00010\nelapsed time: 1753.7 seconds (0.49 hours)\n\nTimestep: 540000\nmean reward (100 episodes): -17.9400\nbest mean reward: -17.9400\ncurrent episode reward: -18.0000\nepisodes: 516\nexploration: 0.51400\nlearning_rate: 0.00010\nelapsed time: 1796.4 seconds (0.50 hours)\n\nTimestep: 550000\nmean reward (100 episodes): -17.8800\nbest mean reward: -17.8800\ncurrent episode reward: -17.0000\nepisodes: 523\nexploration: 0.50500\nlearning_rate: 0.00010\nelapsed time: 1834.9 seconds (0.51 hours)\n\nTimestep: 560000\nmean reward (100 episodes): -17.8700\nbest mean reward: -17.8600\ncurrent episode reward: -18.0000\nepisodes: 529\nexploration: 0.49600\nlearning_rate: 0.00010\nelapsed time: 1874.4 seconds (0.52 hours)\n\nTimestep: 570000\nmean reward (100 episodes): -17.7800\nbest mean reward: -17.7800\ncurrent episode reward: -16.0000\nepisodes: 535\nexploration: 0.48700\nlearning_rate: 0.00010\nelapsed time: 1913.1 seconds (0.53 hours)\n\nTimestep: 580000\nmean reward (100 episodes): -17.6300\nbest mean reward: -17.6300\ncurrent episode reward: -18.0000\nepisodes: 540\nexploration: 0.47800\nlearning_rate: 0.00010\nelapsed time: 1952.6 seconds (0.54 hours)\n\nTimestep: 590000\nmean reward (100 episodes): -17.7300\nbest mean reward: -17.6300\ncurrent episode reward: -18.0000\nepisodes: 546\nexploration: 0.46900\nlearning_rate: 0.00010\nelapsed time: 1992.0 seconds (0.55 hours)\n\nTimestep: 600000\nmean reward (100 episodes): -17.6600\nbest mean reward: -17.6300\ncurrent episode reward: -17.0000\nepisodes: 553\nexploration: 0.46000\nlearning_rate: 0.00010\nelapsed time: 2030.8 seconds (0.56 hours)\n\nTimestep: 610000\nmean reward (100 episodes): -17.5900\nbest mean reward: -17.5900\ncurrent episode reward: -16.0000\nepisodes: 559\nexploration: 0.45100\nlearning_rate: 0.00010\nelapsed time: 2070.4 seconds (0.58 hours)\n\nTimestep: 620000\nmean reward (100 episodes): -17.4900\nbest mean reward: -17.4900\ncurrent episode reward: -15.0000\nepisodes: 565\nexploration: 0.44200\nlearning_rate: 0.00010\nelapsed time: 2110.1 seconds (0.59 hours)\n\nTimestep: 630000\nmean reward (100 episodes): -17.4700\nbest mean reward: -17.4300\ncurrent episode reward: -17.0000\nepisodes: 570\nexploration: 0.43300\nlearning_rate: 0.00010\nelapsed time: 2150.2 seconds (0.60 hours)\n\nTimestep: 640000\nmean reward (100 episodes): -17.3500\nbest mean reward: -17.3500\ncurrent episode reward: -16.0000\nepisodes: 576\nexploration: 0.42400\nlearning_rate: 0.00010\nelapsed time: 2189.7 seconds (0.61 hours)\n\nTimestep: 650000\nmean reward (100 episodes): -17.2800\nbest mean reward: -17.2800\ncurrent episode reward: -16.0000\nepisodes: 582\nexploration: 0.41500\nlearning_rate: 0.00010\nelapsed time: 2229.2 seconds (0.62 hours)\n\nTimestep: 660000\nmean reward (100 episodes): -17.1800\nbest mean reward: -17.1400\ncurrent episode reward: -15.0000\nepisodes: 588\nexploration: 0.40600\nlearning_rate: 0.00010\nelapsed time: 2269.4 seconds (0.63 hours)\n\nTimestep: 670000\nmean reward (100 episodes): -17.1100\nbest mean reward: -17.1100\ncurrent episode reward: -18.0000\nepisodes: 593\nexploration: 0.39700\nlearning_rate: 0.00010\nelapsed time: 2309.9 seconds (0.64 hours)\n\nTimestep: 680000\nmean reward (100 episodes): -16.9900\nbest mean reward: -16.9900\ncurrent episode reward: -16.0000\nepisodes: 598\nexploration: 0.38800\nlearning_rate: 0.00010\nelapsed time: 2350.7 seconds (0.65 hours)\n\nTimestep: 690000\nmean reward (100 episodes): -17.0600\nbest mean reward: -16.9900\ncurrent episode reward: -18.0000\nepisodes: 604\nexploration: 0.37900\nlearning_rate: 0.00010\nelapsed time: 2391.0 seconds (0.66 hours)\n\nTimestep: 700000\nmean reward (100 episodes): -16.9400\nbest mean reward: -16.9400\ncurrent episode reward: -15.0000\nepisodes: 609\nexploration: 0.37000\nlearning_rate: 0.00010\nelapsed time: 2431.2 seconds (0.68 hours)\n\nTimestep: 710000\nmean reward (100 episodes): -16.8400\nbest mean reward: -16.8400\ncurrent episode reward: -14.0000\nepisodes: 615\nexploration: 0.36100\nlearning_rate: 0.00010\nelapsed time: 2472.0 seconds (0.69 hours)\n\nTimestep: 720000\nmean reward (100 episodes): -16.7800\nbest mean reward: -16.7800\ncurrent episode reward: -14.0000\nepisodes: 620\nexploration: 0.35200\nlearning_rate: 0.00010\nelapsed time: 2512.1 seconds (0.70 hours)\n\nTimestep: 730000\nmean reward (100 episodes): -16.7400\nbest mean reward: -16.7200\ncurrent episode reward: -19.0000\nepisodes: 625\nexploration: 0.34300\nlearning_rate: 0.00010\nelapsed time: 2552.9 seconds (0.71 hours)\n\nTimestep: 740000\nmean reward (100 episodes): -16.6500\nbest mean reward: -16.6500\ncurrent episode reward: -15.0000\nepisodes: 630\nexploration: 0.33400\nlearning_rate: 0.00010\nelapsed time: 2594.3 seconds (0.72 hours)\n\nTimestep: 750000\nmean reward (100 episodes): -16.6100\nbest mean reward: -16.6100\ncurrent episode reward: -14.0000\nepisodes: 635\nexploration: 0.32500\nlearning_rate: 0.00010\nelapsed time: 2634.8 seconds (0.73 hours)\n\nTimestep: 760000\nmean reward (100 episodes): -16.5100\nbest mean reward: -16.5100\ncurrent episode reward: -15.0000\nepisodes: 641\nexploration: 0.31600\nlearning_rate: 0.00010\nelapsed time: 2675.7 seconds (0.74 hours)\n\nTimestep: 770000\nmean reward (100 episodes): -16.3300\nbest mean reward: -16.3000\ncurrent episode reward: -20.0000\nepisodes: 645\nexploration: 0.30700\nlearning_rate: 0.00010\nelapsed time: 2716.1 seconds (0.75 hours)\n\nTimestep: 780000\nmean reward (100 episodes): -16.3700\nbest mean reward: -16.3000\ncurrent episode reward: -17.0000\nepisodes: 651\nexploration: 0.29800\nlearning_rate: 0.00010\nelapsed time: 2757.8 seconds (0.77 hours)\n\nTimestep: 790000\nmean reward (100 episodes): -16.3100\nbest mean reward: -16.3000\ncurrent episode reward: -12.0000\nepisodes: 656\nexploration: 0.28900\nlearning_rate: 0.00010\nelapsed time: 2799.1 seconds (0.78 hours)\n\nTimestep: 800000\nmean reward (100 episodes): -16.1700\nbest mean reward: -16.1700\ncurrent episode reward: -14.0000\nepisodes: 660\nexploration: 0.28000\nlearning_rate: 0.00010\nelapsed time: 2840.1 seconds (0.79 hours)\n\nTimestep: 810000\nmean reward (100 episodes): -16.0200\nbest mean reward: -16.0200\ncurrent episode reward: -10.0000\nepisodes: 665\nexploration: 0.27100\nlearning_rate: 0.00010\nelapsed time: 2881.3 seconds (0.80 hours)\n\nTimestep: 820000\nmean reward (100 episodes): -16.0000\nbest mean reward: -15.9300\ncurrent episode reward: -19.0000\nepisodes: 670\nexploration: 0.26200\nlearning_rate: 0.00010\nelapsed time: 2921.7 seconds (0.81 hours)\n\nTimestep: 830000\nmean reward (100 episodes): -15.8600\nbest mean reward: -15.8600\ncurrent episode reward: -7.0000\nepisodes: 674\nexploration: 0.25300\nlearning_rate: 0.00010\nelapsed time: 2964.6 seconds (0.82 hours)\n\nTimestep: 840000\nmean reward (100 episodes): -15.7700\nbest mean reward: -15.7700\ncurrent episode reward: -17.0000\nepisodes: 679\nexploration: 0.24400\nlearning_rate: 0.00010\nelapsed time: 3006.9 seconds (0.84 hours)\n\nTimestep: 850000\nmean reward (100 episodes): -15.6100\nbest mean reward: -15.5700\ncurrent episode reward: -17.0000\nepisodes: 684\nexploration: 0.23500\nlearning_rate: 0.00010\nelapsed time: 3049.9 seconds (0.85 hours)\n\nTimestep: 860000\nmean reward (100 episodes): -15.5700\nbest mean reward: -15.5500\ncurrent episode reward: -17.0000\nepisodes: 688\nexploration: 0.22600\nlearning_rate: 0.00010\nelapsed time: 3092.4 seconds (0.86 hours)\n\nTimestep: 870000\nmean reward (100 episodes): -15.4300\nbest mean reward: -15.4300\ncurrent episode reward: -18.0000\nepisodes: 693\nexploration: 0.21700\nlearning_rate: 0.00010\nelapsed time: 3135.1 seconds (0.87 hours)\n\nTimestep: 880000\nmean reward (100 episodes): -15.3800\nbest mean reward: -15.3800\ncurrent episode reward: -16.0000\nepisodes: 698\nexploration: 0.20800\nlearning_rate: 0.00010\nelapsed time: 3177.3 seconds (0.88 hours)\n\nTimestep: 890000\nmean reward (100 episodes): -15.0500\nbest mean reward: -15.0500\ncurrent episode reward: -11.0000\nepisodes: 702\nexploration: 0.19900\nlearning_rate: 0.00010\nelapsed time: 3220.1 seconds (0.89 hours)\n\nTimestep: 900000\nmean reward (100 episodes): -14.9600\nbest mean reward: -14.9600\ncurrent episode reward: -11.0000\nepisodes: 706\nexploration: 0.19000\nlearning_rate: 0.00010\nelapsed time: 3262.6 seconds (0.91 hours)\n\nTimestep: 910000\nmean reward (100 episodes): -14.8600\nbest mean reward: -14.8600\ncurrent episode reward: -15.0000\nepisodes: 710\nexploration: 0.18100\nlearning_rate: 0.00010\nelapsed time: 3305.2 seconds (0.92 hours)\n\nTimestep: 920000\nmean reward (100 episodes): -14.6700\nbest mean reward: -14.6700\ncurrent episode reward: -12.0000\nepisodes: 714\nexploration: 0.17200\nlearning_rate: 0.00010\nelapsed time: 3347.7 seconds (0.93 hours)\n\nTimestep: 930000\nmean reward (100 episodes): -14.4400\nbest mean reward: -14.4200\ncurrent episode reward: -17.0000\nepisodes: 718\nexploration: 0.16300\nlearning_rate: 0.00010\nelapsed time: 3390.1 seconds (0.94 hours)\n\nTimestep: 940000\nmean reward (100 episodes): -14.2700\nbest mean reward: -14.2700\ncurrent episode reward: -17.0000\nepisodes: 723\nexploration: 0.15400\nlearning_rate: 0.00010\nelapsed time: 3432.8 seconds (0.95 hours)\n\nTimestep: 950000\nmean reward (100 episodes): -14.0000\nbest mean reward: -14.0000\ncurrent episode reward: -7.0000\nepisodes: 726\nexploration: 0.14500\nlearning_rate: 0.00010\nelapsed time: 3475.0 seconds (0.97 hours)\n\nTimestep: 960000\nmean reward (100 episodes): -13.8200\nbest mean reward: -13.8200\ncurrent episode reward: -11.0000\nepisodes: 729\nexploration: 0.13600\nlearning_rate: 0.00010\nelapsed time: 3525.6 seconds (0.98 hours)\n\nTimestep: 970000\nmean reward (100 episodes): -13.4900\nbest mean reward: -13.4900\ncurrent episode reward: -8.0000\nepisodes: 732\nexploration: 0.12700\nlearning_rate: 0.00010\nelapsed time: 3569.4 seconds (0.99 hours)\n\nTimestep: 980000\nmean reward (100 episodes): -13.0900\nbest mean reward: -13.0900\ncurrent episode reward: -9.0000\nepisodes: 736\nexploration: 0.11800\nlearning_rate: 0.00010\nelapsed time: 3613.5 seconds (1.00 hours)\n\nTimestep: 990000\nmean reward (100 episodes): -12.8700\nbest mean reward: -12.8700\ncurrent episode reward: -6.0000\nepisodes: 739\nexploration: 0.10900\nlearning_rate: 0.00010\nelapsed time: 3657.3 seconds (1.02 hours)\n\nTimestep: 1000000\nmean reward (100 episodes): -12.6400\nbest mean reward: -12.6400\ncurrent episode reward: -13.0000\nepisodes: 742\nexploration: 0.10000\nlearning_rate: 0.00010\nelapsed time: 3701.7 seconds (1.03 hours)\n\nTimestep: 1010000\nmean reward (100 episodes): -12.3800\nbest mean reward: -12.3800\ncurrent episode reward: -11.0000\nepisodes: 745\nexploration: 0.09967\nlearning_rate: 0.00010\nelapsed time: 3746.4 seconds (1.04 hours)\n\nTimestep: 1020000\nmean reward (100 episodes): -12.1000\nbest mean reward: -12.1000\ncurrent episode reward: -1.0000\nepisodes: 748\nexploration: 0.09935\nlearning_rate: 0.00010\nelapsed time: 3791.4 seconds (1.05 hours)\n\nTimestep: 1030000\nmean reward (100 episodes): -11.7200\nbest mean reward: -11.7200\ncurrent episode reward: 5.0000\nepisodes: 752\nexploration: 0.09902\nlearning_rate: 0.00010\nelapsed time: 3835.4 seconds (1.07 hours)\n\nTimestep: 1040000\nmean reward (100 episodes): -11.4400\nbest mean reward: -11.4400\ncurrent episode reward: -8.0000\nepisodes: 755\nexploration: 0.09869\nlearning_rate: 0.00010\nelapsed time: 3879.8 seconds (1.08 hours)\n\nTimestep: 1050000\nmean reward (100 episodes): -11.2000\nbest mean reward: -11.2000\ncurrent episode reward: 2.0000\nepisodes: 757\nexploration: 0.09836\nlearning_rate: 0.00010\nelapsed time: 3922.8 seconds (1.09 hours)\n\nTimestep: 1060000\nmean reward (100 episodes): -11.0700\nbest mean reward: -11.0700\ncurrent episode reward: -8.0000\nepisodes: 761\nexploration: 0.09804\nlearning_rate: 0.00009\nelapsed time: 3966.6 seconds (1.10 hours)\n\nTimestep: 1070000\nmean reward (100 episodes): -10.8300\nbest mean reward: -10.8300\ncurrent episode reward: -11.0000\nepisodes: 764\nexploration: 0.09771\nlearning_rate: 0.00009\nelapsed time: 4010.2 seconds (1.11 hours)\n\nTimestep: 1080000\nmean reward (100 episodes): -10.6500\nbest mean reward: -10.6500\ncurrent episode reward: -2.0000\nepisodes: 766\nexploration: 0.09738\nlearning_rate: 0.00009\nelapsed time: 4053.1 seconds (1.13 hours)\n\nTimestep: 1090000\nmean reward (100 episodes): -10.1300\nbest mean reward: -10.1300\ncurrent episode reward: -5.0000\nepisodes: 769\nexploration: 0.09705\nlearning_rate: 0.00009\nelapsed time: 4096.3 seconds (1.14 hours)\n\nTimestep: 1100000\nmean reward (100 episodes): -9.7500\nbest mean reward: -9.7500\ncurrent episode reward: -5.0000\nepisodes: 772\nexploration: 0.09673\nlearning_rate: 0.00009\nelapsed time: 4139.3 seconds (1.15 hours)\n\nTimestep: 1110000\nmean reward (100 episodes): -9.6100\nbest mean reward: -9.6100\ncurrent episode reward: 4.0000\nepisodes: 774\nexploration: 0.09640\nlearning_rate: 0.00009\nelapsed time: 4181.9 seconds (1.16 hours)\n\nTimestep: 1120000\nmean reward (100 episodes): -9.2900\nbest mean reward: -9.2900\ncurrent episode reward: -9.0000\nepisodes: 778\nexploration: 0.09607\nlearning_rate: 0.00009\nelapsed time: 4225.3 seconds (1.17 hours)\n\nTimestep: 1130000\nmean reward (100 episodes): -9.2400\nbest mean reward: -9.2400\ncurrent episode reward: -2.0000\nepisodes: 781\nexploration: 0.09575\nlearning_rate: 0.00009\nelapsed time: 4268.0 seconds (1.19 hours)\n\nTimestep: 1140000\nmean reward (100 episodes): -9.1700\nbest mean reward: -9.1700\ncurrent episode reward: -10.0000\nepisodes: 785\nexploration: 0.09542\nlearning_rate: 0.00009\nelapsed time: 4311.9 seconds (1.20 hours)\n\nTimestep: 1150000\nmean reward (100 episodes): -8.7800\nbest mean reward: -8.7800\ncurrent episode reward: 4.0000\nepisodes: 788\nexploration: 0.09509\nlearning_rate: 0.00009\nelapsed time: 4355.9 seconds (1.21 hours)\n\nTimestep: 1160000\nmean reward (100 episodes): -8.5600\nbest mean reward: -8.5600\ncurrent episode reward: -12.0000\nepisodes: 791\nexploration: 0.09476\nlearning_rate: 0.00009\nelapsed time: 4399.1 seconds (1.22 hours)\n\nTimestep: 1170000\nmean reward (100 episodes): -8.1000\nbest mean reward: -8.1000\ncurrent episode reward: 2.0000\nepisodes: 794\nexploration: 0.09444\nlearning_rate: 0.00009\nelapsed time: 4442.8 seconds (1.23 hours)\n\nTimestep: 1180000\nmean reward (100 episodes): -7.6700\nbest mean reward: -7.6700\ncurrent episode reward: 7.0000\nepisodes: 796\nexploration: 0.09411\nlearning_rate: 0.00009\nelapsed time: 4486.1 seconds (1.25 hours)\n\nTimestep: 1190000\nmean reward (100 episodes): -7.3200\nbest mean reward: -7.3200\ncurrent episode reward: 3.0000\nepisodes: 800\nexploration: 0.09378\nlearning_rate: 0.00009\nelapsed time: 4529.9 seconds (1.26 hours)\n\nTimestep: 1200000\nmean reward (100 episodes): -7.1200\nbest mean reward: -7.1200\ncurrent episode reward: 4.0000\nepisodes: 802\nexploration: 0.09345\nlearning_rate: 0.00009\nelapsed time: 4573.0 seconds (1.27 hours)\n\nTimestep: 1210000\nmean reward (100 episodes): -6.6100\nbest mean reward: -6.6100\ncurrent episode reward: 5.0000\nepisodes: 805\nexploration: 0.09313\nlearning_rate: 0.00009\nelapsed time: 4616.7 seconds (1.28 hours)\n\nTimestep: 1220000\nmean reward (100 episodes): -6.3200\nbest mean reward: -6.3200\ncurrent episode reward: -6.0000\nepisodes: 808\nexploration: 0.09280\nlearning_rate: 0.00009\nelapsed time: 4660.3 seconds (1.29 hours)\n\nTimestep: 1230000\nmean reward (100 episodes): -6.0000\nbest mean reward: -6.0000\ncurrent episode reward: 8.0000\nepisodes: 810\nexploration: 0.09247\nlearning_rate: 0.00009\nelapsed time: 4704.4 seconds (1.31 hours)\n\nTimestep: 1240000\nmean reward (100 episodes): -5.5100\nbest mean reward: -5.5100\ncurrent episode reward: 1.0000\nepisodes: 813\nexploration: 0.09215\nlearning_rate: 0.00009\nelapsed time: 4747.3 seconds (1.32 hours)\n\nTimestep: 1250000\nmean reward (100 episodes): -5.2700\nbest mean reward: -5.2700\ncurrent episode reward: -3.0000\nepisodes: 816\nexploration: 0.09182\nlearning_rate: 0.00009\nelapsed time: 4790.4 seconds (1.33 hours)\n\nTimestep: 1260000\nmean reward (100 episodes): -4.9800\nbest mean reward: -4.9800\ncurrent episode reward: 1.0000\nepisodes: 819\nexploration: 0.09149\nlearning_rate: 0.00009\nelapsed time: 4834.1 seconds (1.34 hours)\n\nTimestep: 1270000\nmean reward (100 episodes): -4.5700\nbest mean reward: -4.5700\ncurrent episode reward: -7.0000\nepisodes: 822\nexploration: 0.09116\nlearning_rate: 0.00009\nelapsed time: 4877.7 seconds (1.35 hours)\n\nTimestep: 1280000\nmean reward (100 episodes): -4.2700\nbest mean reward: -4.2700\ncurrent episode reward: 1.0000\nepisodes: 825\nexploration: 0.09084\nlearning_rate: 0.00009\nelapsed time: 4922.1 seconds (1.37 hours)\n\nTimestep: 1290000\nmean reward (100 episodes): -4.1400\nbest mean reward: -4.1300\ncurrent episode reward: -10.0000\nepisodes: 828\nexploration: 0.09051\nlearning_rate: 0.00009\nelapsed time: 4966.1 seconds (1.38 hours)\n\nTimestep: 1300000\nmean reward (100 episodes): -3.8700\nbest mean reward: -3.8700\ncurrent episode reward: 9.0000\nepisodes: 830\nexploration: 0.09018\nlearning_rate: 0.00009\nelapsed time: 5010.1 seconds (1.39 hours)\n\nTimestep: 1310000\nmean reward (100 episodes): -3.6800\nbest mean reward: -3.6800\ncurrent episode reward: 4.0000\nepisodes: 833\nexploration: 0.08985\nlearning_rate: 0.00009\nelapsed time: 5054.3 seconds (1.40 hours)\n\nTimestep: 1320000\nmean reward (100 episodes): -3.3900\nbest mean reward: -3.3900\ncurrent episode reward: 4.0000\nepisodes: 835\nexploration: 0.08953\nlearning_rate: 0.00009\nelapsed time: 5097.5 seconds (1.42 hours)\n\nTimestep: 1330000\nmean reward (100 episodes): -3.1100\nbest mean reward: -3.1100\ncurrent episode reward: -5.0000\nepisodes: 838\nexploration: 0.08920\nlearning_rate: 0.00009\nelapsed time: 5140.8 seconds (1.43 hours)\n\nTimestep: 1340000\nmean reward (100 episodes): -3.0100\nbest mean reward: -2.9700\ncurrent episode reward: -6.0000\nepisodes: 841\nexploration: 0.08887\nlearning_rate: 0.00009\nelapsed time: 5184.4 seconds (1.44 hours)\n\nTimestep: 1350000\nmean reward (100 episodes): -2.7600\nbest mean reward: -2.7600\ncurrent episode reward: 7.0000\nepisodes: 843\nexploration: 0.08855\nlearning_rate: 0.00009\nelapsed time: 5228.5 seconds (1.45 hours)\n\nTimestep: 1360000\nmean reward (100 episodes): -2.4400\nbest mean reward: -2.4400\ncurrent episode reward: 7.0000\nepisodes: 846\nexploration: 0.08822\nlearning_rate: 0.00009\nelapsed time: 5272.0 seconds (1.46 hours)\n\nTimestep: 1370000\nmean reward (100 episodes): -2.0000\nbest mean reward: -2.0000\ncurrent episode reward: 7.0000\nepisodes: 849\nexploration: 0.08789\nlearning_rate: 0.00009\nelapsed time: 5315.2 seconds (1.48 hours)\n\nTimestep: 1380000\nmean reward (100 episodes): -1.7700\nbest mean reward: -1.7700\ncurrent episode reward: 3.0000\nepisodes: 851\nexploration: 0.08756\nlearning_rate: 0.00009\nelapsed time: 5359.0 seconds (1.49 hours)\n\nTimestep: 1390000\nmean reward (100 episodes): -1.4500\nbest mean reward: -1.4500\ncurrent episode reward: 6.0000\nepisodes: 854\nexploration: 0.08724\nlearning_rate: 0.00009\nelapsed time: 5402.7 seconds (1.50 hours)\n\nTimestep: 1400000\nmean reward (100 episodes): -1.3300\nbest mean reward: -1.3300\ncurrent episode reward: -2.0000\nepisodes: 856\nexploration: 0.08691\nlearning_rate: 0.00009\nelapsed time: 5446.7 seconds (1.51 hours)\n\nTimestep: 1410000\nmean reward (100 episodes): -1.1500\nbest mean reward: -1.1500\ncurrent episode reward: 5.0000\nepisodes: 858\nexploration: 0.08658\nlearning_rate: 0.00009\nelapsed time: 5489.5 seconds (1.52 hours)\n\nTimestep: 1420000\nmean reward (100 episodes): -0.7600\nbest mean reward: -0.7600\ncurrent episode reward: 2.0000\nepisodes: 861\nexploration: 0.08625\nlearning_rate: 0.00009\nelapsed time: 5533.9 seconds (1.54 hours)\n\nTimestep: 1430000\nmean reward (100 episodes): -0.6400\nbest mean reward: -0.6400\ncurrent episode reward: 3.0000\nepisodes: 863\nexploration: 0.08593\nlearning_rate: 0.00009\nelapsed time: 5576.9 seconds (1.55 hours)\n\nTimestep: 1440000\nmean reward (100 episodes): -0.4000\nbest mean reward: -0.4000\ncurrent episode reward: 9.0000\nepisodes: 865\nexploration: 0.08560\nlearning_rate: 0.00009\nelapsed time: 5620.3 seconds (1.56 hours)\n\nTimestep: 1450000\nmean reward (100 episodes): -0.4100\nbest mean reward: -0.3400\ncurrent episode reward: -4.0000\nepisodes: 868\nexploration: 0.08527\nlearning_rate: 0.00009\nelapsed time: 5664.4 seconds (1.57 hours)\n\nTimestep: 1460000\nmean reward (100 episodes): -0.1000\nbest mean reward: -0.1000\ncurrent episode reward: 5.0000\nepisodes: 871\nexploration: 0.08495\nlearning_rate: 0.00009\nelapsed time: 5708.1 seconds (1.59 hours)\n\nTimestep: 1470000\nmean reward (100 episodes): 0.2000\nbest mean reward: 0.2000\ncurrent episode reward: 5.0000\nepisodes: 874\nexploration: 0.08462\nlearning_rate: 0.00009\nelapsed time: 5751.8 seconds (1.60 hours)\n\nTimestep: 1480000\nmean reward (100 episodes): 0.4100\nbest mean reward: 0.4100\ncurrent episode reward: 6.0000\nepisodes: 877\nexploration: 0.08429\nlearning_rate: 0.00009\nelapsed time: 5795.8 seconds (1.61 hours)\n\nTimestep: 1490000\nmean reward (100 episodes): 1.1200\nbest mean reward: 1.1200\ncurrent episode reward: 12.0000\nepisodes: 880\nexploration: 0.08396\nlearning_rate: 0.00009\nelapsed time: 5839.3 seconds (1.62 hours)\n\nTimestep: 1500000\nmean reward (100 episodes): 1.5100\nbest mean reward: 1.5100\ncurrent episode reward: -5.0000\nepisodes: 883\nexploration: 0.08364\nlearning_rate: 0.00009\nelapsed time: 5882.8 seconds (1.63 hours)\n\nTimestep: 1510000\nmean reward (100 episodes): 1.9000\nbest mean reward: 1.9000\ncurrent episode reward: -2.0000\nepisodes: 885\nexploration: 0.08331\nlearning_rate: 0.00009\nelapsed time: 5926.4 seconds (1.65 hours)\n\nTimestep: 1520000\nmean reward (100 episodes): 2.2300\nbest mean reward: 2.2500\ncurrent episode reward: 2.0000\nepisodes: 888\nexploration: 0.08298\nlearning_rate: 0.00009\nelapsed time: 5970.3 seconds (1.66 hours)\n\nTimestep: 1530000\nmean reward (100 episodes): 2.5600\nbest mean reward: 2.5600\ncurrent episode reward: 5.0000\nepisodes: 891\nexploration: 0.08265\nlearning_rate: 0.00009\nelapsed time: 6014.2 seconds (1.67 hours)\n\nTimestep: 1540000\nmean reward (100 episodes): 2.7700\nbest mean reward: 2.7700\ncurrent episode reward: 10.0000\nepisodes: 893\nexploration: 0.08233\nlearning_rate: 0.00009\nelapsed time: 6057.9 seconds (1.68 hours)\n\nTimestep: 1550000\nmean reward (100 episodes): 3.1100\nbest mean reward: 3.1100\ncurrent episode reward: 16.0000\nepisodes: 897\nexploration: 0.08200\nlearning_rate: 0.00009\nelapsed time: 6100.9 seconds (1.69 hours)\n\nTimestep: 1560000\nmean reward (100 episodes): 3.5800\nbest mean reward: 3.5800\ncurrent episode reward: 6.0000\nepisodes: 900\nexploration: 0.08167\nlearning_rate: 0.00009\nelapsed time: 6145.0 seconds (1.71 hours)\n\nTimestep: 1570000\nmean reward (100 episodes): 3.8500\nbest mean reward: 3.8500\ncurrent episode reward: 14.0000\nepisodes: 904\nexploration: 0.08135\nlearning_rate: 0.00009\nelapsed time: 6189.0 seconds (1.72 hours)\n\nTimestep: 1580000\nmean reward (100 episodes): 4.2200\nbest mean reward: 4.2200\ncurrent episode reward: 9.0000\nepisodes: 907\nexploration: 0.08102\nlearning_rate: 0.00009\nelapsed time: 6231.7 seconds (1.73 hours)\n\nTimestep: 1590000\nmean reward (100 episodes): 4.7500\nbest mean reward: 4.7500\ncurrent episode reward: 12.0000\nepisodes: 911\nexploration: 0.08069\nlearning_rate: 0.00009\nelapsed time: 6275.7 seconds (1.74 hours)\n\nTimestep: 1600000\nmean reward (100 episodes): 5.0700\nbest mean reward: 5.0700\ncurrent episode reward: 12.0000\nepisodes: 915\nexploration: 0.08036\nlearning_rate: 0.00009\nelapsed time: 6320.2 seconds (1.76 hours)\n\nTimestep: 1610000\nmean reward (100 episodes): 5.7100\nbest mean reward: 5.7100\ncurrent episode reward: 14.0000\nepisodes: 919\nexploration: 0.08004\nlearning_rate: 0.00009\nelapsed time: 6363.9 seconds (1.77 hours)\n\nTimestep: 1620000\nmean reward (100 episodes): 5.9700\nbest mean reward: 5.9700\ncurrent episode reward: 10.0000\nepisodes: 922\nexploration: 0.07971\nlearning_rate: 0.00009\nelapsed time: 6408.1 seconds (1.78 hours)\n\nTimestep: 1630000\nmean reward (100 episodes): 6.3400\nbest mean reward: 6.3400\ncurrent episode reward: 10.0000\nepisodes: 925\nexploration: 0.07938\nlearning_rate: 0.00009\nelapsed time: 6451.4 seconds (1.79 hours)\n\nTimestep: 1640000\nmean reward (100 episodes): 7.0100\nbest mean reward: 7.0100\ncurrent episode reward: 15.0000\nepisodes: 929\nexploration: 0.07905\nlearning_rate: 0.00009\nelapsed time: 6495.3 seconds (1.80 hours)\n\nTimestep: 1650000\nmean reward (100 episodes): 7.5900\nbest mean reward: 7.5900\ncurrent episode reward: 17.0000\nepisodes: 934\nexploration: 0.07873\nlearning_rate: 0.00009\nelapsed time: 6539.8 seconds (1.82 hours)\n\nTimestep: 1660000\nmean reward (100 episodes): 8.1900\nbest mean reward: 8.1900\ncurrent episode reward: 17.0000\nepisodes: 938\nexploration: 0.07840\nlearning_rate: 0.00008\nelapsed time: 6584.0 seconds (1.83 hours)\n\nTimestep: 1670000\nmean reward (100 episodes): 8.9500\nbest mean reward: 8.9500\ncurrent episode reward: 14.0000\nepisodes: 943\nexploration: 0.07807\nlearning_rate: 0.00008\nelapsed time: 6628.5 seconds (1.84 hours)\n\nTimestep: 1680000\nmean reward (100 episodes): 9.3600\nbest mean reward: 9.3600\ncurrent episode reward: 19.0000\nepisodes: 947\nexploration: 0.07775\nlearning_rate: 0.00008\nelapsed time: 6673.0 seconds (1.85 hours)\n\nTimestep: 1690000\nmean reward (100 episodes): 9.9400\nbest mean reward: 9.9400\ncurrent episode reward: 14.0000\nepisodes: 952\nexploration: 0.07742\nlearning_rate: 0.00008\nelapsed time: 6717.4 seconds (1.87 hours)\n\nTimestep: 1700000\nmean reward (100 episodes): 10.4700\nbest mean reward: 10.4700\ncurrent episode reward: 17.0000\nepisodes: 956\nexploration: 0.07709\nlearning_rate: 0.00008\nelapsed time: 6761.8 seconds (1.88 hours)\n\nTimestep: 1710000\nmean reward (100 episodes): 11.1400\nbest mean reward: 11.1400\ncurrent episode reward: 20.0000\nepisodes: 961\nexploration: 0.07676\nlearning_rate: 0.00008\nelapsed time: 6805.4 seconds (1.89 hours)\n\nTimestep: 1720000\nmean reward (100 episodes): 11.5800\nbest mean reward: 11.5800\ncurrent episode reward: 16.0000\nepisodes: 965\nexploration: 0.07644\nlearning_rate: 0.00008\nelapsed time: 6848.8 seconds (1.90 hours)\n\nTimestep: 1730000\nmean reward (100 episodes): 12.1700\nbest mean reward: 12.1700\ncurrent episode reward: 16.0000\nepisodes: 970\nexploration: 0.07611\nlearning_rate: 0.00008\nelapsed time: 6893.3 seconds (1.91 hours)\n\nTimestep: 1740000\nmean reward (100 episodes): 12.5800\nbest mean reward: 12.5800\ncurrent episode reward: 16.0000\nepisodes: 974\nexploration: 0.07578\nlearning_rate: 0.00008\nelapsed time: 6937.3 seconds (1.93 hours)\n\nTimestep: 1750000\nmean reward (100 episodes): 13.1500\nbest mean reward: 13.1500\ncurrent episode reward: 18.0000\nepisodes: 979\nexploration: 0.07545\nlearning_rate: 0.00008\nelapsed time: 6981.6 seconds (1.94 hours)\n\nTimestep: 1760000\nmean reward (100 episodes): 13.6000\nbest mean reward: 13.6000\ncurrent episode reward: 18.0000\nepisodes: 984\nexploration: 0.07513\nlearning_rate: 0.00008\nelapsed time: 7025.8 seconds (1.95 hours)\n\nTimestep: 1770000\nmean reward (100 episodes): 14.2200\nbest mean reward: 14.2200\ncurrent episode reward: 14.0000\nepisodes: 989\nexploration: 0.07480\nlearning_rate: 0.00008\nelapsed time: 7069.5 seconds (1.96 hours)\n\nTimestep: 1780000\nmean reward (100 episodes): 14.5800\nbest mean reward: 14.5800\ncurrent episode reward: 17.0000\nepisodes: 993\nexploration: 0.07447\nlearning_rate: 0.00008\nelapsed time: 7113.4 seconds (1.98 hours)\n\nTimestep: 1790000\nmean reward (100 episodes): 14.7100\nbest mean reward: 14.7200\ncurrent episode reward: 15.0000\nepisodes: 997\nexploration: 0.07415\nlearning_rate: 0.00008\nelapsed time: 7157.2 seconds (1.99 hours)\n\nTimestep: 1800000\nmean reward (100 episodes): 15.1400\nbest mean reward: 15.1400\ncurrent episode reward: 18.0000\nepisodes: 1002\nexploration: 0.07382\nlearning_rate: 0.00008\nelapsed time: 7207.2 seconds (2.00 hours)\n\nTimestep: 1810000\nmean reward (100 episodes): 15.1900\nbest mean reward: 15.1900\ncurrent episode reward: 20.0000\nepisodes: 1006\nexploration: 0.07349\nlearning_rate: 0.00008\nelapsed time: 7251.2 seconds (2.01 hours)\n\nTimestep: 1820000\nmean reward (100 episodes): 15.3700\nbest mean reward: 15.3700\ncurrent episode reward: 17.0000\nepisodes: 1011\nexploration: 0.07316\nlearning_rate: 0.00008\nelapsed time: 7294.8 seconds (2.03 hours)\n\nTimestep: 1830000\nmean reward (100 episodes): 15.6600\nbest mean reward: 15.6700\ncurrent episode reward: 13.0000\nepisodes: 1016\nexploration: 0.07284\nlearning_rate: 0.00008\nelapsed time: 7338.2 seconds (2.04 hours)\n\nTimestep: 1840000\nmean reward (100 episodes): 15.7900\nbest mean reward: 15.7900\ncurrent episode reward: 15.0000\nepisodes: 1020\nexploration: 0.07251\nlearning_rate: 0.00008\nelapsed time: 7381.3 seconds (2.05 hours)\n\nTimestep: 1850000\nmean reward (100 episodes): 16.0400\nbest mean reward: 16.0400\ncurrent episode reward: 18.0000\nepisodes: 1025\nexploration: 0.07218\nlearning_rate: 0.00008\nelapsed time: 7425.2 seconds (2.06 hours)\n\nTimestep: 1860000\nmean reward (100 episodes): 16.2400\nbest mean reward: 16.2400\ncurrent episode reward: 16.0000\nepisodes: 1030\nexploration: 0.07185\nlearning_rate: 0.00008\nelapsed time: 7469.4 seconds (2.07 hours)\n\nTimestep: 1870000\nmean reward (100 episodes): 16.1700\nbest mean reward: 16.2400\ncurrent episode reward: 15.0000\nepisodes: 1034\nexploration: 0.07153\nlearning_rate: 0.00008\nelapsed time: 7512.7 seconds (2.09 hours)\n\nTimestep: 1880000\nmean reward (100 episodes): 16.2000\nbest mean reward: 16.2500\ncurrent episode reward: 12.0000\nepisodes: 1038\nexploration: 0.07120\nlearning_rate: 0.00008\nelapsed time: 7557.7 seconds (2.10 hours)\n\nTimestep: 1890000\nmean reward (100 episodes): 16.2400\nbest mean reward: 16.2500\ncurrent episode reward: 16.0000\nepisodes: 1043\nexploration: 0.07087\nlearning_rate: 0.00008\nelapsed time: 7602.0 seconds (2.11 hours)\n\nTimestep: 1900000\nmean reward (100 episodes): 16.2900\nbest mean reward: 16.3500\ncurrent episode reward: 13.0000\nepisodes: 1047\nexploration: 0.07055\nlearning_rate: 0.00008\nelapsed time: 7646.1 seconds (2.12 hours)\n\nTimestep: 1910000\nmean reward (100 episodes): 16.3000\nbest mean reward: 16.3500\ncurrent episode reward: 12.0000\nepisodes: 1051\nexploration: 0.07022\nlearning_rate: 0.00008\nelapsed time: 7689.9 seconds (2.14 hours)\n\nTimestep: 1920000\nmean reward (100 episodes): 16.2500\nbest mean reward: 16.3500\ncurrent episode reward: 14.0000\nepisodes: 1056\nexploration: 0.06989\nlearning_rate: 0.00008\nelapsed time: 7733.6 seconds (2.15 hours)\n\nTimestep: 1930000\nmean reward (100 episodes): 16.3000\nbest mean reward: 16.3500\ncurrent episode reward: 19.0000\nepisodes: 1061\nexploration: 0.06956\nlearning_rate: 0.00008\nelapsed time: 7777.3 seconds (2.16 hours)\n\nTimestep: 1940000\nmean reward (100 episodes): 16.4000\nbest mean reward: 16.4000\ncurrent episode reward: 18.0000\nepisodes: 1065\nexploration: 0.06924\nlearning_rate: 0.00008\nelapsed time: 7821.6 seconds (2.17 hours)\n\nTimestep: 1950000\nmean reward (100 episodes): 16.4200\nbest mean reward: 16.4200\ncurrent episode reward: 19.0000\nepisodes: 1070\nexploration: 0.06891\nlearning_rate: 0.00008\nelapsed time: 7866.0 seconds (2.19 hours)\n\nTimestep: 1960000\nmean reward (100 episodes): 16.5000\nbest mean reward: 16.5000\ncurrent episode reward: 18.0000\nepisodes: 1075\nexploration: 0.06858\nlearning_rate: 0.00008\nelapsed time: 7909.7 seconds (2.20 hours)\n\nTimestep: 1970000\nmean reward (100 episodes): 16.4700\nbest mean reward: 16.5000\ncurrent episode reward: 18.0000\nepisodes: 1079\nexploration: 0.06825\nlearning_rate: 0.00008\nelapsed time: 7953.1 seconds (2.21 hours)\n\nTimestep: 1980000\nmean reward (100 episodes): 16.4600\nbest mean reward: 16.5000\ncurrent episode reward: 20.0000\nepisodes: 1084\nexploration: 0.06793\nlearning_rate: 0.00008\nelapsed time: 7996.2 seconds (2.22 hours)\n\nTimestep: 1990000\nmean reward (100 episodes): 16.4500\nbest mean reward: 16.5000\ncurrent episode reward: 20.0000\nepisodes: 1089\nexploration: 0.06760\nlearning_rate: 0.00008\nelapsed time: 8040.0 seconds (2.23 hours)\n\nTimestep: 2000000\nmean reward (100 episodes): 16.4600\nbest mean reward: 16.5000\ncurrent episode reward: 14.0000\nepisodes: 1094\nexploration: 0.06727\nlearning_rate: 0.00008\nelapsed time: 8083.6 seconds (2.25 hours)\n\nTimestep: 2010000\nmean reward (100 episodes): 16.5100\nbest mean reward: 16.5100\ncurrent episode reward: 17.0000\nepisodes: 1099\nexploration: 0.06695\nlearning_rate: 0.00008\nelapsed time: 8126.0 seconds (2.26 hours)\n\nTimestep: 2020000\nmean reward (100 episodes): 16.5600\nbest mean reward: 16.5700\ncurrent episode reward: 16.0000\nepisodes: 1104\nexploration: 0.06662\nlearning_rate: 0.00008\nelapsed time: 8170.2 seconds (2.27 hours)\n\nTimestep: 2030000\nmean reward (100 episodes): 16.6200\nbest mean reward: 16.6300\ncurrent episode reward: 17.0000\nepisodes: 1109\nexploration: 0.06629\nlearning_rate: 0.00008\nelapsed time: 8214.3 seconds (2.28 hours)\n\nTimestep: 2040000\nmean reward (100 episodes): 16.6400\nbest mean reward: 16.6600\ncurrent episode reward: 20.0000\nepisodes: 1113\nexploration: 0.06596\nlearning_rate: 0.00008\nelapsed time: 8257.9 seconds (2.29 hours)\n\nTimestep: 2050000\nmean reward (100 episodes): 16.6800\nbest mean reward: 16.6800\ncurrent episode reward: 17.0000\nepisodes: 1118\nexploration: 0.06564\nlearning_rate: 0.00008\nelapsed time: 8302.0 seconds (2.31 hours)\n\nTimestep: 2060000\nmean reward (100 episodes): 16.7700\nbest mean reward: 16.7700\ncurrent episode reward: 18.0000\nepisodes: 1122\nexploration: 0.06531\nlearning_rate: 0.00008\nelapsed time: 8345.1 seconds (2.32 hours)\n\nTimestep: 2070000\nmean reward (100 episodes): 16.7600\nbest mean reward: 16.8100\ncurrent episode reward: 17.0000\nepisodes: 1127\nexploration: 0.06498\nlearning_rate: 0.00008\nelapsed time: 8388.8 seconds (2.33 hours)\n\nTimestep: 2080000\nmean reward (100 episodes): 16.7700\nbest mean reward: 16.8100\ncurrent episode reward: 17.0000\nepisodes: 1132\nexploration: 0.06465\nlearning_rate: 0.00008\nelapsed time: 8433.1 seconds (2.34 hours)\n\nTimestep: 2090000\nmean reward (100 episodes): 16.7900\nbest mean reward: 16.8300\ncurrent episode reward: 20.0000\nepisodes: 1137\nexploration: 0.06433\nlearning_rate: 0.00008\nelapsed time: 8476.5 seconds (2.35 hours)\n\nTimestep: 2100000\nmean reward (100 episodes): 16.9300\nbest mean reward: 16.9300\ncurrent episode reward: 18.0000\nepisodes: 1141\nexploration: 0.06400\nlearning_rate: 0.00008\nelapsed time: 8519.9 seconds (2.37 hours)\n\nTimestep: 2110000\nmean reward (100 episodes): 16.9500\nbest mean reward: 16.9600\ncurrent episode reward: 16.0000\nepisodes: 1146\nexploration: 0.06367\nlearning_rate: 0.00008\nelapsed time: 8563.4 seconds (2.38 hours)\n\nTimestep: 2120000\nmean reward (100 episodes): 16.9900\nbest mean reward: 16.9900\ncurrent episode reward: 17.0000\nepisodes: 1150\nexploration: 0.06335\nlearning_rate: 0.00008\nelapsed time: 8607.4 seconds (2.39 hours)\n\nTimestep: 2130000\nmean reward (100 episodes): 17.0900\nbest mean reward: 17.0900\ncurrent episode reward: 18.0000\nepisodes: 1155\nexploration: 0.06302\nlearning_rate: 0.00008\nelapsed time: 8650.4 seconds (2.40 hours)\n\nTimestep: 2140000\nmean reward (100 episodes): 17.2300\nbest mean reward: 17.2300\ncurrent episode reward: 18.0000\nepisodes: 1160\nexploration: 0.06269\nlearning_rate: 0.00008\nelapsed time: 8694.4 seconds (2.42 hours)\n\nTimestep: 2150000\nmean reward (100 episodes): 17.1300\nbest mean reward: 17.2300\ncurrent episode reward: 18.0000\nepisodes: 1165\nexploration: 0.06236\nlearning_rate: 0.00008\nelapsed time: 8738.3 seconds (2.43 hours)\n\nTimestep: 2160000\nmean reward (100 episodes): 17.1900\nbest mean reward: 17.2300\ncurrent episode reward: 16.0000\nepisodes: 1170\nexploration: 0.06204\nlearning_rate: 0.00008\nelapsed time: 8781.6 seconds (2.44 hours)\n\nTimestep: 2170000\nmean reward (100 episodes): 17.2100\nbest mean reward: 17.2300\ncurrent episode reward: 20.0000\nepisodes: 1175\nexploration: 0.06171\nlearning_rate: 0.00008\nelapsed time: 8825.3 seconds (2.45 hours)\n\nTimestep: 2180000\nmean reward (100 episodes): 17.2400\nbest mean reward: 17.2700\ncurrent episode reward: 13.0000\nepisodes: 1180\nexploration: 0.06138\nlearning_rate: 0.00008\nelapsed time: 8868.6 seconds (2.46 hours)\n\nTimestep: 2190000\nmean reward (100 episodes): 17.2800\nbest mean reward: 17.3000\ncurrent episode reward: 19.0000\nepisodes: 1185\nexploration: 0.06105\nlearning_rate: 0.00008\nelapsed time: 8912.4 seconds (2.48 hours)\n\nTimestep: 2200000\nmean reward (100 episodes): 17.3100\nbest mean reward: 17.3300\ncurrent episode reward: 16.0000\nepisodes: 1190\nexploration: 0.06073\nlearning_rate: 0.00008\nelapsed time: 8955.9 seconds (2.49 hours)\n\nTimestep: 2210000\nmean reward (100 episodes): 17.3600\nbest mean reward: 17.3600\ncurrent episode reward: 19.0000\nepisodes: 1195\nexploration: 0.06040\nlearning_rate: 0.00008\nelapsed time: 8999.7 seconds (2.50 hours)\n\nTimestep: 2220000\nmean reward (100 episodes): 17.3900\nbest mean reward: 17.4100\ncurrent episode reward: 17.0000\nepisodes: 1200\nexploration: 0.06007\nlearning_rate: 0.00008\nelapsed time: 9042.8 seconds (2.51 hours)\n\nTimestep: 2230000\nmean reward (100 episodes): 17.4100\nbest mean reward: 17.4100\ncurrent episode reward: 19.0000\nepisodes: 1205\nexploration: 0.05975\nlearning_rate: 0.00008\nelapsed time: 9086.5 seconds (2.52 hours)\n\nTimestep: 2240000\nmean reward (100 episodes): 17.2500\nbest mean reward: 17.4100\ncurrent episode reward: 16.0000\nepisodes: 1210\nexploration: 0.05942\nlearning_rate: 0.00008\nelapsed time: 9130.2 seconds (2.54 hours)\n\nTimestep: 2250000\nmean reward (100 episodes): 17.3000\nbest mean reward: 17.4100\ncurrent episode reward: 20.0000\nepisodes: 1214\nexploration: 0.05909\nlearning_rate: 0.00008\nelapsed time: 9173.2 seconds (2.55 hours)\n\nTimestep: 2260000\nmean reward (100 episodes): 17.3000\nbest mean reward: 17.4100\ncurrent episode reward: 18.0000\nepisodes: 1219\nexploration: 0.05876\nlearning_rate: 0.00007\nelapsed time: 9216.8 seconds (2.56 hours)\n\nTimestep: 2270000\nmean reward (100 episodes): 17.3400\nbest mean reward: 17.4100\ncurrent episode reward: 14.0000\nepisodes: 1224\nexploration: 0.05844\nlearning_rate: 0.00007\nelapsed time: 9260.5 seconds (2.57 hours)\n\nTimestep: 2280000\nmean reward (100 episodes): 17.3600\nbest mean reward: 17.4100\ncurrent episode reward: 19.0000\nepisodes: 1229\nexploration: 0.05811\nlearning_rate: 0.00007\nelapsed time: 9304.2 seconds (2.58 hours)\n\nTimestep: 2290000\nmean reward (100 episodes): 17.4000\nbest mean reward: 17.4100\ncurrent episode reward: 20.0000\nepisodes: 1234\nexploration: 0.05778\nlearning_rate: 0.00007\nelapsed time: 9348.3 seconds (2.60 hours)\n\nTimestep: 2300000\nmean reward (100 episodes): 17.3800\nbest mean reward: 17.4700\ncurrent episode reward: 18.0000\nepisodes: 1239\nexploration: 0.05745\nlearning_rate: 0.00007\nelapsed time: 9392.4 seconds (2.61 hours)\n\nTimestep: 2310000\nmean reward (100 episodes): 17.4200\nbest mean reward: 17.4700\ncurrent episode reward: 16.0000\nepisodes: 1243\nexploration: 0.05713\nlearning_rate: 0.00007\nelapsed time: 9435.7 seconds (2.62 hours)\n\nTimestep: 2320000\nmean reward (100 episodes): 17.5200\nbest mean reward: 17.5200\ncurrent episode reward: 20.0000\nepisodes: 1249\nexploration: 0.05680\nlearning_rate: 0.00007\nelapsed time: 9480.0 seconds (2.63 hours)\n\nTimestep: 2330000\nmean reward (100 episodes): 17.6200\nbest mean reward: 17.6200\ncurrent episode reward: 19.0000\nepisodes: 1254\nexploration: 0.05647\nlearning_rate: 0.00007\nelapsed time: 9524.6 seconds (2.65 hours)\n\nTimestep: 2340000\nmean reward (100 episodes): 17.6100\nbest mean reward: 17.6300\ncurrent episode reward: 21.0000\nepisodes: 1259\nexploration: 0.05615\nlearning_rate: 0.00007\nelapsed time: 9568.9 seconds (2.66 hours)\n\nTimestep: 2350000\nmean reward (100 episodes): 17.7300\nbest mean reward: 17.7300\ncurrent episode reward: 19.0000\nepisodes: 1264\nexploration: 0.05582\nlearning_rate: 0.00007\nelapsed time: 9613.2 seconds (2.67 hours)\n\nTimestep: 2360000\nmean reward (100 episodes): 17.7700\nbest mean reward: 17.7700\ncurrent episode reward: 20.0000\nepisodes: 1269\nexploration: 0.05549\nlearning_rate: 0.00007\nelapsed time: 9656.4 seconds (2.68 hours)\n\nTimestep: 2370000\nmean reward (100 episodes): 17.8200\nbest mean reward: 17.8200\ncurrent episode reward: 18.0000\nepisodes: 1274\nexploration: 