Repository: Observerspy/CS294
Branch: master
Commit: 849aa311e276
Files: 224
Total size: 77.1 MB
Directory structure:
gitextract_ql1s9b61/
├── README.md
├── hw1/
│ ├── .idea/
│ │ ├── hw1.iml
│ │ ├── misc.xml
│ │ ├── modules.xml
│ │ └── workspace.xml
│ ├── BehavioralCloning.py
│ ├── DAgger.py
│ ├── README.md
│ ├── data/
│ │ ├── Ant-v1.train.npz
│ │ ├── HalfCheetah-v1.train.npz
│ │ ├── Hopper-v1.train.npz
│ │ ├── Humanoid-v1.train.npz
│ │ ├── Reacher-v1.train.npz
│ │ └── Walker2d-v1.train.npz
│ ├── demo.bash
│ ├── experts/
│ │ ├── Ant-v1.pkl
│ │ ├── HalfCheetah-v1.pkl
│ │ ├── Hopper-v1.pkl
│ │ ├── Humanoid-v1.pkl
│ │ ├── Reacher-v1.pkl
│ │ └── Walker2d-v1.pkl
│ ├── load_policy.py
│ ├── log/
│ │ ├── Ant-v1_BC_30-01-2018_10-32-45/
│ │ │ └── log.txt
│ │ ├── Ant-v1_DA_30-01-2018_10-51-03/
│ │ │ └── log.txt
│ │ ├── HalfCheetah-v1_BC_30-01-2018_10-51-19/
│ │ │ └── log.txt
│ │ ├── HalfCheetah-v1_DA_30-01-2018_11-11-33/
│ │ │ └── log.txt
│ │ ├── Hopper-v1_BC_30-01-2018_10-55-39/
│ │ │ └── log.txt
│ │ ├── Hopper-v1_BCbig_30-01-2018_11-02-29/
│ │ │ └── log.txt
│ │ ├── Hopper-v1_DA_30-01-2018_11-24-58/
│ │ │ └── log.txt
│ │ ├── Humanoid-v1_BC_30-01-2018_10-28-53/
│ │ │ └── log.txt
│ │ ├── Humanoid-v1_DA_30-01-2018_10-31-26/
│ │ │ └── log.txt
│ │ ├── Reacher-v1_BC_30-01-2018_10-57-25/
│ │ │ └── log.txt
│ │ ├── Reacher-v1_DA_30-01-2018_11-27-44/
│ │ │ └── log.txt
│ │ ├── Walker2d-v1_BC_30-01-2018_10-58-02/
│ │ │ └── log.txt
│ │ └── Walker2d-v1_DA_30-01-2018_11-28-50/
│ │ └── log.txt
│ ├── logz.py
│ ├── plot.py
│ ├── run_expert.py
│ └── tf_util.py
├── hw2/
│ ├── .idea/
│ │ ├── hw2.iml
│ │ ├── misc.xml
│ │ ├── modules.xml
│ │ └── workspace.xml
│ ├── data/
│ │ ├── HalfCheetah_b50000_rtg_na_25bl_HalfCheetah-v1_31-01-2018_19-35-00/
│ │ │ ├── 1/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 11/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 21/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 31/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ └── 41/
│ │ │ ├── log.txt
│ │ │ ├── params.json
│ │ │ └── vars.pkl
│ │ ├── InvertedPendulum_sb_rtg_na_0.02_InvertedPendulum-v1_02-02-2018_10-42-58/
│ │ │ ├── 1/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 11/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 21/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 31/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ └── 41/
│ │ │ ├── log.txt
│ │ │ ├── params.json
│ │ │ └── vars.pkl
│ │ ├── InvertedPendulum_sb_rtg_na_bl_0.02_InvertedPendulum-v1_02-02-2018_10-42-44/
│ │ │ ├── 1/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 11/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 21/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 31/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ └── 41/
│ │ │ ├── log.txt
│ │ │ ├── params.json
│ │ │ └── vars.pkl
│ │ ├── lb_no_rtg_dna_CartPole-v0_24-01-2018_09-28-29/
│ │ │ ├── 1/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 11/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 21/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 31/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ └── 41/
│ │ │ ├── log.txt
│ │ │ ├── params.json
│ │ │ └── vars.pkl
│ │ ├── lb_rtg_dna_CartPole-v0_24-01-2018_09-20-37/
│ │ │ ├── 1/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 11/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 21/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 31/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ └── 41/
│ │ │ ├── log.txt
│ │ │ ├── params.json
│ │ │ └── vars.pkl
│ │ ├── lb_rtg_na_CartPole-v0_24-01-2018_09-11-55/
│ │ │ ├── 1/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 11/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 21/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 31/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ └── 41/
│ │ │ ├── log.txt
│ │ │ ├── params.json
│ │ │ └── vars.pkl
│ │ ├── sb_no_rtg_dna_CartPole-v0_24-01-2018_09-00-15/
│ │ │ ├── 1/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 11/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 21/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 31/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ └── 41/
│ │ │ ├── log.txt
│ │ │ ├── params.json
│ │ │ └── vars.pkl
│ │ ├── sb_rtg_dna_CartPole-v0_24-01-2018_09-04-19/
│ │ │ ├── 1/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 11/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 21/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 31/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ └── 41/
│ │ │ ├── log.txt
│ │ │ ├── params.json
│ │ │ └── vars.pkl
│ │ ├── sb_rtg_na_CartPole-v0_24-01-2018_09-08-49/
│ │ │ ├── 1/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 11/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 21/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ ├── 31/
│ │ │ │ ├── log.txt
│ │ │ │ ├── params.json
│ │ │ │ └── vars.pkl
│ │ │ └── 41/
│ │ │ ├── log.txt
│ │ │ ├── params.json
│ │ │ └── vars.pkl
│ │ └── sb_rtg_na_l2_CartPole-v0_25-01-2018_09-22-07/
│ │ ├── 1/
│ │ │ ├── log.txt
│ │ │ ├── params.json
│ │ │ └── vars.pkl
│ │ ├── 11/
│ │ │ ├── log.txt
│ │ │ ├── params.json
│ │ │ └── vars.pkl
│ │ ├── 21/
│ │ │ ├── log.txt
│ │ │ ├── params.json
│ │ │ └── vars.pkl
│ │ ├── 31/
│ │ │ ├── log.txt
│ │ │ ├── params.json
│ │ │ └── vars.pkl
│ │ └── 41/
│ │ ├── log.txt
│ │ ├── params.json
│ │ └── vars.pkl
│ ├── logz.py
│ ├── plot.py
│ └── train_pg.py
├── hw3/
│ ├── .idea/
│ │ ├── hw3.iml
│ │ ├── misc.xml
│ │ ├── modules.xml
│ │ └── workspace.xml
│ ├── README
│ ├── atari_wrappers.py
│ ├── dqn.py
│ ├── dqn_utils.py
│ ├── log/
│ │ ├── _RAM_30-01-2018_15-20-56/
│ │ │ └── log.txt
│ │ ├── _RAM_30-01-2018_22-29-12/
│ │ │ └── log.txt
│ │ └── _RAM_31-01-2018_08-28-28/
│ │ └── log.txt
│ ├── logz.py
│ ├── plot.py
│ ├── run_dqn_atari.py
│ └── run_dqn_ram.py
└── hw4/
├── .idea/
│ ├── hw4.iml
│ ├── misc.xml
│ ├── modules.xml
│ └── workspace.xml
├── cheetah_env.py
├── controllers.py
├── cost_functions.py
├── data/
│ ├── mb_mpc_HalfCheetah-v1_28-01-2018_16-06-09/
│ │ └── log.txt
│ └── mb_mpc_HalfCheetah-v1_30-01-2018_09-57-32/
│ └── log.txt
├── dynamics.py
├── logz.py
├── main.py
└── plot.py
================================================
FILE CONTENTS
================================================
================================================
FILE: README.md
================================================
# CS294
homework for CS294 Fall 2017
================================================
FILE: hw1/.idea/hw1.iml
================================================
================================================
FILE: hw1/.idea/misc.xml
================================================
================================================
FILE: hw1/.idea/modules.xml
================================================
================================================
FILE: hw1/.idea/workspace.xml
================================================
int64_list
value=
1516085912078
1516085912078
file://$PROJECT_DIR$/run_expert.py
33
================================================
FILE: hw1/BehavioralCloning.py
================================================
import tensorflow as tf
import os
import numpy as np
import tqdm
import gym
import logz
import time
import math
class Config(object):
n_features = 11
n_classes = 3
dropout = 0.5
hidden_size_1 = 128
hidden_size_2 = 256
hidden_size_3 = 64
batch_size = 256
lr = 0.0005
itera = 20
train_itera = 20
envname = 'Hopper-v1'
max_steps = 1000
class NN(object):
def add_placeholders(self):
self.input_placeholder = tf.placeholder(tf.float32, shape=(None, Config.n_features), name="input")
self.labels_placeholder = tf.placeholder(tf.float32, shape=(None, Config.n_classes), name="label")
self.dropout_placeholder = tf.placeholder(tf.float32, name="drop")
self.is_training = tf.placeholder(tf.bool)
def create_feed_dict(self, inputs_batch, labels_batch=None, dropout=1, is_training=False):
if labels_batch is None:
feed_dict = {self.input_placeholder: inputs_batch,
self.dropout_placeholder: dropout, self.is_training: is_training}
else:
feed_dict = {self.input_placeholder: inputs_batch, self.labels_placeholder: labels_batch,
self.dropout_placeholder: dropout, self.is_training: is_training}
return feed_dict
def add_prediction_op(self):
self.global_step = tf.Variable(0)
with tf.name_scope('layer1'):
hidden1 = tf.contrib.layers.fully_connected(self.input_placeholder, num_outputs=Config.hidden_size_1,
activation_fn=tf.nn.relu)
with tf.name_scope('layer2'):
hidden2 = tf.contrib.layers.fully_connected(hidden1, num_outputs=Config.hidden_size_2,
activation_fn=tf.nn.relu)
with tf.name_scope('layer3'):
hidden3 = tf.contrib.layers.fully_connected(hidden2, num_outputs=Config.hidden_size_3,
activation_fn=tf.nn.relu)
# hidden3 = tf.nn.dropout(hidden3, self.dropout_placeholder)
with tf.name_scope('output'):
pred = tf.contrib.layers.fully_connected(hidden3, num_outputs=Config.n_classes,
activation_fn=None)
return pred
def add_loss_op(self, pred):
loss = tf.losses.mean_squared_error(predictions=pred, labels=self.labels_placeholder)
tf.summary.scalar('loss', loss)
return loss
def add_training_op(self, loss):
extra_update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(extra_update_ops):
learning_rate = tf.train.exponential_decay(Config.lr, self.global_step, 1000, 0.8, staircase=True)
train_op = tf.train.AdamOptimizer(learning_rate).minimize(loss, global_step=self.global_step)
return train_op
def train_on_batch(self, sess, inputs_batch, labels_batch, merged, train_writer, i):
feed = self.create_feed_dict(inputs_batch, labels_batch, self.config.dropout, True)
rs, _, loss = sess.run([merged, self.train_op, self.loss], feed_dict=feed)
train_writer.add_summary(rs, i)
return loss
def __init__(self, config):
self.config = config
self.build()
def fit(self, sess, train_x, train_y):
loss = self.train_on_batch(sess, train_x, train_y)
def build(self):
with tf.name_scope('inputs'):
self.add_placeholders()
with tf.name_scope('predict'):
self.pred = self.add_prediction_op()
with tf.name_scope('loss'):
self.loss = self.add_loss_op(self.pred)
with tf.name_scope('train'):
self.train_op = self.add_training_op(self.loss)
def get_pred(self, sess, inputs_batch):
feed = self.create_feed_dict(inputs_batch, dropout=1, is_training=False)
p = sess.run(self.pred, feed_dict=feed)
return p
def load(path):
all = np.load(path)
X = all["arr_0"]
y = all["arr_1"]
y1 = y.reshape(y.shape[0], y.shape[2])
return X, y1
def main():
PROJECT_ROOT = os.path.dirname(os.path.realpath(__file__))
train_path = os.path.join(PROJECT_ROOT, "data/"+Config.envname+".train.npz")
train_log_path = os.path.join(PROJECT_ROOT, "log/train/")
logz.configure_output_dir(os.path.join(PROJECT_ROOT, "log/"+Config.envname+"_BC_"+time.strftime("%d-%m-%Y_%H-%M-%S")))
X_train, y_train = load(train_path)#debug
print("train size :", X_train.shape, y_train.shape)
print("start training")
with tf.Graph().as_default():
config = Config()
nn = NN(config)
init = tf.global_variables_initializer()
saver = tf.train.Saver(max_to_keep=10, keep_checkpoint_every_n_hours=0.5)
#必须在session外面
shuffle_batch_x, shuffle_batch_y = tf.train.shuffle_batch(
[X_train, y_train], batch_size=Config.batch_size, capacity=10000,
min_after_dequeue=5000, enqueue_many=True)
with tf.Session() as session:
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(train_log_path, session.graph)
session.run(init)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(session, coord)
for j in tqdm.tqdm(range(Config.itera)):
i = 0
try:
for i in range(int(math.ceil(Config.train_itera * X_train.shape[0] / Config.batch_size))):
batch_x, batch_y = session.run([shuffle_batch_x, shuffle_batch_y])
loss = nn.train_on_batch(session, batch_x, batch_y, merged, train_writer, i)
i += 1
if i % 1000 == 0:
print("step:", i, "loss:", loss)
saver.save(session, os.path.join(PROJECT_ROOT, "model/model_ckpt"), global_step=i)
except tf.errors.OutOfRangeError:
print("")
finally:
coord.request_stop()
coord.join(threads)
env = gym.make(Config.envname)
rollouts = 20
returns = []
for _ in range(rollouts):
obs = env.reset()
done = False
totalr = 0.
steps = 0
while not done:
action = nn.get_pred(session, obs[None, :])
obs, r, done, _ = env.step(action)
totalr += r
steps += 1
# if args.render:
# env.render()
if steps >= Config.max_steps:
break
returns.append(totalr)
# print('results for ', Config.envname)
# print('returns', returns)
# print('mean return', np.mean(returns))
# print('std of return', np.std(returns))
logz.log_tabular('Iteration', j)
logz.log_tabular('AverageReturn', np.mean(returns))
logz.log_tabular('StdReturn', np.std(returns))
logz.dump_tabular()
if __name__ == '__main__':
main()
================================================
FILE: hw1/DAgger.py
================================================
import tensorflow as tf
import os
import numpy as np
import tqdm
import gym
import load_policy
import math
import logz
import time
class Config(object):
n_features = 17
n_classes = 6
dropout = 0.5
hidden_size_1 = 128
hidden_size_2 = 256
hidden_size_3 = 64
batch_size = 256
lr = 0.0005
itera = 20
train_itera = 20
envname = 'Walker2d-v1'
max_steps = 1000
class NN(object):
def add_placeholders(self):
self.input_placeholder = tf.placeholder(tf.float32, shape=(None, Config.n_features), name="input")
self.labels_placeholder = tf.placeholder(tf.float32, shape=(None, Config.n_classes), name="label")
self.dropout_placeholder = tf.placeholder(tf.float32, name="drop")
self.is_training = tf.placeholder(tf.bool)
def create_feed_dict(self, inputs_batch, labels_batch=None, dropout=1, is_training=False):
if labels_batch is None:
feed_dict = {self.input_placeholder: inputs_batch,
self.dropout_placeholder: dropout, self.is_training: is_training}
else:
feed_dict = {self.input_placeholder: inputs_batch, self.labels_placeholder: labels_batch,
self.dropout_placeholder: dropout, self.is_training: is_training}
return feed_dict
def add_prediction_op(self):
self.global_step = tf.Variable(0)
with tf.name_scope('layer1'):
hidden1 = tf.contrib.layers.fully_connected(self.input_placeholder, num_outputs=Config.hidden_size_1,
activation_fn=tf.nn.relu)
with tf.name_scope('layer2'):
hidden2 = tf.contrib.layers.fully_connected(hidden1, num_outputs=Config.hidden_size_2,
activation_fn=tf.nn.relu)
with tf.name_scope('layer3'):
hidden3 = tf.contrib.layers.fully_connected(hidden2, num_outputs=Config.hidden_size_3,
activation_fn=tf.nn.relu)
with tf.name_scope('output'):
pred = tf.contrib.layers.fully_connected(hidden3, num_outputs=Config.n_classes,
activation_fn=None)
return pred
def add_loss_op(self, pred):
loss = tf.losses.mean_squared_error(predictions=pred, labels=self.labels_placeholder)
tf.summary.scalar('loss', loss)
return loss
def add_training_op(self, loss):
extra_update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(extra_update_ops):
learning_rate = tf.train.exponential_decay(Config.lr, self.global_step, 1000, 0.8, staircase=True)
train_op = tf.train.AdamOptimizer(learning_rate).minimize(loss, global_step=self.global_step)
return train_op
def train_on_batch(self, sess, inputs_batch, labels_batch, merged, train_writer, i):
feed = self.create_feed_dict(inputs_batch, labels_batch, self.config.dropout, True)
rs, _, loss = sess.run([merged, self.train_op, self.loss], feed_dict=feed)
train_writer.add_summary(rs, i)
return loss
def __init__(self, config):
self.config = config
self.build()
def fit(self, sess, train_x, train_y):
loss = self.train_on_batch(sess, train_x, train_y)
def build(self):
with tf.name_scope('inputs'):
self.add_placeholders()
with tf.name_scope('predict'):
self.pred = self.add_prediction_op()
with tf.name_scope('loss'):
self.loss = self.add_loss_op(self.pred)
with tf.name_scope('train'):
self.train_op = self.add_training_op(self.loss)
def get_pred(self, sess, inputs_batch):
feed = self.create_feed_dict(inputs_batch, dropout=1, is_training=False)
p = sess.run(self.pred, feed_dict=feed)
return p
def load(path):
all = np.load(path)
X = all["arr_0"]
y = all["arr_1"]
y1 = y.reshape(y.shape[0], y.shape[2])
return X, y1
def run_env(env, nn,session):
obs = env.reset()
done = False
totalr = 0.
steps = 0
observations = []
while not done:
action = nn.get_pred(session, obs[None, :])
observations.append(obs)
obs, r, done, _ = env.step(action)
totalr += r
steps += 1
# if args.render:
# env.render()
if steps >= Config.max_steps:
break
return totalr, observations
def shuffle(X_train, y_train):
training_data = np.concatenate((X_train, y_train), axis=1)
np.random.shuffle(training_data)
X = training_data[:, :-Config.n_classes]
y = training_data[:, -Config.n_classes:]
return X, y
def main():
PROJECT_ROOT = os.path.dirname(os.path.realpath(__file__))
train_path = os.path.join(PROJECT_ROOT, "data/"+Config.envname+".train.npz")
policy_path = os.path.join(PROJECT_ROOT, "experts/"+Config.envname+".pkl")
train_log_path = os.path.join(PROJECT_ROOT, "log/train/")
logz.configure_output_dir(os.path.join(PROJECT_ROOT, "log/"+Config.envname+"_DA_"+time.strftime("%d-%m-%Y_%H-%M-%S")))
X_train, y_train = load(train_path)#debug
print("train size :", X_train.shape, y_train.shape)
print("start training")
with tf.Graph().as_default():
config = Config()
nn = NN(config)
init = tf.global_variables_initializer()
saver = tf.train.Saver(max_to_keep=10, keep_checkpoint_every_n_hours=0.5)
print('loading and building expert policy')
policy_fn = load_policy.load_policy(policy_path)
print('loaded and built')
with tf.Session() as session:
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(train_log_path, session.graph)
session.run(init)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(session, coord)
#iter
for j in tqdm.tqdm(range(Config.itera)):
#train
X_train, y_train = shuffle(X_train, y_train)
i = 0
try:
for i in range(int(math.ceil(Config.train_itera * X_train.shape[0] / Config.batch_size))):
offset = (i * Config.batch_size) % X_train.shape[0]
# shuffle
batch_x = X_train[offset:(offset + Config.batch_size), :]
batch_y = y_train[offset:(offset + Config.batch_size)]
loss = nn.train_on_batch(session, batch_x, batch_y, merged, train_writer, i)
i += 1
print("step:", i, "loss:", loss)
# saver.save(session, os.path.join(PROJECT_ROOT, "model/model_ckpt"), global_step=i)
except tf.errors.OutOfRangeError:
print("done")
finally:
coord.request_stop()
coord.join(threads)
#get new data and label
observations = []
actions = []
env = gym.make(Config.envname)
for _ in range(10):
_, o = run_env(env, nn, session)
observations.extend(o)
action = policy_fn(o)
actions.extend(action)
new_x = np.array(observations)
new_y = np.array(actions)
X_train = np.concatenate((X_train, new_x))
y_train = np.concatenate((y_train, new_y))
print("train size :", X_train.shape, y_train.shape)
#test
# print("iter:", j, " train finished")
# print(Config.envname + " start")
rollouts = 20
returns = []
for _ in range(rollouts):
totalr, _ = run_env(env, nn, session)
returns.append(totalr)
# print('results for ', Config.envname)
# print('returns', returns)
# print('mean return', np.mean(returns), 'std of return', np.std(returns))
# print('mean return', np.mean(returns))
print()
logz.log_tabular('Iteration', j)
logz.log_tabular('AverageReturn', np.mean(returns))
logz.log_tabular('StdReturn', np.std(returns))
logz.dump_tabular()
if __name__ == '__main__':
main()
================================================
FILE: hw1/README.md
================================================
# CS294-112 HW 1: Imitation Learning
Dependencies: TensorFlow, MuJoCo version 1.31, OpenAI Gym
**Note**: MuJoCo versions until 1.5 do not support NVMe disks therefore won't be compatible with recent Mac machines.
There is a request for OpenAI to support it that can be followed [here](https://github.com/openai/gym/issues/638).
The only file that you need to look at is `run_expert.py`, which is code to load up an expert policy, run a specified number of roll-outs, and save out data.
In `experts/`, the provided expert policies are:
* Ant-v1.pkl
* HalfCheetah-v1.pkl
* Hopper-v1.pkl
* Humanoid-v1.pkl
* Reacher-v1.pkl
* Walker2d-v1.pkl
The name of the pickle file corresponds to the name of the gym environment.
================================================
FILE: hw1/data/Ant-v1.train.npz
================================================
[File too large to display: 17.5 MB]
================================================
FILE: hw1/data/Humanoid-v1.train.npz
================================================
[File too large to display: 58.7 MB]
================================================
FILE: hw1/demo.bash
================================================
#!/bin/bash
set -eux
for e in Hopper-v1 Ant-v1 HalfCheetah-v1 Humanoid-v1 Reacher-v1 Walker2d-v1
do
python run_expert.py experts/$e.pkl $e --render --num_rollouts=1
done
================================================
FILE: hw1/load_policy.py
================================================
import pickle, tensorflow as tf, tf_util, numpy as np
def load_policy(filename):
with open(filename, 'rb') as f:
data = pickle.loads(f.read())
# assert len(data.keys()) == 2
nonlin_type = data['nonlin_type']
policy_type = [k for k in data.keys() if k != 'nonlin_type'][0]
assert policy_type == 'GaussianPolicy', 'Policy type {} not supported'.format(policy_type)
policy_params = data[policy_type]
assert set(policy_params.keys()) == {'logstdevs_1_Da', 'hidden', 'obsnorm', 'out'}
# Keep track of input and output dims (i.e. observation and action dims) for the user
def build_policy(obs_bo):
def read_layer(l):
assert list(l.keys()) == ['AffineLayer']
assert sorted(l['AffineLayer'].keys()) == ['W', 'b']
return l['AffineLayer']['W'].astype(np.float32), l['AffineLayer']['b'].astype(np.float32)
def apply_nonlin(x):
if nonlin_type == 'lrelu':
return tf_util.lrelu(x, leak=.01) # openai/imitation nn.py:233
elif nonlin_type == 'tanh':
return tf.tanh(x)
else:
raise NotImplementedError(nonlin_type)
# Build the policy. First, observation normalization.
assert list(policy_params['obsnorm'].keys()) == ['Standardizer']
obsnorm_mean = policy_params['obsnorm']['Standardizer']['mean_1_D']
obsnorm_meansq = policy_params['obsnorm']['Standardizer']['meansq_1_D']
obsnorm_stdev = np.sqrt(np.maximum(0, obsnorm_meansq - np.square(obsnorm_mean)))
print('obs', obsnorm_mean.shape, obsnorm_stdev.shape)
normedobs_bo = (obs_bo - obsnorm_mean) / (obsnorm_stdev + 1e-6) # 1e-6 constant from Standardizer class in nn.py:409 in openai/imitation
curr_activations_bd = normedobs_bo
# Hidden layers next
assert list(policy_params['hidden'].keys()) == ['FeedforwardNet']
layer_params = policy_params['hidden']['FeedforwardNet']
for layer_name in sorted(layer_params.keys()):
l = layer_params[layer_name]
W, b = read_layer(l)
curr_activations_bd = apply_nonlin(tf.matmul(curr_activations_bd, W) + b)
# Output layer
W, b = read_layer(policy_params['out'])
output_bo = tf.matmul(curr_activations_bd, W) + b
return output_bo
obs_bo = tf.placeholder(tf.float32, [None, None])
a_ba = build_policy(obs_bo)
policy_fn = tf_util.function([obs_bo], a_ba)
return policy_fn
================================================
FILE: hw1/log/Ant-v1_BC_30-01-2018_10-32-45/log.txt
================================================
Iteration AverageReturn StdReturn
0 4460.34148867 504.993919545
1 4361.62089192 787.910341533
2 4238.35328327 1021.28077134
3 4551.3024466 220.243030137
4 4587.54091281 168.335418179
5 4536.1299135 153.39311344
6 4571.65449705 123.782802078
7 4468.68140776 489.42171743
8 4363.04400464 670.930898282
9 4477.84996454 448.159752304
10 4428.80299023 509.894288663
11 4219.75072886 982.726078559
12 4315.68265715 819.480876493
13 4549.6823578 116.079270449
14 4108.95615517 1174.93913987
15 4215.44535307 936.071898708
16 4431.84062818 476.960091374
17 4586.95139781 110.834919291
18 4431.21646369 610.424550643
19 4520.70269831 347.196475846
================================================
FILE: hw1/log/Ant-v1_DA_30-01-2018_10-51-03/log.txt
================================================
Iteration AverageReturn StdReturn
0 4543.92556297 163.700815617
1 4532.86754019 651.078836035
2 4718.40341227 334.079528476
3 4804.59842376 93.0563181661
4 4785.65700683 127.465976282
5 4831.53888416 93.6407853724
6 4767.63356673 112.208596337
7 4801.27090284 91.1866352943
8 4601.36647927 951.83089995
9 4787.38593852 275.842000254
10 4664.15443565 710.401178585
11 4804.25359337 113.174008233
12 4806.84341705 88.881374471
13 4772.95084954 103.853744593
14 4646.54370371 603.505425269
15 4604.3418062 770.681770359
16 4809.23885621 100.484625256
17 4703.23717096 418.746724941
18 4790.78266831 113.777606254
19 4783.07195431 108.151801332
================================================
FILE: hw1/log/HalfCheetah-v1_BC_30-01-2018_10-51-19/log.txt
================================================
Iteration AverageReturn StdReturn
0 3817.96495454 121.424448089
1 3936.04442016 149.995208225
2 3852.30571246 120.093945537
3 3906.3257817 137.039474081
4 3927.96557883 92.3172335412
5 3905.73231232 132.250735059
6 3894.78388609 104.606664587
7 3927.04549651 108.76612839
8 3891.86357872 120.74589099
9 3857.56540305 135.371682439
10 3876.91409242 118.576842405
11 3907.41133635 109.120138546
12 3877.17466 141.174229105
13 3875.88491827 149.663161746
14 3893.42180931 125.035365858
15 3927.75757089 114.108252154
16 3901.79379918 131.083160122
17 3884.49668982 145.973126754
18 3926.50703736 107.673754351
19 3902.56928807 121.983220478
================================================
FILE: hw1/log/HalfCheetah-v1_DA_30-01-2018_11-11-33/log.txt
================================================
Iteration AverageReturn StdReturn
0 3976.17700506 114.034047864
1 4080.46221353 84.1893455539
2 4133.95250959 81.0167961747
3 4101.48136021 94.9826005054
4 4135.3255688 80.7781973991
5 4140.00386975 97.4145974268
6 4127.59048502 98.0957605992
7 4136.09651306 87.8447357049
8 4168.61448977 58.1743328113
9 4175.37724354 76.5500116081
10 4152.01156376 100.515577257
11 4121.61130162 86.6234243495
12 4134.83157964 109.120217262
13 4128.08832282 70.0049383219
14 4142.06574835 99.4376440103
15 4145.22541853 68.6286481839
16 4164.73279931 89.1040051378
17 4096.95377812 90.370097307
18 4148.86261807 88.9318617818
19 4160.6740329 50.5316630273
================================================
FILE: hw1/log/Hopper-v1_BC_30-01-2018_10-55-39/log.txt
================================================
Iteration AverageReturn StdReturn
0 696.648776946 27.07925021
1 748.47888752 151.429815664
2 700.073941219 72.9177435482
3 731.887652211 113.92031914
4 715.92036383 112.632748448
5 702.746427086 72.807579689
6 737.028510731 118.896270982
7 753.175757248 123.58988432
8 728.528427466 88.1725040827
9 767.419942833 135.862982943
10 704.908491269 37.7345201986
11 820.057900984 162.74570912
12 722.067580433 95.4241626287
13 710.949850348 96.7033252778
14 721.164026913 74.5446602988
15 748.766636126 126.705015019
16 732.385777969 99.6523391183
17 732.09846089 121.161806134
18 754.424397187 137.548581585
19 718.219629462 97.6934148631
================================================
FILE: hw1/log/Hopper-v1_BCbig_30-01-2018_11-02-29/log.txt
================================================
Iteration AverageReturn StdReturn
0 1138.58195909 332.371517359
1 896.423291123 254.391048933
2 1151.49985307 695.596874896
3 933.454536471 275.828983102
4 1060.26470964 711.936395806
5 943.419330413 322.135059245
6 914.833224501 272.414134066
7 999.866949869 522.351021601
8 1061.79869625 347.475856152
9 1000.63941619 386.03117231
10 975.857956381 353.259897077
11 862.772266804 337.564889514
12 997.908818987 339.37936976
13 1161.14782133 389.451785869
14 994.682731442 313.7296743
15 1108.21639631 427.538386532
16 1014.65476481 321.52762664
17 1051.94580151 372.616078853
18 1072.21491361 383.494569749
19 1168.59860878 531.649394659
================================================
FILE: hw1/log/Hopper-v1_DA_30-01-2018_11-24-58/log.txt
================================================
Iteration AverageReturn StdReturn
0 1054.7477548 44.5027933049
1 2294.09469315 467.288023567
2 3707.44200499 260.030021057
3 3172.08454655 856.691867273
4 3778.9154217 4.68171457329
5 3775.94642069 2.83087791895
6 3776.23605724 3.29135654141
7 3776.0847846 4.88839549559
8 3775.58082393 3.35472305027
9 3776.7114718 3.99064616387
10 3775.31472267 2.87022549201
11 3776.24774355 2.89276807641
12 3775.22554377 3.05415386535
13 3775.01634936 4.56489670726
14 3777.48680881 3.09514046612
15 3776.23465168 4.09691179256
16 3777.64782077 4.50033528355
17 3775.7392206 3.79610240281
18 3777.38831693 3.00064812486
19 3775.72011362 4.24151812416
================================================
FILE: hw1/log/Humanoid-v1_BC_30-01-2018_10-28-53/log.txt
================================================
Iteration AverageReturn StdReturn
0 295.814730365 88.5813632879
1 238.349607493 76.3277190139
2 243.129245237 81.1495698412
3 259.916241087 57.306794984
4 247.425765644 56.0124802139
5 241.914222088 46.0838442162
6 253.931450644 63.2003431654
7 251.555778685 78.5263630011
8 268.208717827 64.7656412232
9 247.556079083 72.1923660942
10 251.774811937 69.0744558299
11 254.696568892 45.9480436897
12 253.242338361 76.8047371933
13 228.623935494 59.7224981115
14 229.862209508 57.370454754
15 229.956419335 55.6306188663
16 234.963972145 54.0542848773
17 265.384523529 68.401751621
18 254.279404448 82.3064869712
19 232.650468408 63.4344756441
================================================
FILE: hw1/log/Humanoid-v1_DA_30-01-2018_10-31-26/log.txt
================================================
Iteration AverageReturn StdReturn
0 277.763885265 74.5699695095
1 340.013799005 83.8174345466
2 281.151168831 58.8467520166
3 266.38751159 29.5122759836
4 273.078970953 22.275127559
5 245.575394751 18.4615901498
6 328.153923421 40.2691355568
7 388.722635173 78.4953628383
8 398.844472211 117.74492814
9 474.793752092 205.53054157
10 423.280078799 99.1227466344
11 500.104497995 187.592754877
12 454.008649777 133.582121407
13 508.123738555 171.632223784
14 464.06309332 136.519517931
15 505.570051114 158.128001299
16 537.379418303 162.645475863
17 496.810935012 105.635839043
18 539.956389194 170.934547794
19 500.060948891 133.550493957
================================================
FILE: hw1/log/Reacher-v1_BC_30-01-2018_10-57-25/log.txt
================================================
Iteration AverageReturn StdReturn
0 -9.14313732169 2.1057737525
1 -10.2464604937 2.91303780186
2 -9.36505170342 2.89134055057
3 -9.6073462012 2.38382175938
4 -9.0086068586 2.22443507996
5 -9.14235838387 1.41554386753
6 -9.32533608551 1.92161010184
7 -9.52716548162 2.15173210654
8 -9.18721318721 2.43739650362
9 -8.76734130122 1.87788078057
10 -9.31907915487 2.54378382632
11 -8.70922062576 1.71550860527
12 -9.42346594896 2.18220439629
13 -8.48235034653 1.9664693231
14 -9.52440599013 2.67361159834
15 -10.0461903527 2.14692809316
16 -10.4576060332 2.28085450116
17 -9.40975591137 2.4899395935
18 -9.7550098025 2.27262128127
19 -8.75621744838 1.7181797476
================================================
FILE: hw1/log/Reacher-v1_DA_30-01-2018_11-27-44/log.txt
================================================
Iteration AverageReturn StdReturn
0 -9.514077968 4.67060656967
1 -6.8483366701 2.22806332751
2 -7.28919411373 3.00020247685
3 -5.14896746284 1.78107674457
4 -4.61655540225 1.47905228634
5 -4.17923458664 1.21148217865
6 -4.23271202296 1.57480039431
7 -4.30797880136 1.56205175651
8 -3.86158286292 1.32237728902
9 -4.11994541821 1.39324099865
10 -4.33389428086 1.80342014308
11 -4.66312498685 1.19078597682
12 -3.88081879349 1.56953718566
13 -4.16823813172 1.25349473697
14 -3.78993609335 1.38466284504
15 -4.19153633158 1.7151942544
16 -3.35060677979 1.29864476833
17 -4.76815479509 1.75597118833
18 -4.48480997587 1.46280164822
19 -3.52572072065 1.45917975484
================================================
FILE: hw1/log/Walker2d-v1_BC_30-01-2018_10-58-02/log.txt
================================================
Iteration AverageReturn StdReturn
0 731.896679135 356.841079416
1 245.597115443 370.464617925
2 517.360851842 524.222617
3 375.242482521 396.621897565
4 586.719647307 560.506067304
5 452.02708465 572.73838478
6 315.448568014 432.609821525
7 605.402818104 488.550645007
8 399.929967675 379.255007212
9 662.501627219 561.574809086
10 464.163909044 642.583052804
11 572.401418705 554.032101995
12 446.562993296 583.800058368
13 408.118004614 472.033537121
14 341.961541246 468.061476134
15 537.260068744 668.650000523
16 455.874748994 496.489902983
17 403.340101964 466.662009166
18 391.087910426 636.457336138
19 596.027603618 501.401229289
================================================
FILE: hw1/log/Walker2d-v1_DA_30-01-2018_11-28-50/log.txt
================================================
Iteration AverageReturn StdReturn
0 672.000153601 623.031121462
1 1867.64727184 877.010515332
2 5434.69323044 45.0795878762
3 5421.01186299 47.2655173625
4 5454.79401462 90.7731058749
5 5453.22811906 123.152769513
6 5460.86284453 63.7242425634
7 5473.87194235 65.0663030077
8 5469.63486304 67.2099162387
9 5484.99459822 44.1331706997
10 5282.960857 866.813632308
11 5460.96627823 80.2270775643
12 5469.98407369 63.2927678597
13 5472.67758044 53.748518416
14 5283.16625756 864.037643147
15 5480.75283479 61.9244106372
16 5388.20256771 512.71497588
17 5085.95568353 984.286351731
18 5496.42654867 51.7899718995
19 5285.86858374 857.049898125
================================================
FILE: hw1/logz.py
================================================
import json
"""
Some simple logging functionality, inspired by rllab's logging.
Assumes that each diagnostic gets logged each iteration
Call logz.configure_output_dir() to start logging to a
tab-separated-values file (some_folder_name/log.txt)
To load the learning curves, you can do, for example
A = np.genfromtxt('/tmp/expt_1468984536/log.txt',delimiter='\t',dtype=None, names=True)
A['EpRewMean']
"""
import os.path as osp, shutil, time, atexit, os, subprocess
import pickle
import tensorflow as tf
color2num = dict(
gray=30,
red=31,
green=32,
yellow=33,
blue=34,
magenta=35,
cyan=36,
white=37,
crimson=38
)
def colorize(string, color, bold=False, highlight=False):
attr = []
num = color2num[color]
if highlight: num += 10
attr.append(str(num))
if bold: attr.append('1')
return '\x1b[%sm%s\x1b[0m' % (';'.join(attr), string)
class G:
output_dir = None
output_file = None
first_row = True
log_headers = []
log_current_row = {}
def configure_output_dir(d=None):
"""
Set output directory to d, or to /tmp/somerandomnumber if d is None
"""
G.output_dir = d or "/tmp/experiments/%i"%int(time.time())
if osp.exists(G.output_dir):
print("Log dir %s already exists! Delete it first or use a different dir"%G.output_dir)
else:
os.makedirs(G.output_dir)
G.output_file = open(osp.join(G.output_dir, "log.txt"), 'w')
atexit.register(G.output_file.close)
print(colorize("Logging data to %s"%G.output_file.name, 'green', bold=True))
def log_tabular(key, val):
"""
Log a value of some diagnostic
Call this once for each diagnostic quantity, each iteration
"""
if G.first_row:
G.log_headers.append(key)
else:
assert key in G.log_headers, "Trying to introduce a new key %s that you didn't include in the first iteration"%key
assert key not in G.log_current_row, "You already set %s this iteration. Maybe you forgot to call dump_tabular()"%key
G.log_current_row[key] = val
def save_params(params):
with open(osp.join(G.output_dir, "params.json"), 'w') as out:
out.write(json.dumps(params, separators=(',\n','\t:\t'), sort_keys=True))
def pickle_tf_vars():
"""
Saves tensorflow variables
Requires them to be initialized first, also a default session must exist
"""
_dict = {v.name : v.eval() for v in tf.global_variables()}
with open(osp.join(G.output_dir, "vars.pkl"), 'wb') as f:
pickle.dump(_dict, f)
def dump_tabular():
"""
Write all of the diagnostics from the current iteration
"""
vals = []
key_lens = [len(key) for key in G.log_headers]
max_key_len = max(15,max(key_lens))
keystr = '%'+'%d'%max_key_len
fmt = "| " + keystr + "s | %15s |"
n_slashes = 22 + max_key_len
print("-"*n_slashes)
for key in G.log_headers:
val = G.log_current_row.get(key, "")
if hasattr(val, "__float__"): valstr = "%8.3g"%val
else: valstr = val
print(fmt%(key, valstr))
vals.append(val)
print("-"*n_slashes)
if G.output_file is not None:
if G.first_row:
G.output_file.write("\t".join(G.log_headers))
G.output_file.write("\n")
G.output_file.write("\t".join(map(str,vals)))
G.output_file.write("\n")
G.output_file.flush()
G.log_current_row.clear()
G.first_row=False
================================================
FILE: hw1/plot.py
================================================
import seaborn as sns
import pandas as pd
import matplotlib.pyplot as plt
import json
import os
"""
Using the plotter:
Call it from the command line, and supply it with logdirs to experiments.
Suppose you ran an experiment with name 'test', and you ran 'test' for 10
random seeds. The runner code stored it in the directory structure
data
L test_EnvName_DateTime
L 0
L log.txt
L params.json
L 1
L log.txt
L params.json
.
.
.
L 9
L log.txt
L params.json
To plot learning curves from the experiment, averaged over all random
seeds, call
python plot.py data/test_EnvName_DateTime --value AverageReturn
and voila. To see a different statistics, change what you put in for
the keyword --value. You can also enter /multiple/ values, and it will
make all of them in order.
Suppose you ran two experiments: 'test1' and 'test2'. In 'test2' you tried
a different set of hyperparameters from 'test1', and now you would like
to compare them -- see their learning curves side-by-side. Just call
python plot.py data/test1 data/test2
and it will plot them both! They will be given titles in the legend according
to their exp_name parameters. If you want to use custom legend titles, use
the --legend flag and then provide a title for each logdir.
"""
def plot_data(data, value="AverageReturn"):
if isinstance(data, list):
data = pd.concat(data, ignore_index=True)
sns.set(style="darkgrid", font_scale=1.5)
sns.tsplot(data=data, time="Iteration", value=value, unit="Unit", condition="Condition")
plt.legend(loc='best').draggable()
plt.show()
def get_datasets(fpath, condition=None):
unit = 0
flag = ""
datasets = []
for root, dir, files in os.walk(fpath):
if 'log.txt' in files:
# param_path = open(os.path.join(root,'params.json'))
# params = json.load(param_path)
# exp_name = params['exp_name']
paths = fpath.split("_")
exp_name = paths[0].split("/")[1]+"_"+paths[1]
log_path = os.path.join(root,'log.txt')
experiment_data = pd.read_table(log_path)
experiment_data.insert(
len(experiment_data.columns),
'Unit',
unit
)
experiment_data.insert(
len(experiment_data.columns),
'Condition',
condition or exp_name
)
datasets.append(experiment_data)
unit += 1
return datasets
def main():
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('logdir', nargs='*')
parser.add_argument('--legend', nargs='*')
parser.add_argument('--value', default='AverageReturn', nargs='*')
args = parser.parse_args()
use_legend = False
if args.legend is not None:
assert len(args.legend) == len(args.logdir), \
"Must give a legend title for each set of experiments."
use_legend = True
data = []
if use_legend:
for logdir, legend_title in zip(args.logdir, args.legend):
data += get_datasets(logdir, legend_title)
else:
for logdir in args.logdir:
data += get_datasets(logdir)
if isinstance(args.value, list):
values = args.value
else:
values = [args.value]
for value in values:
plot_data(data, value=value)
if __name__ == "__main__":
main()
================================================
FILE: hw1/run_expert.py
================================================
#!/usr/bin/env python
"""
Code to load an expert policy and generate roll-out data for behavioral cloning.
Example usage:
python run_expert.py experts/Humanoid-v1.pkl Humanoid-v1 --render \
--num_rollouts 20
Author of this script and included expert policies: Jonathan Ho (hoj@openai.com)
"""
import pickle
import tensorflow as tf
import numpy as np
import tf_util
import gym
import load_policy
import os
def main():
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('expert_policy_file', type=str)
parser.add_argument('envname', type=str)
parser.add_argument('--render', action='store_true')
parser.add_argument("--max_timesteps", type=int)
parser.add_argument('--num_rollouts', type=int, default=20,
help='Number of expert roll outs')
args = parser.parse_args()
print('loading and building expert policy')
policy_fn = load_policy.load_policy(args.expert_policy_file)
print('loaded and built')
with tf.Session():
tf_util.initialize()
env = gym.make(args.envname)
max_steps = args.max_timesteps or env.spec.timestep_limit
print('max_steps:', max_steps)
returns = []
observations = []
actions = []
for i in range(args.num_rollouts):
print('iter', i)
obs = env.reset()
done = False
totalr = 0.
steps = 0
while not done:
action = policy_fn(obs[None,:])
observations.append(obs)
actions.append(action)
obs, r, done, _ = env.step(action)
totalr += r
steps += 1
# if args.render:
# env.render()
if steps % 100 == 0: print("%i/%i"%(steps, max_steps))
if steps >= max_steps:
break
returns.append(totalr)
print('returns', returns)
print('mean return', np.mean(returns))
print('std of return', np.std(returns))
expert_data = {'observations': np.array(observations), #(1000, 11)
'actions': np.array(actions)} #(1000, 1, 3)
#write
PROJECT_ROOT = os.path.dirname(os.path.realpath(__file__))
save_dir = os.path.join(PROJECT_ROOT, "data/")
out = os.path.join(save_dir, args.envname+'.train')
np.savez(out, expert_data['observations'], expert_data['actions'])
print("finished")
if __name__ == '__main__':
main()
================================================
FILE: hw1/tf_util.py
================================================
import numpy as np
import tensorflow as tf # pylint: ignore-module
#import builtins
import functools
import copy
import os
import collections
# ================================================================
# Import all names into common namespace
# ================================================================
clip = tf.clip_by_value
# Make consistent with numpy
# ----------------------------------------
def sum(x, axis=None, keepdims=False):
return tf.reduce_sum(x, reduction_indices=None if axis is None else [axis], keep_dims = keepdims)
def mean(x, axis=None, keepdims=False):
return tf.reduce_mean(x, reduction_indices=None if axis is None else [axis], keep_dims = keepdims)
def var(x, axis=None, keepdims=False):
meanx = mean(x, axis=axis, keepdims=keepdims)
return mean(tf.square(x - meanx), axis=axis, keepdims=keepdims)
def std(x, axis=None, keepdims=False):
return tf.sqrt(var(x, axis=axis, keepdims=keepdims))
def max(x, axis=None, keepdims=False):
return tf.reduce_max(x, reduction_indices=None if axis is None else [axis], keep_dims = keepdims)
def min(x, axis=None, keepdims=False):
return tf.reduce_min(x, reduction_indices=None if axis is None else [axis], keep_dims = keepdims)
def concatenate(arrs, axis=0):
return tf.concat(axis, arrs)
def argmax(x, axis=None):
return tf.argmax(x, dimension=axis)
def switch(condition, then_expression, else_expression):
'''Switches between two operations depending on a scalar value (int or bool).
Note that both `then_expression` and `else_expression`
should be symbolic tensors of the *same shape*.
# Arguments
condition: scalar tensor.
then_expression: TensorFlow operation.
else_expression: TensorFlow operation.