0.05516\nlearning_rate: 0.00007\nelapsed time: 9701.5 seconds (2.69 hours)\n\nTimestep: 2380000\nmean reward (100 episodes): 17.7100\nbest mean reward: 17.8200\ncurrent episode reward: 11.0000\nepisodes: 1279\nexploration: 0.05484\nlearning_rate: 0.00007\nelapsed time: 9746.1 seconds (2.71 hours)\n\nTimestep: 2390000\nmean reward (100 episodes): 17.7600\nbest mean reward: 17.8200\ncurrent episode reward: 19.0000\nepisodes: 1283\nexploration: 0.05451\nlearning_rate: 0.00007\nelapsed time: 9790.7 seconds (2.72 hours)\n\nTimestep: 2400000\nmean reward (100 episodes): 17.6600\nbest mean reward: 17.8200\ncurrent episode reward: 19.0000\nepisodes: 1288\nexploration: 0.05418\nlearning_rate: 0.00007\nelapsed time: 9835.1 seconds (2.73 hours)\n\nTimestep: 2410000\nmean reward (100 episodes): 17.7000\nbest mean reward: 17.8200\ncurrent episode reward: 17.0000\nepisodes: 1293\nexploration: 0.05385\nlearning_rate: 0.00007\nelapsed time: 9878.7 seconds (2.74 hours)\n\nTimestep: 2420000\nmean reward (100 episodes): 17.7300\nbest mean reward: 17.8200\ncurrent episode reward: 17.0000\nepisodes: 1298\nexploration: 0.05353\nlearning_rate: 0.00007\nelapsed time: 9922.2 seconds (2.76 hours)\n\nTimestep: 2430000\nmean reward (100 episodes): 17.8000\nbest mean reward: 17.8200\ncurrent episode reward: 20.0000\nepisodes: 1303\nexploration: 0.05320\nlearning_rate: 0.00007\nelapsed time: 9966.4 seconds (2.77 hours)\n\nTimestep: 2440000\nmean reward (100 episodes): 17.8600\nbest mean reward: 17.8600\ncurrent episode reward: 20.0000\nepisodes: 1308\nexploration: 0.05287\nlearning_rate: 0.00007\nelapsed time: 10010.1 seconds (2.78 hours)\n\nTimestep: 2450000\nmean reward (100 episodes): 18.0100\nbest mean reward: 18.0100\ncurrent episode reward: 21.0000\nepisodes: 1313\nexploration: 0.05255\nlearning_rate: 0.00007\nelapsed time: 10053.5 seconds (2.79 hours)\n\nTimestep: 2460000\nmean reward (100 episodes): 17.9800\nbest mean reward: 18.0100\ncurrent episode reward: 19.0000\nepisodes: 1317\nexploration: 0.05222\nlearning_rate: 0.00007\nelapsed time: 10097.3 seconds (2.80 hours)\n\nTimestep: 2470000\nmean reward (100 episodes): 17.9300\nbest mean reward: 18.0100\ncurrent episode reward: 18.0000\nepisodes: 1323\nexploration: 0.05189\nlearning_rate: 0.00007\nelapsed time: 10141.0 seconds (2.82 hours)\n\nTimestep: 2480000\nmean reward (100 episodes): 18.0700\nbest mean reward: 18.0700\ncurrent episode reward: 19.0000\nepisodes: 1328\nexploration: 0.05156\nlearning_rate: 0.00007\nelapsed time: 10184.1 seconds (2.83 hours)\n\nTimestep: 2490000\nmean reward (100 episodes): 18.0600\nbest mean reward: 18.0700\ncurrent episode reward: 19.0000\nepisodes: 1333\nexploration: 0.05124\nlearning_rate: 0.00007\nelapsed time: 10228.5 seconds (2.84 hours)\n\nTimestep: 2500000\nmean reward (100 episodes): 18.0900\nbest mean reward: 18.0900\ncurrent episode reward: 19.0000\nepisodes: 1338\nexploration: 0.05091\nlearning_rate: 0.00007\nelapsed time: 10272.1 seconds (2.85 hours)\n\nTimestep: 2510000\nmean reward (100 episodes): 18.1200\nbest mean reward: 18.1200\ncurrent episode reward: 18.0000\nepisodes: 1343\nexploration: 0.05058\nlearning_rate: 0.00007\nelapsed time: 10315.8 seconds (2.87 hours)\n\nTimestep: 2520000\nmean reward (100 episodes): 18.1200\nbest mean reward: 18.1400\ncurrent episode reward: 17.0000\nepisodes: 1348\nexploration: 0.05025\nlearning_rate: 0.00007\nelapsed time: 10360.3 seconds (2.88 hours)\n\nTimestep: 2530000\nmean reward (100 episodes): 18.0700\nbest mean reward: 18.1400\ncurrent episode reward: 19.0000\nepisodes: 1353\nexploration: 0.04993\nlearning_rate: 0.00007\nelapsed time: 10405.2 seconds (2.89 hours)\n\nTimestep: 2540000\nmean reward (100 episodes): 18.0800\nbest mean reward: 18.1400\ncurrent episode reward: 20.0000\nepisodes: 1358\nexploration: 0.04960\nlearning_rate: 0.00007\nelapsed time: 10448.7 seconds (2.90 hours)\n\nTimestep: 2550000\nmean reward (100 episodes): 17.9300\nbest mean reward: 18.1400\ncurrent episode reward: 13.0000\nepisodes: 1362\nexploration: 0.04927\nlearning_rate: 0.00007\nelapsed time: 10492.9 seconds (2.91 hours)\n\nTimestep: 2560000\nmean reward (100 episodes): 17.9500\nbest mean reward: 18.1400\ncurrent episode reward: 19.0000\nepisodes: 1368\nexploration: 0.04895\nlearning_rate: 0.00007\nelapsed time: 10536.9 seconds (2.93 hours)\n\nTimestep: 2570000\nmean reward (100 episodes): 17.9600\nbest mean reward: 18.1400\ncurrent episode reward: 19.0000\nepisodes: 1373\nexploration: 0.04862\nlearning_rate: 0.00007\nelapsed time: 10581.1 seconds (2.94 hours)\n\nTimestep: 2580000\nmean reward (100 episodes): 17.9100\nbest mean reward: 18.1400\ncurrent episode reward: 17.0000\nepisodes: 1378\nexploration: 0.04829\nlearning_rate: 0.00007\nelapsed time: 10625.3 seconds (2.95 hours)\n\nTimestep: 2590000\nmean reward (100 episodes): 17.9700\nbest mean reward: 18.1400\ncurrent episode reward: 19.0000\nepisodes: 1382\nexploration: 0.04796\nlearning_rate: 0.00007\nelapsed time: 10669.1 seconds (2.96 hours)\n\nTimestep: 2600000\nmean reward (100 episodes): 18.0200\nbest mean reward: 18.1400\ncurrent episode reward: 19.0000\nepisodes: 1387\nexploration: 0.04764\nlearning_rate: 0.00007\nelapsed time: 10713.1 seconds (2.98 hours)\n\nTimestep: 2610000\nmean reward (100 episodes): 17.9800\nbest mean reward: 18.1400\ncurrent episode reward: 16.0000\nepisodes: 1392\nexploration: 0.04731\nlearning_rate: 0.00007\nelapsed time: 10757.4 seconds (2.99 hours)\n\nTimestep: 2620000\nmean reward (100 episodes): 17.9500\nbest mean reward: 18.1400\ncurrent episode reward: 18.0000\nepisodes: 1397\nexploration: 0.04698\nlearning_rate: 0.00007\nelapsed time: 10801.7 seconds (3.00 hours)\n\nTimestep: 2630000\nmean reward (100 episodes): 17.9700\nbest mean reward: 18.1400\ncurrent episode reward: 18.0000\nepisodes: 1402\nexploration: 0.04665\nlearning_rate: 0.00007\nelapsed time: 10846.0 seconds (3.01 hours)\n\nTimestep: 2640000\nmean reward (100 episodes): 17.9500\nbest mean reward: 18.1400\ncurrent episode reward: 19.0000\nepisodes: 1407\nexploration: 0.04633\nlearning_rate: 0.00007\nelapsed time: 10890.1 seconds (3.03 hours)\n\nTimestep: 2650000\nmean reward (100 episodes): 17.9600\nbest mean reward: 18.1400\ncurrent episode reward: 20.0000\nepisodes: 1413\nexploration: 0.04600\nlearning_rate: 0.00007\nelapsed time: 10935.1 seconds (3.04 hours)\n\nTimestep: 2660000\nmean reward (100 episodes): 18.0700\nbest mean reward: 18.1400\ncurrent episode reward: 18.0000\nepisodes: 1418\nexploration: 0.04567\nlearning_rate: 0.00007\nelapsed time: 10979.8 seconds (3.05 hours)\n\nTimestep: 2670000\nmean reward (100 episodes): 18.0900\nbest mean reward: 18.1400\ncurrent episode reward: 20.0000\nepisodes: 1423\nexploration: 0.04535\nlearning_rate: 0.00007\nelapsed time: 11023.8 seconds (3.06 hours)\n\nTimestep: 2680000\nmean reward (100 episodes): 18.1200\nbest mean reward: 18.1400\ncurrent episode reward: 19.0000\nepisodes: 1428\nexploration: 0.04502\nlearning_rate: 0.00007\nelapsed time: 11067.5 seconds (3.07 hours)\n\nTimestep: 2690000\nmean reward (100 episodes): 18.2700\nbest mean reward: 18.2700\ncurrent episode reward: 21.0000\nepisodes: 1434\nexploration: 0.04469\nlearning_rate: 0.00007\nelapsed time: 11111.5 seconds (3.09 hours)\n\nTimestep: 2700000\nmean reward (100 episodes): 18.3000\nbest mean reward: 18.3000\ncurrent episode reward: 20.0000\nepisodes: 1439\nexploration: 0.04436\nlearning_rate: 0.00007\nelapsed time: 11155.9 seconds (3.10 hours)\n\nTimestep: 2710000\nmean reward (100 episodes): 18.2400\nbest mean reward: 18.3000\ncurrent episode reward: 15.0000\nepisodes: 1444\nexploration: 0.04404\nlearning_rate: 0.00007\nelapsed time: 11200.0 seconds (3.11 hours)\n\nTimestep: 2720000\nmean reward (100 episodes): 18.2700\nbest mean reward: 18.3000\ncurrent episode reward: 19.0000\nepisodes: 1449\nexploration: 0.04371\nlearning_rate: 0.00007\nelapsed time: 11244.2 seconds (3.12 hours)\n\nTimestep: 2730000\nmean reward (100 episodes): 18.3100\nbest mean reward: 18.3100\ncurrent episode reward: 21.0000\nepisodes: 1455\nexploration: 0.04338\nlearning_rate: 0.00007\nelapsed time: 11288.2 seconds (3.14 hours)\n\nTimestep: 2740000\nmean reward (100 episodes): 18.3500\nbest mean reward: 18.3500\ncurrent episode reward: 19.0000\nepisodes: 1459\nexploration: 0.04305\nlearning_rate: 0.00007\nelapsed time: 11332.3 seconds (3.15 hours)\n\nTimestep: 2750000\nmean reward (100 episodes): 18.3700\nbest mean reward: 18.3700\ncurrent episode reward: 20.0000\nepisodes: 1464\nexploration: 0.04273\nlearning_rate: 0.00007\nelapsed time: 11376.8 seconds (3.16 hours)\n\nTimestep: 2760000\nmean reward (100 episodes): 18.3200\nbest mean reward: 18.3800\ncurrent episode reward: 20.0000\nepisodes: 1469\nexploration: 0.04240\nlearning_rate: 0.00007\nelapsed time: 11421.5 seconds (3.17 hours)\n\nTimestep: 2770000\nmean reward (100 episodes): 18.3600\nbest mean reward: 18.3800\ncurrent episode reward: 18.0000\nepisodes: 1475\nexploration: 0.04207\nlearning_rate: 0.00007\nelapsed time: 11465.3 seconds (3.18 hours)\n\nTimestep: 2780000\nmean reward (100 episodes): 18.4500\nbest mean reward: 18.4500\ncurrent episode reward: 19.0000\nepisodes: 1480\nexploration: 0.04175\nlearning_rate: 0.00007\nelapsed time: 11509.2 seconds (3.20 hours)\n\nTimestep: 2790000\nmean reward (100 episodes): 18.5300\nbest mean reward: 18.5500\ncurrent episode reward: 18.0000\nepisodes: 1485\nexploration: 0.04142\nlearning_rate: 0.00007\nelapsed time: 11552.5 seconds (3.21 hours)\n\nTimestep: 2800000\nmean reward (100 episodes): 18.5800\nbest mean reward: 18.6000\ncurrent episode reward: 19.0000\nepisodes: 1490\nexploration: 0.04109\nlearning_rate: 0.00007\nelapsed time: 11596.1 seconds (3.22 hours)\n\nTimestep: 2810000\nmean reward (100 episodes): 18.6800\nbest mean reward: 18.6800\ncurrent episode reward: 19.0000\nepisodes: 1495\nexploration: 0.04076\nlearning_rate: 0.00007\nelapsed time: 11639.9 seconds (3.23 hours)\n\nTimestep: 2820000\nmean reward (100 episodes): 18.6800\nbest mean reward: 18.6800\ncurrent episode reward: 19.0000\nepisodes: 1500\nexploration: 0.04044\nlearning_rate: 0.00007\nelapsed time: 11683.5 seconds (3.25 hours)\n\nTimestep: 2830000\nmean reward (100 episodes): 18.7700\nbest mean reward: 18.7700\ncurrent episode reward: 20.0000\nepisodes: 1505\nexploration: 0.04011\nlearning_rate: 0.00007\nelapsed time: 11727.8 seconds (3.26 hours)\n\nTimestep: 2840000\nmean reward (100 episodes): 18.7600\nbest mean reward: 18.8400\ncurrent episode reward: 19.0000\nepisodes: 1511\nexploration: 0.03978\nlearning_rate: 0.00007\nelapsed time: 11771.5 seconds (3.27 hours)\n\nTimestep: 2850000\nmean reward (100 episodes): 18.7900\nbest mean reward: 18.8400\ncurrent episode reward: 19.0000\nepisodes: 1516\nexploration: 0.03945\nlearning_rate: 0.00007\nelapsed time: 11815.6 seconds (3.28 hours)\n\nTimestep: 2860000\nmean reward (100 episodes): 18.8800\nbest mean reward: 18.8800\ncurrent episode reward: 19.0000\nepisodes: 1522\nexploration: 0.03913\nlearning_rate: 0.00006\nelapsed time: 11859.8 seconds (3.29 hours)\n\nTimestep: 2870000\nmean reward (100 episodes): 18.8300\nbest mean reward: 18.8800\ncurrent episode reward: 16.0000\nepisodes: 1527\nexploration: 0.03880\nlearning_rate: 0.00006\nelapsed time: 11903.9 seconds (3.31 hours)\n\nTimestep: 2880000\nmean reward (100 episodes): 18.7900\nbest mean reward: 18.8800\ncurrent episode reward: 18.0000\nepisodes: 1532\nexploration: 0.03847\nlearning_rate: 0.00006\nelapsed time: 11948.5 seconds (3.32 hours)\n\nTimestep: 2890000\nmean reward (100 episodes): 18.6800\nbest mean reward: 18.8800\ncurrent episode reward: 17.0000\nepisodes: 1537\nexploration: 0.03815\nlearning_rate: 0.00006\nelapsed time: 11992.7 seconds (3.33 hours)\n\nTimestep: 2900000\nmean reward (100 episodes): 18.7200\nbest mean reward: 18.8800\ncurrent episode reward: 19.0000\nepisodes: 1542\nexploration: 0.03782\nlearning_rate: 0.00006\nelapsed time: 12036.8 seconds (3.34 hours)\n\nTimestep: 2910000\nmean reward (100 episodes): 18.7800\nbest mean reward: 18.8800\ncurrent episode reward: 20.0000\nepisodes: 1548\nexploration: 0.03749\nlearning_rate: 0.00006\nelapsed time: 12081.0 seconds (3.36 hours)\n\nTimestep: 2920000\nmean reward (100 episodes): 18.7800\nbest mean reward: 18.8800\ncurrent episode reward: 19.0000\nepisodes: 1553\nexploration: 0.03716\nlearning_rate: 0.00006\nelapsed time: 12124.6 seconds (3.37 hours)\n\nTimestep: 2930000\nmean reward (100 episodes): 18.8300\nbest mean reward: 18.8800\ncurrent episode reward: 21.0000\nepisodes: 1558\nexploration: 0.03684\nlearning_rate: 0.00006\nelapsed time: 12168.0 seconds (3.38 hours)\n\nTimestep: 2940000\nmean reward (100 episodes): 18.9100\nbest mean reward: 18.9400\ncurrent episode reward: 17.0000\nepisodes: 1564\nexploration: 0.03651\nlearning_rate: 0.00006\nelapsed time: 12212.5 seconds (3.39 hours)\n\nTimestep: 2950000\nmean reward (100 episodes): 18.9900\nbest mean reward: 19.0000\ncurrent episode reward: 19.0000\nepisodes: 1569\nexploration: 0.03618\nlearning_rate: 0.00006\nelapsed time: 12257.1 seconds (3.40 hours)\n\nTimestep: 2960000\nmean reward (100 episodes): 19.0800\nbest mean reward: 19.0800\ncurrent episode reward: 20.0000\nepisodes: 1575\nexploration: 0.03585\nlearning_rate: 0.00006\nelapsed time: 12301.6 seconds (3.42 hours)\n\nTimestep: 2970000\nmean reward (100 episodes): 19.1200\nbest mean reward: 19.1200\ncurrent episode reward: 20.0000\nepisodes: 1580\nexploration: 0.03553\nlearning_rate: 0.00006\nelapsed time: 12345.4 seconds (3.43 hours)\n\nTimestep: 2980000\nmean reward (100 episodes): 19.1000\nbest mean reward: 19.1400\ncurrent episode reward: 15.0000\nepisodes: 1585\nexploration: 0.03520\nlearning_rate: 0.00006\nelapsed time: 12389.7 seconds (3.44 hours)\n\nTimestep: 2990000\nmean reward (100 episodes): 19.1300\nbest mean reward: 19.1500\ncurrent episode reward: 19.0000\nepisodes: 1591\nexploration: 0.03487\nlearning_rate: 0.00006\nelapsed time: 12433.9 seconds (3.45 hours)\n\nTimestep: 3000000\nmean reward (100 episodes): 19.0900\nbest mean reward: 19.1500\ncurrent episode reward: 19.0000\nepisodes: 1596\nexploration: 0.03455\nlearning_rate: 0.00006\nelapsed time: 12477.7 seconds (3.47 hours)\n\nTimestep: 3010000\nmean reward (100 episodes): 19.1000\nbest mean reward: 19.1500\ncurrent episode reward: 19.0000\nepisodes: 1601\nexploration: 0.03422\nlearning_rate: 0.00006\nelapsed time: 12521.6 seconds (3.48 hours)\n\nTimestep: 3020000\nmean reward (100 episodes): 19.1100\nbest mean reward: 19.1500\ncurrent episode reward: 20.0000\nepisodes: 1607\nexploration: 0.03389\nlearning_rate: 0.00006\nelapsed time: 12565.7 seconds (3.49 hours)\n\nTimestep: 3030000\nmean reward (100 episodes): 19.1400\nbest mean reward: 19.1600\ncurrent episode reward: 19.0000\nepisodes: 1612\nexploration: 0.03356\nlearning_rate: 0.00006\nelapsed time: 12609.1 seconds (3.50 hours)\n\nTimestep: 3040000\nmean reward (100 episodes): 19.0300\nbest mean reward: 19.1600\ncurrent episode reward: 17.0000\nepisodes: 1617\nexploration: 0.03324\nlearning_rate: 0.00006\nelapsed time: 12653.1 seconds (3.51 hours)\n\nTimestep: 3050000\nmean reward (100 episodes): 18.9900\nbest mean reward: 19.1600\ncurrent episode reward: 19.0000\nepisodes: 1622\nexploration: 0.03291\nlearning_rate: 0.00006\nelapsed time: 12697.2 seconds (3.53 hours)\n\nTimestep: 3060000\nmean reward (100 episodes): 19.0100\nbest mean reward: 19.1600\ncurrent episode reward: 19.0000\nepisodes: 1628\nexploration: 0.03258\nlearning_rate: 0.00006\nelapsed time: 12740.7 seconds (3.54 hours)\n\nTimestep: 3070000\nmean reward (100 episodes): 19.0600\nbest mean reward: 19.1600\ncurrent episode reward: 20.0000\nepisodes: 1633\nexploration: 0.03225\nlearning_rate: 0.00006\nelapsed time: 12784.3 seconds (3.55 hours)\n\nTimestep: 3080000\nmean reward (100 episodes): 19.0600\nbest mean reward: 19.1600\ncurrent episode reward: 17.0000\nepisodes: 1638\nexploration: 0.03193\nlearning_rate: 0.00006\nelapsed time: 12827.7 seconds (3.56 hours)\n\nTimestep: 3090000\nmean reward (100 episodes): 19.1000\nbest mean reward: 19.1600\ncurrent episode reward: 19.0000\nepisodes: 1644\nexploration: 0.03160\nlearning_rate: 0.00006\nelapsed time: 12871.9 seconds (3.58 hours)\n\nTimestep: 3100000\nmean reward (100 episodes): 19.1500\nbest mean reward: 19.1600\ncurrent episode reward: 20.0000\nepisodes: 1649\nexploration: 0.03127\nlearning_rate: 0.00006\nelapsed time: 12915.6 seconds (3.59 hours)\n\nTimestep: 3110000\nmean reward (100 episodes): 19.1700\nbest mean reward: 19.1800\ncurrent episode reward: 20.0000\nepisodes: 1654\nexploration: 0.03095\nlearning_rate: 0.00006\nelapsed time: 12959.3 seconds (3.60 hours)\n\nTimestep: 3120000\nmean reward (100 episodes): 19.1200\nbest mean reward: 19.1800\ncurrent episode reward: 19.0000\nepisodes: 1660\nexploration: 0.03062\nlearning_rate: 0.00006\nelapsed time: 13003.0 seconds (3.61 hours)\n\nTimestep: 3130000\nmean reward (100 episodes): 19.1100\nbest mean reward: 19.1800\ncurrent episode reward: 20.0000\nepisodes: 1665\nexploration: 0.03029\nlearning_rate: 0.00006\nelapsed time: 13047.8 seconds (3.62 hours)\n\nTimestep: 3140000\nmean reward (100 episodes): 19.0800\nbest mean reward: 19.1800\ncurrent episode reward: 21.0000\nepisodes: 1670\nexploration: 0.02996\nlearning_rate: 0.00006\nelapsed time: 13091.9 seconds (3.64 hours)\n\nTimestep: 3150000\nmean reward (100 episodes): 19.1000\nbest mean reward: 19.1800\ncurrent episode reward: 21.0000\nepisodes: 1676\nexploration: 0.02964\nlearning_rate: 0.00006\nelapsed time: 13135.4 seconds (3.65 hours)\n\nTimestep: 3160000\nmean reward (100 episodes): 19.0700\nbest mean reward: 19.1800\ncurrent episode reward: 18.0000\nepisodes: 1681\nexploration: 0.02931\nlearning_rate: 0.00006\nelapsed time: 13180.1 seconds (3.66 hours)\n\nTimestep: 3170000\nmean reward (100 episodes): 19.0600\nbest mean reward: 19.1800\ncurrent episode reward: 20.0000\nepisodes: 1687\nexploration: 0.02898\nlearning_rate: 0.00006\nelapsed time: 13224.1 seconds (3.67 hours)\n\nTimestep: 3180000\nmean reward (100 episodes): 19.0900\nbest mean reward: 19.1800\ncurrent episode reward: 20.0000\nepisodes: 1692\nexploration: 0.02865\nlearning_rate: 0.00006\nelapsed time: 13269.0 seconds (3.69 hours)\n\nTimestep: 3190000\nmean reward (100 episodes): 19.1500\nbest mean reward: 19.1800\ncurrent episode reward: 20.0000\nepisodes: 1698\nexploration: 0.02833\nlearning_rate: 0.00006\nelapsed time: 13313.5 seconds (3.70 hours)\n\nTimestep: 3200000\nmean reward (100 episodes): 19.1500\nbest mean reward: 19.1900\ncurrent episode reward: 18.0000\nepisodes: 1703\nexploration: 0.02800\nlearning_rate: 0.00006\nelapsed time: 13357.0 seconds (3.71 hours)\n\nTimestep: 3210000\nmean reward (100 episodes): 19.1400\nbest mean reward: 19.1900\ncurrent episode reward: 19.0000\nepisodes: 1708\nexploration: 0.02767\nlearning_rate: 0.00006\nelapsed time: 13400.5 seconds (3.72 hours)\n\nTimestep: 3220000\nmean reward (100 episodes): 19.2100\nbest mean reward: 19.2100\ncurrent episode reward: 20.0000\nepisodes: 1714\nexploration: 0.02735\nlearning_rate: 0.00006\nelapsed time: 13444.3 seconds (3.73 hours)\n\nTimestep: 3230000\nmean reward (100 episodes): 19.2900\nbest mean reward: 19.2900\ncurrent episode reward: 20.0000\nepisodes: 1719\nexploration: 0.02702\nlearning_rate: 0.00006\nelapsed time: 13488.6 seconds (3.75 hours)\n\nTimestep: 3240000\nmean reward (100 episodes): 19.2800\nbest mean reward: 19.2900\ncurrent episode reward: 18.0000\nepisodes: 1724\nexploration: 0.02669\nlearning_rate: 0.00006\nelapsed time: 13532.5 seconds (3.76 hours)\n\nTimestep: 3250000\nmean reward (100 episodes): 19.2400\nbest mean reward: 19.3000\ncurrent episode reward: 20.0000\nepisodes: 1729\nexploration: 0.02636\nlearning_rate: 0.00006\nelapsed time: 13576.6 seconds (3.77 hours)\n\nTimestep: 3260000\nmean reward (100 episodes): 19.2600\nbest mean reward: 19.3000\ncurrent episode reward: 20.0000\nepisodes: 1735\nexploration: 0.02604\nlearning_rate: 0.00006\nelapsed time: 13621.3 seconds (3.78 hours)\n\nTimestep: 3270000\nmean reward (100 episodes): 19.2900\nbest mean reward: 19.3000\ncurrent episode reward: 18.0000\nepisodes: 1740\nexploration: 0.02571\nlearning_rate: 0.00006\nelapsed time: 13664.6 seconds (3.80 hours)\n\nTimestep: 3280000\nmean reward (100 episodes): 19.2100\nbest mean reward: 19.3000\ncurrent episode reward: 19.0000\nepisodes: 1746\nexploration: 0.02538\nlearning_rate: 0.00006\nelapsed time: 13709.5 seconds (3.81 hours)\n\nTimestep: 3290000\nmean reward (100 episodes): 19.2100\nbest mean reward: 19.3000\ncurrent episode reward: 19.0000\nepisodes: 1751\nexploration: 0.02505\nlearning_rate: 0.00006\nelapsed time: 13754.8 seconds (3.82 hours)\n\nTimestep: 3300000\nmean reward (100 episodes): 19.2200\nbest mean reward: 19.3000\ncurrent episode reward: 20.0000\nepisodes: 1757\nexploration: 0.02473\nlearning_rate: 0.00006\nelapsed time: 13799.6 seconds (3.83 hours)\n\nTimestep: 3310000\nmean reward (100 episodes): 19.2800\nbest mean reward: 19.3000\ncurrent episode reward: 19.0000\nepisodes: 1762\nexploration: 0.02440\nlearning_rate: 0.00006\nelapsed time: 13843.3 seconds (3.85 hours)\n\nTimestep: 3320000\nmean reward (100 episodes): 19.3500\nbest mean reward: 19.3500\ncurrent episode reward: 19.0000\nepisodes: 1768\nexploration: 0.02407\nlearning_rate: 0.00006\nelapsed time: 13887.5 seconds (3.86 hours)\n\nTimestep: 3330000\nmean reward (100 episodes): 19.3000\nbest mean reward: 19.3500\ncurrent episode reward: 21.0000\nepisodes: 1773\nexploration: 0.02375\nlearning_rate: 0.00006\nelapsed time: 13931.2 seconds (3.87 hours)\n\nTimestep: 3340000\nmean reward (100 episodes): 19.2900\nbest mean reward: 19.3500\ncurrent episode reward: 20.0000\nepisodes: 1779\nexploration: 0.02342\nlearning_rate: 0.00006\nelapsed time: 13975.3 seconds (3.88 hours)\n\nTimestep: 3350000\nmean reward (100 episodes): 19.3700\nbest mean reward: 19.3700\ncurrent episode reward: 20.0000\nepisodes: 1785\nexploration: 0.02309\nlearning_rate: 0.00006\nelapsed time: 14019.9 seconds (3.89 hours)\n\nTimestep: 3360000\nmean reward (100 episodes): 19.4100\nbest mean reward: 19.4100\ncurrent episode reward: 21.0000\nepisodes: 1790\nexploration: 0.02276\nlearning_rate: 0.00006\nelapsed time: 14063.7 seconds (3.91 hours)\n\nTimestep: 3370000\nmean reward (100 episodes): 19.4600\nbest mean reward: 19.4700\ncurrent episode reward: 20.0000\nepisodes: 1795\nexploration: 0.02244\nlearning_rate: 0.00006\nelapsed time: 14107.8 seconds (3.92 hours)\n\nTimestep: 3380000\nmean reward (100 episodes): 19.4300\nbest mean reward: 19.4700\ncurrent episode reward: 19.0000\nepisodes: 1801\nexploration: 0.02211\nlearning_rate: 0.00006\nelapsed time: 14151.6 seconds (3.93 hours)\n\nTimestep: 3390000\nmean reward (100 episodes): 19.5000\nbest mean reward: 19.5000\ncurrent episode reward: 21.0000\nepisodes: 1807\nexploration: 0.02178\nlearning_rate: 0.00006\nelapsed time: 14196.0 seconds (3.94 hours)\n\nTimestep: 3400000\nmean reward (100 episodes): 19.5300\nbest mean reward: 19.5400\ncurrent episode reward: 20.0000\nepisodes: 1812\nexploration: 0.02145\nlearning_rate: 0.00006\nelapsed time: 14239.4 seconds (3.96 hours)\n\nTimestep: 3410000\nmean reward (100 episodes): 19.5700\nbest mean reward: 19.5700\ncurrent episode reward: 20.0000\nepisodes: 1818\nexploration: 0.02113\nlearning_rate: 0.00006\nelapsed time: 14284.0 seconds (3.97 hours)\n\nTimestep: 3420000\nmean reward (100 episodes): 19.5900\nbest mean reward: 19.5900\ncurrent episode reward: 20.0000\nepisodes: 1824\nexploration: 0.02080\nlearning_rate: 0.00006\nelapsed time: 14327.9 seconds (3.98 hours)\n\nTimestep: 3430000\nmean reward (100 episodes): 19.6900\nbest mean reward: 19.6900\ncurrent episode reward: 20.0000\nepisodes: 1829\nexploration: 0.02047\nlearning_rate: 0.00006\nelapsed time: 14372.5 seconds (3.99 hours)\n\nTimestep: 3440000\nmean reward (100 episodes): 19.7300\nbest mean reward: 19.7300\ncurrent episode reward: 20.0000\nepisodes: 1835\nexploration: 0.02015\nlearning_rate: 0.00006\nelapsed time: 14416.2 seconds (4.00 hours)\n\nTimestep: 3450000\nmean reward (100 episodes): 19.8300\nbest mean reward: 19.8300\ncurrent episode reward: 21.0000\nepisodes: 1841\nexploration: 0.01982\nlearning_rate: 0.00006\nelapsed time: 14460.0 seconds (4.02 hours)\n\nTimestep: 3460000\nmean reward (100 episodes): 19.9000\nbest mean reward: 19.9100\ncurrent episode reward: 20.0000\nepisodes: 1847\nexploration: 0.01949\nlearning_rate: 0.00005\nelapsed time: 14504.0 seconds (4.03 hours)\n\nTimestep: 3470000\nmean reward (100 episodes): 19.9500\nbest mean reward: 19.9500\ncurrent episode reward: 20.0000\nepisodes: 1852\nexploration: 0.01916\nlearning_rate: 0.00005\nelapsed time: 14548.5 seconds (4.04 hours)\n\nTimestep: 3480000\nmean reward (100 episodes): 19.9600\nbest mean reward: 19.9600\ncurrent episode reward: 19.0000\nepisodes: 1858\nexploration: 0.01884\nlearning_rate: 0.00005\nelapsed time: 14592.3 seconds (4.05 hours)\n\nTimestep: 3490000\nmean reward (100 episodes): 19.9500\nbest mean reward: 19.9700\ncurrent episode reward: 21.0000\nepisodes: 1863\nexploration: 0.01851\nlearning_rate: 0.00005\nelapsed time: 14636.6 seconds (4.07 hours)\n\nTimestep: 3500000\nmean reward (100 episodes): 19.9700\nbest mean reward: 19.9700\ncurrent episode reward: 20.0000\nepisodes: 1869\nexploration: 0.01818\nlearning_rate: 0.00005\nelapsed time: 14680.5 seconds (4.08 hours)\n\nTimestep: 3510000\nmean reward (100 episodes): 19.9600\nbest mean reward: 20.0000\ncurrent episode reward: 18.0000\nepisodes: 1875\nexploration: 0.01785\nlearning_rate: 0.00005\nelapsed time: 14724.5 seconds (4.09 hours)\n\nTimestep: 3520000\nmean reward (100 episodes): 19.9800\nbest mean reward: 20.0000\ncurrent episode reward: 19.0000\nepisodes: 1880\nexploration: 0.01753\nlearning_rate: 0.00005\nelapsed time: 14769.2 seconds (4.10 hours)\n\nTimestep: 3530000\nmean reward (100 episodes): 20.0200\nbest mean reward: 20.0200\ncurrent episode reward: 21.0000\nepisodes: 1886\nexploration: 0.01720\nlearning_rate: 0.00005\nelapsed time: 14813.1 seconds (4.11 hours)\n\nTimestep: 3540000\nmean reward (100 episodes): 20.0200\nbest mean reward: 20.0300\ncurrent episode reward: 21.0000\nepisodes: 1892\nexploration: 0.01687\nlearning_rate: 0.00005\nelapsed time: 14857.5 seconds (4.13 hours)\n\nTimestep: 3550000\nmean reward (100 episodes): 20.0500\nbest mean reward: 20.0500\ncurrent episode reward: 20.0000\nepisodes: 1898\nexploration: 0.01655\nlearning_rate: 0.00005\nelapsed time: 14901.7 seconds (4.14 hours)\n\nTimestep: 3560000\nmean reward (100 episodes): 20.0800\nbest mean reward: 20.0800\ncurrent episode reward: 21.0000\nepisodes: 1903\nexploration: 0.01622\nlearning_rate: 0.00005\nelapsed time: 14946.3 seconds (4.15 hours)\n\nTimestep: 3570000\nmean reward (100 episodes): 20.0900\nbest mean reward: 20.0900\ncurrent episode reward: 21.0000\nepisodes: 1909\nexploration: 0.01589\nlearning_rate: 0.00005\nelapsed time: 14991.0 seconds (4.16 hours)\n\nTimestep: 3580000\nmean reward (100 episodes): 20.1100\nbest mean reward: 20.1200\ncurrent episode reward: 20.0000\nepisodes: 1915\nexploration: 0.01556\nlearning_rate: 0.00005\nelapsed time: 15035.4 seconds (4.18 hours)\n\nTimestep: 3590000\nmean reward (100 episodes): 20.0900\nbest mean reward: 20.1200\ncurrent episode reward: 21.0000\nepisodes: 1920\nexploration: 0.01524\nlearning_rate: 0.00005\nelapsed time: 15079.9 seconds (4.19 hours)\n\nTimestep: 3600000\nmean reward (100 episodes): 20.1100\nbest mean reward: 20.1200\ncurrent episode reward: 20.0000\nepisodes: 1926\nexploration: 0.01491\nlearning_rate: 0.00005\nelapsed time: 15124.2 seconds (4.20 hours)\n\nTimestep: 3610000\nmean reward (100 episodes): 20.0800\nbest mean reward: 20.1200\ncurrent episode reward: 18.0000\nepisodes: 1931\nexploration: 0.01458\nlearning_rate: 0.00005\nelapsed time: 15168.5 seconds (4.21 hours)\n\nTimestep: 3620000\nmean reward (100 episodes): 20.0600\nbest mean reward: 20.1200\ncurrent episode reward: 20.0000\nepisodes: 1937\nexploration: 0.01425\nlearning_rate: 0.00005\nelapsed time: 15213.3 seconds (4.23 hours)\n\nTimestep: 3630000\nmean reward (100 episodes): 20.0000\nbest mean reward: 20.1200\ncurrent episode reward: 19.0000\nepisodes: 1942\nexploration: 0.01393\nlearning_rate: 0.00005\nelapsed time: 15258.0 seconds (4.24 hours)\n\nTimestep: 3640000\nmean reward (100 episodes): 20.0300\nbest mean reward: 20.1200\ncurrent episode reward: 21.0000\nepisodes: 1948\nexploration: 0.01360\nlearning_rate: 0.00005\nelapsed time: 15301.9 seconds (4.25 hours)\n\nTimestep: 3650000\nmean reward (100 episodes): 20.0400\nbest mean reward: 20.1200\ncurrent episode reward: 20.0000\nepisodes: 1954\nexploration: 0.01327\nlearning_rate: 0.00005\nelapsed time: 15346.1 seconds (4.26 hours)\n\nTimestep: 3660000\nmean reward (100 episodes): 20.0600\nbest mean reward: 20.1200\ncurrent episode reward: 21.0000\nepisodes: 1960\nexploration: 0.01295\nlearning_rate: 0.00005\nelapsed time: 15390.3 seconds (4.28 hours)\n\nTimestep: 3670000\nmean reward (100 episodes): 20.1000\nbest mean reward: 20.1200\ncurrent episode reward: 20.0000\nepisodes: 1965\nexploration: 0.01262\nlearning_rate: 0.00005\nelapsed time: 15434.3 seconds (4.29 hours)\n\nTimestep: 3680000\nmean reward (100 episodes): 20.1300\nbest mean reward: 20.1300\ncurrent episode reward: 20.0000\nepisodes: 1971\nexploration: 0.01229\nlearning_rate: 0.00005\nelapsed time: 15478.0 seconds (4.30 hours)\n\nTimestep: 3690000\nmean reward (100 episodes): 20.1500\nbest mean reward: 20.1500\ncurrent episode reward: 21.0000\nepisodes: 1977\nexploration: 0.01196\nlearning_rate: 0.00005\nelapsed time: 15522.4 seconds (4.31 hours)\n\nTimestep: 3700000\nmean reward (100 episodes): 20.1600\nbest mean reward: 20.1600\ncurrent episode reward: 21.0000\nepisodes: 1983\nexploration: 0.01164\nlearning_rate: 0.00005\nelapsed time: 15566.9 seconds (4.32 hours)\n\nTimestep: 3710000\nmean reward (100 episodes): 20.1400\nbest mean reward: 20.1600\ncurrent episode reward: 20.0000\nepisodes: 1989\nexploration: 0.01131\nlearning_rate: 0.00005\nelapsed time: 15611.6 seconds (4.34 hours)\n\nTimestep: 3720000\nmean reward (100 episodes): 20.1400\nbest mean reward: 20.1600\ncurrent episode reward: 20.0000\nepisodes: 1994\nexploration: 0.01098\nlearning_rate: 0.00005\nelapsed time: 15655.8 seconds (4.35 hours)\n\nTimestep: 3730000\nmean reward (100 episodes): 20.1900\nbest mean reward: 20.2100\ncurrent episode reward: 19.0000\nepisodes: 2000\nexploration: 0.01065\nlearning_rate: 0.00005\nelapsed time: 15702.1 seconds (4.36 hours)\n\nTimestep: 3740000\nmean reward (100 episodes): 20.2000\nbest mean reward: 20.2100\ncurrent episode reward: 20.0000\nepisodes: 2006\nexploration: 0.01033\nlearning_rate: 0.00005\nelapsed time: 15747.8 seconds (4.37 hours)\n\nTimestep: 3750000\nmean reward (100 episodes): 20.1900\nbest mean reward: 20.2100\ncurrent episode reward: 20.0000\nepisodes: 2012\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 15792.3 seconds (4.39 hours)\n\nTimestep: 3760000\nmean reward (100 episodes): 20.2100\nbest mean reward: 20.2100\ncurrent episode reward: 21.0000\nepisodes: 2018\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 15836.1 seconds (4.40 hours)\n\nTimestep: 3770000\nmean reward (100 episodes): 20.2700\nbest mean reward: 20.2700\ncurrent episode reward: 20.0000\nepisodes: 2024\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 15879.6 seconds (4.41 hours)\n\nTimestep: 3780000\nmean reward (100 episodes): 20.2800\nbest mean reward: 20.2800\ncurrent episode reward: 21.0000\nepisodes: 2029\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 15924.1 seconds (4.42 hours)\n\nTimestep: 3790000\nmean reward (100 episodes): 20.3100\nbest mean reward: 20.3100\ncurrent episode reward: 21.0000\nepisodes: 2035\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 15968.1 seconds (4.44 hours)\n\nTimestep: 3800000\nmean reward (100 episodes): 20.3700\nbest mean reward: 20.3700\ncurrent episode reward: 21.0000\nepisodes: 2041\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16012.3 seconds (4.45 hours)\n\nTimestep: 3810000\nmean reward (100 episodes): 20.3900\nbest mean reward: 20.3900\ncurrent episode reward: 19.0000\nepisodes: 2047\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16057.1 seconds (4.46 hours)\n\nTimestep: 3820000\nmean reward (100 episodes): 20.3800\nbest mean reward: 20.4000\ncurrent episode reward: 19.0000\nepisodes: 2052\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16101.0 seconds (4.47 hours)\n\nTimestep: 3830000\nmean reward (100 episodes): 20.4100\nbest mean reward: 20.4100\ncurrent episode reward: 20.0000\nepisodes: 2058\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16145.6 seconds (4.48 hours)\n\nTimestep: 3840000\nmean reward (100 episodes): 20.3700\nbest mean reward: 20.4100\ncurrent episode reward: 20.0000\nepisodes: 2064\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16190.9 seconds (4.50 hours)\n\nTimestep: 3850000\nmean reward (100 episodes): 20.3500\nbest mean reward: 20.4100\ncurrent episode reward: 19.0000\nepisodes: 2070\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16235.4 seconds (4.51 hours)\n\nTimestep: 3860000\nmean reward (100 episodes): 20.4000\nbest mean reward: 20.4100\ncurrent episode reward: 20.0000\nepisodes: 2076\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16280.0 seconds (4.52 hours)\n\nTimestep: 3870000\nmean reward (100 episodes): 20.4200\nbest mean reward: 20.4200\ncurrent episode reward: 21.0000\nepisodes: 2081\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16324.7 seconds (4.53 hours)\n\nTimestep: 3880000\nmean reward (100 episodes): 20.4700\nbest mean reward: 20.4700\ncurrent episode reward: 21.0000\nepisodes: 2088\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16368.7 seconds (4.55 hours)\n\nTimestep: 3890000\nmean reward (100 episodes): 20.4500\nbest mean reward: 20.4700\ncurrent episode reward: 20.0000\nepisodes: 2093\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16413.4 seconds (4.56 hours)\n\nTimestep: 3900000\nmean reward (100 episodes): 20.4500\nbest mean reward: 20.4700\ncurrent episode reward: 20.0000\nepisodes: 2099\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16458.4 seconds (4.57 hours)\n\nTimestep: 3910000\nmean reward (100 episodes): 20.4400\nbest mean reward: 20.4700\ncurrent episode reward: 20.0000\nepisodes: 2105\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16503.1 seconds (4.58 hours)\n\nTimestep: 3920000\nmean reward (100 episodes): 20.4500\nbest mean reward: 20.4700\ncurrent episode reward: 21.0000\nepisodes: 2111\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16547.6 seconds (4.60 hours)\n\nTimestep: 3930000\nmean reward (100 episodes): 20.4500\nbest mean reward: 20.4700\ncurrent episode reward: 21.0000\nepisodes: 2117\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16592.6 seconds (4.61 hours)\n\nTimestep: 3940000\nmean reward (100 episodes): 20.4600\nbest mean reward: 20.4700\ncurrent episode reward: 21.0000\nepisodes: 2123\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16636.7 seconds (4.62 hours)\n\nTimestep: 3950000\nmean reward (100 episodes): 20.4600\nbest mean reward: 20.4700\ncurrent episode reward: 21.0000\nepisodes: 2128\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16681.1 seconds (4.63 hours)\n\nTimestep: 3960000\nmean reward (100 episodes): 20.4700\nbest mean reward: 20.4800\ncurrent episode reward: 20.0000\nepisodes: 2134\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16725.0 seconds (4.65 hours)\n\nTimestep: 3970000\nmean reward (100 episodes): 20.4300\nbest mean reward: 20.4800\ncurrent episode reward: 21.0000\nepisodes: 2140\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16768.9 seconds (4.66 hours)\n\nTimestep: 3980000\nmean reward (100 episodes): 20.4500\nbest mean reward: 20.4800\ncurrent episode reward: 21.0000\nepisodes: 2146\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16813.2 seconds (4.67 hours)\n\nTimestep: 3990000\nmean reward (100 episodes): 20.4500\nbest mean reward: 20.4800\ncurrent episode reward: 21.0000\nepisodes: 2151\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16858.5 seconds (4.68 hours)\n\nTimestep: 4000000\nmean reward (100 episodes): 20.4400\nbest mean reward: 20.4900\ncurrent episode reward: 19.0000\nepisodes: 2157\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16902.3 seconds (4.70 hours)\n\nTimestep: 4010000\nmean reward (100 episodes): 20.4600\nbest mean reward: 20.4900\ncurrent episode reward: 21.0000\nepisodes: 2163\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16946.4 seconds (4.71 hours)\n\nTimestep: 4020000\nmean reward (100 episodes): 20.4900\nbest mean reward: 20.4900\ncurrent episode reward: 21.0000\nepisodes: 2169\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 16991.0 seconds (4.72 hours)\n\nTimestep: 4030000\nmean reward (100 episodes): 20.5100\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2175\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17034.7 seconds (4.73 hours)\n\nTimestep: 4040000\nmean reward (100 episodes): 20.4900\nbest mean reward: 20.5200\ncurrent episode reward: 20.0000\nepisodes: 2181\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17078.8 seconds (4.74 hours)\n\nTimestep: 4050000\nmean reward (100 episodes): 20.4800\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2186\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17122.6 seconds (4.76 hours)\n\nTimestep: 4060000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2193\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17166.8 seconds (4.77 hours)\n\nTimestep: 4070000\nmean reward (100 episodes): 20.5000\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2198\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17210.3 seconds (4.78 hours)\n\nTimestep: 4080000\nmean reward (100 episodes): 20.5100\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2204\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17254.3 seconds (4.79 hours)\n\nTimestep: 4090000\nmean reward (100 episodes): 20.5100\nbest mean reward: 20.5200\ncurrent episode reward: 21.0000\nepisodes: 2210\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17299.4 seconds (4.81 hours)\n\nTimestep: 4100000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5300\ncurrent episode reward: 20.0000\nepisodes: 2216\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17344.1 seconds (4.82 hours)\n\nTimestep: 4110000\nmean reward (100 episodes): 20.4800\nbest mean reward: 20.5300\ncurrent episode reward: 20.0000\nepisodes: 2222\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17388.7 seconds (4.83 hours)\n\nTimestep: 4120000\nmean reward (100 episodes): 20.4800\nbest mean reward: 20.5300\ncurrent episode reward: 21.0000\nepisodes: 2228\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17433.7 seconds (4.84 hours)\n\nTimestep: 4130000\nmean reward (100 episodes): 20.4900\nbest mean reward: 20.5300\ncurrent episode reward: 21.0000\nepisodes: 2234\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17478.0 seconds (4.86 hours)\n\nTimestep: 4140000\nmean reward (100 episodes): 20.5300\nbest mean reward: 20.5300\ncurrent episode reward: 21.0000\nepisodes: 2240\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17523.0 seconds (4.87 hours)\n\nTimestep: 4150000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5300\ncurrent episode reward: 21.0000\nepisodes: 2245\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17566.5 seconds (4.88 hours)\n\nTimestep: 4160000\nmean reward (100 episodes): 20.5000\nbest mean reward: 20.5300\ncurrent episode reward: 19.0000\nepisodes: 2251\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17610.6 seconds (4.89 hours)\n\nTimestep: 4170000\nmean reward (100 episodes): 20.5400\nbest mean reward: 20.5400\ncurrent episode reward: 21.0000\nepisodes: 2257\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17654.3 seconds (4.90 hours)\n\nTimestep: 4180000\nmean reward (100 episodes): 20.5700\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2263\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17698.6 seconds (4.92 hours)\n\nTimestep: 4190000\nmean reward (100 episodes): 20.5700\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2269\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17743.3 seconds (4.93 hours)\n\nTimestep: 4200000\nmean reward (100 episodes): 20.5300\nbest mean reward: 20.5700\ncurrent episode reward: 19.0000\nepisodes: 2275\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17787.4 seconds (4.94 hours)\n\nTimestep: 4210000\nmean reward (100 episodes): 20.5400\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2281\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17832.9 seconds (4.95 hours)\n\nTimestep: 4220000\nmean reward (100 episodes): 20.5000\nbest mean reward: 20.5700\ncurrent episode reward: 19.0000\nepisodes: 2286\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17876.9 seconds (4.97 hours)\n\nTimestep: 4230000\nmean reward (100 episodes): 20.4900\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2292\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17921.3 seconds (4.98 hours)\n\nTimestep: 4240000\nmean reward (100 episodes): 20.5100\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2298\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 17966.4 seconds (4.99 hours)\n\nTimestep: 4250000\nmean reward (100 episodes): 20.5100\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2304\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18011.1 seconds (5.00 hours)\n\nTimestep: 4260000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2310\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18055.6 seconds (5.02 hours)\n\nTimestep: 4270000\nmean reward (100 episodes): 20.5300\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2316\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18099.3 seconds (5.03 hours)\n\nTimestep: 4280000\nmean reward (100 episodes): 20.5300\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2322\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18143.7 seconds (5.04 hours)\n\nTimestep: 4290000\nmean reward (100 episodes): 20.5400\nbest mean reward: 20.5700\ncurrent episode reward: 19.0000\nepisodes: 2328\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18188.6 seconds (5.05 hours)\n\nTimestep: 4300000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2334\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18233.5 seconds (5.06 hours)\n\nTimestep: 4310000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2340\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18277.8 seconds (5.08 hours)\n\nTimestep: 4320000\nmean reward (100 episodes): 20.4800\nbest mean reward: 20.5700\ncurrent episode reward: 19.0000\nepisodes: 2345\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18322.5 seconds (5.09 hours)\n\nTimestep: 4330000\nmean reward (100 episodes): 20.5000\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2351\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18366.6 seconds (5.10 hours)\n\nTimestep: 4340000\nmean reward (100 episodes): 20.4700\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2357\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18410.4 seconds (5.11 hours)\n\nTimestep: 4350000\nmean reward (100 episodes): 20.4700\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2363\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18455.5 seconds (5.13 hours)\n\nTimestep: 4360000\nmean reward (100 episodes): 20.4600\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2369\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18500.0 seconds (5.14 hours)\n\nTimestep: 4370000\nmean reward (100 episodes): 20.5100\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2375\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18543.9 seconds (5.15 hours)\n\nTimestep: 4380000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2381\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18588.5 seconds (5.16 hours)\n\nTimestep: 4390000\nmean reward (100 episodes): 20.5600\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2387\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18632.6 seconds (5.18 hours)\n\nTimestep: 4400000\nmean reward (100 episodes): 20.5400\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2393\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18677.0 seconds (5.19 hours)\n\nTimestep: 4410000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2399\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18720.9 seconds (5.20 hours)\n\nTimestep: 4420000\nmean reward (100 episodes): 20.5300\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2405\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18765.5 seconds (5.21 hours)\n\nTimestep: 4430000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2411\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18810.2 seconds (5.23 hours)\n\nTimestep: 4440000\nmean reward (100 episodes): 20.5100\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2416\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18854.3 seconds (5.24 hours)\n\nTimestep: 4450000\nmean reward (100 episodes): 20.5300\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2422\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18898.5 seconds (5.25 hours)\n\nTimestep: 4460000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2428\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18943.3 seconds (5.26 hours)\n\nTimestep: 4470000\nmean reward (100 episodes): 20.5100\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2434\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 18986.9 seconds (5.27 hours)\n\nTimestep: 4480000\nmean reward (100 episodes): 20.4800\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2440\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19032.0 seconds (5.29 hours)\n\nTimestep: 4490000\nmean reward (100 episodes): 20.5300\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2446\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19076.7 seconds (5.30 hours)\n\nTimestep: 4500000\nmean reward (100 episodes): 20.5300\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2451\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19120.7 seconds (5.31 hours)\n\nTimestep: 4510000\nmean reward (100 episodes): 20.5500\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2457\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19164.7 seconds (5.32 hours)\n\nTimestep: 4520000\nmean reward (100 episodes): 20.5500\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2463\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19209.1 seconds (5.34 hours)\n\nTimestep: 4530000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2469\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19252.8 seconds (5.35 hours)\n\nTimestep: 4540000\nmean reward (100 episodes): 20.5000\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2475\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19296.8 seconds (5.36 hours)\n\nTimestep: 4550000\nmean reward (100 episodes): 20.5000\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2481\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19341.1 seconds (5.37 hours)\n\nTimestep: 4560000\nmean reward (100 episodes): 20.4800\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2486\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19385.9 seconds (5.38 hours)\n\nTimestep: 4570000\nmean reward (100 episodes): 20.4900\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2492\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19429.6 seconds (5.40 hours)\n\nTimestep: 4580000\nmean reward (100 episodes): 20.4500\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2498\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19473.7 seconds (5.41 hours)\n\nTimestep: 4590000\nmean reward (100 episodes): 20.4300\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2504\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19518.5 seconds (5.42 hours)\n\nTimestep: 4600000\nmean reward (100 episodes): 20.4400\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2510\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19563.7 seconds (5.43 hours)\n\nTimestep: 4610000\nmean reward (100 episodes): 20.4600\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2516\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19609.5 seconds (5.45 hours)\n\nTimestep: 4620000\nmean reward (100 episodes): 20.4500\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2522\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19654.1 seconds (5.46 hours)\n\nTimestep: 4630000\nmean reward (100 episodes): 20.4400\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2528\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19698.6 seconds (5.47 hours)\n\nTimestep: 4640000\nmean reward (100 episodes): 20.4500\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2534\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19743.3 seconds (5.48 hours)\n\nTimestep: 4650000\nmean reward (100 episodes): 20.4700\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2539\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19787.9 seconds (5.50 hours)\n\nTimestep: 4660000\nmean reward (100 episodes): 20.4700\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2545\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19833.0 seconds (5.51 hours)\n\nTimestep: 4670000\nmean reward (100 episodes): 20.5000\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2551\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19876.8 seconds (5.52 hours)\n\nTimestep: 4680000\nmean reward (100 episodes): 20.4900\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2557\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19921.4 seconds (5.53 hours)\n\nTimestep: 4690000\nmean reward (100 episodes): 20.4700\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2563\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 19965.5 seconds (5.55 hours)\n\nTimestep: 4700000\nmean reward (100 episodes): 20.4700\nbest mean reward: 20.5700\ncurrent episode reward: 19.0000\nepisodes: 2569\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20010.5 seconds (5.56 hours)\n\nTimestep: 4710000\nmean reward (100 episodes): 20.4500\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2574\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20054.8 seconds (5.57 hours)\n\nTimestep: 4720000\nmean reward (100 episodes): 20.4500\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2580\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20099.2 seconds (5.58 hours)\n\nTimestep: 4730000\nmean reward (100 episodes): 20.4700\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2586\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20143.7 seconds (5.60 hours)\n\nTimestep: 4740000\nmean reward (100 episodes): 20.4700\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2592\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20188.1 seconds (5.61 hours)\n\nTimestep: 4750000\nmean reward (100 episodes): 20.5100\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2598\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20233.0 seconds (5.62 hours)\n\nTimestep: 4760000\nmean reward (100 episodes): 20.5000\nbest mean reward: 20.5700\ncurrent episode reward: 20.0000\nepisodes: 2604\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20276.9 seconds (5.63 hours)\n\nTimestep: 4770000\nmean reward (100 episodes): 20.4900\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2609\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20321.7 seconds (5.64 hours)\n\nTimestep: 4780000\nmean reward (100 episodes): 20.4900\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2615\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20366.3 seconds (5.66 hours)\n\nTimestep: 4790000\nmean reward (100 episodes): 20.5100\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2621\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20410.3 seconds (5.67 hours)\n\nTimestep: 4800000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2627\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20454.6 seconds (5.68 hours)\n\nTimestep: 4810000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5700\ncurrent episode reward: 19.0000\nepisodes: 2633\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20499.3 seconds (5.69 hours)\n\nTimestep: 4820000\nmean reward (100 episodes): 20.5500\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2639\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20544.6 seconds (5.71 hours)\n\nTimestep: 4830000\nmean reward (100 episodes): 20.5600\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2645\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20589.1 seconds (5.72 hours)\n\nTimestep: 4840000\nmean reward (100 episodes): 20.5400\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2651\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20633.2 seconds (5.73 hours)\n\nTimestep: 4850000\nmean reward (100 episodes): 20.5400\nbest mean reward: 20.5700\ncurrent episode reward: 21.0000\nepisodes: 2657\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20678.4 seconds (5.74 hours)\n\nTimestep: 4860000\nmean reward (100 episodes): 20.5400\nbest mean reward: 20.5700\ncurrent episode reward: 19.0000\nepisodes: 2663\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20723.1 seconds (5.76 hours)\n\nTimestep: 4870000\nmean reward (100 episodes): 20.5500\nbest mean reward: 20.5700\ncurrent episode reward: 19.0000\nepisodes: 2668\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20767.2 seconds (5.77 hours)\n\nTimestep: 4880000\nmean reward (100 episodes): 20.5700\nbest mean reward: 20.5800\ncurrent episode reward: 20.0000\nepisodes: 2674\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20811.8 seconds (5.78 hours)\n\nTimestep: 4890000\nmean reward (100 episodes): 20.5600\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2680\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20855.4 seconds (5.79 hours)\n\nTimestep: 4900000\nmean reward (100 episodes): 20.5300\nbest mean reward: 20.5800\ncurrent episode reward: 20.0000\nepisodes: 2686\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20899.4 seconds (5.81 hours)\n\nTimestep: 4910000\nmean reward (100 episodes): 20.5000\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2692\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20944.3 seconds (5.82 hours)\n\nTimestep: 4920000\nmean reward (100 episodes): 20.5100\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2698\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 20988.6 seconds (5.83 hours)\n\nTimestep: 4930000\nmean reward (100 episodes): 20.5300\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2703\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21033.4 seconds (5.84 hours)\n\nTimestep: 4940000\nmean reward (100 episodes): 20.5500\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2709\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21078.2 seconds (5.86 hours)\n\nTimestep: 4950000\nmean reward (100 episodes): 20.5400\nbest mean reward: 20.5800\ncurrent episode reward: 20.0000\nepisodes: 2715\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21122.7 seconds (5.87 hours)\n\nTimestep: 4960000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5800\ncurrent episode reward: 19.0000\nepisodes: 2721\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21167.6 seconds (5.88 hours)\n\nTimestep: 4970000\nmean reward (100 episodes): 20.4900\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2727\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21212.0 seconds (5.89 hours)\n\nTimestep: 4980000\nmean reward (100 episodes): 20.4900\nbest mean reward: 20.5800\ncurrent episode reward: 20.0000\nepisodes: 2733\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21256.6 seconds (5.90 hours)\n\nTimestep: 4990000\nmean reward (100 episodes): 20.4500\nbest mean reward: 20.5800\ncurrent episode reward: 20.0000\nepisodes: 2739\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21301.1 seconds (5.92 hours)\n\nTimestep: 5000000\nmean reward (100 episodes): 20.4200\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2745\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21345.6 seconds (5.93 hours)\n\nTimestep: 5010000\nmean reward (100 episodes): 20.4400\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2751\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21389.5 seconds (5.94 hours)\n\nTimestep: 5020000\nmean reward (100 episodes): 20.4600\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2757\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21434.0 seconds (5.95 hours)\n\nTimestep: 5030000\nmean reward (100 episodes): 20.4200\nbest mean reward: 20.5800\ncurrent episode reward: 19.0000\nepisodes: 2762\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21477.9 seconds (5.97 hours)\n\nTimestep: 5040000\nmean reward (100 episodes): 20.4400\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2768\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21522.2 seconds (5.98 hours)\n\nTimestep: 5050000\nmean reward (100 episodes): 20.4600\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2774\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21566.3 seconds (5.99 hours)\n\nTimestep: 5060000\nmean reward (100 episodes): 20.4700\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2780\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21610.1 seconds (6.00 hours)\n\nTimestep: 5070000\nmean reward (100 episodes): 20.5100\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2786\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21654.0 seconds (6.02 hours)\n\nTimestep: 5080000\nmean reward (100 episodes): 20.5500\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2792\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21698.4 seconds (6.03 hours)\n\nTimestep: 5090000\nmean reward (100 episodes): 20.5400\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2798\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21742.4 seconds (6.04 hours)\n\nTimestep: 5100000\nmean reward (100 episodes): 20.5300\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2804\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21786.9 seconds (6.05 hours)\n\nTimestep: 5110000\nmean reward (100 episodes): 20.5300\nbest mean reward: 20.5800\ncurrent episode reward: 20.0000\nepisodes: 2810\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21831.7 seconds (6.06 hours)\n\nTimestep: 5120000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5800\ncurrent episode reward: 20.0000\nepisodes: 2816\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21876.1 seconds (6.08 hours)\n\nTimestep: 5130000\nmean reward (100 episodes): 20.4900\nbest mean reward: 20.5800\ncurrent episode reward: 20.0000\nepisodes: 2821\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21920.8 seconds (6.09 hours)\n\nTimestep: 5140000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2827\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 21965.7 seconds (6.10 hours)\n\nTimestep: 5150000\nmean reward (100 episodes): 20.5100\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2833\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22010.3 seconds (6.11 hours)\n\nTimestep: 5160000\nmean reward (100 episodes): 20.4900\nbest mean reward: 20.5800\ncurrent episode reward: 20.0000\nepisodes: 2839\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22054.8 seconds (6.13 hours)\n\nTimestep: 5170000\nmean reward (100 episodes): 20.5300\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2845\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22099.1 seconds (6.14 hours)\n\nTimestep: 5180000\nmean reward (100 episodes): 20.5300\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2851\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22143.6 seconds (6.15 hours)\n\nTimestep: 5190000\nmean reward (100 episodes): 20.5000\nbest mean reward: 20.5800\ncurrent episode reward: 20.0000\nepisodes: 2857\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22187.5 seconds (6.16 hours)\n\nTimestep: 5200000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2863\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22231.9 seconds (6.18 hours)\n\nTimestep: 5210000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2869\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22276.8 seconds (6.19 hours)\n\nTimestep: 5220000\nmean reward (100 episodes): 20.5000\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2875\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22321.5 seconds (6.20 hours)\n\nTimestep: 5230000\nmean reward (100 episodes): 20.4700\nbest mean reward: 20.5800\ncurrent episode reward: 20.0000\nepisodes: 2880\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22365.8 seconds (6.21 hours)\n\nTimestep: 5240000\nmean reward (100 episodes): 20.4600\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2886\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22410.6 seconds (6.23 hours)\n\nTimestep: 5250000\nmean reward (100 episodes): 20.4500\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2892\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22454.7 seconds (6.24 hours)\n\nTimestep: 5260000\nmean reward (100 episodes): 20.4300\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2898\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22498.7 seconds (6.25 hours)\n\nTimestep: 5270000\nmean reward (100 episodes): 20.4300\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2904\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22542.6 seconds (6.26 hours)\n\nTimestep: 5280000\nmean reward (100 episodes): 20.4100\nbest mean reward: 20.5800\ncurrent episode reward: 20.0000\nepisodes: 2910\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22587.3 seconds (6.27 hours)\n\nTimestep: 5290000\nmean reward (100 episodes): 20.4100\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2916\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22631.4 seconds (6.29 hours)\n\nTimestep: 5300000\nmean reward (100 episodes): 20.4600\nbest mean reward: 20.5800\ncurrent episode reward: 20.0000\nepisodes: 2922\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22675.9 seconds (6.30 hours)\n\nTimestep: 5310000\nmean reward (100 episodes): 20.4800\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2927\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22719.5 seconds (6.31 hours)\n\nTimestep: 5320000\nmean reward (100 episodes): 20.5000\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2933\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22763.1 seconds (6.32 hours)\n\nTimestep: 5330000\nmean reward (100 episodes): 20.5300\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2939\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22806.8 seconds (6.34 hours)\n\nTimestep: 5340000\nmean reward (100 episodes): 20.5100\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2945\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22851.9 seconds (6.35 hours)\n\nTimestep: 5350000\nmean reward (100 episodes): 20.4900\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2951\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22896.6 seconds (6.36 hours)\n\nTimestep: 5360000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2957\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22941.6 seconds (6.37 hours)\n\nTimestep: 5370000\nmean reward (100 episodes): 20.5500\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2963\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 22986.3 seconds (6.39 hours)\n\nTimestep: 5380000\nmean reward (100 episodes): 20.5400\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2969\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23031.0 seconds (6.40 hours)\n\nTimestep: 5390000\nmean reward (100 episodes): 20.5500\nbest mean reward: 20.5800\ncurrent episode reward: 21.0000\nepisodes: 2975\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23075.4 seconds (6.41 hours)\n\nTimestep: 5400000\nmean reward (100 episodes): 20.5900\nbest mean reward: 20.5900\ncurrent episode reward: 20.0000\nepisodes: 2981\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23119.5 seconds (6.42 hours)\n\nTimestep: 5410000\nmean reward (100 episodes): 20.5900\nbest mean reward: 20.5900\ncurrent episode reward: 21.0000\nepisodes: 2987\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23164.0 seconds (6.43 hours)\n\nTimestep: 5420000\nmean reward (100 episodes): 20.6300\nbest mean reward: 20.6300\ncurrent episode reward: 21.0000\nepisodes: 2993\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23208.2 seconds (6.45 hours)\n\nTimestep: 5430000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 2999\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23252.6 seconds (6.46 hours)\n\nTimestep: 5440000\nmean reward (100 episodes): 20.6500\nbest mean reward: 20.6700\ncurrent episode reward: 19.0000\nepisodes: 3005\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23301.1 seconds (6.47 hours)\n\nTimestep: 5450000\nmean reward (100 episodes): 20.6300\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3010\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23345.5 seconds (6.48 hours)\n\nTimestep: 5460000\nmean reward (100 episodes): 20.6000\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3016\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23391.3 seconds (6.50 hours)\n\nTimestep: 5470000\nmean reward (100 episodes): 20.6100\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3022\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23436.1 seconds (6.51 hours)\n\nTimestep: 5480000\nmean reward (100 episodes): 20.6100\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3028\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23480.1 seconds (6.52 hours)\n\nTimestep: 5490000\nmean reward (100 episodes): 20.5800\nbest mean reward: 20.6700\ncurrent episode reward: 20.0000\nepisodes: 3034\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23524.8 seconds (6.53 hours)\n\nTimestep: 5500000\nmean reward (100 episodes): 20.5900\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3040\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23568.4 seconds (6.55 hours)\n\nTimestep: 5510000\nmean reward (100 episodes): 20.5800\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3045\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23613.0 seconds (6.56 hours)\n\nTimestep: 5520000\nmean reward (100 episodes): 20.5700\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3051\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23656.7 seconds (6.57 hours)\n\nTimestep: 5530000\nmean reward (100 episodes): 20.5500\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3057\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23701.2 seconds (6.58 hours)\n\nTimestep: 5540000\nmean reward (100 episodes): 20.5100\nbest mean reward: 20.6700\ncurrent episode reward: 20.0000\nepisodes: 3063\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23744.4 seconds (6.60 hours)\n\nTimestep: 5550000\nmean reward (100 episodes): 20.5300\nbest mean reward: 20.6700\ncurrent episode reward: 20.0000\nepisodes: 3068\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23788.7 seconds (6.61 hours)\n\nTimestep: 5560000\nmean reward (100 episodes): 20.5400\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3074\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23833.1 seconds (6.62 hours)\n\nTimestep: 5570000\nmean reward (100 episodes): 20.5600\nbest mean reward: 20.6700\ncurrent episode reward: 20.0000\nepisodes: 3081\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23877.4 seconds (6.63 hours)\n\nTimestep: 5580000\nmean reward (100 episodes): 20.5100\nbest mean reward: 20.6700\ncurrent episode reward: 20.0000\nepisodes: 3086\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23921.8 seconds (6.64 hours)\n\nTimestep: 5590000\nmean reward (100 episodes): 20.4900\nbest mean reward: 20.6700\ncurrent episode reward: 20.0000\nepisodes: 3092\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 23966.4 seconds (6.66 hours)\n\nTimestep: 5600000\nmean reward (100 episodes): 20.4400\nbest mean reward: 20.6700\ncurrent episode reward: 19.0000\nepisodes: 3098\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24010.7 seconds (6.67 hours)\n\nTimestep: 5610000\nmean reward (100 episodes): 20.4300\nbest mean reward: 20.6700\ncurrent episode reward: 20.0000\nepisodes: 3104\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24055.0 seconds (6.68 hours)\n\nTimestep: 5620000\nmean reward (100 episodes): 20.4900\nbest mean reward: 20.6700\ncurrent episode reward: 20.0000\nepisodes: 3110\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24099.5 seconds (6.69 hours)\n\nTimestep: 5630000\nmean reward (100 episodes): 20.4900\nbest mean reward: 20.6700\ncurrent episode reward: 20.0000\nepisodes: 3116\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24143.8 seconds (6.71 hours)\n\nTimestep: 5640000\nmean reward (100 episodes): 20.5000\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3122\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24188.4 seconds (6.72 hours)\n\nTimestep: 5650000\nmean reward (100 episodes): 20.5000\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3128\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24233.3 seconds (6.73 hours)\n\nTimestep: 5660000\nmean reward (100 episodes): 20.5400\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3134\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24276.9 seconds (6.74 hours)\n\nTimestep: 5670000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.6700\ncurrent episode reward: 20.0000\nepisodes: 3140\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24321.1 seconds (6.76 hours)\n\nTimestep: 5680000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.6700\ncurrent episode reward: 19.0000\nepisodes: 3146\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24366.0 seconds (6.77 hours)\n\nTimestep: 5690000\nmean reward (100 episodes): 20.5400\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3152\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24410.0 seconds (6.78 hours)\n\nTimestep: 5700000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.6700\ncurrent episode reward: 20.0000\nepisodes: 3157\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24454.0 seconds (6.79 hours)\n\nTimestep: 5710000\nmean reward (100 episodes): 20.5400\nbest mean reward: 20.6700\ncurrent episode reward: 20.0000\nepisodes: 3163\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24498.2 seconds (6.81 hours)\n\nTimestep: 5720000\nmean reward (100 episodes): 20.5500\nbest mean reward: 20.6700\ncurrent episode reward: 20.0000\nepisodes: 3169\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24542.0 seconds (6.82 hours)\n\nTimestep: 5730000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3175\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24586.8 seconds (6.83 hours)\n\nTimestep: 5740000\nmean reward (100 episodes): 20.5200\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3181\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24631.2 seconds (6.84 hours)\n\nTimestep: 5750000\nmean reward (100 episodes): 20.5500\nbest mean reward: 20.6700\ncurrent episode reward: 20.0000\nepisodes: 3187\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24675.8 seconds (6.85 hours)\n\nTimestep: 5760000\nmean reward (100 episodes): 20.5800\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3193\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24720.4 seconds (6.87 hours)\n\nTimestep: 5770000\nmean reward (100 episodes): 20.6100\nbest mean reward: 20.6700\ncurrent episode reward: 19.0000\nepisodes: 3199\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24764.7 seconds (6.88 hours)\n\nTimestep: 5780000\nmean reward (100 episodes): 20.6300\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3205\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24808.7 seconds (6.89 hours)\n\nTimestep: 5790000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3211\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24853.2 seconds (6.90 hours)\n\nTimestep: 5800000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3217\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24898.5 seconds (6.92 hours)\n\nTimestep: 5810000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.6700\ncurrent episode reward: 20.0000\nepisodes: 3223\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24943.7 seconds (6.93 hours)\n\nTimestep: 5820000\nmean reward (100 episodes): 20.6500\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3229\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 24987.2 seconds (6.94 hours)\n\nTimestep: 5830000\nmean reward (100 episodes): 20.6400\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3235\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25031.8 seconds (6.95 hours)\n\nTimestep: 5840000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.6700\ncurrent episode reward: 21.0000\nepisodes: 3240\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25075.6 seconds (6.97 hours)\n\nTimestep: 5850000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.6800\ncurrent episode reward: 20.0000\nepisodes: 3246\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25120.4 seconds (6.98 hours)\n\nTimestep: 5860000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.6900\ncurrent episode reward: 21.0000\nepisodes: 3252\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25164.4 seconds (6.99 hours)\n\nTimestep: 5870000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.7200\ncurrent episode reward: 21.0000\nepisodes: 3258\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25209.6 seconds (7.00 hours)\n\nTimestep: 5880000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.7200\ncurrent episode reward: 21.0000\nepisodes: 3264\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25254.2 seconds (7.02 hours)\n\nTimestep: 5890000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.7200\ncurrent episode reward: 21.0000\nepisodes: 3270\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25298.3 seconds (7.03 hours)\n\nTimestep: 5900000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.7200\ncurrent episode reward: 21.0000\nepisodes: 3276\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25342.9 seconds (7.04 hours)\n\nTimestep: 5910000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.7200\ncurrent episode reward: 21.0000\nepisodes: 3282\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25387.0 seconds (7.05 hours)\n\nTimestep: 5920000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3288\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25431.8 seconds (7.06 hours)\n\nTimestep: 5930000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3294\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25475.7 seconds (7.08 hours)\n\nTimestep: 5940000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.7300\ncurrent episode reward: 20.0000\nepisodes: 3300\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25519.6 seconds (7.09 hours)\n\nTimestep: 5950000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3306\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25563.9 seconds (7.10 hours)\n\nTimestep: 5960000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3312\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25608.5 seconds (7.11 hours)\n\nTimestep: 5970000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3318\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25652.5 seconds (7.13 hours)\n\nTimestep: 5980000\nmean reward (100 episodes): 20.6500\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3324\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25696.6 seconds (7.14 hours)\n\nTimestep: 5990000\nmean reward (100 episodes): 20.6500\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3330\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25739.8 seconds (7.15 hours)\n\nTimestep: 6000000\nmean reward (100 episodes): 20.6400\nbest mean reward: 20.7300\ncurrent episode reward: 20.0000\nepisodes: 3336\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25784.4 seconds (7.16 hours)\n\nTimestep: 6010000\nmean reward (100 episodes): 20.6400\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3342\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25828.9 seconds (7.17 hours)\n\nTimestep: 6020000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3348\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25872.5 seconds (7.19 hours)\n\nTimestep: 6030000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3353\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25916.7 seconds (7.20 hours)\n\nTimestep: 6040000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3359\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 25961.3 seconds (7.21 hours)\n\nTimestep: 6050000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3365\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26005.9 seconds (7.22 hours)\n\nTimestep: 6060000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.7300\ncurrent episode reward: 19.0000\nepisodes: 3371\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26051.1 seconds (7.24 hours)\n\nTimestep: 6070000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.7300\ncurrent episode reward: 20.0000\nepisodes: 3377\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26095.7 seconds (7.25 hours)\n\nTimestep: 6080000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3383\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26140.2 seconds (7.26 hours)\n\nTimestep: 6090000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3389\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26185.4 seconds (7.27 hours)\n\nTimestep: 6100000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3395\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26230.2 seconds (7.29 hours)\n\nTimestep: 6110000\nmean reward (100 episodes): 20.6500\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3401\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26275.2 seconds (7.30 hours)\n\nTimestep: 6120000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3407\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26319.4 seconds (7.31 hours)\n\nTimestep: 6130000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3413\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26363.4 seconds (7.32 hours)\n\nTimestep: 6140000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3419\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26407.3 seconds (7.34 hours)\n\nTimestep: 6150000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.7300\ncurrent episode reward: 20.0000\nepisodes: 3425\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26452.6 seconds (7.35 hours)\n\nTimestep: 6160000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.7300\ncurrent episode reward: 21.0000\nepisodes: 3431\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26496.6 seconds (7.36 hours)\n\nTimestep: 6170000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.7400\ncurrent episode reward: 21.0000\nepisodes: 3437\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26540.8 seconds (7.37 hours)\n\nTimestep: 6180000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.7400\ncurrent episode reward: 21.0000\nepisodes: 3443\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26585.2 seconds (7.38 hours)\n\nTimestep: 6190000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.7400\ncurrent episode reward: 20.0000\nepisodes: 3449\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26630.3 seconds (7.40 hours)\n\nTimestep: 6200000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.7400\ncurrent episode reward: 21.0000\nepisodes: 3455\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26674.9 seconds (7.41 hours)\n\nTimestep: 6210000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.7400\ncurrent episode reward: 20.0000\nepisodes: 3460\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26718.8 seconds (7.42 hours)\n\nTimestep: 6220000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.7400\ncurrent episode reward: 20.0000\nepisodes: 3466\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26763.3 seconds (7.43 hours)\n\nTimestep: 6230000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.7400\ncurrent episode reward: 21.0000\nepisodes: 3471\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26808.2 seconds (7.45 hours)\n\nTimestep: 6240000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.7400\ncurrent episode reward: 21.0000\nepisodes: 3478\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26852.2 seconds (7.46 hours)\n\nTimestep: 6250000\nmean reward (100 episodes): 20.6500\nbest mean reward: 20.7400\ncurrent episode reward: 21.0000\nepisodes: 3483\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26896.5 seconds (7.47 hours)\n\nTimestep: 6260000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.7400\ncurrent episode reward: 21.0000\nepisodes: 3489\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26940.5 seconds (7.48 hours)\n\nTimestep: 6270000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.7400\ncurrent episode reward: 21.0000\nepisodes: 3495\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 26984.7 seconds (7.50 hours)\n\nTimestep: 6280000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.7400\ncurrent episode reward: 21.0000\nepisodes: 3501\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27029.5 seconds (7.51 hours)\n\nTimestep: 6290000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.7400\ncurrent episode reward: 20.0000\nepisodes: 3507\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27073.4 seconds (7.52 hours)\n\nTimestep: 