'''
x_shape = copy.copy(then_expression.get_shape())
x = tf.cond(tf.cast(condition, 'bool'),
lambda: then_expression,
lambda: else_expression)
x.set_shape(x_shape)
return x
# Extras
# ----------------------------------------
def l2loss(params):
if len(params) == 0:
return tf.constant(0.0)
else:
return tf.add_n([sum(tf.square(p)) for p in params])
def lrelu(x, leak=0.2):
f1 = 0.5 * (1 + leak)
f2 = 0.5 * (1 - leak)
return f1 * x + f2 * abs(x)
def categorical_sample_logits(X):
# https://github.com/tensorflow/tensorflow/issues/456
U = tf.random_uniform(tf.shape(X))
return argmax(X - tf.log(-tf.log(U)), axis=1)
# ================================================================
# Global session
# ================================================================
def get_session():
return tf.get_default_session()
def single_threaded_session():
tf_config = tf.ConfigProto(
inter_op_parallelism_threads=1,
intra_op_parallelism_threads=1)
return tf.Session(config=tf_config)
def make_session(num_cpu):
tf_config = tf.ConfigProto(
inter_op_parallelism_threads=num_cpu,
intra_op_parallelism_threads=num_cpu)
return tf.Session(config=tf_config)
ALREADY_INITIALIZED = set()
def initialize():
new_variables = set(tf.all_variables()) - ALREADY_INITIALIZED
get_session().run(tf.initialize_variables(new_variables))
ALREADY_INITIALIZED.update(new_variables)
def eval(expr, feed_dict=None):
if feed_dict is None: feed_dict = {}
return get_session().run(expr, feed_dict=feed_dict)
def set_value(v, val):
get_session().run(v.assign(val))
def load_state(fname):
saver = tf.train.Saver()
saver.restore(get_session(), fname)
def save_state(fname):
os.makedirs(os.path.dirname(fname), exist_ok=True)
saver = tf.train.Saver()
saver.save(get_session(), fname)
# ================================================================
# Model components
# ================================================================
def normc_initializer(std=1.0):
def _initializer(shape, dtype=None, partition_info=None): #pylint: disable=W0613
out = np.random.randn(*shape).astype(np.float32)
out *= std / np.sqrt(np.square(out).sum(axis=0, keepdims=True))
return tf.constant(out)
return _initializer
def conv2d(x, num_filters, name, filter_size=(3, 3), stride=(1, 1), pad="SAME", dtype=tf.float32, collections=None,
summary_tag=None):
with tf.variable_scope(name):
stride_shape = [1, stride[0], stride[1], 1]
filter_shape = [filter_size[0], filter_size[1], int(x.get_shape()[3]), num_filters]
# there are "num input feature maps * filter height * filter width"
# inputs to each hidden unit
fan_in = intprod(filter_shape[:3])
# each unit in the lower layer receives a gradient from:
# "num output feature maps * filter height * filter width" /
# pooling size
fan_out = intprod(filter_shape[:2]) * num_filters
# initialize weights with random weights
w_bound = np.sqrt(6. / (fan_in + fan_out))
w = tf.get_variable("W", filter_shape, dtype, tf.random_uniform_initializer(-w_bound, w_bound),
collections=collections)
b = tf.get_variable("b", [1, 1, 1, num_filters], initializer=tf.zeros_initializer,
collections=collections)
if summary_tag is not None:
tf.image_summary(summary_tag,
tf.transpose(tf.reshape(w, [filter_size[0], filter_size[1], -1, 1]),
[2, 0, 1, 3]),
max_images=10)
return tf.nn.conv2d(x, w, stride_shape, pad) + b
def dense(x, size, name, weight_init=None, bias=True):
w = tf.get_variable(name + "/w", [x.get_shape()[1], size], initializer=weight_init)
ret = tf.matmul(x, w)
if bias:
b = tf.get_variable(name + "/b", [size], initializer=tf.zeros_initializer)
return ret + b
else:
return ret
def wndense(x, size, name, init_scale=1.0):
v = tf.get_variable(name + "/V", [int(x.get_shape()[1]), size],
initializer=tf.random_normal_initializer(0, 0.05))
g = tf.get_variable(name + "/g", [size], initializer=tf.constant_initializer(init_scale))
b = tf.get_variable(name + "/b", [size], initializer=tf.constant_initializer(0.0))
# use weight normalization (Salimans & Kingma, 2016)
x = tf.matmul(x, v)
scaler = g / tf.sqrt(sum(tf.square(v), axis=0, keepdims=True))
return tf.reshape(scaler, [1, size]) * x + tf.reshape(b, [1, size])
def densenobias(x, size, name, weight_init=None):
return dense(x, size, name, weight_init=weight_init, bias=False)
def dropout(x, pkeep, phase=None, mask=None):
mask = tf.floor(pkeep + tf.random_uniform(tf.shape(x))) if mask is None else mask
if phase is None:
return mask * x
else:
return switch(phase, mask*x, pkeep*x)
def batchnorm(x, name, phase, updates, gamma=0.96):
k = x.get_shape()[1]
runningmean = tf.get_variable(name+"/mean", shape=[1, k], initializer=tf.constant_initializer(0.0), trainable=False)
runningvar = tf.get_variable(name+"/var", shape=[1, k], initializer=tf.constant_initializer(1e-4), trainable=False)
testy = (x - runningmean) / tf.sqrt(runningvar)
mean_ = mean(x, axis=0, keepdims=True)
var_ = mean(tf.square(x), axis=0, keepdims=True)
std = tf.sqrt(var_)
trainy = (x - mean_) / std
updates.extend([
tf.assign(runningmean, runningmean * gamma + mean_ * (1 - gamma)),
tf.assign(runningvar, runningvar * gamma + var_ * (1 - gamma))
])
y = switch(phase, trainy, testy)
out = y * tf.get_variable(name+"/scaling", shape=[1, k], initializer=tf.constant_initializer(1.0), trainable=True)\
+ tf.get_variable(name+"/translation", shape=[1,k], initializer=tf.constant_initializer(0.0), trainable=True)
return out
# ================================================================
# Basic Stuff
# ================================================================
def function(inputs, outputs, updates=None, givens=None):
if isinstance(outputs, list):
return _Function(inputs, outputs, updates, givens=givens)
elif isinstance(outputs, (dict, collections.OrderedDict)):
f = _Function(inputs, outputs.values(), updates, givens=givens)
return lambda *inputs : type(outputs)(zip(outputs.keys(), f(*inputs)))
else:
f = _Function(inputs, [outputs], updates, givens=givens)
return lambda *inputs : f(*inputs)[0]
class _Function(object):
def __init__(self, inputs, outputs, updates, givens, check_nan=False):
assert all(len(i.op.inputs)==0 for i in inputs), "inputs should all be placeholders"
self.inputs = inputs
updates = updates or []
self.update_group = tf.group(*updates)
self.outputs_update = list(outputs) + [self.update_group]
self.givens = {} if givens is None else givens
self.check_nan = check_nan
def __call__(self, *inputvals):
assert len(inputvals) == len(self.inputs)
feed_dict = dict(zip(self.inputs, inputvals))
feed_dict.update(self.givens)
results = get_session().run(self.outputs_update, feed_dict=feed_dict)[:-1]
if self.check_nan:
if any(np.isnan(r).any() for r in results):
raise RuntimeError("Nan detected")
return results
def mem_friendly_function(nondata_inputs, data_inputs, outputs, batch_size):
if isinstance(outputs, list):
return _MemFriendlyFunction(nondata_inputs, data_inputs, outputs, batch_size)
else:
f = _MemFriendlyFunction(nondata_inputs, data_inputs, [outputs], batch_size)
return lambda *inputs : f(*inputs)[0]
class _MemFriendlyFunction(object):
def __init__(self, nondata_inputs, data_inputs, outputs, batch_size):
self.nondata_inputs = nondata_inputs
self.data_inputs = data_inputs
self.outputs = list(outputs)
self.batch_size = batch_size
def __call__(self, *inputvals):
assert len(inputvals) == len(self.nondata_inputs) + len(self.data_inputs)
nondata_vals = inputvals[0:len(self.nondata_inputs)]
data_vals = inputvals[len(self.nondata_inputs):]
feed_dict = dict(zip(self.nondata_inputs, nondata_vals))
n = data_vals[0].shape[0]
for v in data_vals[1:]:
assert v.shape[0] == n
for i_start in range(0, n, self.batch_size):
slice_vals = [v[i_start:min(i_start+self.batch_size, n)] for v in data_vals]
for (var,val) in zip(self.data_inputs, slice_vals):
feed_dict[var]=val
results = tf.get_default_session().run(self.outputs, feed_dict=feed_dict)
if i_start==0:
sum_results = results
else:
for i in range(len(results)):
sum_results[i] = sum_results[i] + results[i]
for i in range(len(results)):
sum_results[i] = sum_results[i] / n
return sum_results
# ================================================================
# Modules
# ================================================================
class Module(object):
def __init__(self, name):
self.name = name
self.first_time = True
self.scope = None
self.cache = {}
def __call__(self, *args):
if args in self.cache:
print("(%s) retrieving value from cache"%self.name)
return self.cache[args]
with tf.variable_scope(self.name, reuse=not self.first_time):
scope = tf.get_variable_scope().name
if self.first_time:
self.scope = scope
print("(%s) running function for the first time"%self.name)
else:
assert self.scope == scope, "Tried calling function with a different scope"
print("(%s) running function on new inputs"%self.name)
self.first_time = False
out = self._call(*args)
self.cache[args] = out
return out
def _call(self, *args):
raise NotImplementedError
@property
def trainable_variables(self):
assert self.scope is not None, "need to call module once before getting variables"
return tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, self.scope)
@property
def variables(self):
assert self.scope is not None, "need to call module once before getting variables"
return tf.get_collection(tf.GraphKeys.VARIABLES, self.scope)
def module(name):
@functools.wraps
def wrapper(f):
class WrapperModule(Module):
def _call(self, *args):
return f(*args)
return WrapperModule(name)
return wrapper
# ================================================================
# Graph traversal
# ================================================================
VARIABLES = {}
def get_parents(node):
return node.op.inputs
def topsorted(outputs):
"""
Topological sort via non-recursive depth-first search
"""
assert isinstance(outputs, (list,tuple))
marks = {}
out = []
stack = [] #pylint: disable=W0621
# i: node
# jidx = number of children visited so far from that node
# marks: state of each node, which is one of
# 0: haven't visited
# 1: have visited, but not done visiting children
# 2: done visiting children
for x in outputs:
stack.append((x,0))
while stack:
(i,jidx) = stack.pop()
if jidx == 0:
m = marks.get(i,0)
if m == 0:
marks[i] = 1
elif m == 1:
raise ValueError("not a dag")
else:
continue
ps = get_parents(i)
if jidx == len(ps):
marks[i] = 2
out.append(i)
else:
stack.append((i,jidx+1))
j = ps[jidx]
stack.append((j,0))
return out
# ================================================================
# Flat vectors
# ================================================================
def var_shape(x):
out = [k.value for k in x.get_shape()]
assert all(isinstance(a, int) for a in out), \
"shape function assumes that shape is fully known"
return out
def numel(x):
return intprod(var_shape(x))
def intprod(x):
return int(np.prod(x))
def flatgrad(loss, var_list):
grads = tf.gradients(loss, var_list)
return tf.concat(0, [tf.reshape(grad, [numel(v)])
for (v, grad) in zip(var_list, grads)])
class SetFromFlat(object):
def __init__(self, var_list, dtype=tf.float32):
assigns = []
shapes = list(map(var_shape, var_list))
total_size = np.sum([intprod(shape) for shape in shapes])
self.theta = theta = tf.placeholder(dtype,[total_size])
start=0
assigns = []
for (shape,v) in zip(shapes,var_list):
size = intprod(shape)
assigns.append(tf.assign(v, tf.reshape(theta[start:start+size],shape)))
start+=size
self.op = tf.group(*assigns)
def __call__(self, theta):
get_session().run(self.op, feed_dict={self.theta:theta})
class GetFlat(object):
def __init__(self, var_list):
self.op = tf.concat(0, [tf.reshape(v, [numel(v)]) for v in var_list])
def __call__(self):
return get_session().run(self.op)
# ================================================================
# Misc
# ================================================================
def fancy_slice_2d(X, inds0, inds1):
"""
like numpy X[inds0, inds1]
XXX this implementation is bad
"""
inds0 = tf.cast(inds0, tf.int64)
inds1 = tf.cast(inds1, tf.int64)
shape = tf.cast(tf.shape(X), tf.int64)
ncols = shape[1]
Xflat = tf.reshape(X, [-1])
return tf.gather(Xflat, inds0 * ncols + inds1)
def scope_vars(scope, trainable_only):
"""
Get variables inside a scope
The scope can be specified as a string
"""
return tf.get_collection(
tf.GraphKeys.TRAINABLE_VARIABLES if trainable_only else tf.GraphKeys.VARIABLES,
scope=scope if isinstance(scope, str) else scope.name
)
def lengths_to_mask(lengths_b, max_length):
"""
Turns a vector of lengths into a boolean mask
Args:
lengths_b: an integer vector of lengths
max_length: maximum length to fill the mask
Returns:
a boolean array of shape (batch_size, max_length)
row[i] consists of True repeated lengths_b[i] times, followed by False
"""
lengths_b = tf.convert_to_tensor(lengths_b)
assert lengths_b.get_shape().ndims == 1
mask_bt = tf.expand_dims(tf.range(max_length), 0) < tf.expand_dims(lengths_b, 1)
return mask_bt
def in_session(f):
@functools.wraps(f)
def newfunc(*args, **kwargs):
with tf.Session():
f(*args, **kwargs)
return newfunc
_PLACEHOLDER_CACHE = {} # name -> (placeholder, dtype, shape)
def get_placeholder(name, dtype, shape):
print("calling get_placeholder", name)
if name in _PLACEHOLDER_CACHE:
out, dtype1, shape1 = _PLACEHOLDER_CACHE[name]
assert dtype1==dtype and shape1==shape
return out
else:
out = tf.placeholder(dtype=dtype, shape=shape, name=name)
_PLACEHOLDER_CACHE[name] = (out,dtype,shape)
return out
def get_placeholder_cached(name):
return _PLACEHOLDER_CACHE[name][0]
def flattenallbut0(x):
return tf.reshape(x, [-1, intprod(x.get_shape().as_list()[1:])])
def reset():
global _PLACEHOLDER_CACHE
global VARIABLES
_PLACEHOLDER_CACHE = {}
VARIABLES = {}
tf.reset_default_graph()
================================================
FILE: hw2/.idea/hw2.iml
================================================
================================================
FILE: hw2/.idea/misc.xml
================================================
================================================
FILE: hw2/.idea/modules.xml
================================================
================================================
FILE: hw2/.idea/workspace.xml
================================================
ob_no
loss
#bl2
build_mlp
1516669850648
1516669850648
================================================
FILE: hw2/data/HalfCheetah_b50000_rtg_na_25bl_HalfCheetah-v1_31-01-2018_19-35-00/1/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.133293 25.448426246643066 0 -179.33068933 39.2898608549 -64.8887104153 -299.604089513 151.0 0.0 50132 50132
0.0511833 42.846628189086914 1 -148.606064338 42.533900249 -49.9120428547 -276.510779299 151.0 0.0 50132 100264
0.0572527 61.10300421714783 2 -120.536215955 39.4846258104 -5.9060736545 -240.029126655 151.0 0.0 50132 150396
0.0298718 79.34754776954651 3 -97.9565585579 35.6283471029 -11.0812879966 -260.096540085 151.0 0.0 50132 200528
0.0322279 97.38736867904663 4 -94.2633140782 32.3465301386 9.16578404748 -202.962048552 151.0 0.0 50132 250660
0.016316 115.01092791557312 5 -93.9071039577 31.2213294903 0.401268223837 -227.466183436 151.0 0.0 50132 300792
0.0167591 132.51984119415283 6 -94.8293881237 29.1252327052 50.2664705411 -195.40892016 151.0 0.0 50132 350924
0.0264593 149.86110424995422 7 -95.7902107153 31.3967198491 -17.6409104329 -201.065445477 151.0 0.0 50132 401056
0.0203816 167.2442409992218 8 -86.1974336082 29.9126825368 -11.1624613763 -229.269790683 151.0 0.0 50132 451188
0.0195637 184.57763361930847 9 -75.3971787064 28.4099883616 -2.91159419919 -201.487737878 151.0 0.0 50132 501320
0.015681 201.94242334365845 10 -66.5291743251 27.3617021986 8.65267583443 -151.060197382 151.0 0.0 50132 551452
0.0202405 219.30347180366516 11 -63.0298191441 27.2448855245 -6.47570459077 -170.185939103 151.0 0.0 50132 601584
0.0156047 236.7127959728241 12 -57.3076110784 25.1331179495 3.6367831527 -137.297945971 151.0 0.0 50132 651716
0.015131 254.0550982952118 13 -50.3196637051 24.4452423525 17.5518845558 -152.020824906 151.0 0.0 50132 701848
0.0159931 271.41443967819214 14 -44.389283081 21.2386244378 11.3105494853 -122.173791072 151.0 0.0 50132 751980
0.0165923 288.7827877998352 15 -44.5700555413 22.5160967597 12.0620372677 -112.419782168 151.0 0.0 50132 802112
0.0185337 306.18880701065063 16 -38.8550387528 20.2803802874 29.8354785787 -106.702525151 151.0 0.0 50132 852244
0.019082 323.7642719745636 17 -36.0911314892 20.9151817188 22.393443393 -109.884108994 151.0 0.0 50132 902376
0.0225671 341.1691167354584 18 -34.0105432078 20.8576622287 15.754886997 -107.961152444 151.0 0.0 50132 952508
0.0102453 358.6126923561096 19 -35.0251613878 22.0372439003 29.8823515524 -127.517257298 151.0 0.0 50132 1002640
0.0161908 375.9906620979309 20 -31.5873060429 22.7862157451 34.1843875213 -117.737950912 151.0 0.0 50132 1052772
0.0169231 393.39186453819275 21 -28.5671175488 19.4448337439 27.8019358833 -97.6354796118 151.0 0.0 50132 1102904
0.017502 410.7973198890686 22 -22.4539025367 20.6658131139 26.8015904639 -126.852927183 151.0 0.0 50132 1153036
0.0144892 428.25348806381226 23 -16.8346210051 18.4712133575 34.3619588892 -93.4809736692 151.0 0.0 50132 1203168
0.0175294 445.75735449790955 24 -13.7300606352 16.5279274615 45.1834395994 -68.6667838992 151.0 0.0 50132 1253300
0.0269088 463.25252509117126 25 -11.6646432237 18.931788653 44.3404809664 -85.5989880009 151.0 0.0 50132 1303432
0.0183992 480.66894268989563 26 -8.8125187567 17.0538149711 40.0261280321 -64.0965170699 151.0 0.0 50132 1353564
0.0270967 498.06955766677856 27 -7.61458414919 15.5363423438 38.6545067547 -73.5994991664 151.0 0.0 50132 1403696
0.0202837 515.4838519096375 28 -7.5643906963 13.1692132795 28.8422193159 -58.7653458719 151.0 0.0 50132 1453828
0.032324 533.6044790744781 29 -7.88732992076 13.6205604434 23.7089055113 -52.7262926622 151.0 0.0 50132 1503960
0.017226 551.0418577194214 30 -4.81328252996 14.4281045663 40.3022453044 -60.7769945891 151.0 0.0 50132 1554092
0.0237148 568.540479183197 31 0.503191612289 14.7629697393 42.6004038947 -57.6291822069 151.0 0.0 50132 1604224
0.0241208 586.0562088489532 32 5.31118377239 17.3671926803 44.7379480195 -53.1878315807 151.0 0.0 50132 1654356
0.0157807 604.7549903392792 33 10.89034033 19.0480939249 55.0128118318 -73.1248891571 151.0 0.0 50132 1704488
0.020365 622.1728205680847 34 17.7671103225 17.7904016311 58.4101610036 -43.7355593981 151.0 0.0 50132 1754620
0.0129134 639.5883619785309 35 22.42801249 18.1763262835 66.1780468444 -46.6517369961 151.0 0.0 50132 1804752
0.00868595 656.9805538654327 36 24.6239850216 20.690837396 67.0156129223 -68.2607863022 151.0 0.0 50132 1854884
0.01336 674.3199441432953 37 28.7251779744 18.2555714257 69.4029800012 -41.9340622203 151.0 0.0 50132 1905016
0.0126717 692.2312703132629 38 29.6963350254 23.933793475 83.9837053273 -49.838575588 151.0 0.0 50132 1955148
0.0204675 709.6087455749512 39 33.0208667623 25.6643776793 98.4086242795 -80.8446065203 151.0 0.0 50132 2005280
0.0232269 726.9732248783112 40 40.6926470132 21.3550453036 92.3745433988 -52.7401874135 151.0 0.0 50132 2055412
-0.0107402 744.4198088645935 41 47.7884448095 20.3955976231 94.760215677 -29.0397346658 151.0 0.0 50132 2105544
-0.0106151 761.82421708107 42 53.1096144229 27.7124088791 108.505558718 -62.2108937376 151.0 0.0 50132 2155676
-0.00608519 779.2861967086792 43 51.8660344441 27.2646686222 103.014925578 -63.4603096516 151.0 0.0 50132 2205808
0.0137518 796.7234201431274 44 48.5393239361 35.3895358101 102.183362434 -61.5291894318 151.0 0.0 50132 2255940
0.0155841 814.1130645275116 45 48.6577722028 30.2651964165 100.343212064 -54.0211094641 151.0 0.0 50132 2306072
0.00917006 831.4584109783173 46 56.7313055657 26.0706073002 99.0665713258 -61.2469985286 151.0 0.0 50132 2356204
0.000182971 848.8481845855713 47 71.4240228836 26.6106093683 117.391216718 -24.3428371699 151.0 0.0 50132 2406336
0.00452052 866.282511472702 48 74.1239186246 28.1015744381 125.933737237 -23.664714475 151.0 0.0 50132 2456468
0.0138416 883.5756363868713 49 66.893572219 31.160214229 145.319864383 -46.7460073729 151.0 0.0 50132 2506600
0.0719024 901.0127730369568 50 71.5834981937 29.261178731 143.144330252 -21.1289007802 151.0 0.0 50132 2556732
-0.0407039 918.319787979126 51 76.4148287165 20.3878858901 118.227515096 1.67577172767 151.0 0.0 50132 2606864
-0.0166612 935.6414361000061 52 78.8036213533 20.4435520398 128.780111637 -25.4414792569 151.0 0.0 50132 2656996
-0.151419 952.9851241111755 53 87.6104612233 22.346310915 134.274052772 -23.4992014494 151.0 0.0 50132 2707128
-0.0136276 970.4374308586121 54 77.8166196929 23.6091843875 130.683760336 -6.52469421412 151.0 0.0 50132 2757260
-0.0302435 987.770161151886 55 81.0041288771 25.0533640845 139.95905789 -17.8392294624 151.0 0.0 50132 2807392
0.0260241 1005.0541090965271 56 78.3369537352 30.0950142681 126.539841377 -45.7873870624 151.0 0.0 50132 2857524
0.037265 1022.390073299408 57 81.0994985703 32.8203956722 128.559321558 -29.8774157352 151.0 0.0 50132 2907656
0.000206351 1039.7500381469727 58 80.1786041875 29.6551329964 133.21483671 -49.0817390529 151.0 0.0 50132 2957788
0.00672939 1057.593801021576 59 81.8096754822 23.7911667265 127.593774963 -12.6151574985 151.0 0.0 50132 3007920
0.0307942 1074.9470241069794 60 88.1199699425 20.7148027326 122.087145452 -24.3563414879 151.0 0.0 50132 3058052
0.0181423 1092.2785639762878 61 96.7669312931 21.7270481497 134.439164635 -16.063387008 151.0 0.0 50132 3108184
-0.0951916 1109.5738620758057 62 109.207726365 26.5131899319 161.72765998 2.68148326057 151.0 0.0 50132 3158316
-0.0543005 1126.9086530208588 63 103.894204594 28.5914713128 160.952670048 -17.6150390193 151.0 0.0 50132 3208448
-0.109457 1144.4107794761658 64 103.223968281 31.806931454 165.112164853 -47.0618067798 151.0 0.0 50132 3258580
-0.119589 1161.7094781398773 65 108.609907959 29.8939910654 171.629600104 -12.8924113624 151.0 0.0 50132 3308712
-0.0522546 1178.9669692516327 66 110.733140574 22.5958373242 144.517156909 -20.4782387412 151.0 0.0 50132 3358844
0.021341 1196.3099405765533 67 96.6009209841 21.2273345108 137.211783659 -14.1044777758 151.0 0.0 50132 3408976
-0.00994848 1213.7535479068756 68 108.917960397 18.6427279424 145.423670085 -40.7204619291 151.0 0.0 50132 3459108
-0.00197615 1231.0432980060577 69 120.291524999 16.8451213817 157.450465138 50.859044525 151.0 0.0 50132 3509240
0.0263877 1248.5932233333588 70 132.397156157 19.8816245645 175.026190802 35.1192246829 151.0 0.0 50132 3559372
-0.000850692 1266.052000284195 71 124.351170344 21.2110330596 170.371379569 15.0654154297 151.0 0.0 50132 3609504
0.0281867 1283.4100875854492 72 117.992789746 25.1851159455 166.57367373 -1.24354605101 151.0 0.0 50132 3659636
-0.0152832 1300.7378389835358 73 124.586990639 24.5938885653 170.878334584 7.81948911508 151.0 0.0 50132 3709768
-0.0137309 1318.1021897792816 74 128.61676341 27.8226730477 185.34528317 -4.14498221351 151.0 0.0 50132 3759900
-0.00500324 1335.4428339004517 75 131.302294374 28.5093408432 175.439084762 -6.57414068791 151.0 0.0 50132 3810032
0.0298657 1352.786170721054 76 135.503006655 22.6088686337 171.659523591 10.2975411796 151.0 0.0 50132 3860164
0.0430857 1369.9960262775421 77 135.012632709 17.9255098169 178.105758033 16.6179029283 151.0 0.0 50132 3910296
-0.000391383 1387.2642958164215 78 128.120669702 16.156769715 165.704975806 39.7954755939 151.0 0.0 50132 3960428
0.0278823 1404.5721728801727 79 123.90797326 17.9023473024 165.591772792 16.4438175941 151.0 0.0 50132 4010560
0.0431979 1421.912649154663 80 133.730214763 19.2199251931 189.347381836 39.545368668 151.0 0.0 50132 4060692
0.0640927 1439.2352764606476 81 133.076134323 22.8076704668 182.248326883 50.8470641852 151.0 0.0 50132 4110824
0.000945015 1456.4754464626312 82 113.582360316 41.2400371818 175.522275478 -8.19092507599 151.0 0.0 50132 4160956
-0.00385883 1473.756596326828 83 120.111571484 37.3903531712 166.492059968 -14.654343465 151.0 0.0 50132 4211088
0.2068 1491.0191214084625 84 127.278022046 26.8683626835 168.060325895 -15.7795142641 151.0 0.0 50132 4261220
0.0606409 1508.2981476783752 85 132.445201222 22.7112558845 169.298954893 -9.93169153637 151.0 0.0 50132 4311352
0.0986238 1525.5257413387299 86 137.673055324 17.5801615814 177.260248395 4.26701663692 151.0 0.0 50132 4361484
0.0580756 1542.7471117973328 87 137.952956407 16.1518806479 180.779046073 40.0552755122 151.0 0.0 50132 4411616
0.0152075 1559.9642806053162 88 118.090676764 41.1089102579 191.687041477 -21.2552235901 151.0 0.0 50132 4461748
0.0871946 1577.3119723796844 89 78.0761778291 62.6995555419 177.279672828 -32.172458644 151.0 0.0 50132 4511880
0.0861108 1594.578145980835 90 122.934924499 33.4669167603 172.162768163 -17.9278211916 151.0 0.0 50132 4562012
0.327106 1611.8292326927185 91 129.888923775 13.8975333486 166.656061132 86.3408857062 151.0 0.0 50132 4612144
0.0406095 1629.1160552501678 92 151.76482434 16.7412807028 190.689096854 25.6853591997 151.0 0.0 50132 4662276
-0.0338379 1646.4187574386597 93 148.798054311 21.1627531468 193.143202885 55.5361234051 151.0 0.0 50132 4712408
-0.326612 1663.6832489967346 94 142.325134132 20.9087122605 180.1284824 32.90802496 151.0 0.0 50132 4762540
-0.112979 1680.9754304885864 95 140.834106068 18.7779267411 185.781068192 7.76995464114 151.0 0.0 50132 4812672
-0.0305067 1698.2448518276215 96 136.959483761 19.5082067964 190.485582299 43.9965753337 151.0 0.0 50132 4862804
0.156979 1715.5525453090668 97 143.838990449 20.1867732249 195.767328563 64.0663237813 151.0 0.0 50132 4912936
-0.0117669 1732.8337411880493 98 150.5317061 18.1365910766 197.701370993 93.4293046108 151.0 0.0 50132 4963068
0.443599 1750.078330039978 99 154.288889537 16.9159632689 197.161612264 62.827653579 151.0 0.0 50132 5013200
================================================
FILE: hw2/data/HalfCheetah_b50000_rtg_na_25bl_HalfCheetah-v1_31-01-2018_19-35-00/1/params.json
================================================
{"animate" : false,
"env_name" : "HalfCheetah-v1",
"exp_name" : "HalfCheetah_b50000_rtg_na_25bl",
"gamma" : 0.9,
"learning_rate" : 0.025,
"logdir" : "data/HalfCheetah_b50000_rtg_na_25bl_HalfCheetah-v1_31-01-2018_19-35-00/1",
"max_path_length" : 150.0,
"min_timesteps_per_batch" : 50000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : true,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 1,
"size" : 32}
================================================
FILE: hw2/data/HalfCheetah_b50000_rtg_na_25bl_HalfCheetah-v1_31-01-2018_19-35-00/11/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.156345 24.443801641464233 0 -270.807132938 51.144434011 -124.247270511 -408.722559886 151.0 0.0 50132 50132
0.0745756 41.68954515457153 1 -208.174620004 42.8050799888 -96.1271702736 -322.408903503 151.0 0.0 50132 100264
0.0524621 58.94227194786072 2 -163.86329966 39.0648217774 -33.541631339 -297.024382203 151.0 0.0 50132 150396
0.0376806 76.17933058738708 3 -143.120324724 38.1613540631 -39.9368740615 -269.867959189 151.0 0.0 50132 200528
0.0194735 93.40901017189026 4 -131.582923395 37.4306005119 -41.4770662667 -262.189696779 151.0 0.0 50132 250660
0.019406 110.68946814537048 5 -123.347786916 36.2345390801 -16.1396148984 -245.603064289 151.0 0.0 50132 300792
0.0184991 127.94105243682861 6 -112.889513591 34.2592915777 -24.9485828047 -256.295959957 151.0 0.0 50132 350924
0.0212448 145.12072658538818 7 -108.85053352 34.216731248 -23.4573843867 -223.650869786 151.0 0.0 50132 401056
0.0176691 162.28984999656677 8 -100.777447103 33.0336073048 35.1413112999 -198.531529377 151.0 0.0 50132 451188
0.0136455 179.48703360557556 9 -96.4646472196 33.4928776315 7.01913793564 -207.898906884 151.0 0.0 50132 501320
0.0215281 196.7747299671173 10 -91.0654907222 34.8100614151 27.756712229 -188.680406673 151.0 0.0 50132 551452
0.0223921 214.01161670684814 11 -84.0375624954 35.4480411913 67.3296271314 -189.716663059 151.0 0.0 50132 601584
0.0215174 231.31497406959534 12 -76.0735008025 32.7773397301 20.2344331449 -186.426370003 151.0 0.0 50132 651716
0.0169964 248.65626192092896 13 -69.2143664409 31.9517135993 20.7611302791 -190.809494716 151.0 0.0 50132 701848
0.0142232 265.9935550689697 14 -57.9622883197 29.9415468864 26.8067527548 -170.49599844 151.0 0.0 50132 751980
0.0127593 283.34787821769714 15 -57.0049868941 29.7788677367 42.0555399094 -150.776807077 151.0 0.0 50132 802112
0.01255 300.75698709487915 16 -52.4070161588 27.7440190479 33.0667652876 -156.973353495 151.0 0.0 50132 852244
0.0157212 318.07285737991333 17 -50.0178988864 26.7919215559 26.1940825337 -147.869435494 151.0 0.0 50132 902376
0.0116063 335.4031457901001 18 -47.058347119 27.2101543524 23.8799112773 -147.117599183 151.0 0.0 50132 952508
0.0103434 352.7371082305908 19 -46.1477791211 24.7258875208 17.455954359 -136.159242166 151.0 0.0 50132 1002640
0.0141757 370.0111255645752 20 -44.7421885101 26.5518099028 18.9852314352 -158.481592444 151.0 0.0 50132 1052772
0.0170411 387.3496460914612 21 -37.6113435456 24.610869755 21.3342743107 -118.900679407 151.0 0.0 50132 1102904
0.0172864 404.6649658679962 22 -34.4413393363 24.8922226735 24.7217700601 -132.064007648 151.0 0.0 50132 1153036
0.0125309 422.0147588253021 23 -32.5791391956 25.1413827803 36.8870949818 -128.689781434 151.0 0.0 50132 1203168
0.0113816 439.35777401924133 24 -28.9719738336 19.8485325046 14.9354028209 -96.2432326478 151.0 0.0 50132 1253300
0.0127849 456.69245052337646 25 -26.6872084597 22.4459651495 30.3132533702 -106.262946466 151.0 0.0 50132 1303432
0.014384 474.02413630485535 26 -26.492911924 21.1923023928 31.8756407404 -121.618312114 151.0 0.0 50132 1353564
0.0150111 491.3865704536438 27 -22.5471363888 21.7282683118 51.4644042612 -139.288884604 151.0 0.0 50132 1403696
0.0107308 508.7335605621338 28 -21.8625348799 22.4595421731 59.1765901322 -98.4716067074 151.0 0.0 50132 1453828
0.0106887 526.0901181697845 29 -19.122674373 22.0124968795 52.5566398805 -122.764009032 151.0 0.0 50132 1503960
0.0135209 543.3986639976501 30 -20.1571496979 19.2183764843 35.8787573842 -90.683500138 151.0 0.0 50132 1554092
0.0148105 560.7340970039368 31 -18.1932959063 20.1338105964 42.5484711637 -114.017780143 151.0 0.0 50132 1604224
0.0168172 578.1244428157806 32 -17.3113719715 18.3242251908 32.1464217304 -95.2990426232 151.0 0.0 50132 1654356
0.0239558 595.9245526790619 33 -14.8479686503 15.621951826 33.904274897 -57.0699736474 151.0 0.0 50132 1704488
0.0141534 613.3564751148224 34 -13.1165029339 15.3295797531 29.245383332 -63.4801824559 151.0 0.0 50132 1754620
0.0158751 631.1353979110718 35 -12.6115729411 14.1498657802 31.5550869502 -62.2967103864 151.0 0.0 50132 1804752
0.0187876 649.3035516738892 36 -9.74873734089 12.9087835191 31.4540828312 -52.1836839756 151.0 0.0 50132 1854884
0.0205946 667.242800951004 37 -6.39376571649 13.3664898159 33.5742004633 -50.6052205571 151.0 0.0 50132 1905016
0.020675 687.1851966381073 38 -1.64690829924 16.1347912646 50.8222697974 -53.8731015827 151.0 0.0 50132 1955148
0.0180232 705.7867012023926 39 5.58895562653 17.3748414648 61.5233847372 -62.4213041612 151.0 0.0 50132 2005280
0.0214217 724.5065524578094 40 8.44418711816 16.390860669 66.8289876494 -63.5820963371 151.0 0.0 50132 2055412
0.0159438 749.6698753833771 41 8.61961584828 18.1544462687 60.8472784198 -44.707776249 151.0 0.0 50132 2105544
0.0165443 772.5674297809601 42 13.0264712926 16.0456063036 51.4251914293 -44.5981381416 151.0 0.0 50132 2155676
0.0143073 799.0406270027161 43 16.4536457806 15.6875054846 65.3031723392 -46.5263470391 151.0 0.0 50132 2205808
0.0191986 823.7559452056885 44 23.1974222047 16.7922518446 71.8889865064 -59.6553980292 151.0 0.0 50132 2255940
0.0169812 845.5439846515656 45 30.8654521791 21.452045185 85.2246107747 -57.0336624229 151.0 0.0 50132 2306072
0.0195603 865.8228287696838 46 35.7817425256 25.1589567016 86.6341985197 -93.5013420866 151.0 0.0 50132 2356204
0.0205392 887.0430307388306 47 39.7167506798 25.0403232768 94.2910649383 -46.7231567874 151.0 0.0 50132 2406336
0.00594468 908.2338352203369 48 51.2064485835 27.9200442591 103.265646891 -67.0813596421 151.0 0.0 50132 2456468
0.0130448 925.3884208202362 49 50.3234196493 29.7048632605 100.007991175 -46.522801209 151.0 0.0 50132 2506600
0.0242518 942.632294178009 50 49.8872459679 30.3881984586 104.918423251 -54.1735014646 151.0 0.0 50132 2556732
0.0204469 959.8109889030457 51 60.4612486257 26.8470099409 108.431421818 -50.2798967417 151.0 0.0 50132 2606864
0.0274831 977.0340876579285 52 64.0796140974 24.0725047216 105.907963541 -40.1578980498 151.0 0.0 50132 2656996
0.0240855 994.2316606044769 53 70.0180890763 18.146930569 117.538417677 0.0539951720255 151.0 0.0 50132 2707128
0.0291589 1011.4263353347778 54 77.0394790875 21.9981690846 120.661425928 -28.9163894042 151.0 0.0 50132 2757260
0.0152475 1028.5558805465698 55 86.9063687535 28.4297652798 142.984622225 -39.0498226022 151.0 0.0 50132 2807392
0.0214814 1045.6518015861511 56 87.7389149336 30.1476799697 147.91640431 -32.5425927192 151.0 0.0 50132 2857524
0.0197347 1062.789380788803 57 91.9224177279 28.5295269597 146.520222155 -44.2126761433 151.0 0.0 50132 2907656
0.0244948 1079.828236579895 58 95.1937808035 24.4394575485 143.225390406 -36.8699767283 151.0 0.0 50132 2957788
0.0291605 1096.8878691196442 59 91.2198217279 19.6436648462 128.851842416 -2.52456424265 151.0 0.0 50132 3007920
0.0170105 1114.0013291835785 60 86.0783659977 22.0866557276 129.556461159 -44.4423881159 151.0 0.0 50132 3058052
0.0585194 1131.1018915176392 61 92.4430588896 27.5265606691 139.718015317 -32.3077818066 151.0 0.0 50132 3108184
0.0107379 1148.2288718223572 62 87.8335394781 42.3994360402 152.307235048 -36.3599110433 151.0 0.0 50132 3158316
0.0738931 1165.37731051445 63 95.1449936882 29.9372617955 148.221298645 -17.4016885397 151.0 0.0 50132 3208448
0.00196401 1182.9774658679962 64 113.366769111 22.8176478714 158.342030284 -20.8055941882 151.0 0.0 50132 3258580
0.0257016 1200.0777685642242 65 101.891218234 21.5139339988 152.21256244 10.6277785019 151.0 0.0 50132 3308712
0.035666 1217.0094940662384 66 106.993209315 22.2765695381 153.008343057 -3.98400623564 151.0 0.0 50132 3358844
0.0267421 1233.9572584629059 67 116.750444257 23.0781954654 156.692886787 5.28665443411 151.0 0.0 50132 3408976
0.00536058 1252.9021184444427 68 107.992246665 36.3715297805 168.829405001 -14.5241811204 151.0 0.0 50132 3459108
0.0388299 1276.3621952533722 69 119.818148259 25.3014594114 164.534762626 -14.4663782028 151.0 0.0 50132 3509240
0.0289253 1296.22412276268 70 118.958933142 16.2935292019 158.573217925 45.1061127994 151.0 0.0 50132 3559372
0.00399954 1319.5692286491394 71 122.253037304 19.2025817564 166.385413012 45.5740948036 151.0 0.0 50132 3609504
-0.0025171 1336.4224970340729 72 133.059699773 23.6835090439 191.334367118 29.8291021627 151.0 0.0 50132 3659636
0.0254654 1353.2402832508087 73 129.887894452 27.2782072848 183.121149262 7.03850994806 151.0 0.0 50132 3709768
0.0378958 1370.1964020729065 74 131.436466745 25.9695131805 181.828270811 15.9956452175 151.0 0.0 50132 3759900
0.0287882 1387.1644208431244 75 137.462854549 21.213564358 181.657198203 13.5230592931 151.0 0.0 50132 3810032
0.0363687 1404.0474846363068 76 134.283955796 20.2636771391 187.253073008 29.5261382737 151.0 0.0 50132 3860164
0.0276075 1421.1449337005615 77 136.21439875 17.5353492814 184.462083085 76.9448736842 151.0 0.0 50132 3910296
0.0166955 1437.9838910102844 78 147.848918428 18.0620904164 193.859455075 40.651529847 151.0 0.0 50132 3960428
0.0121087 1454.828234910965 79 151.439633187 19.861722188 191.388273873 41.8960327984 151.0 0.0 50132 4010560
0.030101 1471.7287895679474 80 152.720079589 25.4702452017 202.231301104 -6.03768322686 151.0 0.0 50132 4060692
0.0331579 1488.5854642391205 81 152.109954982 22.7632641386 193.223533603 33.7299732257 151.0 0.0 50132 4110824
0.00135813 1505.4706330299377 82 157.323813746 19.8485591495 198.796394131 6.45282378137 151.0 0.0 50132 4160956
0.0423434 1522.3156311511993 83 152.527799863 19.5720795101 204.471543769 58.8893421734 151.0 0.0 50132 4211088
0.0253047 1539.0953946113586 84 154.654856521 22.7286714125 216.412050839 60.2356178898 151.0 0.0 50132 4261220
0.209883 1556.6230838298798 85 138.964597373 26.7855433292 197.007959878 26.0988262075 151.0 0.0 50132 4311352
0.0507359 1576.3277297019958 86 155.025858592 28.069273723 204.862363459 24.7556513974 151.0 0.0 50132 4361484
-0.151607 1593.2155303955078 87 142.980756837 29.1081306133 190.263756091 -27.3028635101 151.0 0.0 50132 4411616
0.0597955 1611.778851032257 88 127.859529801 38.5270466418 186.050405817 -29.7251590232 151.0 0.0 50132 4461748
0.0718467 1630.3496758937836 89 125.487502983 34.38721446 183.777501867 -13.2943008097 151.0 0.0 50132 4511880
0.00945624 1647.4859533309937 90 149.194999799 25.9601188005 212.143210583 11.5337576863 151.0 0.0 50132 4562012
0.0269386 1668.2153010368347 91 147.241223461 26.8564662814 207.567658497 26.0897613812 151.0 0.0 50132 4612144
0.0975457 1685.1769154071808 92 129.705021685 27.0230976014 177.503046355 5.77588939463 151.0 0.0 50132 4662276
0.0341558 1702.838742017746 93 134.968933171 24.2360338229 187.492442221 16.3165210175 151.0 0.0 50132 4712408
0.146843 1721.7922065258026 94 151.391529616 18.353520309 199.56123239 76.1616950038 151.0 0.0 50132 4762540
-0.070617 1739.300965309143 95 153.134481426 19.4791113047 199.244787185 42.8832644866 151.0 0.0 50132 4812672
0.0234003 1757.9904987812042 96 146.572508337 26.529475938 191.706583041 -15.5332168737 151.0 0.0 50132 4862804
0.0162911 1775.992045879364 97 146.041561919 31.7945806263 202.258060192 -30.044358145 151.0 0.0 50132 4912936
0.0659341 1794.1720831394196 98 136.124565595 29.6728462594 191.418251642 -10.8424923183 151.0 0.0 50132 4963068
0.0651561 1812.3902924060822 99 128.064240825 22.3645523068 174.156419102 31.9355341804 151.0 0.0 50132 5013200
================================================
FILE: hw2/data/HalfCheetah_b50000_rtg_na_25bl_HalfCheetah-v1_31-01-2018_19-35-00/11/params.json
================================================
{"animate" : false,
"env_name" : "HalfCheetah-v1",
"exp_name" : "HalfCheetah_b50000_rtg_na_25bl",
"gamma" : 0.9,
"learning_rate" : 0.025,
"logdir" : "data/HalfCheetah_b50000_rtg_na_25bl_HalfCheetah-v1_31-01-2018_19-35-00/11",
"max_path_length" : 150.0,
"min_timesteps_per_batch" : 50000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : true,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 11,
"size" : 32}
================================================
FILE: hw2/data/HalfCheetah_b50000_rtg_na_25bl_HalfCheetah-v1_31-01-2018_19-35-00/21/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.102255 25.70679473876953 0 -323.969673021 43.1211691714 -217.811784236 -472.659356681 151.0 0.0 50132 50132
0.0718359 42.85335898399353 1 -250.27580682 40.1936177359 -156.424604331 -374.707362593 151.0 0.0 50132 100264
0.0435652 59.91646480560303 2 -211.692384319 42.9265427551 -102.852937032 -352.736889921 151.0 0.0 50132 150396
0.026953 77.0094940662384 3 -188.875982318 43.8484870388 -83.3887182982 -319.687682358 151.0 0.0 50132 200528
0.0228926 94.11019897460938 4 -174.544094296 41.2176119966 -39.5838291301 -308.938616966 151.0 0.0 50132 250660
0.0197197 111.01148295402527 5 -167.771087918 37.3406721385 -77.1771885839 -276.662634771 151.0 0.0 50132 300792
0.0203707 127.54880833625793 6 -159.484659432 37.1298473241 -44.9099404577 -262.807247182 151.0 0.0 50132 350924
0.0203714 144.100172996521 7 -152.546285016 34.3399475656 -51.9027151929 -249.941427996 151.0 0.0 50132 401056
0.0213025 160.65814924240112 8 -148.334343787 33.0527210193 -50.6568253621 -257.001018225 151.0 0.0 50132 451188
0.0225206 177.2000379562378 9 -132.206156129 30.4062844509 -36.7580883033 -229.444688309 151.0 0.0 50132 501320
0.0210093 193.96677803993225 10 -123.431683276 28.1405986935 -37.1403380317 -235.797141132 151.0 0.0 50132 551452
0.0217689 211.28513169288635 11 -113.047048108 27.9222395298 -48.2442085882 -251.136819168 151.0 0.0 50132 601584
0.0236207 227.737380027771 12 -105.388254515 26.5204241642 -42.2873947152 -234.612112767 151.0 0.0 50132 651716
0.0204891 243.94443535804749 13 -98.0988877784 27.15046787 -26.9000314373 -233.693521394 151.0 0.0 50132 701848
0.0149134 260.25616121292114 14 -89.4653586628 22.947040142 -21.9975423918 -181.150584705 151.0 0.0 50132 751980
0.015993 276.4550313949585 15 -80.9568825201 23.8378058116 -14.3509826819 -181.321452913 151.0 0.0 50132 802112
0.0157254 292.6598074436188 16 -74.6336739486 26.3237757111 2.46803542256 -174.076436597 151.0 0.0 50132 852244
0.0158872 308.81813526153564 17 -70.850949906 25.678098135 1.15593412153 -153.042407926 151.0 0.0 50132 902376
0.0142792 324.9872281551361 18 -66.5133763792 25.5341598637 1.10210784721 -143.269514166 151.0 0.0 50132 952508
0.01619 341.1147994995117 19 -60.3243259469 25.444427888 36.596611818 -190.402268596 151.0 0.0 50132 1002640
0.0156251 357.30160903930664 20 -53.8180871352 24.239016034 15.7492563142 -169.296391319 151.0 0.0 50132 1052772
0.0137708 373.5174825191498 21 -51.55170019 24.6630451187 23.4155576904 -167.134562627 151.0 0.0 50132 1102904
0.0142438 389.690792798996 22 -45.5551235839 22.4433246618 13.3640874197 -148.185348854 151.0 0.0 50132 1153036
0.0143602 405.8326666355133 23 -43.9457356134 20.3547346281 12.6920359877 -117.680771557 151.0 0.0 50132 1203168
0.0155879 422.0374765396118 24 -42.9179297498 18.3397747538 10.1915958873 -105.586127798 151.0 0.0 50132 1253300
0.0204003 438.1307604312897 25 -40.3388933606 18.1256027294 20.4143013065 -111.281708383 151.0 0.0 50132 1303432
0.0255731 454.292268037796 26 -33.6774479916 17.4437129626 21.3489022474 -91.3885648604 151.0 0.0 50132 1353564
0.0140367 470.48041915893555 27 -30.6840460282 14.8707003227 16.4483022744 -70.811585945 151.0 0.0 50132 1403696
0.0133913 486.66046118736267 28 -28.3152501779 14.5460187026 16.1757897819 -84.9330387246 151.0 0.0 50132 1453828
0.0150401 502.7844190597534 29 -26.8132272684 13.5034840718 12.8957620058 -71.1787846657 151.0 0.0 50132 1503960
0.0159091 518.8856642246246 30 -23.8083704466 14.1947632241 11.9608637222 -67.3223615711 151.0 0.0 50132 1554092
0.0182149 535.0031504631042 31 -20.7848430514 13.0379433706 31.8350867446 -70.0749656611 151.0 0.0 50132 1604224
0.0214277 551.1289420127869 32 -18.3675213046 13.2768588224 21.5335140569 -57.4363776166 151.0 0.0 50132 1654356
0.0123329 567.297483921051 33 -14.0103907226 13.5160295985 26.7475426565 -69.2939908596 151.0 0.0 50132 1704488
0.0179343 583.4274439811707 34 -12.4618964833 14.0772799483 14.4490440327 -62.2395811357 151.0 0.0 50132 1754620
0.0140565 599.5822839736938 35 -8.32411653353 13.9311029153 27.8670320248 -63.1880865031 151.0 0.0 50132 1804752
0.016101 615.7283067703247 36 -4.76575933409 14.9172887945 34.1090437139 -68.2811508459 151.0 0.0 50132 1854884
0.0159986 631.8710033893585 37 -0.846634538965 14.3527046952 31.9478789707 -48.2931346211 151.0 0.0 50132 1905016
0.0131352 647.9776313304901 38 6.66422018579 16.5929490783 43.6131263883 -62.0069955394 151.0 0.0 50132 1955148
0.0149884 664.0657420158386 39 10.8310135299 21.5580188082 53.4050203982 -76.6274250649 151.0 0.0 50132 2005280
0.0133125 680.1107017993927 40 14.8660972496 24.4449729926 63.9009317675 -108.881512104 151.0 0.0 50132 2055412
0.0151188 696.1627497673035 41 23.1667380124 21.9864323198 69.2704215861 -69.6767194088 151.0 0.0 50132 2105544
0.0144031 712.1865272521973 42 23.7011563519 28.6488370844 74.0668269084 -91.4865969773 151.0 0.0 50132 2155676
0.0230641 728.2595946788788 43 29.6903315333 26.445817871 85.4311855333 -70.6201135742 151.0 0.0 50132 2205808
0.0330029 744.2708251476288 44 34.8996347338 24.533056575 83.5357651963 -82.8109500333 151.0 0.0 50132 2255940
0.0152059 760.3170561790466 45 35.7263670174 23.4637735099 86.4952645798 -76.2326316108 151.0 0.0 50132 2306072
0.0268034 776.377941608429 46 42.1218530537 22.9748166419 91.4909521042 -78.9933552093 151.0 0.0 50132 2356204
0.0162035 792.4250874519348 47 43.889804171 27.2636028428 94.0750157397 -68.602567579 151.0 0.0 50132 2406336
0.0163368 808.8426806926727 48 44.7562404424 33.0763994267 109.239524884 -69.8231436181 151.0 0.0 50132 2456468
0.0308516 825.3182489871979 49 54.6337905603 32.6978476247 105.288561197 -69.2987236584 151.0 0.0 50132 2506600
0.0241431 841.5765602588654 50 58.9986152298 26.4014086158 121.081281687 -51.5185729953 151.0 0.0 50132 2556732
0.021702 857.894558429718 51 58.1795111332 23.6259701738 108.012422855 -46.4501184846 151.0 0.0 50132 2606864
0.0199002 873.9185883998871 52 59.7864584712 22.9908694071 111.933247601 -56.1759173409 151.0 0.0 50132 2656996
0.0266708 889.9072835445404 53 72.8960772825 21.2535299426 117.789043563 -43.0505662623 151.0 0.0 50132 2707128
0.0209752 905.854489326477 54 79.6919922396 25.3710036598 129.299555008 -46.8741768659 151.0 0.0 50132 2757260
0.0210029 921.8397271633148 55 76.5678888021 33.7933325393 132.949564083 -55.9922751254 151.0 0.0 50132 2807392
0.0228996 937.8692770004272 56 68.508640693 35.1560415122 124.522167635 -61.2194289418 151.0 0.0 50132 2857524
0.05528 953.9288382530212 57 66.0477123406 28.7872587295 131.369078599 -46.5718718896 151.0 0.0 50132 2907656
0.0420829 969.8998148441315 58 73.7220115476 19.4707475593 119.384121605 0.515974206919 151.0 0.0 50132 2957788
0.0325335 985.8666784763336 59 86.8149087823 21.4657180367 147.9180831 -8.99830459291 151.0 0.0 50132 3007920
0.00410522 1001.8111519813538 60 99.3138106975 20.774695375 144.681356625 -8.10624391235 151.0 0.0 50132 3058052
0.0114449 1017.7370657920837 61 98.3421971169 27.3775953935 140.450383548 -26.6840265504 151.0 0.0 50132 3108184
0.0944026 1033.7344601154327 62 93.1629008936 34.7118301181 141.069634442 -37.487192472 151.0 0.0 50132 3158316
0.0596393 1049.660225391388 63 103.957806283 28.2253049919 142.375389778 -29.4456424345 151.0 0.0 50132 3208448
0.0266865 1065.54434132576 64 107.274604237 23.8590676332 144.963016754 -18.1222261813 151.0 0.0 50132 3258580
0.0198457 1081.4847359657288 65 108.701044317 19.7778646222 149.205726045 -19.8966574521 151.0 0.0 50132 3308712
0.0384747 1097.3906419277191 66 114.264637926 17.8230535463 156.360585072 18.7021231799 151.0 0.0 50132 3358844
0.0277865 1113.3256862163544 67 120.474405171 20.1692552051 167.083537244 18.3312619966 151.0 0.0 50132 3408976
0.143776 1129.2098016738892 68 116.423750256 22.1935147692 166.015400599 22.4382833843 151.0 0.0 50132 3459108
0.0200211 1145.2448682785034 69 115.515474841 28.1035450734 165.126234972 -0.670809441993 151.0 0.0 50132 3509240
0.0901678 1161.1808726787567 70 122.691701527 20.0957039741 165.942393894 24.6172318293 151.0 0.0 50132 3559372
0.0515626 1177.0716366767883 71 119.741289628 18.542192245 162.816997271 22.8979288109 151.0 0.0 50132 3609504
0.0216305 1192.9946014881134 72 119.253601648 14.4973023425 153.166738005 27.4342175452 151.0 0.0 50132 3659636
0.00866893 1208.887521982193 73 127.805758594 17.7487036426 171.467227092 52.4729986828 151.0 0.0 50132 3709768
0.0404077 1224.8040578365326 74 131.761632754 24.6841543941 180.883252508 -1.72452677977 151.0 0.0 50132 3759900
0.0289831 1240.7240166664124 75 138.543600374 24.6644739572 192.873929705 39.8066315724 151.0 0.0 50132 3810032
0.024745 1256.5996561050415 76 139.112191065 24.0078266343 199.800306519 -16.2100125198 151.0 0.0 50132 3860164
0.0253608 1272.4813752174377 77 136.343215269 28.0751326835 193.314465817 -16.4726678741 151.0 0.0 50132 3910296
0.0258509 1288.3132491111755 78 135.525932112 25.7890004981 196.866017985 -21.3685099615 151.0 0.0 50132 3960428
0.0300737 1304.2520060539246 79 145.862719115 20.2253936598 188.853754882 42.5244451034 151.0 0.0 50132 4010560
0.0223602 1320.219141960144 80 147.177975689 25.1961125966 196.503986966 -19.3069965066 151.0 0.0 50132 4060692
0.0367636 1336.2501208782196 81 131.345400948 44.4840618872 192.184920074 -34.4540549913 151.0 0.0 50132 4110824
0.0406775 1352.2665147781372 82 127.77501305 51.8557140199 199.352991085 -37.4636368382 151.0 0.0 50132 4160956
-0.0077692 1368.2241833209991 83 147.726069939 28.6886626731 204.624845761 -11.9716458347 151.0 0.0 50132 4211088
-0.043617 1384.1780722141266 84 154.528153399 20.3905168874 199.045802437 67.6875360231 151.0 0.0 50132 4261220
-0.019866 1400.1033561229706 85 154.433144883 22.228242372 202.50099925 40.5043530744 151.0 0.0 50132 4311352
0.0238131 1415.9775621891022 86 154.651550929 21.2147744236 224.480479495 40.5992400976 151.0 0.0 50132 4361484
0.00343529 1431.8327820301056 87 157.761814048 18.1808725956 208.392225681 82.1925561271 151.0 0.0 50132 4411616
-0.00244395 1447.7117676734924 88 160.445862764 19.5062224268 206.999202814 74.4782152449 151.0 0.0 50132 4461748
0.0528812 1463.596872806549 89 160.386689119 23.1501666331 211.408343845 9.09378989967 151.0 0.0 50132 4511880
0.0344855 1479.5526022911072 90 149.895101373 22.9329635835 199.304230206 39.2703671724 151.0 0.0 50132 4562012