6300000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.7400\ncurrent episode reward: 21.0000\nepisodes: 3513\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27117.3 seconds (7.53 hours)\n\nTimestep: 6310000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.7400\ncurrent episode reward: 21.0000\nepisodes: 3520\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27161.7 seconds (7.54 hours)\n\nTimestep: 6320000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.7400\ncurrent episode reward: 21.0000\nepisodes: 3526\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27206.6 seconds (7.56 hours)\n\nTimestep: 6330000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.7400\ncurrent episode reward: 21.0000\nepisodes: 3532\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27251.6 seconds (7.57 hours)\n\nTimestep: 6340000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.7400\ncurrent episode reward: 21.0000\nepisodes: 3537\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27295.4 seconds (7.58 hours)\n\nTimestep: 6350000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.7400\ncurrent episode reward: 20.0000\nepisodes: 3543\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27339.6 seconds (7.59 hours)\n\nTimestep: 6360000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.7400\ncurrent episode reward: 21.0000\nepisodes: 3549\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27383.5 seconds (7.61 hours)\n\nTimestep: 6370000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.7400\ncurrent episode reward: 20.0000\nepisodes: 3555\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27428.2 seconds (7.62 hours)\n\nTimestep: 6380000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.7400\ncurrent episode reward: 21.0000\nepisodes: 3561\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27473.0 seconds (7.63 hours)\n\nTimestep: 6390000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.7400\ncurrent episode reward: 21.0000\nepisodes: 3567\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27516.9 seconds (7.64 hours)\n\nTimestep: 6400000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3573\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27561.2 seconds (7.66 hours)\n\nTimestep: 6410000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.7600\ncurrent episode reward: 20.0000\nepisodes: 3579\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27605.5 seconds (7.67 hours)\n\nTimestep: 6420000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3585\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27649.5 seconds (7.68 hours)\n\nTimestep: 6430000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3591\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27693.6 seconds (7.69 hours)\n\nTimestep: 6440000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.7600\ncurrent episode reward: 20.0000\nepisodes: 3597\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27737.6 seconds (7.70 hours)\n\nTimestep: 6450000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.7600\ncurrent episode reward: 20.0000\nepisodes: 3603\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27781.8 seconds (7.72 hours)\n\nTimestep: 6460000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.7600\ncurrent episode reward: 20.0000\nepisodes: 3609\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27826.1 seconds (7.73 hours)\n\nTimestep: 6470000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.7600\ncurrent episode reward: 20.0000\nepisodes: 3615\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27870.5 seconds (7.74 hours)\n\nTimestep: 6480000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3621\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27914.5 seconds (7.75 hours)\n\nTimestep: 6490000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3627\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 27958.2 seconds (7.77 hours)\n\nTimestep: 6500000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3633\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28002.8 seconds (7.78 hours)\n\nTimestep: 6510000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.7600\ncurrent episode reward: 19.0000\nepisodes: 3639\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28046.3 seconds (7.79 hours)\n\nTimestep: 6520000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3645\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28090.7 seconds (7.80 hours)\n\nTimestep: 6530000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3651\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28134.0 seconds (7.82 hours)\n\nTimestep: 6540000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.7600\ncurrent episode reward: 20.0000\nepisodes: 3657\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28179.2 seconds (7.83 hours)\n\nTimestep: 6550000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.7600\ncurrent episode reward: 20.0000\nepisodes: 3663\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28223.6 seconds (7.84 hours)\n\nTimestep: 6560000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3669\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28267.9 seconds (7.85 hours)\n\nTimestep: 6570000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3675\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28312.4 seconds (7.86 hours)\n\nTimestep: 6580000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.7600\ncurrent episode reward: 20.0000\nepisodes: 3681\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28356.3 seconds (7.88 hours)\n\nTimestep: 6590000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3687\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28400.6 seconds (7.89 hours)\n\nTimestep: 6600000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3693\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28444.3 seconds (7.90 hours)\n\nTimestep: 6610000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3699\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28488.6 seconds (7.91 hours)\n\nTimestep: 6620000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3704\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28532.7 seconds (7.93 hours)\n\nTimestep: 6630000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3710\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28577.1 seconds (7.94 hours)\n\nTimestep: 6640000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3716\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28621.6 seconds (7.95 hours)\n\nTimestep: 6650000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3722\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28666.0 seconds (7.96 hours)\n\nTimestep: 6660000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3728\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28709.7 seconds (7.97 hours)\n\nTimestep: 6670000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.7600\ncurrent episode reward: 20.0000\nepisodes: 3734\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28754.4 seconds (7.99 hours)\n\nTimestep: 6680000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3740\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28798.8 seconds (8.00 hours)\n\nTimestep: 6690000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.7600\ncurrent episode reward: 20.0000\nepisodes: 3746\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28842.6 seconds (8.01 hours)\n\nTimestep: 6700000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3752\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28886.8 seconds (8.02 hours)\n\nTimestep: 6710000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3758\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28931.0 seconds (8.04 hours)\n\nTimestep: 6720000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3764\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 28975.9 seconds (8.05 hours)\n\nTimestep: 6730000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3770\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29019.5 seconds (8.06 hours)\n\nTimestep: 6740000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3776\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29063.6 seconds (8.07 hours)\n\nTimestep: 6750000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3782\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29108.2 seconds (8.09 hours)\n\nTimestep: 6760000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.7600\ncurrent episode reward: 20.0000\nepisodes: 3788\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29152.0 seconds (8.10 hours)\n\nTimestep: 6770000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.7600\ncurrent episode reward: 21.0000\nepisodes: 3794\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29196.6 seconds (8.11 hours)\n\nTimestep: 6780000\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.7700\ncurrent episode reward: 21.0000\nepisodes: 3800\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29241.6 seconds (8.12 hours)\n\nTimestep: 6790000\nmean reward (100 episodes): 20.7900\nbest mean reward: 20.7900\ncurrent episode reward: 21.0000\nepisodes: 3806\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29286.3 seconds (8.14 hours)\n\nTimestep: 6800000\nmean reward (100 episodes): 20.8200\nbest mean reward: 20.8200\ncurrent episode reward: 21.0000\nepisodes: 3812\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29330.3 seconds (8.15 hours)\n\nTimestep: 6810000\nmean reward (100 episodes): 20.8300\nbest mean reward: 20.8300\ncurrent episode reward: 21.0000\nepisodes: 3818\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29374.5 seconds (8.16 hours)\n\nTimestep: 6820000\nmean reward (100 episodes): 20.8200\nbest mean reward: 20.8300\ncurrent episode reward: 21.0000\nepisodes: 3824\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29419.0 seconds (8.17 hours)\n\nTimestep: 6830000\nmean reward (100 episodes): 20.8100\nbest mean reward: 20.8300\ncurrent episode reward: 20.0000\nepisodes: 3830\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29463.1 seconds (8.18 hours)\n\nTimestep: 6840000\nmean reward (100 episodes): 20.8100\nbest mean reward: 20.8300\ncurrent episode reward: 21.0000\nepisodes: 3836\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29507.7 seconds (8.20 hours)\n\nTimestep: 6850000\nmean reward (100 episodes): 20.8300\nbest mean reward: 20.8400\ncurrent episode reward: 21.0000\nepisodes: 3842\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29552.4 seconds (8.21 hours)\n\nTimestep: 6860000\nmean reward (100 episodes): 20.8400\nbest mean reward: 20.8400\ncurrent episode reward: 21.0000\nepisodes: 3848\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29597.0 seconds (8.22 hours)\n\nTimestep: 6870000\nmean reward (100 episodes): 20.8300\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 3854\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29640.9 seconds (8.23 hours)\n\nTimestep: 6880000\nmean reward (100 episodes): 20.8300\nbest mean reward: 20.8500\ncurrent episode reward: 20.0000\nepisodes: 3860\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29685.9 seconds (8.25 hours)\n\nTimestep: 6890000\nmean reward (100 episodes): 20.8300\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 3866\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29730.6 seconds (8.26 hours)\n\nTimestep: 6900000\nmean reward (100 episodes): 20.8300\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 3872\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29774.4 seconds (8.27 hours)\n\nTimestep: 6910000\nmean reward (100 episodes): 20.8200\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 3878\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29818.1 seconds (8.28 hours)\n\nTimestep: 6920000\nmean reward (100 episodes): 20.8100\nbest mean reward: 20.8500\ncurrent episode reward: 20.0000\nepisodes: 3884\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29862.2 seconds (8.30 hours)\n\nTimestep: 6930000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 3890\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29906.9 seconds (8.31 hours)\n\nTimestep: 6940000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 3896\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29950.7 seconds (8.32 hours)\n\nTimestep: 6950000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 3902\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 29995.4 seconds (8.33 hours)\n\nTimestep: 6960000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.8500\ncurrent episode reward: 20.0000\nepisodes: 3908\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30039.8 seconds (8.34 hours)\n\nTimestep: 6970000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8500\ncurrent episode reward: 20.0000\nepisodes: 3914\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30083.7 seconds (8.36 hours)\n\nTimestep: 6980000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8500\ncurrent episode reward: 20.0000\nepisodes: 3920\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30127.4 seconds (8.37 hours)\n\nTimestep: 6990000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 3926\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30171.7 seconds (8.38 hours)\n\nTimestep: 7000000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 3932\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30215.1 seconds (8.39 hours)\n\nTimestep: 7010000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 3938\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30259.3 seconds (8.41 hours)\n\nTimestep: 7020000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 3944\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30303.3 seconds (8.42 hours)\n\nTimestep: 7030000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.8500\ncurrent episode reward: 20.0000\nepisodes: 3950\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30347.3 seconds (8.43 hours)\n\nTimestep: 7040000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.8500\ncurrent episode reward: 20.0000\nepisodes: 3956\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30392.1 seconds (8.44 hours)\n\nTimestep: 7050000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 3962\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30436.2 seconds (8.45 hours)\n\nTimestep: 7060000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 3968\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30481.0 seconds (8.47 hours)\n\nTimestep: 7070000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 3974\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30525.1 seconds (8.48 hours)\n\nTimestep: 7080000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 3980\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30568.9 seconds (8.49 hours)\n\nTimestep: 7090000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.8500\ncurrent episode reward: 18.0000\nepisodes: 3985\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30613.1 seconds (8.50 hours)\n\nTimestep: 7100000\nmean reward (100 episodes): 20.6600\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 3991\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30657.0 seconds (8.52 hours)\n\nTimestep: 7110000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.8500\ncurrent episode reward: 20.0000\nepisodes: 3997\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30701.2 seconds (8.53 hours)\n\nTimestep: 7120000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4003\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30749.6 seconds (8.54 hours)\n\nTimestep: 7130000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4009\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30794.3 seconds (8.55 hours)\n\nTimestep: 7140000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.8500\ncurrent episode reward: 20.0000\nepisodes: 4015\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30838.6 seconds (8.57 hours)\n\nTimestep: 7150000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4022\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30883.7 seconds (8.58 hours)\n\nTimestep: 7160000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4028\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30927.0 seconds (8.59 hours)\n\nTimestep: 7170000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.8500\ncurrent episode reward: 19.0000\nepisodes: 4033\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 30971.0 seconds (8.60 hours)\n\nTimestep: 7180000\nmean reward (100 episodes): 20.6700\nbest mean reward: 20.8500\ncurrent episode reward: 20.0000\nepisodes: 4039\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31014.8 seconds (8.62 hours)\n\nTimestep: 7190000\nmean reward (100 episodes): 20.6900\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4045\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31059.8 seconds (8.63 hours)\n\nTimestep: 7200000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4051\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31103.6 seconds (8.64 hours)\n\nTimestep: 7210000\nmean reward (100 episodes): 20.7100\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4058\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31147.9 seconds (8.65 hours)\n\nTimestep: 7220000\nmean reward (100 episodes): 20.7200\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4064\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31192.6 seconds (8.66 hours)\n\nTimestep: 7230000\nmean reward (100 episodes): 20.6800\nbest mean reward: 20.8500\ncurrent episode reward: 19.0000\nepisodes: 4069\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31236.1 seconds (8.68 hours)\n\nTimestep: 7240000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4076\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31280.0 seconds (8.69 hours)\n\nTimestep: 7250000\nmean reward (100 episodes): 20.7000\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4082\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31324.0 seconds (8.70 hours)\n\nTimestep: 7260000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4088\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31368.2 seconds (8.71 hours)\n\nTimestep: 7270000\nmean reward (100 episodes): 20.7300\nbest mean reward: 20.8500\ncurrent episode reward: 19.0000\nepisodes: 4093\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31412.4 seconds (8.73 hours)\n\nTimestep: 7280000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4100\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31456.7 seconds (8.74 hours)\n\nTimestep: 7290000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4106\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31501.3 seconds (8.75 hours)\n\nTimestep: 7300000\nmean reward (100 episodes): 20.7600\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4112\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31546.4 seconds (8.76 hours)\n\nTimestep: 7310000\nmean reward (100 episodes): 20.7400\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4118\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31591.2 seconds (8.78 hours)\n\nTimestep: 7320000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4124\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31635.9 seconds (8.79 hours)\n\nTimestep: 7330000\nmean reward (100 episodes): 20.7500\nbest mean reward: 20.8500\ncurrent episode reward: 20.0000\nepisodes: 4130\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31680.0 seconds (8.80 hours)\n\nTimestep: 7340000\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.8500\ncurrent episode reward: 20.0000\nepisodes: 4136\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31724.3 seconds (8.81 hours)\n\nTimestep: 7350000\nmean reward (100 episodes): 20.7900\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4142\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31769.7 seconds (8.82 hours)\n\nTimestep: 7360000\nmean reward (100 episodes): 20.7900\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4148\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31814.1 seconds (8.84 hours)\n\nTimestep: 7370000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4154\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31858.0 seconds (8.85 hours)\n\nTimestep: 7380000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4160\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31902.0 seconds (8.86 hours)\n\nTimestep: 7390000\nmean reward (100 episodes): 20.8100\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4166\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31946.6 seconds (8.87 hours)\n\nTimestep: 7400000\nmean reward (100 episodes): 20.8200\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4172\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 31990.4 seconds (8.89 hours)\n\nTimestep: 7410000\nmean reward (100 episodes): 20.8100\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4178\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32034.5 seconds (8.90 hours)\n\nTimestep: 7420000\nmean reward (100 episodes): 20.8100\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4184\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32078.9 seconds (8.91 hours)\n\nTimestep: 7430000\nmean reward (100 episodes): 20.7900\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4190\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32123.5 seconds (8.92 hours)\n\nTimestep: 7440000\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4196\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32167.6 seconds (8.94 hours)\n\nTimestep: 7450000\nmean reward (100 episodes): 20.7700\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4202\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32212.1 seconds (8.95 hours)\n\nTimestep: 7460000\nmean reward (100 episodes): 20.7800\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4208\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32256.3 seconds (8.96 hours)\n\nTimestep: 7470000\nmean reward (100 episodes): 20.7900\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4214\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32300.5 seconds (8.97 hours)\n\nTimestep: 7476547\nmean reward (100 episodes): 20.8000\nbest mean reward: 20.8500\ncurrent episode reward: 21.0000\nepisodes: 4218\nexploration: 0.01000\nlearning_rate: 0.00005\nelapsed time: 32329.7 seconds (8.98 hours)\n"
  },
  {
    "path": "dqn/plot_dqn.py",
    "content": "import matplotlib.pyplot as plt\nimport numpy as np\nimport pickle\nimport seaborn as sns\nplt.style.use('seaborn-darkgrid')\nnp.set_printoptions(edgeitems=100,\n                    linewidth=100,\n                    suppress=True)\n\n# Some default settings.\nLOGDIR = 'logs_pkls/'\nFIGDIR = 'figures/'\ntitle_size = 22\naxis_size = 20\ntick_size = 18\nlegend_size = 20\nlw = 3\n\ndef smoothed_block(x, n):\n    \"\"\" Smoothed average in a block (size n) on array x. \"\"\"\n    assert (len(x.shape) == 1) and (x.shape[0] > n)\n    length = x.shape[0]-n+1\n    sm = np.zeros((length,))\n    for i in range(length):\n        sm[i] = np.mean(x[i:i+n])\n    return sm\n\n\n########\n# Pong #\n########\n\nname = \"Pong\"\nfig, axarr = plt.subplots(2,2, figsize=(15,12))\n\npong_data = []\npong_eps = []\npong_t = []\npong_mean = []\npong_best_mean = []\npong_ep = []\npong_eps_sm = []\npong_colors = ['red','black']\npong_labels = ['seed=1','seed=2']\n\nfor i in range(0,2):\n    index_str = str(i+1)\n    with open(LOGDIR+'Pong_s00'+index_str+'.pkl', 'rb') as f:\n        pong_data.append( np.array(pickle.load(f)) )\n        pong_eps.append( np.array(pickle.load(f)) )\n    pong_data[i] = np.maximum(pong_data[i], -21)\n    pong_t.append((pong_data[i][:,0]) / 1000000.0)\n    pong_mean.append(pong_data[i][:,1])\n    pong_best_mean.append(pong_data[i][:,2])\n    pong_ep.append(pong_data[i][:,3])\n    pong_eps_sm.append(smoothed_block(pong_eps[i], 100))\n\n    axarr[0,0].set_title(name+ \" Scores at Timesteps\", fontsize=title_size)\n    axarr[0,1].set_title(name+ \" Scores at Timesteps (Block 100)\", fontsize=title_size)\n    axarr[0,0].plot(pong_t[i], pong_ep[i], c=pong_colors[i], lw=lw,\n                    label=pong_labels[i])\n    axarr[0,1].plot(pong_t[i], pong_mean[i], c=pong_colors[i], lw=lw, \n                    label=pong_labels[i])\n    axarr[0,0].set_xlabel(\"Training Steps (in Millions)\", fontsize=axis_size)\n    axarr[0,1].set_xlabel(\"Training Steps (in Millions)\", fontsize=axis_size)\n    \n    axarr[1,0].set_title(name+ \" Scores per Episode\", fontsize=title_size)\n    axarr[1,1].set_title(name+ \" Scores per Episode (Block 100)\", fontsize=title_size)\n    axarr[1,0].plot(pong_eps[i], c=pong_colors[i], lw=lw, \n                    label=pong_labels[i])\n    axarr[1,1].plot(pong_eps_sm[i], c=pong_colors[i], lw=lw, \n                    label=pong_labels[i])\n    axarr[1,0].set_xlabel(\"Number of Episodes\", fontsize=axis_size)\n    axarr[1,1].set_xlabel(\"Number of Episodes\", fontsize=axis_size)\n\nfor i in range(2):\n    for j in range(2):\n        axarr[i,j].set_ylabel(\"Rewards\", fontsize=axis_size)\n        axarr[i,j].tick_params(axis='x', labelsize=tick_size)\n        axarr[i,j].tick_params(axis='y', labelsize=tick_size)\n        axarr[i,j].legend(loc='lower right', prop={'size':legend_size})\n        axarr[i,j].set_ylim([-23,23])\nplt.tight_layout()\nplt.savefig(FIGDIR+name+\".png\")\n\n\n############\n# Breakout #\n############\n\nname = \"Breakout\"\nfig, axarr = plt.subplots(2,2, figsize=(15,12))\n\nbreakout_data = []\nbreakout_eps = []\nbreakout_t = []\nbreakout_mean = []\nbreakout_best_mean = []\nbreakout_ep = []\nbreakout_eps_sm = []\nbreakout_colors = ['blue','yellow']\nbreakout_labels = ['seed=1','seed=2']\n\nfor i in range(0,2):\n    index_str = str(i+1)\n    with open(LOGDIR+'Breakout_s00'+index_str+'.pkl', 'rb') as f:\n        breakout_data.append( np.array(pickle.load(f)) )\n        breakout_eps.append( np.array(pickle.load(f)) )\n    breakout_data[i] = np.maximum(breakout_data[i], -21)\n    breakout_t.append((breakout_data[i][:,0]) / 1000000.0)\n    breakout_mean.append(breakout_data[i][:,1])\n    breakout_best_mean.append(breakout_data[i][:,2])\n    breakout_ep.append(breakout_data[i][:,3])\n    breakout_eps_sm.append(smoothed_block(breakout_eps[i], 100))\n\n    axarr[0,0].set_title(name+ \" Scores at Timesteps\", fontsize=title_size)\n    axarr[0,1].set_title(name+ \" Scores at Timesteps (Block 100)\", fontsize=title_size)\n    axarr[0,0].plot(breakout_t[i], breakout_ep[i], c=breakout_colors[i], lw=lw,\n                    label=breakout_labels[i])\n    axarr[0,1].plot(breakout_t[i], breakout_mean[i], c=breakout_colors[i], lw=lw, \n                    label=breakout_labels[i])\n    axarr[0,0].set_xlabel(\"Training Steps (in Millions)\", fontsize=axis_size)\n    axarr[0,1].set_xlabel(\"Training Steps (in Millions)\", fontsize=axis_size)\n    \n    axarr[1,0].set_title(name+ \" Scores per Episode\", fontsize=title_size)\n    axarr[1,1].set_title(name+ \" Scores per Episode (Block 100)\", fontsize=title_size)\n    axarr[1,0].plot(breakout_eps[i], c=breakout_colors[i], lw=lw, \n                    label=breakout_labels[i])\n    axarr[1,1].plot(breakout_eps_sm[i], c=breakout_colors[i], lw=lw, \n                    label=breakout_labels[i])\n    axarr[1,0].set_xlabel(\"Number of Episodes\", fontsize=axis_size)\n    axarr[1,1].set_xlabel(\"Number of Episodes\", fontsize=axis_size)\n\nfor i in range(2):\n    for j in range(2):\n        axarr[i,j].set_ylabel(\"Rewards\", fontsize=axis_size)\n        axarr[i,j].tick_params(axis='x', labelsize=tick_size)\n        axarr[i,j].tick_params(axis='y', labelsize=tick_size)\n        axarr[i,j].legend(loc='upper left', prop={'size':legend_size})\nplt.tight_layout()\nplt.savefig(FIGDIR+name+\".png\")\n\n\n#############\n# BeamRider #\n#############\n\nname = \"BeamRider\"\nfig, axarr = plt.subplots(2,2, figsize=(15,12))\n\nbeamrider_data = []\nbeamrider_eps = []\nbeamrider_t = []\nbeamrider_mean = []\nbeamrider_best_mean = []\nbeamrider_ep = []\nbeamrider_eps_sm = []\nbeamrider_colors = ['orange','purple']\nbeamrider_labels = ['seed=1','seed=2']\n\nfor i in range(0,2):\n    index_str = str(i+1)\n    with open(LOGDIR+'BeamRider_s00'+index_str+'.pkl', 'rb') as f:\n        beamrider_data.append( np.array(pickle.load(f)) )\n        beamrider_eps.append( np.array(pickle.load(f)) )\n    beamrider_data[i] = np.maximum(beamrider_data[i], -21)\n    beamrider_t.append((beamrider_data[i][:,0]) / 1000000.0)\n    beamrider_mean.append(beamrider_data[i][:,1])\n    beamrider_best_mean.append(beamrider_data[i][:,2])\n    beamrider_ep.append(beamrider_data[i][:,3])\n    beamrider_eps_sm.append(smoothed_block(beamrider_eps[i], 100))\n\n    axarr[0,0].set_title(name+ \" Scores at Timesteps\", fontsize=title_size)\n    axarr[0,1].set_title(name+ \" Scores at Timesteps (Block 100)\", fontsize=title_size)\n    axarr[0,0].plot(beamrider_t[i], beamrider_ep[i], c=beamrider_colors[i], lw=lw,\n                    label=beamrider_labels[i])\n    axarr[0,1].plot(beamrider_t[i], beamrider_mean[i], c=beamrider_colors[i], lw=lw, \n                    label=beamrider_labels[i])\n    axarr[0,0].set_xlabel(\"Training Steps (in Millions)\", fontsize=axis_size)\n    axarr[0,1].set_xlabel(\"Training Steps (in Millions)\", fontsize=axis_size)\n    \n    axarr[1,0].set_title(name+ \" Scores per Episode\", fontsize=title_size)\n    axarr[1,1].set_title(name+ \" Scores per Episode (Block 100)\", fontsize=title_size)\n    axarr[1,0].plot(beamrider_eps[i], c=beamrider_colors[i], lw=lw, \n                    label=beamrider_labels[i])\n    axarr[1,1].plot(beamrider_eps_sm[i], c=beamrider_colors[i], lw=lw, \n                    label=beamrider_labels[i])\n    axarr[1,0].set_xlabel(\"Number of Episodes\", fontsize=axis_size)\n    axarr[1,1].set_xlabel(\"Number of Episodes\", fontsize=axis_size)\n\nfor i in range(2):\n    for j in range(2):\n        axarr[i,j].set_ylabel(\"Rewards\", fontsize=axis_size)\n        axarr[i,j].tick_params(axis='x', labelsize=tick_size)\n        axarr[i,j].tick_params(axis='y', labelsize=tick_size)\n        axarr[i,j].legend(loc='upper left', prop={'size':legend_size})\nplt.tight_layout()\nplt.savefig(FIGDIR+name+\".png\")\n\n\n\n##########\n# Enduro #\n##########\n\nname = \"Enduro\"\nfig, axarr = plt.subplots(2,2, figsize=(15,12))\n\nenduro_data = []\nenduro_eps = []\nenduro_t = []\nenduro_mean = []\nenduro_best_mean = []\nenduro_ep = []\nenduro_eps_sm = []\nenduro_colors = ['gold','midnightblue']\nenduro_labels = ['seed=1','seed=2']\n\nfor i in range(0,2):\n    index_str = str(i+1)\n    with open(LOGDIR+'Enduro_s00'+index_str+'.pkl', 'rb') as f:\n        enduro_data.append( np.array(pickle.load(f)) )\n        enduro_eps.append( np.array(pickle.load(f)) )\n    enduro_data[i] = np.maximum(enduro_data[i], -21)\n    enduro_t.append((enduro_data[i][:,0]) / 1000000.0)\n    enduro_mean.append(enduro_data[i][:,1])\n    enduro_best_mean.append(enduro_data[i][:,2])\n    enduro_ep.append(enduro_data[i][:,3])\n    enduro_eps_sm.append(smoothed_block(enduro_eps[i], 100))\n\n    axarr[0,0].set_title(name+ \" Scores at Timesteps\", fontsize=title_size)\n    axarr[0,1].set_title(name+ \" Scores at Timesteps (Block 100)\", fontsize=title_size)\n    axarr[0,0].plot(enduro_t[i], enduro_ep[i], c=enduro_colors[i], lw=lw,\n                    label=enduro_labels[i])\n    axarr[0,1].plot(enduro_t[i], enduro_mean[i], c=enduro_colors[i], lw=lw, \n                    label=enduro_labels[i])\n    axarr[0,0].set_xlabel(\"Training Steps (in Millions)\", fontsize=axis_size)\n    axarr[0,1].set_xlabel(\"Training Steps (in Millions)\", fontsize=axis_size)\n    \n    axarr[1,0].set_title(name+ \" Scores per Episode\", fontsize=title_size)\n    axarr[1,1].set_title(name+ \" Scores per Episode (Block 100)\", fontsize=title_size)\n    axarr[1,0].plot(enduro_eps[i], c=enduro_colors[i], lw=lw, \n                    label=enduro_labels[i])\n    axarr[1,1].plot(enduro_eps_sm[i], c=enduro_colors[i], lw=lw, \n                    label=enduro_labels[i])\n    axarr[1,0].set_xlabel(\"Number of Episodes\", fontsize=axis_size)\n    axarr[1,1].set_xlabel(\"Number of Episodes\", fontsize=axis_size)\n\nfor i in range(2):\n    for j in range(2):\n        axarr[i,j].set_ylabel(\"Rewards\", fontsize=axis_size)\n        axarr[i,j].tick_params(axis='x', labelsize=tick_size)\n        axarr[i,j].tick_params(axis='y', labelsize=tick_size)\n        axarr[i,j].legend(loc='upper left', prop={'size':legend_size})\nplt.tight_layout()\nplt.savefig(FIGDIR+name+\".png\")\n"
  },
  {
    "path": "dqn/run_dqn_atari.py",
    "content": "import argparse\nimport gym\nfrom gym import wrappers\nimport os.path as osp\nimport random\nimport numpy as np\nimport tensorflow as tf\nimport tensorflow.contrib.layers as layers\nimport argparse\nimport sys\n\nimport dqn\nfrom dqn_utils import *\nfrom atari_wrappers import *\n\n\ndef atari_model(img_in, num_actions, scope, reuse=False):\n    # as described in https://storage.googleapis.com/deepmind-data/assets/papers/DeepMindNature14236Paper.pdf\n    with tf.variable_scope(scope, reuse=reuse):\n        out = img_in\n        with tf.variable_scope(\"convnet\"):\n            # original architecture\n            out = layers.convolution2d(out, num_outputs=32, kernel_size=8, stride=4, activation_fn=tf.nn.relu)\n            out = layers.convolution2d(out, num_outputs=64, kernel_size=4, stride=2, activation_fn=tf.nn.relu)\n            out = layers.convolution2d(out, num_outputs=64, kernel_size=3, stride=1, activation_fn=tf.nn.relu)\n        out = layers.flatten(out)\n        with tf.variable_scope(\"action_value\"):\n            out = layers.fully_connected(out, num_outputs=512,         activation_fn=tf.nn.relu)\n            out = layers.fully_connected(out, num_outputs=num_actions, activation_fn=None)\n\n        return out\n\ndef atari_learn(env,\n                session,\n                num_timesteps,\n                log_file = './logs_pkls/rewards.pkl'):\n    # This is just a rough estimate\n    num_iterations = float(num_timesteps) / 4.0\n\n    lr_multiplier = 1.0\n    lr_schedule = PiecewiseSchedule([\n                                         (0,                   1e-4 * lr_multiplier),\n                                         (num_iterations / 10, 1e-4 * lr_multiplier),\n                                         (num_iterations / 2,  5e-5 * lr_multiplier),\n                                    ],\n                                    outside_value=5e-5 * lr_multiplier)\n    optimizer = dqn.OptimizerSpec(\n        constructor=tf.train.AdamOptimizer,\n        kwargs=dict(epsilon=1e-4),\n        lr_schedule=lr_schedule\n    )\n\n    def stopping_criterion(env, t):\n        # notice that here t is the number of steps of the wrapped env,\n        # which is different from the number of steps in the underlying env\n        return get_wrapper_by_name(env, \"Monitor\").get_total_steps() >= num_timesteps\n\n    exploration_schedule = PiecewiseSchedule(\n        [\n            (0, 1.0),\n            (1e6, 0.1),\n            (num_iterations / 2, 0.01),\n        ], outside_value=0.01\n    )\n\n    dqn.learn(\n        env,\n        q_func=atari_model,\n        optimizer_spec=optimizer,\n        session=session,\n        exploration=exploration_schedule,\n        stopping_criterion=stopping_criterion,\n        replay_buffer_size=1000000,\n        batch_size=32,\n        gamma=0.99,\n        learning_starts=50000,\n        learning_freq=4,\n        frame_history_len=4,\n        target_update_freq=10000,\n        grad_norm_clipping=10,\n        log_file=log_file\n    )\n    env.close()\n\n\ndef get_available_gpus():\n    from tensorflow.python.client import device_lib\n    local_device_protos = device_lib.list_local_devices()\n    return [x.physical_device_desc for x in local_device_protos if x.device_type == 'GPU']\n\n\ndef set_global_seeds(i):\n    try:\n        import tensorflow as tf\n    except ImportError:\n        pass\n    else:\n        tf.set_random_seed(i) \n    np.random.seed(i)\n    random.seed(i)\n\n\ndef get_session():\n    tf.reset_default_graph()\n    tf_config = tf.ConfigProto(\n        inter_op_parallelism_threads=1,\n        intra_op_parallelism_threads=1)\n\n    # This was the default provided in the starter code.\n    #session = tf.Session(config=tf_config)\n\n    # Use this if I want to see what is on the GPU.\n    #session = tf.Session(config=tf.ConfigProto(log_device_placement=True))\n\n    # Use this for limiting memory allocated for the GPU.\n    gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.5)\n    session = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))\n\n    print(\"AVAILABLE GPUS: \", get_available_gpus())\n    return session\n\n\ndef get_env(task, seed):\n    env_id = task.env_id\n    env = gym.make(env_id)\n    set_global_seeds(seed)\n    env.seed(seed)\n    expt_dir = '/tmp/hw3_vid_dir2/'\n    env = wrappers.Monitor(env, osp.join(expt_dir, \"gym\"), force=True)\n    env = wrap_deepmind(env)\n    return env\n\n\ndef main():\n    # Games that we'll be testing.\n    game_to_ID = {'BeamRider':0,\n                  'Breakout':1,\n                  'Enduro':2,\n                  'Pong':3,\n                  'Qbert':4}\n\n    # Get some arguments here. Note: num_timesteps default uses tasks default.\n    parser = argparse.ArgumentParser()\n    parser.add_argument('--game', type=str, default='Pong')\n    parser.add_argument('--seed', type=int, default=0)\n    parser.add_argument('--num_timesteps', type=int, default=40000000)\n    args = parser.parse_args()\n\n    # Choose the game to play and set log file.\n    benchmark = gym.benchmark_spec('Atari40M')\n    task = benchmark.tasks[game_to_ID[args.game]]\n    log_name = args.game+\"_s\"+str(args.seed).zfill(3)+\".pkl\"\n\n    # Run training. Should change the seed if possible!\n    # Also, the actual # of iterations run is _roughly_ num_timesteps/4.\n    seed = args.seed\n    env = get_env(task, seed)\n    session = get_session()\n    print(\"task = {}\".format(task))\n    atari_learn(env, \n                session, \n                num_timesteps=args.num_timesteps,\n                log_file=log_name)\n\nif __name__ == \"__main__\":\n    main()\n"
  },
  {
    "path": "dqn/run_dqn_ram.py",
    "content": "import argparse\nimport gym\nfrom gym import wrappers\nimport os.path as osp\nimport random\nimport numpy as np\nimport tensorflow as tf\nimport tensorflow.contrib.layers as layers\n\nimport dqn\nfrom dqn_utils import *\nfrom atari_wrappers import *\n\n\ndef atari_model(ram_in, num_actions, scope, reuse=False):\n    with tf.variable_scope(scope, reuse=reuse):\n        out = ram_in\n        #out = tf.concat(1,(ram_in[:,4:5],ram_in[:,8:9],ram_in[:,11:13],ram_in[:,21:22],ram_in[:,50:51], ram_in[:,60:61],ram_in[:,64:65]))\n        with tf.variable_scope(\"action_value\"):\n            out = layers.fully_connected(out, num_outputs=256, activation_fn=tf.nn.relu)\n            out = layers.fully_connected(out, num_outputs=128, activation_fn=tf.nn.relu)\n            out = layers.fully_connected(out, num_outputs=64, activation_fn=tf.nn.relu)\n            out = layers.fully_connected(out, num_outputs=num_actions, activation_fn=None)\n\n        return out\n\ndef atari_learn(env,\n                session,\n                num_timesteps):\n    # This is just a rough estimate\n    num_iterations = float(num_timesteps) / 4.0\n\n    lr_multiplier = 1.0 \n    lr_schedule = PiecewiseSchedule([\n                                         (0,                   1e-4 * lr_multiplier),\n                                         (num_iterations / 10, 1e-4 * lr_multiplier),\n                                         (num_iterations / 2,  5e-5 * lr_multiplier),\n                                    ],\n                                    outside_value=5e-5 * lr_multiplier)\n    optimizer = dqn.OptimizerSpec(\n        constructor=tf.train.AdamOptimizer,\n        kwargs=dict(epsilon=1e-4),\n        lr_schedule=lr_schedule\n    )\n\n    def stopping_criterion(env, t):\n        # notice that here t is the number of steps of the wrapped env,\n        # which is different from the number of steps in the underlying env\n        return get_wrapper_by_name(env, \"Monitor\").get_total_steps() >= num_timesteps\n\n    exploration_schedule = PiecewiseSchedule(\n        [\n            (0, 0.2),\n            (1e6, 0.1),\n            (num_iterations / 2, 0.01),\n        ], outside_value=0.01\n    )\n\n    dqn.learn(\n        env,\n        q_func=atari_model,\n        optimizer_spec=optimizer,\n        session=session,\n        exploration=exploration_schedule,\n        stopping_criterion=stopping_criterion,\n        replay_buffer_size=1000000,\n        batch_size=32,\n        gamma=0.99,\n        learning_starts=50000,\n        learning_freq=4,\n        frame_history_len=1,\n        target_update_freq=10000,\n        grad_norm_clipping=10\n    )\n    env.close()\n\ndef get_available_gpus():\n    from tensorflow.python.client import device_lib\n    local_device_protos = device_lib.list_local_devices()\n    return [x.physical_device_desc for x in local_device_protos if x.device_type == 'GPU']\n\ndef set_global_seeds(i):\n    try:\n        import tensorflow as tf\n    except ImportError:\n        pass\n    else:\n        tf.set_random_seed(i) \n    np.random.seed(i)\n    random.seed(i)\n\ndef get_session():\n    tf.reset_default_graph()\n    tf_config = tf.ConfigProto(\n        inter_op_parallelism_threads=1,\n        intra_op_parallelism_threads=1)\n    session = tf.Session(config=tf_config)\n    print(\"AVAILABLE GPUS: \", get_available_gpus())\n    return session\n\ndef get_env(seed):\n    env = gym.make('Pong-ram-v0')\n\n    set_global_seeds(seed)\n    env.seed(seed)\n\n    expt_dir = '/tmp/hw3_vid_dir/'\n    env = wrappers.Monitor(env, osp.join(expt_dir, \"gym\"), force=True)\n    env = wrap_deepmind_ram(env)\n\n    return env\n\ndef main():\n    # Run training\n    seed = 0 # Use a seed of zero (you may want to randomize the seed!)\n    env = get_env(seed)\n    session = get_session()\n    atari_learn(env, session, num_timesteps=int(4e7))\n\nif __name__ == \"__main__\":\n    main()\n"
  },
  {
    "path": "es/README.md",
    "content": "# Evolution Strategies\n\nInspired by [recent work from OpenAI][1].\n\n# Code Usage\n\nSee the bash scripts.\n\nThe ES code I am using includes the following tricks:\n\n- Mirrored sampling \n- Ranking transformation\n\nI do not use the trick of instantiating a large block of Gaussian noise for each\nworker, because this code is designed to run sequentially.\n\nNote: as of 05/18/2017, `npop` INCLUDES the mirroring so it must be divisible by\ntwo.\n\nIt uses TensorFlow but maybe that's not even needed for our purposes? Because\nthere are no gradients to update a network. (We have to do gradient ascent, but\nthat's done explicitly here and I don't think autodiff is necessary.) Tensorflow\nand the GPU are mostly useful for the *forward* pass in RL, which is not even\nthe most critical step.\n\n\n# Results\n\n## Inverted Pendulum\n\nI originally ran this for 800 iterations, but it seems like 700 is also a safe\nupper bound on the number of iterations.\n\nArgs (this one is with `npop` **not** counting the mirroring):\n\n```\nNamespace(do_not_save=False, envname='InvertedPendulum-v1', es_iters=800,\nlog_every_t_iter=2, lrate_es=0.005, npop=100, render=False, seed=4, sigma=0.1,\nsnapshot_every_t_iter=50, test_trajs=10, verbose=True)\n```\n\nand (with revised `npop` and also with 700 iterations):\n\n```\nNamespace(do_not_save=False, envname='InvertedPendulum-v1', es_iters=700,\nlog_every_t_iter=2, lrate_es=0.005, npop=200, render=False, seed=5, sigma=0.1,\nsnapshot_every_t_iter=50, test_trajs=10, verbose=True)\n```\n\nThe results look good! The results reach the perfect score *faster* than with\nthe Gaussian sampling of actions afterwards.\n\n![InvertedPendulum01](figures/InvertedPendulum-v1_log.png?raw=true)\n\n![InvertedPendulum02](figures/InvertedPendulum-v1_rewards_std.png?raw=true)\n\n\n## Inverted Pendulum (+Gaussian Sampling)\n\nThis uses the Gaussian sampling, which we should *not* be doing.\n\nNote: I ran this twice with normalized features (seeds 0 and 1), twice with\nranking transformation (seeds 2 and 3).\n\nRun with (for one seed):\n\n```\nrm -r outputs/InvertedPendulum-v1/seed0000\nclear\npython main.py InvertedPendulum-v1 \\\n    --es_iters 1000 \\\n    --log_every_t_iter 1 \\\n    --npop 200 \\\n    --seed 0 \\\n    --sigma 0.1 \\\n    --test_trajs 10 \\\n    --verbose\n```\n\nAnd then do the same thing, but with seed 0001 instead.\n\nI then did seeds 2 and 3, which has the actual reward rank transformation. Seed\n3 uses the following args (note: this time, `npop` gets doubled ... so they are\nequivalent ... sorry for the confusion):\n\n```\nNamespace(do_not_save=False, envname='InvertedPendulum-v1', es_iters=1000,\nlog_every_t_iter=1, lrate_es=0.005, npop=100, render=False, seed=3, sigma=0.1,\nsnapshot_every_t_iter=50, test_trajs=10, verbose=True)\n```\n\nYowza! It works! Here's the figure log, followed by the rewards and standard\ndeviations. They all reach the maximum score of 1000. I stopped seed 3 after 800\niterations, so **if I need to use expert trajectories, use seed 2** because that\none ran for the full 1000 iterations. The seed 2 trial took about 8 and 1/3\nhours.\n\nThe plots named \"Final\"-something contain statistics related to the 10\nrollouts the agent made each iteration, *after* it made the evolution strategies\nweight update. The plots named \"Scores\"-something contain statistics related to\nthe 200 rollouts the agent made each iteration, where the 200 rollouts are each\nwith some weight perturbation. (This is the `npop` parameter I have.)\n\n![InvertedPendulum01](figures/InvertedPendulum-v1-old_log.png?raw=true)\n\n![InvertedPendulum02](figures/InvertedPendulum-v1-old_rewards_std.png?raw=true)\n\n\n## Half Cheetah-v1 (+Gaussian Sampling)\n\nRun with:\n\n```\nrm -r outputs/HalfCheetah-v1/seed0000\nclear\npython main.py HalfCheetah-v1 \\\n    --es_iters 1000 \\\n    --log_every_t_iter 1 \\\n    --npop 200 \\\n    --seed 0 \\\n    --sigma 0.1 \\\n    --test_trajs 10 \\\n    --verbose\n```\n\nActually, I had to terminate this one after about 690 iterations because it was\ntaking too long. This took maybe 16 hours to generate! But at least it is\nlearning *something*. TRPO on HalfCheetah-v1 gets roughly 2400 so this has a\nlong way to go.\n\n![HalfCheetah01](figures/HalfCheetah-v1_log.png?raw=true)\n\n![HalfCheetah02](figures/HalfCheetah-v1_rewards_std.png?raw=true)\n\n\n[1]:https://blog.openai.com/evolution-strategies/\n"
  },
  {
    "path": "es/bash_scripts/InvertedPendulum-v1.sh",
    "content": "#!/bin/bash\nclear\npython main.py InvertedPendulum-v1 \\\n    --es_iters 700 \\\n    --lrate_es 0.005 \\\n    --log_every_t_iter 2 \\\n    --npop 200 \\\n    --seed 5 \\\n    --sigma 0.1 \\\n    --snapshot_every_t_iter 50 \\\n    --test_trajs 10 \\\n    --verbose\n"
  },
  {
    "path": "es/es.py",
    "content": "\"\"\"\nThis is Natural Evolution Strategies, designed to run on one computer and not a\ncluster.\n\n(c) May 2017 by Daniel Seita, though obviously based on OpenAI's work/idea.\n\"\"\"\n\nimport gym\nimport logz\nimport numpy as np\nimport os\nimport pickle\nimport sys\nimport tensorflow as tf\nimport tensorflow.contrib.layers as layers\nimport time\nimport utils\nfrom collections import defaultdict\nfrom gym import wrappers\nnp.set_printoptions(edgeitems=100, linewidth=100, suppress=True, precision=5)\n\n\nclass ESAgent:\n\n    def __init__(self, session, args, log_dir=None, continuous=True):\n        \"\"\" An Evolution Strategies agent.\n\n        It uses the same network architecture from OpenAI's paper, and I think\n        OpenAI didn't sample the actions from a Gaussian afterwards. The agent\n        has functionality for obtaining and updating weights in vector form to\n        make ES addition easier.\n\n        Args:\n            session: A Tensorflow session.\n            args: The argparse from the user.\n            log_dir: The log directory for the logging, if any.\n            continuous: Whether the agent acts in a continuous or discrete\n                action space. (Right now only continuous is supported.)\n        \"\"\"\n        assert continuous == True, \"Error: only continuous==True is supported.\"\n        tf.set_random_seed(args.seed)\n        self.sess = session\n        self.args = args\n        self.log_dir = log_dir\n        self.env = gym.make(args.envname)\n        ob_dim = self.env.observation_space.shape[0]\n        ac_dim = self.env.action_space.shape[0]\n        self.ob_no = tf.placeholder(shape=[None, ob_dim], dtype=tf.float32)\n\n        # Build the final network layer, which is our action (no sampling!).\n        self.sampled_ac = self._make_network(data_in=self.ob_no, out_dim=ac_dim)[0]\n\n        # To *extract* weight values, run a session on `self.weights_v`.\n        self.weights   = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='ESAgent')\n        self.weights_v = tf.concat([tf.reshape(w, [-1]) for w in self.weights], axis=0)\n        self.shapes    = [w.get_shape().as_list() for w in self.weights]\n        self.num_ws    = np.sum([np.prod(sh) for sh in self.shapes])\n\n        # To *update* weights, run `self.set_params_op` w/feed `self.new_weights_v`.\n        self.new_weights_v = tf.placeholder(tf.float32, shape=[self.num_ws])\n        updates = []\n        start = 0\n        for (i,w) in enumerate(self.weights):\n            shape = self.shapes[i]\n            size = np.prod(shape)\n            updates.append(\n                    tf.assign(w, tf.reshape(self.new_weights_v[start:start+size], shape))\n            )\n            start += size\n        self.set_params_op = tf.group(*updates)\n\n        if args.verbose:\n            self._print_summary()\n        self.sess.run(tf.global_variables_initializer())\n\n\n    def _make_network(self, data_in, out_dim):\n        \"\"\" Build the network with the same architecture following OpenAI's paper.\n\n        Returns the final *layer* of the network, which corresponds to our\n        chosen action.  There is no non-linearity for the last layer because\n        different envs have different action ranges.\n        \"\"\"\n        with tf.variable_scope(\"ESAgent\", reuse=False):\n            out = data_in\n            out = layers.fully_connected(out, num_outputs=64,\n                    weights_initializer = layers.xavier_initializer(uniform=True),\n                    #weights_initializer = utils.normc_initializer(0.5),\n                    activation_fn = tf.nn.tanh)\n            out = layers.fully_connected(out, num_outputs=64,\n                    weights_initializer = layers.xavier_initializer(uniform=True),\n                    #weights_initializer = utils.normc_initializer(0.5),\n                    activation_fn = tf.nn.tanh)\n            out = layers.fully_connected(out, num_outputs=out_dim,\n                    weights_initializer = layers.xavier_initializer(uniform=True),\n                    #weights_initializer = utils.normc_initializer(0.5),\n                    activation_fn = None)\n            return out\n\n\n    def _compute_return(self, test=False, store_info=False):\n        \"\"\" Runs the current neural network policy. \n\n        For now, we assume we run **one** episode. Also, we expand the\n        observations to get a dummy dimension, in case we figure out how to make\n        use of minibatches later.\n        \n        Args:\n            test True if testing, False if part of training. The testing could\n                be either the tests done after each weight update, or the tests\n                done as a result fo the `test` method.\n            store_info: True if storing info is desired, meaning that we return\n                observations and actions.\n\n        Returns:\n            The scalar return to be evaluated by the ES agent.\n        \"\"\"\n        max_steps = self.env.spec.timestep_limit\n        obs = self.env.reset()\n        done = False\n        steps = 0\n        total_rew = 0\n        observations = []\n        actions = []\n\n        while not done:\n            exp_obs = np.expand_dims(obs, axis=0)\n            action = self.sess.run(self.sampled_ac, {self.ob_no:exp_obs})\n            observations.append(obs)\n            actions.append(action)\n            \n            # Apply the action *after* storing the current obs/action pair.\n            obs, r, done, _ = self.env.step(action)\n            total_rew += r\n            steps += 1\n            if self.args.render and test:\n                self.env.render()\n            if steps >= max_steps or done:\n                break\n\n        if store_info:\n            return total_rew, observations, actions\n        else:\n            return total_rew\n\n\n    def _print_summary(self):\n        \"\"\" Just for debugging assistance. \"\"\"\n        print(\"\\nES Agent NN weight shapes:\\n{}\".format(self.shapes))\n        print(\"\\nES Agent NN weights:\")\n        for w in self.weights:\n            print(w)\n        print(\"\\nNumber of weights: {}\".format(self.num_ws))\n        print(\"\\naction space: {}\".format(self.env.action_space))\n        print(\"lower bound: {}\".format(self.env.action_space.low))\n        print(\"upper bound: {}\".format(self.env.action_space.high))\n        print(\"self.sampled_ac: {}\\n\".format(self.sampled_ac))\n\n\n    def run_es(self):\n        \"\"\" Runs Evolution Strategies.\n\n        Tricks used:\n            - Antithetic (i.e. mirrored) sampling.\n            - Rank transformation, using OpenAI's code.\n\n        Tricks avoided:\n            - Fixed Gaussian block. I like to just regenerate here.\n            - Virtual batch normalization, seems to be only for Atari games.\n            - Weight decay. Not sure how to do this.\n            - Action discretization. For now, it adds extra complexity.\n\n        Final weights are saved and can be pre-loaded elsewhere.\n        \"\"\"\n        args = self.args\n        t_start = time.time()\n\n        for i in range(args.es_iters):\n            if (i % args.log_every_t_iter == 0):\n                print(\"\\n************ Iteration %i ************\"%i)\n            stats = defaultdict(list)\n\n            # Set stuff up for perturbing weights and determining fitness.\n            weights_old = self.sess.run(self.weights_v) # Shape (numw,)\n            eps_nw = np.random.randn(args.npop/2, self.num_ws)\n            scores_n2 = []\n\n            for j in range(args.npop/2):\n                # Mirrored sampling, positive case, +eps_j.\n                weights_new_pos = weights_old + args.sigma * eps_nw[j]\n                self.sess.run(self.set_params_op, \n                              feed_dict={self.new_weights_v: weights_new_pos})\n                rews_pos = self._compute_return()\n\n                # Mirrored sampling, negative case, -eps_j.\n                weights_new_neg = weights_old - args.sigma * eps_nw[j]\n                self.sess.run(self.set_params_op, \n                              feed_dict={self.new_weights_v: weights_new_neg})\n                rews_neg = self._compute_return()\n\n                scores_n2.append([rews_pos,rews_neg])\n\n            # Determine the new weights based on OpenAI's rank updating.\n            proc_returns_n2 = utils.compute_centered_ranks(np.array(scores_n2))\n            F_n = proc_returns_n2[:,0] - proc_returns_n2[:,1]\n            grad = np.dot(eps_nw.T, F_n)\n\n            # Apply the gradient update. TODO: Change this to ADAM.\n            alpha = (args.lrate_es / (args.sigma*args.npop))\n            next_weights = weights_old + alpha * grad\n            self.sess.run(self.set_params_op, \n                          feed_dict={self.new_weights_v: next_weights})\n            \n            # Report relevant logs.\n            if (i % args.log_every_t_iter == 0):\n                hours = (time.time()-t_start) / (60*60.)\n\n                # Test roll-outs with these new weights.\n                returns = []\n                for _ in range(args.test_trajs):\n                    returns.append(self._compute_return(test=True))\n\n                logz.log_tabular(\"FinalAvgReturns\",  np.mean(returns))\n                logz.log_tabular(\"FinalStdReturns\",  np.std(returns))\n                logz.log_tabular(\"FinalMaxReturns\",  np.max(returns))\n                logz.log_tabular(\"FinalMinReturns\",  np.min(returns))\n                logz.log_tabular(\"ScoresAvg\",        np.mean(scores_n2))\n                logz.log_tabular(\"ScoresStd\",        np.std(scores_n2))\n                logz.log_tabular(\"ScoresMax\",        np.max(scores_n2))\n                logz.log_tabular(\"ScoresMin\",        np.min(scores_n2))\n                logz.log_tabular(\"TotalTimeHours\",   hours)\n                logz.log_tabular(\"TotalIterations\",  i)\n                logz.dump_tabular()\n\n            # Save the weights so I can test them later.\n            if (i % args.snapshot_every_t_iter == 0):\n                itr = str(i).zfill(len(str(abs(args.es_iters))))\n                with open(self.log_dir+'/snapshots/weights_'+itr+'.pkl', 'wb') as f:\n                    pickle.dump(next_weights, f)\n\n        # Save the *final* weights.\n        itr = str(i).zfill(len(str(abs(args.es_iters))))\n        with open(self.log_dir+'/snapshots/weights_'+itr+'.pkl', 'wb') as f:\n            pickle.dump(next_weights, f)\n\n\n    def test(self, just_one=True):\n        \"\"\" This is for test-time evaluation. No training is done here. By\n        default, iterate through every snapshot.  If `just_one` is true, this\n        only runs one set of weights, to ensure that we record right away since\n        OpenAI will only record subsets and less frequently.  Changing the loop\n        over snapshots is also needed.\n        \"\"\"\n        os.makedirs(self.args.directory+'/videos')\n        self.env = wrappers.Monitor(self.env, self.args.directory+'/videos', force=True)\n\n        headdir = self.args.directory+'/snapshots/'\n        snapshots = os.listdir(headdir)\n        snapshots.sort()\n        num_rollouts = 10\n        if just_one:\n            num_rollouts = 1\n\n        for sn in snapshots:\n            print(\"\\n***** Currently on snapshot {} *****\".format(sn))\n\n            ### Add your own criteria here.\n            # if \"800\" not in sn:\n            #     continue\n            ###\n\n            with open(headdir+sn, 'rb') as f:\n                weights = pickle.load(f)\n            self.sess.run(self.set_params_op, \n                          feed_dict={self.new_weights_v: weights})\n            returns = []\n            for i in range(num_rollouts):\n                returns.append( self._compute_return(test=True) )\n            print(\"mean: \\t{}\".format(np.mean(returns)))\n            print(\"std: \\t{}\".format(np.std(returns)))\n            print(\"max: \\t{}\".format(np.max(returns)))\n            print(\"min: \\t{}\".format(np.min(returns)))\n            print(\"returns:\\n{}\".format(returns))\n\n\n    def generate_rollout_data(self, weights, num_rollouts):\n        \"\"\" Roll out the expert data and save the observations and actions for\n        imitation learning later.\n\n        The observations and actions are stored in two separate lists of lists.\n        For instance, with InvertedPendulum and 100 rollouts, the shapes will be\n        be (100,1000,4) and (100,1000,1), with the 1000 representing 1000 time\n        steps. The actual expert roll-outs may not last the same time length.\n        Use the `ENV_TO_OBS_SHAPE` to guard against this scenario. We\n        **zero-pad** if needed (maybe randomizing is better? but MuJoCo is\n        continuous and actions are centered at zero...).\n\n        TL;DR: leading dimension is the minibatch, second leading dimension is\n        the timestep, third is the obs/act shape. If the obs/acts have two\n        dimensions, let's linearize to avoid worrying about it.\n\n        By the way, to experiment later with the *transits* only, just use the\n        same data here except shuffle the code. This happens elsewhere.\n\n        Args:\n            weights: The desired weight vector.\n            num_rollouts: The number of expert rollouts to save.\n        \"\"\"\n        # These are the shapes we need **for each trajectory**.\n        ENV_TO_OBS_SHAPE = {\"InvertedPendulum-v1\": (1000,4)}\n        ENV_TO_ACT_SHAPE = {\"InvertedPendulum-v1\": (1000,1)}\n        if self.args.envname not in ENV_TO_OBS_SHAPE:\n            print(\"Error, this environment is not supported.\")\n            sys.exit()\n    \n        headdir = self.args.directory+ '/expert_data'\n        if not os.path.exists(headdir):\n            os.makedirs(headdir)\n        self.sess.run(self.set_params_op, feed_dict={self.new_weights_v: weights})\n        returns = []\n        observations = []\n        actions = []\n\n        for i in range(num_rollouts):\n            if i % 10 == 0: \n                print(\"rollout {}\".format(i))\n            rew, obs_l, acts_l = self._compute_return(test=False, store_info=True)\n            returns.append(rew)\n            observations.append(obs_l)\n            actions.append(acts_l)\n        print(\"returns\", returns)\n        print(\"mean return\", np.mean(returns))\n        print(\"std of return\", np.std(returns))\n\n        # Fix padding issue to make lists have the same shape; we later make an\n        # array.  Check each (ol,al), tuple of lists, to ensure shapes match. If\n        # the obs-list doesn't match, neither will the act-list, so test one.\n        for (i,(ol,al)) in enumerate(zip(observations,actions)):\n            obs_l = np.array(ol)\n            act_l = np.array(al)\n            print(\"{} {} {}\".format(i, obs_l.shape, act_l.shape))\n            if obs_l.shape != ENV_TO_OBS_SHAPE[self.args.envname]:\n                result_o = np.zeros(ENV_TO_OBS_SHAPE[self.args.envname])\n                result_a = np.zeros(ENV_TO_ACT_SHAPE[self.args.envname])\n                result_o[:obs_l.shape[0],:obs_l.shape[1]] = obs_l\n                result_a[:act_l.shape[0],:act_l.shape[1]] = act_l\n                print(\"revised shapes: {} {}\".format(result_o.shape, result_a.shape))\n                obs_l = result_o\n                act_l = result_a\n            observations[i] = obs_l\n            actions[i] = act_l\n\n        expert_data = {'observations': np.array(observations),\n                       'actions': np.array(actions)}\n\n        # Save the data\n        print(\"obs-shape = {}\".format(expert_data['observations'].shape))\n        print(\"act-shape = {}\".format(expert_data['actions'].shape))\n        str_roll = str(num_rollouts).zfill(4)\n        name = headdir+ \"/\" +self.args.envname+ \"_\" +str_roll+ \"rollouts_trajs\"\n        np.save(name, expert_data)\n        print(\"Expert data has been saved in: {}.npy\".format(name))\n"
  },
  {
    "path": "es/logz.py",
    "content": "\"\"\"\n\nSome simple logging functionality, inspired by rllab's logging.\nAssumes that each diagnostic gets logged each iteration\n\nCall logz.configure_output_dir() to start logging to a \ntab-separated-values file (some_folder_name/log.txt)\n\nTo load the learning curves, you can do, for example\n\nA = np.genfromtxt('/tmp/expt_1468984536/log.txt',delimiter='\\t',dtype=None, names=True)\nA['EpRewMean']\n\n\"\"\"\n\nimport os.path as osp, shutil, time, atexit, os, subprocess\n\ncolor2num = dict(\n    gray=30,\n    red=31,\n    green=32,\n    yellow=33,\n    blue=34,\n    magenta=35,\n    cyan=36,\n    white=37,\n    crimson=38\n)\n\ndef colorize(string, color, bold=False, highlight=False):\n    attr = []\n    num = color2num[color]\n    if highlight: num += 10\n    attr.append(str(num))\n    if bold: attr.append('1')\n    return '\\x1b[%sm%s\\x1b[0m' % (';'.join(attr), string)\n\nclass G:\n    output_dir = None\n    output_file = None\n    first_row = True\n    log_headers = []\n    log_current_row = {}\n\ndef configure_output_dir(d=None):\n    \"\"\"\n    Set output directory to d, or to /tmp/somerandomnumber if d is None\n    \"\"\"\n    G.output_dir = d or \"/tmp/experiments/%i\"%int(time.time())\n    assert not osp.exists(G.output_dir), \"Log dir %s already exists! Delete it first or use a different dir\"%G.output_dir\n    os.makedirs(G.output_dir)\n    G.output_file = open(osp.join(G.output_dir, \"log.txt\"), 'w')\n    atexit.register(G.output_file.close)\n    try:\n        cmd = \"cd %s && git diff > %s 2>/dev/null\"%(osp.dirname(__file__), osp.join(G.output_dir, \"a.diff\"))\n        subprocess.check_call(cmd, shell=True) # Save git diff to experiment directory\n    except subprocess.CalledProcessError:\n        print(\"configure_output_dir: not storing the git diff, probably because you're not in a git repo\")\n    print(colorize(\"Logging data to %s\"%G.output_file.name, 'green', bold=True))\n\ndef log_tabular(key, val):\n    \"\"\"\n    Log a value of some diagnostic\n    Call this once for each diagnostic quantity, each iteration\n    \"\"\"\n    if G.first_row:\n        G.log_headers.append(key)\n    else:\n        assert key in G.log_headers, \"Trying to introduce a new key %s that you didn't include in the first iteration\"%key\n    assert key not in G.log_current_row, \"You already set %s this iteration. Maybe you forgot to call dump_tabular()\"%key\n    G.log_current_row[key] = val\n\ndef dump_tabular():\n    \"\"\"\n    Write all of the diagnostics from the current iteration\n    \"\"\"\n    vals = []\n    print(\"-\"*47)\n    for key in G.log_headers:\n        val = G.log_current_row.get(key, \"\")\n        if hasattr(val, \"__float__\"): valstr = \"%8.4g\"%val\n        else: valstr = val\n        print(\"| %20s | %20s |\"%(key, valstr))\n        vals.append(val)\n    print(\"-\"*47)\n    if G.output_file is not None:\n        if G.first_row:\n            G.output_file.write(\"\\t\".join(G.log_headers))\n            G.output_file.write(\"\\n\")\n        G.output_file.write(\"\\t\".join(map(str,vals)))\n        G.output_file.write(\"\\n\")\n        G.output_file.flush()\n    G.log_current_row.clear()\n    G.first_row=False\n"
  },
  {
    "path": "es/main.py",
    "content": "\"\"\"\nUse this script for setting the arguments.\n\n(c) May 2017 by Daniel Seita\n\"\"\"\n\nimport argparse\nimport logz\nimport os\nimport pickle\nimport tensorflow as tf\nimport utils\nfrom es import ESAgent\n\n\nif __name__ == \"__main__\":\n    \"\"\" LOTS of arguments here, but hopefully most are straightforward. Run\n    `python main.py -h` to visualize the help messages.\n    \"\"\"\n    parser = argparse.ArgumentParser()\n    parser.add_argument('envname', type=str, \n            help='The OpenAI gym environment name (case sensitive).')\n    parser.add_argument('--do_not_save', action='store_true',\n            help='Sets the log_dir to be None.')\n    parser.add_argument('--es_iters', type=int, default=100,\n            help='Iterations to run ES.')\n    parser.add_argument('--log_every_t_iter', type=int, default=1,\n            help='Controls the amount of time information is logged.')\n    parser.add_argument('--lrate_es', type=float, default=0.001,\n            help='Learning rate for the ES gradient update.')\n    parser.add_argument('--npop', type=int, default=200, \n            help='Weight vectors to sample for ES (INCLUDING the mirroring')\n    parser.add_argument('--render', action='store_true',\n            help='Use `--render` to visualize trajectories each iteration.')\n    parser.add_argument('--seed', type=int, default=0,\n            help='The random seed.')\n    parser.add_argument('--sigma', type=float, default=0.1,\n            help='Sigma (standard deviation) for the Gaussian noise.')\n    parser.add_argument('--snapshot_every_t_iter', type=int, default=100,\n            help='Save the model every t iterations so we can inspect later.')\n    parser.add_argument('--test_trajs', type=int, default=10, \n            help='Number of evaluation trajectories after each iteration.')\n    parser.add_argument('--verbose', action='store_true',\n            help='Use `--verbose` for a few additional debugging messages.')\n    args = parser.parse_args()\n    assert args.npop % 2 == 0 # Just to be consistent with my other code.\n\n    # Make the TensorFlow session and do some logic with handling arguments.\n    session = utils.get_tf_session()\n    log_dir = None\n    if not args.do_not_save:\n        log_dir = 'outputs/' +args.envname+ '/seed' +str(args.seed).zfill(4)\n        logz.configure_output_dir(log_dir)\n        os.makedirs(log_dir+'/snapshots/')\n        with open(log_dir+'/args.pkl','wb') as f:\n            pickle.dump(args, f)\n\n    # Build and run evolution strategies.\n    es_agent = ESAgent(session, args, log_dir)\n    es_agent.run_es()\n"
  },
  {
    "path": "es/optimizers.py",
    "content": "\"\"\"\nThis code was written by Jonathan Ho. See:\n\nhttps://github.com/openai/evolution-strategies-starter/blob/master/es_distributed/optimizers.py\n\"\"\"\n\nimport numpy as np\n\n\nclass Optimizer(object):\n    def __init__(self, pi):\n        self.pi = pi\n        self.dim = pi.num_params\n        self.t = 0\n\n    def update(self, globalg):\n        self.t += 1\n        step = self._compute_step(globalg)\n        theta = self.pi.get_trainable_flat()\n        ratio = np.linalg.norm(step) / np.linalg.norm(theta)\n        self.pi.set_trainable_flat(theta + step)\n        return ratio\n\n    def _compute_step(self, globalg):\n        raise NotImplementedError\n\n\nclass SGD(Optimizer):\n    def __init__(self, pi, stepsize, momentum=0.9):\n        Optimizer.__init__(self, pi)\n        self.v = np.zeros(self.dim, dtype=np.float32)\n        self.stepsize, self.momentum = stepsize, momentum\n\n    def _compute_step(self, globalg):\n        self.v = self.momentum * self.v + (1. - self.momentum) * globalg\n        step = -self.stepsize * self.v\n        return step\n\n\nclass Adam(Optimizer):\n    def __init__(self, pi, stepsize, beta1=0.9, beta2=0.999, epsilon=1e-08):\n        Optimizer.__init__(self, pi)\n        self.stepsize = stepsize\n        self.beta1 = beta1\n        self.beta2 = beta2\n        self.epsilon = epsilon\n        self.m = np.zeros(self.dim, dtype=np.float32)\n        self.v = np.zeros(self.dim, dtype=np.float32)\n\n    def _compute_step(self, globalg):\n        a = self.stepsize * np.sqrt(1 - self.beta2 ** self.t) / (1 - self.beta1 ** self.t)\n        self.m = self.beta1 * self.m + (1 - self.beta1) * globalg\n        self.v = self.beta2 * self.v + (1 - self.beta2) * (globalg * globalg)\n        step = -a * self.m / (np.sqrt(self.v) + self.epsilon)\n        return step\n"
  },
  {
    "path": "es/plot.py",
    "content": "\"\"\"\nTo plot this, you need to provide the experiment directory plus an output stem.\nI use this for InvertedPendulum:\n\n    python plot.py outputs/InvertedPendulum-v1 --envname InvertedPendulum-v1 \\\n            --out figures/InvertedPendulum-v1\n\n(c) May 2017 by Daniel Seita\n\"\"\"\n\nimport argparse\nimport matplotlib\nmatplotlib.use('Agg')\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport os\nimport pickle\nimport seaborn as sns\nimport sys\nfrom os.path import join\nfrom pylab import subplots\nplt.style.use('seaborn-darkgrid')\nsns.set_context(rc={'lines.markeredgewidth': 1.0})\nnp.set_printoptions(edgeitems=100,linewidth=100,suppress=True)\n\n# Some matplotlib settings.\nLOGDIR = 'outputs/'\nFIGDIR = 'figures/'\ntitle_size = 22\ntick_size = 18\nlegend_size = 17\nysize = 18\nxsize = 18\nlw = 1\nms = 8\nerror_region_alpha = 0.3\n\n# Attributes to include in a plot.\nATTRIBUTES = [\"FinalAvgReturns\",\n              \"FinalStdReturns\",\n              \"FinalMaxReturns\",\n              \"FinalMinReturns\",\n              \"ScoresAvg\",\n              \"ScoresStd\",\n              \"ScoresMax\",\n              \"ScoresMin\"]\n\n# Axes labels for environments.\nENV_TO_YLABELS = {\"HalfCheetah-v1\": [-800,1000],\n                  \"InvertedPendulum-v1\": [0,1000]}\n\n# Colors. In general we won't use all of these.\nCOLORS = ['blue', 'red', 'gold', 'black']\n\ndef plot_one_dir(args, directory):\n    \"\"\" The actual plotting code.\n\n    Assumes that we'll be plotting from one directory, which usually means\n    considering one random seed only, however it's better to have multiple\n    random seeds so this code generalizes. For ES, we should store the output at\n    *every* timestep, so A['TotalIterations'] should be like np.arange(...), but\n    this generalizes in case Ray can help me run for many more iterations.\n    \"\"\"\n    print(\"Now plotting based on directory {} ...\".format(directory))\n\n    ### Figure 1: The log.txt file.\n    num = len(ATTRIBUTES)\n    fig, axes = subplots(num, figsize=(12,3*num))\n    for (dd, cc) in zip(directory, COLORS):\n        A = np.genfromtxt(join(args.expdir, dd, 'log.txt'),\n                          delimiter='\\t', dtype=None, names=True)\n        x = A['TotalIterations']\n        for (i,attr) in enumerate(ATTRIBUTES):\n            axes[i].plot(x, A[attr], '-', lw=lw, color=cc, label=dd)\n            axes[i].set_ylabel(attr, fontsize=ysize)\n            axes[i].tick_params(axis='x', labelsize=tick_size)\n            axes[i].tick_params(axis='y', labelsize=tick_size)\n            axes[i].legend(loc='best', ncol=1, prop={'size':legend_size})\n    plt.tight_layout()\n    plt.savefig(args.out+'_log.png')\n\n    ### Figure 2: Error regions.\n    num = len(directory)\n    if num == 1: \n        num+= 1\n    fig, axes = subplots(1,num, figsize=(12*num,10))\n    for (i, (dd, cc)) in enumerate(zip(directory, COLORS)):\n        A = np.genfromtxt(join(args.expdir, dd, 'log.txt'),\n                          delimiter='\\t', dtype=None, names=True)\n        axes[i].plot(A['TotalIterations'], A[\"FinalAvgReturns\"], \n                     color=cc, marker='x', ms=ms, lw=lw)\n        axes[i].fill_between(A['TotalIterations'],\n                             A[\"FinalAvgReturns\"] - A[\"FinalStdReturns\"],\n                             A[\"FinalAvgReturns\"] + A[\"FinalStdReturns\"],\n                             alpha = error_region_alpha,\n                             facecolor='y')\n        axes[i].set_ylim(ENV_TO_YLABELS[args.envname])\n        axes[i].tick_params(axis='x', labelsize=tick_size)\n        axes[i].tick_params(axis='y', labelsize=tick_size)\n        axes[i].set_title(\"Mean Episode Rewards ({})\".format(dd), fontsize=title_size)\n        axes[i].set_xlabel(\"ES Iterations\", fontsize=xsize)\n        axes[i].set_ylabel(\"Rewards\", fontsize=ysize)\n    plt.tight_layout()\n    plt.savefig(args.out+'_rewards_std.png')\n\n\nif __name__ == \"__main__\":\n    \"\"\" \n    Handle logic with argument parsing. \n    \"\"\"\n    parser = argparse.ArgumentParser()\n    parser.add_argument(\"expdir\", help=\"experiment dir, e.g., /tmp/experiments\")\n    parser.add_argument(\"--out\", type=str, help=\"full directory where to save\")\n    parser.add_argument(\"--envname\", type=str)\n    args = parser.parse_args()\n    plot_one_dir(args, directory=os.listdir(args.expdir))\n"
  },
  {
    "path": "es/test.py",
    "content": "\"\"\"\nThis will load in snapshots of weights generated from Evolution Strategies and\nevaluate the agent by generating roll-outs. Use this to produce videos and so\nforth. No weight updates happen here, as this is like the agent evaluation\nstage. Provide the directory (envname and seed) and the arguments and snapshots\nwill be automatically loaded. Also provide the rendering option if desired. This\nwill OVERRIDE the previous render option from the training stage. Fortunately,\nthe `Namespace` class means adding and updating is easy.\n\nUsage example:\n\n    python test.py outputs/InvertedPendulum-v1/seed0004 --numr 2000\n\nAdd --render if desired. Videos are recorded and stored in a special folder in the directory.\n\n(c) May 2017 by Daniel Seita\n\"\"\"\n\nimport argparse\nimport pickle\nimport utils\nfrom es import ESAgent\n\nif __name__ == \"__main__\":\n    parser = argparse.ArgumentParser()\n    parser.add_argument('directory', type=str, \n            help='Must include envname and random seed!')\n    parser.add_argument('--numr', type=int, default=1000,\n            help='The number of expert rollouts to save.')\n    parser.add_argument('--render', action='store_true',\n            help='Use `--render` to visualize trajectories each iteration.')\n    args = parser.parse_args()\n\n    # Extract the old arguments and update the rendering.\n    with open(args.directory+'/args.pkl', 'rb') as f:\n        old_args = pickle.load(f)\n    old_args.render = args.render\n    old_args.directory = args.directory\n\n    # Run a test to see performance and/or save expert rollout data.\n    session = utils.get_tf_session()\n    es_agent = ESAgent(session, old_args, log_dir=None)\n\n    # Option 1: just run a test (videos)\n    #es_agent.test(just_one=False)\n\n    # Option 2: save expert roll-outs, dimensions = (#trajs, #times, state/act)\n    ### PUT WEIGHT PICKLE FILE HERE ###\n    pklweights = args.directory+'/snapshots/weights_700.pkl'\n    with open(pklweights, 'rb') as f:\n        weights = pickle.load(f)\n    es_agent.generate_rollout_data(weights=weights, num_rollouts=args.numr)\n"
  },
  {
    "path": "es/toy_es.py",
    "content": "\"\"\"\nBasic evolution strategies, based on Andrej Karpathy's starter code. We have the\nactual solutions here only for didactic purposes, and to get the number of\nweights correct. Actually, how similar is this to the cross entropy method that\nI've worked with before? Both re-scale and then center at the new update. I\nremember that the CEM may have only used a strict cutoff, but that's not really\na huge difference (we could smooth it out).\n\nTested on both solution sets here.\n\"\"\"\n\nimport argparse\nimport sys\nimport matplotlib.pyplot as plt\nplt.style.use('seaborn-darkgrid')\nimport numpy as np\nnp.set_printoptions(suppress=True, precision=5)\n\n# Adjust the solutions here as needed.\nSOLUTIONS = [\n    np.array([0.5, 0.1, -0.3]),\n    np.array([0.5, 0.1, -0.3, 1.0, 1.0, 0.4])\n]\n\n\ndef f(w, sol):\n    \"\"\" Define whatever function we want to optimize. \"\"\"\n    return -np.sum(np.square(sol-w))\n\n\ndef run_es(args):\n    \"\"\" Runs basic evolution strategies using the provided arguments. \n    \n    It uses the solution here only for the size and determining performance. In\n    a real problem, we wouldn't have access to it. Also, we standardize the\n    rewards. I think just because it makes sense to standardize a lot of things\n    and in our case we're just concerned about the relative benefit for each\n    weight, so rescaling is OK (e.g. for numerical purposes).\n\n    We adjust the amount of noise with sigma. This is the standard deviation and\n    we multiply it with the standard Gaussian, which is the usual way to do it.\n\n    The last line performs something that _looks_ like a gradient update. What\n    really happens is that each weight is updated using a linear combination of\n    all the weights, plus some jittered noise. We divide by npop because\n    otherwise we'd get super-large changes.\n    \"\"\"\n\n    sol = SOLUTIONS[args.sol_index]\n    w = np.random.randn(sol.size)\n\n    for i in range(args.num_iters):\n        if (i % args.print_every == 0):\n            print(\"iter {}.  w: {},  solution: {},  reward: {:.5f}\".format(\n                    str(i).zfill(4), str(w), sol, f(w,sol)))\n        N = np.random.randn(args.npop, sol.size)\n        R = np.zeros(args.npop)\n        for j in range(args.npop):\n            R[j] = f(w+args.sigma*N[j], sol)\n        A = (R - np.mean(R)) / (np.std(R)+0.000001)\n        w = w + args.lrate/(args.npop*args.sigma) * np.dot(N.T, A)\n\n\nif __name__ == \"__main__\":\n    parser = argparse.ArgumentParser() \n    parser.add_argument('--npop', type=int, default=50)\n    parser.add_argument('--sigma', type=float, default=0.1)\n    parser.add_argument('--lrate', type=float, default=0.001)\n    parser.add_argument('--sol_index', type=int, default=0)\n    parser.add_argument('--num_iters', type=int, default=500)\n    parser.add_argument('--print_every', type=int, default=20)\n    args = parser.parse_args()\n    run_es(args)\n"
  },
  {
    "path": "es/utils.py",