0.00789516 1495.5338101387024 91 160.676660258 18.2853667056 208.600834902 91.7438790128 151.0 0.0 50132 4612144
0.0565331 1511.4780023097992 92 165.268686187 16.439704144 207.552721623 99.366429248 151.0 0.0 50132 4662276
0.0195069 1527.3645250797272 93 163.099531936 18.9345012753 210.435798978 97.9324245657 151.0 0.0 50132 4712408
0.0201567 1543.2536556720734 94 163.690341008 19.8303935404 211.5204182 72.8971792427 151.0 0.0 50132 4762540
0.0578299 1559.1140539646149 95 166.319303534 21.1021512464 225.583249453 23.0924826496 151.0 0.0 50132 4812672
-0.0281224 1575.030605316162 96 165.501761168 18.9318046148 219.171207163 66.5306777305 151.0 0.0 50132 4862804
0.0629756 1590.9852712154388 97 156.530854022 24.887882918 208.232027537 -12.7468570691 151.0 0.0 50132 4912936
0.00399466 1606.9721901416779 98 145.083674598 26.8406610254 190.727577801 4.9207258872 151.0 0.0 50132 4963068
0.0460498 1622.927895307541 99 149.925630217 26.7623627599 197.210988875 -27.3056911812 151.0 0.0 50132 5013200
================================================
FILE: hw2/data/HalfCheetah_b50000_rtg_na_25bl_HalfCheetah-v1_31-01-2018_19-35-00/21/params.json
================================================
{"animate" : false,
"env_name" : "HalfCheetah-v1",
"exp_name" : "HalfCheetah_b50000_rtg_na_25bl",
"gamma" : 0.9,
"learning_rate" : 0.025,
"logdir" : "data/HalfCheetah_b50000_rtg_na_25bl_HalfCheetah-v1_31-01-2018_19-35-00/21",
"max_path_length" : 150.0,
"min_timesteps_per_batch" : 50000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : true,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 21,
"size" : 32}
================================================
FILE: hw2/data/HalfCheetah_b50000_rtg_na_25bl_HalfCheetah-v1_31-01-2018_19-35-00/31/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.137417 21.064739227294922 0 -190.897240893 46.6089352185 -27.2258743391 -372.279547816 151.0 0.0 50132 50132
0.0548721 37.01219916343689 1 -140.687068262 37.5550347376 -15.4241633182 -347.560100712 151.0 0.0 50132 100264
0.0254206 52.98334240913391 2 -113.443101657 34.0651847357 6.5220181492 -226.412047749 151.0 0.0 50132 150396
0.0229544 68.96394920349121 3 -105.550082432 33.0630189002 -11.4026858985 -272.110759389 151.0 0.0 50132 200528
0.0215282 84.92519497871399 4 -100.724926887 29.7726846102 -25.4093405734 -220.793134011 151.0 0.0 50132 250660
0.0358222 100.9263162612915 5 -95.3767389644 30.6686572264 -22.3396122994 -213.260223785 151.0 0.0 50132 300792
0.0333784 116.99193334579468 6 -85.999404569 30.0432932559 -2.8104806923 -190.148792127 151.0 0.0 50132 350924
0.0253062 133.03315663337708 7 -72.1831591657 30.5999142771 17.7072532409 -200.888970509 151.0 0.0 50132 401056
0.0263611 149.11539363861084 8 -62.3333370128 30.3892770612 9.6332473869 -149.657489918 151.0 0.0 50132 451188
0.0255504 165.21782279014587 9 -57.4430553633 30.8875057162 18.7988287752 -183.82465023 151.0 0.0 50132 501320
0.0260348 181.41210007667542 10 -52.7501158126 25.3706754653 9.88592885505 -142.767834982 151.0 0.0 50132 551452
0.0201632 197.60471081733704 11 -51.2299891808 25.5608389428 19.5304245515 -141.964951906 151.0 0.0 50132 601584
0.015544 213.8857123851776 12 -47.3960241402 22.4114420524 26.3482275294 -132.262491589 151.0 0.0 50132 651716
0.0227444 230.15306186676025 13 -43.0149192138 20.9134460855 15.5373348516 -105.819302002 151.0 0.0 50132 701848
0.0270518 246.42102670669556 14 -38.7075874201 21.1408371093 16.2063365962 -131.815378584 151.0 0.0 50132 751980
0.0172788 262.65814113616943 15 -31.2693537199 18.7788736951 9.01618803073 -95.9511355041 151.0 0.0 50132 802112
0.0234184 278.8505423069 16 -29.0126709299 21.0707990403 28.2062867717 -125.234625004 151.0 0.0 50132 852244
0.0141834 294.98457193374634 17 -28.4471979452 19.7859834242 30.174272082 -117.61103905 151.0 0.0 50132 902376
0.0166277 311.05715465545654 18 -22.2930285644 19.1015513297 32.3666313002 -95.1723354391 151.0 0.0 50132 952508
0.0125452 327.1181809902191 19 -23.9325267928 19.8857207975 64.9427207886 -102.838066938 151.0 0.0 50132 1002640
0.0189832 343.1677055358887 20 -20.8642412711 20.2847755858 45.3923779366 -86.0235282556 151.0 0.0 50132 1052772
0.013688 359.22139048576355 21 -19.3619143454 19.4877900823 45.6431997911 -110.105098728 151.0 0.0 50132 1102904
0.0125831 375.23385977745056 22 -17.8529041217 19.9704261934 45.9422125709 -91.4852726421 151.0 0.0 50132 1153036
0.0162405 391.25556445121765 23 -14.5962164577 18.1935978051 42.2348051417 -107.280705997 151.0 0.0 50132 1203168
0.0202018 407.3027181625366 24 -13.1290494069 18.0261722097 34.4999885246 -62.8706914659 151.0 0.0 50132 1253300
0.0125985 423.3434066772461 25 -9.11078535316 16.4889916967 37.3181087863 -68.8006536647 151.0 0.0 50132 1303432
0.0200693 439.427223443985 26 -5.98068360088 15.7397560912 33.6409458905 -59.202459919 151.0 0.0 50132 1353564
0.0182452 455.47803831100464 27 -3.80501670307 15.1027528677 39.6468017656 -59.7213575001 151.0 0.0 50132 1403696
0.0243192 471.5159430503845 28 -2.45456027794 16.4637145066 33.5793841049 -60.4364516043 151.0 0.0 50132 1453828
0.0172235 487.513060092926 29 0.397111874907 15.7741482805 43.0901944993 -62.7576281623 151.0 0.0 50132 1503960
0.0181344 503.5424602031708 30 4.13516144519 17.4775060875 51.5956691576 -60.8039150411 151.0 0.0 50132 1554092
0.0219125 519.5819807052612 31 9.50153589248 18.5738665156 44.169005618 -63.324388225 151.0 0.0 50132 1604224
0.0157505 535.6305468082428 32 16.1005977172 20.6026930298 58.0264111574 -70.9330947236 151.0 0.0 50132 1654356
-0.005294 551.6901745796204 33 24.9695532164 21.1432296201 82.9368017193 -43.9526836755 151.0 0.0 50132 1704488
-0.00591889 567.7029840946198 34 31.7967625286 24.0974367746 79.0996233926 -54.2324659506 151.0 0.0 50132 1754620
0.0044767 583.6846339702606 35 36.7059585589 23.7288604499 89.4803002521 -67.4458974113 151.0 0.0 50132 1804752
0.0128981 599.671145439148 36 36.7625442245 26.081213187 99.9900685996 -57.6794475541 151.0 0.0 50132 1854884
0.0192258 615.6673228740692 37 41.0395612631 20.3254110718 93.4537018014 -23.2376133829 151.0 0.0 50132 1905016
0.0185188 631.6752853393555 38 45.4456976307 19.6714241482 104.124720889 -19.8603178666 151.0 0.0 50132 1955148
0.0228116 647.7017242908478 39 50.9457191851 19.3041116212 103.358485316 -16.1255487068 151.0 0.0 50132 2005280
0.0180701 663.755931854248 40 57.6866521229 21.7429541533 111.104701745 -32.1495732232 151.0 0.0 50132 2055412
0.0106462 679.7545435428619 41 65.3190478679 26.0372874473 116.342681955 -29.6507731649 151.0 0.0 50132 2105544
0.00469465 695.7248232364655 42 71.2761746527 27.0363985822 117.515091394 -22.5523999252 151.0 0.0 50132 2155676
0.0160797 711.6601173877716 43 80.6191865677 23.4371856629 129.832033136 -19.3377565008 151.0 0.0 50132 2205808
0.0163915 727.5960166454315 44 84.6768397483 24.5951832231 128.871368921 -17.4015387765 151.0 0.0 50132 2255940
0.0139268 743.5306708812714 45 86.0862117043 22.8650820411 128.747166869 -23.8155350137 151.0 0.0 50132 2306072
0.0137846 759.4366879463196 46 87.2088382449 22.7556186433 135.253044616 -5.87497609026 151.0 0.0 50132 2356204
0.0203777 775.3622851371765 47 88.3591791027 23.0475673916 142.627940218 -16.762946082 151.0 0.0 50132 2406336
0.0268116 791.2670509815216 48 91.0385866577 21.9926116962 136.526814219 -24.6036446253 151.0 0.0 50132 2456468
0.0257699 807.2021043300629 49 99.9906003041 22.9885674879 149.712585927 12.6479903912 151.0 0.0 50132 2506600
0.0217925 823.1649551391602 50 104.611142617 22.0755950715 151.034175448 -26.934059419 151.0 0.0 50132 2556732
0.0261802 839.4466128349304 51 106.218069624 22.5821631552 147.519430053 0.986892782937 151.0 0.0 50132 2606864
0.0204284 855.4352321624756 52 107.626738118 25.2706140748 147.806524856 -22.2732395798 151.0 0.0 50132 2656996
0.0320903 871.473474740982 53 104.53489423 30.1239150721 166.368379604 -8.60838109098 151.0 0.0 50132 2707128
0.0100599 887.474080324173 54 105.658615772 31.2614493293 162.987306642 -32.1394791563 151.0 0.0 50132 2757260
0.0107538 903.4120011329651 55 105.896688067 30.2527260044 165.584853701 -8.81360683908 151.0 0.0 50132 2807392
0.022464 919.3731837272644 56 105.32372695 34.6778233199 167.041198655 -40.077478116 151.0 0.0 50132 2857524
0.0321536 935.292423248291 57 116.312775875 26.8671333107 172.506968886 13.7994565857 151.0 0.0 50132 2907656
0.0353605 951.2215664386749 58 122.264585082 22.8301050567 165.951528707 14.7650316181 151.0 0.0 50132 2957788
-0.0119476 967.1317303180695 59 124.32549326 26.5050807841 170.429519205 1.95642025583 151.0 0.0 50132 3007920
-0.0143712 983.0468466281891 60 120.569354417 27.7430991638 172.523001202 -3.79190992541 151.0 0.0 50132 3058052
-0.0167701 998.9787476062775 61 121.200116812 24.4472005983 160.563812104 5.74553897134 151.0 0.0 50132 3108184
0.0276545 1014.8646898269653 62 117.285467142 22.3092820979 156.194329845 -31.5740898392 151.0 0.0 50132 3158316
0.0691551 1030.7945408821106 63 119.735544482 24.3995869152 165.593272125 10.8347979966 151.0 0.0 50132 3208448
0.0366182 1046.7075304985046 64 120.829524317 28.580546142 173.049784169 -5.68561368214 151.0 0.0 50132 3258580
0.0370144 1062.6959280967712 65 112.524071897 23.8027319316 165.804496396 31.2370132772 151.0 0.0 50132 3308712
0.0410086 1078.6244604587555 66 119.44230413 25.836517742 175.575571767 38.8972999883 151.0 0.0 50132 3358844
0.0946967 1094.5336291790009 67 135.399392361 22.4698488347 193.159269423 54.4406988058 151.0 0.0 50132 3408976
-0.110919 1110.4563348293304 68 136.510087407 23.9653281527 213.377574093 37.065811337 151.0 0.0 50132 3459108
-0.0295646 1126.4224982261658 69 124.864810199 17.1312447219 175.76342357 27.0759522219 151.0 0.0 50132 3509240
0.00613683 1142.4214551448822 70 123.843163252 17.3028488197 162.86355707 44.2659596417 151.0 0.0 50132 3559372
0.0318044 1158.3676855564117 71 123.05398977 18.5697683321 163.464111825 40.0986141339 151.0 0.0 50132 3609504
-0.0080424 1174.3955261707306 72 126.986674957 15.3685943703 158.887686276 56.0884548705 151.0 0.0 50132 3659636
0.0310976 1190.3974478244781 73 123.018958227 30.5229205001 166.095622963 -46.7811467477 151.0 0.0 50132 3709768
-0.000173947 1206.3737201690674 74 128.834892594 33.0510381498 185.451717526 1.05212078254 151.0 0.0 50132 3759900
0.0503898 1222.3190937042236 75 108.135696171 30.193786233 175.333513676 5.06389558324 151.0 0.0 50132 3810032
0.0605938 1238.2503597736359 76 127.366785702 28.638840751 195.951592661 11.3634381923 151.0 0.0 50132 3860164
7.23675e-05 1254.1596319675446 77 146.785480524 28.9668171373 194.432402821 -16.7274724239 151.0 0.0 50132 3910296
0.0877231 1270.0584568977356 78 144.385623936 30.2308058821 192.418453892 -1.52514026908 151.0 0.0 50132 3960428
-0.00821127 1285.9651894569397 79 141.063429493 31.0539604671 193.28060745 6.04300520934 151.0 0.0 50132 4010560
-0.0067739 1301.8844435214996 80 144.245392853 32.0111066051 208.416420987 -17.3969057581 151.0 0.0 50132 4060692
0.0179708 1317.7896411418915 81 145.15146033 28.8281195075 199.236234651 -6.10514908489 151.0 0.0 50132 4110824
0.0915122 1333.6866042613983 82 146.28937227 29.2069902817 201.807066435 -5.158123083 151.0 0.0 50132 4160956
0.062984 1349.6002659797668 83 139.017868502 33.2192232155 208.0613458 -6.15201574544 151.0 0.0 50132 4211088
0.059793 1365.5366797447205 84 126.864133614 40.4792665584 196.544770556 -7.3524048053 151.0 0.0 50132 4261220
0.0496565 1381.4220111370087 85 128.052448353 35.77401687 194.236839139 -7.35784445802 151.0 0.0 50132 4311352
0.0478142 1397.2881262302399 86 134.963429725 26.6651546718 194.454548263 5.70977726239 151.0 0.0 50132 4361484
0.0924642 1413.1531331539154 87 136.213102083 25.9502107517 191.550277921 7.42879903451 151.0 0.0 50132 4411616
-0.00198442 1428.998836517334 88 147.565589072 24.0131481892 201.679760648 13.513128648 151.0 0.0 50132 4461748
-0.0310461 1444.8442780971527 89 156.948905202 22.6537496866 217.69771094 37.6546074469 151.0 0.0 50132 4511880
0.0500035 1460.7586226463318 90 158.064444312 26.6572565049 209.557967109 34.3832976218 151.0 0.0 50132 4562012
0.0319117 1476.6869475841522 91 164.103193677 29.3934628212 218.489585414 25.8229741521 151.0 0.0 50132 4612144
0.018292 1492.6327545642853 92 154.910139111 27.5757373039 209.881530496 14.6025504371 151.0 0.0 50132 4662276
0.0548965 1508.5741333961487 93 160.094527516 34.2672127714 220.856103055 3.59092864054 151.0 0.0 50132 4712408
-0.02815 1524.54474568367 94 169.125404351 30.3557143004 221.326089617 34.2464946659 151.0 0.0 50132 4762540
0.0105981 1540.5418820381165 95 172.517137357 24.74626262 216.631143465 3.85256406492 151.0 0.0 50132 4812672
0.034569 1556.4314408302307 96 170.725648839 24.7441750658 221.565513713 0.620424055449 151.0 0.0 50132 4862804
0.0150373 1572.3306019306183 97 170.558405329 22.5123383908 220.845101031 24.5149662247 151.0 0.0 50132 4912936
0.0321328 1588.204396724701 98 173.092370678 26.0050740862 224.217380234 21.99377081 151.0 0.0 50132 4963068
0.0411354 1604.059950351715 99 177.459250372 22.9436883216 223.817000099 78.6554298667 151.0 0.0 50132 5013200
================================================
FILE: hw2/data/HalfCheetah_b50000_rtg_na_25bl_HalfCheetah-v1_31-01-2018_19-35-00/31/params.json
================================================
{"animate" : false,
"env_name" : "HalfCheetah-v1",
"exp_name" : "HalfCheetah_b50000_rtg_na_25bl",
"gamma" : 0.9,
"learning_rate" : 0.025,
"logdir" : "data/HalfCheetah_b50000_rtg_na_25bl_HalfCheetah-v1_31-01-2018_19-35-00/31",
"max_path_length" : 150.0,
"min_timesteps_per_batch" : 50000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : true,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 31,
"size" : 32}
================================================
FILE: hw2/data/HalfCheetah_b50000_rtg_na_25bl_HalfCheetah-v1_31-01-2018_19-35-00/41/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.12708 21.07270121574402 0 -220.923293543 41.8852142808 -84.9146953094 -365.906994022 151.0 0.0 50132 50132
0.0828835 36.975881814956665 1 -152.368270919 39.6479378083 -22.9116375258 -283.23569561 151.0 0.0 50132 100264
0.0541419 52.87936806678772 2 -114.866907633 38.2358158574 -6.42254067536 -256.0310684 151.0 0.0 50132 150396
0.0277502 68.8259904384613 3 -94.8193382495 36.6486287629 7.19623192755 -199.112537248 151.0 0.0 50132 200528
0.0162455 84.75660634040833 4 -91.404183621 31.5728078088 -0.122650228138 -197.039697753 151.0 0.0 50132 250660
0.0239755 100.7247838973999 5 -85.8920768798 28.9281341705 5.42222038764 -170.248391172 151.0 0.0 50132 300792
0.0262909 116.67663073539734 6 -79.5540397663 31.4061724845 -9.69072756 -200.215836372 151.0 0.0 50132 350924
0.027545 132.68261218070984 7 -71.5500120659 27.4276084428 13.3135340861 -173.290089517 151.0 0.0 50132 401056
0.0249774 148.73846530914307 8 -61.4299746673 28.860293709 19.6304159498 -163.082549169 151.0 0.0 50132 451188
0.0244535 164.80112862586975 9 -52.9705518414 28.522470284 49.8972559042 -156.563903992 151.0 0.0 50132 501320
0.0227323 180.86191201210022 10 -51.8480606971 26.5960537989 16.4989694823 -152.835243066 151.0 0.0 50132 551452
0.0238927 196.9472119808197 11 -50.1130165535 26.0689582863 37.1180119778 -121.637885079 151.0 0.0 50132 601584
0.0207184 213.1076855659485 12 -46.9240699581 22.3102127087 22.8842104682 -102.635826569 151.0 0.0 50132 651716
0.019643 229.25678372383118 13 -41.825285099 21.707630837 18.0107051749 -120.668560988 151.0 0.0 50132 701848
0.0155793 245.43969988822937 14 -36.2214581322 19.107626561 21.4518346061 -91.1213900714 151.0 0.0 50132 751980
0.0154737 261.58561658859253 15 -31.1491137562 19.9187426527 37.4903697888 -91.0116023285 151.0 0.0 50132 802112
0.0117041 277.74159717559814 16 -29.3128868326 18.6327247978 20.5705600009 -95.1644777332 151.0 0.0 50132 852244
0.0145751 293.88827538490295 17 -26.3793280215 20.6436833015 29.5633176691 -98.1250890621 151.0 0.0 50132 902376
0.0164439 310.3397397994995 18 -23.853876261 18.6645127205 19.4776324886 -102.910120506 151.0 0.0 50132 952508
0.0193119 326.73000836372375 19 -21.5594629322 17.8896655289 31.4067387932 -82.5182753938 151.0 0.0 50132 1002640
0.0175859 343.23356652259827 20 -18.498051078 17.2768930112 26.4530861336 -108.945833152 151.0 0.0 50132 1052772
0.026074 359.85977363586426 21 -16.6607530155 16.1084689108 44.595963184 -74.5210111382 151.0 0.0 50132 1102904
0.0221995 376.271719455719 22 -12.1129743153 16.1414910866 40.9557563369 -69.1437662123 151.0 0.0 50132 1153036
0.018561 392.67700958251953 23 -8.28632810328 15.9856287639 29.7609416178 -84.2809059242 151.0 0.0 50132 1203168
0.0140461 409.49606704711914 24 -4.71828370599 17.7622847842 56.5155861545 -79.4748900298 151.0 0.0 50132 1253300
0.0139689 425.8870892524719 25 -0.160263681851 16.996391833 43.9362404463 -64.0432616135 151.0 0.0 50132 1303432
0.0211519 442.1293981075287 26 3.39413040279 17.0561480412 48.7308724988 -57.7461385642 151.0 0.0 50132 1353564
0.018658 458.2996304035187 27 10.1604726403 16.8217040873 59.9784910839 -49.9519879026 151.0 0.0 50132 1403696
0.0138661 474.45201563835144 28 11.70998111 15.5889152149 58.0373833058 -35.9967093066 151.0 0.0 50132 1453828
0.015394 490.58042645454407 29 12.6324075463 15.3203529395 55.5502179713 -39.2071382881 151.0 0.0 50132 1503960
0.0230869 506.73017859458923 30 13.264358341 13.9385575392 68.7895095886 -30.1707473872 151.0 0.0 50132 1554092
0.0315863 522.8333723545074 31 19.1102750828 16.5549311779 66.3593414584 -65.2065182421 151.0 0.0 50132 1604224
0.00591601 538.9353394508362 32 29.6801084263 19.9664266463 75.302475314 -31.1851161586 151.0 0.0 50132 1654356
0.00235279 555.0165634155273 33 34.9358966389 24.1271391133 83.3020348805 -52.312587542 151.0 0.0 50132 1704488
0.0128948 571.0490593910217 34 40.3295941214 25.405476514 97.4659655494 -38.1299446801 151.0 0.0 50132 1754620
0.01702 587.1206603050232 35 45.4784098084 27.4554448471 102.602926817 -52.759024737 151.0 0.0 50132 1804752
0.00378656 603.1493413448334 36 49.8221469528 25.2981552597 98.8910932274 -38.8901626401 151.0 0.0 50132 1854884
0.0171225 619.1681020259857 37 52.6877079053 24.5837952235 104.609912348 -33.7148520043 151.0 0.0 50132 1905016
0.010039 635.2099323272705 38 55.3098856299 25.3984565006 97.458672425 -65.2413630983 151.0 0.0 50132 1955148
0.00850409 651.2657423019409 39 60.3025958911 26.6330333061 112.973069882 -38.7426859855 151.0 0.0 50132 2005280
0.0193669 667.2855832576752 40 66.8110061639 28.1214823154 126.114862883 -48.5702787866 151.0 0.0 50132 2055412
0.00486695 683.2934782505035 41 81.0035491191 26.9163143154 139.81491947 -27.0794689436 151.0 0.0 50132 2105544
0.00273382 699.2686598300934 42 85.7973019526 25.2992905599 135.911682186 -22.1127843511 151.0 0.0 50132 2155676
0.0102085 715.3002729415894 43 88.6107577173 26.5906177042 139.137772247 -19.5933510368 151.0 0.0 50132 2205808
0.00499843 731.3660926818848 44 87.1463180729 29.5942594498 137.851244223 -6.74959245858 151.0 0.0 50132 2255940
0.0277139 747.3739247322083 45 96.4381236548 25.3673564432 152.283941822 -25.3621564773 151.0 0.0 50132 2306072
0.0105407 763.3241529464722 46 100.186901199 24.5900919696 147.788789965 -16.9339933999 151.0 0.0 50132 2356204
0.0196431 779.3152277469635 47 101.332158321 19.2262274975 146.800582961 -23.2174938978 151.0 0.0 50132 2406336
0.00635867 795.3148963451385 48 106.501908075 25.2635106471 156.469493534 -20.7997518503 151.0 0.0 50132 2456468
0.0186458 811.2650392055511 49 107.974479572 25.478450392 153.289817991 -48.7780446696 151.0 0.0 50132 2506600
0.0111561 827.2407681941986 50 112.743347089 27.0198518045 162.030034891 -4.59662986033 151.0 0.0 50132 2556732
0.0205485 843.2783930301666 51 113.635470199 26.2936585283 163.802731554 11.1848641882 151.0 0.0 50132 2606864
0.00409291 859.2426459789276 52 115.34929309 29.343268563 170.435470171 -14.1801635789 151.0 0.0 50132 2656996
0.0106318 875.241016626358 53 116.195418488 31.1474951786 170.72265754 -2.41219586455 151.0 0.0 50132 2707128
0.0295054 891.2339463233948 54 116.788771949 26.0913063734 166.742123953 -4.31214301717 151.0 0.0 50132 2757260
0.0388965 907.2292096614838 55 124.827516243 22.8057192384 163.644975689 22.332689543 151.0 0.0 50132 2807392
0.0466941 923.2126085758209 56 134.472299284 22.9366132876 187.301125596 -23.6476558021 151.0 0.0 50132 2857524
0.0175752 939.1847531795502 57 130.700796534 31.5085679302 184.161942597 -15.3740634266 151.0 0.0 50132 2907656
0.0518835 955.1277551651001 58 132.321929808 34.3173247971 196.362167654 2.769473853 151.0 0.0 50132 2957788
0.0253744 971.2207598686218 59 137.906631678 30.1028870468 195.470557578 -0.326238371907 151.0 0.0 50132 3007920
0.0113437 987.234326839447 60 129.550997372 31.2339428421 179.166674367 0.819867278957 151.0 0.0 50132 3058052
0.0529975 1003.226350069046 61 124.037113408 25.8421159375 178.068351646 -9.49730122666 151.0 0.0 50132 3108184
0.00839074 1019.136340379715 62 142.346288249 28.6768034112 203.388516326 -11.4114011496 151.0 0.0 50132 3158316
0.0129732 1035.1205027103424 63 153.747901709 28.4112073031 203.734756138 -15.0993184067 151.0 0.0 50132 3208448
0.0162256 1051.0646121501923 64 144.399488384 23.7115014096 199.629631592 30.7307788076 151.0 0.0 50132 3258580
0.0649607 1067.0842497348785 65 133.729870392 21.7004689094 183.116755547 53.1446101439 151.0 0.0 50132 3308712
0.0375514 1083.0518975257874 66 148.576177426 17.0274998644 193.10616678 84.30155934 151.0 0.0 50132 3358844
0.0200252 1099.0055470466614 67 158.469828362 18.2338566601 207.738006256 43.6628336487 151.0 0.0 50132 3408976
-0.00331602 1114.9424951076508 68 158.264754595 21.2759091457 207.498901777 30.033308789 151.0 0.0 50132 3459108
0.00842844 1130.846292257309 69 151.0246263 24.2069982233 202.952190252 46.2487258606 151.0 0.0 50132 3509240
0.0422203 1146.7755208015442 70 154.319072567 26.4719532924 210.722339317 10.8817028456 151.0 0.0 50132 3559372
-0.0224658 1162.715653181076 71 160.935713817 27.6417918042 216.054729911 7.33029723716 151.0 0.0 50132 3609504
-0.00407064 1178.625952720642 72 157.529412134 26.4469426963 209.245472196 43.3499755084 151.0 0.0 50132 3659636
0.0312973 1194.5514740943909 73 152.999458578 33.1020789767 227.212425053 -8.93640639293 151.0 0.0 50132 3709768
-0.0102214 1210.4479343891144 74 156.461508201 25.5975478631 213.830874542 30.3287995339 151.0 0.0 50132 3759900
0.0268055 1226.378385066986 75 149.509954537 26.2837276067 211.832369072 -9.17958865547 151.0 0.0 50132 3810032
-0.0407771 1242.2990992069244 76 152.426630167 24.7909814718 208.919701534 10.0289425916 151.0 0.0 50132 3860164
0.311808 1258.2240889072418 77 127.806972193 19.7946826021 178.881778739 26.7269463047 151.0 0.0 50132 3910296
0.0462513 1274.0994503498077 78 153.88212704 20.0611854975 195.76003036 83.1346760376 151.0 0.0 50132 3960428
-0.0130791 1289.971929550171 79 155.123372645 23.9776277466 209.070200201 52.6926327132 151.0 0.0 50132 4010560
-0.0223044 1305.9302129745483 80 153.535803604 29.2030884149 205.026440956 -7.29082282524 151.0 0.0 50132 4060692
0.0300717 1321.8447451591492 81 138.520845632 38.9659452841 207.954292892 15.2333249848 151.0 0.0 50132 4110824
0.116867 1337.782033920288 82 146.044282625 33.6667796301 206.538708981 14.9616932891 151.0 0.0 50132 4160956
0.0752258 1353.6613144874573 83 152.455908379 27.7847639984 211.808457349 45.1002907526 151.0 0.0 50132 4211088
0.021047 1369.5640931129456 84 149.818281883 23.5539854646 212.543887418 31.1640895757 151.0 0.0 50132 4261220
-0.00357469 1385.4445531368256 85 154.807549201 23.7587891107 204.479418675 19.446904557 151.0 0.0 50132 4311352
-0.0831478 1401.3308084011078 86 165.073308438 25.2280173293 218.173918542 52.9616057052 151.0 0.0 50132 4361484
-0.0178012 1417.2557497024536 87 163.589466245 28.1610647173 227.463465479 34.3157710895 151.0 0.0 50132 4411616
0.224079 1433.194581747055 88 150.260310893 24.2015421728 209.349731243 55.8937025004 151.0 0.0 50132 4461748
0.0275891 1449.001769065857 89 124.070375088 23.3194163902 172.906351653 26.7539427537 151.0 0.0 50132 4511880
0.078205 1464.8036906719208 90 116.821878427 32.7447352801 170.800877753 -0.687701316085 151.0 0.0 50132 4562012
0.0712893 1480.580598115921 91 135.932953929 15.9698102843 185.040708545 85.733918891 151.0 0.0 50132 4612144
-0.271885 1496.284797668457 92 151.015589544 15.6587658302 190.302083375 102.404421608 151.0 0.0 50132 4662276
-0.295132 1512.0198142528534 93 149.186562335 16.7787220378 201.86569471 102.520195047 151.0 0.0 50132 4712408
-0.140751 1527.711982011795 94 148.141625711 23.4508556444 191.278971452 -31.6761775448 151.0 0.0 50132 4762540
0.0352029 1543.3818192481995 95 159.413002958 22.951530397 214.428208655 28.0422936655 151.0 0.0 50132 4812672
0.177194 1559.0737857818604 96 160.453372131 23.6332118447 213.81337905 48.6882801387 151.0 0.0 50132 4862804
0.105576 1574.8353633880615 97 166.211329149 27.5100657993 224.660564422 38.5172514877 151.0 0.0 50132 4912936
-0.0260659 1590.5823757648468 98 159.964576546 29.481163381 229.273469784 -0.00698520156626 151.0 0.0 50132 4963068
-0.0762075 1606.3994948863983 99 152.15949126 25.9411095777 212.084252709 56.2887050775 151.0 0.0 50132 5013200
================================================
FILE: hw2/data/HalfCheetah_b50000_rtg_na_25bl_HalfCheetah-v1_31-01-2018_19-35-00/41/params.json
================================================
{"animate" : false,
"env_name" : "HalfCheetah-v1",
"exp_name" : "HalfCheetah_b50000_rtg_na_25bl",
"gamma" : 0.9,
"learning_rate" : 0.025,
"logdir" : "data/HalfCheetah_b50000_rtg_na_25bl_HalfCheetah-v1_31-01-2018_19-35-00/41",
"max_path_length" : 150.0,
"min_timesteps_per_batch" : 50000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : true,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 41,
"size" : 32}
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_0.02_InvertedPendulum-v1_02-02-2018_10-42-58/1/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.602091 6.76475715637207 0 9.03571428571 5.57085619771 32.0 3.0 9.03571428571 5.57085619771 1012 1012
0.0882509 7.067959547042847 1 19.0555555556 9.58860563506 55.0 6.0 19.0555555556 9.58860563506 1029 2041
0.00134369 7.353352069854736 2 27.3513513514 11.7501379318 70.0 13.0 27.3513513514 11.7501379318 1012 3053
0.00994612 7.644820690155029 3 26.7631578947 13.8268126451 58.0 8.0 26.7631578947 13.8268126451 1017 4070
0.0226749 7.9196436405181885 4 28.25 13.0987170703 58.0 12.0 28.25 13.0987170703 1017 5087
0.016652 8.210463523864746 5 40.8076923077 24.5717461744 105.0 12.0 40.8076923077 24.5717461744 1061 6148
0.0273083 8.482748031616211 6 32.875 18.3042857003 81.0 12.0 32.875 18.3042857003 1052 7200
0.0178182 8.766393184661865 7 58.3333333333 43.4281015012 195.0 17.0 58.3333333333 43.4281015012 1050 8250
0.0218356 9.023099660873413 8 67.5333333333 52.6128839312 248.0 16.0 67.5333333333 52.6128839312 1013 9263
0.00636999 9.28016448020935 9 91.3636363636 51.793774156 203.0 39.0 91.3636363636 51.793774156 1005 10268
0.00664996 9.550451517105103 10 88.1666666667 27.8652511602 157.0 49.0 88.1666666667 27.8652511602 1058 11326
0.0220992 9.80831265449524 11 100.2 22.8814335215 134.0 62.0 100.2 22.8814335215 1002 12328
0.0100588 10.088838338851929 12 98.5454545455 18.941842266 137.0 70.0 98.5454545455 18.941842266 1084 13412
0.000466488 10.362831354141235 13 80.8461538462 11.4679899241 97.0 62.0 80.8461538462 11.4679899241 1051 14463
0.0059433 10.631492137908936 14 89.75 17.5647611237 120.0 62.0 89.75 17.5647611237 1077 15540
0.000191879 10.909849882125854 15 121.333333333 54.5832697201 244.0 32.0 121.333333333 54.5832697201 1092 16632
0.0298251 11.174779176712036 16 105.2 27.9134376242 151.0 72.0 105.2 27.9134376242 1052 17684
0.0120746 11.471116542816162 17 106.090909091 50.1949916833 208.0 30.0 106.090909091 50.1949916833 1167 18851
-0.00228642 11.737281322479248 18 68.3333333333 46.1557748885 192.0 20.0 68.3333333333 46.1557748885 1025 19876
0.0210015 12.016618490219116 19 48.5 29.9161707564 144.0 13.0 48.5 29.9161707564 1067 20943
0.0249124 12.29704737663269 20 72.1333333333 60.1452316388 203.0 12.0 72.1333333333 60.1452316388 1082 22025
0.0107623 12.561517477035522 21 114.0 49.9510871865 219.0 61.0 114.0 49.9510871865 1026 23051
0.0379473 12.825831413269043 22 149.428571429 49.1204267747 219.0 61.0 149.428571429 49.1204267747 1046 24097
0.0146601 13.269243240356445 23 857.0 143.0 1000.0 714.0 857.0 143.0 1714 25811
0.00387304 13.550962209701538 24 520.5 479.5 1000.0 41.0 520.5 479.5 1041 26852
-0.00445846 13.936067581176758 25 748.0 202.0 950.0 546.0 748.0 202.0 1496 28348
-0.00309289 14.287321329116821 26 343.5 259.08927033 720.0 47.0 343.5 259.08927033 1374 29722
0.00437352 14.56696891784668 27 120.777777778 30.89688146 167.0 73.0 120.777777778 30.89688146 1087 30809
0.013809 14.830055713653564 28 151.142857143 98.735474261 332.0 40.0 151.142857143 98.735474261 1058 31867
0.00959165 15.085086584091187 29 144.857142857 35.6708307061 189.0 98.0 144.857142857 35.6708307061 1014 32881
0.00861404 15.364528179168701 30 268.75 144.210566534 402.0 52.0 268.75 144.210566534 1075 33956
0.00630407 15.767969608306885 31 522.333333333 148.755578794 631.0 312.0 522.333333333 148.755578794 1567 35523
-0.00306702 16.293739795684814 32 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 37523
0.000587873 16.816981077194214 33 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 39523
0.0119693 17.338316917419434 34 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 41523
-0.00308531 17.867908716201782 35 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 43523
0.00772547 18.39204430580139 36 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 45523
0.00597157 18.91360378265381 37 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 47523
-0.00474364 19.187209367752075 38 348.333333333 165.387088036 571.0 175.0 348.333333333 165.387088036 1045 48568
0.00159111 19.456584692001343 39 513.5 132.5 646.0 381.0 513.5 132.5 1027 49595
0.000936993 19.9298152923584 40 307.0 314.23451964 903.0 26.0 307.0 314.23451964 1842 51437
0.0111146 20.18559980392456 41 145.428571429 103.453035781 272.0 5.0 145.428571429 103.453035781 1018 52455
0.00332006 20.538946390151978 42 442.333333333 357.172538449 904.0 34.0 442.333333333 357.172538449 1327 53782
0.00513766 20.93329095840454 43 505.0 355.404933374 1000.0 182.0 505.0 355.404933374 1515 55297
0.00254112 21.45427918434143 44 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 57297
0.00570995 21.979018688201904 45 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 59297
-0.00294264 22.50430154800415 46 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 61297
-0.000595535 23.031405925750732 47 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 63297
0.000307902 23.549055337905884 48 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 65297
0.002502 24.067930698394775 49 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 67297
0.00701737 24.5829815864563 50 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 69297
-7.87489e-05 25.10943102836609 51 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 71297
0.00197969 25.636685609817505 52 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 73297
0.00185306 26.166483879089355 53 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 75297
0.00235633 26.693531274795532 54 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 77297
0.003282 27.220266580581665 55 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 79297
0.00744414 27.7472984790802 56 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 81297
0.00106317 28.268240928649902 57 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 83297
0.00464073 28.79481077194214 58 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 85297
0.000234872 29.32617974281311 59 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 87297
-0.00017265 29.84268832206726 60 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 89297
-0.000419483 30.367334127426147 61 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 91297
-0.000131996 30.885836601257324 62 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 93297
0.00541081 31.39881730079651 63 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 95297
0.0027751 31.913252353668213 64 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 97297
0.00705485 32.43810844421387 65 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 99297
0.00756834 32.84289884567261 66 388.5 205.808770464 631.0 184.0 388.5 205.808770464 1554 100851
0.0282454 33.221885204315186 67 734.0 266.0 1000.0 468.0 734.0 266.0 1468 102319
0.00228373 33.74599099159241 68 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 104319
0.00151597 34.28067183494568 69 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 106319
0.00324522 34.82058072090149 70 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 108319
0.000135124 35.35584092140198 71 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 110319
0.00073885 35.906853914260864 72 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 112319
0.000151843 36.456477880477905 73 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 114319
0.00253202 37.01272749900818 74 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 116319
0.00139823 37.56826639175415 75 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 118319
0.00708318 38.12512946128845 76 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 120319
0.000988686 38.69096875190735 77 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 122319
0.00213949 39.30945086479187 78 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 124319
-0.000421284 39.91579341888428 79 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 126319
0.000149263 40.31728267669678 80 756.0 244.0 1000.0 512.0 756.0 244.0 1512 127831
-0.000102263 40.83227825164795 81 545.666666667 336.715837993 1000.0 195.0 545.666666667 336.715837993 1637 129468
0.00492216 41.186660289764404 82 436.0 399.462972836 1000.0 126.0 436.0 399.462972836 1308 130776
0.00174772 41.59078574180603 83 771.0 229.0 1000.0 542.0 771.0 229.0 1542 132318
0.000779479 42.13102340698242 84 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 134318
0.00434309 42.662580490112305 85 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 136318
0.00265961 43.18075108528137 86 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 138318
0.00101361 43.70223069190979 87 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 140318
0.00352905 44.22879147529602 88 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 142318
0.0036558 44.75788187980652 89 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 144318
0.00685947 45.286428451538086 90 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 146318
0.00302239 45.807966232299805 91 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 148318
0.0148254 46.31892967224121 92 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 150318
-0.002683 46.83810997009277 93 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 152318
0.00536365 47.38642716407776 94 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 154318
-0.00564025 47.920905351638794 95 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 156318
4.73112e-05 48.40345025062561 96 623.0 267.156633207 1000.0 413.0 623.0 267.156633207 1869 158187
0.0013827 48.83704614639282 97 833.0 167.0 1000.0 666.0 833.0 167.0 1666 159853
0.00276896 49.29080605506897 98 591.666666667 313.796466236 1000.0 237.0 591.666666667 313.796466236 1775 161628
-0.000452832 49.81399321556091 99 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 163628
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_0.02_InvertedPendulum-v1_02-02-2018_10-42-58/1/params.json
================================================
{"animate" : false,
"env_name" : "InvertedPendulum-v1",
"exp_name" : "InvertedPendulum_sb_rtg_na_0.02",
"gamma" : 1.0,
"learning_rate" : 0.02,
"logdir" : "data/InvertedPendulum_sb_rtg_na_0.02_InvertedPendulum-v1_02-02-2018_10-42-58/1",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 2,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 1,
"size" : 32}
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_0.02_InvertedPendulum-v1_02-02-2018_10-42-58/11/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
9.84485 7.2229578495025635 0 8.41666666667 2.47515431618 20.0 5.0 8.41666666667 2.47515431618 1010 1010
1.50212 7.51533055305481 1 20.22 3.79626131872 30.0 15.0 20.22 3.79626131872 1011 2021
1.25737 7.7772440910339355 2 57.0555555556 13.8342257633 98.0 37.0 57.0555555556 13.8342257633 1027 3048
0.535736 8.046581268310547 3 180.5 94.2368470044 376.0 96.0 180.5 94.2368470044 1083 4131
0.400931 8.321382999420166 4 83.2307692308 30.3724415729 161.0 53.0 83.2307692308 30.3724415729 1082 5213
-0.0160533 8.57603931427002 5 50.6 13.7164135254 85.0 25.0 50.6 13.7164135254 1012 6225
0.041017 8.83631682395935 6 38.6923076923 14.5675330016 68.0 13.0 38.6923076923 14.5675330016 1006 7231
0.0517083 9.095884084701538 7 40.8 10.4957134107 59.0 15.0 40.8 10.4957134107 1020 8251
0.0212874 9.370235204696655 8 45.5909090909 10.5729461402 82.0 32.0 45.5909090909 10.5729461402 1003 9254
0.0239413 9.634948968887329 9 44.3043478261 8.91230113558 64.0 31.0 44.3043478261 8.91230113558 1019 10273
0.2061 9.910567045211792 10 51.9 15.9715371834 102.0 32.0 51.9 15.9715371834 1038 11311
0.492431 10.165862798690796 11 53.2631578947 13.6337124931 80.0 37.0 53.2631578947 13.6337124931 1012 12323
0.0759064 10.429330110549927 12 69.4666666667 20.9089029416 136.0 45.0 69.4666666667 20.9089029416 1042 13365
-0.0115777 10.688966989517212 13 103.9 27.9086008248 159.0 68.0 103.9 27.9086008248 1039 14404
0.10276 10.948424816131592 14 116.111111111 27.5012906543 172.0 74.0 116.111111111 27.5012906543 1045 15449
0.107211 11.213691711425781 15 207.2 35.9410628669 261.0 165.0 207.2 35.9410628669 1036 16485
0.254836 11.547999382019043 16 342.5 94.7800084406 455.0 238.0 342.5 94.7800084406 1370 17855
0.180811 11.81119704246521 17 257.0 19.7610728454 287.0 232.0 257.0 19.7610728454 1028 18883
0.0363615 12.093258142471313 18 155.857142857 45.1772021249 242.0 113.0 155.857142857 45.1772021249 1091 19974
0.0222054 12.344907283782959 19 101.2 17.9710878914 139.0 68.0 101.2 17.9710878914 1012 20986
0.00786898 12.595535516738892 20 116.222222222 31.12261692 165.0 66.0 116.222222222 31.12261692 1046 22032
-0.00338071 12.849928379058838 21 129.0 35.2526594741 181.0 88.0 129.0 35.2526594741 1032 23064
0.0334179 13.097781896591187 22 170.333333333 18.3636113611 198.0 145.0 170.333333333 18.3636113611 1022 24086
0.0154595 13.49902081489563 23 326.4 166.928248059 639.0 185.0 326.4 166.928248059 1632 25718
0.0102083 13.915255784988403 24 550.666666667 289.196972475 877.0 174.0 550.666666667 289.196972475 1652 27370
0.00266306 14.426665544509888 25 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 29370
0.00419491 14.956173658370972 26 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 31370
0.000947851 15.548860311508179 27 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 33370
0.0491228 16.1032931804657 28 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 35370
0.000598127 16.35001277923584 29 201.4 17.9398996653 236.0 185.0 201.4 17.9398996653 1007 36377
0.205319 16.642978191375732 30 193.666666667 22.6175939382 236.0 159.0 193.666666667 22.6175939382 1162 37539
0.0578096 17.157249212265015 31 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 39539
-0.00536724 17.665299654006958 32 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 41539
0.00977675 18.185539722442627 33 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 43539
-0.0024191 18.71018099784851 34 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 45539
0.000597108 19.224491596221924 35 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 47539
-0.000200507 19.740996599197388 36 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 49539
0.00456004 20.31839609146118 37 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 51539
0.00168774 20.86813521385193 38 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 53539
0.0102562 21.422646522521973 39 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 55539
-0.000356285 21.972156763076782 40 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 57539
0.00434321 22.51257061958313 41 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 59539
0.00314676 23.06043553352356 42 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 61539
0.0119144 23.60994815826416 43 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 63539
0.00132382 24.147279977798462 44 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 65539
-0.00246824 24.692411184310913 45 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 67539
0.00578189 25.244147539138794 46 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 69539
0.00142292 25.791747093200684 47 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 71539
0.00720477 26.34340000152588 48 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 73539
-0.000640061 26.88925313949585 49 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 75539
-0.000631195 27.199026823043823 50 395.0 73.9729680356 491.0 311.0 395.0 73.9729680356 1185 76724
0.00845176 27.46857786178589 51 352.666666667 46.6357040141 414.0 301.0 352.666666667 46.6357040141 1058 77782
0.0327231 27.9066219329834 52 561.0 164.17673404 775.0 376.0 561.0 164.17673404 1683 79465
0.0178538 28.435946941375732 53 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 81465
-0.00175977 29.014880657196045 54 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 83465
-0.00183104 29.539748668670654 55 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 85465
0.0011446 30.06399655342102 56 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 87465
0.00530291 30.591025352478027 57 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 89465
0.00815219 31.11577296257019 58 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 91465
0.00294679 31.638994693756104 59 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 93465
0.00234366 32.16615128517151 60 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 95465
0.00537469 32.686542987823486 61 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 97465
0.00254938 33.2045464515686 62 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 99465
0.00851973 33.71687150001526 63 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 101465
-0.00166347 34.24772596359253 64 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 103465
0.00554468 34.76952028274536 65 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 105465
-0.00221764 35.286675453186035 66 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 107465
-0.000778406 35.80536460876465 67 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 109465
0.00339717 36.20728349685669 68 786.0 214.0 1000.0 572.0 786.0 214.0 1572 111037
0.0537435 36.46434426307678 69 144.857142857 64.0143478815 246.0 72.0 144.857142857 64.0143478815 1014 112051
0.0154534 36.77367043495178 70 608.0 231.0 839.0 377.0 608.0 231.0 1216 113267
0.00536814 37.2880973815918 71 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 115267
0.000375593 37.80867886543274 72 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 117267
0.00246562 38.328699827194214 73 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 119267
0.0235415 38.859750509262085 74 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 121267
0.00377482 39.377413511276245 75 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 123267
-0.00155859 39.93961238861084 76 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 125267
-0.000933135 40.46783971786499 77 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 127267
0.00555035 40.987693071365356 78 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 129267
0.0253226 41.50291180610657 79 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 131267
0.0373722 42.02027869224548 80 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 133267
-0.00281248 42.53746962547302 81 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 135267
0.0538512 43.04693007469177 82 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 137267
-0.0150499 43.56194829940796 83 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 139267
0.022479 44.06363844871521 84 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 141267
0.0127346 44.571359395980835 85 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 143267
0.0459498 45.08292746543884 86 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 145267
-0.0156565 45.60513257980347 87 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 147267
0.0348157 46.12567448616028 88 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 149267
-0.0149153 46.52139449119568 89 768.5 231.5 1000.0 537.0 768.5 231.5 1537 150804
0.0471378 46.77190947532654 90 169.5 90.4778978536 350.0 97.0 169.5 90.4778978536 1017 151821
0.00488421 47.03598880767822 91 74.7857142857 34.4926049454 131.0 34.0 74.7857142857 34.4926049454 1047 152868
0.00946848 47.2924861907959 92 86.25 31.5888297768 145.0 40.0 86.25 31.5888297768 1035 153903
0.0110376 47.55975818634033 93 82.0769230769 25.0920199955 129.0 41.0 82.0769230769 25.0920199955 1067 154970
0.0196664 47.811049461364746 94 114.0 49.8352842427 206.0 41.0 114.0 49.8352842427 1026 155996
0.0104369 48.06812262535095 95 147.428571429 21.2861936667 177.0 112.0 147.428571429 21.2861936667 1032 157028
0.0215529 48.36423707008362 96 242.2 23.7267781209 276.0 203.0 242.2 23.7267781209 1211 158239
-0.00103157 48.64035892486572 97 262.75 42.3755530937 332.0 218.0 262.75 42.3755530937 1051 159290
0.00117358 49.18579912185669 98 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 161290
0.00522744 49.70541977882385 99 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 163290
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_0.02_InvertedPendulum-v1_02-02-2018_10-42-58/11/params.json
================================================
{"animate" : false,
"env_name" : "InvertedPendulum-v1",
"exp_name" : "InvertedPendulum_sb_rtg_na_0.02",
"gamma" : 1.0,
"learning_rate" : 0.02,
"logdir" : "data/InvertedPendulum_sb_rtg_na_0.02_InvertedPendulum-v1_02-02-2018_10-42-58/11",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 2,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 11,
"size" : 32}
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_0.02_InvertedPendulum-v1_02-02-2018_10-42-58/21/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.350545 7.623704195022583 0 8.73043478261 5.11149044737 30.0 3.0 8.73043478261 5.11149044737 1004 1004
0.152718 7.933123350143433 1 19.0740740741 11.3379922644 55.0 4.0 19.0740740741 11.3379922644 1030 2034
0.0429787 8.199016094207764 2 37.6296296296 23.3906409713 129.0 10.0 37.6296296296 23.3906409713 1016 3050
0.0148822 8.450114250183105 3 37.2962962963 21.1831778381 80.0 6.0 37.2962962963 21.1831778381 1007 4057
0.0104328 8.721006631851196 4 28.2162162162 20.3962571224 121.0 9.0 28.2162162162 20.3962571224 1044 5101
0.018495 8.987627506256104 5 29.5588235294 16.2339353651 68.0 8.0 29.5588235294 16.2339353651 1005 6106
0.00639337 9.252012729644775 6 30.6060606061 23.7179632652 106.0 8.0 30.6060606061 23.7179632652 1010 7116
0.0222873 9.539709329605103 7 39.7777777778 21.0631033086 90.0 12.0 39.7777777778 21.0631033086 1074 8190
0.0089298 9.825225114822388 8 47.1818181818 43.3481008954 206.0 9.0 47.1818181818 43.3481008954 1038 9228
0.0281346 10.153348445892334 9 53.35 19.5378478856 82.0 11.0 53.35 19.5378478856 1067 10295
-0.0016746 10.516669750213623 10 77.3571428571 12.2801066937 97.0 57.0 77.3571428571 12.2801066937 1083 11378
0.01356 10.803219079971313 11 86.0 16.5025250593 108.0 42.0 86.0 16.5025250593 1032 12410
0.0040417 11.082040071487427 12 72.5 19.452322667 88.0 7.0 72.5 19.452322667 1015 13425
0.0136989 11.35108470916748 13 77.2857142857 6.45233702322 88.0 68.0 77.2857142857 6.45233702322 1082 14507
0.0160684 11.614316701889038 14 74.1428571429 5.42292939889 82.0 66.0 74.1428571429 5.42292939889 1038 15545
0.0569116 11.87187647819519 15 86.75 9.9676560267 99.0 67.0 86.75 9.9676560267 1041 16586
0.0433088 12.153593301773071 16 89.3333333333 46.7552730241 137.0 6.0 89.3333333333 46.7552730241 1072 17658
0.0112266 12.42675232887268 17 68.1875 30.6251913259 100.0 9.0 68.1875 30.6251913259 1091 18749
0.0558085 12.747072696685791 18 79.5333333333 70.9684123787 253.0 10.0 79.5333333333 70.9684123787 1193 19942
0.007598 13.030377864837646 19 167.857142857 16.0394920781 190.0 140.0 167.857142857 16.0394920781 1175 21117
-0.00639769 13.296810626983643 20 134.125 10.6587698634 155.0 121.0 134.125 10.6587698634 1073 22190
0.003167 13.558030605316162 21 117.666666667 6.41179468722 127.0 107.0 117.666666667 6.41179468722 1059 23249
0.00376649 13.822790145874023 22 118.555555556 9.2269064409 138.0 104.0 118.555555556 9.2269064409 1067 24316
0.0175271 14.091765403747559 23 116.111111111 6.11817773242 129.0 109.0 116.111111111 6.11817773242 1045 25361
-0.000405248 14.353772640228271 24 104.6 4.82078831728 112.0 98.0 104.6 4.82078831728 1046 26407
-0.000334972 14.619886875152588 25 97.3636363636 4.55816404972 105.0 89.0 97.3636363636 4.55816404972 1071 27478
0.00266277 14.882812738418579 26 95.5454545455 5.03377025451 105.0 89.0 95.5454545455 5.03377025451 1051 28529
0.0051884 15.143433570861816 27 98.1818181818 3.29788311768 103.0 89.0 98.1818181818 3.29788311768 1080 29609
0.00461172 15.427077531814575 28 102.5 5.76628129734 110.0 90.0 102.5 5.76628129734 1025 30634
0.0143375 15.703834772109985 29 108.9 8.75728268357 125.0 95.0 108.9 8.75728268357 1089 31723
0.0164663 16.047930002212524 30 123.111111111 10.0933910659 142.0 113.0 123.111111111 10.0933910659 1108 32831
0.0734041 16.371893882751465 31 160.142857143 25.4301765144 216.0 131.0 160.142857143 25.4301765144 1121 33952
0.0209195 16.675029754638672 32 315.75 40.8495716012 360.0 249.0 315.75 40.8495716012 1263 35215
0.0045359 16.970834493637085 33 301.0 33.6229088569 351.0 266.0 301.0 33.6229088569 1204 36419
-0.0162555 17.29827642440796 34 199.666666667 28.2823069938 229.0 140.0 199.666666667 28.2823069938 1198 37617
0.00934858 17.58111262321472 35 127.111111111 64.2986857382 193.0 24.0 127.111111111 64.2986857382 1144 38761
0.00314428 17.835707187652588 36 176.666666667 12.3782964184 198.0 164.0 176.666666667 12.3782964184 1060 39821
0.011018 18.11056923866272 37 157.857142857 23.4668676553 177.0 103.0 157.857142857 23.4668676553 1105 40926
0.00261322 18.374802827835083 38 152.714285714 33.779597755 190.0 88.0 152.714285714 33.779597755 1069 41995
0.00184643 18.63509750366211 39 175.166666667 19.8948625418 200.0 140.0 175.166666667 19.8948625418 1051 43046
0.00787114 18.91007685661316 40 110.0 55.0036362434 197.0 36.0 110.0 55.0036362434 1100 44146
0.0023341 19.169974327087402 41 147.571428571 38.1981942088 186.0 60.0 147.571428571 38.1981942088 1033 45179
-0.000996647 19.444185972213745 42 183.5 10.6105293616 202.0 172.0 183.5 10.6105293616 1101 46280
0.0361872 19.763829469680786 43 196.166666667 5.98377435701 207.0 188.0 196.166666667 5.98377435701 1177 47457
-0.00198973 20.01742458343506 44 263.0 6.204836823 273.0 256.0 263.0 6.204836823 1052 48509
0.0185856 20.284472942352295 45 364.0 24.1246761636 388.0 331.0 364.0 24.1246761636 1092 49601
0.00496694 20.546913623809814 46 115.444444444 91.4975544435 317.0 39.0 115.444444444 91.4975544435 1039 50640
0.0330575 20.873517274856567 47 169.857142857 99.9220104044 272.0 10.0 169.857142857 99.9220104044 1189 51829
0.0344604 21.179991006851196 48 167.428571429 70.6275080826 257.0 30.0 167.428571429 70.6275080826 1172 53001
0.0205699 21.45786952972412 49 175.833333333 15.464116169 206.0 155.0 175.833333333 15.464116169 1055 54056
-0.00851114 21.756019592285156 50 188.333333333 13.1613913483 205.0 171.0 188.333333333 13.1613913483 1130 55186
0.00929796 22.021973848342896 51 203.2 23.0599219426 234.0 175.0 203.2 23.0599219426 1016 56202
0.00810973 22.326077699661255 52 290.0 33.3016516107 335.0 243.0 290.0 33.3016516107 1160 57362
0.0143014 22.624312162399292 53 378.333333333 61.4780900448 465.0 329.0 378.333333333 61.4780900448 1135 58497
0.0230448 22.979187488555908 54 665.5 93.5 759.0 572.0 665.5 93.5 1331 59828
0.0323814 23.37579083442688 55 506.333333333 98.4084458887 605.0 372.0 506.333333333 98.4084458887 1519 61347
0.00398331 23.916831016540527 56 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 63347
-0.00126615 24.45587158203125 57 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 65347
0.00829495 24.990619659423828 58 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 67347
0.00470978 25.51140570640564 59 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 69347
0.00532265 26.039437294006348 60 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 71347
0.00514702 26.562456130981445 61 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 73347
0.00158479 27.10531449317932 62 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 75347
0.014562 27.638699293136597 63 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 77347
0.00113166 28.16949987411499 64 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 79347
0.00471543 28.56187129020691 65 757.0 243.0 1000.0 514.0 757.0 243.0 1514 80861
0.0417658 28.829689025878906 66 93.6363636364 115.90613187 439.0 9.0 93.6363636364 115.90613187 1030 81891
0.0360292 29.110421895980835 67 185.333333333 156.388050126 401.0 14.0 185.333333333 156.388050126 1112 83003
0.00307429 29.627554655075073 68 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 85003
-0.00208698 30.15225338935852 69 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 87003
0.000237605 30.684929609298706 70 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 89003
-0.00365509 31.202202558517456 71 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 91003
0.00270619 31.72530221939087 72 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 93003
-0.00141715 32.236183643341064 73 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 95003
0.00174803 32.75935506820679 74 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 97003
0.00294137 33.27057981491089 75 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 99003
0.00612107 33.54245471954346 76 515.0 485.0 1000.0 30.0 515.0 485.0 1030 100033
0.000486661 33.83180022239685 77 514.5 485.5 1000.0 29.0 514.5 485.5 1029 101062
0.00178058 34.346622467041016 78 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 103062
0.00217812 34.86988806724548 79 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 105062
0.00209597 35.203787326812744 80 640.0 360.0 1000.0 280.0 640.0 360.0 1280 106342
0.0025814 35.72733783721924 81 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 108342
0.0004908 36.24655270576477 82 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 110342
0.000522666 36.767661333084106 83 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 112342
0.000994201 37.29701209068298 84 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 114342
0.00246152 37.8122718334198 85 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 116342
-5.16772e-05 38.32043981552124 86 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 118342
0.00437572 38.847431659698486 87 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 120342
-8.2776e-06 39.36740565299988 88 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 122342
0.00191971 39.879302740097046 89 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 124342
0.00125631 40.395965576171875 90 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 126342
0.00755961 40.91072130203247 91 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 128342
-0.000780614 41.42177677154541 92 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 130342
0.00119386 41.950058460235596 93 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 132342
0.0029334 42.470048666000366 94 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 134342
0.00528921 42.79389667510986 95 584.5 415.5 1000.0 169.0 584.5 415.5 1169 135511
-0.00271168 43.321409463882446 96 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 137511
0.000188325 43.83671522140503 97 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 139511
0.0047191 44.36561918258667 98 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 141511
-0.000626978 44.703309297561646 99 623.0 377.0 1000.0 246.0 623.0 377.0 1246 142757
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_0.02_InvertedPendulum-v1_02-02-2018_10-42-58/21/params.json
================================================
{"animate" : false,
"env_name" : "InvertedPendulum-v1",
"exp_name" : "InvertedPendulum_sb_rtg_na_0.02",
"gamma" : 1.0,
"learning_rate" : 0.02,
"logdir" : "data/InvertedPendulum_sb_rtg_na_0.02_InvertedPendulum-v1_02-02-2018_10-42-58/21",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 2,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 21,
"size" : 32}
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_0.02_InvertedPendulum-v1_02-02-2018_10-42-58/31/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.282001 7.312387466430664 0 5.01 2.78206757646 18.0 2.0 5.01 2.78206757646 1002 1002
0.172524 7.62332010269165 1 8.59829059829 4.49322344281 24.0 2.0 8.59829059829 4.49322344281 1006 2008
0.0445865 7.896857023239136 2 17.5614035088 14.9596152777 66.0 2.0 17.5614035088 14.9596152777 1001 3009
-0.000305377 8.180015563964844 3 16.9830508475 9.81436430058 49.0 4.0 16.9830508475 9.81436430058 1002 4011
-0.00812558 8.459576606750488 4 13.012987013 9.04748441251 56.0 3.0 13.012987013 9.04748441251 1002 5013
0.00731168 8.742552042007446 5 12.8333333333 8.00867585116 42.0 4.0 12.8333333333 8.00867585116 1001 6014
0.0139483 9.034139156341553 6 13.3866666667 8.82102538761 48.0 3.0 13.3866666667 8.82102538761 1004 7018
0.0345713 9.342700242996216 7 15.2575757576 11.9218549071 64.0 3.0 15.2575757576 11.9218549071 1007 8025
0.0259883 9.668273448944092 8 20.9791666667 13.0391870646 63.0 4.0 20.9791666667 13.0391870646 1007 9032
0.0146477 9.962856769561768 9 26.9473684211 19.7136706086 84.0 4.0 26.9473684211 19.7136706086 1024 10056
0.00605139 10.227054357528687 10 26.6315789474 19.1358317144 72.0 3.0 26.6315789474 19.1358317144 1012 11068
0.0055303 10.511155366897583 11 35.7586206897 27.0741703759 123.0 2.0 35.7586206897 27.0741703759 1037 12105
0.00416327 10.784699201583862 12 43.6956521739 25.6488575601 98.0 12.0 43.6956521739 25.6488575601 1005 13110
0.00450304 11.054237604141235 13 33.7666666667 17.0287665111 75.0 6.0 33.7666666667 17.0287665111 1013 14123
0.00688669 11.369384288787842 14 38.2222222222 22.7959277282 87.0 2.0 38.2222222222 22.7959277282 1032 15155
0.0123785 11.676459550857544 15 46.9090909091 26.1375889041 92.0 4.0 46.9090909091 26.1375889041 1032 16187
0.0229735 12.007859468460083 16 57.7222222222 24.4217697865 112.0 13.0 57.7222222222 24.4217697865 1039 17226
9.02265e-05 12.395692825317383 17 67.8666666667 28.7468645633 141.0 33.0 67.8666666667 28.7468645633 1018 18244
0.00436269 12.823171615600586 18 76.7857142857 36.876586787 179.0 21.0 76.7857142857 36.876586787 1075 19319
0.000832288 13.18827486038208 19 71.7857142857 20.3651613281 114.0 45.0 71.7857142857 20.3651613281 1005 20324
0.00870012 13.477786302566528 20 71.8571428571 16.4440920475 101.0 46.0 71.8571428571 16.4440920475 1006 21330
0.0120689 14.333693981170654 21 102.5 31.7372021451 159.0 56.0 102.5 31.7372021451 1025 22355
0.0298275 14.675322532653809 22 94.0909090909 13.2559046566 118.0 66.0 94.0909090909 13.2559046566 1035 23390
0.0175917 14.950211524963379 23 88.3333333333 27.6445694888 143.0 20.0 88.3333333333 27.6445694888 1060 24450
0.0309296 15.215370893478394 24 110.0 34.3802268753 160.0 29.0 110.0 34.3802268753 1100 25550
0.0219253 15.493776082992554 25 125.111111111 27.4810821574 182.0 86.0 125.111111111 27.4810821574 1126 26676
0.01993 15.806857109069824 26 133.125 42.6510184521 184.0 63.0 133.125 42.6510184521 1065 27741
0.00948069 16.06858730316162 27 147.142857143 84.1553471205 245.0 23.0 147.142857143 84.1553471205 1030 28771
0.00733437 16.379229068756104 28 172.0 34.4009966633 227.0 131.0 172.0 34.4009966633 1204 29975
0.00373782 16.674012899398804 29 230.0 55.1035389063 324.0 175.0 230.0 55.1035389063 1150 31125
0.00224628 17.006991624832153 30 250.0 104.747315001 378.0 97.0 250.0 104.747315001 1250 32375
0.00142848 17.399035453796387 31 197.166666667 42.819063771 237.0 110.0 197.166666667 42.819063771 1183 33558
0.00201405 17.78662109375 32 228.4 36.9897283039 268.0 168.0 228.4 36.9897283039 1142 34700
0.0105207 18.167629718780518 33 323.75 164.038676842 541.0 101.0 323.75 164.038676842 1295 35995
0.00527436 18.44786262512207 34 345.0 73.9053448676 449.0 284.0 345.0 73.9053448676 1035 37030
0.0106588 18.75380778312683 35 307.0 61.1596272062 387.0 216.0 307.0 61.1596272062 1228 38258
0.0120677 19.117998361587524 36 348.5 183.159083859 568.0 87.0 348.5 183.159083859 1394 39652
0.0116939 19.52215886116028 37 497.333333333 112.866686356 594.0 339.0 497.333333333 112.866686356 1492 41144
0.00378681 19.968299388885498 38 805.0 76.0 881.0 729.0 805.0 76.0 1610 42754
0.0190845 20.335937976837158 39 512.333333333 209.76865564 805.0 324.0 512.333333333 209.76865564 1537 44291
0.0038603 20.59479546546936 40 205.8 192.392723355 545.0 18.0 205.8 192.392723355 1029 45320
0.00200821 20.94540023803711 41 337.5 177.844735654 478.0 42.0 337.5 177.844735654 1350 46670
0.0103986 21.3856782913208 42 403.25 313.231843049 844.0 69.0 403.25 313.231843049 1613 48283
0.0171077 21.749302625656128 43 721.5 145.5 867.0 576.0 721.5 145.5 1443 49726
0.0369906 22.028206825256348 44 357.0 41.2391399846 407.0 306.0 357.0 41.2391399846 1071 50797
0.0256809 22.518272161483765 45 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 52797
0.00742462 23.032599687576294 46 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 54797
0.00652308 23.54715895652771 47 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 56797
0.00603457 24.062268018722534 48 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 58797
0.00317419 24.44228720664978 49 736.0 264.0 1000.0 472.0 736.0 264.0 1472 60269
0.00238441 24.743547439575195 50 122.8 132.263978467 412.0 15.0 122.8 132.263978467 1228 61497
0.0094297 24.999162673950195 51 84.4166666667 57.5564336591 237.0 22.0 84.4166666667 57.5564336591 1013 62510
0.0131472 25.26547861099243 52 120.888888889 99.0818342409 335.0 22.0 120.888888889 99.0818342409 1088 63598
0.0163767 25.726291179656982 53 746.0 254.0 1000.0 492.0 746.0 254.0 1492 65090
-0.00281046 26.24703359603882 54 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 67090
0.00402751 26.77224326133728 55 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 69090
0.00296333 27.305210828781128 56 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 71090
-0.00310079 27.83940887451172 57 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 73090
-0.0002505 28.353312969207764 58 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 75090
-0.000481693 28.879303216934204 59 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 77090
0.00363952 29.422998666763306 60 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 79090
0.00546345 29.7506582736969 61 501.5 498.5 1000.0 3.0 501.5 498.5 1003 80093
0.0326573 30.065977811813354 62 225.6 125.891381754 395.0 23.0 225.6 125.891381754 1128 81221
-0.00110697 30.614723443984985 63 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 83221
0.00161732 31.200130462646484 64 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 85221
0.00975754 31.746546506881714 65 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 87221
0.000699978 32.43704557418823 66 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 89221
0.00472833 33.13878107070923 67 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 91221
6.5342e-05 33.68362808227539 68 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 93221
-0.000237209 34.227681398391724 69 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 95221
0.00658811 34.77618598937988 70 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 97221
0.0156395 35.31828761100769 71 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 99221
0.00261402 35.90537357330322 72 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 101221
0.00998117 36.61380195617676 73 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 103221
-0.00180377 37.259708642959595 74 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 105221
0.000665281 37.93757438659668 75 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 107221
-0.00212865 38.57337307929993 76 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 109221
0.000542132 39.159015417099 77 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 111221
1.9501e-05 39.82950830459595 78 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 113221
0.00839446 40.41243100166321 79 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 115221
0.00393064 41.03753924369812 80 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 117221
0.00531562 41.61378026008606 81 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 119221
-0.000715502 42.13232183456421 82 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 121221
0.0113394 42.71115756034851 83 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 123221
0.00185691 43.246108055114746 84 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 125221
-0.00110251 43.805136919021606 85 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 127221
0.00662219 44.33530044555664 86 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 129221
3.92115e-05 44.89397621154785 87 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 131221
0.000212441 45.57003712654114 88 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 133221
0.0022497 46.254772663116455 89 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 135221
0.00151402 46.85601735115051 90 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 137221
0.0032796 47.66975259780884 91 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 139221
0.00930224 48.6252224445343 92 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 141221
0.000486953 49.42156147956848 93 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 143221
0.0213688 49.994943618774414 94 667.5 332.5 1000.0 335.0 667.5 332.5 1335 144556
-0.00534622 50.996365785598755 95 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 146556
0.0685333 51.361817836761475 96 127.888888889 99.1053810003 274.0 23.0 127.888888889 99.1053810003 1151 147707
0.029234 51.9111807346344 97 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 149707
5.58803e-05 52.47572875022888 98 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 151707
0.00232072 53.01692867279053 99 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 153707
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_0.02_InvertedPendulum-v1_02-02-2018_10-42-58/31/params.json
================================================
{"animate" : false,
"env_name" : "InvertedPendulum-v1",
"exp_name" : "InvertedPendulum_sb_rtg_na_0.02",
"gamma" : 1.0,
"learning_rate" : 0.02,
"logdir" : "data/InvertedPendulum_sb_rtg_na_0.02_InvertedPendulum-v1_02-02-2018_10-42-58/31",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 2,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 31,
"size" : 32}
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_0.02_InvertedPendulum-v1_02-02-2018_10-42-58/41/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.106758 7.284057378768921 0 3.60791366906 2.10195403259 13.0 1.0 3.60791366906 2.10195403259 1003 1003
0.0785343 7.639320611953735 1 4.53846153846 3.2420617127 25.0 2.0 4.53846153846 3.2420617127 1003 2006
0.0394014 7.987441539764404 2 5.66101694915 4.30323818221 29.0 1.0 5.66101694915 4.30323818221 1002 3008
0.0181109 8.424543857574463 3 5.96428571429 3.98343722291 24.0 2.0 5.96428571429 3.98343722291 1002 4010
-0.000488117 8.774697065353394 4 5.69886363636 3.65643872685 20.0 1.0 5.69886363636 3.65643872685 1003 5013
0.000395879 9.162546157836914 5 5.69101123596 3.78198391697 22.0 2.0 5.69101123596 3.78198391697 1013 6026
0.00616884 9.497287511825562 6 5.87719298246 3.50807010525 22.0 1.0 5.87719298246 3.50807010525 1005 7031
0.00759745 9.822256326675415 7 6.10365853659 4.24353008599 28.0 2.0 6.10365853659 4.24353008599 1001 8032
0.00967595 10.152882814407349 8 5.75706214689 4.25895777304 31.0 1.0 5.75706214689 4.25895777304 1019 9051
0.0114911 10.463143348693848 9 7.3768115942 5.71953542574 43.0 2.0 7.3768115942 5.71953542574 1018 10069
0.0192858 10.777193546295166 10 6.81632653061 4.18130013983 27.0 2.0 6.81632653061 4.18130013983 1002 11071
0.0183719 11.082221508026123 11 7.81395348837 5.00351417879 24.0 1.0 7.81395348837 5.00351417879 1008 12079
0.0156121 11.377616882324219 12 8.43697478992 6.16800998302 31.0 2.0 8.43697478992 6.16800998302 1004 13083
0.00823773 11.67189621925354 13 8.39166666667 7.0548988102 43.0 2.0 8.39166666667 7.0548988102 1007 14090
0.00830379 11.967941522598267 14 9.72380952381 8.28365601145 48.0 1.0 9.72380952381 8.28365601145 1021 15111
0.0156088 12.279528856277466 15 9.58095238095 7.88341351299 41.0 1.0 9.58095238095 7.88341351299 1006 16117
0.0150717 12.573928356170654 16 9.41121495327 8.28798620573 49.0 2.0 9.41121495327 8.28798620573 1007 17124
0.0261717 12.912641286849976 17 11.010989011 7.58467875187 34.0 2.0 11.010989011 7.58467875187 1002 18126
0.0189215 13.220044374465942 18 15.4923076923 11.3437520274 42.0 2.0 15.4923076923 11.3437520274 1007 19133
0.0136903 13.523660898208618 19 18.4909090909 12.2680260356 52.0 2.0 18.4909090909 12.2680260356 1017 20150
0.0160765 13.82912564277649 20 15.671875 11.1776209 44.0 2.0 15.671875 11.1776209 1003 21153
0.0127196 14.111699342727661 21 19.75 12.5833757853 47.0 2.0 19.75 12.5833757853 1027 22180
0.020452 14.383026599884033 22 23.9534883721 13.5885613462 57.0 2.0 23.9534883721 13.5885613462 1030 23210
0.0115186 14.64767074584961 23 31.303030303 21.5357136059 100.0 4.0 31.303030303 21.5357136059 1033 24243
0.0148707 14.924425840377808 24 25.575 16.4725339581 67.0 2.0 25.575 16.4725339581 1023 25266
0.00771938 15.181899547576904 25 35.2068965517 20.0437096683 86.0 4.0 35.2068965517 20.0437096683 1021 26287
0.00730248 15.47615933418274 26 31.4375 14.7752696676 63.0 3.0 31.4375 14.7752696676 1006 27293
0.0308177 15.74492359161377 27 33.7333333333 20.3501569746 78.0 2.0 33.7333333333 20.3501569746 1012 28305
0.0143698 16.049623489379883 28 27.0 16.2433418312 60.0 5.0 27.0 16.2433418312 1053 29358
0.0241901 16.325273036956787 29 33.6 19.6851890178 64.0 5.0 33.6 19.6851890178 1008 30366
0.026001 16.610926628112793 30 41.44 21.2284337623 86.0 8.0 41.44 21.2284337623 1036 31402
0.0182948 16.902549505233765 31 44.4583333333 23.7889665718 104.0 5.0 44.4583333333 23.7889665718 1067 32469
0.0780125 17.198312759399414 32 59.7058823529 16.7604741821 87.0 30.0 59.7058823529 16.7604741821 1015 33484
0.0506846 17.488971710205078 33 59.5555555556 28.4843470118 107.0 5.0 59.5555555556 28.4843470118 1072 34556
0.0184569 17.78071141242981 34 54.7894736842 34.9835735098 120.0 3.0 54.7894736842 34.9835735098 1041 35597
0.0203717 18.134108304977417 35 60.3888888889 34.3836829662 120.0 3.0 60.3888888889 34.3836829662 1087 36684
0.00940327 18.41169023513794 36 62.9411764706 28.8474090757 102.0 15.0 62.9411764706 28.8474090757 1070 37754
0.0700241 18.694947719573975 37 91.8461538462 44.7486074624 244.0 60.0 91.8461538462 44.7486074624 1194 38948
0.0174554 18.94204807281494 38 86.1666666667 45.3446677007 142.0 9.0 86.1666666667 45.3446677007 1034 39982
0.0189856 19.19516634941101 39 169.0 67.9803893291 276.0 78.0 169.0 67.9803893291 1014 40996
0.0298058 19.492891311645508 40 64.25 36.3653337672 111.0 10.0 64.25 36.3653337672 1028 42024
0.0112537 19.779700994491577 41 63.1176470588 29.1666254737 91.0 7.0 63.1176470588 29.1666254737 1073 43097
0.0767165 20.020016193389893 42 66.8 23.3215208195 87.0 13.0 66.8 23.3215208195 1002 44099
0.00656838 20.26701545715332 43 67.375 26.6713212084 92.0 2.0 67.375 26.6713212084 1078 45177
0.0136275 20.50745415687561 44 57.1111111111 28.2191599388 102.0 4.0 57.1111111111 28.2191599388 1028 46205
0.0194944 20.75212025642395 45 45.0 28.3610265344 114.0 5.0 45.0 28.3610265344 1035 47240
0.0222454 21.01098108291626 46 68.3125 28.6175618065 106.0 9.0 68.3125 28.6175618065 1093 48333
0.0427315 21.258219242095947 47 105.0 7.89936706325 116.0 91.0 105.0 7.89936706325 1050 49383
0.0837711 21.511165618896484 48 118.111111111 15.9055856328 136.0 77.0 118.111111111 15.9055856328 1063 50446
0.0367609 21.76816463470459 49 152.285714286 52.9655259464 194.0 35.0 152.285714286 52.9655259464 1066 51512
0.0343097 22.034436225891113 50 182.166666667 120.567293335 363.0 54.0 182.166666667 120.567293335 1093 52605
0.017415 22.33947491645813 51 265.6 109.198168483 438.0 145.0 265.6 109.198168483 1328 53933
-0.00251888 22.73759651184082 52 221.428571429 199.406159199 605.0 26.0 221.428571429 199.406159199 1550 55483
0.021798 23.095412969589233 53 234.333333333 208.72922385 525.0 15.0 234.333333333 208.72922385 1406 56889
0.0238611 23.363054752349854 54 590.0 182.0 772.0 408.0 590.0 182.0 1180 58069
0.00725312 23.75075888633728 55 337.2 345.981155556 1000.0 40.0 337.2 345.981155556 1686 59755
0.0193887 24.05042552947998 56 594.0 406.0 1000.0 188.0 594.0 406.0 1188 60943
0.00442563 24.293947458267212 57 37.962962963 26.2290219265 118.0 6.0 37.962962963 26.2290219265 1025 61968
0.00969861 24.55141019821167 58 36.75 27.6839626086 113.0 8.0 36.75 27.6839626086 1029 62997
0.0151157 24.79852294921875 59 60.0555555556 45.225941698 213.0 3.0 60.0555555556 45.225941698 1081 64078
0.0406449 25.081185817718506 60 131.222222222 88.1939501298 331.0 25.0 131.222222222 88.1939501298 1181 65259
0.00215795 25.364320993423462 61 394.333333333 433.409993219 1000.0 10.0 394.333333333 433.409993219 1183 66442
-0.00445928 25.792022705078125 62 883.5 116.5 1000.0 767.0 883.5 116.5 1767 68209
-0.00490801 26.071626663208008 63 293.75 226.341970257 663.0 49.0 293.75 226.341970257 1175 69384
0.00455188 26.343390464782715 64 134.111111111 94.247245105 293.0 16.0 134.111111111 94.247245105 1207 70591
0.0133085 26.587870121002197 65 171.0 142.885735234 386.0 20.0 171.0 142.885735234 1026 71617
0.00977667 26.93328833580017 66 464.666666667 268.548361049 756.0 108.0 464.666666667 268.548361049 1394 73011
0.00144062 27.178211212158203 67 524.5 279.5 804.0 245.0 524.5 279.5 1049 74060
-0.000323314 27.574430465698242 68 552.0 342.353618354 1000.0 169.0 552.0 342.353618354 1656 75716
0.000839488 28.048272371292114 69 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 77716
0.022433 28.320209980010986 70 502.0 498.0 1000.0 4.0 502.0 498.0 1004 78720
-0.00272391 28.62666368484497 71 191.0 177.37624794 500.0 11.0 191.0 177.37624794 1146 79866
0.0116535 28.88386559486389 72 504.5 322.5 827.0 182.0 504.5 322.5 1009 80875
-0.00123866 29.380232334136963 73 468.25 462.115989228 1000.0 4.0 468.25 462.115989228 1873 82748
0.00225924 29.68993091583252 74 93.8333333333 106.533119524 342.0 4.0 93.8333333333 106.533119524 1126 83874
0.00238417 29.99078869819641 75 135.625 167.340175615 548.0 5.0 135.625 167.340175615 1085 84959
0.0485598 30.25145173072815 76 159.0 110.339735104 354.0 6.0 159.0 110.339735104 1113 86072
0.0292388 30.546036958694458 77 293.0 54.831560255 356.0 215.0 293.0 54.831560255 1172 87244
0.00610909 31.047698974609375 78 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 89244
-0.00502772 31.31730628013611 79 501.0 499.0 1000.0 2.0 501.0 499.0 1002 90246
0.0747514 31.608322381973267 80 11.1777777778 21.8807768386 124.0 2.0 11.1777777778 21.8807768386 1006 91252
0.0528806 31.85103154182434 81 77.0769230769 71.2800128836 197.0 2.0 77.0769230769 71.2800128836 1002 92254
0.00977656 32.35729503631592 82 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 94254
0.0142199 32.908666133880615 83 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 96254
-0.00962702 33.42824339866638 84 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 98254
0.0022073 33.895281076431274 85 748.5 251.5 1000.0 497.0 748.5 251.5 1497 99751
0.00852792 34.178210973739624 86 548.0 435.0 983.0 113.0 548.0 435.0 1096 100847
0.0108218 34.48817276954651 87 582.5 417.5 1000.0 165.0 582.5 417.5 1165 102012
0.00594607 34.85589289665222 88 294.4 357.798043594 1000.0 26.0 294.4 357.798043594 1472 103484
-0.00289746 35.1089870929718 89 171.5 126.754026892 396.0 20.0 171.5 126.754026892 1029 104513
0.00586876 35.36204195022583 90 273.25 90.7561981354 406.0 154.0 273.25 90.7561981354 1093 105606
0.0142663 35.61124539375305 91 202.4 90.3893799072 267.0 29.0 202.4 90.3893799072 1012 106618
-0.00356334 35.98733139038086 92 480.0 372.626712229 1000.0 146.0 480.0 372.626712229 1440 108058
0.00664708 36.43728995323181 93 577.0 355.0 932.0 222.0 577.0 355.0 1154 109212
0.00380704 36.77241110801697 94 534.5 170.5 705.0 364.0 534.5 170.5 1069 110281
0.0267115 37.09428930282593 95 505.0 495.0 1000.0 10.0 505.0 495.0 1010 111291
0.00592971 37.39833879470825 96 257.75 123.232250243 414.0 98.0 257.75 123.232250243 1031 112322
0.0147735 37.911346435546875 97 653.0 248.162581117 1000.0 434.0 653.0 248.162581117 1959 114281
-0.000496693 38.166609048843384 98 501.0 499.0 1000.0 2.0 501.0 499.0 1002 115283
-0.00688129 38.42163801193237 99 169.0 123.384223735 328.0 3.0 169.0 123.384223735 1014 116297
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_0.02_InvertedPendulum-v1_02-02-2018_10-42-58/41/params.json
================================================
{"animate" : false,
"env_name" : "InvertedPendulum-v1",
"exp_name" : "InvertedPendulum_sb_rtg_na_0.02",
"gamma" : 1.0,
"learning_rate" : 0.02,
"logdir" : "data/InvertedPendulum_sb_rtg_na_0.02_InvertedPendulum-v1_02-02-2018_10-42-58/41",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 2,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 41,
"size" : 32}
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_bl_0.02_InvertedPendulum-v1_02-02-2018_10-42-44/1/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.65681 5.921943664550781 0 9.70192307692 6.05087375714 31.0 3.0 9.70192307692 6.05087375714 1009 1009
0.213782 6.246542930603027 1 23.6046511628 12.8608646222 78.0 6.0 23.6046511628 12.8608646222 1015 2024
-0.00181338 6.515802621841431 2 25.45 10.3003640712 51.0 10.0 25.45 10.3003640712 1018 3042
0.0170982 6.788865089416504 3 23.3953488372 9.59200135501 46.0 6.0 23.3953488372 9.59200135501 1006 4048
0.0105337 7.107732534408569 4 28.0540540541 11.5546783457 53.0 8.0 28.0540540541 11.5546783457 1038 5086
0.00721723 7.417774200439453 5 29.5277777778 16.1305199184 78.0 9.0 29.5277777778 16.1305199184 1063 6149
0.0344248 7.685825347900391 6 23.9761904762 9.80643155145 54.0 7.0 23.9761904762 9.80643155145 1007 7156
0.0461275 7.953003883361816 7 46.2272727273 22.1070367616 114.0 15.0 46.2272727273 22.1070367616 1017 8173
0.0460937 8.221400260925293 8 53.0 23.6197954445 109.0 15.0 53.0 23.6197954445 1007 9180
0.0322253 8.519217014312744 9 86.6153846154 41.2469830347 150.0 8.0 86.6153846154 41.2469830347 1126 10306
0.00211605 8.788473844528198 10 81.1538461538 26.5788989581 135.0 36.0 81.1538461538 26.5788989581 1055 11361
0.0010847 9.04500961303711 11 143.857142857 98.3716401807 343.0 30.0 143.857142857 98.3716401807 1007 12368
0.0189489 9.322344303131104 12 119.555555556 33.3969762807 164.0 53.0 119.555555556 33.3969762807 1076 13444
0.00470537 9.583792924880981 13 175.333333333 91.3503633758 378.0 112.0 175.333333333 91.3503633758 1052 14496
-0.00394302 9.892807722091675 14 178.571428571 54.4606204856 296.0 120.0 178.571428571 54.4606204856 1250 15746
0.0215333 10.148624420166016 15 254.25 92.9068754183 380.0 165.0 254.25 92.9068754183 1017 16763
0.0196541 10.43825078010559 16 157.428571429 49.7159277233 260.0 112.0 157.428571429 49.7159277233 1102 17865
0.0422502 10.708437204360962 17 211.6 72.1598226162 323.0 133.0 211.6 72.1598226162 1058 18923
0.0336627 11.081825971603394 18 709.5 290.5 1000.0 419.0 709.5 290.5 1419 20342
0.00291193 11.382060527801514 19 567.5 432.5 1000.0 135.0 567.5 432.5 1135 21477
0.000888654 11.64992094039917 20 337.666666667 215.513856219 635.0 131.0 337.666666667 215.513856219 1013 22490
0.00609263 11.917691469192505 21 261.25 191.741199277 476.0 57.0 261.25 191.741199277 1045 23535
-0.000509544 12.285603523254395 22 711.0 289.0 1000.0 422.0 711.0 289.0 1422 24957
0.00338517 12.744702577590942 23 869.5 18.5 888.0 851.0 869.5 18.5 1739 26696
0.00491164 13.292344570159912 24 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 28696
0.00209816 13.579151630401611 25 513.0 487.0 1000.0 26.0 513.0 487.0 1026 29722
0.0241206 13.880393266677856 26 548.5 155.5 704.0 393.0 548.5 155.5 1097 30819
-0.000372243 14.37480354309082 27 920.0 80.0 1000.0 840.0 920.0 80.0 1840 32659
0.0119054 14.738826274871826 28 665.5 334.5 1000.0 331.0 665.5 334.5 1331 33990
0.00447677 15.030537843704224 29 279.0 148.988254571 488.0 135.0 279.0 148.988254571 1116 35106
0.0083901 15.314415216445923 30 359.333333333 126.915544972 472.0 182.0 359.333333333 126.915544972 1078 36184
0.0111767 15.718443393707275 31 753.0 247.0 1000.0 506.0 753.0 247.0 1506 37690
0.013445 16.28428030014038 32 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 39690
0.00557792 16.843411445617676 33 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 41690
0.00263344 17.3973171710968 34 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 43690
0.0203104 17.947505950927734 35 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 45690
0.00269564 18.511975526809692 36 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 47690
-0.00128667 19.069863319396973 37 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 49690
0.00108515 19.625020027160645 38 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 51690
0.00135699 20.182510375976562 39 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 53690
0.0101074 20.75623846054077 40 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 55690
0.0237509 21.312490701675415 41 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 57690
0.00408293 21.88839054107666 42 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 59690
-0.00113464 22.431108951568604 43 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 61690
0.00294532 22.979462146759033 44 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 63690
-0.00747096 23.50528383255005 45 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 65690
0.0338572 24.04133415222168 46 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 67690
0.0155495 24.4175763130188 47 463.0 394.827388445 1000.0 62.0 463.0 394.827388445 1389 69079
-0.00654473 24.68772792816162 48 41.9583333333 33.1127860082 123.0 5.0 41.9583333333 33.1127860082 1007 70086
0.0240096 24.96385383605957 49 24.8536585366 19.7033623175 91.0 5.0 24.8536585366 19.7033623175 1019 71105
0.0228321 25.250755786895752 50 54.05 48.3730038348 205.0 8.0 54.05 48.3730038348 1081 72186
0.0292024 25.515681743621826 51 171.333333333 144.748824597 418.0 29.0 171.333333333 144.748824597 1028 73214
-0.0080143 26.051583766937256 52 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 75214
-3.96738e-05 26.587148189544678 53 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 77214
0.00652049 27.122626066207886 54 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 79214
0.006655 27.655648708343506 55 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 81214
0.00732646 28.18738031387329 56 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 83214
0.0028464 28.49863362312317 57 588.0 412.0 1000.0 176.0 588.0 412.0 1176 84390
0.00461558 28.867473602294922 58 676.5 323.5 1000.0 353.0 676.5 323.5 1353 85743
0.000517682 29.39583134651184 59 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 87743
0.0112258 29.933870553970337 60 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 89743
0.001065 30.463274240493774 61 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 91743
0.0131858 30.996042490005493 62 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 93743
0.000513528 31.33595371246338 63 634.0 245.0 879.0 389.0 634.0 245.0 1268 95011
0.00287981 31.86590576171875 64 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 97011
0.00417976 32.409926652908325 65 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 99011
0.0111535 32.93211221694946 66 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 101011
0.00722502 33.46823453903198 67 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 103011
0.000704715 34.00064182281494 68 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 105011
0.000176819 34.54117393493652 69 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 107011
0.00250239 35.07385015487671 70 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 109011
0.0210343 35.60860753059387 71 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 111011
0.0207027 36.14377760887146 72 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 113011
0.00960941 36.68504881858826 73 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 115011
-0.0031522 37.1137318611145 74 803.5 196.5 1000.0 607.0 803.5 196.5 1607 116618
0.00255869 37.451183557510376 75 426.333333333 154.450279666 541.0 208.0 426.333333333 154.450279666 1279 117897
-0.000141602 37.75602674484253 76 73.9375 51.2121430302 231.0 27.0 73.9375 51.2121430302 1183 119080
0.0419858 38.043612480163574 77 111.3 80.2459344765 330.0 38.0 111.3 80.2459344765 1113 120193
-0.00531841 38.435373306274414 78 499.0 384.007812421 1000.0 67.0 499.0 384.007812421 1497 121690
-0.000429136 38.96215629577637 79 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 123690
0.00150048 39.50255823135376 80 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 125690
-0.000609376 40.03552198410034 81 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 127690
0.0185778 40.57927131652832 82 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 129690
0.0134202 41.11819672584534 83 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 131690
0.028029 41.648770809173584 84 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 133690
-0.0119552 42.178263902664185 85 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 135690
0.00153149 42.71791076660156 86 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 137690
0.0432963 43.2538685798645 87 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 139690
0.0247108 43.78805899620056 88 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 141690
-0.00662904 44.32231378555298 89 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 143690
0.0525039 44.63638234138489 90 171.428571429 72.1008364185 257.0 80.0 171.428571429 72.1008364185 1200 144890
0.0224897 45.16150736808777 91 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 146890
0.0048047 45.691975831985474 92 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 148890
0.0101704 46.215564489364624 93 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 150890
-0.00442803 46.75301814079285 94 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 152890
0.0129944 47.29700326919556 95 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 154890
-0.00437123 47.828943967819214 96 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 156890
0.00610429 48.35720872879028 97 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 158890
0.00935259 48.90680003166199 98 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 160890
-0.00316111 49.440929651260376 99 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 162890
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_bl_0.02_InvertedPendulum-v1_02-02-2018_10-42-44/1/params.json
================================================
{"animate" : false,
"env_name" : "InvertedPendulum-v1",
"exp_name" : "InvertedPendulum_sb_rtg_na_bl_0.02",
"gamma" : 1.0,
"learning_rate" : 0.02,
"logdir" : "data/InvertedPendulum_sb_rtg_na_bl_0.02_InvertedPendulum-v1_02-02-2018_10-42-44/1",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 2,
"nn_baseline" : true,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 1,
"size" : 32}
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_bl_0.02_InvertedPendulum-v1_02-02-2018_10-42-44/11/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
11.7045 7.2061004638671875 0 8.5 2.13823148847 15.0 5.0 8.5 2.13823148847 1003 1003
1.55378 7.533061742782593 1 13.8356164384 1.81329714548 18.0 10.0 13.8356164384 1.81329714548 1010 2013
1.48607 7.796994924545288 2 48.8095238095 10.5677814387 75.0 39.0 48.8095238095 10.5677814387 1025 3038
0.725455 8.060013055801392 3 42.375 3.7728470682 48.0 36.0 42.375 3.7728470682 1017 4055
0.148527 8.33285903930664 4 20.44 2.53108672313 26.0 14.0 20.44 2.53108672313 1022 5077
0.663771 8.605287313461304 5 18.9622641509 2.51007226951 26.0 14.0 18.9622641509 2.51007226951 1005 6082
0.0121059 8.890965461730957 6 20.7142857143 4.43547848465 32.0 13.0 20.7142857143 4.43547848465 1015 7097
0.0104453 9.166807413101196 7 32.0625 11.2414898368 68.0 18.0 32.0625 11.2414898368 1026 8123
-0.0215238 9.42681360244751 8 52.7368421053 16.0782366972 96.0 24.0 52.7368421053 16.0782366972 1002 9125
0.020923 9.702447891235352 9 43.7826086957 12.4165265805 78.0 27.0 43.7826086957 12.4165265805 1007 10132
0.0449551 9.974973440170288 10 39.8846153846 10.5841933055 64.0 19.0 39.8846153846 10.5841933055 1037 11169
0.10827 10.244594812393188 11 44.3913043478 10.8857271149 70.0 27.0 44.3913043478 10.8857271149 1021 12190
0.0227503 10.522151231765747 12 44.3913043478 12.5515948421 66.0 24.0 44.3913043478 12.5515948421 1021 13211
0.023549 10.788429737091064 13 49.4761904762 11.0264575653 69.0 22.0 49.4761904762 11.0264575653 1039 14250
0.0232301 11.050525188446045 14 65.5 12.2780291578 94.0 53.0 65.5 12.2780291578 1048 15298
0.0150099 11.313689708709717 15 80.3076923077 20.0552491321 118.0 45.0 80.3076923077 20.0552491321 1044 16342
0.0216235 11.579869747161865 16 80.0769230769 18.4243214611 110.0 45.0 80.0769230769 18.4243214611 1041 17383
0.0390359 11.864346742630005 17 60.0 23.8992985376 103.0 21.0 60.0 23.8992985376 1020 18403
-0.00208596 12.144469261169434 18 43.0 21.0792156717 101.0 20.0 43.0 21.0792156717 1032 19435
0.0615025 12.426112413406372 19 40.0384615385 12.0654649221 71.0 21.0 40.0384615385 12.0654649221 1041 20476
0.0103757 12.696955919265747 20 61.0588235294 14.0313539166 106.0 44.0 61.0588235294 14.0313539166 1038 21514
0.04426 12.965277671813965 21 67.4 17.4195292703 110.0 41.0 67.4 17.4195292703 1011 22525
0.00831573 13.231522560119629 22 56.5 9.90650740114 73.0 40.0 56.5 9.90650740114 1017 23542
0.0325927 13.506860971450806 23 75.9285714286 16.3115396738 112.0 49.0 75.9285714286 16.3115396738 1063 24605
-0.000654949 13.768703937530518 24 68.9333333333 13.7572607092 110.0 53.0 68.9333333333 13.7572607092 1034 25639
0.00590716 14.037980318069458 25 75.0 21.9317121995 138.0 50.0 75.0 21.9317121995 1050 26689
0.102181 14.30500340461731 26 91.1818181818 17.2827721988 127.0 64.0 91.1818181818 17.2827721988 1003 27692
0.0234914 14.576403856277466 27 96.5454545455 14.8591180233 128.0 78.0 96.5454545455 14.8591180233 1062 28754
0.25584 14.85524320602417 28 104.2 20.4489608538 149.0 80.0 104.2 20.4489608538 1042 29796
0.14556 15.149534702301025 29 108.8 16.4972725018 128.0 88.0 108.8 16.4972725018 1088 30884
0.0165137 15.450135946273804 30 108.2 14.6 145.0 91.0 108.2 14.6 1082 31966
0.0684101 15.747101545333862 31 107.1 14.0602275942 133.0 86.0 107.1 14.0602275942 1071 33037
0.0557214 16.042152643203735 32 120.222222222 20.1482162308 162.0 91.0 120.222222222 20.1482162308 1082 34119
0.0972813 16.338342905044556 33 121.666666667 17.4865027315 154.0 101.0 121.666666667 17.4865027315 1095 35214
0.0243035 16.628013849258423 34 88.25 5.70270403698 100.0 78.0 88.25 5.70270403698 1059 36273
0.0733536 16.91515064239502 35 74.2857142857 4.09579176767 83.0 68.0 74.2857142857 4.09579176767 1040 37313
0.0995013 17.21030354499817 36 71.4666666667 4.1931160516 80.0 66.0 71.4666666667 4.1931160516 1072 38385
0.179694 17.54624843597412 37 69.8 3.52514775104 78.0 62.0 69.8 3.52514775104 1047 39432
1.29006 17.813350915908813 38 63.5625 2.14967294024 68.0 61.0 63.5625 2.14967294024 1017 40449
0.127353 18.087921857833862 39 21.5744680851 8.33282328302 51.0 6.0 21.5744680851 8.33282328302 1014 41463
1.42018 18.362076997756958 40 15.1666666667 9.53873019523 36.0 5.0 15.1666666667 9.53873019523 1001 42464
0.132812 18.630330562591553 41 35.8214285714 2.13898459603 41.0 32.0 35.8214285714 2.13898459603 1003 43467
-0.171086 18.909693241119385 42 35.4137931034 1.82921202895 39.0 31.0 35.4137931034 1.82921202895 1027 44494
-0.0264522 19.189926862716675 43 39.8076923077 1.92192273056 45.0 36.0 39.8076923077 1.92192273056 1035 45529
0.0042314 19.466017484664917 44 43.9565217391 3.81619274043 55.0 39.0 43.9565217391 3.81619274043 1011 46540
0.0344692 19.73353862762451 45 55.6111111111 10.6673900218 77.0 42.0 55.6111111111 10.6673900218 1001 47541
-0.0418813 20.021475076675415 46 64.2352941176 18.3352101378 112.0 41.0 64.2352941176 18.3352101378 1092 48633
0.0469023 20.29670810699463 47 56.1666666667 12.6589889012 88.0 41.0 56.1666666667 12.6589889012 1011 49644
-0.0124818 20.607692003250122 48 48.0454545455 11.7993731449 74.0 31.0 48.0454545455 11.7993731449 1057 50701
0.00798526 20.9602108001709 49 42.25 7.87533068089 67.0 35.0 42.25 7.87533068089 1014 51715
0.0113816 21.26477026939392 50 46.5909090909 11.0932374605 78.0 34.0 46.5909090909 11.0932374605 1025 52740
3.59723e-07 21.53436303138733 51 44.4782608696 7.49416912596 59.0 29.0 44.4782608696 7.49416912596 1023 53763
0.0405006 21.839683294296265 52 44.7391304348 12.7457320779 72.0 31.0 44.7391304348 12.7457320779 1029 54792
0.0149869 22.12533688545227 53 45.6956521739 10.8605179739 83.0 32.0 45.6956521739 10.8605179739 1051 55843
0.0525743 22.392416954040527 54 56.2777777778 18.2416055445 112.0 40.0 56.2777777778 18.2416055445 1013 56856
0.0822369 22.657915353775024 55 58.4444444444 10.1610488425 73.0 39.0 58.4444444444 10.1610488425 1052 57908
0.0744667 22.926461458206177 56 46.2727272727 8.25272306675 65.0 36.0 46.2727272727 8.25272306675 1018 58926
0.233698 23.185916423797607 57 38.8461538462 6.75785757865 59.0 30.0 38.8461538462 6.75785757865 1010 59936
0.121131 23.44883108139038 58 35.1379310345 3.98898602561 44.0 27.0 35.1379310345 3.98898602561 1019 60955
0.000561269 23.714980125427246 59 34.8965517241 4.78031038948 45.0 26.0 34.8965517241 4.78031038948 1012 61967
0.00926767 23.996949911117554 60 36.2142857143 6.65130031786 53.0 27.0 36.2142857143 6.65130031786 1014 62981
0.0306266 24.268360137939453 61 41.0 15.4583310872 99.0 24.0 41.0 15.4583310872 1025 64006
0.0193006 24.5430326461792 62 47.0909090909 8.69644175359 64.0 34.0 47.0909090909 8.69644175359 1036 65042
0.0180716 24.828959941864014 63 60.1111111111 17.2494408569 111.0 40.0 60.1111111111 17.2494408569 1082 66124
-0.00867577 25.10487651824951 64 63.0588235294 16.9027341618 103.0 44.0 63.0588235294 16.9027341618 1072 67196
0.00972628 25.362435817718506 65 63.8125 13.9831092304 87.0 41.0 63.8125 13.9831092304 1021 68217
0.018861 25.625185012817383 66 59.1176470588 16.3415110286 104.0 34.0 59.1176470588 16.3415110286 1005 69222
0.0124581 25.889661073684692 67 56.1666666667 12.5620681241 86.0 41.0 56.1666666667 12.5620681241 1011 70233
0.0252474 26.15059471130371 68 74.3571428571 30.9921813708 183.0 50.0 74.3571428571 30.9921813708 1041 71274
-0.00370035 26.414311408996582 69 68.8 13.1260555131 94.0 48.0 68.8 13.1260555131 1032 72306
0.0321889 26.69553780555725 70 70.5333333333 15.3573724604 115.0 51.0 70.5333333333 15.3573724604 1058 73364
0.058332 26.990634441375732 71 68.6 22.0448028645 114.0 38.0 68.6 22.0448028645 1029 74393
0.00610398 27.235929012298584 72 77.1538461538 20.0032541731 111.0 50.0 77.1538461538 20.0032541731 1003 75396
-0.0117332 27.49501061439514 73 93.5454545455 46.5410154133 206.0 34.0 93.5454545455 46.5410154133 1029 76425
-0.130916 27.747349739074707 74 92.3636363636 28.5251809883 141.0 43.0 92.3636363636 28.5251809883 1016 77441
-0.0590201 28.00259757041931 75 91.6363636364 18.0970752397 119.0 68.0 91.6363636364 18.0970752397 1008 78449
-0.113362 28.273985385894775 76 108.0 26.7507009254 153.0 74.0 108.0 26.7507009254 1080 79529
-0.166386 28.527508974075317 77 91.5454545455 22.2398644386 149.0 70.0 91.5454545455 22.2398644386 1007 80536
0.00999315 28.799049854278564 78 97.2727272727 25.8389800991 156.0 67.0 97.2727272727 25.8389800991 1070 81606
-0.0325427 29.063709259033203 79 104.6 29.3843495759 170.0 56.0 104.6 29.3843495759 1046 82652
-0.0107769 29.33789825439453 80 127.25 29.7058495923 191.0 90.0 127.25 29.7058495923 1018 83670
0.0353046 29.612918853759766 81 107.4 21.932624102 152.0 85.0 107.4 21.932624102 1074 84744
-0.0107984 29.89547896385193 82 89.25 18.8905840743 142.0 74.0 89.25 18.8905840743 1071 85815
0.00126684 30.217963933944702 83 80.1538461538 8.92572904884 103.0 66.0 80.1538461538 8.92572904884 1042 86857
0.0232354 30.540754795074463 84 88.5833333333 15.2559187057 127.0 73.0 88.5833333333 15.2559187057 1063 87920
0.0352949 30.80761194229126 85 102.7 17.3611635555 133.0 75.0 102.7 17.3611635555 1027 88947
0.00743975 31.07540249824524 86 104.4 37.2188124475 206.0 67.0 104.4 37.2188124475 1044 89991