    "content": "\"\"\"\nRandom supporting methods.\n\n(c) May 2017 by Daniel Seita\n\"\"\"\n\nimport numpy as np\nimport sys\nimport tensorflow as tf\n\n\ndef compute_ranks(x):\n    \"\"\" Returns ranks in [0, len(x))\n\n    Note: This is different from scipy.stats.rankdata, which returns\n    ranks in [1, len(x)].\n\n    Note: this is from OpenAI's code.\n    \"\"\"\n    assert x.ndim == 1\n    ranks = np.empty(len(x), dtype=int)\n    ranks[x.argsort()] = np.arange(len(x))\n    return ranks\n\n\ndef compute_centered_ranks(x):\n    \"\"\" This is OpenAI's rank transformation code. \n    \n    They call this with x.shape = (n,2). The first column indicates the return\n    for the +eps_i case, the second for the -eps_i case (mirrored sampling).\n    Each time a roll-out happens, they append [rews_pos, rews_neg] to a list,\n    which they then vertically concatenate to get to (n,2), so n must indicate\n    the npop parameter (or maybe half of it).\n\n    This will make the maximum score have a rank of 0.5, the smallest score have\n    a rank of -0.5, and all other values get ranks uniformly distributed in\n    (-0.5, 0.5), with ties broken based on the order from np.argsort().\n\n    The OpenAI code, for each generated +eps_i noise vector, the weight for that\n    vector is actually (F_i-F_i') where F_i' is the result from negating that\n    vector. So when they do the update, they don't \"use\" the -eps_i vector. It's\n    just the +eps_i vector with a *weight* that takes into account the negative\n    case. Actually that seems right to me, if the weight is negative then we\n    would have wanted -eps_i and that would be encouraged.\n\n    See their `batched_weighted_sum` method, which takes as its first argument a\n    vector of length (n,) where n is presumably npop. Each component in that\n    vector represents an F_i-F_i' term. They then do a (1,n)*(n,numparams)\n    matrix multiply to get a final (1,numparam) weight update.\n\n    Finally, they *further* divide that vector by (n*2) before feeding it to the\n    update. That should represent the (1/npop) which I've been doing.\n    \"\"\"\n    y = compute_ranks(x.ravel()).reshape(x.shape).astype(np.float32)\n    y /= (x.size - 1)\n    y -= .5\n    return y\n\n\ndef get_tf_session():\n    \"\"\" Returning a session. Set options here (e.g. for GPUs) if desired. \"\"\"\n    tf.reset_default_graph()\n    tf_config = tf.ConfigProto(inter_op_parallelism_threads=1,\n                               intra_op_parallelism_threads=1)\n    gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.5)\n    session = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))\n\n    def get_available_gpus():\n        from tensorflow.python.client import device_lib\n        local_device_protos = device_lib.list_local_devices()\n        return [x.physical_device_desc for x in local_device_protos if x.device_type == 'GPU']\n\n    print(\"AVAILABLE GPUS: \", get_available_gpus())\n    return session\n\n\ndef normc_initializer(std=1.0):\n    \"\"\" Initialize array with normalized columns \"\"\"\n    def _initializer(shape, dtype=None, partition_info=None): #pylint: disable=W0613\n        out = np.random.randn(*shape).astype(np.float32)\n        out *= std / np.sqrt(np.square(out).sum(axis=0, keepdims=True))\n        return tf.constant(out)\n    return _initializer\n"
  },
  {
    "path": "g_learning/G-Learning.py",
    "content": "\"\"\"\n(c) 2017 by Daniel Seita\n\nG-Learning, as described in:\n\n    Taming the Noise in Reinforcement Learning via Soft Updates (UAI 2016)\n    Authors: Roy Fox*, Ari Pakman*, Naftali Tishby\n\nThis code will face the same constraints as Denny Britz's code, i.e. we need\nsimple tabular scenarios. I have tested G-learning on the following:\n\n1. CliffWorldEnv. It runs, but the results seem to be worse than Q-learning.\n\"\"\"\n\nfrom __future__ import print_function\nimport gym\nimport itertools\nimport matplotlib\nimport numpy as np\nimport sys\nif \"../\" not in sys.path:\n    sys.path.append('../')\nfrom collections import defaultdict\nfrom lib.envs.cliff_walking import CliffWalkingEnv\nfrom lib.envs.gridworld import GridworldEnv\nfrom lib import plotting\nmatplotlib.style.use('ggplot')\n\n\nclass GLearningAgent():\n\n    def __init__(self, env, k):\n        \"\"\" For now, we'll make a limitation that we know the number of states\n        and actions.  It creates:\n        \n        - G: Contains G(state,action) values.\n        - N: Contains N(state,action) values, counts of the times each\n            state-action pair was visited; needed for the alpha update.\n        - rho: The \\rho(a|s) function in the paper, the prior policy (see\n            Section 3.1 in the paper). ** Assumes uniform prior!! **\n\n        Args:\n            env: An OpenAI gym environment, either custom or built-in, but be\n                aware that not all of them can be used in this setting.\n            k: The parameter which adjusts the beta term. Should be tested.\n        \"\"\"\n        ns, na = env.observation_space.n, env.action_space.n\n        self.G = np.zeros((ns,na))\n        self.N = np.zeros((ns,na))\n        self.rho = np.ones((ns,na), dtype=float) / na\n        self.k = k\n\n\n    def policy_exploration(self, state, epsilon=0.0):\n        \"\"\" The agent's current exploration policy. Right now we default to\n        epsilon-greedy on the G(s,a) values.\n        \n        Args:\n            state: The current state the agent is in.\n            epsilon: The probability of taking a random action.\n        \n        Returns:\n            The action to take.\n        \"\"\"\n        na = self.G.shape[1]\n        action_probs = np.ones(na, dtype=float) * epsilon / na\n        best_action = np.argmax(self.G[state,:])\n        action_probs[best_action] += (1.0-epsilon)\n        return np.random.choice(np.arange(na), p=action_probs)\n \n\n    def alpha_schedule(self, t, state, action):\n        \"\"\" The alpha scheduling. By default, Equation 29 in the paper.\n        \n        Args:\n            t: The iteration of the current episode (t >= 1).\n            state: The current state.\n            action: The current action.\n\n        Returns:\n            The alpha to use for the G-learning update.\n        \"\"\"\n        alpha = self.N[state,action] ** -0.8\n        assert 0 < alpha <= 1, \"Error, alpha = {}\".format(alpha)\n        return alpha\n\n\n    def beta_schedule(self, t):\n        \"\"\" The beta scheduling. By default, Equation 26 in the paper.\n        \n        Args:\n            t: The iteration of the current episode (t >= 1).\n\n        Returns:\n            The beta to use for the G-learning update. If it's 0, G-learning\n            turns into Q^\\rho-learning. If it approaches infinity, G-learning\n            approaches Q-learning.\n        \"\"\"\n        beta = self.k * t\n        assert beta >= 0, \"Error, beta={}, k={}, t={}\".format(beta, self.k, t)\n        return beta\n\n\n    def g_learning(self, num_episodes, max_ep_steps=10000, discount=1.0, epsilon=0.1):\n        \"\"\" The G-learning algorithm.\n    \n        Args:\n            num_episodes: Number of episodes to run.\n            max_ep_steps: Maximum time steps allocated to one episode.\n            discount: Standard discount factor, usually denoted as \\gamma.\n            epsilon: Probability of taking random actions during exploration.\n    \n        Returns:\n            A tuple (G, stats) of the G-values and statistics, which should be\n            plotted and thoroughly analyzed.\n        \"\"\"\n        cum_t = 0\n        stats = plotting.EpisodeStats(episode_lengths=np.zeros(num_episodes),\n                                      episode_rewards=np.zeros(num_episodes))\n\n        for i_episode in range(num_episodes):\n            if (i_episode+1) % 1 == 0:\n                print(\"\\rEpisode {}/{}.\".format(i_episode+1, num_episodes), end=\"\")\n                sys.stdout.flush()\n            state = env.reset()\n\n            # Run this episode until we finish as indicated by the environment.\n            for t in range(1, max_ep_steps+1):\n\n                # Uses exploration policy to take a step.\n                action = self.policy_exploration(state, epsilon)\n                next_state, reward, done, _ = env.step(action)\n                cost = -reward \n\n                # Collect statistics (cum_t currently not used).\n                stats.episode_rewards[i_episode] += cost\n                stats.episode_lengths[i_episode] = t\n                self.N[state,action] += 1\n                cum_t += 1\n\n                # Intermediate terms for the G-learning update.\n                alpha = self.alpha_schedule(t, state, action)\n                beta = self.beta_schedule(t)\n                temp = np.sum(self.rho[next_state,:] * \n                              np.exp(-beta * self.G[next_state,:]))\n\n                # Official G-learning update at last. Equation 18 in the paper.\n                td_target = cost - (discount/beta) * np.log(temp)\n                td_delta = td_target - self.G[state,action]\n                self.G[state,action] += (alpha * td_delta)\n\n                if done:\n                    break\n                state = next_state\n    \n        print(\"\")\n        return self.G, stats\n\n\nif __name__ == \"__main__\":\n    \"\"\" This will run G-learning. Be sure to double check all parameters,\n    including the ones for plotting (e.g., file names).  \"\"\"\n\n    # Should test with k in {1e-3, 1e-4, 5*1e-5, 1e-6}\n    env = CliffWalkingEnv()\n    agent = GLearningAgent(env, k=1e-3) \n    G, stats = agent.g_learning(num_episodes=1000,\n                                max_ep_steps=500,\n                                discount=0.95,\n                                epsilon=0.1)\n    plotting.plot_episode_stats(stats,\n                                smoothing_window=5,\n                                noshow=False,\n                                figdir=\"figures/cliff_\",\n                                dosave=True)\n"
  },
  {
    "path": "g_learning/README.md",
    "content": "# Standard Tabular G-learning (not Q-Learning!)\n\nThis is mainly to benchmark against tabular Q-learning, [which I've implemented here](https://github.com/DanielTakeshi/rl_algorithms/tree/master/q_learning).\n\n**Note**: The paper reference for G-learning [1] uses *costs*, not rewards, so whenever I say reward here, just negate it and view it as the cost. Thus, the reward of -100 for Q-learning is really a cost of 100 for G-learning.\n\n## Cliff World\n\n### Environment\n\nI tested with `CliffWorldEnv` using the following settings:\n\n- number of episodes = 1000\n- discount factor = 0.95\n- alpha = n(s,a)^(-0.8) for the temporal difference update, where n(s,a) is the number of times that (s,a) have been visited. It's Equation 29 in reference [1].\n- epsilon = 0.1 for greedy-epsilon exploration. Once the agent executes an action, it's deterministic.\n- k = 1e-3, a special scheduling parameter for the \\beta term in G-learning, which not used in Q-learning. I also tuned with 1e4, 5\\*1e-5, and 1e-6 as reported in [1] and got similar results.\n\nFor rewards, the agent gets a -1 living reward, gets 0 if it manages to get to the bottom right corner, but gets -100 if it falls off the cliff. The agent starts at the bottom left corner and can move in one of four directions deterministically (but the **exploration policy** is epsilon-greedy based on the G(s,a) values).\n\n**Note**: In [1], the reported cost is 5 for going off the cliff, but I made it 100 because with the discount factor we have here, I don't see how the agent can learn to go to the goal. It takes a cost of 5 to immediately jump off the cliff, but it would take about a cost of 10 to go to the goal ... so the agent would prefer to jump off the cliff in the first move? When I ran Q-learning with this, Q-learning indeed learned to jump off the cliff right away.\n\n### Results\n\nFirst, episode **COSTS** over the trials, smoothed over a window of five trials. I know it says \"rewards\" in the figure but it's really \"costs\". We want the curve to decrease.\n\n![Rewards of episodes](figures/cliff_episode_reward_time.png?raw=true)\n\nUnfortunately, the agent doesn't seem to be learning anything except to jump off the cliff right away and incur a cost of 100. This is what I see when rendering the environment on the command line. \n\nWe never see costs below 100, which would happen if the agent took a path (either the riksy or the safe one) to go to the correct goal state.\n\nNext, we have the length of episodes (i.e. number of time steps). The minium we can get is 1 since the agent could actually dive into the pit on the first action. If the agent is following the \"risky\" path during training and manages to make it to the end (despite the randomness in the epsilon-greedy policy) then that's 13 steps. \n\n![Length of episodes](figures/cliff_episode_length_time.png?raw=true)\n\nUnfortunately this isn't what I want to see. I actually had to cap the number of steps in an episode (which I didn't need to do for G-learning).\n\nI'm not sure what's going on.\n\n### References\n\n[1] Taming the Noise in Reinforcement Learning via Soft Updates, UAI 2016\n"
  },
  {
    "path": "g_learning/__init__.py",
    "content": ""
  },
  {
    "path": "lib/__init__.py",
    "content": ""
  },
  {
    "path": "lib/envs/README.md",
    "content": "Different (custom) environments that we can load in and test. \n\nFrom Denny Britz:\n\n- `blackjack.py`\n- `cliff_walking.py`\n- `gridworld.py`\n- `windy_gridworld.py`\n\nFrom myself:\n\n- `two_room_domain.py`\n"
  },
  {
    "path": "lib/envs/__init__.py",
    "content": ""
  },
  {
    "path": "lib/envs/blackjack.py",
    "content": "import gym\nfrom gym import spaces\nfrom gym.utils import seeding\n\ndef cmp(a, b):\n    return int((a > b)) - int((a < b))\n\n# 1 = Ace, 2-10 = Number cards, Jack/Queen/King = 10\ndeck = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 10, 10, 10]\n\n\ndef draw_card(np_random):\n    return np_random.choice(deck)\n\n\ndef draw_hand(np_random):\n    return [draw_card(np_random), draw_card(np_random)]\n\n\ndef usable_ace(hand):  # Does this hand have a usable ace?\n    return 1 in hand and sum(hand) + 10 <= 21\n\n\ndef sum_hand(hand):  # Return current hand total\n    if usable_ace(hand):\n            return sum(hand) + 10\n    return sum(hand)\n\n\ndef is_bust(hand):  # Is this hand a bust?\n    return sum_hand(hand) > 21\n\n\ndef score(hand):  # What is the score of this hand (0 if bust)\n    return 0 if is_bust(hand) else sum_hand(hand)\n\n\ndef is_natural(hand):  # Is this hand a natural blackjack?\n    return sorted(hand) == [1, 10]\n\n\nclass BlackjackEnv(gym.Env):\n    \"\"\"Simple blackjack environment\n    Blackjack is a card game where the goal is to obtain cards that sum to as\n    near as possible to 21 without going over.  They're playing against a fixed\n    dealer.\n    Face cards (Jack, Queen, King) have point value 10.\n    Aces can either count as 11 or 1, and it's called 'usable' at 11.\n    This game is placed with an infinite deck (or with replacement).\n    The game starts with each (player and dealer) having one face up and one\n    face down card.\n    The player can request additional cards (hit=1) until they decide to stop\n    (stick=0) or exceed 21 (bust).\n    After the player sticks, the dealer reveals their facedown card, and draws\n    until their sum is 17 or greater.  If the dealer goes bust the player wins.\n    If neither player nor dealer busts, the outcome (win, lose, draw) is\n    decided by whose sum is closer to 21.  The reward for winning is +1,\n    drawing is 0, and losing is -1.\n    The observation of a 3-tuple of: the players current sum,\n    the dealer's one showing card (1-10 where 1 is ace),\n    and whether or not the player holds a usable ace (0 or 1).\n    This environment corresponds to the version of the blackjack problem\n    described in Example 5.1 in Reinforcement Learning: An Introduction\n    by Sutton and Barto (1998).\n    https://webdocs.cs.ualberta.ca/~sutton/book/the-book.html\n    \"\"\"\n    def __init__(self, natural=False):\n        self.action_space = spaces.Discrete(2)\n        self.observation_space = spaces.Tuple((\n            spaces.Discrete(32),\n            spaces.Discrete(11),\n            spaces.Discrete(2)))\n        self._seed()\n\n        # Flag to payout 1.5 on a \"natural\" blackjack win, like casino rules\n        # Ref: http://www.bicyclecards.com/how-to-play/blackjack/\n        self.natural = natural\n        # Start the first game\n        self._reset()        # Number of \n        self.nA = 2\n\n    def _seed(self, seed=None):\n        self.np_random, seed = seeding.np_random(seed)\n        return [seed]\n\n    def _step(self, action):\n        assert self.action_space.contains(action)\n        if action:  # hit: add a card to players hand and return\n            self.player.append(draw_card(self.np_random))\n            if is_bust(self.player):\n                done = True\n                reward = -1\n            else:\n                done = False\n                reward = 0\n        else:  # stick: play out the dealers hand, and score\n            done = True\n            while sum_hand(self.dealer) < 17:\n                self.dealer.append(draw_card(self.np_random))\n            reward = cmp(score(self.player), score(self.dealer))\n            if self.natural and is_natural(self.player) and reward == 1:\n                reward = 1.5\n        return self._get_obs(), reward, done, {}\n\n    def _get_obs(self):\n        return (sum_hand(self.player), self.dealer[0], usable_ace(self.player))\n\n    def _reset(self):\n        self.dealer = draw_hand(self.np_random)\n        self.player = draw_hand(self.np_random)\n\n        # Auto-draw another card if the score is less than 12\n        while sum_hand(self.player) < 12:\n            self.player.append(draw_card(self.np_random))\n\n        return self._get_obs()"
  },
  {
    "path": "lib/envs/cliff_walking.py",
    "content": "\"\"\"\nThis is adapted from Denny Britz's repository. I will modify as needed to\nreplicate existing literature results.\n\"\"\"\n\nimport numpy as np\nimport sys\nfrom gym.envs.toy_text import discrete\n\nUP = 0\nRIGHT = 1\nDOWN = 2\nLEFT = 3\n\nclass CliffWalkingEnv(discrete.DiscreteEnv):\n\n    metadata = {'render.modes': ['human', 'ansi']}\n\n    def _limit_coordinates(self, coord):\n        coord[0] = min(coord[0], self.shape[0] - 1)\n        coord[0] = max(coord[0], 0)\n        coord[1] = min(coord[1], self.shape[1] - 1)\n        coord[1] = max(coord[1], 0)\n        return coord\n\n    def _calculate_transition_prob(self, current, delta):\n        new_position = np.array(current) + np.array(delta)\n        new_position = self._limit_coordinates(new_position).astype(int)\n        new_state = np.ravel_multi_index(tuple(new_position), self.shape)\n\n        # Newer version of rewards/costs from G-learning paper\n        # reward = -100.0 if self._cliff[tuple(new_position)] else -1.0\n        reward = -1.0\n        if self._cliff[tuple(new_position)]:\n            reward = -100.0\n        elif tuple(new_position) == (3,11):\n            reward = 0.0\n\n        is_done = self._cliff[tuple(new_position)] or (tuple(new_position) == (3,11))\n        return [(1.0, new_state, reward, is_done)]\n\n    def __init__(self):\n        self.shape = (4, 12)\n\n        nS = np.prod(self.shape)\n        nA = 4\n\n        # Cliff Location\n        self._cliff = np.zeros(self.shape, dtype=np.bool)\n        self._cliff[3, 1:-1] = True\n\n        # Calculate transition probabilities\n        P = {}\n        for s in range(nS):\n            position = np.unravel_index(s, self.shape)\n            P[s] = { a : [] for a in range(nA) }\n            P[s][UP] = self._calculate_transition_prob(position, [-1, 0])\n            P[s][RIGHT] = self._calculate_transition_prob(position, [0, 1])\n            P[s][DOWN] = self._calculate_transition_prob(position, [1, 0])\n            P[s][LEFT] = self._calculate_transition_prob(position, [0, -1])\n\n        # We always start in state (3, 0)\n        isd = np.zeros(nS)\n        isd[np.ravel_multi_index((3,0), self.shape)] = 1.0\n\n        super(CliffWalkingEnv, self).__init__(nS, nA, P, isd)\n\n    def _render(self, mode='human', close=False):\n        if close:\n            return\n\n        outfile = StringIO() if mode == 'ansi' else sys.stdout\n\n        for s in range(self.nS):\n            position = np.unravel_index(s, self.shape)\n            # print(self.s)\n            if self.s == s:\n                output = \" x \"\n            elif position == (3,11):\n                output = \" T \"\n            elif self._cliff[position]:\n                output = \" C \"\n            else:\n                output = \" o \"\n\n            if position[1] == 0:\n                output = output.lstrip() \n            if position[1] == self.shape[1] - 1:\n                output = output.rstrip() \n                output += \"\\n\"\n\n            outfile.write(output)\n        outfile.write(\"\\n\")\n"
  },
  {
    "path": "lib/envs/gridworld.py",
    "content": "import numpy as np\nimport sys\nfrom gym.envs.toy_text import discrete\n\nUP = 0\nRIGHT = 1\nDOWN = 2\nLEFT = 3\n\nclass GridworldEnv(discrete.DiscreteEnv):\n    \"\"\"\n    Grid World environment from Sutton's Reinforcement Learning book chapter 4.\n    You are an agent on an MxN grid and your goal is to reach the terminal\n    state at the top left or the bottom right corner.\n\n    For example, a 4x4 grid looks as follows:\n\n    T  o  o  o\n    o  x  o  o\n    o  o  o  o\n    o  o  o  T\n\n    x is your position and T are the two terminal states.\n\n    You can take actions in each direction (UP=0, RIGHT=1, DOWN=2, LEFT=3).\n    Actions going off the edge leave you in your current state.\n    You receive a reward of -1 at each step until you reach a terminal state.\n    \"\"\"\n\n    metadata = {'render.modes': ['human', 'ansi']}\n\n    def __init__(self, shape=[4,4]):\n        if not isinstance(shape, (list, tuple)) or not len(shape) == 2:\n            raise ValueError('shape argument must be a list/tuple of length 2')\n\n        self.shape = shape\n\n        nS = np.prod(shape)\n        nA = 4\n\n        MAX_Y = shape[0]\n        MAX_X = shape[1]\n\n        P = {}\n        grid = np.arange(nS).reshape(shape)\n        it = np.nditer(grid, flags=['multi_index'])\n\n        while not it.finished:\n            s = it.iterindex\n            y, x = it.multi_index\n\n            P[s] = {a : [] for a in range(nA)}\n\n            is_done = lambda s: s == 0 or s == (nS - 1)\n            reward = 0.0 if is_done(s) else -1.0\n\n            # We're stuck in a terminal state\n            if is_done(s):\n                P[s][UP] = [(1.0, s, reward, True)]\n                P[s][RIGHT] = [(1.0, s, reward, True)]\n                P[s][DOWN] = [(1.0, s, reward, True)]\n                P[s][LEFT] = [(1.0, s, reward, True)]\n            # Not a terminal state\n            else:\n                ns_up = s if y == 0 else s - MAX_X\n                ns_right = s if x == (MAX_X - 1) else s + 1\n                ns_down = s if y == (MAX_Y - 1) else s + MAX_X\n                ns_left = s if x == 0 else s - 1\n                P[s][UP] = [(1.0, ns_up, reward, is_done(ns_up))]\n                P[s][RIGHT] = [(1.0, ns_right, reward, is_done(ns_right))]\n                P[s][DOWN] = [(1.0, ns_down, reward, is_done(ns_down))]\n                P[s][LEFT] = [(1.0, ns_left, reward, is_done(ns_left))]\n\n            it.iternext()\n\n        # Initial state distribution is uniform\n        isd = np.ones(nS) / nS\n\n        # We expose the model of the environment for educational purposes\n        # This should not be used in any model-free learning algorithm\n        self.P = P\n\n        super(GridworldEnv, self).__init__(nS, nA, P, isd)\n\n    def _render(self, mode='human', close=False):\n        if close:\n            return\n\n        outfile = StringIO() if mode == 'ansi' else sys.stdout\n\n        grid = np.arange(self.nS).reshape(self.shape)\n        it = np.nditer(grid, flags=['multi_index'])\n        while not it.finished:\n            s = it.iterindex\n            y, x = it.multi_index\n\n            if self.s == s:\n                output = \" x \"\n            elif s == 0 or s == self.nS - 1:\n                output = \" T \"\n            else:\n                output = \" o \"\n\n            if x == 0:\n                output = output.lstrip() \n            if x == self.shape[1] - 1:\n                output = output.rstrip()\n\n            outfile.write(output)\n\n            if x == self.shape[1] - 1:\n                outfile.write(\"\\n\")\n\n            it.iternext()"
  },
  {
    "path": "lib/envs/two_room_domain.py",
    "content": "\"\"\"\n(c) December 2016 by Daniel Seita\n\nThis implements the two room domain, as described in the experiment of:\n\n    Principled Option Learning in Markov Decision Processes\n    Roy Fox*, Michal Moshkovitz*, Naftali Tishby, EWRL 2016\n\nI'm trying to get it similar to the OpenAI gym interface, with a 'step' function\nthat returns similar stuff. Also, the number of non-terminal actions is\nhard-coded at 9 and follows numpad conventions:\n\n6 7 8\n3 4 5\n0 1 2\n\nSo 5 is the NO-OP action, for instance. The special termination action is\nindicated by -1. The grid is represented with a grid such as:\n\n_ _ _ X X X _ _ _\n_ _ _ X X X _ S _\n_ _ _ X X X _ _ _\n_ _ _ X X X _ _ A\n_ _ _ _ _ _ _ _ _\n_ _ _ X X X _ _ _\nG _ _ X X X _ _ _\n_ _ _ X X X _ _ _\n_ _ _ X X X _ _ _\n\nX = wall\n_ = open spot\nG = goal\nS = start\nA = agent\n\nThough actually, there probably isn't any reason for me to use the starting\nstate if the agent will be there. UPDATE: Actually wait, we do want it if we\nneed to reset the scenario.\n\nStatus: WIP\n\"\"\"\n\nimport numpy as np\nimport sys\nnp.set_printoptions(suppress=True)\n\nA_TERM = -1\nWALL   = \"X\"\nOPEN   = \"_\"\nAGENT  = \"A\"\nGOAL   = \"G\"\n\nclass TwoRooms:\n\n    def __init__(self, length=9):\n        \"\"\" Initializes the state. See elsewhere for details. \"\"\"\n        assert length >= 3, \"assert={} is too low\".format(length)\n        self.length = length\n        self.num_acts = 9\n        self.grid = np.zeros((self.length,self.length), dtype=str)\n        self.s_start, self.s_agent, self.s_goal = self._init_grid()\n\n\n    def _init_grid(self):\n        \"\"\" Initializes the grid. Currently works best for multiples of 3 which\n        are also odd. For now let's only test on 9x9 grids. \"\"\"\n\n        self.grid.fill(OPEN)\n        w1 = np.maximum((self.length/3), 1)\n        w2 = np.minimum(2*(self.length/3), self.length)\n        self.grid[:, w1:w2].fill(WALL)\n        self.grid[self.length/2, :].fill(OPEN)\n\n        sx = np.random.randint(0, self.length)\n        sy = np.random.randint(0, w1)\n        gx = np.random.randint(0, self.length)\n        gy = np.random.randint(w2, self.length)\n        s_agent = (sx,sy)\n        s_goal = (gx,gy)\n\n        assert s_agent != s_goal\n        assert self.grid[s_agent] != WALL\n        assert self.grid[s_goal] != WALL\n        self.grid[s_agent] = AGENT\n        self.grid[s_goal] = GOAL\n        s_start = s_agent\n        return s_start, s_agent, s_goal\n\n\n    def _check_coords_and_move(self, coord):\n        \"\"\" Checks if the coordinates are valid. If true, move the agent there.\n        Otherwise, we don't move. \"\"\"\n        if (coord[0] < 0 or coord[0] >= self.length or \\\n            coord[1] < 0 or coord[1] >= self.length or \\\n            self.grid[coord] == WALL):\n            pass\n        else:\n            self.grid[self.s_agent] = OPEN\n            self.s_agent = coord\n            self.grid[self.s_agent] = AGENT\n\n\n    def step(self, action):\n        \"\"\" Take one step through the environment, and return the same stuff\n        that OpenAI gym returns, with the exception of costs instead of rewards.\n        This is meant to be called by external agents.\n\n        Args:\n            action: The action to be taken by the agent.\n        \"\"\"\n\n        if action == 0:\n            self._check_coords_and_move((self.s_agent[0]+1, self.s_agent[1]-1))\n        elif action == 1:\n            self._check_coords_and_move((self.s_agent[0]+1, self.s_agent[1]))\n        elif action == 2:\n            self._check_coords_and_move((self.s_agent[0]+1, self.s_agent[1]+1))\n        elif action == 3:\n            self._check_coords_and_move((self.s_agent[0], self.s_agent[1]-1))\n        elif action == 4:\n            pass\n        elif action == 5:\n            self._check_coords_and_move((self.s_agent[0], self.s_agent[1]+1))\n        elif action == 6:\n            self._check_coords_and_move((self.s_agent[0]-1, self.s_agent[1]-1))\n        elif action == 7:\n            self._check_coords_and_move((self.s_agent[0]-1, self.s_agent[1]))\n        elif action == 8:\n            self._check_coords_and_move((self.s_agent[0]-1, self.s_agent[1]+1))\n\n        cost = 1\n        done = (action == A_TERM or self.s_agent == self.s_goal)\n        return (self.grid, cost, done, None)\n\n\n    def reset(self):\n        \"\"\" Resets the environment, like OpenAI gym. \"\"\"\n        self.s_start, self.s_agent, self.s_goal = self._init_grid()\n\n\n    def render(self):\n        \"\"\" Like in OpenAI gym, except I'll probably use it to write the image\n        to a file or something, instead of playing a video. \"\"\"\n        pass\n\n\n    def action_space_sample(self):\n        \"\"\" This is meant to be the equivalent of OpenAI gym's\n        action_space.sample, except it's in one method for simplicity.  \"\"\"\n        return np.random.randint(low=0, high=self.num_acts)\n\n\n    def _pretty_print(self):\n        print(self.grid)\n\n\ndef test_nine_rooms():\n    # Test the basic 9 room set-up.\n    env = TwoRooms(9)\n    print(\"Initial environment\")\n    env._pretty_print()\n\n    for i in range(100):\n        a = env.action_space_sample()\n        print(\"\\nTaking {}-th action a={}. Here's the environment:\".format(i,a))\n        (_, _, done, _) = env.step(a)\n        env._pretty_print()\n        if done:\n            break\n\n    env.reset()\n    print(\"\\nAfter resetting the environment:\")\n    env._pretty_print()\n\n\nif __name__ == \"__main__\":\n    \"\"\" Some testing code. \"\"\"\n    test_nine_rooms()\n"
  },
  {
    "path": "lib/envs/windy_gridworld.py",
    "content": "import gym\nimport numpy as np\nimport sys\nfrom gym.envs.toy_text import discrete\n\nUP = 0\nRIGHT = 1\nDOWN = 2\nLEFT = 3\n\nclass WindyGridworldEnv(discrete.DiscreteEnv):\n\n    metadata = {'render.modes': ['human', 'ansi']}\n\n    def _limit_coordinates(self, coord):\n        coord[0] = min(coord[0], self.shape[0] - 1)\n        coord[0] = max(coord[0], 0)\n        coord[1] = min(coord[1], self.shape[1] - 1)\n        coord[1] = max(coord[1], 0)\n        return coord\n\n    def _calculate_transition_prob(self, current, delta, winds):\n        new_position = np.array(current) + np.array(delta) + np.array([-1, 0]) * winds[tuple(current)]\n        new_position = self._limit_coordinates(new_position).astype(int)\n        new_state = np.ravel_multi_index(tuple(new_position), self.shape)\n        is_done = tuple(new_position) == (3, 7)\n        return [(1.0, new_state, -1.0, is_done)]\n\n    def __init__(self):\n        self.shape = (7, 10)\n\n        nS = np.prod(self.shape)\n        nA = 4\n\n        # Wind strength\n        winds = np.zeros(self.shape)\n        winds[:,[3,4,5,8]] = 1\n        winds[:,[6,7]] = 2\n\n        # Calculate transition probabilities\n        P = {}\n        for s in range(nS):\n            position = np.unravel_index(s, self.shape)\n            P[s] = { a : [] for a in range(nA) }\n            P[s][UP] = self._calculate_transition_prob(position, [-1, 0], winds)\n            P[s][RIGHT] = self._calculate_transition_prob(position, [0, 1], winds)\n            P[s][DOWN] = self._calculate_transition_prob(position, [1, 0], winds)\n            P[s][LEFT] = self._calculate_transition_prob(position, [0, -1], winds)\n\n        # We always start in state (3, 0)\n        isd = np.zeros(nS)\n        isd[np.ravel_multi_index((3,0), self.shape)] = 1.0\n\n        super(WindyGridworldEnv, self).__init__(nS, nA, P, isd)\n\n    def _render(self, mode='human', close=False):\n        if close:\n            return\n\n        outfile = StringIO() if mode == 'ansi' else sys.stdout\n\n        for s in range(self.nS):\n            position = np.unravel_index(s, self.shape)\n            # print(self.s)\n            if self.s == s:\n                output = \" x \"\n            elif position == (3,7):\n                output = \" T \"\n            else:\n                output = \" o \"\n\n            if position[1] == 0:\n                output = output.lstrip()\n            if position[1] == self.shape[1] - 1:\n                output = output.rstrip()\n                output += \"\\n\"\n\n            outfile.write(output)\n        outfile.write(\"\\n\")"
  },
  {
    "path": "lib/plotting.py",
    "content": "import matplotlib\nimport numpy as np\nimport pandas as pd\nfrom collections import namedtuple\nfrom matplotlib import pyplot as plt\nfrom mpl_toolkits.mplot3d import Axes3D\n\nEpisodeStats = namedtuple(\"Stats\",[\"episode_lengths\", \"episode_rewards\"])\n\ndef plot_cost_to_go_mountain_car(env, estimator, num_tiles=20):\n    x = np.linspace(env.observation_space.low[0], env.observation_space.high[0], num=num_tiles)\n    y = np.linspace(env.observation_space.low[1], env.observation_space.high[1], num=num_tiles)\n    X, Y = np.meshgrid(x, y)\n    Z = np.apply_along_axis(lambda _: -np.max(estimator.predict(_)), 2, np.dstack([X, Y]))\n\n    fig = plt.figure(figsize=(10, 5))\n    ax = fig.add_subplot(111, projection='3d')\n    surf = ax.plot_surface(X, Y, Z, rstride=1, cstride=1,\n                           cmap=matplotlib.cm.coolwarm, vmin=-1.0, vmax=1.0)\n    ax.set_xlabel('Position')\n    ax.set_ylabel('Velocity')\n    ax.set_zlabel('Value')\n    ax.set_title(\"Mountain \\\"Cost To Go\\\" Function\")\n    fig.colorbar(surf)\n    plt.show()\n\n\ndef plot_value_function(V, title=\"Value Function\"):\n    \"\"\"\n    Plots the value function as a surface plot.\n    \"\"\"\n    min_x = min(k[0] for k in V.keys())\n    max_x = max(k[0] for k in V.keys())\n    min_y = min(k[1] for k in V.keys())\n    max_y = max(k[1] for k in V.keys())\n\n    x_range = np.arange(min_x, max_x + 1)\n    y_range = np.arange(min_y, max_y + 1)\n    X, Y = np.meshgrid(x_range, y_range)\n\n    # Find value for all (x, y) coordinates\n    Z_noace = np.apply_along_axis(lambda _: V[(_[0], _[1], False)], 2, np.dstack([X, Y]))\n    Z_ace = np.apply_along_axis(lambda _: V[(_[0], _[1], True)], 2, np.dstack([X, Y]))\n\n    def plot_surface(X, Y, Z, title):\n        fig = plt.figure(figsize=(20, 10))\n        ax = fig.add_subplot(111, projection='3d')\n        surf = ax.plot_surface(X, Y, Z, rstride=1, cstride=1,\n                               cmap=matplotlib.cm.coolwarm, vmin=-1.0, vmax=1.0)\n        ax.set_xlabel('Player Sum')\n        ax.set_ylabel('Dealer Showing')\n        ax.set_zlabel('Value')\n        ax.set_title(title)\n        ax.view_init(ax.elev, -120)\n        fig.colorbar(surf)\n        plt.show()\n\n    plot_surface(X, Y, Z_noace, \"{} (No Usable Ace)\".format(title))\n    plot_surface(X, Y, Z_ace, \"{} (Usable Ace)\".format(title))\n\n\n\ndef plot_episode_stats(stats, smoothing_window=10, noshow=False, dosave=True, figdir=\"\"):\n    \"\"\" Modified to now save figures. Use the figdir to act as the directory\n    stem. \"\"\"\n\n    # Plot the episode length over time\n    fig1 = plt.figure(figsize=(10,5))\n    plt.plot(stats.episode_lengths)\n    plt.xlabel(\"Epsiode\")\n    plt.ylabel(\"Epsiode Length\")\n    plt.title(\"Episode Length over Time\")\n    if dosave:\n        plt.savefig(figdir + \"episode_length_time.png\", dpi=fig1.dpi*2)\n    if noshow:\n        plt.close(fig1)\n    else:\n        plt.show(fig1)\n\n    # Plot the episode reward over time\n    fig2 = plt.figure(figsize=(10,5))\n    rewards_smoothed = pd.Series(stats.episode_rewards).rolling(smoothing_window, min_periods=smoothing_window).mean()\n    plt.plot(rewards_smoothed)\n    plt.xlabel(\"Epsiode\")\n    plt.ylabel(\"Epsiode Reward (Smoothed)\")\n    plt.title(\"Episode Reward over Time (Smoothed over window size {})\".format(smoothing_window))\n    if dosave:\n        plt.savefig(figdir + \"episode_reward_time.png\", dpi=fig2.dpi*2)\n    if noshow:\n        plt.close(fig2)\n    else:\n        plt.show(fig2)\n\n    # Plot time steps and episode number\n    fig3 = plt.figure(figsize=(10,5))\n    plt.plot(np.cumsum(stats.episode_lengths), np.arange(len(stats.episode_lengths)))\n    plt.xlabel(\"Time Steps\")\n    plt.ylabel(\"Episode\")\n    plt.title(\"Episode per time step\")\n    if dosave:\n        plt.savefig(figdir + \"episodes_per_time.png\", dpi=fig3.dpi*2)\n    if noshow:\n        plt.close(fig3)\n    else:\n        plt.show(fig3)\n\n    return fig1, fig2, fig3\n"
  },
  {
    "path": "q_learning/Q-Learning.py",
    "content": "\"\"\"\nCode for basic tabular Q-learning. This is adapted from Denny Britz's\nrepository. I updated it to use a class to more closely match the G-learning\ncode.\n\nObservations for the **cliff_walking** scenario:\n\n- I was confused why the agent always seemed to go up at the start. But then I\n  found out it's because np.argmax(Q[observation]) will return the leading\n  index, and at the start, it's 0 all the way, so it always picks the first one\n  which is to go up (see cliff_walking.py). It's a little annoying but not a big\n  deal, it works out in the end.\n\n- The policy_fn will return one 0.925 and three 0.025s, since it will pick the\n  best action and *then* adjust for epsilons. If I want to see how the Q-values\n  are evolving, I need to use Q[observation] directly, not A.\n\n- To print, use env.render(). Very useful for the grid-like settings.\n\n- There's no extra reward for the goal state. It's just -1 for all R(s,a,s')\n  unless the successor (new_position in the code) is the cliff, in which case\n  it's -100.\n\nOther observations:\n\n- This code is general so it doesn't have to be cliff-walking, **but** you have\n  to be careful to use an environment that gives a single number as a state, not\n  a continuous state (e.g., unfortunately CartPole wouldn't work here). I can\n  use FrozenLake-v0 but even a 4x4 space requires 10k or so iterations to see\n  improvement.\n\n- At the end, it uses the plotting script, but I should probably roll out a\n  modified verison for my own use.\n\"\"\"\n\nfrom __future__ import print_function\nimport gym\nimport itertools\nimport matplotlib\nimport numpy as np\nimport sys\nif \"../\" not in sys.path:\n    sys.path.append(\"../\") \nfrom collections import defaultdict\nfrom lib.envs.cliff_walking import CliffWalkingEnv\nfrom lib.envs.gridworld import GridworldEnv\nfrom lib import plotting\nmatplotlib.style.use('ggplot')\n\n\nclass QLearningAgent():\n\n    def __init__(self, env):\n        \"\"\" For now, we'll make a limitation that we know the number of states\n        and actions.  It creates:\n        \n        - Q: Contains Q(state,action) values.\n        - N: Contains N(state,action) values, counts of the times each\n            state-action pair was visited; needed for some alpha updates.\n\n        Args:\n            env: An OpenAI gym environment, either custom or built-in, but be\n                aware that not all of them can be used in this setting.\n        \"\"\"\n        ns, na = env.observation_space.n, env.action_space.n\n        self.Q = np.zeros((ns,na))\n        self.N = np.zeros((ns,na))\n\n\n    def policy_exploration(self, state, epsilon=0.0):\n        \"\"\" The agent's current exploration policy. Right now we default to\n        epsilon-greedy on the Q(s,a) values.\n        \n        Args:\n            state: The current state the agent is in.\n            epsilon: The probability of taking a random action.\n        \n        Returns:\n            The action to take.\n        \"\"\"\n        na = self.Q.shape[1]\n        action_probs = np.ones(na, dtype=float) * epsilon / na\n        best_action = np.argmax(self.Q[state,:])\n        action_probs[best_action] += (1.0-epsilon)\n        return np.random.choice(np.arange(na), p=action_probs)\n \n\n    def alpha_schedule(self, t, state, action):\n        \"\"\" The alpha scheduling.\n        \n        Args:\n            t: The iteration of the current episode (t >= 1).\n            state: The current state.\n            action: The current action.\n\n        Returns:\n            The alpha to use for the Q-learning update.\n        \"\"\"\n        # return 0.5     # the most basic strategy\n        alpha = self.N[state,action] ** -0.8\n        assert 0 < alpha <= 1, \"Error, alpha = {}\".format(alpha)\n        return alpha\n\n\n    def q_learning(self, num_episodes, max_ep_steps=10000, discount=1.0, epsilon=0.1):\n        \"\"\" The Q-learning algorithm.\n    \n        Args:\n            num_episodes: Number of episodes to run.\n            max_ep_steps: Maximum time steps allocated to one episode.\n            discount: Standard discount factor, usually denoted as \\gamma.\n            epsilon: Probability of taking random actions during exploration.\n    \n        Returns:\n            A tuple (Q, stats) of the Q-values and statistics, which should be\n            plotted and thoroughly analyzed.\n        \"\"\"\n        cum_t = 0\n        stats = plotting.EpisodeStats(episode_lengths=np.zeros(num_episodes),\n                                      episode_rewards=np.zeros(num_episodes))\n\n        for i_episode in range(num_episodes):\n            if (i_episode+1) % 1 == 0:\n                print(\"\\rEpisode {}/{}.\".format(i_episode+1, num_episodes), end=\"\")\n                sys.stdout.flush()\n            state = env.reset()\n\n            # Run this episode until we finish as indicated by the environment.\n            for t in range(1, max_ep_steps+1):\n\n                # Uses exploration policy to take a step.\n                action = self.policy_exploration(state, epsilon)\n                next_state, reward, done, _ = env.step(action)\n\n                # Collect statistics (cum_t currently not used).\n                stats.episode_rewards[i_episode] += reward\n                stats.episode_lengths[i_episode] = t\n                self.N[state,action] += 1\n                cum_t += 1\n\n                # The official Q-learning update.\n                alpha = self.alpha_schedule(t, state, action)\n                best_next_action = np.argmax(self.Q[next_state,:])\n                td_target = reward + discount * self.Q[next_state,best_next_action]\n                td_delta = td_target - self.Q[state,action]\n                self.Q[state,action] += (alpha * td_delta)\n\n                if done:\n                    break\n                state = next_state\n    \n        print(\"\")\n        return self.Q, stats\n\n\nif __name__ == \"__main__\":\n    \"\"\" This will run Q-learning. Be sure to double check all parameters,\n    including the ones for plotting (e.g., file names).  \"\"\"\n\n    env = CliffWalkingEnv()\n    agent = QLearningAgent(env) \n    Q, stats = agent.q_learning(num_episodes=1000,\n                                max_ep_steps=500,\n                                discount=0.95,\n                                epsilon=0.1)\n    plotting.plot_episode_stats(stats,\n                                smoothing_window=5,\n                                noshow=False,\n                                figdir=\"figures/cliff_\",\n                                dosave=True)\n"
  },
  {
    "path": "q_learning/README.md",
    "content": "# Standard Tabular Q-learning\n\n## Cliff World\n\n### Environment\n\nI tested with `CliffWorldEnv` using the following settings:\n\n- number of episodes = 1000\n- discount factor = 0.95\n- alpha = n(s,a)^(-0.8) for the temporal difference update, where n(s,a) is the number of times that (s,a) have been visited. It's Equation 29 in reference [1].\n- epsilon = 0.1 for greedy-epsilon exploration. Once the agent executes an action, it's deterministic.\n\nFor rewards, the agent gets a -1 living reward, gets 0 if it manages to get to the bottom right corner, but gets -100 if it falls off the cliff. The agent starts at the bottom left corner and can move in one of four directions deterministically (but the **exploration policy** is epsilon-greedy based on the Q(s,a) values).\n\n### Results\n\nFirst, episode reward over the trials, smoothed over a window of five trials:\n\n![Rewards of episodes](figures/cliff_episode_reward_time.png?raw=true)\n\nEarly on we get some -100s due to falling off the cliff, but later we get closer the theoretical best possible of -12. However, because Q-learning is off policy, it learns the path that goes directly next to the cliff, so in **exploration** it will often fall off the cliff due to greedy-epsilon. That's the reason for the spiky nature of the graph. When I printed the environment in the last round of training, the agent would always take the risky path, sometimes succeeding, sometimes failing.\n\nNext, we have the length of episodes (i.e. number of time steps). The minium we can get is 1 since the agent could actually dive into the pit on the first action. If the agent is following the \"risky\" path during training and manages to make it to the end (despite the randomness in the epsilon-greedy policy) then that's 13 steps.\n\n![Length of episodes](figures/cliff_episode_length_time.png?raw=true)\n\nFor the most part, this is what I'd expect. We want episodes to be shorter later because the agent \"knows\" where it's going now.\n\n### References\n\n[1] Taming the Noise in Reinforcement Learning via Soft Updates, UAI 2016\n"
  },
  {
    "path": "q_learning/__init__.py",
    "content": ""
  },
  {
    "path": "trpo/README.md",
    "content": "# Trust Region Policy Optimization\n\nCode outline:\n\n- `main.py` sets up the options and the top-level call to TRPO.\n- `trpo.py` contains the TRPO agent, describing how it gets paths, computes\n  advantages, etc.\n- `utils_trpo.py` contains two particular utils ...\n- `fxn_approx.py` contains linear and neural network value functions.\n"
  },
  {
    "path": "trpo/fxn_approx.py",
    "content": "\"\"\"\nThis will make some function approximators that we can use, particularly: linear\nand neural network value functions. Instantiate instances of these in other\npieces of the code base.\n\n(c) April 2017 by Daniel Seita, built upon `starter code` from John Schulman.\n\"\"\"\n\nimport numpy as np\nimport tensorflow as tf\nimport tensorflow.contrib.distributions as distr\nimport sys\nif \"../\" not in sys.path:\n    sys.path.append(\"../\")\nfrom utils import utils_pg as utils\nnp.set_printoptions(edgeitems=100)\n\n\nclass LinearValueFunction(object):\n    \"\"\" Estimates the baseline function for PGs via ridge regression. \"\"\"\n    coef = None\n\n    def fit(self, X, y):\n        \"\"\" \n        Updates weights (self.coef) with design matrix X (i.e. observations) and\n        targets (i.e. actual returns) y. \n        \"\"\"\n        assert X.shape[0] == y.shape[0]\n        assert len(y.shape) == 1\n        Xp = self.preproc(X)\n        A = Xp.T.dot(Xp)\n        nfeats = Xp.shape[1]\n        A[np.arange(nfeats), np.arange(nfeats)] += 1e-3 # a little ridge regression\n        b = Xp.T.dot(y)\n        self.coef = np.linalg.solve(A, b)\n\n    def predict(self, X):\n        \"\"\" Predicts return from observations (i.e. environment states) X. \"\"\"\n        if self.coef is None:\n            return np.zeros(X.shape[0])\n        else:\n            return self.preproc(X).dot(self.coef)\n\n    def preproc(self, X):\n        \"\"\" Adding a bias column, and also adding squared values (huh). \"\"\"\n        return np.concatenate([np.ones([X.shape[0], 1]), X, np.square(X)/2.0], axis=1)\n\n\nclass NnValueFunction(object):\n    \"\"\" Estimates the baseline function for PGs via neural network. \"\"\"\n\n    def __init__(self, session, ob_dim=None, n_epochs=10, stepsize=1e-3):\n        \"\"\" \n        They provide us with an ob_dim in the code so I assume we can use it;\n        makes it easy to define the layers anyway. This gets constructed upon\n        initialization so future calls to self.fit should remember this. I\n        actually use the pre-processed version, though.\n        \"\"\"\n        self.n_epochs    = n_epochs\n        self.lrate       = stepsize\n        self.sy_ytarg    = tf.placeholder(shape=[None], name=\"nnvf_y\", dtype=tf.float32)\n        self.sy_ob_no    = tf.placeholder(shape=[None, ob_dim+1], name=\"nnvf_ob\", dtype=tf.float32)\n        self.sy_h1       = utils.lrelu(utils.dense(self.sy_ob_no, 32, \"nnvf_h1\", weight_init=utils.normc_initializer(1.0)), leak=0.0)\n        self.sy_h2       = utils.lrelu(utils.dense(self.sy_h1, 32, \"nnvf_h2\", weight_init=utils.normc_initializer(1.0)), leak=0.0)\n        self.sy_final_n  = utils.dense(self.sy_h2, 1, \"nnvf_final\", weight_init=utils.normc_initializer(1.0))\n        self.sy_ypred    = tf.reshape(self.sy_final_n, [-1])\n        self.sy_l2_error = tf.reduce_mean(tf.square(self.sy_ypred - self.sy_ytarg))\n        self.fit_op      = tf.train.AdamOptimizer(stepsize).minimize(self.sy_l2_error)\n        self.sess = session\n\n    def fit(self, X, y):\n        \"\"\" Updates weights (self.coef) with design matrix X (i.e. observations)\n        and targets (i.e. actual returns) y. NOTE! We now return a dictionary\n        `out` so that we can provide information relevant information for the\n        logger.\n        \"\"\"\n        assert X.shape[0] == y.shape[0]\n        assert len(y.shape) == 1\n        out = {}\n        out[\"PredStdevBefore\"]= self.predict(X).std()\n\n        Xp = self.preproc(X)\n        for i in range(self.n_epochs):\n            _,err = self.sess.run(\n                    [self.fit_op, self.sy_l2_error], \n                    feed_dict={self.sy_ob_no: Xp,\n                               self.sy_ytarg: y\n                    })\n            if i == 0:\n                out[\"MSEBefore\"] = np.sqrt(err)\n            if i == self.n_epochs-1:\n                out[\"MSEAfter\"] = np.sqrt(err)\n\n        out[\"PredStdevAfter\"] = self.predict(X).std()\n        out[\"TargStdev\"] = y.std()\n        return out\n\n    def predict(self, X):\n        \"\"\" \n        Predicts returns from observations (i.e. environment states) X. I also\n        think we need a session here. No need to expand dimensions, BTW! It's\n        effectively already done for us elsewhere.\n        \"\"\"\n        Xp = self.preproc(X)\n        return self.sess.run(self.sy_ypred, feed_dict={self.sy_ob_no:Xp})\n\n    def preproc(self, X):\n        \"\"\" Let's add this here to increase dimensionality. \"\"\"\n        #return np.concatenate([np.ones([X.shape[0], 1]), X, np.square(X)/2.0], axis=1)\n        return np.concatenate([np.ones([X.shape[0], 1]), X], axis=1)\n"
  },
  {
    "path": "trpo/main.py",
    "content": "\"\"\"\nThis is the main point for the Trust Region Policy Optimization (TRPO)\nalgorithm. Call this code using one of the bash scripts in my repository.\nOtherwise, to quickly test without saving, use:\n\n    python main.py Pendulum-v0 --vf_type nn --do_not_save --render\n\nDisable --render if this is over SSH!! (There might be a way around this, I'm\nnot sure.)\n\n(c) April 2017 by Daniel Seita. This code is built upon starter code from\nBerkeley CS 294-112.\n\"\"\"\n\nimport argparse\nimport gym\nimport itertools\nimport numpy as np\nimport sys\nimport tensorflow as tf\nimport time\nif \"../\" not in sys.path:\n    sys.path.append(\"../\")\nfrom utils import logz\nfrom fxn_approx import *\nfrom trpo import *\nnp.set_printoptions(edgeitems=100)\n\n\ndef run_trpo_algorithm(args, vf_params, logdir):\n    \"\"\" Runs TRPO and prints/saves the result as needed.\n\n    Params:\n        args: Contains a LOT of user-provided arguments.\n        vf_params: Parameters for the value function we're using.\n        logdir: Where to save the output, if desired.\n    \"\"\"\n    tf.set_random_seed(args.seed)\n    np.random.seed(args.seed)\n    env = gym.make(args.envname)\n    logz.configure_output_dir(logdir)\n\n    # Create `sess` here so that we can pass it to the NN value function.\n    tf_config = tf.ConfigProto(inter_op_parallelism_threads=1, \n                               intra_op_parallelism_threads=1) \n    sess = tf.Session(config=tf_config)\n\n    # Create the TRPO agent, which will also construct its computational graph.\n    TRPOAgent = TRPO(args, sess, env, vf_params)\n\n    # Now some administration to get things started.\n    sess.__enter__()\n    tf.global_variables_initializer().run() #pylint: disable=E1101\n    stepsize = args.initial_stepsize\n    tstart = time.time()\n    seed_iter = itertools.count()\n\n    # Official TRPO iterations.\n    for i in range(args.n_iter):\n        print(\"********** iteration %i ************\"%i)\n        infodict = {}\n        vfdict = {}\n        paths = TRPOAgent.get_paths(seed_iter, env)\n        TRPOAgent.compute_advantages(paths)\n        TRPOAgent.fit_value_function(paths, vfdict)\n        TRPOAgent.update_policy(paths, infodict)\n        TRPOAgent.log_diagnostics(paths, infodict, vfdict)\n    print(\"\\nAll done!\")\n\n\nif __name__ == \"__main__\":\n    # Get all the major arguments set up for TRPO here.\n    p = argparse.ArgumentParser()\n    p.add_argument('envname', type=str)\n    p.add_argument('--cg_damping', type=float, default=0.1)\n    p.add_argument('--do_not_save', action='store_true')\n    p.add_argument('--gamma', type=float, default=0.98)\n    p.add_argument('--initial_stepsize', type=float, default=1e-3)\n    p.add_argument('--max_kl', type=float, default=0.01)\n    p.add_argument('--min_timesteps_per_batch', type=int, default=5000) \n    p.add_argument('--n_iter', type=int, default=250)\n    p.add_argument('--nnvf_epochs', type=int, default=50)\n    p.add_argument('--nnvf_ssize', type=float, default=1e-3)\n    p.add_argument('--render', action='store_true')\n    p.add_argument('--render_frequency', type=int, default=20)\n    p.add_argument('--seed', type=int, default=0)\n    p.add_argument('--vf_type', type=str, default='linear')\n    args = p.parse_args()\n    print(\"\\nRunning TRPO with args:\\n{}\\n\".format(args.__dict__))\n\n    assert args.vf_type == 'linear' or args.vf_type == 'nn'\n    vf_params = {}\n    outstr = 'linearvf-kl' +str(args.max_kl) \n    if args.vf_type == 'nn':\n        vf_params = dict(n_epochs=args.nnvf_epochs, stepsize=args.nnvf_ssize)\n        outstr = 'nnvf-kl' +str(args.max_kl)\n    outstr += '-cg' +str(args.cg_damping)\n    outstr += '-seed' +str(args.seed).zfill(2)\n    logdir = 'outputs/' +args.envname+ '/' +outstr\n    if args.do_not_save:\n        logdir = None\n\n    run_trpo_algorithm(args, vf_params, logdir)\n"
  },
  {
    "path": "trpo/trpo.py",
    "content": "\"\"\"\nThis contains the TRPO class. Following John's code, this will contain the bulk\nof the Tensorflow construction and related code. Call this from the `main.py`\nscript.\n\n(c) April 2017 by Daniel Seita, based upon `starter code` by John Schulman, who\nused a Theano version.\n\"\"\"\n\nimport gym\nimport numpy as np\nimport tensorflow as tf\nimport time\nimport utils_trpo\nfrom collections import defaultdict\nfrom fxn_approx import *\nnp.set_printoptions(suppress=True, precision=5, edgeitems=10)\n\nimport sys\nif \"../\" not in sys.path:\n    sys.path.append(\"../\")\nfrom utils import utils_pg as utils\nfrom utils import logz\n\n\nclass TRPO:\n    \"\"\" A TRPO agent. The constructor builds its computational graph. \"\"\"\n\n    def __init__(self, args, sess, env, vf_params):\n        \"\"\" Initializes the TRPO agent. For now, assume continuous control, so\n        we'll be outputting the mean of Gaussian policies.\n        \n        It's similar to John Schulman's code. Here, `args` plays roughly the\n        role of his `usercfg`, and we also initialize the computational graph\n        here, this time in Tensorflow and not Theano. In his code, agents are\n        already outfitted with value functions and policy functions, among other\n        things. We do something similar by supplying the value function as\n        input. For symbolic variables, I try to be consistent with the naming\n        conventions at the end with `n`, `o`, and/or `a` to describe dimensions.\n        \"\"\"\n        self.args = args\n        self.sess = sess\n        self.env = env\n        self.ob_dim = ob_dim = env.observation_space.shape[0]\n        self.ac_dim = ac_dim = env.action_space.shape[0]\n        if args.vf_type == 'linear':\n            self.vf = LinearValueFunction(**vf_params)\n        elif args.vf_type == 'nn':\n            self.vf = NnValueFunction(session=sess, ob_dim=ob_dim, **vf_params)\n\n        # Placeholders for the feed_dicts, i.e. the \"beginning\" of the graph.\n        self.ob_no = tf.placeholder(shape=[None, ob_dim], name=\"ob\", dtype=tf.float32)\n        self.ac_na = tf.placeholder(shape=[None, ac_dim], name=\"ac\", dtype=tf.float32) \n        self.adv_n = tf.placeholder(shape=[None], name=\"adv\", dtype=tf.float32)\n\n        # Constructing the policy network, mapping from states -> mean vector.\n        self.h1 = utils.lrelu(utils.dense(self.ob_no, 64, \"h1\", weight_init=utils.normc_initializer(1.0)))\n        self.h2 = utils.lrelu(utils.dense(self.h1, 64, \"h2\", weight_init=utils.normc_initializer(1.0)))\n\n        # Last layer of the network to get the mean, plus also an `old` version.\n        self.mean_na    = utils.dense(self.h2, ac_dim, \"mean\", weight_init=utils.normc_initializer(0.05))\n        self.oldmean_na = tf.placeholder(shape=[None, ac_dim], name='oldmean', dtype=tf.float32)\n\n        # The log standard deviation *vector*, to be concatenated with the mean vector.\n        self.logstd_a    = tf.get_variable(\"logstd\", [ac_dim], initializer=tf.zeros_initializer())\n        self.oldlogstd_a = tf.placeholder(shape=[ac_dim], name=\"oldlogstd\", dtype=tf.float32)\n\n        # In VPG, use logprob in surrogate loss. In TRPO, we also need the old one.\n        self.logprob_n    = utils.gauss_log_prob_1(mu=self.mean_na, logstd=self.logstd_a, x=self.ac_na)\n        self.oldlogprob_n = utils.gauss_log_prob_1(mu=self.oldmean_na, logstd=self.oldlogstd_a, x=self.ac_na)\n        self.surr         = - tf.reduce_mean(self.adv_n * tf.exp(self.logprob_n - self.oldlogprob_n))\n\n        # Sample the action. Here, self.mean_na should be of shape (1,a).\n        self.sampled_ac = (tf.random_normal(tf.shape(self.mean_na)) * tf.exp(self.logstd_a) + self.mean_na)[0]\n\n        # Diagnostics, KL divergence, entropy.\n        self.kl  = tf.reduce_mean(utils.gauss_KL_1(self.mean_na, self.logstd_a, self.oldmean_na, self.oldlogstd_a))\n        self.ent = 0.5 * ac_dim * tf.log(2.*np.pi*np.e) + 0.5 * tf.reduce_sum(self.logstd_a)\n\n        # Do we need these?\n        ## self.nbatch = tf.shape(self.ob_no)[0] (maybe)\n        ## self.stepsize = tf.placeholder(shape=[], dtype=tf.float32)  (maybe)\n        ## self.update_op = tf.train.AdamOptimizer(sy_stepsize).minimize(sy_surr) (almost surely delete)\n\n        # Policy gradient vector. Only weights for the policy net, NOT value function.\n        if args.vf_type == 'linear':\n            self.params = tf.trainable_variables()\n        elif args.vf_type == 'nn':\n            self.params = [x for x in tf.trainable_variables() if 'nnvf' not in x.name]\n        self.pg = self._flatgrad(self.surr, self.params)\n        assert len((self.pg).get_shape()) == 1\n\n        # Prepare the Fisher-Vector product computation. I _think_ this is how\n        # to do it, stopping gradients from the _current_ policy (not the old\n        # one) so that the KL divegence is computed with a fixed first argument.\n        # It seems to make sense from John Schulman's slides. Also, the\n        # reduce_mean here should be the mean KL approximation to the max KL.\n        kl_firstfixed = tf.reduce_mean(utils.gauss_KL_1(\n                tf.stop_gradient(self.mean_na), \n                tf.stop_gradient(self.logstd_a),\n                self.mean_na, \n                self.logstd_a\n        ))\n        grads = tf.gradients(kl_firstfixed, self.params)\n\n        # Here, `flat_tangent` is a placeholder vector of size equal to #of (PG)\n        # params. Then `tangents` contains various subsets of that vector.\n        self.flat_tangent = tf.placeholder(tf.float32, shape=[None], name=\"flat_tangent\")\n        shapes = [var.get_shape().as_list() for var in self.params]\n        start = 0\n        tangents = []\n        for shape in shapes:\n            size = np.prod(shape)\n            tangents.append(tf.reshape(self.flat_tangent[start:start+size], shape))\n            start += size\n        self.num_params = start\n\n        # Do elementwise g*tangent then sum components, then add everything at the end.\n        # John Schulman used T.add(*[...]). The TF equivalent seems to be tf.add_n.\n        assert len(grads) == len(tangents)\n        self.gradient_vector_product = tf.add_n(inputs=\n                [tf.reduce_sum(g*tangent) for (g, tangent) in zip(grads, tangents)]\n        )\n\n        # The actual Fisher-vector product operation, where the gradients are\n        # taken w.r.t. the \"loss\" function `gvp`. I _think_ the `grads` from\n        # above computes the first derivatives, and then the `gvp` is computing\n        # the second derivatives. But what about hessian_vector_product?\n        self.fisher_vector_product = self._flatgrad(self.gradient_vector_product, self.params)\n        \n        # Deal with logic about *getting* parameters (as a flat vector).\n        self.get_params_flat_op = tf.concat([tf.reshape(v, [-1]) for v in self.params], axis=0)\n\n        # Finally, deal with logic about *setting* parameters.\n        self.theta = tf.placeholder(tf.float32, shape=[self.num_params], name=\"theta\")\n        start = 0\n        updates = []\n        for v in self.params:\n            shape = v.get_shape()\n            size = tf.reduce_prod(shape)\n            # Note that tf.assign(ref, value) assigns `value` to `ref`.\n            updates.append(\n                    tf.assign(v, tf.reshape(self.theta[start:start+size], shape))\n            )\n            start += size\n        self.set_params_flat_op = tf.group(*updates) # Performs all updates together.\n\n        print(\"In TRPO init, shapes:\\n{}\\nstart={}\".format(shapes, start))\n        print(\"self.pg: {}\\ngvp: {}\\nfvp: {}\".format(self.pg,\n            self.gradient_vector_product, self.fisher_vector_product))\n        print(\"Finished with the TRPO agent initialization.\")\n        self.start_time = time.time()\n    \n\n    def update_policy(self, paths, infodict):\n        \"\"\" Performs the TRPO policy update based on a minibach of data.\n\n        Note: this is mostly where the differences between TRPO and VPG become\n        apparent. We do a conjugate gradient step followed by a line search. I'm\n        not sure if we should be adjusting the step size based on the KL\n        divergence, as we did in VPG. Right now we don't. This is where we do a\n        lot of session calls, FYI.\n        \n        Params:\n            paths: A LIST of defaultdicts with information from the rollouts.\n            infodict: A dictionary with statistics for logging later.\n        \"\"\"\n        prob_np = np.concatenate([path[\"prob\"] for path in paths])\n        ob_no = np.concatenate([path[\"observation\"] for path in paths])\n        action_na = np.concatenate([path[\"action\"] for path in paths])\n        adv_n = np.concatenate([path[\"advantage\"] for path in paths])\n        assert prob_np.shape[0] == ob_no.shape[0] == action_na.shape[0] == adv_n.shape[0]\n        assert len(prob_np.shape) == len(ob_no.shape) == len(action_na.shape) == 2\n        assert len(adv_n.shape) == 1\n\n        # Daniel: simply gets a flat vector of the parameters.\n        thprev = self.sess.run(self.get_params_flat_op)\n\n        # Make a feed to avoid clutter later. Note, our code differs slightly\n        # from John Schulman as we have to explicitly provide the old means and\n        # old logstds, which we concatenated together into the `prob` keyword.\n        # The mean is the first half and the logstd is the second half.\n        k = self.ac_dim\n        feed = {self.ob_no: ob_no,\n                self.ac_na: action_na,\n                self.adv_n: adv_n,\n                self.oldmean_na: prob_np[:,:k],\n                self.oldlogstd_a: prob_np[0,k:]} # Use 0 because all logstd are same.\n\n        # Had to add the extra flat_tangent to the feed, otherwise I'd get errors.\n        def fisher_vector_product(p):\n            feed[self.flat_tangent] = p \n            fvp = self.sess.run(self.fisher_vector_product, feed_dict=feed)\n            return fvp + self.args.cg_damping*p\n\n        # Get the policy gradient. Also the losses, for debugging.\n        g = self.sess.run(self.pg, feed_dict=feed)\n        surrloss_before, kl_before, ent_before = self.sess.run(\n                [self.surr, self.kl, self.ent], feed_dict=feed)\n        assert kl_before == 0\n\n        if np.allclose(g, 0):\n            print(\"\\tGot zero gradient, not updating ...\")\n        else:\n            stepdir = utils_trpo.cg(fisher_vector_product, -g)\n            shs = 0.5*stepdir.dot(fisher_vector_product(stepdir))\n            lm = np.sqrt(shs / self.args.max_kl)\n            infodict[\"LagrangeM\"] = lm\n            fullstep = stepdir / lm\n            neggdotstepdir = -g.dot(stepdir)\n\n            # Returns the current self.surr (surrogate loss).\n            def loss(th):\n                self.sess.run(self.set_params_flat_op, feed_dict={self.theta: th})\n                return self.sess.run(self.surr, feed_dict=feed)\n\n            # Update the weights using `self.set_params_flat_op`.\n            success, theta = utils_trpo.backtracking_line_search(loss, \n                    thprev, fullstep, neggdotstepdir/lm)\n            self.sess.run(self.set_params_flat_op, feed_dict={self.theta: theta})\n\n        surrloss_after, kl_after, ent_after = self.sess.run(\n                [self.surr, self.kl, self.ent], feed_dict=feed)\n        logstd_new = self.sess.run(self.logstd_a, feed_dict=feed)\n        print(\"logstd new = {}\".format(logstd_new))\n\n        # For logging later.\n        infodict[\"gNorm\"] = np.linalg.norm(g)\n        infodict[\"Success\"] = success\n        infodict[\"LagrangeM\"] = lm\n        infodict[\"pol_surr_before\"] = surrloss_before\n        infodict[\"pol_surr_after\"] = surrloss_after\n        infodict[\"pol_kl_before\"] = kl_before\n        infodict[\"pol_kl_after\"] = kl_after\n        infodict[\"pol_ent_before\"] = ent_before\n        infodict[\"pol_ent_after\"] = ent_after\n\n\n    def _flatgrad(self, loss, var_list):\n        \"\"\" A Tensorflow version of John Schulman's `flatgrad` function. It\n        computes the gradients but does NOT apply them (for now). \n\n        This is only called during the `init` of the TRPO graph, so I think it's\n        OK. Otherwise, wouldn't it be constantly rebuilding the computational\n        graph? Or doing something else? Eh, for now I think it's OK.\n\n        Params:\n            loss: The loss function we're optimizing, which I assume is always\n                scalar-valued.\n            var_list: The list of variables (from `tf.trainable_variables()`) to\n                take gradients. This should only be for the policynets.\n\n        Returns:\n            A single flat vector with all gradients concatenated.\n        \"\"\"\n        grads = tf.gradients(loss, var_list)\n        return tf.concat([tf.reshape(g, [-1]) for g in grads], axis=0)\n\n \n    def _act(self, ob):\n        \"\"\" A \"private\" method for the TRPO agent so that it acts and then can\n        provide extra information.\n\n        Note that the mean and logstd here are for the current policy. There is\n        no updating done here; that's done _afterwards_. The agentinfo is a\n        vector of shape (2a,) where a is the action dimension.\n        \"\"\"\n        action, mean, logstd = self.sess.run(\n                [self.sampled_ac, self.mean_na, self.logstd_a], \n                feed_dict={self.ob_no : ob[None]}\n        )\n        agentinfo = dict()\n        agentinfo[\"prob\"] = np.concatenate((mean.flatten(), logstd.flatten()))\n        return (action, agentinfo)\n\n\n    def get_paths(self, seed_iter, env):\n        \"\"\" Computes the paths, which contains all the information from the\n        rollouts that we need for the TRPO update.\n\n        We run enough times (which may be many episodes) as desired from our\n        user-provided parameters, storing relevant material into `paths` for\n        future use. The main difference from VPG is that we have to get extra\n        information about the current log probabilities (which will later be the\n        _old_ log probs) when calling self.act(ob). \n        \n        Equivalent to John Schulman's `do_rollouts_serial` and `do_rollouts`.\n        It's easy to put all lists inside a single defaultdict.\n\n        Params:\n            seed_iter: Itertools for getting new random seeds via incrementing.\n            env: The current OpenAI gym environment.\n\n        Returns:\n            paths: A _list_ where each element is a _dictionary_ corresponding\n                to statistics from ONE episode.\n        \"\"\"\n        paths = []\n        timesteps_sofar = 0\n\n        while True:\n            np.random.seed(seed_iter.next())\n            ob = env.reset()\n            data = defaultdict(list)\n\n            # Run one episode and put the data inside `data`, then in `paths`.\n            while True:\n                data[\"observation\"].append(ob)\n                action, agentinfo = self._act(ob)\n                data[\"action\"].append(action)\n                for (k,v) in agentinfo.iteritems():\n                    data[k].append(v)\n                ob, rew, done, _ = env.step(action)\n                data[\"reward\"].append(rew)\n                if done: \n                    break\n            data = {k:np.array(v) for (k,v) in data.iteritems()}\n            paths.append(data)\n            timesteps_sofar += utils.pathlength(data)\n            if (timesteps_sofar >= self.args.min_timesteps_per_batch):\n                break\n        return paths\n\n\n    def compute_advantages(self, paths):\n        \"\"\" Computes standardized advantages from data collected during the most\n        recent set of rollouts.  \n        \n        No need to return anything, because advantages can be stored in `paths`.\n        Also, self.vf is used to estimate the baseline to reduce variance, and\n        later we will utilize the `path[\"baseline\"]` to refit the value\n        function.  Finally, note that the iteration over `paths` means each\n        `path` item is a dictionary, corresponding to the statistics garnered\n        over ONE episode.  This makes computing the discount easy since we don't\n        have to worry about crossing over different episodes.\n\n        Params:\n            paths: A LIST of defaultdicts with information from the rollouts.\n                Each defaultdict element contains information about ONE episode.\n        \"\"\"\n        for path in paths:\n            path[\"reward\"] = utils.discount(path[\"reward\"], self.args.gamma)\n            path[\"baseline\"] = self.vf.predict(path[\"observation\"])\n            path[\"advantage\"] = path[\"reward\"] - path[\"baseline\"]\n        adv_n = np.concatenate([path[\"advantage\"] for path in paths])    \n        for path in paths:\n            path[\"advantage\"] = (path[\"advantage\"] - adv_n.mean()) / (adv_n.std() + 1e-8)\n\n\n    def fit_value_function(self, paths, vfdict):\n        \"\"\" Fits the TRPO's value function with the current minibatch of data.\n        Also takes in another dictionary, `vfdict`, for relevant statistics\n        related to the value function.\n        \"\"\"\n        ob_no = np.concatenate([path[\"observation\"] for path in paths])\n        vtarg_n = np.concatenate([path[\"reward\"] for path in paths])\n        assert ob_no.shape[0] == vtarg_n.shape[0]\n        out = self.vf.fit(ob_no, vtarg_n)\n        for key in out:\n            vfdict[key] = out[key]\n\n\n    def log_diagnostics(self, paths, infodict, vfdict):\n        \"\"\" Just logging using the `logz` functionality. \"\"\"\n        ob_no = np.concatenate([path[\"observation\"] for path in paths])\n        vpred_n = np.concatenate([path[\"baseline\"] for path in paths])\n        vtarg_n = np.concatenate([path[\"reward\"] for path in paths])\n        elapsed_time = (time.time() - self.start_time) # In seconds\n        episode_rewards = np.array([path[\"reward\"].sum() for path in paths])\n        episode_lengths = np.array([utils.pathlength(path) for path in paths])\n\n        # These are *not* logged in John Schulman's code.\n        #logz.log_tabular(\"Success\",   infodict[\"Success\"])\n        #logz.log_tabular(\"LagrangeM\", infodict[\"LagrangeM\"])\n        #logz.log_tabular(\"gNorm\",     infodict[\"gNorm\"])\n\n        # These *are* logged in John Schulman's code. First, rewards:\n        logz.log_tabular(\"NumEpBatch\", len(paths))\n        logz.log_tabular(\"EpRewMean\",  episode_rewards.mean())\n        logz.log_tabular(\"EpRewMax\",   episode_rewards.max())\n        logz.log_tabular(\"EpRewSEM\",   episode_rewards.std()/np.sqrt(len(paths)))\n        logz.log_tabular(\"EpLenMean\",  episode_lengths.mean())\n        logz.log_tabular(\"EpLenMax\",   episode_lengths.max())\n        logz.log_tabular(\"RewPerStep\", episode_rewards.sum()/episode_lengths.sum())\n        logz.log_tabular(\"vf_mse_before\",      vfdict[\"MSEBefore\"])\n        logz.log_tabular(\"vf_mse_after\",       vfdict[\"MSEAfter\"])\n        logz.log_tabular(\"vf_PredStdevBefore\", vfdict[\"PredStdevBefore\"])\n        logz.log_tabular(\"vf_PredStdevAfter\",  vfdict[\"PredStdevAfter\"])\n        logz.log_tabular(\"vf_TargStdev\",       vfdict[\"TargStdev\"])\n        logz.log_tabular(\"vf_EV_before\",       utils.explained_variance_1d(vpred_n, vtarg_n))\n        logz.log_tabular(\"vf_EV_after\",        utils.explained_variance_1d(self.vf.predict(ob_no), vtarg_n))\n        # If overfitting, EVAfter >> EVBefore. Also, we fit the value function\n        # _after_ using it to compute the baseline to avoid introducing bias.\n        logz.log_tabular(\"pol_surr_before\", infodict[\"pol_surr_before\"])\n        logz.log_tabular(\"pol_surr_after\",  infodict[\"pol_surr_after\"])\n        logz.log_tabular(\"pol_kl_before\",   infodict[\"pol_kl_before\"])\n        logz.log_tabular(\"pol_kl_after\",    infodict[\"pol_kl_after\"])\n        logz.log_tabular(\"pol_ent_before\",  infodict[\"pol_ent_before\"])\n        logz.log_tabular(\"pol_ent_after\",   infodict[\"pol_ent_after\"])\n        logz.log_tabular(\"TimeElapsed\",     elapsed_time)\n        logz.dump_tabular()\n"
  },
  {
    "path": "trpo/utils_trpo.py",
    "content": "\"\"\"\nSome TRPO-specific stuff, which conatins the conjugate gradient and backtracking\nline search methods. Both of these methods are borrowed from John Schulman's\ncode:\n\n    https://github.com/joschu/modular_rl\n\nThey have been slightly modified to suit my code.\n\"\"\"\n\nimport numpy as np\n\n\ndef cg(f_Ax, b, cg_iters=10, verbose=False, residual_tol=1e-10):\n    \"\"\" Conjugate gradient, from John Schulman's code. \n    \n    Sculman used Demmel's book on applied linear algebra, page 312. Fortunately\n    I have a copy of it!! Shewchuk also has a version of this in his paper.\n    However, Shewchuk emphasizes that this is most useful for *sparse* matrices\n    `A`. We certainly have a *large* matrix since the number of rows/columns is\n    equal to the number of neural network parameters, but is it sparse?\n\n    This is used for solving linear systems of `Ax = b`, or `x = A^{-1}b`. In\n    TRPO, we don't want to compute `A` (let alone its inverse).  In addition,\n    `b` is our usual policy gradient. The goal is to find `A^{-1}b` and then\n    later (outside this code) scale that by `alpha`, and then we get the update\n    at last. I *think* the alpha-scaling comes from the line search, but I'm not\n    sure yet.\n\n    Params:\n        f_Ax: A function designed to mimic A*(input). However, we *don't* have\n            the entire matrix A formed. It's the \"Fisher-vector\" product and\n            should be computed with Tensorflow. [TODO HOW??]\n        b: A known vector. In TRPO, it's the vanilla policy gradient (I think).\n        cg_iters: Number of iterations of CG.\n        verbose: Print extra information for debugging.\n        residual_tol: Exit CG if ||r||_2^2 is small enough.\n\n    Returns:\n        Our estimate of `A^{-1}b` where A is (approximately?) the Hessian of the\n        KL divergence and `b` is given to us.\n    \"\"\"\n    p = b.copy()\n    r = b.copy()\n    x = np.zeros_like(b)\n    rdotr = r.dot(r)\n\n    fmtstr =  \"%10i %10.3g %10.3g\"\n    titlestr =  \"%10s %10s %10s\"\n    if verbose: print titlestr % (\"iter\", \"residual norm\", \"soln norm\")\n\n    for i in xrange(cg_iters):\n        if verbose: print fmtstr % (i, rdotr, np.linalg.norm(x))\n        z = f_Ax(p)\n        v = rdotr / p.dot(z)\n        x += v*p\n        r -= v*z\n        newrdotr = r.dot(r)\n        mu = newrdotr/rdotr\n        p = r + mu*p\n        rdotr = newrdotr\n        if rdotr < residual_tol:\n            break\n    if verbose: print fmtstr % (i+1, rdotr, np.linalg.norm(x))  # pylint: disable=W0631\n    return x\n\n\ndef backtracking_line_search(f, x, fullstep, expected_improve_rate, \n                             max_backtracks=10, accept_ratio=0.1):\n    \"\"\" Backtracking line search, from John Schulman's code.\n\n    I think this is the same as what's listed in Boyd & Vandenberghe's book.\n    Remember that with backtracking line search, we have a fixed descent\n    direction (typically the negative gradient, as I explain in my blog post)\n    and we have to progressively decrease the step size. Here, that's\n    `stepfrac`.\n\n    Remember, this is *one* case of backtracking line search. We are *not*\n    changing any directions, i.e. `fullstep` is our only direction we have.\n    Also, conjugate gradient comes *before* this because we need to get the\n    `fullstep` from it.\n    \n    Params:\n        f: The function we're trying to minimize.\n        x: The starting point for backtracking line search. Remember, it's\n            really `theta` since it's the parameters of our policy net.\n        fullstep: The descent direction, provided by conjugate gradient!\n        expected_improve_rate: The slope dy/dx at the initial point.\n        max_backtracks: The maximum amount of iterations (i.e. backtracks).\n        accept_ratio: The ratio which helps to determine our stopping criterion.\n            It seems like a variant of most textbook descriptions of\n            backtracking line search; here, I think it's to ensure we get\n            above a threshold of improvement.\n\n    Returns:\n        A tuple (Y, x) where Y is a boolean indicating whether we've\n        successfully found a new point to go to, and x is that final point, or\n        the original x if the line search didn't find a better point.\n    \"\"\"\n    fval = f(x)\n    print(\"fval before {}\".format(fval))\n    for (_n_backtracks, stepfrac) in enumerate(.5**np.arange(max_backtracks)):\n        xnew = x + stepfrac*fullstep\n        newfval = f(xnew)\n        actual_improve = fval - newfval\n        expected_improve = expected_improve_rate*stepfrac\n        ratio = actual_improve/expected_improve\n        print(\"actual_i / expected_i / ratio = {:.4f} / {:.4f} / {:.4f}\".format(\n                actual_improve, expected_improve, ratio))\n        if ratio > accept_ratio and actual_improve > 0:\n            print(\"fval after {:.4f}\".format(newfval))\n            return (True, xnew)\n    return (False, x)\n"
  },
  {
    "path": "utils/__init__.py",
    "content": ""
  },
  {
    "path": "utils/logz.py",
    "content": "\"\"\"\nSome simple logging functionality, inspired by rllab's logging.\nAssumes that each diagnostic gets logged each iteration\n\nCall logz.configure_output_dir() to start logging to a \ntab-separated-values file (some_folder_name/log.txt)\n\nTo load the learning curves, you can do, for example\n\nA = np.genfromtxt('/tmp/expt_1468984536/log.txt',delimiter='\\t',dtype=None, names=True)\nA['EpRewMean']\n\"\"\"\n\nimport os.path as osp, shutil, time, atexit, os, subprocess\n\ncolor2num = dict(\n    gray=30,\n    red=31,\n    green=32,\n    yellow=33,\n    blue=34,\n    magenta=35,\n    cyan=36,\n    white=37,\n    crimson=38\n)\n\n\ndef colorize(string, color, bold=False, highlight=False):\n    attr = []\n    num = color2num[color]\n    if highlight: num += 10\n    attr.append(str(num))\n    if bold: attr.append('1')\n    return '\\x1b[%sm%s\\x1b[0m' % (';'.join(attr), string)\n\n\nclass G:\n    output_dir = None\n    output_file = None\n    first_row = True\n    log_headers = []\n    log_current_row = {}\n\n\ndef configure_output_dir(d=None):\n    \"\"\"\n    Set output directory to d, or to /tmp/somerandomnumber if d is None\n    \"\"\"\n    G.output_dir = d or \"/tmp/experiments/%i\"%int(time.time())\n    assert not osp.exists(G.output_dir), \"Log dir %s already exists! Delete it first or use a different dir\"%G.output_dir\n    os.makedirs(G.output_dir)\n    G.output_file = open(osp.join(G.output_dir, \"log.txt\"), 'w')\n    atexit.register(G.output_file.close)\n    try:\n        cmd = \"cd %s && git diff > %s 2>/dev/null\"%(osp.dirname(__file__), osp.join(G.output_dir, \"a.diff\"))\n        subprocess.check_call(cmd, shell=True) # Save git diff to experiment directory\n    except subprocess.CalledProcessError:\n        print(\"configure_output_dir: not storing the git diff, probably because you're not in a git repo\")\n    print(colorize(\"Logging data to %s\"%G.output_file.name, 'green', bold=True))\n\n\ndef log_tabular(key, val):\n    \"\"\"\n    Log a value of some diagnostic\n    Call this once for each diagnostic quantity, each iteration\n    \"\"\"\n    if G.first_row:\n        G.log_headers.append(key)\n    else:\n        assert key in G.log_headers, \"Trying to introduce a new key %s that you didn't include in the first iteration\"%key\n    assert key not in G.log_current_row, \"You already set %s this iteration. Maybe you forgot to call dump_tabular()\"%key\n    G.log_current_row[key] = val\n\n\ndef dump_tabular():\n    \"\"\"\n    Write all of the diagnostics from the current iteration\n    \"\"\"\n    vals = []\n    print(\"-\"*47)\n    for key in G.log_headers:\n        val = G.log_current_row.get(key, \"\")\n        if hasattr(val, \"__float__\"): valstr = \"%8.4g\"%val\n        else: valstr = val\n        print(\"| %20s | %20s |\"%(key, valstr))\n        vals.append(val)\n    print(\"-\"*47)\n    if G.output_file is not None:\n        if G.first_row:\n            G.output_file.write(\"\\t\".join(G.log_headers))\n            G.output_file.write(\"\\n\")\n        G.output_file.write(\"\\t\".join(map(str,vals)))\n        G.output_file.write(\"\\n\")\n        G.output_file.flush()\n    G.log_current_row.clear()\n    G.first_row=False\n"