0.0228269 31.34382176399231 87 79.2307692308 19.4230388423 130.0 60.0 79.2307692308 19.4230388423 1030 91021
0.0141842 31.61484980583191 88 69.6 10.1836470219 93.0 53.0 69.6 10.1836470219 1044 92065
0.00484906 31.87059497833252 89 71.5714285714 14.6906884294 101.0 53.0 71.5714285714 14.6906884294 1002 93067
0.0325615 32.14302849769592 90 76.0714285714 14.8538801362 121.0 59.0 76.0714285714 14.8538801362 1065 94132
0.0134502 32.40703630447388 91 88.3333333333 30.370855913 159.0 62.0 88.3333333333 30.370855913 1060 95192
0.0419024 32.68495154380798 92 81.4615384615 12.8219486375 108.0 63.0 81.4615384615 12.8219486375 1059 96251
0.0182182 32.945680379867554 93 78.6923076923 17.9717068895 126.0 63.0 78.6923076923 17.9717068895 1023 97274
0.0209174 33.211605072021484 94 78.2307692308 22.038964956 128.0 56.0 78.2307692308 22.038964956 1017 98291
0.012873 33.491243839263916 95 87.4166666667 18.7459254832 116.0 54.0 87.4166666667 18.7459254832 1049 99340
0.11335 33.76195931434631 96 76.5 13.5843923046 112.0 58.0 76.5 13.5843923046 1071 100411
0.0211067 34.03915071487427 97 76.5 20.095308621 124.0 51.0 76.5 20.095308621 1071 101482
0.0844738 34.28899121284485 98 78.0769230769 24.6060078294 153.0 55.0 78.0769230769 24.6060078294 1015 102497
0.0761199 34.57843351364136 99 62.0588235294 13.1528149 96.0 46.0 62.0588235294 13.1528149 1055 103552
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_bl_0.02_InvertedPendulum-v1_02-02-2018_10-42-44/11/params.json
================================================
{"animate" : false,
"env_name" : "InvertedPendulum-v1",
"exp_name" : "InvertedPendulum_sb_rtg_na_bl_0.02",
"gamma" : 1.0,
"learning_rate" : 0.02,
"logdir" : "data/InvertedPendulum_sb_rtg_na_bl_0.02_InvertedPendulum-v1_02-02-2018_10-42-44/11",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 2,
"nn_baseline" : true,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 11,
"size" : 32}
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_bl_0.02_InvertedPendulum-v1_02-02-2018_10-42-44/21/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.333068 6.829823732376099 0 9.22018348624 5.87383843394 40.0 3.0 9.22018348624 5.87383843394 1005 1005
0.180942 7.162767648696899 1 18.7777777778 11.7215639626 55.0 4.0 18.7777777778 11.7215639626 1014 2019
0.0613567 7.43256950378418 2 37.7407407407 17.5806977332 97.0 16.0 37.7407407407 17.5806977332 1019 3038
-0.00184545 7.704278945922852 3 37.7407407407 20.6766868049 79.0 11.0 37.7407407407 20.6766868049 1019 4057
0.0204356 7.991598606109619 4 32.78125 19.4192790401 91.0 8.0 32.78125 19.4192790401 1049 5106
0.0438514 8.269036293029785 5 39.5769230769 18.6695413749 87.0 7.0 39.5769230769 18.6695413749 1029 6135
0.0223141 8.569506168365479 6 80.1428571429 53.5468515052 217.0 33.0 80.1428571429 53.5468515052 1122 7257
0.0391197 8.86056137084961 7 59.5555555556 18.7889513108 93.0 26.0 59.5555555556 18.7889513108 1072 8329
0.00883168 9.195728302001953 8 92.0 24.969071778 117.0 40.0 92.0 24.969071778 1012 9341
0.0231038 9.457578897476196 9 64.5 20.9970235986 97.0 28.0 64.5 20.9970235986 1032 10373
0.0157582 9.731855630874634 10 68.8666666667 10.0456734745 87.0 50.0 68.8666666667 10.0456734745 1033 11406
0.0188608 10.000314235687256 11 68.4666666667 7.88979650491 80.0 53.0 68.4666666667 7.88979650491 1027 12433
0.0296759 10.273316383361816 12 63.75 9.99687451157 86.0 44.0 63.75 9.99687451157 1020 13453
0.0329861 10.529916763305664 13 91.2727272727 16.2653614614 117.0 66.0 91.2727272727 16.2653614614 1004 14457
0.00833977 10.794724941253662 14 147.0 29.5006053207 188.0 107.0 147.0 29.5006053207 1029 15486
-0.0080251 11.065210819244385 15 87.0 13.4350288425 106.0 62.0 87.0 13.4350288425 1044 16530
0.014735 11.341739177703857 16 65.5625 4.93670879737 73.0 54.0 65.5625 4.93670879737 1049 17579
0.0074826 11.607939004898071 17 57.3333333333 6.72474700061 72.0 46.0 57.3333333333 6.72474700061 1032 18611
0.00503144 11.879899978637695 18 50.55 3.73463518968 57.0 42.0 50.55 3.73463518968 1011 19622
0.00449304 12.146260261535645 19 45.7272727273 9.18586769387 56.0 7.0 45.7272727273 9.18586769387 1006 20628
0.0163741 12.414733648300171 20 48.9523809524 2.768465115 52.0 43.0 48.9523809524 2.768465115 1028 21656
0.00138097 12.686365127563477 21 47.3181818182 9.41655391336 56.0 6.0 47.3181818182 9.41655391336 1041 22697
0.0540504 12.959871053695679 22 49.9047619048 10.2395347825 60.0 6.0 49.9047619048 10.2395347825 1048 23745
0.0782744 13.232528448104858 23 52.95 16.2403048001 61.0 4.0 52.95 16.2403048001 1059 24804
0.118548 13.508362770080566 24 59.6666666667 24.4472220644 79.0 5.0 59.6666666667 24.4472220644 1074 25878
0.0910905 13.786908149719238 25 82.2307692308 25.2895656384 101.0 16.0 82.2307692308 25.2895656384 1069 26947
0.0813128 14.056621074676514 26 132.125 8.80961832317 145.0 116.0 132.125 8.80961832317 1057 28004
0.0441426 14.37411117553711 27 242.4 16.0822883944 270.0 220.0 242.4 16.0822883944 1212 29216
-0.0111264 14.873215913772583 28 954.0 46.0 1000.0 908.0 954.0 46.0 1908 31124
-0.0142851 15.227061033248901 29 453.0 16.7531091642 473.0 432.0 453.0 16.7531091642 1359 32483
0.0204458 15.507790327072144 30 270.0 34.2709789764 307.0 214.0 270.0 34.2709789764 1080 33563
0.0292773 15.845547676086426 31 336.25 29.7268817739 358.0 285.0 336.25 29.7268817739 1345 34908
0.0290698 16.367355585098267 32 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 36908
0.00882585 16.89005756378174 33 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 38908
0.0397768 17.421409845352173 34 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 40908
0.0109752 17.94705080986023 35 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 42908
-0.00504652 18.2846999168396 36 661.5 157.5 819.0 504.0 661.5 157.5 1323 44231
0.000677077 18.56082820892334 37 505.5 305.5 811.0 200.0 505.5 305.5 1011 45242
0.00247386 18.949516534805298 38 300.0 226.681274039 720.0 54.0 300.0 226.681274039 1500 46742
0.000118754 19.479949712753296 39 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 48742
-0.000196531 20.02278184890747 40 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 50742
0.0038227 20.55748748779297 41 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 52742
0.00758889 20.925259828567505 42 474.0 305.41447248 790.0 61.0 474.0 305.41447248 1422 54164
0.00251664 21.311293601989746 43 750.5 249.5 1000.0 501.0 750.5 249.5 1501 55665
-0.000657629 21.835792303085327 44 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 57665
0.00376529 22.359016180038452 45 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 59665
0.017753 22.876609563827515 46 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 61665
0.00487557 23.315872192382812 47 851.0 149.0 1000.0 702.0 851.0 149.0 1702 63367
0.00685191 23.835811376571655 48 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 65367
-0.00290961 24.128767251968384 49 567.0 433.0 1000.0 134.0 567.0 433.0 1134 66501
0.00306383 24.65101647377014 50 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 68501
0.00452954 25.168304920196533 51 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 70501
0.00718984 25.696613073349 52 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 72501
0.00221317 26.22061848640442 53 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 74501
0.0131383 26.741954565048218 54 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 76501
-0.00373041 27.26637053489685 55 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 78501
-0.00312761 27.792269706726074 56 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 80501
0.00434059 28.315589904785156 57 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 82501
-0.0015044 28.854793310165405 58 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 84501
0.000905775 29.41190481185913 59 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 86501
0.00790499 29.970605611801147 60 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 88501
0.00241479 30.550913095474243 61 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 90501
0.000727966 31.101043462753296 62 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 92501
0.00197815 31.6384174823761 63 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 94501
0.00330443 32.210963010787964 64 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 96501
0.000848343 32.92026734352112 65 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 98501
-0.000675034 33.49156904220581 66 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 100501
0.00256413 34.15747332572937 67 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 102501
0.00199149 34.89345741271973 68 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 104501
0.00844269 35.57814955711365 69 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 106501
0.00448019 36.19399404525757 70 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 108501
-0.000605418 36.736658573150635 71 980.5 19.5 1000.0 961.0 980.5 19.5 1961 110462
0.00327053 37.08866786956787 72 257.2 270.190599392 625.0 4.0 257.2 270.190599392 1286 111748
0.00708093 37.64055061340332 73 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 113748
0.00181299 37.93684911727905 74 215.0 222.662974021 646.0 11.0 215.0 222.662974021 1075 114823
0.0261454 38.311767578125 75 368.0 366.540584383 956.0 36.0 368.0 366.540584383 1472 116295
0.0107399 38.85311532020569 76 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 118295
0.00343675 39.40237641334534 77 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 120295
-0.00274976 39.987062215805054 78 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 122295
-0.00150252 40.5959529876709 79 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 124295
0.00271119 41.14276838302612 80 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 126295
0.00381524 41.670745849609375 81 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 128295
0.0094855 42.208566665649414 82 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 130295
0.00193721 42.74086403846741 83 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 132295
0.00411886 43.26260161399841 84 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 134295
0.00428758 43.78267312049866 85 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 136295
-0.00118438 44.315085649490356 86 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 138295
-0.00149999 44.841583490371704 87 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 140295
0.00618362 45.17485046386719 88 596.5 403.5 1000.0 193.0 596.5 403.5 1193 141488
0.00188103 45.51046824455261 89 626.5 373.5 1000.0 253.0 626.5 373.5 1253 142741
0.0310657 46.03515839576721 90 326.6 193.429677144 679.0 128.0 326.6 193.429677144 1633 144374
-0.00356999 46.55544900894165 91 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 146374
0.0138758 47.0986647605896 92 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 148374
0.0562418 47.611000061035156 93 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 150374
0.0248262 48.13995003700256 94 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 152374
-0.0142432 48.6581757068634 95 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 154374
0.01185 49.1844801902771 96 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 156374
0.13484 49.482844829559326 97 44.2173913043 26.8699873331 88.0 9.0 44.2173913043 26.8699873331 1017 157391
0.00758476 49.82879281044006 98 700.0 300.0 1000.0 400.0 700.0 300.0 1400 158791
-0.0048944 50.35861158370972 99 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 160791
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_bl_0.02_InvertedPendulum-v1_02-02-2018_10-42-44/21/params.json
================================================
{"animate" : false,
"env_name" : "InvertedPendulum-v1",
"exp_name" : "InvertedPendulum_sb_rtg_na_bl_0.02",
"gamma" : 1.0,
"learning_rate" : 0.02,
"logdir" : "data/InvertedPendulum_sb_rtg_na_bl_0.02_InvertedPendulum-v1_02-02-2018_10-42-44/21",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 2,
"nn_baseline" : true,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 21,
"size" : 32}
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_bl_0.02_InvertedPendulum-v1_02-02-2018_10-42-44/31/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.261187 6.814549684524536 0 5.1608040201 3.39734915237 29.0 2.0 5.1608040201 3.39734915237 1027 1027
0.149816 7.168595314025879 1 9.75238095238 7.66163099928 39.0 2.0 9.75238095238 7.66163099928 1024 2051
0.0686981 7.455993175506592 2 16.4262295082 14.6985658009 86.0 2.0 16.4262295082 14.6985658009 1002 3053
-0.00966821 7.737934589385986 3 16.6229508197 11.7336058416 58.0 2.0 16.6229508197 11.7336058416 1014 4067
0.00209253 8.034193992614746 4 12.5925925926 8.15403827512 62.0 2.0 12.5925925926 8.15403827512 1020 5087
0.000551339 8.32432246208191 5 14.3571428571 9.23043988162 59.0 3.0 14.3571428571 9.23043988162 1005 6092
0.0109566 8.60882568359375 6 13.7397260274 8.04274095795 36.0 2.0 13.7397260274 8.04274095795 1003 7095
0.0228034 8.89202618598938 7 15.5846153846 13.448353983 60.0 4.0 15.5846153846 13.448353983 1013 8108
0.035307 9.167156219482422 8 21.2291666667 15.0516327787 67.0 3.0 21.2291666667 15.0516327787 1019 9127
0.0279183 9.440757989883423 9 25.575 14.5737563792 56.0 5.0 25.575 14.5737563792 1023 10150
-0.00336304 9.723110675811768 10 30.0882352941 21.7787911498 84.0 3.0 30.0882352941 21.7787911498 1023 11173
0.0011016 10.000059127807617 11 36.0689655172 23.7471320003 97.0 7.0 36.0689655172 23.7471320003 1046 12219
-0.000987761 10.264888286590576 12 32.4516129032 23.3235845052 118.0 6.0 32.4516129032 23.3235845052 1006 13225
0.00818948 10.52840781211853 13 40.08 22.1791253209 97.0 7.0 40.08 22.1791253209 1002 14227
0.00827829 10.797281980514526 14 33.4666666667 21.2033540324 71.0 3.0 33.4666666667 21.2033540324 1004 15231
0.00828343 11.061412572860718 15 48.3333333333 28.7523636019 94.0 4.0 48.3333333333 28.7523636019 1015 16246
0.00584655 11.34033465385437 16 43.4583333333 22.0037481024 84.0 4.0 43.4583333333 22.0037481024 1043 17289
0.00780668 11.602097511291504 17 48.8095238095 18.9098589746 82.0 9.0 48.8095238095 18.9098589746 1025 18314
0.0150128 11.869722843170166 18 53.5263157895 19.3509646735 89.0 6.0 53.5263157895 19.3509646735 1017 19331
0.00697717 12.139777660369873 19 64.125 19.0554290164 99.0 39.0 64.125 19.0554290164 1026 20357
0.0171597 12.40994668006897 20 73.5 27.1181278326 121.0 26.0 73.5 27.1181278326 1029 21386
0.00292142 12.680831909179688 21 81.0769230769 28.6449392455 116.0 11.0 81.0769230769 28.6449392455 1054 22440
0.00731656 12.96976375579834 22 84.5384615385 21.9356239399 129.0 44.0 84.5384615385 21.9356239399 1099 23539
0.0154747 13.253691911697388 23 96.8181818182 27.6004551406 156.0 52.0 96.8181818182 27.6004551406 1065 24604
0.0258939 13.523565292358398 24 88.5 42.584230258 182.0 14.0 88.5 42.584230258 1062 25666
0.0360049 13.7946138381958 25 113.777777778 23.3370367431 159.0 78.0 113.777777778 23.3370367431 1024 26690
0.0225724 14.050893545150757 26 126.0 40.7369611041 219.0 83.0 126.0 40.7369611041 1008 27698
0.0147664 14.341598272323608 27 121.888888889 27.2251699084 164.0 68.0 121.888888889 27.2251699084 1097 28795
0.0489176 14.665267705917358 28 175.142857143 84.8670027942 377.0 112.0 175.142857143 84.8670027942 1226 30021
0.0196378 14.927969455718994 29 257.5 45.6207189772 292.0 179.0 257.5 45.6207189772 1030 31051
-0.000913583 15.202574253082275 30 133.875 61.9867677412 206.0 16.0 133.875 61.9867677412 1071 32122
-0.0052725 15.492135763168335 31 126.666666667 57.2887423496 190.0 19.0 126.666666667 57.2887423496 1140 33262
0.00480038 15.759851455688477 32 128.875 27.5065333148 150.0 59.0 128.875 27.5065333148 1031 34293
0.00460056 16.027931451797485 33 131.375 36.9118459983 176.0 40.0 131.375 36.9118459983 1051 35344
0.0343875 16.337689638137817 34 82.7142857143 46.743110373 172.0 3.0 82.7142857143 46.743110373 1158 36502
0.0432226 16.62576723098755 35 124.888888889 52.3268455521 179.0 34.0 124.888888889 52.3268455521 1124 37626
0.0163009 16.889965295791626 36 252.0 42.3083916026 294.0 190.0 252.0 42.3083916026 1008 38634
0.0741843 17.244778394699097 37 462.333333333 130.236536945 614.0 296.0 462.333333333 130.236536945 1387 40021
-0.00153908 17.76629877090454 38 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 42021
0.00397327 18.297754287719727 39 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 44021
0.000353709 18.558200359344482 40 506.5 170.5 677.0 336.0 506.5 170.5 1013 45034
0.000139147 19.085195779800415 41 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 47034
0.000794186 19.61284637451172 42 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 49034
0.00205399 20.143547773361206 43 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 51034
0.0100068 20.668839931488037 44 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 53034
-0.0017142 21.201462507247925 45 986.0 14.0 1000.0 972.0 986.0 14.0 1972 55006
0.000979208 21.68143630027771 46 909.0 91.0 1000.0 818.0 909.0 91.0 1818 56824
0.00900848 22.134698390960693 47 839.5 160.5 1000.0 679.0 839.5 160.5 1679 58503
0.000321848 22.676936626434326 48 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 60503
0.00229737 23.21058416366577 49 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 62503
0.00108273 23.64555335044861 50 800.5 199.5 1000.0 601.0 800.5 199.5 1601 64104
0.00748854 24.117977380752563 51 587.0 377.773300627 1000.0 87.0 587.0 377.773300627 1761 65865
0.00315187 24.68308115005493 52 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 67865
-0.000595403 25.195835828781128 53 897.5 102.5 1000.0 795.0 897.5 102.5 1795 69660
0.00478997 25.756155490875244 54 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 71660
0.00293986 26.362465620040894 55 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 73660
0.00770111 26.915618658065796 56 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 75660
0.00912193 27.43938112258911 57 905.0 95.0 1000.0 810.0 905.0 95.0 1810 77470
0.0147179 28.00083088874817 58 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 79470
-0.00319337 28.566638708114624 59 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 81470
-6.54468e-05 29.288985013961792 60 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 83470
0.00731703 29.90354824066162 61 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 85470
0.00676064 30.50639772415161 62 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 87470
0.0129207 31.16077160835266 63 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 89470
-0.00384103 31.708671808242798 64 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 91470
0.00458757 32.25620794296265 65 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 93470
0.0022985 32.79607582092285 66 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 95470
0.00225006 33.34905982017517 67 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 97470
0.00274819 33.99421834945679 68 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 99470
0.00178732 34.54354643821716 69 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 101470
0.0154055 34.83283615112305 70 510.5 489.5 1000.0 21.0 510.5 489.5 1021 102491
-0.000178853 35.43658399581909 71 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 104491
0.00030558 36.058197021484375 72 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 106491
0.00278854 36.895596742630005 73 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 108491
0.00502623 37.589388608932495 74 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 110491
0.010919 38.13655233383179 75 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 112491
0.00901791 38.887964487075806 76 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 114491
-0.00101603 39.41062140464783 77 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 116491
0.0165895 39.97598671913147 78 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 118491
-0.000624219 40.28956913948059 79 148.0 119.799833055 429.0 46.0 148.0 119.799833055 1184 119675
0.0458347 40.598774433135986 80 171.142857143 161.259709406 500.0 27.0 171.142857143 161.259709406 1198 120873
-0.00745544 41.14340686798096 81 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 122873
0.000799835 41.846447467803955 82 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 124873
0.0019871 42.448155879974365 83 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 126873
0.00755213 42.98855447769165 84 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 128873
-0.00127269 43.563596963882446 85 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 130873
0.000786208 44.13716149330139 86 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 132873
0.00170027 44.651320934295654 87 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 134873
0.000442943 45.17590117454529 88 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 136873
0.000724137 45.72867941856384 89 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 138873
0.00104072 46.16289210319519 90 796.0 204.0 1000.0 592.0 796.0 204.0 1592 140465
0.000373599 46.476778745651245 91 634.0 366.0 1000.0 268.0 634.0 366.0 1268 141733
-0.000556823 46.86446285247803 92 750.5 249.5 1000.0 501.0 750.5 249.5 1501 143234
0.00380959 47.203986406326294 93 262.4 369.008726184 1000.0 60.0 262.4 369.008726184 1312 144546
0.000191225 47.61037063598633 94 514.333333333 345.249989943 1000.0 228.0 514.333333333 345.249989943 1543 146089
0.00565167 48.076863288879395 95 899.0 39.0 938.0 860.0 899.0 39.0 1798 147887
0.00097426 48.38835573196411 96 595.0 229.0 824.0 366.0 595.0 229.0 1190 149077
0.0108343 48.681633710861206 97 191.333333333 115.025601015 359.0 55.0 191.333333333 115.025601015 1148 150225
-0.000372803 49.05965733528137 98 717.0 283.0 1000.0 434.0 717.0 283.0 1434 151659
0.00265753 49.43298268318176 99 360.25 204.785711171 620.0 82.0 360.25 204.785711171 1441 153100
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_bl_0.02_InvertedPendulum-v1_02-02-2018_10-42-44/31/params.json
================================================
{"animate" : false,
"env_name" : "InvertedPendulum-v1",
"exp_name" : "InvertedPendulum_sb_rtg_na_bl_0.02",
"gamma" : 1.0,
"learning_rate" : 0.02,
"logdir" : "data/InvertedPendulum_sb_rtg_na_bl_0.02_InvertedPendulum-v1_02-02-2018_10-42-44/31",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 2,
"nn_baseline" : true,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 31,
"size" : 32}
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_bl_0.02_InvertedPendulum-v1_02-02-2018_10-42-44/41/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0965388 7.015215873718262 0 3.54416961131 2.02824392691 12.0 1.0 3.54416961131 2.02824392691 1003 1003
0.057816 7.518160104751587 1 4.53846153846 3.31929984775 25.0 1.0 4.53846153846 3.31929984775 1003 2006
0.0379587 7.894266128540039 2 5.72571428571 4.31398674461 30.0 1.0 5.72571428571 4.31398674461 1002 3008
0.0191689 8.222988367080688 3 5.82558139535 3.75620992945 23.0 1.0 5.82558139535 3.75620992945 1002 4010
0.00193715 8.559008359909058 4 5.66666666667 3.4960294939 20.0 2.0 5.66666666667 3.4960294939 1003 5013
0.000795811 8.897673845291138 5 5.78285714286 3.95961655534 22.0 1.0 5.78285714286 3.95961655534 1012 6025
0.00381485 9.229877233505249 6 5.9880952381 3.97909432032 22.0 1.0 5.9880952381 3.97909432032 1006 7031
0.00739726 9.569504022598267 7 6.14110429448 4.27846268563 27.0 2.0 6.14110429448 4.27846268563 1001 8032
0.0106754 9.91623830795288 8 5.88 4.54217065792 34.0 2.0 5.88 4.54217065792 1029 9061
0.00899585 10.225929498672485 9 7.42962962963 5.81637629424 35.0 2.0 7.42962962963 5.81637629424 1003 10064
0.0208958 10.619548320770264 10 6.42948717949 3.81648277379 20.0 2.0 6.42948717949 3.81648277379 1003 11067
0.0132233 10.999320983886719 11 7.38686131387 4.66114264238 23.0 1.0 7.38686131387 4.66114264238 1012 12079
0.0150561 11.417155981063843 12 8.5811965812 6.82283661118 31.0 2.0 8.5811965812 6.82283661118 1004 13083
0.0128231 11.79023289680481 13 8.12096774194 6.08089650375 34.0 2.0 8.12096774194 6.08089650375 1007 14090
0.00707967 12.25986361503601 14 9.46226415094 7.98722391179 48.0 1.0 9.46226415094 7.98722391179 1003 15093
0.0116163 12.616661071777344 15 9.5619047619 7.81320470745 43.0 2.0 9.5619047619 7.81320470745 1004 16097
0.0150719 12.991031169891357 16 8.65517241379 6.46356292303 34.0 2.0 8.65517241379 6.46356292303 1004 17101
0.025462 13.31374478340149 17 10.7553191489 8.19533620643 46.0 2.0 10.7553191489 8.19533620643 1011 18112
0.0215632 13.660294532775879 18 14.3802816901 10.8943275034 45.0 2.0 14.3802816901 10.8943275034 1021 19133
0.00670303 13.953734159469604 19 18.4909090909 12.8443446731 51.0 1.0 18.4909090909 12.8443446731 1017 20150
0.0210106 14.361376523971558 20 14.3285714286 10.993142575 41.0 2.0 14.3285714286 10.993142575 1003 21153
0.0255966 14.69254732131958 21 18.5535714286 11.8922538457 44.0 2.0 18.5535714286 11.8922538457 1039 22192
0.0210514 15.004696130752563 22 24.8292682927 15.1848808616 60.0 2.0 24.8292682927 15.1848808616 1018 23210
0.00662789 15.286370038986206 23 24.023255814 15.7088160288 60.0 2.0 24.023255814 15.7088160288 1033 24243
0.0454191 15.651551723480225 24 18.3035714286 12.8659568003 47.0 2.0 18.3035714286 12.8659568003 1025 25268
-0.000102408 15.955278635025024 25 37.4814814815 24.1267799119 98.0 2.0 37.4814814815 24.1267799119 1012 26280
0.00592934 16.238783597946167 26 36.1785714286 17.109006758 73.0 3.0 36.1785714286 17.109006758 1013 27293
-0.00304552 16.516346216201782 27 36.1428571429 21.5501313979 80.0 4.0 36.1428571429 21.5501313979 1012 28305
0.00650958 16.82654333114624 28 30.1388888889 20.5793218463 95.0 5.0 30.1388888889 20.5793218463 1085 29390
0.0261187 17.0918231010437 29 34.7586206897 22.309198926 97.0 3.0 34.7586206897 22.309198926 1008 30398
0.0429363 17.395127296447754 30 45.6818181818 25.2053139484 95.0 8.0 45.6818181818 25.2053139484 1005 31403
-0.00446444 17.705220699310303 31 55.8947368421 27.3282093254 110.0 8.0 55.8947368421 27.3282093254 1062 32465
0.0153254 17.988741636276245 32 69.5333333333 20.6102455643 116.0 43.0 69.5333333333 20.6102455643 1043 33508
0.00862495 18.294898986816406 33 65.25 21.75 114.0 30.0 65.25 21.75 1044 34552
0.0233489 18.575596570968628 34 58.4444444444 34.8444515306 119.0 2.0 58.4444444444 34.8444515306 1052 35604
0.0151865 18.86219620704651 35 64.7058823529 36.2325247223 126.0 3.0 64.7058823529 36.2325247223 1100 36704
0.00751607 19.134361267089844 36 70.0 32.2035194764 113.0 3.0 70.0 32.2035194764 1050 37754
0.0508118 19.44715905189514 37 70.2 25.2407078612 103.0 5.0 70.2 25.2407078612 1053 38807
0.0692928 19.817426443099976 38 81.1538461538 40.3424688498 163.0 10.0 81.1538461538 40.3424688498 1055 39862
0.0566031 20.134932041168213 39 128.5 54.3920950139 232.0 57.0 128.5 54.3920950139 1028 40890
0.0116623 20.44928216934204 40 66.7333333333 39.3420329362 133.0 13.0 66.7333333333 39.3420329362 1001 41891
0.0417828 20.786069631576538 41 67.4 36.5126462111 118.0 4.0 67.4 36.5126462111 1011 42902
0.00389937 21.076273918151855 42 91.3636363636 40.7771610035 134.0 20.0 91.3636363636 40.7771610035 1005 43907
0.0039189 21.39367413520813 43 93.0 42.5460534793 131.0 2.0 93.0 42.5460534793 1116 45023
-0.0184946 21.7808575630188 44 62.8235294118 29.1915283725 101.0 4.0 62.8235294118 29.1915283725 1068 46091
-0.000730023 22.225303173065186 45 34.4666666667 27.5798638301 97.0 3.0 34.4666666667 27.5798638301 1034 47125
0.000340559 22.6951961517334 46 24.880952381 21.1752352896 80.0 4.0 24.880952381 21.1752352896 1045 48170
0.0292208 23.1264865398407 47 28.7428571429 18.4179149699 65.0 6.0 28.7428571429 18.4179149699 1006 49176
0.00926683 23.545863389968872 48 49.7619047619 24.9149118896 88.0 4.0 49.7619047619 24.9149118896 1045 50221
0.0461256 23.945959091186523 49 61.3529411765 27.3171809252 91.0 6.0 61.3529411765 27.3171809252 1043 51264
0.0266826 24.387595415115356 50 79.1538461538 32.2009224757 105.0 2.0 79.1538461538 32.2009224757 1029 52293
0.0565368 24.7649188041687 51 118.111111111 18.0766543392 144.0 76.0 118.111111111 18.0766543392 1063 53356
0.0314792 25.305351495742798 52 77.0 47.4649668379 163.0 3.0 77.0 47.4649668379 1001 54357
-0.0048259 25.698896646499634 53 281.5 150.539861831 447.0 107.0 281.5 150.539861831 1126 55483
0.0236993 26.0530047416687 54 199.333333333 171.356029625 443.0 14.0 199.333333333 171.356029625 1196 56679
-0.0103388 26.439428567886353 55 695.0 305.0 1000.0 390.0 695.0 305.0 1390 58069
0.00450628 26.799290895462036 56 625.5 374.5 1000.0 251.0 625.5 374.5 1251 59320
-0.00162429 27.234150171279907 57 542.333333333 391.123453088 946.0 13.0 542.333333333 391.123453088 1627 60947
0.00246857 27.55928659439087 58 282.75 236.170886224 682.0 74.0 282.75 236.170886224 1131 62078
0.00190516 27.883344411849976 59 217.6 247.365802002 703.0 5.0 217.6 247.365802002 1088 63166
0.00532123 28.27206778526306 60 149.375 185.508043963 615.0 31.0 149.375 185.508043963 1195 64361
0.00798497 28.66950821876526 61 120.111111111 76.2983099339 246.0 12.0 120.111111111 76.2983099339 1081 65442
-0.000924859 29.21928334236145 62 679.5 320.5 1000.0 359.0 679.5 320.5 1359 66801
-0.000343062 29.654582738876343 63 651.5 348.5 1000.0 303.0 651.5 348.5 1303 68104
0.00506678 30.07858681678772 64 501.666666667 362.557888098 1000.0 148.0 501.666666667 362.557888098 1505 69609
0.00906667 30.349733591079712 65 334.0 226.527408202 546.0 20.0 334.0 226.527408202 1002 70611
0.00572739 30.877410650253296 66 964.5 35.5 1000.0 929.0 964.5 35.5 1929 72540
0.00666748 31.170197248458862 67 502.0 214.0 716.0 288.0 502.0 214.0 1004 73544
0.000269714 31.476089477539062 68 234.4 170.457736697 511.0 5.0 234.4 170.457736697 1172 74716
0.000376643 32.005849838256836 69 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 76716
0.00377248 32.561322927474976 70 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 78716
0.00489545 32.91948485374451 71 230.0 222.743799016 511.0 4.0 230.0 222.743799016 1150 79866
0.00199555 33.41795992851257 72 941.0 59.0 1000.0 882.0 941.0 59.0 1882 81748
0.00225008 33.94421577453613 73 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 83748
0.0144107 34.459471702575684 74 953.5 43.5 997.0 910.0 953.5 43.5 1907 85655
0.00274945 34.99486947059631 75 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 87655
-0.000794724 35.268709659576416 76 258.0 61.069632388 363.0 216.0 258.0 61.069632388 1032 88687
0.0311133 35.559001207351685 77 146.571428571 59.1387162111 197.0 11.0 146.571428571 59.1387162111 1026 89713
0.00577108 35.920496463775635 78 551.0 318.0 869.0 233.0 551.0 318.0 1102 90815
-0.00228181 36.37461471557617 79 481.0 406.989762361 1000.0 6.0 481.0 406.989762361 1443 92258
0.0077017 36.723190784454346 80 501.0 499.0 1000.0 2.0 501.0 499.0 1002 93260
0.0101224 37.292317628860474 81 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 95260
0.00229757 37.8365216255188 82 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 97260
-0.00105143 38.38205409049988 83 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 99260
0.00196272 38.913787841796875 84 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 101260
0.00064279 39.44452905654907 85 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 103260
-0.000336653 39.99968695640564 86 1000.0 0.0 1000.0 1000.0 1000.0 0.0 2000 105260
0.00209258 40.37319827079773 87 456.666666667 384.341283526 1000.0 172.0 456.666666667 384.341283526 1370 106630
0.00447032 40.83456325531006 88 714.0 286.0 1000.0 428.0 714.0 286.0 1428 108058
0.00318981 41.138054609298706 89 501.0 499.0 1000.0 2.0 501.0 499.0 1002 109060
0.0258435 41.67287540435791 90 371.4 355.721014279 1000.0 2.0 371.4 355.721014279 1857 110917
0.00158789 41.99301195144653 91 304.75 179.519323472 467.0 5.0 304.75 179.519323472 1219 112136
0.00359291 42.382558822631836 92 298.6 203.156688297 594.0 4.0 298.6 203.156688297 1493 113629
0.00591366 42.83205246925354 93 853.5 146.5 1000.0 707.0 853.5 146.5 1707 115336
-0.00168001 43.25177454948425 94 184.75 181.913956309 507.0 4.0 184.75 181.913956309 1478 116814
0.00631267 43.54828429222107 95 112.5 100.961626374 300.0 4.0 112.5 100.961626374 1125 117939
0.00505222 43.8476927280426 96 44.2608695652 47.0515142216 175.0 2.0 44.2608695652 47.0515142216 1018 118957
0.0222101 44.1130895614624 97 37.6666666667 36.145795309 127.0 2.0 37.6666666667 36.145795309 1017 119974
0.024137 44.40142297744751 98 59.0 50.8353744367 151.0 4.0 59.0 50.8353744367 1003 120977
0.0144937 44.674586057662964 99 207.8 65.9284460609 290.0 132.0 207.8 65.9284460609 1039 122016
================================================
FILE: hw2/data/InvertedPendulum_sb_rtg_na_bl_0.02_InvertedPendulum-v1_02-02-2018_10-42-44/41/params.json
================================================
{"animate" : false,
"env_name" : "InvertedPendulum-v1",
"exp_name" : "InvertedPendulum_sb_rtg_na_bl_0.02",
"gamma" : 1.0,
"learning_rate" : 0.02,
"logdir" : "data/InvertedPendulum_sb_rtg_na_bl_0.02_InvertedPendulum-v1_02-02-2018_10-42-44/41",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 2,
"nn_baseline" : true,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 41,
"size" : 32}
================================================
FILE: hw2/data/lb_no_rtg_dna_CartPole-v0_24-01-2018_09-28-29/1/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0696182 0.8733839988708496 0 26.8288770053 13.9947515113 75.0 9.0 26.8288770053 13.9947515113 5017 5017
0.0363216 1.606971263885498 1 26.0569948187 13.6943642311 83.0 9.0 26.0569948187 13.6943642311 5029 10046
0.0353184 2.352762460708618 2 26.7914438503 15.6449349939 121.0 9.0 26.7914438503 15.6449349939 5010 15056
0.0379677 3.089353084564209 3 32.5909090909 16.8602404954 96.0 10.0 32.5909090909 16.8602404954 5019 20075
0.0552673 3.824246406555176 4 33.5973154362 18.1821209707 108.0 10.0 33.5973154362 18.1821209707 5006 25081
0.0220718 4.563391208648682 5 34.1360544218 17.9601370598 145.0 11.0 34.1360544218 17.9601370598 5018 30099
0.031868 5.3038318157196045 6 38.0454545455 23.8295282944 181.0 10.0 38.0454545455 23.8295282944 5022 35121
0.0160732 6.034011125564575 7 35.3356643357 17.7594430927 98.0 11.0 35.3356643357 17.7594430927 5053 40174
0.030838 6.772596597671509 8 44.1052631579 22.4074581964 129.0 14.0 44.1052631579 22.4074581964 5028 45202
0.0230446 7.517544507980347 9 40.3709677419 20.0810726733 159.0 13.0 40.3709677419 20.0810726733 5006 50208
0.0225029 8.244481325149536 10 43.7652173913 19.7534060617 97.0 14.0 43.7652173913 19.7534060617 5033 55241
0.0197487 8.954299688339233 11 46.3333333333 22.2431845575 160.0 14.0 46.3333333333 22.2431845575 5004 60245
0.00619507 9.664781332015991 12 49.1078431373 18.0879696032 102.0 15.0 49.1078431373 18.0879696032 5009 65254
0.0174751 10.388200521469116 13 48.9611650485 23.8111185296 146.0 14.0 48.9611650485 23.8111185296 5043 70297
0.0221252 11.119300603866577 14 47.5660377358 22.2583538983 134.0 13.0 47.5660377358 22.2583538983 5042 75339
0.0121307 11.843279123306274 15 50.12 21.9637337445 154.0 19.0 50.12 21.9637337445 5012 80351
0.0241737 12.55958080291748 16 52.9368421053 25.2760800285 140.0 17.0 52.9368421053 25.2760800285 5029 85380
0.0229988 13.293839693069458 17 56.1868131868 27.8299041028 167.0 18.0 56.1868131868 27.8299041028 5113 90493
0.0375404 14.022535562515259 18 57.3295454545 24.4325237742 127.0 18.0 57.3295454545 24.4325237742 5045 95538
0.0472069 14.734794855117798 19 60.3012048193 30.6581363401 188.0 21.0 60.3012048193 30.6581363401 5005 100543
0.0381622 15.44992971420288 20 60.0119047619 24.2896676287 142.0 20.0 60.0119047619 24.2896676287 5041 105584
0.040657 16.163748741149902 21 58.3953488372 25.6126236453 141.0 14.0 58.3953488372 25.6126236453 5022 110606
0.0161018 16.87820601463318 22 57.6896551724 32.1413224001 200.0 21.0 57.6896551724 32.1413224001 5019 115625
0.0059967 17.606189250946045 23 57.1590909091 24.367865559 131.0 23.0 57.1590909091 24.367865559 5030 120655
0.00592422 18.333133220672607 24 69.7083333333 29.8414502459 136.0 25.0 69.7083333333 29.8414502459 5019 125674
0.0250931 19.059171438217163 25 64.7948717949 25.1637503698 134.0 26.0 64.7948717949 25.1637503698 5054 130728
0.012825 19.766155004501343 26 62.024691358 26.3433995334 159.0 23.0 62.024691358 26.3433995334 5024 135752
0.00961304 20.489270210266113 27 65.5064935065 29.4285943536 163.0 22.0 65.5064935065 29.4285943536 5044 140796
0.0176735 21.21580934524536 28 69.8888888889 29.3539489846 152.0 21.0 69.8888888889 29.3539489846 5032 145828
0.0509987 21.942930698394775 29 75.3134328358 35.0322703919 200.0 25.0 75.3134328358 35.0322703919 5046 150874
0.025486 22.705883741378784 30 75.2794117647 37.0305301658 200.0 26.0 75.2794117647 37.0305301658 5119 155993
0.0123367 23.44011664390564 31 78.359375 36.2350689886 197.0 35.0 78.359375 36.2350689886 5015 161008
0.0017128 24.17647886276245 32 75.2089552239 30.9180608539 168.0 28.0 75.2089552239 30.9180608539 5039 166047
0.0229988 24.909669876098633 33 83.3833333333 36.4211896505 200.0 30.0 83.3833333333 36.4211896505 5003 171050
0.00580215 25.658268451690674 34 75.4029850746 29.1537661485 171.0 26.0 75.4029850746 29.1537661485 5052 176102
0.0297165 26.393633365631104 35 74.4852941176 26.6041198971 153.0 25.0 74.4852941176 26.6041198971 5065 181167
0.0181313 27.123620748519897 36 84.1333333333 35.1627011982 198.0 26.0 84.1333333333 35.1627011982 5048 186215
0.00622559 27.888240575790405 37 86.0847457627 37.6762696234 200.0 22.0 86.0847457627 37.6762696234 5079 191294
0.0624084 28.65086340904236 38 95.0925925926 39.446291906 200.0 31.0 95.0925925926 39.446291906 5135 196429
0.0209961 29.393652200698853 39 95.2075471698 46.1888488097 200.0 27.0 95.2075471698 46.1888488097 5046 201475
-0.00279617 30.135545015335083 40 85.0677966102 29.5077492877 198.0 35.0 85.0677966102 29.5077492877 5019 206494
0.0384445 30.86448359489441 41 100.5 42.0985747977 200.0 33.0 100.5 42.0985747977 5025 211519
0.0846672 31.640233993530273 42 88.9655172414 31.8130126907 183.0 36.0 88.9655172414 31.8130126907 5160 216679
0.0377808 32.39010763168335 43 105.291666667 37.6906035667 200.0 38.0 105.291666667 37.6906035667 5054 221733
-0.0144424 33.136738300323486 44 107.127659574 43.306241023 200.0 38.0 107.127659574 43.306241023 5035 226768
0.0991974 33.89745044708252 45 130.461538462 46.0817813457 200.0 60.0 130.461538462 46.0817813457 5088 231856
-0.0526962 34.69429135322571 46 119.302325581 42.9144822326 200.0 39.0 119.302325581 42.9144822326 5130 236986
0.0672226 35.456947565078735 47 133.0 44.6919279183 200.0 58.0 133.0 44.6919279183 5054 242040
-0.0608368 36.231215953826904 48 163.161290323 40.6900929324 200.0 60.0 163.161290323 40.6900929324 5058 247098
-0.515877 37.006874799728394 49 166.161290323 28.6740264331 200.0 111.0 166.161290323 28.6740264331 5151 252249
-0.164619 37.781766176223755 50 175.310344828 27.1789769774 200.0 120.0 175.310344828 27.1789769774 5084 257333
-0.177238 38.5459144115448 51 170.2 32.625552358 200.0 101.0 170.2 32.625552358 5106 262439
0.00646973 39.31731033325195 52 170.9 36.0419662801 200.0 104.0 170.9 36.0419662801 5127 267566
-0.0194168 40.08272957801819 53 165.838709677 35.192646569 200.0 98.0 165.838709677 35.192646569 5141 272707
-0.0979767 40.838207721710205 54 164.096774194 40.8943207972 200.0 57.0 164.096774194 40.8943207972 5087 277794
0.0198669 41.60336518287659 55 159.5625 38.6158464073 200.0 87.0 159.5625 38.6158464073 5106 282900
0.0188675 42.358368158340454 56 169.766666667 37.6604862186 200.0 84.0 169.766666667 37.6604862186 5093 287993
-0.00642395 43.09674644470215 57 159.09375 37.3884669509 200.0 90.0 159.09375 37.3884669509 5091 293084
-0.0349197 43.828078269958496 58 152.212121212 48.8663964454 200.0 40.0 152.212121212 48.8663964454 5023 298107
-0.0180359 44.55853986740112 59 173.034482759 36.7324743654 200.0 100.0 173.034482759 36.7324743654 5018 303125
-0.0159683 45.311683893203735 60 161.6875 38.9650785159 200.0 92.0 161.6875 38.9650785159 5174 308299
0.0398026 46.043479204177856 61 172.448275862 35.263135197 200.0 91.0 172.448275862 35.263135197 5001 313300
0.0378342 46.790393590927124 62 167.6 42.292316087 200.0 79.0 167.6 42.292316087 5028 318328
0.0517883 47.53856921195984 63 176.724137931 34.4272311542 200.0 96.0 176.724137931 34.4272311542 5125 323453
0.0766678 48.28240203857422 64 181.214285714 35.9735588839 200.0 65.0 181.214285714 35.9735588839 5074 328527
-0.00684357 49.04251575469971 65 173.275862069 38.3422847085 200.0 84.0 173.275862069 38.3422847085 5025 333552
-0.00218964 49.78954219818115 66 169.7 41.9206790657 200.0 71.0 169.7 41.9206790657 5091 338643
0.0182648 50.545021057128906 67 178.379310345 33.7295672944 200.0 83.0 178.379310345 33.7295672944 5173 343816
-0.0388336 51.28813290596008 68 187.111111111 26.6309946593 200.0 103.0 187.111111111 26.6309946593 5052 348868
0.00382233 52.03696370124817 69 181.785714286 30.7249981319 200.0 89.0 181.785714286 30.7249981319 5090 353958
-0.0250549 52.78742694854736 70 181.928571429 36.5346494748 200.0 85.0 181.928571429 36.5346494748 5094 359052
-0.00826263 53.52100372314453 71 185.740740741 30.0919487111 200.0 106.0 185.740740741 30.0919487111 5015 364067
-0.0022049 54.27762532234192 72 184.178571429 25.1453681782 200.0 113.0 184.178571429 25.1453681782 5157 369224
0.0967865 55.03714871406555 73 185.814814815 30.7402945081 200.0 99.0 185.814814815 30.7402945081 5017 374241
-0.00389862 55.77925109863281 74 187.666666667 27.6405499222 200.0 93.0 187.666666667 27.6405499222 5067 379308
0.0118713 56.51723384857178 75 192.461538462 23.7069135798 200.0 95.0 192.461538462 23.7069135798 5004 384312
0.0140839 57.26803183555603 76 195.653846154 21.7307692308 200.0 87.0 195.653846154 21.7307692308 5087 389399
-0.0425034 57.99777960777283 77 192.346153846 23.4700173834 200.0 92.0 192.346153846 23.4700173834 5001 394400
-0.0130234 58.742854833602905 78 193.692307692 22.5435804111 200.0 86.0 193.692307692 22.5435804111 5036 399436
0.0836029 59.509639263153076 79 192.0 24.6516470789 200.0 94.0 192.0 24.6516470789 5184 404620
-0.00317383 60.25469207763672 80 196.115384615 19.4230769231 200.0 99.0 196.115384615 19.4230769231 5099 409719
0.0871735 60.997276067733765 81 189.777777778 28.8794856491 200.0 83.0 189.777777778 28.8794856491 5124 414843
-0.00304413 61.73756003379822 82 187.962962963 27.3136534593 200.0 113.0 187.962962963 27.3136534593 5075 419918
0.0582581 62.48872089385986 83 194.115384615 22.8209197601 200.0 86.0 194.115384615 22.8209197601 5047 424965
-0.0770645 63.268754720687866 84 189.481481481 26.2472155424 200.0 104.0 189.481481481 26.2472155424 5116 430081
-0.0524139 64.00893568992615 85 175.344827586 43.0655281475 200.0 61.0 175.344827586 43.0655281475 5085 435166
-0.0425262 64.7614016532898 86 194.884615385 14.8850129146 200.0 142.0 194.884615385 14.8850129146 5067 440233
-0.0806885 65.53559923171997 87 192.444444444 21.0894625844 200.0 110.0 192.444444444 21.0894625844 5196 445429
-0.052536 66.27712678909302 88 195.692307692 13.4986302176 200.0 133.0 195.692307692 13.4986302176 5088 450517
-0.00714111 66.99852752685547 89 185.62962963 35.261087721 200.0 67.0 185.62962963 35.261087721 5012 455529
-0.0360718 67.7715528011322 90 192.185185185 22.9024291725 200.0 101.0 192.185185185 22.9024291725 5189 460718
-0.0298462 68.5326566696167 91 194.576923077 17.6704296167 200.0 111.0 194.576923077 17.6704296167 5059 465777
-0.0052948 69.31969451904297 92 192.592592593 19.2050519188 200.0 129.0 192.592592593 19.2050519188 5200 470977
0.0119324 70.07658791542053 93 193.884615385 20.6422399707 200.0 101.0 193.884615385 20.6422399707 5041 476018
0.0344925 70.85291934013367 94 184.428571429 31.0752871167 200.0 102.0 184.428571429 31.0752871167 5164 481182
0.00389099 71.60849380493164 95 187.074074074 32.8756646754 200.0 72.0 187.074074074 32.8756646754 5051 486233
0.026268 72.36004543304443 96 187.148148148 33.4881999159 200.0 40.0 187.148148148 33.4881999159 5053 491286
0.00260162 73.10664772987366 97 193.038461538 29.2212788237 200.0 50.0 193.038461538 29.2212788237 5019 496305
-0.0186462 73.86835741996765 98 188.407407407 25.5346667178 200.0 106.0 188.407407407 25.5346667178 5087 501392
0.0237198 74.63931894302368 99 177.068965517 42.5999279864 200.0 63.0 177.068965517 42.5999279864 5135 506527
================================================
FILE: hw2/data/lb_no_rtg_dna_CartPole-v0_24-01-2018_09-28-29/1/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "lb_no_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/lb_no_rtg_dna_CartPole-v0_24-01-2018_09-28-29/1",
"max_path_length" : null,
"min_timesteps_per_batch" : 5000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : false,
"seed" : 1,
"size" : 32}
================================================
FILE: hw2/data/lb_no_rtg_dna_CartPole-v0_24-01-2018_09-28-29/11/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0183277 0.8223881721496582 0 18.0649819495 8.24858161419 70.0 8.0 18.0649819495 8.24858161419 5004 5004
0.0212021 1.5629937648773193 1 19.766798419 8.87177901395 56.0 9.0 19.766798419 8.87177901395 5001 10005
0.0210609 2.3035073280334473 2 20.9372384937 10.5016552944 65.0 9.0 20.9372384937 10.5016552944 5004 15009
0.033102 3.0492873191833496 3 23.6650943396 13.0194378806 120.0 8.0 23.6650943396 13.0194378806 5017 20026
0.02845 3.781069278717041 4 25.5408163265 12.1375352769 73.0 9.0 25.5408163265 12.1375352769 5006 25032
0.0854721 4.524351596832275 5 29.5352941176 17.3809036919 131.0 9.0 29.5352941176 17.3809036919 5021 30053
0.101669 5.273976564407349 6 31.8789808917 20.0166651328 173.0 9.0 31.8789808917 20.0166651328 5005 35058
0.0798512 5.996938943862915 7 34.75 19.3263277537 127.0 10.0 34.75 19.3263277537 5004 40062
0.0380325 6.72682523727417 8 35.8142857143 22.1393591707 122.0 11.0 35.8142857143 22.1393591707 5014 45076
0.0146599 7.465633392333984 9 36.3405797101 18.9879810868 124.0 11.0 36.3405797101 18.9879810868 5015 50091
0.022541 8.191442489624023 10 40.096 19.3987315049 136.0 10.0 40.096 19.3987315049 5012 55103
0.00540924 8.921542406082153 11 39.3488372093 18.5734039922 109.0 11.0 39.3488372093 18.5734039922 5076 60179
0.0511627 9.64234471321106 12 41.6611570248 19.8550756335 121.0 13.0 41.6611570248 19.8550756335 5041 65220
0.0216064 10.367475748062134 13 44.4955752212 19.5303820016 109.0 17.0 44.4955752212 19.5303820016 5028 70248
-0.0113564 11.093759298324585 14 43.2586206897 17.2697266963 98.0 18.0 43.2586206897 17.2697266963 5018 75266
-0.00613976 11.82653260231018 15 43.3162393162 16.6956924547 105.0 14.0 43.3162393162 16.6956924547 5068 80334
0.0160332 12.564559698104858 16 47.4905660377 19.8918041732 127.0 15.0 47.4905660377 19.8918041732 5034 85368
0.044796 13.290393829345703 17 50.5656565657 21.4947311449 129.0 15.0 50.5656565657 21.4947311449 5006 90374
0.0450058 14.020903825759888 18 51.824742268 21.8745298903 126.0 18.0 51.824742268 21.8745298903 5027 95401
0.0528107 14.75761365890503 19 55.9888888889 24.6808492761 154.0 14.0 55.9888888889 24.6808492761 5039 100440
0.0139732 15.498506307601929 20 52.5625 25.8794531192 157.0 13.0 52.5625 25.8794531192 5046 105486
0.0235062 16.23076868057251 21 54.6739130435 23.2103372283 121.0 16.0 54.6739130435 23.2103372283 5030 110516
-0.00479889 16.968547582626343 22 51.4183673469 19.5197040529 120.0 18.0 51.4183673469 19.5197040529 5039 115555
0.0360603 17.699443578720093 23 54.4565217391 23.1452939359 168.0 17.0 54.4565217391 23.1452939359 5010 120565
0.0120506 18.43452262878418 24 57.375 22.8698454202 131.0 19.0 57.375 22.8698454202 5049 125614
0.0331612 19.1601722240448 25 53.3191489362 21.3915934801 127.0 15.0 53.3191489362 21.3915934801 5012 130626
0.0231056 19.889690160751343 26 65.9736842105 27.0817348062 183.0 24.0 65.9736842105 27.0817348062 5014 135640
-0.00481415 20.60822033882141 27 61.4268292683 18.8544039546 116.0 19.0 61.4268292683 18.8544039546 5037 140677
-0.00397491 21.318591833114624 28 61.0365853659 23.4351440914 133.0 22.0 61.0365853659 23.4351440914 5005 145682
-0.00137329 22.04351258277893 29 60.369047619 26.3446840042 193.0 18.0 60.369047619 26.3446840042 5071 150753
0.0149689 22.76251244544983 30 60.8915662651 27.6836744759 147.0 14.0 60.8915662651 27.6836744759 5054 155807
-0.00179291 23.482826471328735 31 59.0 21.7049736778 139.0 24.0 59.0 21.7049736778 5015 160822
0.0257607 24.206544876098633 32 64.2051282051 28.0820039894 149.0 24.0 64.2051282051 28.0820039894 5008 165830
0.0250816 24.93258285522461 33 62.8125 26.6308532299 200.0 13.0 62.8125 26.6308532299 5025 170855
0.00924301 25.66456961631775 34 62.6049382716 30.1767136993 200.0 23.0 62.6049382716 30.1767136993 5071 175926
0.0102234 26.398958921432495 35 69.4657534247 28.337536069 153.0 30.0 69.4657534247 28.337536069 5071 180997
0.02005 27.1365647315979 36 66.1038961039 26.265667886 143.0 22.0 66.1038961039 26.265667886 5090 186087
0.0187798 27.858895301818848 37 73.7647058824 27.5478821899 144.0 16.0 73.7647058824 27.5478821899 5016 191103
0.060894 28.578886032104492 38 73.0724637681 27.476640324 153.0 25.0 73.0724637681 27.476640324 5042 196145
-0.00368118 29.300734758377075 39 69.6111111111 25.8357824407 135.0 22.0 69.6111111111 25.8357824407 5012 201157
0.0241928 30.011101722717285 40 75.8333333333 25.5708068237 162.0 29.0 75.8333333333 25.5708068237 5005 206162
-0.0143623 30.728554725646973 41 81.1129032258 30.7409073043 186.0 28.0 81.1129032258 30.7409073043 5029 211191
0.0449028 31.4511501789093 42 83.9 30.7477370441 200.0 33.0 83.9 30.7477370441 5034 216225
-0.0232506 32.17107605934143 43 75.4626865672 22.3522200695 137.0 29.0 75.4626865672 22.3522200695 5056 221281
0.0186119 32.90670132637024 44 82.4677419355 30.3669587747 153.0 24.0 82.4677419355 30.3669587747 5113 226394
-0.00789261 33.63000774383545 45 82.2131147541 35.5629733558 198.0 23.0 82.2131147541 35.5629733558 5015 231409
0.0441513 34.362303018569946 46 100.0 41.7024944004 200.0 34.0 100.0 41.7024944004 5100 236509
0.0217705 35.10180616378784 47 97.9038461538 36.2726107814 200.0 46.0 97.9038461538 36.2726107814 5091 241600
0.0271835 35.87092590332031 48 102.265306122 36.9327991557 200.0 44.0 102.265306122 36.9327991557 5011 246611
0.0372849 36.74180030822754 49 103.040816327 41.1522604253 194.0 25.0 103.040816327 41.1522604253 5049 251660
-0.0691147 37.585965394973755 50 105.0 39.9591628275 200.0 45.0 105.0 39.9591628275 5145 256805
-0.00585175 38.33736276626587 51 129.076923077 46.9972091999 200.0 47.0 129.076923077 46.9972091999 5034 261839
-0.13324 39.1031174659729 52 114.177777778 41.3571377093 200.0 31.0 114.177777778 41.3571377093 5138 266977
-0.0634613 39.84541296958923 53 131.736842105 47.1847902627 200.0 44.0 131.736842105 47.1847902627 5006 271983
-0.0965195 40.617029666900635 54 150.5 42.4889258929 200.0 73.0 150.5 42.4889258929 5117 277100
-0.278687 41.389100551605225 55 157.0 42.2969301845 200.0 53.0 157.0 42.2969301845 5181 282281
-0.281128 42.148433208465576 56 185.555555556 23.1809841183 200.0 117.0 185.555555556 23.1809841183 5010 287291
-0.288818 42.94226813316345 57 178.620689655 29.3462255026 200.0 108.0 178.620689655 29.3462255026 5180 292471
-0.172173 43.70484733581543 58 169.133333333 44.6368557236 200.0 29.0 169.133333333 44.6368557236 5074 297545
-0.0620575 44.47541689872742 59 176.0 30.1181581156 200.0 103.0 176.0 30.1181581156 5104 302649
0.00879669 45.25135827064514 60 166.225806452 44.5064037998 200.0 24.0 166.225806452 44.5064037998 5153 307802
0.0270233 46.00206184387207 61 176.0 33.440631903 200.0 89.0 176.0 33.440631903 5104 312906
0.0888138 46.77706432342529 62 157.272727273 42.5157886732 200.0 76.0 157.272727273 42.5157886732 5190 318096
0.00576019 47.53112006187439 63 179.464285714 34.2527184978 200.0 86.0 179.464285714 34.2527184978 5025 323121
0.121613 48.29541778564453 64 169.366666667 36.3542600285 200.0 73.0 169.366666667 36.3542600285 5081 328202
-0.187645 49.06771945953369 65 183.214285714 24.6393372227 200.0 95.0 183.214285714 24.6393372227 5130 333332
-0.0233765 49.837318897247314 66 181.714285714 30.2794804905 200.0 83.0 181.714285714 30.2794804905 5088 338420
-0.0768127 50.60605978965759 67 165.516129032 41.045899538 200.0 57.0 165.516129032 41.045899538 5131 343551
-0.235901 51.37026834487915 68 164.64516129 33.2406168056 200.0 103.0 164.64516129 33.2406168056 5104 348655
-0.0572891 52.113112926483154 69 162.193548387 42.3833650834 200.0 52.0 162.193548387 42.3833650834 5028 353683
-0.081337 52.88195848464966 70 155.181818182 35.0337106448 200.0 77.0 155.181818182 35.0337106448 5121 358804
-0.0114822 53.637099266052246 71 143.0 33.7215488544 200.0 47.0 143.0 33.7215488544 5005 363809
-0.0346451 54.3959436416626 72 153.242424242 36.8338038936 200.0 36.0 153.242424242 36.8338038936 5057 368866
-0.0337448 55.15545892715454 73 149.852941176 35.4924452218 200.0 44.0 149.852941176 35.4924452218 5095 373961
-0.0158844 55.93423771858215 74 142.805555556 38.6248476764 200.0 31.0 142.805555556 38.6248476764 5141 379102
0.0195312 56.6786208152771 75 149.411764706 35.4111295624 200.0 45.0 149.411764706 35.4111295624 5080 384182
0.00680542 57.4259033203125 76 146.285714286 37.2785433717 200.0 47.0 146.285714286 37.2785433717 5120 389302
0.0135498 58.168540716171265 77 142.138888889 33.8527471212 200.0 66.0 142.138888889 33.8527471212 5117 394419
0.0384293 58.925843477249146 78 151.5 32.6975894057 200.0 59.0 151.5 32.6975894057 5151 399570
0.00196075 59.669734477996826 79 153.696969697 36.0794450408 200.0 43.0 153.696969697 36.0794450408 5072 404642
-0.026886 60.40738487243652 80 158.34375 38.4355055377 200.0 66.0 158.34375 38.4355055377 5067 409709
-0.0217743 61.15913915634155 81 165.387096774 32.1776093454 200.0 62.0 165.387096774 32.1776093454 5127 414836
-0.0179214 61.903923749923706 82 172.655172414 34.1278285296 200.0 54.0 172.655172414 34.1278285296 5007 419843
-0.181229 62.673901319503784 83 190.592592593 14.0086197254 200.0 139.0 190.592592593 14.0086197254 5146 424989
-0.193115 63.4303138256073 84 193.923076923 12.9345187443 200.0 148.0 193.923076923 12.9345187443 5042 430031
-0.125549 64.1886625289917 85 194.653846154 11.4855839666 200.0 149.0 194.653846154 11.4855839666 5061 435092
0.00764465 64.96020483970642 86 194.846153846 16.6217936357 200.0 127.0 194.846153846 16.6217936357 5066 440158
0.0557709 65.77018737792969 87 199.692307692 1.53846153846 200.0 192.0 199.692307692 1.53846153846 5192 445350
0.0243149 66.52928280830383 88 197.307692308 13.4615384615 200.0 130.0 197.307692308 13.4615384615 5130 450480
-0.0615005 67.3765320777893 89 199.615384615 1.92307692308 200.0 190.0 199.615384615 1.92307692308 5190 455670
-0.000732422 68.1816053390503 90 200.0 0.0 200.0 200.0 200.0 0.0 5200 460870
0.0302658 68.9486711025238 91 196.653846154 16.7307692308 200.0 113.0 196.653846154 16.7307692308 5113 465983
-0.0263596 69.73742580413818 92 200.0 0.0 200.0 200.0 200.0 0.0 5200 471183
-0.00592041 70.4967348575592 93 199.961538462 0.192307692308 200.0 199.0 199.961538462 0.192307692308 5199 476382
0.037468 71.25565338134766 94 198.0 10.0 200.0 148.0 198.0 10.0 5148 481530
0.0350418 72.00355219841003 95 193.576923077 18.7784104286 200.0 121.0 193.576923077 18.7784104286 5033 486563
-0.0207443 72.76991629600525 96 200.0 0.0 200.0 200.0 200.0 0.0 5200 491763
0.00515747 73.53293633460999 97 191.148148148 31.4521431922 200.0 69.0 191.148148148 31.4521431922 5161 496924
0.0641708 74.29387283325195 98 200.0 0.0 200.0 200.0 200.0 0.0 5200 502124
0.0374832 75.0562174320221 99 200.0 0.0 200.0 200.0 200.0 0.0 5200 507324
================================================
FILE: hw2/data/lb_no_rtg_dna_CartPole-v0_24-01-2018_09-28-29/11/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "lb_no_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/lb_no_rtg_dna_CartPole-v0_24-01-2018_09-28-29/11",
"max_path_length" : null,
"min_timesteps_per_batch" : 5000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : false,
"seed" : 11,
"size" : 32}
================================================
FILE: hw2/data/lb_no_rtg_dna_CartPole-v0_24-01-2018_09-28-29/21/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0511227 0.8156979084014893 0 21.8384279476 10.754306913 65.0 8.0 21.8384279476 10.754306913 5001 5001
0.0403347 1.5469484329223633 1 24.2259615385 14.3057915598 82.0 8.0 24.2259615385 14.3057915598 5039 10040
0.0550423 2.256683826446533 2 24.5490196078 14.1630058368 101.0 8.0 24.5490196078 14.1630058368 5008 15048
0.0643997 2.9712936878204346 3 27.0648648649 15.5624672576 90.0 9.0 27.0648648649 15.5624672576 5007 20055
0.0774498 3.692415237426758 4 28.1348314607 18.3803088402 136.0 9.0 28.1348314607 18.3803088402 5008 25063
0.0497589 4.416671514511108 5 29.3179190751 15.2663282151 86.0 9.0 29.3179190751 15.2663282151 5072 30135
0.0309067 5.142323970794678 6 30.1796407186 16.1172000173 95.0 10.0 30.1796407186 16.1172000173 5040 35175
0.0445862 5.861584424972534 7 33.5266666667 18.6578657824 105.0 11.0 33.5266666667 18.6578657824 5029 40204
-0.00485611 6.569101810455322 8 34.6896551724 19.6456601302 126.0 10.0 34.6896551724 19.6456601302 5030 45234
-0.00453186 7.294816970825195 9 35.4405594406 19.4190528521 116.0 10.0 35.4405594406 19.4190528521 5068 50302
0.0289307 8.014591217041016 10 41.775 24.6581502753 142.0 11.0 41.775 24.6581502753 5013 55315
0.0605011 8.730493068695068 11 44.610619469 23.7767766627 148.0 10.0 44.610619469 23.7767766627 5041 60356
0.0131149 9.44963026046753 12 45.8899082569 24.8722753612 123.0 10.0 45.8899082569 24.8722753612 5002 65358
0.0419083 10.176836013793945 13 47.8679245283 26.4279281492 169.0 13.0 47.8679245283 26.4279281492 5074 70432
0.0376549 10.920191764831543 14 45.2612612613 25.8525659457 171.0 9.0 45.2612612613 25.8525659457 5024 75456
0.0397453 11.653002500534058 15 50.7878787879 31.0103510667 184.0 13.0 50.7878787879 31.0103510667 5028 80484
0.027771 12.379272699356079 16 49.5392156863 30.0664856638 169.0 13.0 49.5392156863 30.0664856638 5053 85537
0.0607109 13.118503093719482 17 58.8023255814 28.0667061586 137.0 10.0 58.8023255814 28.0667061586 5057 90594
-0.013546 13.844715356826782 18 52.4583333333 27.3244078415 165.0 12.0 52.4583333333 27.3244078415 5036 95630
0.0459557 14.557087659835815 19 60.2771084337 33.7786248991 194.0 14.0 60.2771084337 33.7786248991 5003 100633
0.0179558 15.27777910232544 20 63.5443037975 29.3355952913 158.0 17.0 63.5443037975 29.3355952913 5020 105653
0.0137215 15.998308181762695 21 61.9259259259 31.2942142634 200.0 20.0 61.9259259259 31.2942142634 5016 110669
0.0301476 16.72615885734558 22 75.3432835821 37.9699615127 186.0 14.0 75.3432835821 37.9699615127 5048 115717
0.00873566 17.473997592926025 23 68.9863013699 30.7074098196 156.0 18.0 68.9863013699 30.7074098196 5036 120753
0.0210304 18.225710153579712 24 70.9718309859 31.1624421067 168.0 15.0 70.9718309859 31.1624421067 5039 125792
0.00380707 18.977147340774536 25 71.5915492958 34.5280361547 200.0 21.0 71.5915492958 34.5280361547 5083 130875
0.0564384 19.70322299003601 26 80.7142857143 41.9532727866 194.0 17.0 80.7142857143 41.9532727866 5085 135960
0.107468 20.425137519836426 27 92.7407407407 39.0413765246 183.0 28.0 92.7407407407 39.0413765246 5008 140968
-0.0282288 21.160653591156006 28 89.7368421053 46.9039804228 200.0 25.0 89.7368421053 46.9039804228 5115 146083
-0.00769043 21.889524698257446 29 101.2 48.1995850605 200.0 16.0 101.2 48.1995850605 5060 151143
-0.00387573 22.616206645965576 30 119.761904762 52.4975326059 200.0 17.0 119.761904762 52.4975326059 5030 156173
-0.00434113 23.339226007461548 31 120.214285714 53.0312287665 200.0 26.0 120.214285714 53.0312287665 5049 161222
-0.0032959 24.06978154182434 32 129.923076923 52.0780403622 200.0 16.0 129.923076923 52.0780403622 5067 166289
-0.0657959 24.825272798538208 33 125.585365854 55.565375958 200.0 16.0 125.585365854 55.565375958 5149 171438
-7.62939e-05 25.59409213066101 34 136.5 55.934524693 200.0 21.0 136.5 55.934524693 5187 176625
0.0187683 26.34383773803711 35 151.96969697 50.243338077 200.0 51.0 151.96969697 50.243338077 5015 181640
0.0226364 27.090789079666138 36 151.352941176 51.3115526224 200.0 24.0 151.352941176 51.3115526224 5146 186786
0.0330658 27.865615367889404 37 148.057142857 53.409973845 200.0 57.0 148.057142857 53.409973845 5182 191968
0.072876 28.636560916900635 38 145.057142857 53.6741187204 200.0 45.0 145.057142857 53.6741187204 5077 197045
0.0372543 29.393414735794067 39 157.125 46.7738909542 200.0 55.0 157.125 46.7738909542 5028 202073
-0.010849 30.15648651123047 40 164.677419355 39.5852588209 200.0 57.0 164.677419355 39.5852588209 5105 207178
0.118637 30.90892219543457 41 172.965517241 40.1252201701 200.0 74.0 172.965517241 40.1252201701 5016 212194
0.0112915 31.65230393409729 42 157.6875 48.3098317504 200.0 44.0 157.6875 48.3098317504 5046 217240
-0.0111542 32.41745352745056 43 159.5625 43.9921424092 200.0 36.0 159.5625 43.9921424092 5106 222346
0.0328979 33.18520903587341 44 166.193548387 47.3786527095 200.0 25.0 166.193548387 47.3786527095 5152 227498
0.106934 33.972145557403564 45 179.172413793 42.3051875563 200.0 34.0 179.172413793 42.3051875563 5196 232694
-0.02314 34.731722831726074 46 175.75862069 39.1360625408 200.0 69.0 175.75862069 39.1360625408 5097 237791
-0.00298309 35.51470923423767 47 190.740740741 28.5936960063 200.0 62.0 190.740740741 28.5936960063 5150 242941
-0.0492935 36.286608934402466 48 185.464285714 28.6773705495 200.0 94.0 185.464285714 28.6773705495 5193 248134
-0.0220413 37.07361149787903 49 181.071428571 28.594365793 200.0 108.0 181.071428571 28.594365793 5070 253204
-0.0114136 37.84270620346069 50 189.222222222 20.2910915197 200.0 112.0 189.222222222 20.2910915197 5109 258313
-0.0150223 38.61368489265442 51 182.892857143 27.4881003939 200.0 110.0 182.892857143 27.4881003939 5121 263434
0.0126266 39.39943480491638 52 174.655172414 41.7812661056 200.0 36.0 174.655172414 41.7812661056 5065 268499
0.0131454 40.20315217971802 53 188.444444444 24.2736457201 200.0 117.0 188.444444444 24.2736457201 5088 273587
0.0459213 40.95299291610718 54 186.407407407 21.7821865026 200.0 106.0 186.407407407 21.7821865026 5033 278620
-0.044426 41.787277936935425 55 182.464285714 28.3012899035 200.0 105.0 182.464285714 28.3012899035 5109 283729
0.0102921 42.57747840881348 56 178.034482759 37.2970210132 200.0 35.0 178.034482759 37.2970210132 5163 288892
0.0117264 43.44296431541443 57 185.222222222 23.8798432487 200.0 122.0 185.222222222 23.8798432487 5001 293893
0.0243759 44.32758593559265 58 188.481481481 19.3914268387 200.0 142.0 188.481481481 19.3914268387 5089 298982
0.039772 45.197575092315674 59 188.222222222 18.2398288924 200.0 150.0 188.222222222 18.2398288924 5082 304064
0.0410156 45.9800009727478 60 187.333333333 24.0693442647 200.0 119.0 187.333333333 24.0693442647 5058 309122
-0.016098 46.72489881515503 61 180.75 34.2903828667 200.0 42.0 180.75 34.2903828667 5061 314183
0.00675201 47.46742296218872 62 185.851851852 28.2275196739 200.0 93.0 185.851851852 28.2275196739 5018 319201
0.0153809 48.22783875465393 63 191.444444444 18.585803689 200.0 126.0 191.444444444 18.585803689 5169 324370
0.0210342 48.96152853965759 64 187.407407407 22.537638082 200.0 118.0 187.407407407 22.537638082 5060 329430
0.0176849 49.72043204307556 65 191.851851852 19.0062440105 200.0 132.0 191.851851852 19.0062440105 5180 334610
0.00217438 50.45610189437866 66 187.666666667 22.627416998 200.0 119.0 187.666666667 22.627416998 5067 339677
0.0176468 51.19819784164429 67 185.740740741 22.6283869453 200.0 121.0 185.740740741 22.6283869453 5015 344692
0.0251846 51.926833152770996 68 192.923076923 18.5802274494 200.0 128.0 192.923076923 18.5802274494 5016 349708
0.00663757 52.66562223434448 69 194.730769231 13.6904168962 200.0 149.0 194.730769231 13.6904168962 5063 354771
-0.00435638 53.40940284729004 70 193.615384615 17.9166379982 200.0 134.0 193.615384615 17.9166379982 5034 359805
-0.012291 54.16599202156067 71 196.769230769 9.53660031469 200.0 155.0 196.769230769 9.53660031469 5116 364921
0.0191956 54.902121782302856 72 193.269230769 14.4955104251 200.0 141.0 193.269230769 14.4955104251 5025 369946
0.0139465 55.6463098526001 73 196.653846154 9.99977810405 200.0 153.0 196.653846154 9.99977810405 5113 375059
0.038269 56.395806312561035 74 193.269230769 18.0502667619 200.0 126.0 193.269230769 18.0502667619 5025 380084
0.0494919 57.16002321243286 75 191.37037037 16.5555141271 200.0 136.0 191.37037037 16.5555141271 5167 385251
-0.0141678 57.91460704803467 76 197.5 9.22892609804 200.0 156.0 197.5 9.22892609804 5135 390386
0.0442276 58.69393873214722 77 199.961538462 0.192307692308 200.0 199.0 199.961538462 0.192307692308 5199 395585
0.0122604 59.4540376663208 78 198.384615385 5.65737723329 200.0 176.0 198.384615385 5.65737723329 5158 400743
0.0591583 60.20579981803894 79 191.851851852 20.8818611766 200.0 114.0 191.851851852 20.8818611766 5180 405923
-0.0341873 61.02331590652466 80 196.961538462 12.8376872145 200.0 134.0 196.961538462 12.8376872145 5121 411044
0.0605469 61.84341597557068 81 189.407407407 34.3794288829 200.0 48.0 189.407407407 34.3794288829 5114 416158
-0.069725 62.71775937080383 82 188.962962963 31.9936121882 200.0 53.0 188.962962963 31.9936121882 5102 421260
0.0261154 63.4859344959259 83 185.777777778 30.4233503565 200.0 94.0 185.777777778 30.4233503565 5016 426276
0.0906525 64.24548387527466 84 194.692307692 17.7303937888 200.0 121.0 194.692307692 17.7303937888 5062 431338
-0.133423 65.030832529068 85 196.269230769 9.55372538014 200.0 162.0 196.269230769 9.55372538014 5103 436441
-0.0413666 65.80585598945618 86 191.148148148 21.4850571737 200.0 112.0 191.148148148 21.4850571737 5161 441602
0.000640869 66.55259418487549 87 194.807692308 18.1489970708 200.0 109.0 194.807692308 18.1489970708 5065 446667
-0.00659943 67.29672408103943 88 193.807692308 16.6733763614 200.0 119.0 193.807692308 16.6733763614 5039 451706
0.0131607 68.07141017913818 89 183.035714286 40.0405884633 200.0 71.0 183.035714286 40.0405884633 5125 456831
0.0441666 68.81510877609253 90 193.038461538 18.5171038798 200.0 129.0 193.038461538 18.5171038798 5019 461850
-0.0184555 69.57877588272095 91 198.923076923 4.99940824901 200.0 174.0 198.923076923 4.99940824901 5172 467022
-0.00683594 70.31733012199402 92 187.777777778 23.9866217857 200.0 129.0 187.777777778 23.9866217857 5070 472092
0.0590973 71.08390784263611 93 191.62962963 19.5488905589 200.0 132.0 191.62962963 19.5488905589 5174 477266
0.0140762 71.85006642341614 94 190.592592593 26.0345344143 200.0 83.0 190.592592593 26.0345344143 5146 482412
0.00737 72.6210412979126 95 184.892857143 31.779754658 200.0 84.0 184.892857143 31.779754658 5177 487589
-0.00457764 73.37468981742859 96 189.0 28.8238584304 200.0 79.0 189.0 28.8238584304 5103 492692
0.0067215 74.14418864250183 97 183.035714286 30.0837902994 200.0 99.0 183.035714286 30.0837902994 5125 497817
0.0682297 74.92785739898682 98 192.37037037 19.8160954934 200.0 118.0 192.37037037 19.8160954934 5194 503011
0.0883789 75.67047715187073 99 195.346153846 16.1934039461 200.0 134.0 195.346153846 16.1934039461 5079 508090
================================================
FILE: hw2/data/lb_no_rtg_dna_CartPole-v0_24-01-2018_09-28-29/21/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "lb_no_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/lb_no_rtg_dna_CartPole-v0_24-01-2018_09-28-29/21",
"max_path_length" : null,
"min_timesteps_per_batch" : 5000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : false,
"seed" : 21,
"size" : 32}
================================================
FILE: hw2/data/lb_no_rtg_dna_CartPole-v0_24-01-2018_09-28-29/31/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0643883 0.8456757068634033 0 21.6120689655 12.7003065071 108.0 9.0 21.6120689655 12.7003065071 5014 5014
-0.00219154 1.5726397037506104 1 23.0504587156 11.2177049105 67.0 9.0 23.0504587156 11.2177049105 5025 10039
0.0308857 2.2921245098114014 2 25.0594059406 13.6467613263 98.0 9.0 25.0594059406 13.6467613263 5062 15101
0.0744972 3.0115747451782227 3 27.3715846995 16.6245476935 108.0 9.0 27.3715846995 16.6245476935 5009 20110
0.0525074 3.7293782234191895 4 29.0813953488 17.4284017842 103.0 10.0 29.0813953488 17.4284017842 5002 25112
0.0418167 4.442050933837891 5 32.9869281046 21.4558330135 132.0 10.0 32.9869281046 21.4558330135 5047 30159
0.00278473 5.148921012878418 6 32.9210526316 22.4717736153 149.0 10.0 32.9210526316 22.4717736153 5004 35163
0.0808258 5.866692543029785 7 40.112 24.3593812729 103.0 11.0 40.112 24.3593812729 5014 40177
0.0138817 6.5817711353302 8 43.1982758621 25.5977571174 152.0 12.0 43.1982758621 25.5977571174 5011 45188
0.051796 7.291287183761597 9 41.725 24.8545644701 131.0 10.0 41.725 24.8545644701 5007 50195
0.0839729 8.014230728149414 10 48.4038461538 30.5426937098 175.0 10.0 48.4038461538 30.5426937098 5034 55229
0.0561371 8.730967044830322 11 47.7238095238 23.0933902059 119.0 15.0 47.7238095238 23.0933902059 5011 60240
0.0153542 9.457342386245728 12 51.7319587629 26.7760916067 142.0 13.0 51.7319587629 26.7760916067 5018 65258
-0.00798035 10.173583745956421 13 47.2735849057 24.2543647186 129.0 13.0 47.2735849057 24.2543647186 5011 70269
0.00738525 10.891071796417236 14 53.6914893617 25.5251342947 194.0 12.0 53.6914893617 25.5251342947 5047 75316
0.0181122 11.599868774414062 15 55.6777777778 23.7059897624 123.0 14.0 55.6777777778 23.7059897624 5011 80327
0.0221596 12.326499223709106 16 59.2588235294 29.7563252559 167.0 13.0 59.2588235294 29.7563252559 5037 85364
0.0363884 13.06122350692749 17 65.1818181818 31.9925832609 200.0 13.0 65.1818181818 31.9925832609 5019 90383
0.0159988 13.899434328079224 18 64.6282051282 29.8638401426 176.0 19.0 64.6282051282 29.8638401426 5041 95424
0.00692749 14.708383560180664 19 62.7875 32.0311152436 172.0 22.0 62.7875 32.0311152436 5023 100447
0.0194702 15.44629955291748 20 59.2588235294 26.4860242575 149.0 19.0 59.2588235294 26.4860242575 5037 105484
0.0334702 16.17440938949585 21 70.3472222222 35.5751004224 163.0 15.0 70.3472222222 35.5751004224 5065 110549
0.0507851 16.90620708465576 22 78.8125 33.667897822 196.0 29.0 78.8125 33.667897822 5044 115593
0.0504456 17.637551307678223 23 71.9285714286 35.0828901842 178.0 16.0 71.9285714286 35.0828901842 5035 120628
0.0279007 18.360223531723022 24 84.9491525424 36.3716334472 200.0 30.0 84.9491525424 36.3716334472 5012 125640
0.0488968 19.090811729431152 25 77.4307692308 36.5399546254 200.0 24.0 77.4307692308 36.5399546254 5033 130673
-0.0200195 19.821693658828735 26 78.78125 34.5219444475 185.0 24.0 78.78125 34.5219444475 5042 135715
0.0220642 20.57074499130249 27 87.8103448276 33.5047381603 200.0 21.0 87.8103448276 33.5047381603 5093 140808
0.107162 21.310858249664307 28 99.2352941176 46.6394549103 200.0 40.0 99.2352941176 46.6394549103 5061 145869
0.0893707 22.06187081336975 29 100.02 43.8536155864 200.0 21.0 100.02 43.8536155864 5001 150870
-0.011673 22.81729483604431 30 102.8 42.9301758673 200.0 27.0 102.8 42.9301758673 5140 156010
0.0223999 23.554574251174927 31 110.326086957 40.9533426718 200.0 41.0 110.326086957 40.9533426718 5075 161085
-0.0245514 24.33149027824402 32 123.512195122 41.3993766603 200.0 43.0 123.512195122 41.3993766603 5064 166149
0.0330429 25.101356744766235 33 122.619047619 54.3620807886 200.0 21.0 122.619047619 54.3620807886 5150 171299
0.00945282 25.8627667427063 34 132.210526316 58.6116379205 200.0 20.0 132.210526316 58.6116379205 5024 176323
0.018158 26.618144989013672 35 133.763157895 53.2632164031 200.0 33.0 133.763157895 53.2632164031 5083 181406
0.00421143 27.39572548866272 36 153.787878788 41.1315388654 200.0 59.0 153.787878788 41.1315388654 5075 186481
-0.0607758 28.198476791381836 37 163.741935484 41.0938875778 200.0 45.0 163.741935484 41.0938875778 5076 191557
0.0852509 28.96868872642517 38 151.205882353 49.3443956003 200.0 42.0 151.205882353 49.3443956003 5141 196698
-0.0294342 29.7457492351532 39 166.032258065 39.5160105331 200.0 72.0 166.032258065 39.5160105331 5147 201845
-0.030098 30.495285749435425 40 169.166666667 34.3580008473 200.0 107.0 169.166666667 34.3580008473 5075 206920
-0.033783 31.25906252861023 41 174.862068966 39.309316381 200.0 53.0 174.862068966 39.309316381 5071 211991
-0.0175171 32.02586483955383 42 173.724137931 32.8768827196 200.0 104.0 173.724137931 32.8768827196 5038 217029
-0.00108337 32.78504037857056 43 179.785714286 36.5819599792 200.0 70.0 179.785714286 36.5819599792 5034 222063
0.045578 33.597580671310425 44 172.033333333 40.8031725346 200.0 83.0 172.033333333 40.8031725346 5161 227224
-0.0174866 34.37214946746826 45 173.724137931 40.878201384 200.0 68.0 173.724137931 40.878201384 5038 232262
0.0313034 35.1396062374115 46 170.266666667 42.419282827 200.0 28.0 170.266666667 42.419282827 5108 237370
0.0587463 35.91517949104309 47 178.344827586 34.4766546322 200.0 71.0 178.344827586 34.4766546322 5172 242542
0.053215 36.701788663864136 48 183.714285714 32.7946610886 200.0 81.0 183.714285714 32.7946610886 5144 247686
0.037674 37.452367544174194 49 175.172413793 38.5576764266 200.0 93.0 175.172413793 38.5576764266 5080 252766
-0.0148697 38.2207887172699 50 181.964285714 35.172515795 200.0 101.0 181.964285714 35.172515795 5095 257861
0.0187607 39.00486087799072 51 179.172413793 41.66290748 200.0 64.0 179.172413793 41.66290748 5196 263057
0.0955887 39.77413988113403 52 193.846153846 18.5300012613 200.0 126.0 193.846153846 18.5300012613 5040 268097
-0.035347 40.54476881027222 53 189.444444444 29.9497521579 200.0 95.0 189.444444444 29.9497521579 5115 273212
0.0213928 41.311304569244385 54 197.576923077 12.1153846154 200.0 137.0 197.576923077 12.1153846154 5137 278349
0.00843811 42.079716205596924 55 196.5 16.9098287304 200.0 112.0 196.5 16.9098287304 5109 283458
0.00706482 42.85657238960266 56 192.407407407 26.8276519303 200.0 82.0 192.407407407 26.8276519303 5195 288653
0.0180664 43.61483550071716 57 195.038461538 17.388061265 200.0 126.0 195.038461538 17.388061265 5071 293724
0.0266418 44.38214135169983 58 193.923076923 19.3249999043 200.0 118.0 193.923076923 19.3249999043 5042 298766
-0.0245132 45.1536602973938 59 196.230769231 13.2441792507 200.0 143.0 196.230769231 13.2441792507 5102 303868
-0.000579834 45.90400958061218 60 193.884615385 18.9215524714 200.0 120.0 193.884615385 18.9215524714 5041 308909
0.0118103 46.67436504364014 61 197.230769231 8.84180495108 200.0 158.0 197.230769231 8.84180495108 5128 314037
0.00892639 47.43624830245972 62 197.5 12.5 200.0 135.0 197.5 12.5 5135 319172
0.0229721 48.20817565917969 63 195.269230769 13.7883944854 200.0 143.0 195.269230769 13.7883944854 5077 324249
-0.0068512 48.97896599769592 64 200.0 0.0 200.0 200.0 200.0 0.0 5200 329449
0.001297 49.741021394729614 65 198.115384615 6.78418365973 200.0 167.0 198.115384615 6.78418365973 5151 334600
0.0239868 50.52007174491882 66 197.807692308 10.9615384615 200.0 143.0 197.807692308 10.9615384615 5143 339743
-0.00357056 51.28277564048767 67 195.769230769 15.9839046262 200.0 122.0 195.769230769 15.9839046262 5090 344833
0.00681305 52.06370234489441 68 199.269230769 3.65384615385 200.0 181.0 199.269230769 3.65384615385 5181 350014
0.0244064 52.83050298690796 69 200.0 0.0 200.0 200.0 200.0 0.0 5200 355214
0.0228043 53.597755432128906 70 198.153846154 9.23076923077 200.0 152.0 198.153846154 9.23076923077 5152 360366
0.00984192 54.38085699081421 71 199.192307692 4.03846153846 200.0 179.0 199.192307692 4.03846153846 5179 365545
0.00156403 55.13606548309326 72 193.961538462 17.4432723845 200.0 127.0 193.961538462 17.4432723845 5043 370588
-0.00995636 55.907310247421265 73 197.461538462 12.6923076923 200.0 134.0 197.461538462 12.6923076923 5134 375722
-0.0142365 56.67097854614258 74 191.518518519 25.2195843511 200.0 99.0 191.518518519 25.2195843511 5171 380893
0.0233612 57.43295240402222 75 197.384615385 9.21151838764 200.0 160.0 197.384615385 9.21151838764 5132 386025
0.052887 58.201114892959595 76 199.923076923 0.384615384615 200.0 198.0 199.923076923 0.384615384615 5198 391223
0.0075531 58.98029017448425 77 188.703703704 33.6141667828 200.0 55.0 188.703703704 33.6141667828 5095 396318
-0.0156479 59.72886419296265 78 193.461538462 20.3776475755 200.0 120.0 193.461538462 20.3776475755 5030 401348
-6.10352e-05 60.49043655395508 79 198.423076923 7.88461538462 200.0 159.0 198.423076923 7.88461538462 5159 406507
0.0285339 61.25859189033508 80 191.518518519 25.1710744784 200.0 96.0 191.518518519 25.1710744784 5171 411678
0.00267029 62.01974821090698 81 193.653846154 18.9065359226 200.0 129.0 193.653846154 18.9065359226 5035 416713
0.0106125 62.851001501083374 82 194.884615385 17.21655492 200.0 113.0 194.884615385 17.21655492 5067 421780
0.023056 63.64994287490845 83 195.576923077 16.9936030429 200.0 116.0 195.576923077 16.9936030429 5085 426865
0.0158081 64.43083620071411 84 190.962962963 26.0063830932 200.0 99.0 190.962962963 26.0063830932 5156 432021
0.0286179 65.20004439353943 85 196.230769231 13.059943728 200.0 150.0 196.230769231 13.059943728 5102 437123
0.0390549 65.97207641601562 86 190.62962963 25.0276116381 200.0 108.0 190.62962963 25.0276116381 5147 442270
-0.0136871 66.85933184623718 87 192.148148148 24.1272916067 200.0 94.0 192.148148148 24.1272916067 5188 447458
0.00225067 67.69136214256287 88 198.615384615 6.92307692308 200.0 164.0 198.615384615 6.92307692308 5164 452622
0.0176086 68.50128221511841 89 192.444444444 26.2725505724 200.0 91.0 192.444444444 26.2725505724 5196 457818
0.0288773 69.27488970756531 90 189.518518519 27.1652969939 200.0 92.0 189.518518519 27.1652969939 5117 462935
0.0420761 70.03152775764465 91 192.576923077 23.8394841789 200.0 91.0 192.576923077 23.8394841789 5007 467942
-0.046402 70.78953814506531 92 187.37037037 33.1015811955 200.0 43.0 187.37037037 33.1015811955 5059 473001
-0.0495605 71.56386375427246 93 190.222222222 18.6276046319 200.0 130.0 190.222222222 18.6276046319 5136 478137
-0.0866776 72.32368636131287 94 196.115384615 13.7710033238 200.0 135.0 196.115384615 13.7710033238 5099 483236
-0.112679 73.11704468727112 95 189.740740741 22.9775939052 200.0 112.0 189.740740741 22.9775939052 5123 488359
-0.0240173 73.86889886856079 96 188.222222222 23.7757008439 200.0 119.0 188.222222222 23.7757008439 5082 493441
0.0373001 74.59778618812561 97 185.259259259 27.3761082544 200.0 97.0 185.259259259 27.3761082544 5002 498443
0.0176773 75.36756944656372 98 193.269230769 14.1409326542 200.0 141.0 193.269230769 14.1409326542 5025 503468
0.0500641 76.13140344619751 99 190.259259259 23.8367792266 200.0 111.0 190.259259259 23.8367792266 5137 508605
================================================
FILE: hw2/data/lb_no_rtg_dna_CartPole-v0_24-01-2018_09-28-29/31/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "lb_no_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/lb_no_rtg_dna_CartPole-v0_24-01-2018_09-28-29/31",
"max_path_length" : null,
"min_timesteps_per_batch" : 5000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : false,
"seed" : 31,
"size" : 32}
================================================
FILE: hw2/data/lb_no_rtg_dna_CartPole-v0_24-01-2018_09-28-29/41/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0668201 0.8517470359802246 0 23.679245283 13.4953151688 76.0 9.0 23.679245283 13.4953151688 5020 5020
0.0546741 1.6438319683074951 1 25.3434343434 15.7638261367 97.0 9.0 25.3434343434 15.7638261367 5018 10038
0.0739517 2.422128677368164 2 28.6949152542 17.4436178774 96.0 9.0 28.6949152542 17.4436178774 5079 15117
0.0587845 3.185086965560913 3 31.465408805 20.7575946166 137.0 9.0 31.465408805 20.7575946166 5003 20120
0.0328274 3.9339535236358643 4 32.1666666667 19.7204284727 109.0 10.0 32.1666666667 19.7204284727 5018 25138
0.073513 4.719611883163452 5 38.5307692308 22.4455541123 120.0 10.0 38.5307692308 22.4455541123 5009 30147
0.0570755 5.449851036071777 6 40.136 21.6995277368 111.0 12.0 40.136 21.6995277368 5017 35164
0.00838089 6.175834655761719 7 43.5431034483 25.2516275479 133.0 9.0 43.5431034483 25.2516275479 5051 40215
0.0733833 6.898669242858887 8 43.7913043478 23.2807050738 137.0 9.0 43.7913043478 23.2807050738 5036 45251
0.0566788 7.608281373977661 9 45.2342342342 24.7600939304 146.0 11.0 45.2342342342 24.7600939304 5021 50272
0.00327301 8.356930255889893 10 47.2803738318 25.803641847 127.0 12.0 47.2803738318 25.803641847 5059 55331
0.068779 9.073472023010254 11 52.0 28.3476954396 154.0 14.0 52.0 28.3476954396 5096 60427
0.0141983 9.797252178192139 12 53.7659574468 27.9750745942 143.0 11.0 53.7659574468 27.9750745942 5054 65481
0.0431175 10.516398668289185 13 56.0444444444 28.9903858052 153.0 14.0 56.0444444444 28.9903858052 5044 70525
0.0156784 11.232332468032837 14 60.7108433735 34.0182552411 200.0 18.0 60.7108433735 34.0182552411 5039 75564
0.00812912 11.962613821029663 15 58.8837209302 28.8752000314 142.0 15.0 58.8837209302 28.8752000314 5064 80628
0.0110397 12.67906665802002 16 57.7126436782 27.3751746107 146.0 14.0 57.7126436782 27.3751746107 5021 85649
0.0427666 13.39736032485962 17 67.7432432432 31.6770275747 156.0 20.0 67.7432432432 31.6770275747 5013 90662
0.0421257 14.131338834762573 18 64.3037974684 35.0162184594 200.0 12.0 64.3037974684 35.0162184594 5080 95742
0.0321121 14.840710878372192 19 74.7910447761 35.4765162239 185.0 21.0 74.7910447761 35.4765162239 5011 100753
0.0463257 15.589437246322632 20 79.8307692308 39.410880665 200.0 22.0 79.8307692308 39.410880665 5189 105942
0.00630188 16.314030647277832 21 68.6891891892 32.008413453 200.0 14.0 68.6891891892 32.008413453 5083 111025
0.046051 17.025789976119995 22 78.953125 32.4804891856 177.0 29.0 78.953125 32.4804891856 5053 116078
0.0139046 17.75745677947998 23 85.4237288136 36.9737439547 200.0 24.0 85.4237288136 36.9737439547 5040 121118
0.05793 18.51006317138672 24 86.7413793103 41.7056848622 200.0 30.0 86.7413793103 41.7056848622 5031 126149
0.0524712 19.25197744369507 25 80.28125 39.1601155315 200.0 21.0 80.28125 39.1601155315 5138 131287
-0.00525665 20.01305341720581 26 95.5925925926 39.895938027 200.0 19.0 95.5925925926 39.895938027 5162 136449
0.0255203 20.755272388458252 27 92.7592592593 44.817297911 200.0 17.0 92.7592592593 44.817297911 5009 141458
0.0747757 21.508240938186646 28 100.54 38.7454306983 189.0 18.0 100.54 38.7454306983 5027 146485
0.0467148 22.255969285964966 29 109.086956522 44.9907362866 200.0 33.0 109.086956522 44.9907362866 5018 151503
0.0611801 22.99591374397278 30 131.769230769 44.8298558589 200.0 50.0 131.769230769 44.8298558589 5139 156642
-0.0493698 23.728400945663452 31 142.222222222 40.5257881623 200.0 46.0 142.222222222 40.5257881623 5120 161762
-0.0280075 24.47697615623474 32 147.342857143 50.6347948448 200.0 27.0 147.342857143 50.6347948448 5157 166919
-0.132713 25.245896816253662 33 152.382352941 39.5474508035 200.0 33.0 152.382352941 39.5474508035 5181 172100
-0.117348 26.00709843635559 34 160.28125 47.4777805762 200.0 19.0 160.28125 47.4777805762 5129 177229
-0.127731 26.798988580703735 35 170.966666667 43.9366842425 200.0 29.0 170.966666667 43.9366842425 5129 182358
-0.0303116 27.587594509124756 36 185.142857143 29.3582724843 200.0 87.0 185.142857143 29.3582724843 5184 187542
-0.0802689 28.48682451248169 37 173.206896552 36.500712615 200.0 66.0 173.206896552 36.500712615 5023 192565
0.00245667 29.266734838485718 38 166.806451613 45.9729368881 200.0 79.0 166.806451613 45.9729368881 5171 197736
0.024086 30.063265323638916 39 171.533333333 44.6540280627 200.0 24.0 171.533333333 44.6540280627 5146 202882
-0.0102386 30.86762309074402 40 179.034482759 34.3234942746 200.0 85.0 179.034482759 34.3234942746 5192 208074
0.0139465 31.60632634162903 41 163.806451613 42.2140622915 200.0 83.0 163.806451613 42.2140622915 5078 213152
0.00630951 32.35450291633606 42 170.666666667 41.3258057662 200.0 74.0 170.666666667 41.3258057662 5120 218272
0.018219 33.11089062690735 43 178.068965517 36.4132706337 200.0 96.0 178.068965517 36.4132706337 5164 223436
0.034668 33.854559659957886 44 168.933333333 40.5544352966 200.0 64.0 168.933333333 40.5544352966 5068 228504
0.00865173 34.60305666923523 45 166.129032258 48.8966928992 200.0 21.0 166.129032258 48.8966928992 5150 233654
0.0368042 35.338449001312256 46 185.481481481 33.1152536973 200.0 66.0 185.481481481 33.1152536973 5008 238662
0.0212173 36.09028458595276 47 171.533333333 38.1005103495 200.0 93.0 171.533333333 38.1005103495 5146 243808
-0.0133362 36.860106468200684 48 177.448275862 41.3334515999 200.0 53.0 177.448275862 41.3334515999 5146 248954
0.0146179 37.63217210769653 49 185.357142857 32.051536943 200.0 66.0 185.357142857 32.051536943 5190 254144
0.000106812 38.40463924407959 50 178.689655172 36.9819186465 200.0 67.0 178.689655172 36.9819186465 5182 259326
0.0879745 39.15261745452881 51 194.538461538 17.9898064496 200.0 115.0 194.538461538 17.9898064496 5058 264384
0.0282745 39.9080286026001 52 180.321428571 35.1700497293 200.0 59.0 180.321428571 35.1700497293 5049 269433
0.0675583 40.65045523643494 53 188.111111111 36.0548279331 200.0 41.0 188.111111111 36.0548279331 5079 274512
0.0228043 41.41458749771118 54 192.444444444 21.3512656114 200.0 101.0 192.444444444 21.3512656114 5196 279708
-0.0102615 42.16701555252075 55 184.428571429 29.0706388099 200.0 91.0 184.428571429 29.0706388099 5164 284872
-0.032814 42.93431735038757 56 185.714285714 39.5455046595 200.0 18.0 185.714285714 39.5455046595 5200 290072
-0.0450287 43.67553448677063 57 194.692307692 20.4163758382 200.0 99.0 194.692307692 20.4163758382 5062 295134
0.0211105 44.41314673423767 58 192.538461538 15.748579348 200.0 147.0 192.538461538 15.748579348 5006 300140
-0.0441589 45.15840673446655 59 187.481481481 20.1390911016 200.0 143.0 187.481481481 20.1390911016 5062 305202
0.0608673 45.91464567184448 60 191.259259259 21.1652975806 200.0 115.0 191.259259259 21.1652975806 5164 310366
0.067009 46.66139602661133 61 188.444444444 26.6782382301 200.0 94.0 188.444444444 26.6782382301 5088 315454
0.0113525 47.40117645263672 62 193.269230769 14.0590996875 200.0 143.0 193.269230769 14.0590996875 5025 320479
0.0218811 48.1344153881073 63 186.888888889 24.5754067572 200.0 96.0 186.888888889 24.5754067572 5046 325525
-0.0397491 48.87792921066284 64 198.5 7.5 200.0 161.0 198.5 7.5 5161 330686
-0.0277405 49.6267614364624 65 196.923076923 7.58502105328 200.0 174.0 196.923076923 7.58502105328 5120 335806
0.010231 50.355957984924316 66 193.269230769 14.7870985668 200.0 145.0 193.269230769 14.7870985668 5025 340831
0.0753021 51.1109299659729 67 200.0 0.0 200.0 200.0 200.0 0.0 5200 346031
-0.041275 51.87349081039429 68 199.5 1.78131325799 200.0 192.0 199.5 1.78131325799 5187 351218
-0.0156708 52.646403551101685 69 198.923076923 3.89203404328 200.0 182.0 198.923076923 3.89203404328 5172 356390
0.00354767 53.56320285797119 70 200.0 0.0 200.0 200.0 200.0 0.0 5200 361590
0.00126648 54.35727667808533 71 199.307692308 3.46153846154 200.0 182.0 199.307692308 3.46153846154 5182 366772
-0.0242157 55.130313873291016 72 198.538461538 7.30769230769 200.0 162.0 198.538461538 7.30769230769 5162 371934
0.0152588 55.89621829986572 73 198.5 5.19800257495 200.0 180.0 198.5 5.19800257495 5161 377095
0.00346375 56.68358373641968 74 200.0 0.0 200.0 200.0 200.0 0.0 5200 382295
0.0611877 57.465965032577515 75 200.0 0.0 200.0 200.0 200.0 0.0 5200 387495
-0.0290375 58.25723743438721 76 199.5 2.5 200.0 187.0 199.5 2.5 5187 392682
0.0299454 59.02889394760132 77 196.692307692 13.3927914904 200.0 132.0 196.692307692 13.3927914904 5114 397796
-0.00160217 59.81917357444763 78 200.0 0.0 200.0 200.0 200.0 0.0 5200 402996
0.00572205 60.60580825805664 79 197.923076923 8.40751988 200.0 157.0 197.923076923 8.40751988 5146 408142
0.00219727 61.38616323471069 80 200.0 0.0 200.0 200.0 200.0 0.0 5200 413342
0.0168152 62.174248695373535 81 199.5 1.78131325799 200.0 192.0 199.5 1.78131325799 5187 418529
0.00273132 62.928056955337524 82 196.923076923 7.41061129485 200.0 174.0 196.923076923 7.41061129485 5120 423649
0.0261536 63.692917823791504 83 199.961538462 0.192307692308 200.0 199.0 199.961538462 0.192307692308 5199 428848
0.0331421 64.45616722106934 84 199.692307692 1.53846153846 200.0 192.0 199.692307692 1.53846153846 5192 434040
0.0163498 65.21901893615723 85 199.538461538 2.30769230769 200.0 188.0 199.538461538 2.30769230769 5188 439228
-0.00320435 65.96630573272705 86 197.576923077 12.1153846154 200.0 137.0 197.576923077 12.1153846154 5137 444365
0.016243 66.71728467941284 87 197.0 12.9733454555 200.0 133.0 197.0 12.9733454555 5122 449487
-0.0291443 67.47553706169128 88 197.884615385 7.88536581795 200.0 162.0 197.884615385 7.88536581795 5145 454632
0.0382767 68.2226951122284 89 195.0 25.0 200.0 70.0 195.0 25.0 5070 459702
-0.0256042 68.98524641990662 90 198.923076923 5.38461538462 200.0 172.0 198.923076923 5.38461538462 5172 464874
-0.0215836 69.70715737342834 91 192.423076923 22.1570844321 200.0 119.0 192.423076923 22.1570844321 5003 469877
-0.0197296 70.44760608673096 92 195.846153846 15.2307692308 200.0 128.0 195.846153846 15.2307692308 5092 474969
-0.0117493 71.19535803794861 93 196.076923077 17.3691217548 200.0 110.0 196.076923077 17.3691217548 5098 480067
0.0286713 71.95822310447693 94 200.0 0.0 200.0 200.0 200.0 0.0 5200 485267
0.0101471 72.70316743850708 95 198.961538462 5.19230769231 200.0 173.0 198.961538462 5.19230769231 5173 490440
0.0116806 73.46629571914673 96 189.074074074 31.0243941367 200.0 76.0 189.074074074 31.0243941367 5105 495545
-2.28882e-05 74.2074363231659 97 194.153846154 20.857930253 200.0 106.0 194.153846154 20.857930253 5048 500593
0.027359 74.96639060974121 98 190.518518519 35.1624487943 200.0 33.0 190.518518519 35.1624487943 5144 505737
0.00409698 75.70837783813477 99 196.923076923 10.2052892656 200.0 157.0 196.923076923 10.2052892656 5120 510857
================================================
FILE: hw2/data/lb_no_rtg_dna_CartPole-v0_24-01-2018_09-28-29/41/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "lb_no_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/lb_no_rtg_dna_CartPole-v0_24-01-2018_09-28-29/41",
"max_path_length" : null,
"min_timesteps_per_batch" : 5000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : false,
"seed" : 41,
"size" : 32}
================================================
FILE: hw2/data/lb_rtg_dna_CartPole-v0_24-01-2018_09-20-37/1/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0583839 0.8156819343566895 0 25.5177664975 13.7311361728 98.0 10.0 25.5177664975 13.7311361728 5027 5027
0.0593109 1.541644811630249 1 27.4207650273 14.8880340504 89.0 10.0 27.4207650273 14.8880340504 5018 10045
0.0774584 2.2610371112823486 2 31.1055900621 19.8073336329 121.0 10.0 31.1055900621 19.8073336329 5008 15053
0.0574827 3.0426080226898193 3 32.7254901961 19.4500316024 132.0 10.0 32.7254901961 19.4500316024 5007 20060
0.0518589 3.8186004161834717 4 33.1589403974 15.9536135188 87.0 10.0 33.1589403974 15.9536135188 5007 25067
0.0420427 4.545268774032593 5 35.5744680851 17.2508542465 88.0 10.0 35.5744680851 17.2508542465 5016 30083
0.0384855 5.25580358505249 6 37.8939393939 19.0331678504 133.0 13.0 37.8939393939 19.0331678504 5002 35085
0.0508785 5.986601829528809 7 41.4344262295 20.1421130092 103.0 13.0 41.4344262295 20.1421130092 5055 40140
0.0394878 6.715565919876099 8 41.2049180328 21.7978561604 122.0 12.0 41.2049180328 21.7978561604 5027 45167
0.0256481 7.452190637588501 9 42.1570247934 21.4391347829 147.0 13.0 42.1570247934 21.4391347829 5101 50268
0.0356045 8.19448471069336 10 43.5897435897 18.3778730976 102.0 13.0 43.5897435897 18.3778730976 5100 55368
0.0445518 8.930346012115479 11 46.1926605505 21.0562710763 108.0 17.0 46.1926605505 21.0562710763 5035 60403
0.0379791 9.644671201705933 12 50.08 24.6867089747 133.0 15.0 50.08 24.6867089747 5008 65411
0.0304985 10.37541151046753 13 50.13 21.2789355937 116.0 17.0 50.13 21.2789355937 5013 70424
0.018404 11.122107028961182 14 51.1717171717 21.4810418667 120.0 12.0 51.1717171717 21.4810418667 5066 75490
0.021862 11.860644578933716 15 51.3469387755 22.6608094857 145.0 16.0 51.3469387755 22.6608094857 5032 80522
0.021452 12.603538513183594 16 55.3296703297 25.4014168269 132.0 19.0 55.3296703297 25.4014168269 5035 85557
0.0155773 13.331907749176025 17 49.7920792079 20.3700016437 113.0 16.0 49.7920792079 20.3700016437 5029 90586
0.0263367 14.071773767471313 18 51.7422680412 21.8076305337 128.0 18.0 51.7422680412 21.8076305337 5019 95605
0.0364704 14.799030065536499 19 61.2317073171 26.9703083266 177.0 21.0 61.2317073171 26.9703083266 5021 100626
0.0334988 15.536217212677002 20 63.8987341772 31.4701365118 192.0 20.0 63.8987341772 31.4701365118 5048 105674
0.0221386 16.255946159362793 21 56.875 20.2651808977 131.0 28.0 56.875 20.2651808977 5005 110679
0.0318661 17.011772632598877 22 60.734939759 29.568415393 200.0 14.0 60.734939759 29.568415393 5041 115720
0.0187683 17.762331247329712 23 60.8192771084 22.9211033284 131.0 22.0 60.8192771084 22.9211033284 5048 120768
0.0146751 18.50514531135559 24 60.7469879518 25.1802386533 147.0 20.0 60.7469879518 25.1802386533 5042 125810
0.02458 19.23746132850647 25 62.8641975309 26.4111616353 140.0 27.0 62.8641975309 26.4111616353 5092 130902
0.0284348 19.985639095306396 26 65.358974359 29.8603477572 161.0 20.0 65.358974359 29.8603477572 5098 136000
0.0308094 20.708961248397827 27 73.6764705882 31.6383242921 182.0 27.0 73.6764705882 31.6383242921 5010 141010
0.0279865 21.4510600566864 28 69.4383561644 27.7039071975 160.0 27.0 69.4383561644 27.7039071975 5069 146079
0.0311127 22.204949617385864 29 80.3015873016 28.0649105438 157.0 28.0 80.3015873016 28.0649105438 5059 151138
0.0372238 22.94363832473755 30 74.1911764706 34.7424377522 200.0 20.0 74.1911764706 34.7424377522 5045 156183
0.0357304 23.65464997291565 31 74.9850746269 31.0105867995 170.0 29.0 74.9850746269 31.0105867995 5024 161207
0.0577526 24.391042470932007 32 85.4576271186 39.4600514719 200.0 32.0 85.4576271186 39.4600514719 5042 166249
0.0630264 25.109248399734497 33 92.6111111111 46.0082185358 200.0 22.0 92.6111111111 46.0082185358 5001 171250
0.0811653 25.838764429092407 34 98.8235294118 42.2177854364 200.0 24.0 98.8235294118 42.2177854364 5040 176290
0.0826607 26.6117844581604 35 96.2830188679 39.0579527613 200.0 37.0 96.2830188679 39.0579527613 5103 181393
0.0432854 27.373897790908813 36 120.0 46.9660464997 200.0 28.0 120.0 46.9660464997 5040 186433
0.0547295 28.120433807373047 37 138.378378378 38.8276519961 200.0 36.0 138.378378378 38.8276519961 5120 191553
0.0194397 28.856316566467285 38 137.324324324 51.3583352292 200.0 36.0 137.324324324 51.3583352292 5081 196634
-0.0322342 29.59027647972107 39 137.945945946 41.4337282285 200.0 55.0 137.945945946 41.4337282285 5104 201738
0.0111427 30.311161279678345 40 139.083333333 50.0429676489 200.0 33.0 139.083333333 50.0429676489 5007 206745
0.00100327 31.061776161193848 41 139.388888889 39.0550023669 200.0 73.0 139.388888889 39.0550023669 5018 211763
0.0323181 31.80336093902588 42 145.857142857 45.603347532 200.0 51.0 145.857142857 45.603347532 5105 216868
0.0379982 32.54848074913025 43 153.424242424 45.3952542594 200.0 26.0 153.424242424 45.3952542594 5063 221931
0.0139809 33.30053520202637 44 149.117647059 38.5927185344 200.0 74.0 149.117647059 38.5927185344 5070 227001
0.0518417 34.050830602645874 45 170.3 36.3915283182 200.0 95.0 170.3 36.3915283182 5109 232110
0.0494385 34.809420347213745 46 162.40625 43.0151567583 200.0 42.0 162.40625 43.0151567583 5197 237307
0.0300522 35.56395435333252 47 162.419354839 45.4424657111 200.0 41.0 162.419354839 45.4424657111 5035 242342
0.0249023 36.29573178291321 48 169.233333333 44.5029462196 200.0 31.0 169.233333333 44.5029462196 5077 247419
0.0588531 37.05401539802551 49 191.37037037 21.0627776793 200.0 109.0 191.37037037 21.0627776793 5167 252586
0.00369263 37.8139123916626 50 191.925925926 23.0569760086 200.0 117.0 191.925925926 23.0569760086 5182 257768
-0.0313492 38.56060290336609 51 194.576923077 17.8242986202 200.0 130.0 194.576923077 17.8242986202 5059 262827
-0.0228691 39.300023317337036 52 186.851851852 22.9083580149 200.0 130.0 186.851851852 22.9083580149 5045 267872
0.00969315 40.041165590286255 53 192.961538462 18.8505881753 200.0 115.0 192.961538462 18.8505881753 5017 272889
0.0371895 40.79974603652954 54 196.730769231 9.24686097386 200.0 156.0 196.730769231 9.24686097386 5115 278004
0.00692368 41.54617118835449 55 196.423076923 10.0734726917 200.0 156.0 196.423076923 10.0734726917 5107 283111
0.0209198 42.291162967681885 56 193.230769231 20.80922076 200.0 105.0 193.230769231 20.80922076 5024 288135
0.0157738 43.06597018241882 57 199.884615385 0.576923076923 200.0 197.0 199.884615385 0.576923076923 5197 293332
-0.000911713 43.811638593673706 58 197.538461538 8.665718352 200.0 157.0 197.538461538 8.665718352 5136 298468
0.034687 44.570196866989136 59 195.461538462 16.8642333613 200.0 119.0 195.461538462 16.8642333613 5082 303550
-0.0284119 45.321213245391846 60 194.576923077 19.1555837951 200.0 116.0 194.576923077 19.1555837951 5059 308609
-0.00275421 46.08482074737549 61 198.653846154 6.73076923077 200.0 165.0 198.653846154 6.73076923077 5165 313774
0.0178452 46.87120294570923 62 200.0 0.0 200.0 200.0 200.0 0.0 5200 318974
0.0191269 47.60783362388611 63 194.076923077 27.312892246 200.0 58.0 194.076923077 27.312892246 5046 324020
0.0083847 48.37431716918945 64 199.269230769 3.65384615385 200.0 181.0 199.269230769 3.65384615385 5181 329201
0.0338631 49.15289878845215 65 199.615384615 1.92307692308 200.0 190.0 199.615384615 1.92307692308 5190 334391