  },
  {
    "path": "utils/policies.py",
    "content": "\"\"\"\nFor managing policies. This seems like a better way to organize things. For now,\nwe have **stochastic** policies. This assumes the Python3 way of calling\nsuperclasses' init methods.\n\nTODO figure out a good way to integrate deterministic policies, figure out how\nto get a good configuration file (for neural nets), etc. Lots of fun! :)\n\nTODO figure out how to make assertions that we're in continuous vs discrete\nspaces.\n\nTODO have a net specification which we can use instead of hard-coding networks\nhere.\n\"\"\"\n\nimport numpy as np\nimport sys\nimport tensorflow as tf\nimport tensorflow.contrib.layers as layers\nfrom . import utils_pg as utils\n\n\nclass StochasticPolicy(object):\n\n    def __init__(self, sess, ob_dim, ac_dim):\n        \"\"\" \n        Initializes the neural network policy. Right now there isn't much here,\n        but this is a flexible design pattern for future versions of the code.\n        \"\"\"\n        self.sess = sess\n\n    def sample_action(self, x):\n        \"\"\" To be implemented in the subclass. \"\"\"\n        raise NotImplementedError\n\n\nclass GibbsPolicy(StochasticPolicy):\n    \"\"\" A policy where the action is to be sampled based on sampling a\n    categorical random variable; this is for discrete control. \"\"\"\n\n    def __init__(self, sess, ob_dim, ac_dim):\n        super().__init__(sess, ob_dim, ac_dim)\n\n        # Placeholders for our inputs.\n        self.ob_no = tf.placeholder(shape=[None, ob_dim], name=\"obs\", dtype=tf.float32)\n        self.ac_n  = tf.placeholder(shape=[None], name=\"act\", dtype=tf.int32)\n        self.adv_n = tf.placeholder(shape=[None], name=\"adv\", dtype=tf.float32)\n        self.oldlogits_na = tf.placeholder(shape=[None, ac_dim], name='oldlogits', dtype=tf.float32)\n\n        # Form the policy network and the log probabilities.\n        self.hidden1 = layers.fully_connected(self.ob_no, \n                num_outputs=50,\n                weights_initializer=layers.xavier_initializer(uniform=True),\n                activation_fn=tf.nn.tanh)\n        self.logits_na = layers.fully_connected(self.hidden1, \n                num_outputs=ac_dim,\n                weights_initializer=layers.xavier_initializer(uniform=True),\n                activation_fn=None)\n        self.logp_na = tf.nn.log_softmax(self.logits_na)\n\n        # Log probabilities of the actions in the minibatch, plus sampled action.\n        self.nbatch     = tf.shape(self.ob_no)[0]\n        self.logprob_n  = utils.fancy_slice_2d(self.logp_na, tf.range(self.nbatch), self.ac_n)\n        self.sampled_ac = utils.categorical_sample_logits(self.logits_na)[0]\n\n        # Policy gradients loss function and training step.\n        self.surr_loss = - tf.reduce_mean(self.logprob_n * self.adv_n)\n        self.stepsize  = tf.placeholder(shape=[], dtype=tf.float32)\n        self.update_op = tf.train.AdamOptimizer(self.stepsize).minimize(self.surr_loss)\n\n        # For KL divergence and entropy diagnostic purposes. These are computed\n        # as averages across individual KL/entropy w.r.t each minibatch state.\n        self.oldlogp_na = tf.nn.log_softmax(self.oldlogits_na)\n        self.oldp_na    = tf.exp(self.oldlogp_na)\n        self.p_na       = tf.exp(self.logp_na)\n        self.kl_n       = tf.reduce_sum(self.oldp_na * (self.oldlogp_na - self.logp_na), axis=1)\n\n        # I'm not sure why the KL divergence can be slightly negative. Each row\n        # corresponds to a valid distribution. Must be numerical instability?\n        self.assert_op  = tf.Assert(tf.reduce_all(self.kl_n >= -1e-4), [self.kl_n]) \n        with tf.control_dependencies([self.assert_op]):\n            self.kl_n = tf.identity(self.kl_n)\n        self.kl  = tf.reduce_mean(self.kl_n)\n        self.ent = tf.reduce_mean(tf.reduce_sum( -self.p_na * self.logp_na, axis=1))\n\n\n    def sample_action(self, ob):\n        return self.sess.run(self.sampled_ac, feed_dict={self.ob_no: ob[None]})\n \n\n    def update_policy(self, ob_no, ac_n, std_adv_n, stepsize):\n        \"\"\" \n        Upon getting observations, those are fed through the network to get the\n        logits. After this the computational graph eventually updates the\n        policy, so the logits are now old logits. \n        \"\"\"\n        feed = {self.ob_no: ob_no,\n                self.ac_n: ac_n,\n                self.adv_n: std_adv_n,\n                self.stepsize: stepsize}\n        _, surr_loss, oldlogits_na = self.sess.run(\n                [self.update_op, self.surr_loss, self.logits_na], feed_dict=feed)\n        return surr_loss, oldlogits_na\n\n       \n    def kldiv_and_entropy(self, ob_no, oldlogits_na):\n        \"\"\" Returning KL diverence and current entropy since they can re-use\n        some of the computation. \n        \n        In particular, the entropy doesn't need the old logits, since it just\n        forwards the observation batch through the network to find the current\n        log probabilities. \"\"\"\n        return self.sess.run([self.kl, self.ent], \n                feed_dict={self.ob_no:ob_no, self.oldlogits_na:oldlogits_na})\n\n\nclass GaussianPolicy(StochasticPolicy):\n    \"\"\" A policy where the action is to be sampled based on sampling a Gaussian;\n    this is for continuous control. \"\"\"\n\n    def __init__(self, sess, ob_dim, ac_dim):\n        super().__init__(sess, ob_dim, ac_dim)\n\n        # Placeholders for our inputs. Note that actions are floats.\n        self.ob_no = tf.placeholder(shape=[None, ob_dim], name=\"obs\", dtype=tf.float32)\n        self.ac_na = tf.placeholder(shape=[None, ac_dim], name=\"act\", dtype=tf.float32)\n        self.adv_n = tf.placeholder(shape=[None], name=\"adv\", dtype=tf.float32)\n        self.n     = tf.shape(self.ob_no)[0]\n        \n        # Special to the continuous case, the log std vector, it's a parameter.\n        # Also, make batch versions so we get shape (n,a) (or (1,a)), not (a,).\n        self.logstd_a     = tf.get_variable(\"logstd\", [ac_dim], initializer=tf.zeros_initializer())\n        self.oldlogstd_a  = tf.placeholder(name=\"oldlogstd\", shape=[ac_dim], dtype=tf.float32)\n        self.logstd_na    = tf.ones(shape=(self.n,ac_dim), dtype=tf.float32) * self.logstd_a\n        self.oldlogstd_na = tf.ones(shape=(self.n,ac_dim), dtype=tf.float32) * self.oldlogstd_a\n\n        # The policy network and the logits, which are the mean of a Gaussian.\n        # Then don't forget to make an \"old\" version of that for KL divergences.\n        self.hidden1 = layers.fully_connected(self.ob_no, \n                num_outputs=32,\n                weights_initializer=layers.xavier_initializer(uniform=True),\n                activation_fn=tf.nn.relu)\n        self.hidden2 = layers.fully_connected(self.hidden1, \n                num_outputs=32,\n                weights_initializer=layers.xavier_initializer(uniform=True),\n                activation_fn=tf.nn.relu)\n        self.mean_na = layers.fully_connected(self.hidden2, \n                num_outputs=ac_dim,\n                weights_initializer=layers.xavier_initializer(uniform=True),\n                activation_fn=None)\n        self.oldmean_na = tf.placeholder(shape=[None, ac_dim], name='oldmean', dtype=tf.float32)\n\n        # Diagonal Gaussian distribution for sampling actions and log probabilities.\n        self.logprob_n  = utils.gauss_log_prob(mu=self.mean_na, logstd=self.logstd_na, x=self.ac_na)\n        self.sampled_ac = (tf.random_normal(tf.shape(self.mean_na)) * tf.exp(self.logstd_na) + self.mean_na)[0]\n\n        # Loss function that we'll differentiate to get the policy  gradient\n        self.surr_loss = - tf.reduce_mean(self.logprob_n * self.adv_n) \n        self.stepsize  = tf.placeholder(shape=[], dtype=tf.float32) \n        self.update_op = tf.train.AdamOptimizer(self.stepsize).minimize(self.surr_loss)\n\n        # KL divergence and entropy among Gaussian(s).\n        self.kl  = tf.reduce_mean(utils.gauss_KL(self.mean_na, self.logstd_na, self.oldmean_na, self.oldlogstd_na))\n        self.ent = 0.5 * ac_dim * tf.log(2.*np.pi*np.e) + 0.5 * tf.reduce_sum(self.logstd_a)\n\n\n    def sample_action(self, ob):\n        return self.sess.run(self.sampled_ac, feed_dict={self.ob_no: ob[None]})\n\n\n    def update_policy(self, ob_no, ac_n, std_adv_n, stepsize):\n        \"\"\" \n        The input is the same for the discrete control case, except we return a\n        single log standard deviation vector in addition to our logits. In this\n        case, the logits are really the mean vector of Gaussians, which differs\n        among components (observations) in the minbatch. We return the *old*\n        ones since they are assigned, then `self.update_op` runs, which makes\n        them outdated.\n        \"\"\"\n        feed = {self.ob_no: ob_no,\n                self.ac_na: ac_n,\n                self.adv_n: std_adv_n,\n                self.stepsize: stepsize}\n        _, surr_loss, oldmean_na, oldlogstd_a = self.sess.run(\n                [self.update_op, self.surr_loss, self.mean_na, self.logstd_a],\n                feed_dict=feed)\n        return surr_loss, oldmean_na, oldlogstd_a\n\n       \n    def kldiv_and_entropy(self, ob_no, oldmean_na, oldlogstd_a):\n        \"\"\" Returning KL diverence and current entropy since they can re-use\n        some of the computation. For the KL divergence, though, we reuqire the\n        old mean *and* the old log standard deviation to fully characterize the\n        set of probability distributions we had earlier, each conditioned on\n        different states in the MDP. Then we take the *average* of these, etc.,\n        similar to the discrete case.\n        \"\"\"\n        feed = {self.ob_no: ob_no,\n                self.oldmean_na: oldmean_na,\n                self.oldlogstd_a: oldlogstd_a}\n        return self.sess.run([self.kl, self.ent], feed_dict=feed)\n"
  },
  {
    "path": "utils/utils_pg.py",
    "content": "\"\"\"\nSeveral utilities to reduce clutter in my policy gradient codes.\n\n(c) April-June 2017 (mostly) by Daniel Seita\n\"\"\"\n\nimport numpy as np\nimport tensorflow as tf\nimport scipy.signal\nimport sys\n\ndef gauss_log_prob_1(mu, logstd, x):\n    \"\"\" \n    Calls `gauss_log_prob` with a broadcasted version of logstd. Assumes that\n    logstd is of shape (n,) and mu is of shape (n,a). \n    \"\"\"\n    assert mu.get_shape()[1:] == x.get_shape()[1:]\n    assert len(logstd.get_shape()) == 1\n    logstd_broadcasted = tf.ones(shape=tf.shape(mu), dtype=tf.float32) * logstd\n    return gauss_log_prob(mu, logstd_broadcasted, x)\n\n\ndef gauss_log_prob(mu, logstd, x):\n    \"\"\" Used for computing the log probability, following the formula for the\n    multivariate Gaussian density. \n    \n    All the inputs should have shape (n,a). The `gp_na` contains component-wise\n    probabilitiles, then the reduce_sum results in a tensor of size (n,) which\n    contains the log probability for each of the n elements. (We later perform a\n    mean on this.) Also, the 2*pi part needs 1/2, but doesn't need the sum over\n    the number of components (# of actions) because of the reduce sum here.\n    Finally, logstd doesn't need a 1/2 constant because log(\\sigma_i^2) will\n    bring the 2 over. \n    \n    This formula generalizes for an arbitrary number of actions, BUT it assumes\n    that the covariance matrix is diagonal.\n    \"\"\"\n    var_na = tf.exp(2*logstd)\n    gp_na = -tf.square(x - mu)/(2*var_na) - 0.5*tf.log(tf.constant(2*np.pi)) - logstd\n    return tf.reduce_sum(gp_na, axis=[1])\n\n\ndef gauss_KL_1(mu1, logstd1, mu2, logstd2):\n    \"\"\" \n    Calls `gauss_KL` with a broadcasted version of logstd1 and logstd1.  Assumes\n    that logstd1 and logstd2 are of shape (n,). \n    \"\"\"\n    assert mu1.get_shape()[1:] == mu2.get_shape()[1:]\n    assert len(logstd1.get_shape()) == 1\n    assert len(logstd2.get_shape()) == 1\n    logstd1_broadcasted = tf.ones(shape=tf.shape(mu1), dtype=tf.float32) * logstd1\n    logstd2_broadcasted = tf.ones(shape=tf.shape(mu2), dtype=tf.float32) * logstd2\n    return gauss_KL(mu1, logstd1_broadcasted, mu2, logstd2_broadcasted)\n\n\ndef gauss_KL(mu1, logstd1, mu2, logstd2):\n    \"\"\" Returns KL divergence among two multivariate Gaussians, component-wise.\n\n    It assumes the covariance matrix is diagonal. All inputs have shape (n,a).\n    It is not necessary to know the number of actions because reduce_sum will\n    sum over this to get the `d` constant offset. The part consisting of the\n    trace in the formula is blended with the mean difference squared due to the\n    common \"denominator\" of var2_na.  This forumula generalizes for an arbitrary\n    number of actions.  I think mu2 and logstd2 should represent the policy\n    before the update.\n\n    Returns the KL divergence for each of the n components in the minibatch,\n    then we do a reduce_mean outside this.\n    \"\"\"\n    var1_na = tf.exp(2.*logstd1)\n    var2_na = tf.exp(2.*logstd2)\n    tmp_matrix = 2.*(logstd2 - logstd1) + (var1_na + tf.square(mu1-mu2))/var2_na - 1\n    kl_n = tf.reduce_sum(0.5 * tmp_matrix, axis=[1]) # Don't forget the 1/2 !!\n    assert_op = tf.Assert(tf.reduce_all(kl_n >= -0.0000001), [kl_n]) \n    with tf.control_dependencies([assert_op]):\n        kl_n = tf.identity(kl_n)\n    return kl_n\n\n\ndef normc_initializer(std=1.0):\n    \"\"\" Initialize array with normalized columns \"\"\"\n    def _initializer(shape, dtype=None, partition_info=None): #pylint: disable=W0613\n        out = np.random.randn(*shape).astype(np.float32)\n        out *= std / np.sqrt(np.square(out).sum(axis=0, keepdims=True))\n        return tf.constant(out)\n    return _initializer\n\n\ndef dense(x, size, name, weight_init=None):\n    \"\"\" Dense (fully connected) layer \"\"\"\n    w = tf.get_variable(name + \"/w\", [x.get_shape()[1], size], initializer=weight_init)\n    b = tf.get_variable(name + \"/b\", [size], initializer=tf.zeros_initializer())\n    return tf.matmul(x, w) + b\n\n\ndef fancy_slice_2d(X, inds0, inds1):\n    \"\"\" Like numpy's X[inds0, inds1] \"\"\"\n    inds0 = tf.cast(inds0, tf.int64)\n    inds1 = tf.cast(inds1, tf.int64)\n    shape = tf.cast(tf.shape(X), tf.int64)\n    ncols = shape[1]\n    Xflat = tf.reshape(X, [-1])\n    return tf.gather(Xflat, inds0 * ncols + inds1)\n\n\ndef discount(x, gamma):\n    \"\"\"\n    Compute discounted sum of future values. Returns a list, NOT a scalar!\n    out[i] = in[i] + gamma * in[i+1] + gamma^2 * in[i+2] + ...\n    \"\"\"\n    return scipy.signal.lfilter([1],[1,-gamma],x[::-1], axis=0)[::-1]\n\n\ndef lrelu(x, leak=0.2):\n    \"\"\" Performs a leaky ReLU operation. \"\"\"\n    f1 = 0.5 * (1 + leak)\n    f2 = 0.5 * (1 - leak)\n    return f1 * x + f2 * abs(x)\n\n\ndef explained_variance_1d(ypred,y):\n    \"\"\"\n    Var[ypred - y] / var[y]. \n    https://www.quora.com/What-is-the-meaning-proportion-of-variance-explained-in-linear-regression\n    \"\"\"\n    assert y.ndim == 1 and ypred.ndim == 1    \n    vary = np.var(y)\n    return np.nan if vary==0 else 1 - np.var(y-ypred)/vary\n\n\ndef categorical_sample_logits(logits):\n    \"\"\"\n    Samples (symbolically) from categorical distribution, where logits is a NxK\n    matrix specifying N categorical distributions with K categories\n\n    specifically, exp(logits) / sum( exp(logits), axis=1 ) is the \n    probabilities of the different classes\n\n    Cleverly uses gumbell trick, based on\n    https://github.com/tensorflow/tensorflow/issues/456\n    \"\"\"\n    U = tf.random_uniform(tf.shape(logits))\n    return tf.argmax(logits - tf.log(-tf.log(U)), dimension=1)\n\n\ndef pathlength(path):\n    return len(path[\"reward\"])\n"
  },
  {
    "path": "utils/value_functions.py",
    "content": "\"\"\"\nValue functions, for now we apply them to policy gradients. This uses Python3\nimporting syntax.\n\"\"\"\n\nimport numpy as np\nimport sys\nimport tensorflow as tf\nimport tensorflow.contrib.layers as layers\nfrom . import utils_pg as utils\n\n\nclass LinearValueFunction(object):\n    \"\"\" Estimates the baseline function for PGs via ridge regression. \"\"\"\n\n    def __init__(self):\n        self.coef = None\n\n    def fit(self, X, y):\n        \"\"\" \n        Updates weights (self.coef) with design matrix X (i.e. observations) and\n        targets (i.e. actual returns) y. \n        \"\"\"\n        assert X.shape[0] == y.shape[0]\n        assert len(y.shape) == 1\n        Xp = self.preproc(X)\n        A = Xp.T.dot(Xp)\n        nfeats = Xp.shape[1]\n        A[np.arange(nfeats), np.arange(nfeats)] += 1e-3 # a little ridge regression\n        b = Xp.T.dot(y)\n        self.coef = np.linalg.solve(A, b)\n\n    def predict(self, X):\n        \"\"\" Predicts return from observations (i.e. environment states) X. \"\"\"\n        if self.coef is None:\n            return np.zeros(X.shape[0])\n        else:\n            return self.preproc(X).dot(self.coef)\n\n    def preproc(self, X):\n        \"\"\" Adding a bias column, and also adding squared values (huh). \"\"\"\n        return np.concatenate([np.ones([X.shape[0], 1]), X, np.square(X)/2.0], axis=1)\n\n\nclass NnValueFunction(object):\n    \"\"\" Estimates the baseline function for PGs via neural network. \"\"\"\n\n    def __init__(self, session, ob_dim=None, n_epochs=20, stepsize=1e-3):\n        \"\"\" The network gets constructed upon initialization so future calls to\n        self.fit will remember this. \n        \n        Right now we assume a preprocessing which results ob_dim*2+1 dimensions,\n        and we assume a fixed neural network architecture (input-50-50-1, fully\n        connected with tanh nonlineariites), which we should probably change.\n\n        The number of outputs is one, so that ypreds_n is the predicted vector\n        of state values, to be compared against ytargs_n. Since ytargs_n is of\n        shape (n,), we need to apply a \"squeeze\" on the final predictions, which\n        would otherwise be of shape (n,1). Bleh.\n        \"\"\"\n        # Value function V(s_t) (or b(s_t)), parameterized as a neural network.\n        self.ob_no = tf.placeholder(shape=[None, ob_dim*2+1], name=\"nnvf_ob\", dtype=tf.float32)\n        self.h1 = layers.fully_connected(self.ob_no, \n                num_outputs=50,\n                weights_initializer=layers.xavier_initializer(uniform=True),\n                activation_fn=tf.nn.tanh)\n        self.h2 = layers.fully_connected(self.h1,\n                num_outputs=50,\n                weights_initializer=layers.xavier_initializer(uniform=True),\n                activation_fn=tf.nn.tanh)\n        self.ypreds_n = layers.fully_connected(self.h2,\n                num_outputs=1,\n                weights_initializer=layers.xavier_initializer(uniform=True),\n                activation_fn=None)\n        self.ypreds_n = tf.reshape(self.ypreds_n, [-1]) # (?,1) --> (?,). =)\n\n        # Form the loss function, which is the simple (mean) L2 error.\n        self.n_epochs = n_epochs\n        self.lrate    = stepsize\n        self.ytargs_n = tf.placeholder(shape=[None], name=\"nnvf_y\", dtype=tf.float32)\n        self.l2_error = tf.reduce_mean(tf.square(self.ypreds_n - self.ytargs_n))\n        self.fit_op   = tf.train.AdamOptimizer(self.lrate).minimize(self.l2_error)\n        self.sess     = session\n\n\n    def fit(self, X, y, session=None):\n        \"\"\" \n        Updates weights (self.coef) with design matrix X (i.e. observations) and\n        targets (i.e. actual returns) y. For now, assume that by refitting,\n        we'll be doing it several times (`n_epoch` times).\n        \"\"\"\n        assert X.shape[0] == y.shape[0]\n        assert len(y.shape) == 1\n        Xp = self.preproc(X)\n        for i in range(self.n_epochs):\n            _,err = self.sess.run(\n                    [self.fit_op, self.l2_error], \n                    feed_dict={self.ob_no: Xp,\n                               self.ytargs_n: y\n                    })\n\n\n    def predict(self, X):\n        \"\"\" \n        Predicts returns from observations (i.e. environment states) X. I also\n        think we need a session here. No need to expand dimensions, BTW! It's\n        effectively already done for us elsewhere.\n        \"\"\"\n        Xp = self.preproc(X)\n        return self.sess.run(self.ypreds_n, feed_dict={self.ob_no:Xp})\n\n\n    def preproc(self, X):\n        \"\"\" Let's add this here to increase dimensionality. \"\"\"\n        return np.concatenate([np.ones([X.shape[0], 1]), X, np.square(X)/2.0], axis=1)\n"
  },
  {
    "path": "vpg/README.md",
    "content": "# Vanilla Policy Gradients\n\nThis is the standard vanilla policy gradients with stochastic policies, either\ncontinuous or discrete. I based this off of CS 294-112 starter code.\n\nI'm using Python 3.5.2 and Tensorflow 1.2.0. This code will not work with Python\n2.7.x.  Note to self: when running bash scripts in GNU screen mode, be sure to\nsource my Python 3 conda environment.\n\n# Simple Baselines\n\n## CartPole-v0\n\nBased on `bash_scripts/CartPole-v0.sh`:\n\n![](figures/CartPole-v0.png?raw=true)\n\n![](figures/CartPole-v0_sm.png?raw=true)\n\nArchitectures:\n\n- **Policy**: (input) - 50 - (output), tanh\n- **NN vf**: (input) - 50 - 50 - (output), tanh\n\n## Pendulum-v0\n\nBased on `bash_scripts/Pendulum-v0.sh`:\n\n![Pendulum-v0](figures/Pendulum-v0.png?raw=true)\n\n![Pendulum-v0_sm](figures/Pendulum-v0_sm.png?raw=true)\n\nArchitectures:\n\n- **Policy**: (input) - 32 - 32 - (output), relu\n- **NN vf**: (input) - 50 - 50 - (output), tanh\n\nI think it looks OK. Pendulum is a bit tricky to solve because it requires an\nadaptive learning rate but I still get close to about -100 or so. I'm not sure\nwhat the theoretical best solution is; maybe zero, but that seems impossible.\nThe neural network is only slightly better with these results (I guess?) because\nthe problem is so simple. The action dimension is just one.\n\n\n\n**TODO** haven't tested with these with new API ...\n# MuJoCo Baselines\n\nTested on in alphabetical order:\n\n- HalfCheetah-v1\n- Hopper-v1\n- Walker2d-v1\n\n## HalfCheetah-v1\n\nThe raw runs based on `bash_scripts/halfcheetah.sh`:\n\n![HalfCheetah-v1](figures/HalfCheetah-v1.png?raw=true)\n\nAnd the smooth runs:\n\n![HalfCheetah-v1_sm](figures/HalfCheetah-v1_sm.png?raw=true)\n\nThe GAIL paper said HalfCheetah-v1 should get around 4463.46 ± 105.83 and in\nfact we are almost getting to that level. That's interesting.\n\nWhat's confusing is that the explained variance for the linear case seems to be\nterrible. Then why is the linear VF even working, and why is it just barely\nworse than the NN value function? Hmmm ... I may want to catch a video of this\nin action.\n\n## Hopper-v1\n\nI used the script in `bash_scripts/hopper.sh`. Here are the raw results:\n\n![Hopper-v1](figures/Hopper-v1.png?raw=true)\n\nAnd now the smoothed versions:\n\n![Hopper-v1_sm](figures/Hopper-v1_sm.png?raw=true)\n\n(Ho & Ermon 2016) showed in the GAIL paper that Hopper-v1 should get 3571.38\nwith a standard deviation of 184.20 so ... yeah, these results are a bit\nsub-par! But at least they are learning *something*. Maybe my version of TRPO\nwill do better.\n\n## Walker2d-v1\n\nNext, Walker2d-v1. The raw runs based on `bash_scripts/walker.sh`:\n\n![Walker2d-v1](figures/Walker2d-v1.png?raw=true)\n\nAnd the smooth runs:\n\n![Walker2d-v1_sm](figures/Walker2d-v1_sm.png?raw=true)\n\nThe GAIL paper said Walker-v1 should get around 6717.08 p/m 845.62, but that\nmight not be the same as Walker2d-v1. I'm not sure ... and the code Jonathan Ho\nhas for imitation learning doesn't do as well.\n"
  },
  {
    "path": "vpg/bash_scripts/CartPole-v0.sh",
    "content": "python main.py CartPole-v0 --vf_type linear --seed 0 --initial_stepsize 0.01 --n_iter 100\npython main.py CartPole-v0 --vf_type nn     --seed 0 --initial_stepsize 0.01 --n_iter 100  \npython main.py CartPole-v0 --vf_type linear --seed 1 --initial_stepsize 0.01 --n_iter 100\npython main.py CartPole-v0 --vf_type nn     --seed 1 --initial_stepsize 0.01 --n_iter 100\npython main.py CartPole-v0 --vf_type linear --seed 2 --initial_stepsize 0.01 --n_iter 100\npython main.py CartPole-v0 --vf_type nn     --seed 2 --initial_stepsize 0.01 --n_iter 100\n"
  },
  {
    "path": "vpg/bash_scripts/Pendulum-v0.sh",
    "content": "python main.py Pendulum-v0 --vf_type linear --seed 0 --desired_kl 2e-3 --use_kl_heuristic --n_iter 400 \npython main.py Pendulum-v0 --vf_type nn     --seed 0 --desired_kl 2e-3 --use_kl_heuristic --n_iter 400 \npython main.py Pendulum-v0 --vf_type linear --seed 1 --desired_kl 2e-3 --use_kl_heuristic --n_iter 400 \npython main.py Pendulum-v0 --vf_type nn     --seed 1 --desired_kl 2e-3 --use_kl_heuristic --n_iter 400 \npython main.py Pendulum-v0 --vf_type linear --seed 2 --desired_kl 2e-3 --use_kl_heuristic --n_iter 400 \npython main.py Pendulum-v0 --vf_type nn     --seed 2 --desired_kl 2e-3 --use_kl_heuristic --n_iter 400 \n"
  },
  {
    "path": "vpg/bash_scripts/halfcheetah.sh",
    "content": "#!/bin/bash\npython main.py HalfCheetah-v1 --vf_type linear --seed 4 --n_iter 3000\npython main.py HalfCheetah-v1 --vf_type nn     --seed 4 --n_iter 3000  \npython main.py HalfCheetah-v1 --vf_type linear --seed 6 --n_iter 3000\npython main.py HalfCheetah-v1 --vf_type nn     --seed 6 --n_iter 3000\npython main.py HalfCheetah-v1 --vf_type linear --seed 8 --n_iter 3000\npython main.py HalfCheetah-v1 --vf_type nn     --seed 8 --n_iter 3000\n"
  },
  {
    "path": "vpg/bash_scripts/hopper.sh",
    "content": "#!/bin/bash\npython main.py Hopper-v1 --vf_type linear --seed 4 --n_iter 3000\npython main.py Hopper-v1 --vf_type nn     --seed 4 --n_iter 3000  \npython main.py Hopper-v1 --vf_type linear --seed 6 --n_iter 3000\npython main.py Hopper-v1 --vf_type nn     --seed 6 --n_iter 3000\npython main.py Hopper-v1 --vf_type linear --seed 8 --n_iter 3000\npython main.py Hopper-v1 --vf_type nn     --seed 8 --n_iter 3000\n"
  },
  {
    "path": "vpg/bash_scripts/walker.sh",
    "content": "#!/bin/bash\npython main.py Walker2d-v1 --vf_type linear --seed 4 --n_iter 3000\npython main.py Walker2d-v1 --vf_type nn     --seed 4 --n_iter 3000  \npython main.py Walker2d-v1 --vf_type linear --seed 6 --n_iter 3000\npython main.py Walker2d-v1 --vf_type nn     --seed 6 --n_iter 3000  \npython main.py Walker2d-v1 --vf_type linear --seed 8 --n_iter 3000\npython main.py Walker2d-v1 --vf_type nn     --seed 8 --n_iter 3000  \n"
  },
  {
    "path": "vpg/main.py",
    "content": "\"\"\"\nVanilla Policy Gradients, aka REINFORCE, aka Monte Carlo Policy Gradients.\n\nTo quickly test you can do:\n\n    python main.py Pendulum-v0 --vf_type nn --use_kl_heuristic --do_not_save\n\nAs long as --do_not_save is there, it won't overwrite files.  If I want to\nbenchmark and save results, see the bash scripts. Add --render if desired.\n\n(c) April 2017 by Daniel Seita, built upon starter code from CS 294-112.\n\"\"\"\n\nimport argparse\nimport gym\nimport numpy as np\nnp.set_printoptions(suppress=True, precision=5, edgeitems=10)\nimport pickle\nimport sys\nimport tensorflow as tf\nif \"../\" not in sys.path:\n    sys.path.append(\"../\")\nfrom utils import utils_pg as utils\nfrom utils import value_functions as vfuncs\nfrom utils import logz\nfrom utils import policies\n\n\ndef run_vpg(args, vf_params, logdir, env, sess, continuous_control):\n    \"\"\" General purpose method to run vanilla policy gradients, for both\n    continuous and discrete action environments. \n    \n    Parameters\n    ----------\n    args: [Namespace]\n        Contains user-provided (or default) arguments for VPGs.\n    vf_params: [dict]\n        Dictionary of parameters for the value function.\n    logdir: [string]\n        Where we store the outputs, can be None to avoid saving.\n    env: [OpenAI gym env]\n        The environment the agent is in, from OpenAI gym.\n    sess: [tf Session]\n        Current Tensorflow session, to be passed to (at least) the policy\n        function, and the value function as well if it's a neural network.\n    continuous_control: [boolean]\n        True if continuous control (i.e. actions), false if otherwise.\n    \"\"\"\n    ob_dim = env.observation_space.shape[0]\n\n    if args.vf_type == 'linear':\n        vf = vfuncs.LinearValueFunction(**vf_params)\n    elif args.vf_type == 'nn':\n        vf = vfuncs.NnValueFunction(session=sess, ob_dim=ob_dim, **vf_params)\n\n    if continuous_control:\n        ac_dim = env.action_space.shape[0]\n        policyfn = policies.GaussianPolicy(sess, ob_dim, ac_dim)\n    else:\n        ac_dim = env.action_space.n\n        policyfn = policies.GibbsPolicy(sess, ob_dim, ac_dim)\n\n    sess.__enter__() # equivalent to `with sess:`\n    tf.global_variables_initializer().run() #pylint: disable=E1101\n    total_timesteps = 0\n    stepsize = args.initial_stepsize\n\n    for i in range(args.n_iter):\n        print(\"\\n********** Iteration %i ************\"%i)\n\n        # Collect paths until we have enough timesteps.\n        timesteps_this_batch = 0\n        paths = []\n        while True:\n            ob = env.reset()\n            terminated = False\n            obs, acs, rewards = [], [], []\n            animate_this_episode = (len(paths) == 0 and (i%100 == 0) and args.render)\n            while True:\n                if animate_this_episode:\n                    env.render()\n                obs.append(ob)\n                ac = policyfn.sample_action(ob)\n                acs.append(ac)\n                ob, rew, done, _ = env.step(ac)\n                rewards.append(rew)\n                if done:\n                    break                    \n            path = {\"observation\" : np.array(obs), \"terminated\" : terminated,\n                    \"reward\" : np.array(rewards), \"action\" : np.array(acs)}\n            paths.append(path)\n            timesteps_this_batch += utils.pathlength(path)\n            if timesteps_this_batch > args.min_timesteps_per_batch:\n                break\n        total_timesteps += timesteps_this_batch\n\n        # Estimate advantage function using baseline vf (these are lists!).\n        # return_t: list of sum of discounted rewards (to end of episode), one per time\n        # vpred_t: list of value function's predictions of components of return_t\n        vtargs, vpreds, advs = [], [], []\n        for path in paths:\n            rew_t = path[\"reward\"]\n            return_t = utils.discount(rew_t, args.gamma)\n            vpred_t = vf.predict(path[\"observation\"])\n            adv_t = return_t - vpred_t\n            advs.append(adv_t)\n            vtargs.append(return_t)\n            vpreds.append(vpred_t)\n\n        # Build arrays for policy update and **re-fit the baseline**.\n        ob_no = np.concatenate([path[\"observation\"] for path in paths])\n        ac_n  = np.concatenate([path[\"action\"] for path in paths])\n        adv_n = np.concatenate(advs)\n        std_adv_n = (adv_n - adv_n.mean()) / (adv_n.std() + 1e-8)\n        vtarg_n = np.concatenate(vtargs)\n        vpred_n = np.concatenate(vpreds)\n        vf.fit(ob_no, vtarg_n)\n\n        # Policy update, plus diagnostics stuff. Is there a better way to handle\n        # the continuous vs discrete control cases?\n        if continuous_control:\n            surr_loss, oldmean_na, oldlogstd_a = policyfn.update_policy(\n                    ob_no, ac_n, std_adv_n, stepsize)\n            kl, ent = policyfn.kldiv_and_entropy(ob_no, oldmean_na, oldlogstd_a)\n        else:\n            surr_loss, oldlogits_na = policyfn.update_policy(\n                    ob_no, ac_n, std_adv_n, stepsize)\n            kl, ent = policyfn.kldiv_and_entropy(ob_no, oldlogits_na)\n\n        # A step size heuristic to ensure that we don't take too large steps.\n        if args.use_kl_heuristic:\n            if kl > args.desired_kl * 2: \n                stepsize /= 1.5\n                print('PG stepsize -> %s' % stepsize)\n            elif kl < args.desired_kl / 2: \n                stepsize *= 1.5\n                print('PG stepsize -> %s' % stepsize)\n            else:\n                print('PG stepsize OK')\n\n        # Log diagnostics\n        if i % args.log_every_t_iter == 0:\n            logz.log_tabular(\"EpRewMean\", np.mean([path[\"reward\"].sum() for path in paths]))\n            logz.log_tabular(\"EpLenMean\", np.mean([utils.pathlength(path) for path in paths]))\n            logz.log_tabular(\"KLOldNew\", kl)\n            logz.log_tabular(\"Entropy\", ent)\n            logz.log_tabular(\"EVBefore\", utils.explained_variance_1d(vpred_n, vtarg_n))\n            logz.log_tabular(\"EVAfter\", utils.explained_variance_1d(vf.predict(ob_no), vtarg_n))\n            logz.log_tabular(\"SurrogateLoss\", surr_loss)\n            logz.log_tabular(\"TimestepsSoFar\", total_timesteps)\n            # If you're overfitting, EVAfter will be way larger than EVBefore.\n            # Note that we fit the value function AFTER using it to compute the\n            # advantage function to avoid introducing bias\n            logz.dump_tabular()\n\n\nif __name__ == \"__main__\":\n    p = argparse.ArgumentParser()\n    p.add_argument('envname', type=str)\n    p.add_argument('--render', action='store_true')\n    p.add_argument('--do_not_save', action='store_true')\n    p.add_argument('--use_kl_heuristic', action='store_true')\n\n    p.add_argument('--n_iter', type=int, default=500)\n    p.add_argument('--seed', type=int, default=0)\n    p.add_argument('--gamma', type=float, default=0.97)\n    p.add_argument('--desired_kl', type=float, default=2e-3)\n    p.add_argument('--min_timesteps_per_batch', type=int, default=2500) \n    p.add_argument('--initial_stepsize', type=float, default=1e-3)\n    p.add_argument('--log_every_t_iter', type=int, default=1)\n\n    p.add_argument('--vf_type', type=str, default='linear')\n    p.add_argument('--nnvf_epochs', type=int, default=20)\n    p.add_argument('--nnvf_ssize', type=float, default=1e-3)\n    args = p.parse_args()\n\n    # Handle value function type and the log directory (and save the args!).\n    assert args.vf_type == 'linear' or args.vf_type == 'nn'\n    vf_params = {}\n    outstr = 'linearvf-kl' +str(args.desired_kl) \n    if args.vf_type == 'nn':\n        vf_params = dict(n_epochs=args.nnvf_epochs, stepsize=args.nnvf_ssize)\n        outstr = 'nnvf-kl' +str(args.desired_kl)\n    outstr += '-seed' +str(args.seed).zfill(2)\n    logdir = 'outputs/' +args.envname+ '/' +outstr\n    if args.do_not_save:\n        logdir = None\n    logz.configure_output_dir(logdir)\n    if logdir is not None:\n        with open(logdir+'/args.pkl', 'wb') as f:\n            pickle.dump(args, f)\n    print(\"Saving in logdir: {}\".format(logdir))\n\n    # Other stuff for seeding and getting things set up.\n    tf.set_random_seed(args.seed)\n    np.random.seed(args.seed)\n    env = gym.make(args.envname)\n    continuous = True\n    if 'discrete' in str(type(env.action_space)).lower():\n        # A bit of a hack, is there a better way to do this?  Another option\n        # could be following Jonathan Ho's code and detecting spaces.Box?\n        continuous = False\n    print(\"Continuous control? {}\".format(continuous))\n    tf_config = tf.ConfigProto(inter_op_parallelism_threads=1, \n                               intra_op_parallelism_threads=1) \n    sess = tf.Session(config=tf_config)\n\n    run_vpg(args, vf_params, logdir, env, sess, continuous)\n"
  },
  {
    "path": "vpg/plot_learning_curves.py",
    "content": "\"\"\" \nTo plot, you need to provide the experiment directory. \n\npython plot_learning_curves.py outputs/Pendulum-v0 --out figures/Pendulum-v0.png\npython plot_learning_curves.py outputs/Pendulum-v0 --out figures/Pendulum-v0_sm.png --smooth\n\n(Don't forget to add `sm` to the figure name!)\n\nDo this for each environment tested, e.g. with Hopper-v1 as well. Also, be\ncareful to check the number of iterations!\n\"\"\"\n\nimport argparse\nimport os\nfrom os.path import join\nimport sys\nimport matplotlib\nmatplotlib.use('Agg')\nfrom pylab import *\nimport matplotlib.pyplot as plt\nplt.style.use('seaborn-darkgrid')\n\n# Argument parser.\nparser = argparse.ArgumentParser()\nparser.add_argument(\"expdir\", help=\"experiment dir, e.g., /tmp/experiments\")\nparser.add_argument(\"--out\", type=str, help=\"full directory where to save\")\nparser.add_argument(\"--niter\", type=int, default=100, help=\"the number of iterations used\")\nparser.add_argument('--smooth', action='store_true')\nargs = parser.parse_args()\ndirnames = os.listdir(args.expdir)\nniter = args.niter\n\n# CAREFUL!\nif 'CartPole-v0' in args.expdir:\n    niter = 100\nif 'Pendulum-v0' in args.expdir:\n    niter = 400\nif ('Hopper-v1' in args.expdir) or ('Walker2d-v1' in args.expdir) or \\\n    ('HalfCheetah-v1' in args.expdir):\n    niter = 3000\nprint(\"dirnames:\\n{}\".format(dirnames))\nprint(\"niter: {}\".format(niter))\n\n# Matplotlib settings\nlw = 2\nfont = 18\nfig, axes = subplots(4, figsize=(14,18))\n\n# Try to handle the smoothed case separately. It's a bit ugly. I'm assuming I\n# did three different seeds, BTW.\nif args.smooth:\n    n = 3\n    colors = ['gold', 'midnightblue']\n\n    avgx_lin = np.zeros(niter,)\n    avgx_nn = np.zeros(niter,)\n    avg_rew_lin = np.zeros(niter,)\n    avg_rew_nn = np.zeros(niter,)\n    avg_kl_lin = np.zeros(niter,)\n    avg_kl_nn = np.zeros(niter,)\n    avg_ent_lin = np.zeros(niter,)\n    avg_ent_nn = np.zeros(niter,)\n    avg_ev_lin = np.zeros(niter,)\n    avg_ev_nn = np.zeros(niter,)\n\n    for dirname in dirnames:\n        A = np.genfromtxt(join(args.expdir, dirname, 'log.txt'),delimiter='\\t',dtype=None, names=True)\n        if 'linearvf' in dirname:\n            avgx_lin += A['TimestepsSoFar']\n            avg_rew_lin += A['EpRewMean']\n            avg_kl_lin += A['KLOldNew']\n            avg_ent_lin += A['Entropy']\n            avg_ev_lin += A['EVBefore']\n        elif 'nnvf' in dirname:\n            avgx_nn += A['TimestepsSoFar']\n            avg_rew_nn += A['EpRewMean']\n            avg_kl_nn += A['KLOldNew']\n            avg_ent_nn += A['Entropy']\n            avg_ev_nn += A['EVBefore']\n\n    avgx_lin /= n\n    avgx_nn /= n\n    avg_rew_lin /= n\n    avg_rew_nn /= n\n    avg_kl_lin /= n\n    avg_kl_nn /= n\n    avg_ent_lin /= n\n    avg_ent_nn /= n\n    avg_ev_lin /= n\n    avg_ev_nn /= n\n\n    axes[0].plot(avgx_lin, avg_rew_lin, '-', color=colors[0], lw=lw)\n    axes[0].plot(avgx_nn,  avg_rew_nn,  '-', color=colors[1], lw=lw)\n    axes[1].plot(avgx_lin, avg_kl_lin,  '-', color=colors[0], lw=lw)\n    axes[1].plot(avgx_nn,  avg_kl_nn,   '-', color=colors[1], lw=lw)\n    axes[2].plot(avgx_lin, avg_ent_lin, '-', color=colors[0], lw=lw)\n    axes[2].plot(avgx_nn,  avg_ent_nn,  '-', color=colors[1], lw=lw)\n    axes[3].plot(avgx_lin, avg_ev_lin,  '-', color=colors[0], lw=lw, label='Linear VF')\n    axes[3].plot(avgx_nn,  avg_ev_nn,   '-', color=colors[1], lw=lw, label='NN VF')\n    axes[3].legend(loc='best',ncol=2)\n\nelse:\n    colors = ['blue', 'red', 'yellow', 'black', 'gray', 'cyan']\n    for dirname, c in zip(dirnames, colors):\n        A = np.genfromtxt(join(args.expdir, dirname, 'log.txt'),delimiter='\\t',dtype=None, names=True)\n        x = A['TimestepsSoFar']\n        axes[0].plot(x, A['EpRewMean'], '-', color=c, lw=lw)\n        axes[1].plot(x, A['KLOldNew'], '-', color=c, lw=lw)\n        axes[2].plot(x, A['Entropy'], '-', color=c, lw=lw)\n        axes[3].plot(x, A['EVBefore'], '-', color=c, lw=lw)\n        legend(dirnames,loc='best',ncol=2).draggable()\n\naxes[0].set_ylabel(\"EpRewMean\", fontsize=font)\naxes[1].set_ylabel(\"KLOldNew\", fontsize=font)\naxes[2].set_ylabel(\"Entropy\", fontsize=font)\naxes[3].set_ylabel(\"EVBefore\", fontsize=font)\naxes[3].set_ylim(-1,1)\naxes[-1].set_xlabel(\"Iterations\", fontsize=font)\nplt.tight_layout()\nfig.savefig(args.out)\n"
  }
]