0.00993347 49.911349058151245 66 200.0 0.0 200.0 200.0 200.0 0.0 5200 339591
0.0150299 50.66248178482056 67 196.730769231 16.3461538462 200.0 115.0 196.730769231 16.3461538462 5115 344706
0.0187225 51.418113708496094 68 195.653846154 18.2986807168 200.0 106.0 195.653846154 18.2986807168 5087 349793
-0.0171356 52.168784618377686 69 199.153846154 4.23076923077 200.0 178.0 199.153846154 4.23076923077 5178 354971
-0.0249023 52.91205954551697 70 195.230769231 23.8461538462 200.0 76.0 195.230769231 23.8461538462 5076 360047
0.00372314 53.63766527175903 71 192.384615385 26.3585877453 200.0 78.0 192.384615385 26.3585877453 5002 365049
0.031601 54.37115502357483 72 195.153846154 24.2307692308 200.0 74.0 195.153846154 24.2307692308 5074 370123
0.014061 55.14990520477295 73 200.0 0.0 200.0 200.0 200.0 0.0 5200 375323
0.0596313 55.91307997703552 74 191.925925926 27.2368567365 200.0 76.0 191.925925926 27.2368567365 5182 380505
0.00674438 56.673977851867676 75 189.185185185 30.6365033265 200.0 85.0 189.185185185 30.6365033265 5108 385613
-0.065464 57.42653298377991 76 197.115384615 8.67501683916 200.0 160.0 197.115384615 8.67501683916 5125 390738
0.0263138 58.19474458694458 77 199.884615385 0.423076923077 200.0 198.0 199.884615385 0.423076923077 5197 395935
-0.0378685 58.94911313056946 78 198.076923077 3.76137328566 200.0 189.0 198.076923077 3.76137328566 5150 401085
-0.0260658 59.67841053009033 79 194.076923077 12.03495894 200.0 148.0 194.076923077 12.03495894 5046 406131
0.0373573 60.41922163963318 80 181.107142857 29.2859538318 200.0 52.0 181.107142857 29.2859538318 5071 411202
-0.0359688 61.164666414260864 81 187.407407407 15.41105726 200.0 150.0 187.407407407 15.41105726 5060 416262
-0.0163612 61.92675566673279 82 190.740740741 17.3260510185 200.0 134.0 190.740740741 17.3260510185 5150 421412
0.013176 62.663830518722534 83 182.678571429 22.9783338502 200.0 89.0 182.678571429 22.9783338502 5115 426527
0.00636292 63.40858173370361 84 185.62962963 17.3421946327 200.0 143.0 185.62962963 17.3421946327 5012 431539
0.0166397 64.15923428535461 85 189.148148148 17.3839084888 200.0 132.0 189.148148148 17.3839084888 5107 436646
0.00110245 64.89390277862549 86 178.607142857 34.9032737778 200.0 85.0 178.607142857 34.9032737778 5001 441647
-0.0465622 65.65525221824646 87 191.148148148 24.6361728986 200.0 81.0 191.148148148 24.6361728986 5161 446808
-0.05476 66.38670182228088 88 185.444444444 37.1526713394 200.0 37.0 185.444444444 37.1526713394 5007 451815
0.0169945 67.16834115982056 89 185.607142857 36.746563771 200.0 36.0 185.607142857 36.746563771 5197 457012
-0.0442924 67.90475749969482 90 186.888888889 28.4804459668 200.0 97.0 186.888888889 28.4804459668 5046 462058
-0.0609207 68.65266180038452 91 173.448275862 45.1163906349 200.0 30.0 173.448275862 45.1163906349 5030 467088
-0.0401001 69.40853333473206 92 182.75 36.1165029552 200.0 87.0 182.75 36.1165029552 5117 472205
-0.00963593 70.16376996040344 93 197.846153846 10.7692307692 200.0 144.0 197.846153846 10.7692307692 5144 477349
-0.00213623 70.8938536643982 94 185.962962963 39.5282191572 200.0 41.0 185.962962963 39.5282191572 5021 482370
0.0383759 71.64577269554138 95 188.185185185 35.8887551119 200.0 53.0 188.185185185 35.8887551119 5081 487451
0.00069809 72.39587640762329 96 188.62962963 34.7202024104 200.0 54.0 188.62962963 34.7202024104 5093 492544
0.0127487 73.13797450065613 97 188.222222222 40.9383758506 200.0 24.0 188.222222222 40.9383758506 5082 497626
0.0174294 73.89098310470581 98 190.592592593 31.3289113419 200.0 42.0 190.592592593 31.3289113419 5146 502772
0.0348167 74.62288641929626 99 179.928571429 41.223197848 200.0 68.0 179.928571429 41.223197848 5038 507810
================================================
FILE: hw2/data/lb_rtg_dna_CartPole-v0_24-01-2018_09-20-37/1/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "lb_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/lb_rtg_dna_CartPole-v0_24-01-2018_09-20-37/1",
"max_path_length" : null,
"min_timesteps_per_batch" : 5000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : true,
"seed" : 1,
"size" : 32}
================================================
FILE: hw2/data/lb_rtg_dna_CartPole-v0_24-01-2018_09-20-37/11/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0489631 0.82861328125 0 17.8964285714 8.47559446473 80.0 8.0 17.8964285714 8.47559446473 5011 5011
0.0601931 1.5653579235076904 1 19.8968253968 9.9349705946 62.0 9.0 19.8968253968 9.9349705946 5014 10025
0.0676165 2.3114302158355713 2 21.9649122807 11.2436569444 77.0 9.0 21.9649122807 11.2436569444 5008 15033
0.0731831 3.045854330062866 3 25.6871794872 14.0102376394 91.0 9.0 25.6871794872 14.0102376394 5009 20042
0.0621376 3.7681686878204346 4 25.8298969072 13.4289628907 96.0 8.0 25.8298969072 13.4289628907 5011 25053
0.0783234 4.490455389022827 5 29.1569767442 15.1409581637 98.0 10.0 29.1569767442 15.1409581637 5015 30068
0.0632877 5.222829818725586 6 28.5828571429 14.4843853997 80.0 11.0 28.5828571429 14.4843853997 5002 35070
0.0696821 5.950580835342407 7 34.4178082192 17.0959247124 99.0 10.0 34.4178082192 17.0959247124 5025 40095
0.0303154 6.6728315353393555 8 33.8310810811 17.6965367331 96.0 9.0 33.8310810811 17.6965367331 5007 45102
0.0372467 7.409032344818115 9 35.0 16.721913097 139.0 10.0 35.0 16.721913097 5005 50107
0.0433464 8.153112649917603 10 38.7461538462 17.5588292664 122.0 10.0 38.7461538462 17.5588292664 5037 55144
0.0316477 8.882149457931519 11 39.7698412698 19.1949740026 115.0 13.0 39.7698412698 19.1949740026 5011 60155
0.0563278 9.619252920150757 12 45.6036036036 22.8821025617 141.0 11.0 45.6036036036 22.8821025617 5062 65217
0.0294685 10.371363639831543 13 42.7394957983 18.7667962573 97.0 11.0 42.7394957983 18.7667962573 5086 70303
0.0311546 11.108451128005981 14 48.2115384615 19.2711786978 135.0 16.0 48.2115384615 19.2711786978 5014 75317
0.0120182 11.850956201553345 15 48.2596153846 22.2887498322 169.0 14.0 48.2596153846 22.2887498322 5019 80336
0.0444736 12.592875719070435 16 55.8555555556 25.7861121584 142.0 20.0 55.8555555556 25.7861121584 5027 85363
0.0308666 13.336446046829224 17 50.05 22.1636526773 129.0 16.0 50.05 22.1636526773 5005 90368
0.0202675 14.057314395904541 18 52.3229166667 25.3111860942 148.0 21.0 52.3229166667 25.3111860942 5023 95391
0.0122375 14.794421672821045 19 53.4361702128 22.5112541644 136.0 17.0 53.4361702128 22.5112541644 5023 100414
0.0301151 15.540148735046387 20 52.1875 23.1356113041 130.0 19.0 52.1875 23.1356113041 5010 105424
0.012949 16.27898645401001 21 50.7676767677 18.927735132 113.0 13.0 50.7676767677 18.927735132 5026 110450
0.0162029 17.026137590408325 22 56.4719101124 21.9673352435 131.0 20.0 56.4719101124 21.9673352435 5026 115476
0.0287685 17.760610103607178 23 54.4130434783 26.2103332485 193.0 22.0 54.4130434783 26.2103332485 5006 120482
0.0278816 18.49950361251831 24 57.1136363636 22.5259606889 131.0 20.0 57.1136363636 22.5259606889 5026 125508
0.0115604 19.219770669937134 25 59.9285714286 23.5370962092 137.0 25.0 59.9285714286 23.5370962092 5034 130542
0.00829887 19.94955563545227 26 58.2558139535 20.6545147081 117.0 19.0 58.2558139535 20.6545147081 5010 135552
0.00959778 20.680553913116455 27 63.4683544304 25.3476263803 154.0 21.0 63.4683544304 25.3476263803 5014 140566
0.0114765 21.411751985549927 28 62.1851851852 27.8501772546 200.0 24.0 62.1851851852 27.8501772546 5037 145603
0.0218182 22.138895988464355 29 64.5384615385 26.6533743992 144.0 25.0 64.5384615385 26.6533743992 5034 150637
0.0206089 22.876145124435425 30 70.1666666667 24.9794359869 138.0 29.0 70.1666666667 24.9794359869 5052 155689
0.012991 23.622285842895508 31 60.4285714286 25.4788828128 200.0 20.0 60.4285714286 25.4788828128 5076 160765
0.0236912 24.354888677597046 32 65.0779220779 23.8260831829 145.0 32.0 65.0779220779 23.8260831829 5011 165776
0.0262032 25.086447954177856 33 68.602739726 23.0412017654 134.0 33.0 68.602739726 23.0412017654 5008 170784
0.0265541 25.827704668045044 34 72.0285714286 33.1731265715 200.0 29.0 72.0285714286 33.1731265715 5042 175826
0.0329819 26.560333490371704 35 76.8484848485 31.3877231473 171.0 28.0 76.8484848485 31.3877231473 5072 180898
0.00932884 27.295092821121216 36 67.7162162162 25.5335075402 138.0 29.0 67.7162162162 25.5335075402 5011 185909
0.030838 28.041789531707764 37 78.3230769231 32.2371537646 174.0 26.0 78.3230769231 32.2371537646 5091 191000
0.0089035 28.786449670791626 38 76.5151515152 27.2859395606 160.0 35.0 76.5151515152 27.2859395606 5050 196050
0.0280724 29.531095266342163 39 88.3333333333 31.5574293159 167.0 29.0 88.3333333333 31.5574293159 5035 201085
0.0461674 30.28827452659607 40 89.1754385965 34.6679096304 200.0 38.0 89.1754385965 34.6679096304 5083 206168
0.0369701 31.020925521850586 41 81.0 29.21996666 172.0 35.0 81.0 29.21996666 5022 211190
0.0711613 31.7571382522583 42 91.9454545455 34.6858200956 200.0 29.0 91.9454545455 34.6858200956 5057 216247
0.0410595 32.50470423698425 43 93.0545454545 35.7966063307 200.0 33.0 93.0545454545 35.7966063307 5118 221365
0.0600204 33.256269454956055 44 103.34 42.288348277 200.0 33.0 103.34 42.288348277 5167 226532
0.0519905 34.00924515724182 45 107.416666667 34.9975197534 179.0 40.0 107.416666667 34.9975197534 5156 231688
0.0671577 34.754374504089355 46 116.136363636 44.6962429319 200.0 43.0 116.136363636 44.6962429319 5110 236798
0.0201874 35.496336460113525 47 136.027027027 45.7912339578 200.0 31.0 136.027027027 45.7912339578 5033 241831
0.00388718 36.24022603034973 48 145.628571429 41.0220050456 200.0 46.0 145.628571429 41.0220050456 5097 246928
0.0674896 37.00166058540344 49 166.580645161 33.8142689804 200.0 96.0 166.580645161 33.8142689804 5164 252092
-0.0866966 37.74805665016174 50 168.933333333 35.0836460794 200.0 72.0 168.933333333 35.0836460794 5068 257160
-0.0266571 38.50079846382141 51 177.172413793 32.8403336594 200.0 106.0 177.172413793 32.8403336594 5138 262298
-0.0462837 39.262587547302246 52 177.413793103 30.0028932414 200.0 122.0 177.413793103 30.0028932414 5145 267443
-0.031601 40.00334072113037 53 181.964285714 32.0529496557 200.0 51.0 181.964285714 32.0529496557 5095 272538
-0.0234451 40.74433898925781 54 180.892857143 40.4363161436 200.0 16.0 180.892857143 40.4363161436 5065 277603
-0.00514221 41.50669455528259 55 179.275862069 33.3093096148 200.0 83.0 179.275862069 33.3093096148 5199 282802
-0.00644302 42.26334190368652 56 176.172413793 42.9017071966 200.0 75.0 176.172413793 42.9017071966 5109 287911
0.00272751 43.017560720443726 57 176.586206897 36.1419779256 200.0 93.0 176.586206897 36.1419779256 5121 293032
-0.00222015 43.75551176071167 58 174.24137931 38.7508889085 200.0 77.0 174.24137931 38.7508889085 5053 298085
0.0198631 44.51128315925598 59 183.964285714 30.1596728654 200.0 90.0 183.964285714 30.1596728654 5151 303236
0.0128326 45.266794204711914 60 189.925925926 26.510551255 200.0 87.0 189.925925926 26.510551255 5128 308364
0.0284996 46.029773473739624 61 195.884615385 13.7849609332 200.0 143.0 195.884615385 13.7849609332 5093 313457
0.0472031 46.77374291419983 62 181.928571429 34.8147429479 200.0 85.0 181.928571429 34.8147429479 5094 318551
-0.00903702 47.52978014945984 63 186.740740741 29.8435334426 200.0 94.0 186.740740741 29.8435334426 5042 323593
0.0281181 48.2915153503418 64 190.037037037 27.1572669239 200.0 96.0 190.037037037 27.1572669239 5131 328724
-0.135265 49.06886672973633 65 191.851851852 22.3866754412 200.0 119.0 191.851851852 22.3866754412 5180 333904
-0.0418472 49.82426953315735 66 194.961538462 11.8369719661 200.0 156.0 194.961538462 11.8369719661 5069 338973
-0.00441742 50.59288263320923 67 190.62962963 18.0578251185 200.0 132.0 190.62962963 18.0578251185 5147 344120
0.0112343 51.33300828933716 68 186.777777778 34.5910856996 200.0 35.0 186.777777778 34.5910856996 5043 349163
0.0253143 52.07990217208862 69 185.851851852 34.7069250254 200.0 33.0 185.851851852 34.7069250254 5018 354181
-0.00824356 52.84633755683899 70 180.892857143 30.5769979907 200.0 52.0 180.892857143 30.5769979907 5065 359246
0.0247307 53.59450435638428 71 184.392857143 22.9756692514 200.0 91.0 184.392857143 22.9756692514 5163 364409
-0.000133514 54.32626008987427 72 186.37037037 30.0729337496 200.0 52.0 186.37037037 30.0729337496 5032 369441
0.0117836 55.066972494125366 73 193.461538462 11.4227531682 200.0 163.0 193.461538462 11.4227531682 5030 374471
0.00996399 55.81751871109009 74 190.37037037 14.4559308555 200.0 139.0 190.37037037 14.4559308555 5140 379611
0.00629807 56.58711242675781 75 192.407407407 15.970480313 200.0 144.0 192.407407407 15.970480313 5195 384806
0.0104713 57.32960629463196 76 193.769230769 12.9356623698 200.0 147.0 193.769230769 12.9356623698 5038 389844
0.0160599 58.08197808265686 77 195.192307692 8.13831976029 200.0 170.0 195.192307692 8.13831976029 5075 394919
-0.0106087 58.81996440887451 78 195.230769231 13.3770978004 200.0 139.0 195.230769231 13.3770978004 5076 399995
0.0302582 59.57921123504639 79 190.888888889 16.0423821389 200.0 144.0 190.888888889 16.0423821389 5154 405149
0.0464935 60.33486461639404 80 197.076923077 6.98857901768 200.0 169.0 197.076923077 6.98857901768 5124 410273
-0.0201225 61.08813738822937 81 189.703703704 32.1556570852 200.0 32.0 189.703703704 32.1556570852 5122 415395
-0.00642776 61.838597774505615 82 196.384615385 7.32790726279 200.0 174.0 196.384615385 7.32790726279 5106 420501
0.0116615 62.57221031188965 83 194.461538462 10.3709311548 200.0 162.0 194.461538462 10.3709311548 5056 425557
0.0288315 63.29608869552612 84 193.692307692 9.70633904989 200.0 168.0 193.692307692 9.70633904989 5036 430593
0.00241089 64.03670072555542 85 191.888888889 17.4850906507 200.0 122.0 191.888888889 17.4850906507 5181 435774
0.0519753 64.75864291191101 86 186.814814815 17.1205681738 200.0 132.0 186.814814815 17.1205681738 5044 440818
-0.00915909 65.50290083885193 87 192.074074074 13.2662923619 200.0 150.0 192.074074074 13.2662923619 5186 446004
0.018261 66.23870182037354 88 189.703703704 16.948319735 200.0 147.0 189.703703704 16.948319735 5122 451126
-0.00391769 66.9576256275177 89 193.769230769 8.9584841279 200.0 168.0 193.769230769 8.9584841279 5038 456164
0.00559616 67.68006134033203 90 187.111111111 23.6961214725 200.0 91.0 187.111111111 23.6961214725 5052 461216
0.0274734 68.4073281288147 91 192.884615385 13.3541319537 200.0 157.0 192.884615385 13.3541319537 5015 466231
0.00605774 69.14635014533997 92 188.888888889 10.9420471148 200.0 165.0 188.888888889 10.9420471148 5100 471331
-0.00523376 69.88931584358215 93 190.814814815 15.8091324686 200.0 147.0 190.814814815 15.8091324686 5152 476483
0.0219421 70.64008045196533 94 191.481481481 14.6448584591 200.0 141.0 191.481481481 14.6448584591 5170 481653
0.0484886 71.37928199768066 95 197.230769231 5.35872898469 200.0 182.0 197.230769231 5.35872898469 5128 486781
0.00136566 72.12665176391602 96 197.615384615 8.80592861078 200.0 158.0 197.615384615 8.80592861078 5138 491919
0.00246048 72.86450099945068 97 196.230769231 8.32192513003 200.0 168.0 196.230769231 8.32192513003 5102 497021
-5.34058e-05 73.61387968063354 98 197.038461538 10.2412468037 200.0 148.0 197.038461538 10.2412468037 5123 502144
-0.0195312 74.35401630401611 99 200.0 0.0 200.0 200.0 200.0 0.0 5200 507344
================================================
FILE: hw2/data/lb_rtg_dna_CartPole-v0_24-01-2018_09-20-37/11/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "lb_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/lb_rtg_dna_CartPole-v0_24-01-2018_09-20-37/11",
"max_path_length" : null,
"min_timesteps_per_batch" : 5000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : true,
"seed" : 11,
"size" : 32}
================================================
FILE: hw2/data/lb_rtg_dna_CartPole-v0_24-01-2018_09-20-37/21/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0450411 0.8262073993682861 0 19.8102766798 9.07999000553 57.0 8.0 19.8102766798 9.07999000553 5012 5012
0.0741663 1.5565552711486816 1 23.0730593607 14.5223542141 93.0 8.0 23.0730593607 14.5223542141 5053 10065
0.0927773 2.281233549118042 2 27.0053763441 16.0508256284 90.0 10.0 27.0053763441 16.0508256284 5023 15088
0.0701799 2.984316825866699 3 27.2336956522 15.4998161081 88.0 9.0 27.2336956522 15.4998161081 5011 20099
0.070385 3.7018251419067383 4 29.4941860465 17.3340963546 132.0 10.0 29.4941860465 17.3340963546 5073 25172
0.057457 4.425563335418701 5 29.3103448276 17.4864876206 108.0 8.0 29.3103448276 17.4864876206 5100 30272
0.0662022 5.149742841720581 6 33.2631578947 18.5513997351 96.0 10.0 33.2631578947 18.5513997351 5056 35328
0.0456619 5.863052129745483 7 33.6912751678 21.4872833717 136.0 9.0 33.6912751678 21.4872833717 5020 40348
0.0406475 6.574002265930176 8 38.2824427481 24.5677983272 132.0 9.0 38.2824427481 24.5677983272 5015 45363
0.0487537 7.294687986373901 9 38.1984732824 24.3387103622 144.0 9.0 38.1984732824 24.3387103622 5004 50367
0.0505676 8.017372846603394 10 43.0854700855 24.9356685625 190.0 10.0 43.0854700855 24.9356685625 5041 55408
0.0537395 8.721525192260742 11 45.5272727273 25.5224354391 124.0 11.0 45.5272727273 25.5224354391 5008 60416
0.0394058 9.442970037460327 12 42.3025210084 20.4916685763 113.0 8.0 42.3025210084 20.4916685763 5034 65450
0.0246696 10.155640840530396 13 45.6090909091 23.7644101564 164.0 12.0 45.6090909091 23.7644101564 5017 70467
0.0398693 10.875059604644775 14 48.2307692308 26.9844081652 151.0 12.0 48.2307692308 26.9844081652 5016 75483
0.02672 11.598340034484863 15 51.2346938776 26.8392041232 142.0 10.0 51.2346938776 26.8392041232 5021 80504
0.0334606 12.312464475631714 16 52.7684210526 28.9996198275 171.0 12.0 52.7684210526 28.9996198275 5013 85517
0.0408859 13.02834177017212 17 60.6265060241 32.3429331002 182.0 14.0 60.6265060241 32.3429331002 5032 90549
0.0249844 13.74483847618103 18 54.652173913 25.216210617 126.0 13.0 54.652173913 25.216210617 5028 95577
0.0385056 14.475249528884888 19 60.6987951807 33.537152547 200.0 11.0 60.6987951807 33.537152547 5038 100615
0.0455456 15.186398983001709 20 64.2179487179 26.8187876339 143.0 19.0 64.2179487179 26.8187876339 5009 105624
0.0318165 15.909932851791382 21 68.2567567568 33.496292982 183.0 12.0 68.2567567568 33.496292982 5051 110675
0.0336132 16.62094736099243 22 63.6835443038 29.0749987445 181.0 15.0 63.6835443038 29.0749987445 5031 115706
0.0328312 17.34173822402954 23 73.7246376812 33.6300780048 175.0 17.0 73.7246376812 33.6300780048 5087 120793
0.0431271 18.058817625045776 24 76.3787878788 36.1360078758 175.0 15.0 76.3787878788 36.1360078758 5041 125834
0.0803108 18.771949768066406 25 84.9661016949 42.5253527977 195.0 14.0 84.9661016949 42.5253527977 5013 130847
0.0600395 19.499238967895508 26 81.1428571429 36.5955401667 200.0 24.0 81.1428571429 36.5955401667 5112 135959
0.126293 20.232662200927734 27 106.0 55.3165135079 200.0 12.0 106.0 55.3165135079 5088 141047
0.0367584 20.945877075195312 28 98.2745098039 44.9841272361 200.0 19.0 98.2745098039 44.9841272361 5012 146059
0.0514297 21.67428731918335 29 130.358974359 54.5989983845 200.0 18.0 130.358974359 54.5989983845 5084 151143
0.0393257 22.418105840682983 30 132.692307692 52.958209865 200.0 32.0 132.692307692 52.958209865 5175 156318
0.00126648 23.140052556991577 31 136.486486486 52.7424243934 200.0 22.0 136.486486486 52.7424243934 5050 161368
-0.00255203 23.859087705612183 32 143.057142857 53.7539063602 200.0 24.0 143.057142857 53.7539063602 5007 166375
-0.000339508 24.596675395965576 33 140.944444444 56.0981008019 200.0 33.0 140.944444444 56.0981008019 5074 171449
-0.00931549 25.310323476791382 34 139.527777778 46.3192341325 200.0 54.0 139.527777778 46.3192341325 5023 176472
0.0355797 26.042215824127197 35 163.580645161 50.6772037531 200.0 17.0 163.580645161 50.6772037531 5071 181543
0.0329704 26.776606798171997 36 151.529411765 55.3232401406 200.0 29.0 151.529411765 55.3232401406 5152 186695
0.0535583 27.51152992248535 37 164.580645161 40.5937975507 200.0 79.0 164.580645161 40.5937975507 5102 191797
0.0426254 28.23815107345581 38 170.5 38.1127712628 200.0 74.0 170.5 38.1127712628 5115 196912
0.0266266 28.965182065963745 39 180.25 39.9746571503 200.0 32.0 180.25 39.9746571503 5047 201959
0.00766754 29.709632635116577 40 191.851851852 18.8221770373 200.0 116.0 191.851851852 18.8221770373 5180 207139
0.0161209 30.43006205558777 41 185.222222222 25.2635491089 200.0 105.0 185.222222222 25.2635491089 5001 212140
0.00915527 31.159303426742554 42 171.4 48.4957730117 200.0 27.0 171.4 48.4957730117 5142 217282
-0.00128174 31.888792276382446 43 183.0 33.5878379349 200.0 74.0 183.0 33.5878379349 5124 222406
0.0196877 32.61609745025635 44 182.392857143 19.9612826773 200.0 140.0 182.392857143 19.9612826773 5107 227513
0.0257835 33.35137152671814 45 183.464285714 33.0372972594 200.0 43.0 183.464285714 33.0372972594 5137 232650
-0.00647354 34.07750725746155 46 179.535714286 24.9649499196 200.0 124.0 179.535714286 24.9649499196 5027 237677
0.015316 34.81552577018738 47 182.75 26.5311474632 200.0 110.0 182.75 26.5311474632 5117 242794
0.00592804 35.541518688201904 48 173.965517241 28.6482625803 200.0 113.0 173.965517241 28.6482625803 5045 247839
-0.00242615 36.271355628967285 49 174.379310345 28.257942177 200.0 108.0 174.379310345 28.257942177 5057 252896
-0.0133934 37.01572394371033 50 179.068965517 27.1190619237 200.0 120.0 179.068965517 27.1190619237 5193 258089
0.0377312 37.75216841697693 51 178.896551724 25.8194591513 200.0 124.0 178.896551724 25.8194591513 5188 263277
0.00421524 38.486414670944214 52 183.25 24.7092015828 200.0 100.0 183.25 24.7092015828 5131 268408
0.00256729 39.222169160842896 53 175.896551724 30.7855147617 200.0 90.0 175.896551724 30.7855147617 5101 273509
0.0464668 39.942662477493286 54 179.357142857 28.6645802911 200.0 125.0 179.357142857 28.6645802911 5022 278531
0.0124092 40.67772626876831 55 181.964285714 25.3355793625 200.0 121.0 181.964285714 25.3355793625 5095 283626
-0.0103493 41.40083146095276 56 185.333333333 27.0965352439 200.0 96.0 185.333333333 27.0965352439 5004 288630
0.0338516 42.123655796051025 57 185.222222222 34.2791733914 200.0 29.0 185.222222222 34.2791733914 5001 293631
0.0101929 42.8599157333374 58 191.0 19.7802744991 200.0 127.0 191.0 19.7802744991 5157 298788
-0.00876236 43.582720041275024 59 180.678571429 26.5868570799 200.0 103.0 180.678571429 26.5868570799 5059 303847
0.0252914 44.325129985809326 60 189.962962963 19.8652525251 200.0 134.0 189.962962963 19.8652525251 5129 308976
-0.000179291 45.04391884803772 61 186.296296296 23.3314520112 200.0 126.0 186.296296296 23.3314520112 5030 314006
-0.00479507 45.786325216293335 62 191.444444444 19.0386222139 200.0 128.0 191.444444444 19.0386222139 5169 319175
0.0329323 46.51962852478027 63 196.461538462 13.1331370944 200.0 137.0 196.461538462 13.1331370944 5108 324283
-0.0261955 47.26353192329407 64 199.307692308 3.26719393563 200.0 183.0 199.307692308 3.26719393563 5182 329465
-0.00834656 48.01894974708557 65 200.0 0.0 200.0 200.0 200.0 0.0 5200 334665
0.0127716 48.76284742355347 66 200.0 0.0 200.0 200.0 200.0 0.0 5200 339865
-0.00914764 49.51041007041931 67 200.0 0.0 200.0 200.0 200.0 0.0 5200 345065
-0.00534821 50.25908970832825 68 197.961538462 10.1923076923 200.0 147.0 197.961538462 10.1923076923 5147 350212
0.040905 51.012207984924316 69 200.0 0.0 200.0 200.0 200.0 0.0 5200 355412
0.00387955 51.750479221343994 70 196.615384615 10.6629369712 200.0 150.0 196.615384615 10.6629369712 5112 360524
0.0136032 52.50134515762329 71 200.0 0.0 200.0 200.0 200.0 0.0 5200 365724
0.0074234 53.258440017700195 72 200.0 0.0 200.0 200.0 200.0 0.0 5200 370924
0.00769424 54.00620460510254 73 199.692307692 1.53846153846 200.0 192.0 199.692307692 1.53846153846 5192 376116
0.049614 54.76391077041626 74 200.0 0.0 200.0 200.0 200.0 0.0 5200 381316
0.0325851 55.50467658042908 75 200.0 0.0 200.0 200.0 200.0 0.0 5200 386516
0.030098 56.25809621810913 76 200.0 0.0 200.0 200.0 200.0 0.0 5200 391716
0.00312424 56.99479365348816 77 196.923076923 15.3846153846 200.0 120.0 196.923076923 15.3846153846 5120 396836
-0.0270386 57.75302600860596 78 200.0 0.0 200.0 200.0 200.0 0.0 5200 402036
0.0203247 58.489142417907715 79 200.0 0.0 200.0 200.0 200.0 0.0 5200 407236
0.00747681 59.2335205078125 80 199.038461538 4.80769230769 200.0 175.0 199.038461538 4.80769230769 5175 412411
0.000133514 59.97301959991455 81 200.0 0.0 200.0 200.0 200.0 0.0 5200 417611
0.0104637 60.72220301628113 82 199.615384615 1.92307692308 200.0 190.0 199.615384615 1.92307692308 5190 422801
0.00856018 61.46384859085083 83 200.0 0.0 200.0 200.0 200.0 0.0 5200 428001
-0.00260162 62.21070861816406 84 200.0 0.0 200.0 200.0 200.0 0.0 5200 433201
-0.0121689 62.954439878463745 85 199.576923077 2.11538461538 200.0 189.0 199.576923077 2.11538461538 5189 438390
-0.00215149 63.702558517456055 86 200.0 0.0 200.0 200.0 200.0 0.0 5200 443590
-0.00271606 64.4572081565857 87 200.0 0.0 200.0 200.0 200.0 0.0 5200 448790
0.00296021 65.19976282119751 88 200.0 0.0 200.0 200.0 200.0 0.0 5200 453990
0.0157547 65.95722556114197 89 200.0 0.0 200.0 200.0 200.0 0.0 5200 459190
0.019516 66.7078628540039 90 200.0 0.0 200.0 200.0 200.0 0.0 5200 464390
-0.013195 67.45815920829773 91 200.0 0.0 200.0 200.0 200.0 0.0 5200 469590
0.00982285 68.1871726512909 92 194.423076923 27.8846153846 200.0 55.0 194.423076923 27.8846153846 5055 474645
0.00579834 68.93310499191284 93 198.846153846 5.76923076923 200.0 170.0 198.846153846 5.76923076923 5170 479815
0.0217934 69.68494129180908 94 200.0 0.0 200.0 200.0 200.0 0.0 5200 485015
-0.00403595 70.42124962806702 95 200.0 0.0 200.0 200.0 200.0 0.0 5200 490215
0.0296669 71.17968130111694 96 200.0 0.0 200.0 200.0 200.0 0.0 5200 495415
0.0279808 71.9282956123352 97 200.0 0.0 200.0 200.0 200.0 0.0 5200 500615
-0.0116119 72.67991924285889 98 200.0 0.0 200.0 200.0 200.0 0.0 5200 505815
-0.00270462 73.42717909812927 99 200.0 0.0 200.0 200.0 200.0 0.0 5200 511015
================================================
FILE: hw2/data/lb_rtg_dna_CartPole-v0_24-01-2018_09-20-37/21/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "lb_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/lb_rtg_dna_CartPole-v0_24-01-2018_09-20-37/21",
"max_path_length" : null,
"min_timesteps_per_batch" : 5000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : true,
"seed" : 21,
"size" : 32}
================================================
FILE: hw2/data/lb_rtg_dna_CartPole-v0_24-01-2018_09-20-37/31/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0600958 0.8112151622772217 0 20.9539748954 9.99173167041 63.0 9.0 20.9539748954 9.99173167041 5008 5008
0.0738554 1.5200369358062744 1 23.1712962963 12.8309272703 94.0 8.0 23.1712962963 12.8309272703 5005 10013
0.0696745 2.2284233570098877 2 23.8285714286 13.749429178 88.0 9.0 23.8285714286 13.749429178 5004 15017
0.0899334 2.950821876525879 3 29.1453488372 18.3849923438 114.0 9.0 29.1453488372 18.3849923438 5013 20030
0.0805845 3.6759867668151855 4 30.9938271605 19.6922297497 115.0 9.0 30.9938271605 19.6922297497 5021 25051
0.0701647 4.385343551635742 5 34.4178082192 20.8601858597 131.0 10.0 34.4178082192 20.8601858597 5025 30076
0.0514164 5.094944000244141 6 36.5766423358 19.6378610293 116.0 10.0 36.5766423358 19.6378610293 5011 35087
0.0748539 5.817645072937012 7 46.0810810811 32.0014456698 200.0 11.0 46.0810810811 32.0014456698 5115 40202
0.0774269 6.530958652496338 8 42.1092436975 28.306779755 169.0 10.0 42.1092436975 28.306779755 5011 45213
0.0590992 7.238082408905029 9 47.2924528302 25.6522340714 125.0 12.0 47.2924528302 25.6522340714 5013 50226
0.0620594 7.948439359664917 10 50.5757575758 31.4890043047 176.0 11.0 50.5757575758 31.4890043047 5007 55233
0.0332146 8.661653280258179 11 50.21 24.722578749 129.0 17.0 50.21 24.722578749 5021 60254
0.032093 9.37789511680603 12 52.46875 27.8017359788 154.0 18.0 52.46875 27.8017359788 5037 65291
0.0260715 10.09050464630127 13 57.6436781609 27.0529395906 146.0 19.0 57.6436781609 27.0529395906 5015 70306
0.0327225 10.798506498336792 14 58.9647058824 29.6451353251 200.0 13.0 58.9647058824 29.6451353251 5012 75318
0.047205 11.51948881149292 15 60.3012048193 33.1483467177 200.0 13.0 60.3012048193 33.1483467177 5005 80323
0.0389462 12.231024503707886 16 60.8674698795 29.5943543478 154.0 16.0 60.8674698795 29.5943543478 5052 85375
0.0423145 12.943362474441528 17 69.8611111111 35.1620477044 170.0 14.0 69.8611111111 35.1620477044 5030 90405
0.015934 13.658470153808594 18 67.1333333333 33.5210713167 200.0 21.0 67.1333333333 33.5210713167 5035 95440
0.042757 14.374126195907593 19 75.1791044776 36.0157201884 167.0 15.0 75.1791044776 36.0157201884 5037 100477
0.0419598 15.093021869659424 20 77.5538461538 35.1007476446 184.0 11.0 77.5538461538 35.1007476446 5041 105518
0.0668774 15.813343048095703 21 79.8412698413 37.5204521368 200.0 25.0 79.8412698413 37.5204521368 5030 110548
0.06637 16.56160831451416 22 84.3442622951 42.5459771541 200.0 13.0 84.3442622951 42.5459771541 5145 115693
0.0782776 17.279974937438965 23 89.7543859649 45.7519171113 200.0 29.0 89.7543859649 45.7519171113 5116 120809
0.0728416 17.999879598617554 24 104.0 45.1419529747 200.0 38.0 104.0 45.1419529747 5096 125905
0.063797 18.71016526222229 25 98.5490196078 53.1587757592 200.0 20.0 98.5490196078 53.1587757592 5026 130931
0.0771675 19.43394660949707 26 112.977777778 49.133147394 200.0 32.0 112.977777778 49.133147394 5084 136015
0.0650711 20.163068532943726 27 129.435897436 55.6895215812 200.0 25.0 129.435897436 55.6895215812 5048 141063
0.0106468 20.891000270843506 28 128.487179487 52.2885837395 200.0 29.0 128.487179487 52.2885837395 5011 146074
0.0308228 21.62237811088562 29 150.117647059 50.4087788257 200.0 14.0 150.117647059 50.4087788257 5104 151178
0.044754 22.366085529327393 30 152.029411765 51.4984210461 200.0 20.0 152.029411765 51.4984210461 5169 156347
0.0162926 23.087540864944458 31 143.428571429 49.486093697 200.0 34.0 143.428571429 49.486093697 5020 161367
0.0411644 23.830024242401123 32 152.058823529 44.3621070261 200.0 57.0 152.058823529 44.3621070261 5170 166537
0.0213432 24.546687364578247 33 143.171428571 44.5725640881 200.0 41.0 143.171428571 44.5725640881 5011 171548
0.00619888 25.27321767807007 34 158.15625 41.99710509 200.0 84.0 158.15625 41.99710509 5061 176609
0.0349426 25.98290467262268 35 157.25 47.8010198636 200.0 40.0 157.25 47.8010198636 5032 181641
0.0354195 26.718429803848267 36 165.451612903 41.6264794058 200.0 35.0 165.451612903 41.6264794058 5129 186770
0.0185776 27.4345223903656 37 156.6875 41.5672929567 200.0 71.0 156.6875 41.5672929567 5014 191784
0.024601 28.17476201057434 38 166.35483871 41.0094783592 200.0 61.0 166.35483871 41.0094783592 5157 196941
0.0137253 28.912630081176758 39 177.793103448 43.4982197895 200.0 14.0 177.793103448 43.4982197895 5156 202097
-0.00281143 29.652870893478394 40 171.7 42.295113981 200.0 54.0 171.7 42.295113981 5151 207248
0.0521164 30.401338815689087 41 185.392857143 30.4470726786 200.0 72.0 185.392857143 30.4470726786 5191 212439
0.00287247 31.14111828804016 42 189.259259259 30.7023857109 200.0 77.0 189.259259259 30.7023857109 5110 217549
0.0559654 31.891887664794922 43 181.214285714 36.6034318677 200.0 56.0 181.214285714 36.6034318677 5074 222623
0.0328865 32.60334801673889 44 192.769230769 21.2282607214 200.0 103.0 192.769230769 21.2282607214 5012 227635
-0.0066452 33.32523512840271 45 194.038461538 15.8174216737 200.0 142.0 194.038461538 15.8174216737 5045 232680
0.0139542 34.0499312877655 46 192.423076923 13.6245623131 200.0 158.0 192.423076923 13.6245623131 5003 237683
-0.0487976 34.78154420852661 47 188.518518519 19.5246669633 200.0 120.0 188.518518519 19.5246669633 5090 242773
-0.0266914 35.518083572387695 48 181.392857143 29.442849345 200.0 103.0 181.392857143 29.442849345 5079 247852
0.0036087 36.23173403739929 49 173.620689655 43.7448824933 200.0 49.0 173.620689655 43.7448824933 5035 252887
0.0379333 36.95907378196716 50 181.785714286 24.3726385565 200.0 123.0 181.785714286 24.3726385565 5090 257977
-0.00121689 37.68800354003906 51 182.5 24.7436860633 200.0 127.0 182.5 24.7436860633 5110 263087
0.0290718 38.42139387130737 52 175.827586207 27.1459261763 200.0 113.0 175.827586207 27.1459261763 5099 268186
-0.0147362 39.165337800979614 53 184.464285714 22.2894628258 200.0 135.0 184.464285714 22.2894628258 5165 273351
0.0173378 39.909751653671265 54 185.642857143 20.6833512857 200.0 124.0 185.642857143 20.6833512857 5198 278549
0.0537834 40.627156257629395 55 194.423076923 16.5300962744 200.0 128.0 194.423076923 16.5300962744 5055 283604
-0.00769806 41.3525493144989 56 182.357142857 34.8170876415 200.0 36.0 182.357142857 34.8170876415 5106 288710
0.00943375 42.0809543132782 57 190.296296296 25.6151211343 200.0 94.0 190.296296296 25.6151211343 5138 293848
0.0229645 42.8197226524353 58 198.730769231 4.39893074689 200.0 183.0 198.730769231 4.39893074689 5167 299015
0.00187302 43.54933190345764 59 194.923076923 24.7913183888 200.0 71.0 194.923076923 24.7913183888 5068 304083
-0.0279694 44.272584438323975 60 195.192307692 19.3470713959 200.0 102.0 195.192307692 19.3470713959 5075 309158
-0.0271034 44.998164892196655 61 195.692307692 13.4672515349 200.0 141.0 195.692307692 13.4672515349 5088 314246
-0.00235367 45.74230360984802 62 199.269230769 2.82240612445 200.0 186.0 199.269230769 2.82240612445 5181 319427
0.0437393 46.47599148750305 63 196.615384615 16.9230769231 200.0 112.0 196.615384615 16.9230769231 5112 324539
-0.000980377 47.20028305053711 64 192.807692308 25.0184842909 200.0 79.0 192.807692308 25.0184842909 5013 329552
0.00920486 47.91202712059021 65 185.444444444 32.8253891499 200.0 86.0 185.444444444 32.8253891499 5007 334559
0.00799561 48.65900921821594 66 192.518518519 29.7761654253 200.0 47.0 192.518518519 29.7761654253 5198 339757
-0.0158157 49.406556844711304 67 199.346153846 3.26923076923 200.0 183.0 199.346153846 3.26923076923 5183 344940
-0.0026474 50.158512115478516 68 192.592592593 19.3069921306 200.0 120.0 192.592592593 19.3069921306 5200 350140
0.00162125 50.89095377922058 69 188.740740741 29.4600703937 200.0 79.0 188.740740741 29.4600703937 5096 355236
0.00353241 51.62881851196289 70 189.111111111 24.9508158159 200.0 114.0 189.111111111 24.9508158159 5106 360342
0.019043 52.367936849594116 71 197.846153846 10.7692307692 200.0 144.0 197.846153846 10.7692307692 5144 365486
0.0168724 53.11186170578003 72 191.222222222 21.140330656 200.0 133.0 191.222222222 21.140330656 5163 370649
-0.015419 53.8262677192688 73 185.777777778 41.6700739348 200.0 26.0 185.777777778 41.6700739348 5016 375665
0.00782013 54.55403113365173 74 183.857142857 30.9708552925 200.0 102.0 183.857142857 30.9708552925 5148 380813
-0.0022316 55.28831338882446 75 198.192307692 9.03846153846 200.0 153.0 198.192307692 9.03846153846 5153 385966
0.0052681 56.0388720035553 76 199.346153846 2.58609161139 200.0 187.0 199.346153846 2.58609161139 5183 391149
0.0101547 56.770336866378784 77 193.884615385 21.1847676102 200.0 120.0 193.884615385 21.1847676102 5041 396190
0.00239944 57.505324602127075 78 189.0 24.8938487122 200.0 99.0 189.0 24.8938487122 5103 401293
0.00321198 58.245736598968506 79 199.153846154 4.23076923077 200.0 178.0 199.153846154 4.23076923077 5178 406471
0.0241928 58.983787298202515 80 197.807692308 10.9615384615 200.0 143.0 197.807692308 10.9615384615 5143 411614
-0.00402451 59.72374105453491 81 199.576923077 2.11538461538 200.0 189.0 199.576923077 2.11538461538 5189 416803
0.0268898 60.457014322280884 82 196.307692308 13.3669202217 200.0 138.0 196.307692308 13.3669202217 5104 421907
-0.00566864 61.186158657073975 83 190.37037037 28.0754910226 200.0 89.0 190.37037037 28.0754910226 5140 427047
0.010746 61.9101448059082 84 194.307692308 19.7284823986 200.0 100.0 194.307692308 19.7284823986 5052 432099
0.0126762 62.639323472976685 85 192.653846154 25.8083801353 200.0 89.0 192.653846154 25.8083801353 5009 437108
8.01086e-05 63.37616324424744 86 189.703703704 25.4584844546 200.0 113.0 189.703703704 25.4584844546 5122 442230
0.0135422 64.11422276496887 87 199.5 2.5 200.0 187.0 199.5 2.5 5187 447417
0.00380707 64.86438512802124 88 200.0 0.0 200.0 200.0 200.0 0.0 5200 452617
0.00761032 65.5884280204773 89 194.538461538 18.9923684456 200.0 123.0 194.538461538 18.9923684456 5058 457675
0.0334587 66.32678771018982 90 196.846153846 15.7692307692 200.0 118.0 196.846153846 15.7692307692 5118 462793
0.0157967 67.05586862564087 91 196.307692308 18.4615384615 200.0 104.0 196.307692308 18.4615384615 5104 467897
0.0171738 67.79700875282288 92 199.384615385 2.28838073548 200.0 189.0 199.384615385 2.28838073548 5184 473081
0.0097084 68.53009128570557 93 195.807692308 17.8627658096 200.0 108.0 195.807692308 17.8627658096 5091 478172
-0.00401306 69.2748510837555 94 199.884615385 0.576923076923 200.0 197.0 199.884615385 0.576923076923 5197 483369
-0.0117645 70.01878952980042 95 200.0 0.0 200.0 200.0 200.0 0.0 5200 488569
0.00477982 70.75467705726624 96 197.923076923 10.3846153846 200.0 146.0 197.923076923 10.3846153846 5146 493715
-0.0544853 71.5006000995636 97 199.961538462 0.192307692308 200.0 199.0 199.961538462 0.192307692308 5199 498914
-0.0156593 72.23487186431885 98 190.222222222 22.7699173429 200.0 97.0 190.222222222 22.7699173429 5136 504050
-0.0199242 72.94847583770752 99 193.269230769 14.5880817854 200.0 149.0 193.269230769 14.5880817854 5025 509075
================================================
FILE: hw2/data/lb_rtg_dna_CartPole-v0_24-01-2018_09-20-37/31/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "lb_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/lb_rtg_dna_CartPole-v0_24-01-2018_09-20-37/31",
"max_path_length" : null,
"min_timesteps_per_batch" : 5000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : true,
"seed" : 31,
"size" : 32}
================================================
FILE: hw2/data/lb_rtg_dna_CartPole-v0_24-01-2018_09-20-37/41/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0771532 0.8028819561004639 0 23.5117370892 14.4354188592 119.0 9.0 23.5117370892 14.4354188592 5008 5008
0.105606 1.518303632736206 1 28.2824858757 17.2616742951 92.0 9.0 28.2824858757 17.2616742951 5006 10014
0.060051 2.2269694805145264 2 27.0324324324 13.9845098486 103.0 8.0 27.0324324324 13.9845098486 5001 15015
0.0920601 2.9395534992218018 3 33.6375838926 22.6529743118 147.0 10.0 33.6375838926 22.6529743118 5012 20027
0.0677662 3.656031608581543 4 33.0460526316 18.5767748376 97.0 10.0 33.0460526316 18.5767748376 5023 25050
0.0645971 4.373595714569092 5 35.013986014 18.9920800622 121.0 9.0 35.013986014 18.9920800622 5007 30057
0.0479202 5.079150676727295 6 37.4552238806 21.9390661142 125.0 12.0 37.4552238806 21.9390661142 5019 35076
0.052599 5.79546046257019 7 41.5081967213 22.6752721175 135.0 13.0 41.5081967213 22.6752721175 5064 40140
0.0428543 6.5146825313568115 8 44.7857142857 23.4499575736 129.0 11.0 44.7857142857 23.4499575736 5016 45156
0.0407639 7.238849401473999 9 47.8380952381 24.994903789 136.0 11.0 47.8380952381 24.994903789 5023 50179
0.0269413 7.955668687820435 10 46.7476635514 24.1626472593 135.0 14.0 46.7476635514 24.1626472593 5002 55181
0.0394897 8.66911506652832 11 53.6063829787 27.3165907366 159.0 15.0 53.6063829787 27.3165907366 5039 60220
0.0313797 9.379432201385498 12 49.3137254902 26.246561079 177.0 13.0 49.3137254902 26.246561079 5030 65250
0.0297813 10.079515218734741 13 54.4456521739 30.1342518286 200.0 15.0 54.4456521739 30.1342518286 5009 70259
0.0288181 10.797240495681763 14 55.0769230769 28.7521545372 147.0 13.0 55.0769230769 28.7521545372 5012 75271
0.038147 11.508926391601562 15 63.8481012658 30.9008576374 150.0 15.0 63.8481012658 30.9008576374 5044 80315
0.0400753 12.234404802322388 16 60.9518072289 32.2116134166 176.0 18.0 60.9518072289 32.2116134166 5059 85374
0.0265446 12.955068588256836 17 61.0609756098 32.967222288 200.0 16.0 61.0609756098 32.967222288 5007 90381
0.0355511 13.679707050323486 18 66.4078947368 32.1166367904 200.0 17.0 66.4078947368 32.1166367904 5047 95428
0.0343494 14.402028560638428 19 69.1232876712 32.7556102924 200.0 21.0 69.1232876712 32.7556102924 5046 100474
0.0535355 15.128974914550781 20 78.0307692308 34.2955342376 200.0 17.0 78.0307692308 34.2955342376 5072 105546
0.0643692 15.843761205673218 21 77.0923076923 35.080883717 171.0 17.0 77.0923076923 35.080883717 5011 110557
0.0649796 16.55949354171753 22 86.8103448276 43.195807945 199.0 27.0 86.8103448276 43.195807945 5035 115592
0.0814247 17.2722270488739 23 93.6481481481 41.8295294452 200.0 20.0 93.6481481481 41.8295294452 5057 120649
0.12429 17.98696756362915 24 102.102040816 47.3821825196 200.0 14.0 102.102040816 47.3821825196 5003 125652
0.0622749 18.71837615966797 25 108.765957447 46.9500471375 200.0 31.0 108.765957447 46.9500471375 5112 130764
0.0287743 19.437434196472168 26 119.619047619 48.6566945333 200.0 25.0 119.619047619 48.6566945333 5024 135788
0.0830193 20.16329836845398 27 140.333333333 54.5440698477 200.0 24.0 140.333333333 54.5440698477 5052 140840
0.0435181 20.889440774917603 28 163.709677419 35.3144341762 200.0 78.0 163.709677419 35.3144341762 5075 145915
-0.0212822 21.62032651901245 29 159.0 37.6638088886 200.0 35.0 159.0 37.6638088886 5088 151003
0.0309944 22.35004162788391 30 162.741935484 48.9291573089 200.0 28.0 162.741935484 48.9291573089 5045 156048
-0.0101433 23.087426900863647 31 151.264705882 52.8734943179 200.0 32.0 151.264705882 52.8734943179 5143 161191
0.0495682 23.822831869125366 32 153.727272727 55.901576238 200.0 34.0 153.727272727 55.901576238 5073 166264
0.0284233 24.5584499835968 33 165.806451613 42.7795695546 200.0 77.0 165.806451613 42.7795695546 5140 171404
0.019989 25.306041955947876 34 151.352941176 50.1021793309 200.0 30.0 151.352941176 50.1021793309 5146 176550
0.0695877 26.02964186668396 35 180.285714286 32.7248891113 200.0 83.0 180.285714286 32.7248891113 5048 181598
0.00587463 26.750684022903442 36 172.551724138 46.0925502298 200.0 37.0 172.551724138 46.0925502298 5004 186602
0.00671005 27.49039053916931 37 170.966666667 42.4047822251 200.0 77.0 170.966666667 42.4047822251 5129 191731
0.00875092 28.213773488998413 38 173.793103448 39.4534901304 200.0 52.0 173.793103448 39.4534901304 5040 196771
-0.0149498 28.94206142425537 39 179.035714286 31.0902857392 200.0 107.0 179.035714286 31.0902857392 5013 201784
0.0444031 29.6753990650177 40 188.555555556 20.4691879253 200.0 114.0 188.555555556 20.4691879253 5091 206875
0.00732422 30.421806573867798 41 176.0 34.595195999 200.0 89.0 176.0 34.595195999 5104 211979
-0.0067215 31.145166873931885 42 173.931034483 44.201678104 200.0 34.0 173.931034483 44.201678104 5044 217023
-0.00138474 31.873716831207275 43 181.392857143 28.1822376757 200.0 100.0 181.392857143 28.1822376757 5079 222102
-0.00673294 32.61938762664795 44 177.655172414 31.2523387948 200.0 94.0 177.655172414 31.2523387948 5152 227254
0.0180969 33.35728454589844 45 176.068965517 39.0021493965 200.0 52.0 176.068965517 39.0021493965 5106 232360
0.0115547 34.09204149246216 46 184.178571429 25.7405371953 200.0 115.0 184.178571429 25.7405371953 5157 237517
0.0315857 34.84378504753113 47 185.0 27.3378335436 200.0 106.0 185.0 27.3378335436 5180 242697
-0.00430679 35.5821795463562 48 190.222222222 17.5189491764 200.0 133.0 190.222222222 17.5189491764 5136 247833
-0.0345421 36.30470061302185 49 194.192307692 16.4387423035 200.0 127.0 194.192307692 16.4387423035 5049 252882
0.0120049 37.04418396949768 50 190.481481481 24.634168337 200.0 107.0 190.481481481 24.634168337 5143 258025
-0.00615311 37.76688194274902 51 194.384615385 19.1111665366 200.0 110.0 194.384615385 19.1111665366 5054 263079
0.00697708 38.49098205566406 52 195.192307692 20.8953790084 200.0 92.0 195.192307692 20.8953790084 5075 268154
0.00860596 39.21939539909363 53 193.5 19.7060123586 200.0 125.0 193.5 19.7060123586 5031 273185
-0.0243454 39.95396876335144 54 193.038461538 25.0775424652 200.0 77.0 193.038461538 25.0775424652 5019 278204
0.00756836 40.691356897354126 55 194.884615385 21.2355415484 200.0 90.0 194.884615385 21.2355415484 5067 283271
0.0116272 41.43429183959961 56 199.846153846 0.769230769231 200.0 196.0 199.846153846 0.769230769231 5196 288467
-0.0191078 42.16548299789429 57 195.807692308 15.5959048638 200.0 125.0 195.807692308 15.5959048638 5091 293558
0.0161324 42.89598798751831 58 193.423076923 20.3869737388 200.0 109.0 193.423076923 20.3869737388 5029 298587
-0.0125389 43.642297983169556 59 196.5 15.6186525569 200.0 119.0 196.5 15.6186525569 5109 303696
0.0348778 44.37451529502869 60 195.346153846 12.8869113913 200.0 150.0 195.346153846 12.8869113913 5079 308775
-0.000354767 45.121959924697876 61 198.615384615 6.92307692308 200.0 164.0 198.615384615 6.92307692308 5164 313939
0.0527878 45.86292600631714 62 199.615384615 1.92307692308 200.0 190.0 199.615384615 1.92307692308 5190 319129
-0.00793839 46.60887312889099 63 200.0 0.0 200.0 200.0 200.0 0.0 5200 324329
-0.0133286 47.346511125564575 64 197.115384615 14.4230769231 200.0 125.0 197.115384615 14.4230769231 5125 329454
-0.00200653 48.10574197769165 65 200.0 0.0 200.0 200.0 200.0 0.0 5200 334654
0.0110092 48.84552192687988 66 198.769230769 6.15384615385 200.0 168.0 198.769230769 6.15384615385 5168 339822
0.0242119 49.59027910232544 67 200.0 0.0 200.0 200.0 200.0 0.0 5200 345022
0.0174713 50.333660364151 68 199.923076923 0.384615384615 200.0 198.0 199.923076923 0.384615384615 5198 350220
0.00565338 51.07314872741699 69 197.807692308 10.9615384615 200.0 143.0 197.807692308 10.9615384615 5143 355363
0.00764465 51.804325580596924 70 194.846153846 22.7776751493 200.0 82.0 194.846153846 22.7776751493 5066 360429
-0.00103378 52.55413269996643 71 199.923076923 0.384615384615 200.0 198.0 199.923076923 0.384615384615 5198 365627
-0.010643 53.29349756240845 72 196.269230769 13.3115267931 200.0 140.0 196.269230769 13.3115267931 5103 370730
-0.00190735 54.05140686035156 73 199.846153846 0.769230769231 200.0 196.0 199.846153846 0.769230769231 5196 375926
-0.00962448 54.81413769721985 74 192.407407407 19.2011945216 200.0 121.0 192.407407407 19.2011945216 5195 381121
-0.000480652 55.55890893936157 75 200.0 0.0 200.0 200.0 200.0 0.0 5200 386321
0.00258255 56.292922496795654 76 197.769230769 7.70767695377 200.0 163.0 197.769230769 7.70767695377 5142 391463
0.016716 57.04535365104675 77 191.740740741 24.1501362508 200.0 103.0 191.740740741 24.1501362508 5177 396640
0.0292587 57.787031412124634 78 190.444444444 27.2401301641 200.0 104.0 190.444444444 27.2401301641 5142 401782
-0.00576782 58.53011894226074 79 191.185185185 29.5547665355 200.0 87.0 191.185185185 29.5547665355 5162 406944
0.000453949 59.25182747840881 80 192.730769231 18.8711372865 200.0 135.0 192.730769231 18.8711372865 5011 411955
0.00710297 59.99426579475403 81 199.846153846 0.769230769231 200.0 196.0 199.846153846 0.769230769231 5196 417151
0.0201683 60.73959708213806 82 185.428571429 35.6895628715 200.0 74.0 185.428571429 35.6895628715 5192 422343
-6.48499e-05 61.49524211883545 83 190.962962963 24.3469999391 200.0 110.0 190.962962963 24.3469999391 5156 427499
0.0161018 62.22880434989929 84 196.884615385 11.7221910628 200.0 143.0 196.884615385 11.7221910628 5119 432618
0.0128746 62.9756338596344 85 200.0 0.0 200.0 200.0 200.0 0.0 5200 437818
-0.00278473 63.72838497161865 86 199.692307692 1.53846153846 200.0 192.0 199.692307692 1.53846153846 5192 443010
-0.00294876 64.47300386428833 87 197.884615385 7.36063815731 200.0 170.0 197.884615385 7.36063815731 5145 448155
0.0279961 65.22263312339783 88 200.0 0.0 200.0 200.0 200.0 0.0 5200 453355
0.0567818 65.95522594451904 89 195.884615385 14.4070680386 200.0 139.0 195.884615385 14.4070680386 5093 458448
-0.0243187 66.68140530586243 90 194.5 27.5 200.0 57.0 194.5 27.5 5057 463505
0.00421524 67.41744875907898 91 198.769230769 6.15384615385 200.0 168.0 198.769230769 6.15384615385 5168 468673
-0.020565 68.166677236557 92 200.0 0.0 200.0 200.0 200.0 0.0 5200 473873
0.0165138 68.9151120185852 93 200.0 0.0 200.0 200.0 200.0 0.0 5200 479073
-0.0152512 69.6612286567688 94 200.0 0.0 200.0 200.0 200.0 0.0 5200 484273
-0.00219727 70.40035915374756 95 200.0 0.0 200.0 200.0 200.0 0.0 5200 489473
0.0176201 71.15700221061707 96 199.923076923 0.384615384615 200.0 198.0 199.923076923 0.384615384615 5198 494671
0.0108299 71.9083924293518 97 200.0 0.0 200.0 200.0 200.0 0.0 5200 499871
0.0183487 72.66075325012207 98 200.0 0.0 200.0 200.0 200.0 0.0 5200 505071
0.018856 73.39920258522034 99 199.730769231 1.34615384615 200.0 193.0 199.730769231 1.34615384615 5193 510264
================================================
FILE: hw2/data/lb_rtg_dna_CartPole-v0_24-01-2018_09-20-37/41/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "lb_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/lb_rtg_dna_CartPole-v0_24-01-2018_09-20-37/41",
"max_path_length" : null,
"min_timesteps_per_batch" : 5000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : true,
"seed" : 41,
"size" : 32}
================================================
FILE: hw2/data/lb_rtg_na_CartPole-v0_24-01-2018_09-11-55/1/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0063868 0.8420774936676025 0 25.385786802 13.608126902 75.0 9.0 25.385786802 13.608126902 5001 5001
0.00525531 1.633702039718628 1 27.5604395604 14.4345501201 103.0 8.0 27.5604395604 14.4345501201 5016 10017
0.00535492 2.4135117530822754 2 27.9 12.7506426853 71.0 11.0 27.9 12.7506426853 5022 15039
0.00340952 3.152466058731079 3 31.198757764 17.4308999122 129.0 9.0 31.198757764 17.4308999122 5023 20062
0.00390902 3.8814897537231445 4 32.3483870968 15.9853132385 86.0 9.0 32.3483870968 15.9853132385 5014 25076
0.00301743 4.6129961013793945 5 34.5862068966 17.0785552998 93.0 11.0 34.5862068966 17.0785552998 5015 30091
0.00311275 5.345637321472168 6 35.8928571429 16.4163230739 88.0 11.0 35.8928571429 16.4163230739 5025 35116
0.00152305 6.075947284698486 7 38.25 20.8127929045 122.0 13.0 38.25 20.8127929045 5049 40165
0.00161444 6.814359188079834 8 38.2651515152 19.8505247043 141.0 10.0 38.2651515152 19.8505247043 5051 45216
0.00197905 7.5445051193237305 9 38.9769230769 18.3736707042 117.0 11.0 38.9769230769 18.3736707042 5067 50283
0.00141314 8.27737307548523 10 44.1315789474 24.0483843999 136.0 15.0 44.1315789474 24.0483843999 5031 55314
0.00109187 9.01082730293274 11 43.5304347826 17.5337298491 96.0 10.0 43.5304347826 17.5337298491 5006 60320
0.00163624 9.733712434768677 12 41.1475409836 16.6584159458 91.0 12.0 41.1475409836 16.6584159458 5020 65340
0.00102582 10.467440128326416 13 47.6857142857 21.6993808495 103.0 13.0 47.6857142857 21.6993808495 5007 70347
0.000956879 11.209193468093872 14 45.0990990991 19.3628021551 122.0 14.0 45.0990990991 19.3628021551 5006 75353
0.000844965 11.966494798660278 15 56.8426966292 25.8004001695 153.0 17.0 56.8426966292 25.8004001695 5059 80412
0.00122935 12.74616003036499 16 49.3431372549 23.8296631336 154.0 19.0 49.3431372549 23.8296631336 5033 85445
0.00107329 13.47432279586792 17 54.5869565217 24.3311181027 158.0 15.0 54.5869565217 24.3311181027 5022 90467
0.00123146 14.211679697036743 18 58.488372093 24.1370814723 150.0 17.0 58.488372093 24.1370814723 5030 95497
0.000781654 14.94622254371643 19 52.8842105263 20.6840203554 140.0 20.0 52.8842105263 20.6840203554 5024 100521
0.000476001 15.670190334320068 20 61.987654321 28.8677246522 200.0 23.0 61.987654321 28.8677246522 5021 105542
0.000997569 16.39939546585083 21 57.5747126437 23.6947213598 131.0 22.0 57.5747126437 23.6947213598 5009 110551
0.000897535 17.13254737854004 22 58.2643678161 31.5843915221 169.0 20.0 58.2643678161 31.5843915221 5069 115620
0.0012026 17.87738800048828 23 59.5833333333 19.1735236182 125.0 20.0 59.5833333333 19.1735236182 5005 120625
0.00116465 18.632447004318237 24 57.8045977011 24.1207875629 128.0 23.0 57.8045977011 24.1207875629 5029 125654
0.00084196 19.36769676208496 25 65.3896103896 26.5560694968 135.0 14.0 65.3896103896 26.5560694968 5035 130689
0.00132419 20.127912044525146 26 61.4634146341 24.7530215559 139.0 20.0 61.4634146341 24.7530215559 5040 135729
0.000334724 20.86565661430359 27 67.7432432432 29.9689302223 200.0 17.0 67.7432432432 29.9689302223 5013 140742
0.00052933 21.635022401809692 28 75.3235294118 34.778898765 189.0 24.0 75.3235294118 34.778898765 5122 145864
0.000825342 22.416949033737183 29 67.32 30.045370137 185.0 22.0 67.32 30.045370137 5049 150913
0.000980859 23.168538570404053 30 70.7323943662 32.6289242404 199.0 24.0 70.7323943662 32.6289242404 5022 155935
0.00106099 23.916141748428345 31 66.4078947368 29.1462634743 180.0 26.0 66.4078947368 29.1462634743 5047 160982
0.00093415 24.668829202651978 32 81.2741935484 33.879372997 190.0 28.0 81.2741935484 33.879372997 5039 166021
0.0015798 25.4109525680542 33 78.578125 34.5786262955 184.0 24.0 78.578125 34.5786262955 5029 171050
0.00110778 26.165154218673706 34 82.8360655738 37.7238370212 200.0 35.0 82.8360655738 37.7238370212 5053 176103
0.00174398 26.924659490585327 35 76.9696969697 43.2522445369 200.0 18.0 76.9696969697 43.2522445369 5080 181183
0.00220239 27.670087814331055 36 90.2678571429 43.5162084218 200.0 26.0 90.2678571429 43.5162084218 5055 186238
0.00239888 28.44137978553772 37 103.673469388 44.4115207314 200.0 39.0 103.673469388 44.4115207314 5080 191318
0.00324861 29.208786249160767 38 102.7 43.873112495 200.0 15.0 102.7 43.873112495 5135 196453
0.00388993 29.960748434066772 39 122.243902439 52.7607487547 200.0 28.0 122.243902439 52.7607487547 5012 201465
0.00182624 30.716398000717163 40 124.487804878 43.2633016067 200.0 34.0 124.487804878 43.2633016067 5104 206569
0.00124153 31.46278953552246 41 145.771428571 44.579999176 200.0 58.0 145.771428571 44.579999176 5102 211671
0.00353618 32.21239256858826 42 134.473684211 57.0732386556 200.0 38.0 134.473684211 57.0732386556 5110 216781
0.00185509 32.99056529998779 43 126.225 55.4281009507 200.0 18.0 126.225 55.4281009507 5049 221830
0.000788631 33.77147650718689 44 138.513513514 42.4019515242 200.0 18.0 138.513513514 42.4019515242 5125 226955
0.000572399 34.55799341201782 45 147.142857143 47.7236945385 200.0 42.0 147.142857143 47.7236945385 5150 232105
0.000153512 35.32166242599487 46 135.216216216 45.0909801822 200.0 54.0 135.216216216 45.0909801822 5003 237108
0.000874536 36.11688780784607 47 144.0 45.8433322427 200.0 41.0 144.0 45.8433322427 5184 242292
0.000224067 36.8776581287384 48 127.525 33.5067064183 200.0 74.0 127.525 33.5067064183 5101 247393
0.000694555 37.63187861442566 49 128.41025641 39.9202525227 200.0 54.0 128.41025641 39.9202525227 5008 252401
0.000620444 38.39607906341553 50 147.735294118 40.7245473189 200.0 69.0 147.735294118 40.7245473189 5023 257424
0.000519844 39.166157722473145 51 135.236842105 43.5735519798 200.0 73.0 135.236842105 43.5735519798 5139 262563
0.000452291 39.92753529548645 52 144.542857143 40.7944974281 200.0 57.0 144.542857143 40.7944974281 5059 267622
0.000598712 40.68093180656433 53 149.558823529 44.4940122716 200.0 68.0 149.558823529 44.4940122716 5085 272707
0.00101414 41.44749569892883 54 158.71875 41.5205027479 200.0 92.0 158.71875 41.5205027479 5079 277786
0.000597851 42.20836138725281 55 168.233333333 40.4233293477 200.0 74.0 168.233333333 40.4233293477 5047 282833
0.00178301 42.98753523826599 56 171.733333333 39.795253765 200.0 82.0 171.733333333 39.795253765 5152 287985
0.00123982 43.75298476219177 57 159.40625 44.2018518949 200.0 75.0 159.40625 44.2018518949 5101 293086
0.000567047 44.5258526802063 58 166.903225806 49.4566312712 200.0 16.0 166.903225806 49.4566312712 5174 298260
0.00083382 45.27634310722351 59 180.071428571 37.5689162658 200.0 48.0 180.071428571 37.5689162658 5042 303302
0.000641726 46.01953053474426 60 185.555555556 28.9755111588 200.0 72.0 185.555555556 28.9755111588 5010 308312
0.000851093 46.76450777053833 61 181.285714286 29.7679803323 200.0 111.0 181.285714286 29.7679803323 5076 313388
0.000380925 47.51181697845459 62 189.444444444 32.4874144672 200.0 37.0 189.444444444 32.4874144672 5115 318503
-0.000194557 48.266581296920776 63 187.481481481 21.050856181 200.0 125.0 187.481481481 21.050856181 5062 323565
0.000312931 48.999338150024414 64 185.333333333 31.1043643478 200.0 55.0 185.333333333 31.1043643478 5004 328569
5.73471e-05 49.74167251586914 65 193.730769231 15.5873659202 200.0 143.0 193.730769231 15.5873659202 5037 333606
0.00011922 50.50078296661377 66 189.703703704 21.1779319363 200.0 125.0 189.703703704 21.1779319363 5122 338728
0.000366116 51.255610942840576 67 199.423076923 2.6914833903 200.0 186.0 199.423076923 2.6914833903 5185 343913
0.000193828 51.99089288711548 68 192.692307692 15.0096615827 200.0 145.0 192.692307692 15.0096615827 5010 348923
0.000197133 52.7332489490509 69 195.846153846 11.6542904206 200.0 149.0 195.846153846 11.6542904206 5092 354015
0.000212909 53.48803997039795 70 197.346153846 10.9577591326 200.0 144.0 197.346153846 10.9577591326 5131 359146
-0.000217594 54.2285041809082 71 193.461538462 17.2609625572 200.0 123.0 193.461538462 17.2609625572 5030 364176
-7.28793e-05 54.98472237586975 72 200.0 0.0 200.0 200.0 200.0 0.0 5200 369376
5.68563e-05 55.718749046325684 73 194.461538462 15.5073946858 200.0 140.0 194.461538462 15.5073946858 5056 374432
0.000152636 56.48402118682861 74 193.230769231 12.2295596886 200.0 158.0 193.230769231 12.2295596886 5024 379456
0.000240509 57.25986647605896 75 196.038461538 8.10261481646 200.0 169.0 196.038461538 8.10261481646 5097 384553
0.000584039 58.02433967590332 76 199.038461538 3.14374555183 200.0 186.0 199.038461538 3.14374555183 5175 389728
6.53568e-05 58.78241157531738 77 199.538461538 2.30769230769 200.0 188.0 199.538461538 2.30769230769 5188 394916
-8.08286e-05 59.56317186355591 78 199.961538462 0.192307692308 200.0 199.0 199.961538462 0.192307692308 5199 400115
6.003e-05 60.36890172958374 79 196.615384615 15.3999923154 200.0 120.0 196.615384615 15.3999923154 5112 405227
1.78963e-05 61.126331090927124 80 195.307692308 15.8933203937 200.0 126.0 195.307692308 15.8933203937 5078 410305
2.82532e-05 61.91744112968445 81 199.692307692 1.53846153846 200.0 192.0 199.692307692 1.53846153846 5192 415497
0.000125698 62.695329904556274 82 199.230769231 3.84615384615 200.0 180.0 199.230769231 3.84615384615 5180 420677
0.000272585 63.477558612823486 83 198.653846154 6.34242314584 200.0 167.0 198.653846154 6.34242314584 5165 425842
7.96355e-05 64.24319243431091 84 200.0 0.0 200.0 200.0 200.0 0.0 5200 431042
2.97092e-05 65.00944948196411 85 194.192307692 24.6374000108 200.0 73.0 194.192307692 24.6374000108 5049 436091
0.000255863 65.77909088134766 86 197.153846154 14.2307692308 200.0 126.0 197.153846154 14.2307692308 5126 441217
0.000136037 66.55039882659912 87 197.076923077 8.41666422559 200.0 162.0 197.076923077 8.41666422559 5124 446341
0.00072132 67.34288311004639 88 198.192307692 6.79377107679 200.0 167.0 198.192307692 6.79377107679 5153 451494
0.000216601 68.0917558670044 89 193.923076923 16.2833635651 200.0 138.0 193.923076923 16.2833635651 5042 456536
0.000337987 68.8577446937561 90 194.923076923 14.1745250278 200.0 149.0 194.923076923 14.1745250278 5068 461604
-1.9135e-05 69.63355326652527 91 190.222222222 13.9929435479 200.0 150.0 190.222222222 13.9929435479 5136 466740
-7.96486e-05 70.41926121711731 92 185.428571429 30.8109773706 200.0 58.0 185.428571429 30.8109773706 5192 471932
2.62843e-05 71.18084025382996 93 189.37037037 15.6540094217 200.0 146.0 189.37037037 15.6540094217 5113 477045
0.000440812 71.97455549240112 94 177.103448276 30.176886368 200.0 94.0 177.103448276 30.176886368 5136 482181
0.00117131 72.74159979820251 95 193.807692308 13.9090983803 200.0 152.0 193.807692308 13.9090983803 5039 487220
0.000418276 73.49688506126404 96 186.259259259 18.526442749 200.0 137.0 186.259259259 18.526442749 5029 492249
0.0002787 74.25104713439941 97 196.923076923 9.73859521114 200.0 156.0 196.923076923 9.73859521114 5120 497369
0.000843057 75.01481175422668 98 197.884615385 7.43343239424 200.0 168.0 197.884615385 7.43343239424 5145 502514
0.000245077 75.77536749839783 99 197.769230769 7.01815060182 200.0 169.0 197.769230769 7.01815060182 5142 507656
================================================
FILE: hw2/data/lb_rtg_na_CartPole-v0_24-01-2018_09-11-55/1/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "lb_rtg_na",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/lb_rtg_na_CartPole-v0_24-01-2018_09-11-55/1",
"max_path_length" : null,
"min_timesteps_per_batch" : 5000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 1,
"size" : 32}
================================================
FILE: hw2/data/lb_rtg_na_CartPole-v0_24-01-2018_09-11-55/11/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0105773 0.8143682479858398 0 18.2254545455 7.99909581667 52.0 9.0 18.2254545455 7.99909581667 5012 5012
0.0103061 1.5477631092071533 1 19.9880478088 9.13226497204 58.0 8.0 19.9880478088 9.13226497204 5017 10029
0.00804929 2.2843234539031982 2 22.2699115044 11.8330075692 82.0 9.0 22.2699115044 11.8330075692 5033 15062
0.00821722 3.0127038955688477 3 24.5196078431 12.7230918614 75.0 9.0 24.5196078431 12.7230918614 5002 20064
0.0067809 3.761721134185791 4 25.4568527919 13.3896852582 80.0 10.0 25.4568527919 13.3896852582 5015 25079
0.00517964 4.520713806152344 5 30.717791411 18.3425179753 107.0 10.0 30.717791411 18.3425179753 5007 30086
0.00415358 5.259512662887573 6 29.869047619 14.805307737 100.0 10.0 29.869047619 14.805307737 5018 35104
0.00354232 6.005943775177002 7 34.1020408163 16.0994928276 89.0 11.0 34.1020408163 16.0994928276 5013 40117
0.0039164 6.742534160614014 8 32.5584415584 15.7484227258 97.0 10.0 32.5584415584 15.7484227258 5014 45131
0.00319652 7.464856147766113 9 35.5106382979 19.087189652 121.0 10.0 35.5106382979 19.087189652 5007 50138
0.00304066 8.19768476486206 10 39.09375 18.292517895 110.0 12.0 39.09375 18.292517895 5004 55142
0.00151004 8.94117784500122 11 37.7518796992 18.1208997499 119.0 12.0 37.7518796992 18.1208997499 5021 60163
0.00209156 9.687880039215088 12 44.1315789474 22.5075087502 152.0 11.0 44.1315789474 22.5075087502 5031 65194
0.00214316 10.443288803100586 13 43.9561403509 20.5107547103 125.0 13.0 43.9561403509 20.5107547103 5011 70205
0.00162569 11.178599834442139 14 44.3451327434 21.9761616269 123.0 9.0 44.3451327434 21.9761616269 5011 75216
0.00153849 11.93626070022583 15 46.3727272727 20.2533315288 117.0 15.0 46.3727272727 20.2533315288 5101 80317
0.0015688 12.694477796554565 16 46.5555555556 20.1477566683 134.0 15.0 46.5555555556 20.1477566683 5028 85345
0.00127187 13.41974925994873 17 45.6636363636 17.0167175944 92.0 16.0 45.6636363636 17.0167175944 5023 90368
0.00127531 14.161622762680054 18 52.1443298969 25.6543196623 141.0 13.0 52.1443298969 25.6543196623 5058 95426
0.00121093 14.912331581115723 19 48.0476190476 17.9233186512 116.0 14.0 48.0476190476 17.9233186512 5045 100471
0.000638824 15.662923812866211 20 52.1041666667 23.8753181334 140.0 12.0 52.1041666667 23.8753181334 5002 105473
0.00135413 16.414910316467285 21 47.7641509434 18.2392650706 112.0 19.0 47.7641509434 18.2392650706 5063 110536
0.000700573 17.157273769378662 22 56.404494382 26.7294892914 143.0 19.0 56.404494382 26.7294892914 5020 115556
0.00181422 17.911693811416626 23 51.3775510204 21.0773673501 126.0 14.0 51.3775510204 21.0773673501 5035 120591
0.000873956 18.660968542099 24 56.4606741573 21.2121738312 135.0 14.0 56.4606741573 21.2121738312 5025 125616
0.00100801 19.40562391281128 25 59.1529411765 23.3492692327 133.0 24.0 59.1529411765 23.3492692327 5028 130644
0.000719984 20.149693489074707 26 51.7422680412 20.0186914464 136.0 19.0 51.7422680412 20.0186914464 5019 135663
0.000728176 20.892398834228516 27 56.0777777778 26.2505990525 160.0 17.0 56.0777777778 26.2505990525 5047 140710
0.00089298 21.62714385986328 28 57.2272727273 23.2714843418 142.0 16.0 57.2272727273 23.2714843418 5036 145746
0.000543047 22.355082988739014 29 59.7738095238 21.6664933274 123.0 25.0 59.7738095238 21.6664933274 5021 150767
0.000667085 23.08968758583069 30 59.7529411765 26.2651215302 161.0 18.0 59.7529411765 26.2651215302 5079 155846
0.000729825 23.830260038375854 31 56.6853932584 21.1477390114 134.0 17.0 56.6853932584 21.1477390114 5045 160891
0.00101255 24.568735122680664 32 59.3176470588 23.2050764044 137.0 21.0 59.3176470588 23.2050764044 5042 165933
0.000377043 25.304160356521606 33 60.119047619 23.4837353857 173.0 27.0 60.119047619 23.4837353857 5050 170983
0.000578684 26.035377264022827 34 67.2133333333 24.9235060847 139.0 22.0 67.2133333333 24.9235060847 5041 176024
0.000866341 26.764827251434326 35 65.4025974026 27.3116975749 169.0 21.0 65.4025974026 27.3116975749 5036 181060
0.00127801 27.489142179489136 36 65.8947368421 30.0659708621 200.0 22.0 65.8947368421 30.0659708621 5008 186068
0.000953105 28.224390506744385 37 68.2162162162 24.8554036054 141.0 20.0 68.2162162162 24.8554036054 5048 191116
0.000155028 28.961978673934937 38 73.5507246377 25.6868184951 149.0 27.0 73.5507246377 25.6868184951 5075 196191
0.000502283 29.71060538291931 39 65.987012987 25.9156942404 200.0 22.0 65.987012987 25.9156942404 5081 201272
0.000469707 30.464702606201172 40 66.7236842105 23.9822295418 146.0 22.0 66.7236842105 23.9822295418 5071 206343
0.000762885 31.204124212265015 41 72.5072463768 29.8530814026 151.0 27.0 72.5072463768 29.8530814026 5003 211346
0.000831139 31.940929889678955 42 71.9714285714 27.7529774097 189.0 33.0 71.9714285714 27.7529774097 5038 216384
0.00032175 32.664103984832764 43 68.698630137 21.7013887135 127.0 16.0 68.698630137 21.7013887135 5015 221399
0.000983771 33.41014647483826 44 74.1029411765 29.7188490919 200.0 33.0 74.1029411765 29.7188490919 5039 226438
0.00119801 34.1444149017334 45 74.0588235294 29.2186898048 176.0 34.0 74.0588235294 29.2186898048 5036 231474
-2.9193e-05 34.88904619216919 46 86.3728813559 29.3389879466 200.0 40.0 86.3728813559 29.3389879466 5096 236570
0.000888577 35.61894631385803 47 85.3389830508 31.5135753204 166.0 36.0 85.3389830508 31.5135753204 5035 241605
0.000783239 36.34210133552551 48 79.9047619048 27.2558217376 166.0 40.0 79.9047619048 27.2558217376 5034 246639
0.000875896 37.09191298484802 49 78.625 28.6991397955 200.0 34.0 78.625 28.6991397955 5032 251671
0.000921857 37.93996572494507 50 89.5714285714 40.5197734547 200.0 20.0 89.5714285714 40.5197734547 5016 256687
0.000941476 38.76096820831299 51 86.8275862069 32.4542850532 195.0 31.0 86.8275862069 32.4542850532 5036 261723
0.000804049 39.515870809555054 52 97.7884615385 34.3457177593 200.0 40.0 97.7884615385 34.3457177593 5085 266808
0.000887642 40.27672076225281 53 101.5 36.8951216287 200.0 38.0 101.5 36.8951216287 5075 271883
0.00136711 41.024505376815796 54 100.34 40.3834669141 200.0 23.0 100.34 40.3834669141 5017 276900
0.00145344 41.77324175834656 55 102.163265306 35.8889141765 190.0 51.0 102.163265306 35.8889141765 5006 281906
0.00109367 42.535563707351685 56 114.863636364 41.6503797369 200.0 52.0 114.863636364 41.6503797369 5054 286960
0.00312584 43.279245376586914 57 102.489795918 32.9725442055 200.0 40.0 102.489795918 32.9725442055 5022 291982
0.00218063 44.04502820968628 58 116.227272727 40.6027672794 200.0 56.0 116.227272727 40.6027672794 5114 297096
0.00379006 44.803322553634644 59 120.833333333 44.6680436888 200.0 39.0 120.833333333 44.6680436888 5075 302171
0.00426648 45.55811643600464 60 138.486486486 37.3396547572 200.0 55.0 138.486486486 37.3396547572 5124 307295
0.00612824 46.33311629295349 61 155.696969697 38.8505176039 200.0 41.0 155.696969697 38.8505176039 5138 312433
0.00119338 47.098618507385254 62 169.166666667 36.5532336311 200.0 88.0 169.166666667 36.5532336311 5075 317508
0.00400569 47.86279487609863 63 173.24137931 34.0209420012 200.0 103.0 173.24137931 34.0209420012 5024 322532
0.00297006 48.64613676071167 64 172.066666667 32.8186261477 200.0 75.0 172.066666667 32.8186261477 5162 327694
0.000847508 49.44326043128967 65 178.379310345 27.4871929966 200.0 112.0 178.379310345 27.4871929966 5173 332867
-0.000368216 50.199233293533325 66 174.931034483 35.1351391399 200.0 88.0 174.931034483 35.1351391399 5073 337940
0.000455814 50.94071435928345 67 173.931034483 34.1396028849 200.0 95.0 173.931034483 34.1396028849 5044 342984
-0.000188774 51.689690351486206 68 155.575757576 41.4816719682 200.0 83.0 155.575757576 41.4816719682 5134 348118
1.27833e-05 52.42171359062195 69 161.64516129 40.6095081724 200.0 83.0 161.64516129 40.6095081724 5011 353129
-1.18166e-05 53.17059850692749 70 172.75862069 37.831436638 200.0 102.0 172.75862069 37.831436638 5010 358139
0.000311595 53.9037823677063 71 167.833333333 39.3946555879 200.0 85.0 167.833333333 39.3946555879 5035 363174
3.4133e-05 54.64700126647949 72 175.793103448 33.2517868956 200.0 92.0 175.793103448 33.2517868956 5098 368272
0.000232779 55.40592694282532 73 185.392857143 27.9672503446 200.0 98.0 185.392857143 27.9672503446 5191 373463
0.000155463 56.14131021499634 74 173.75862069 38.4507344196 200.0 78.0 173.75862069 38.4507344196 5039 378502
0.000283174 56.87232160568237 75 179.285714286 37.7433600053 200.0 82.0 179.285714286 37.7433600053 5020 383522
0.000339395 57.61250948905945 76 186.518518519 26.7323778859 200.0 91.0 186.518518519 26.7323778859 5036 388558
0.000387498 58.359134912490845 77 187.444444444 28.6347798539 200.0 85.0 187.444444444 28.6347798539 5061 393619
0.000383216 59.08751034736633 78 179.428571429 35.3931274316 200.0 96.0 179.428571429 35.3931274316 5024 398643
0.000784987 59.84214425086975 79 187.814814815 30.8329273691 200.0 94.0 187.814814815 30.8329273691 5071 403714
0.00127842 60.60195255279541 80 185.25 30.4860916766 200.0 82.0 185.25 30.4860916766 5187 408901
0.000300896 61.35276961326599 81 189.851851852 29.5330369984 200.0 84.0 189.851851852 29.5330369984 5126 414027
0.0011514 62.087745904922485 82 194.615384615 15.6551218531 200.0 134.0 194.615384615 15.6551218531 5060 419087
0.000869313 62.82675790786743 83 194.461538462 18.3517569254 200.0 112.0 194.461538462 18.3517569254 5056 424143
0.00153546 63.594058990478516 84 190.962962963 28.1088907531 200.0 85.0 190.962962963 28.1088907531 5156 429299
-0.000268757 64.33792185783386 85 185.925925926 38.3124831469 200.0 51.0 185.925925926 38.3124831469 5020 434319
0.000304921 65.09815979003906 86 199.961538462 0.192307692308 200.0 199.0 199.961538462 0.192307692308 5199 439518
0.00207902 65.85063219070435 87 187.703703704 21.7269500081 200.0 126.0 187.703703704 21.7269500081 5068 444586
-0.000176729 66.61139178276062 88 184.285714286 35.4530445427 200.0 31.0 184.285714286 35.4530445427 5160 449746
0.000418452 67.42202663421631 89 190.296296296 22.1857725762 200.0 112.0 190.296296296 22.1857725762 5138 454884
5.90081e-05 68.22730016708374 90 190.851851852 18.832013137 200.0 122.0 190.851851852 18.832013137 5153 460037
-3.22791e-05 68.98505663871765 91 188.222222222 17.5168349359 200.0 156.0 188.222222222 17.5168349359 5082 465119
0.000217133 69.72587561607361 92 192.769230769 15.7169866272 200.0 134.0 192.769230769 15.7169866272 5012 470131
2.28211e-05 70.4915201663971 93 192.769230769 14.5266537316 200.0 140.0 192.769230769 14.5266537316 5012 475143
1.9134e-05 71.30477261543274 94 192.961538462 16.3271382608 200.0 121.0 192.961538462 16.3271382608 5017 480160
0.000211738 72.0791425704956 95 189.37037037 33.9979826723 200.0 28.0 189.37037037 33.9979826723 5113 485273
0.000518169 72.84925603866577 96 198.538461538 4.36093470248 200.0 183.0 198.538461538 4.36093470248 5162 490435
8.30565e-05 73.6331775188446 97 191.962962963 35.3254514075 200.0 13.0 191.962962963 35.3254514075 5183 495618
-7.70125e-05 74.4358856678009 98 194.730769231 12.0657101302 200.0 159.0 194.730769231 12.0657101302 5063 500681
-4.77671e-05 75.23541116714478 99 197.346153846 11.2692307692 200.0 142.0 197.346153846 11.2692307692 5131 505812
================================================
FILE: hw2/data/lb_rtg_na_CartPole-v0_24-01-2018_09-11-55/11/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "lb_rtg_na",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/lb_rtg_na_CartPole-v0_24-01-2018_09-11-55/11",
"max_path_length" : null,
"min_timesteps_per_batch" : 5000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 11,
"size" : 32}
================================================
FILE: hw2/data/lb_rtg_na_CartPole-v0_24-01-2018_09-11-55/21/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.00709982 0.844219446182251 0 20.8916666667 10.4317590665 76.0 8.0 20.8916666667 10.4317590665 5014 5014
0.00758859 1.61476731300354 1 21.2278481013 10.5301849036 70.0 8.0 21.2278481013 10.5301849036 5031 10045
0.00566304 2.3656728267669678 2 25.6666666667 15.5222476124 94.0 9.0 25.6666666667 15.5222476124 5005 15050
0.00635696 3.1253530979156494 3 25.9072164948 13.7406631649 80.0 10.0 25.9072164948 13.7406631649 5026 20076
0.00465509 3.879255533218384 4 28.1348314607 16.3914139015 97.0 9.0 28.1348314607 16.3914139015 5008 25084
0.00445579 4.621240139007568 5 30.9197530864 18.6554127435 120.0 9.0 30.9197530864 18.6554127435 5009 30093
0.00373886 5.3823723793029785 6 34.2876712329 20.6218260834 105.0 9.0 34.2876712329 20.6218260834 5006 35099
0.00520976 6.136051893234253 7 31.0745341615 17.7034062747 100.0 10.0 31.0745341615 17.7034062747 5003 40102
0.00324665 6.88628363609314 8 34.8472222222 20.7412362499 106.0 11.0 34.8472222222 20.7412362499 5018 45120
0.00303591 7.634983539581299 9 40.6290322581 24.2212475845 126.0 11.0 40.6290322581 24.2212475845 5038 50158
0.00199103 8.381307363510132 10 41.5289256198 20.4886884254 105.0 9.0 41.5289256198 20.4886884254 5025 55183
0.00184191 9.133768081665039 11 45.7090909091 24.5024471707 129.0 12.0 45.7090909091 24.5024471707 5028 60211
0.00211094 9.931074619293213 12 43.5913043478 22.7075531016 134.0 10.0 43.5913043478 22.7075531016 5013 65224
0.00222015 10.667287349700928 13 46.8518518519 22.6003174407 115.0 13.0 46.8518518519 22.6003174407 5060 70284
0.00207962 11.389039993286133 14 51.0306122449 24.7862099916 146.0 16.0 51.0306122449 24.7862099916 5001 75285
0.00187184 12.130177974700928 15 52.2783505155 25.1726992798 124.0 13.0 52.2783505155 25.1726992798 5071 80356
0.00164369 12.850882768630981 16 55.0549450549 28.643455282 164.0 16.0 55.0549450549 28.643455282 5010 85366
0.00135211 13.587401390075684 17 56.1 24.8511345594 140.0 19.0 56.1 24.8511345594 5049 90415
0.000852295 14.365530252456665 18 61.243902439 31.6919474944 198.0 12.0 61.243902439 31.6919474944 5022 95437
0.00137572 15.137531518936157 19 54.6774193548 25.5208796198 126.0 15.0 54.6774193548 25.5208796198 5085 100522
0.00105478 15.864173173904419 20 63.425 29.6550059012 156.0 18.0 63.425 29.6550059012 5074 105596
0.000993645 16.592454433441162 21 59.8928571429 24.2285830104 143.0 17.0 59.8928571429 24.2285830104 5031 110627
0.00100151 17.32512593269348 22 67.8 32.3324398502 198.0 18.0 67.8 32.3324398502 5085 115712
0.0010774 18.058011054992676 23 63.0375 30.3189065395 149.0 17.0 63.0375 30.3189065395 5043 120755
0.00150949 18.787478923797607 24 62.3456790123 25.7035139519 145.0 15.0 62.3456790123 25.7035139519 5050 125805
0.00100639 19.53034210205078 25 71.2253521127 35.9609323161 198.0 22.0 71.2253521127 35.9609323161 5057 130862
0.00158904 20.26245355606079 26 76.0454545455 33.2380905161 188.0 13.0 76.0454545455 33.2380905161 5019 135881
0.0006617 20.993446350097656 27 83.8166666667 33.5685823684 165.0 15.0 83.8166666667 33.5685823684 5029 140910
0.0012265 21.72940421104431 28 76.0757575758 40.6713772505 200.0 26.0 76.0757575758 40.6713772505 5021 145931
0.00119584 22.4600772857666 29 96.4423076923 35.0776136487 184.0 30.0 96.4423076923 35.0776136487 5015 150946
0.00131831 23.196717262268066 30 95.2075471698 37.9504933175 192.0 37.0 95.2075471698 37.9504933175 5046 155992
0.00184584 23.97110390663147 31 92.375 38.3557420268 200.0 27.0 92.375 38.3557420268 5173 161165
0.002163 24.722668647766113 32 102.36 38.9824370711 200.0 30.0 102.36 38.9824370711 5118 166283
0.00239399 25.46923828125 33 100.98 42.2863997049 200.0 14.0 100.98 42.2863997049 5049 171332
0.00341676 26.21594214439392 34 107.872340426 41.7401368251 200.0 16.0 107.872340426 41.7401368251 5070 176402
0.00327373 26.989912271499634 35 124.219512195 49.8443979753 200.0 24.0 124.219512195 49.8443979753 5093 181495
0.00164797 27.74598717689514 36 153.727272727 42.6900547124 200.0 71.0 153.727272727 42.6900547124 5073 186568
0.00237085 28.52032732963562 37 138.405405405 62.8096478471 200.0 17.0 138.405405405 62.8096478471 5121 191689
0.000858045 29.302531242370605 38 148.4 47.5191390013 200.0 47.0 148.4 47.5191390013 5194 196883
0.000702469 30.06991982460022 39 161.580645161 45.9465146234 200.0 24.0 161.580645161 45.9465146234 5009 201892
6.67535e-05 30.83187770843506 40 159.4375 43.6977813367 200.0 58.0 159.4375 43.6977813367 5102 206994
0.000159435 31.586252450942993 41 167.166666667 43.4749608651 200.0 51.0 167.166666667 43.4749608651 5015 212009
0.000333372 32.33633232116699 42 149.294117647 48.5226020178 200.0 21.0 149.294117647 48.5226020178 5076 217085
0.000437649 33.1016149520874 43 157.6875 36.0628249552 200.0 87.0 157.6875 36.0628249552 5046 222131
0.000664655 33.869017362594604 44 148.411764706 47.4825773912 200.0 62.0 148.411764706 47.4825773912 5046 227177
0.000666774 34.64691114425659 45 155.454545455 52.242494551 200.0 40.0 155.454545455 52.242494551 5130 232307
0.00021074 35.402334690093994 46 185.464285714 29.3494732769 200.0 81.0 185.464285714 29.3494732769 5193 237500
0.000403689 36.15603947639465 47 176.931034483 34.0009442409 200.0 88.0 176.931034483 34.0009442409 5131 242631
0.000573501 36.930792570114136 48 156.424242424 52.3097014602 200.0 25.0 156.424242424 52.3097014602 5162 247793
0.000405891 37.70341086387634 49 182.178571429 36.9643202208 200.0 48.0 182.178571429 36.9643202208 5101 252894
3.05005e-05 38.49839973449707 50 183.142857143 34.8534834145 200.0 74.0 183.142857143 34.8534834145 5128 258022
0.000533218 39.25599145889282 51 176.24137931 37.1406043926 200.0 75.0 176.24137931 37.1406043926 5111 263133
0.000626715 40.02505707740784 52 181.642857143 33.7302474322 200.0 70.0 181.642857143 33.7302474322 5086 268219
0.00037971 40.80280017852783 53 191.185185185 23.9954270906 200.0 101.0 191.185185185 23.9954270906 5162 273381
0.000356653 41.57303333282471 54 183.464285714 30.863156656 200.0 81.0 183.464285714 30.863156656 5137 278518
0.000826013 42.343125104904175 55 189.148148148 29.7367508047 200.0 75.0 189.148148148 29.7367508047 5107 283625
3.74415e-05 43.14119100570679 56 191.703703704 17.1114317751 200.0 135.0 191.703703704 17.1114317751 5176 288801
-8.32407e-05 43.90609431266785 57 188.148148148 31.353071447 200.0 44.0 188.148148148 31.353071447 5080 293881
0.000242933 44.65326499938965 58 186.814814815 32.5667827099 200.0 44.0 186.814814815 32.5667827099 5044 298925
2.38908e-05 45.41275978088379 59 193.0 15.5637646227 200.0 141.0 193.0 15.5637646227 5018 303943
0.000331896 46.163726568222046 60 196.192307692 7.22718814759 200.0 177.0 196.192307692 7.22718814759 5101 309044
0.000248192 46.902114152908325 61 186.0 21.5647174115 200.0 141.0 186.0 21.5647174115 5022 314066
0.000207475 47.665032625198364 62 181.892857143 29.7997354803 200.0 86.0 181.892857143 29.7997354803 5093 319159
6.89714e-06 48.42055153846741 63 191.62962963 19.845977572 200.0 101.0 191.62962963 19.845977572 5174 324333
0.000384181 49.180017709732056 64 197.461538462 8.79348871535 200.0 156.0 197.461538462 8.79348871535 5134 329467
5.45445e-05 49.981200218200684 65 197.769230769 7.27645144024 200.0 164.0 197.769230769 7.27645144024 5142 334609
1.588e-05 50.756521701812744 66 186.851851852 22.3121021864 200.0 121.0 186.851851852 22.3121021864 5045 339654
-5.02236e-05 51.52238130569458 67 194.846153846 13.2829917497 200.0 145.0 194.846153846 13.2829917497 5066 344720
0.000230215 52.29427790641785 68 181.892857143 30.8884389904 200.0 79.0 181.892857143 30.8884389904 5093 349813
6.05779e-06 53.08458185195923 69 195.0 13.1441709807 200.0 144.0 195.0 13.1441709807 5070 354883
0.000117386 53.84615898132324 70 192.538461538 16.793384158 200.0 131.0 192.538461538 16.793384158 5006 359889
0.000431694 54.64445209503174 71 191.333333333 19.7709101684 200.0 121.0 191.333333333 19.7709101684 5166 365055
4.46535e-05 55.41445183753967 72 196.269230769 9.80799396218 200.0 153.0 196.269230769 9.80799396218 5103 370158
-1.41176e-05 56.223687171936035 73 192.37037037 26.1974668667 200.0 64.0 192.37037037 26.1974668667 5194 375352
0.000649582 56.99431538581848 74 195.423076923 10.9022689132 200.0 157.0 195.423076923 10.9022689132 5081 380433
0.000594444 57.78494358062744 75 192.592592593 22.7746760911 200.0 82.0 192.592592593 22.7746760911 5200 385633
0.000152631 58.545631647109985 76 194.615384615 22.0594945947 200.0 86.0 194.615384615 22.0594945947 5060 390693
0.000268918 59.339725494384766 77 198.307692308 4.80199662616 200.0 181.0 198.307692308 4.80199662616 5156 395849
-0.000115577 60.11688733100891 78 199.653846154 1.73076923077 200.0 191.0 199.653846154 1.73076923077 5191 401040
-1.40513e-05 60.89062786102295 79 188.222222222 28.3527166813 200.0 111.0 188.222222222 28.3527166813 5082 406122
0.000109149 61.682870388031006 80 198.730769231 6.34615384615 200.0 167.0 198.730769231 6.34615384615 5167 411289
0.000325727 62.45433592796326 81 200.0 0.0 200.0 200.0 200.0 0.0 5200 416489
-2.08034e-06 63.20403838157654 82 193.769230769 18.3162552696 200.0 113.0 193.769230769 18.3162552696 5038 421527
7.98893e-05 63.95370030403137 83 193.5 20.4887398719 200.0 106.0 193.5 20.4887398719 5031 426558
0.000118044 64.7363224029541 84 197.576923077 12.1153846154 200.0 137.0 197.576923077 12.1153846154 5137 431695
0.000279564 65.49648714065552 85 196.384615385 12.5363377154 200.0 151.0 196.384615385 12.5363377154 5106 436801
7.79564e-05 66.2943046092987 86 199.730769231 1.34615384615 200.0 193.0 199.730769231 1.34615384615 5193 441994
1.27966e-05 67.07741832733154 87 196.961538462 12.2928395957 200.0 137.0 196.961538462 12.2928395957 5121 447115
0.000237506 67.86163139343262 88 199.730769231 0.942896205549 200.0 196.0 199.730769231 0.942896205549 5193 452308
-5.64558e-05 68.65244507789612 89 199.038461538 4.80769230769 200.0 175.0 199.038461538 4.80769230769 5175 457483
0.000251357 69.41124963760376 90 194.961538462 17.4675099921 200.0 132.0 194.961538462 17.4675099921 5069 462552
9.15024e-06 70.25489521026611 91 194.769230769 26.1538461538 200.0 64.0 194.769230769 26.1538461538 5064 467616
8.82237e-05 71.0567774772644 92 197.653846154 8.32485762268 200.0 163.0 197.653846154 8.32485762268 5139 472755
9.28479e-05 71.82378005981445 93 200.0 0.0 200.0 200.0 200.0 0.0 5200 477955
0.000385324 72.59261584281921 94 197.923076923 10.3846153846 200.0 146.0 197.923076923 10.3846153846 5146 483101
4.76184e-05 73.37181735038757 95 198.192307692 9.03846153846 200.0 153.0 198.192307692 9.03846153846 5153 488254
3.30666e-05 74.19956159591675 96 197.884615385 8.63947524705 200.0 156.0 197.884615385 8.63947524705 5145 493399
-7.58166e-06 74.93940758705139 97 194.230769231 23.2731401675 200.0 82.0 194.230769231 23.2731401675 5050 498449
0.000164103 75.6761224269867 98 193.461538462 25.7282107501 200.0 71.0 193.461538462 25.7282107501 5030 503479
2.32203e-05 76.44355249404907 99 200.0 0.0 200.0 200.0 200.0 0.0 5200 508679
================================================
FILE: hw2/data/lb_rtg_na_CartPole-v0_24-01-2018_09-11-55/21/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "lb_rtg_na",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/lb_rtg_na_CartPole-v0_24-01-2018_09-11-55/21",
"max_path_length" : null,
"min_timesteps_per_batch" : 5000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 21,
"size" : 32}
================================================
FILE: hw2/data/lb_rtg_na_CartPole-v0_24-01-2018_09-11-55/31/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.00852818 0.8192634582519531 0 23.5943396226 13.2250322266 76.0 8.0 23.5943396226 13.2250322266 5002 5002
0.00825548 1.5513641834259033 1 23.7311320755 12.795502329 74.0 8.0 23.7311320755 12.795502329 5031 10033
0.00692091 2.2784814834594727 2 25.8041237113 16.1329138977 112.0 9.0 25.8041237113 16.1329138977 5006 15039
0.00729473 3.0048444271087646 3 28.5170454545 15.9754692746 92.0 9.0 28.5170454545 15.9754692746 5019 20058
0.00589581 3.7355637550354004 4 30.4606060606 18.3413746452 100.0 10.0 30.4606060606 18.3413746452 5026 25084
0.00514365 4.46544623374939 5 34.986013986 19.518320608 115.0 11.0 34.986013986 19.518320608 5003 30087
0.0049184 5.208836555480957 6 35.7816901408 20.6305926936 115.0 9.0 35.7816901408 20.6305926936 5081 35168
0.00307455 5.936997413635254 7 40.6532258065 23.9293463895 155.0 11.0 40.6532258065 23.9293463895 5041 40209
0.00235437 6.660306453704834 8 41.775 24.6507141546 135.0 13.0 41.775 24.6507141546 5013 45222
0.00217444 7.38954496383667 9 41.1147540984 25.5333907778 200.0 9.0 41.1147540984 25.5333907778 5016 50238
0.00200507 8.157692670822144 10 47.0934579439 26.4067864084 135.0 13.0 47.0934579439 26.4067864084 5039 55277
0.00224532 8.892680168151855 11 49.8910891089 26.3967823535 151.0 14.0 49.8910891089 26.3967823535 5039 60316
0.00150588 9.637669563293457 12 54.0537634409 27.6811203046 153.0 14.0 54.0537634409 27.6811203046 5027 65343
0.00169684 10.381162643432617 13 55.0769230769 24.2411106486 109.0 15.0 55.0769230769 24.2411106486 5012 70355
0.00141397 11.1191987991333 14 64.6538461538 35.0398406664 196.0 15.0 64.6538461538 35.0398406664 5043 75398
0.00117437 11.877361536026001 15 61.6463414634 28.0741057461 154.0 11.0 61.6463414634 28.0741057461 5055 80453
0.00131834 12.646126747131348 16 61.3048780488 32.2322702349 163.0 18.0 61.3048780488 32.2322702349 5027 85480
0.00134269 13.384125232696533 17 65.8684210526 40.1760409439 200.0 17.0 65.8684210526 40.1760409439 5006 90486
0.00119478 14.140536546707153 18 66.0789473684 34.6561163273 200.0 10.0 66.0789473684 34.6561163273 5022 95508
0.000940827 14.888510704040527 19 70.8333333333 33.8739493482 197.0 13.0 70.8333333333 33.8739493482 5100 100608
0.00109478 15.643760681152344 20 72.3857142857 33.2274812498 183.0 19.0 72.3857142857 33.2274812498 5067 105675
0.00149433 16.41217827796936 21 81.0793650794 30.9794102577 180.0 30.0 81.0793650794 30.9794102577 5108 110783
0.00146056 17.17789912223816 22 83.8333333333 39.0555871661 183.0 26.0 83.8333333333 39.0555871661 5030 115813
0.0020229 17.922330379486084 23 78.25 34.9553286353 160.0 17.0 78.25 34.9553286353 5008 120821
0.00119456 18.645370721817017 24 87.9649122807 43.4878345208 200.0 25.0 87.9649122807 43.4878345208 5014 125835
0.0018345 19.391769409179688 25 94.5 50.1408202152 200.0 21.0 94.5 50.1408202152 5103 130938
0.00259639 20.142621278762817 26 89.1228070175 46.9049319127 200.0 20.0 89.1228070175 46.9049319127 5080 136018
0.00158356 20.893524646759033 27 117.23255814 52.4230719708 200.0 30.0 117.23255814 52.4230719708 5041 141059
0.00206387 21.653827667236328 28 107.446808511 55.5352326391 200.0 19.0 107.446808511 55.5352326391 5050 146109
0.00216241 22.407994747161865 29 123.219512195 53.9473601584 200.0 28.0 123.219512195 53.9473601584 5052 151161
0.00093225 23.15457844734192 30 131.947368421 52.2025142409 200.0 18.0 131.947368421 52.2025142409 5014 156175
0.00108183 23.92946982383728 31 144.138888889 41.4314378608 200.0 33.0 144.138888889 41.4314378608 5189 161364
0.000267847 24.68761444091797 32 149.882352941 50.2281645306 200.0 31.0 149.882352941 50.2281645306 5096 166460
0.000409525 25.434409856796265 33 126.575 59.1387721804 200.0 25.0 126.575 59.1387721804 5063 171523
0.000595581 26.180766344070435 34 136.513513514 55.506328649 200.0 25.0 136.513513514 55.506328649 5051 176574
0.000612896 26.93289589881897 35 159.03125 35.5488083265 200.0 90.0 159.03125 35.5488083265 5089 181663
0.000619702 27.708857774734497 36 152.323529412 49.2602456278 200.0 39.0 152.323529412 49.2602456278 5179 186842
0.000422613 28.45651650428772 37 161.612903226 49.8104001443 200.0 36.0 161.612903226 49.8104001443 5010 191852
0.0008023 29.226497888565063 38 154.636363636 43.1107229731 200.0 66.0 154.636363636 43.1107229731 5103 196955
0.000669142 29.981744289398193 39 173.655172414 44.8432333434 200.0 54.0 173.655172414 44.8432333434 5036 201991
0.000790442 30.739632606506348 40 164.806451613 45.2879100543 200.0 32.0 164.806451613 45.2879100543 5109 207100
0.000698908 31.489598989486694 41 157.09375 50.4277697399 200.0 27.0 157.09375 50.4277697399 5027 212127
0.000993903 32.25964689254761 42 160.21875 47.2260087075 200.0 26.0 160.21875 47.2260087075 5127 217254
0.00088098 33.02883172035217 43 164.258064516 44.365031087 200.0 36.0 164.258064516 44.365031087 5092 222346
-7.74884e-06 33.79120969772339 44 181.821428571 30.1485057334 200.0 70.0 181.821428571 30.1485057334 5091 227437
-4.9924e-05 34.55176758766174 45 180.107142857 32.4327207855 200.0 79.0 180.107142857 32.4327207855 5043 232480
0.00013655 35.33647131919861 46 172.533333333 41.4911503282 200.0 38.0 172.533333333 41.4911503282 5176 237656
0.000444423 36.09844899177551 47 160.03125 34.807941241 200.0 71.0 160.03125 34.807941241 5121 242777
0.000319959 36.87384295463562 48 177.620689655 36.3255526983 200.0 64.0 177.620689655 36.3255526983 5151 247928
0.000149456 37.65054202079773 49 168.066666667 46.1850865781 200.0 48.0 168.066666667 46.1850865781 5042 252970
-3.11681e-05 38.42203140258789 50 185.666666667 22.9766386995 200.0 116.0 185.666666667 22.9766386995 5013 257983
0.000193019 39.19131779670715 51 186.296296296 26.5773710692 200.0 70.0 186.296296296 26.5773710692 5030 263013
0.000103998 39.95960474014282 52 192.111111111 17.2548078825 200.0 130.0 192.111111111 17.2548078825 5187 268200
0.000104373 40.713011026382446 53 193.115384615 24.6986871702 200.0 86.0 193.115384615 24.6986871702 5021 273221
0.000215173 41.47309684753418 54 186.444444444 21.7857128401 200.0 122.0 186.444444444 21.7857128401 5034 278255
5.3172e-05 42.250810861587524 55 190.703703704 18.7533993261 200.0 116.0 190.703703704 18.7533993261 5149 283404
7.06115e-05 43.01404547691345 56 188.333333333 18.6388681901 200.0 148.0 188.333333333 18.6388681901 5085 288489
0.000189525 43.79591679573059 57 192.111111111 20.2582097365 200.0 113.0 192.111111111 20.2582097365 5187 293676
0.000428502 44.55479955673218 58 191.222222222 19.1124030571 200.0 129.0 191.222222222 19.1124030571 5163 298839
0.000122165 45.31778860092163 59 180.071428571 33.9052551462 200.0 50.0 180.071428571 33.9052551462 5042 303881
0.000197837 46.068172216415405 60 186.37037037 27.6085710633 200.0 105.0 186.37037037 27.6085710633 5032 308913
0.0001629 46.81413006782532 61 182.035714286 22.0510481495 200.0 115.0 182.035714286 22.0510481495 5097 314010
0.00023856 47.581167221069336 62 190.62962963 16.5622241934 200.0 152.0 190.62962963 16.5622241934 5147 319157
4.71873e-05 48.34981036186218 63 191.666666667 15.2242496622 200.0 152.0 191.666666667 15.2242496622 5175 324332
5.49315e-05 49.10484790802002 64 191.444444444 15.5856851068 200.0 145.0 191.444444444 15.5856851068 5169 329501
0.000161896 49.84175181388855 65 188.296296296 15.803925473 200.0 134.0 188.296296296 15.803925473 5084 334585
0.000108373 50.5724561214447 66 193.230769231 11.7057109412 200.0 167.0 193.230769231 11.7057109412 5024 339609
8.91141e-05 51.31172013282776 67 187.259259259 26.4387378426 200.0 97.0 187.259259259 26.4387378426 5056 344665
0.000196564 52.06863069534302 68 190.333333333 17.3632220939 200.0 140.0 190.333333333 17.3632220939 5139 349804
0.00016378 52.81809973716736 69 191.259259259 19.5231915131 200.0 120.0 191.259259259 19.5231915131 5164 354968
0.000104967 53.567174673080444 70 188.777777778 19.1027113323 200.0 131.0 188.777777778 19.1027113323 5097 360065
3.7506e-05 54.31502103805542 71 183.642857143 23.1705081727 200.0 133.0 183.642857143 23.1705081727 5142 365207
-4.48567e-05 55.05347013473511 72 195.461538462 12.5122425255 200.0 153.0 195.461538462 12.5122425255 5082 370289
8.75229e-05 55.79431176185608 73 187.074074074 22.566651774 200.0 120.0 187.074074074 22.566651774 5051 375340
0.000193975 56.54970598220825 74 192.333333333 20.2210011841 200.0 112.0 192.333333333 20.2210011841 5193 380533
0.000424758 57.28663969039917 75 195.153846154 10.4538999263 200.0 160.0 195.153846154 10.4538999263 5074 385607
-3.79484e-05 58.035866022109985 76 195.423076923 11.8813786979 200.0 154.0 195.423076923 11.8813786979 5081 390688
-3.13865e-05 58.78322887420654 77 195.692307692 8.90880822026 200.0 169.0 195.692307692 8.90880822026 5088 395776
2.90154e-05 59.532947063446045 78 195.961538462 7.72349447232 200.0 173.0 195.961538462 7.72349447232 5095 400871
0.000310309 60.27763295173645 79 189.444444444 23.8037241614 200.0 102.0 189.444444444 23.8037241614 5115 405986
0.000192861 61.020285844802856 80 195.384615385 12.6554242645 200.0 152.0 195.384615385 12.6554242645 5080 411066
3.37482e-05 61.75401759147644 81 194.961538462 12.6384053559 200.0 155.0 194.961538462 12.6384053559 5069 416135
0.000311275 62.50336503982544 82 192.0 24.4570674478 200.0 78.0 192.0 24.4570674478 5184 421319
-4.14848e-05 63.23930740356445 83 195.384615385 12.1910336631 200.0 152.0 195.384615385 12.1910336631 5080 426399
8.35683e-05 63.99020981788635 84 197.230769231 9.54869178437 200.0 156.0 197.230769231 9.54869178437 5128 431527
-8.54547e-05 64.74620199203491 85 189.703703704 32.8946858421 200.0 59.0 189.703703704 32.8946858421 5122 436649
0.000109387 65.5024299621582 86 189.444444444 33.139808593 200.0 62.0 189.444444444 33.139808593 5115 441764
5.19487e-05 66.24031376838684 87 194.269230769 11.5710437409 200.0 157.0 194.269230769 11.5710437409 5051 446815
7.99679e-05 66.9940824508667 88 198.461538462 4.81368856836 200.0 182.0 198.461538462 4.81368856836 5160 451975
-2.84911e-05 67.72430562973022 89 196.192307692 13.8980331502 200.0 128.0 196.192307692 13.8980331502 5101 457076
0.000151173 68.46254849433899 90 194.307692308 21.703897613 200.0 90.0 194.307692308 21.703897613 5052 462128
4.51384e-05 69.2202799320221 91 199.692307692 1.35218429471 200.0 193.0 199.692307692 1.35218429471 5192 467320
6.59333e-05 69.97366285324097 92 198.346153846 8.26923076923 200.0 157.0 198.346153846 8.26923076923 5157 472477
0.000195397 70.72436618804932 93 190.37037037 21.0134844681 200.0 110.0 190.37037037 21.0134844681 5140 477617
7.83659e-05 71.46233987808228 94 196.230769231 10.5148528367 200.0 156.0 196.230769231 10.5148528367 5102 482719
0.000434656 72.20595240592957 95 195.0 18.1043981057 200.0 116.0 195.0 18.1043981057 5070 487789
2.01697e-05 72.95549416542053 96 191.0 18.8934634983 200.0 123.0 191.0 18.8934634983 5157 492946
4.04462e-05 73.70103120803833 97 195.653846154 12.8300797638 200.0 145.0 195.653846154 12.8300797638 5087 498033
0.000268863 74.4306275844574 98 192.769230769 16.807296246 200.0 147.0 192.769230769 16.807296246 5012 503045
0.000188474 75.18953919410706 99 198.923076923 3.74086658947 200.0 185.0 198.923076923 3.74086658947 5172 508217
================================================
FILE: hw2/data/lb_rtg_na_CartPole-v0_24-01-2018_09-11-55/31/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "lb_rtg_na",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/lb_rtg_na_CartPole-v0_24-01-2018_09-11-55/31",
"max_path_length" : null,
"min_timesteps_per_batch" : 5000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 31,
"size" : 32}
================================================
FILE: hw2/data/lb_rtg_na_CartPole-v0_24-01-2018_09-11-55/41/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0070728 0.8127944469451904 0 22.9497716895 11.6635574765 103.0 9.0 22.9497716895 11.6635574765 5026 5026
0.00689626 1.5295259952545166 1 24.6650246305 14.818312076 96.0 8.0 24.6650246305 14.818312076 5007 10033
0.00575969 2.260253429412842 2 30.2530120482 18.2653423699 137.0 9.0 30.2530120482 18.2653423699 5022 15055
0.00519163 2.975419282913208 3 31.4716981132 18.1817557741 102.0 8.0 31.4716981132 18.1817557741 5004 20059
0.00623068 3.7028419971466064 4 32.487012987 20.4184271921 128.0 8.0 32.487012987 20.4184271921 5003 25062
0.00336916 4.427679061889648 5 37.6492537313 22.7308251036 134.0 10.0 37.6492537313 22.7308251036 5045 30107
0.00304474 5.163336277008057 6 38.2824427481 20.5088976443 106.0 12.0 38.2824427481 20.5088976443 5015 35122
0.0032114 5.887061595916748 7 38.0984848485 19.8436539923 103.0 11.0 38.0984848485 19.8436539923 5029 40151
0.0023353 6.597307205200195 8 47.1401869159 29.3708001088 147.0 9.0 47.1401869159 29.3708001088 5044 45195
0.00162027 7.323731422424316 9 51.1734693878 35.5966707656 200.0 9.0 51.1734693878 35.5966707656 5015 50210
0.0018194 8.063063383102417 10 48.1037735849 27.2818722194 135.0 14.0 48.1037735849 27.2818722194 5099 55309
0.00277128 8.789302110671997 11 48.1923076923 23.0626558461 128.0 16.0 48.1923076923 23.0626558461 5012 60321
0.00230305 9.507325410842896 12 48.7766990291 25.2947410163 177.0 10.0 48.7766990291 25.2947410163 5024 65345
0.00140344 10.23879337310791 13 54.4456521739 25.8349123956 140.0 15.0 54.4456521739 25.8349123956 5009 70354
0.000822934 10.955813646316528 14 58.9764705882 31.6632934523 200.0 14.0 58.9764705882 31.6632934523 5013 75367
0.00137248 11.668684959411621 15 52.28125 27.0153132212 159.0 15.0 52.28125 27.0153132212 5019 80386
0.00130177 12.395529985427856 16 62.1358024691 30.5665649202 200.0 22.0 62.1358024691 30.5665649202 5033 85419
0.00158033 13.120411157608032 17 59.630952381 30.3953237952 175.0 18.0 59.630952381 30.3953237952 5009 90428
0.00151476 13.838882446289062 18 61.5609756098 27.2074673936 137.0 20.0 61.5609756098 27.2074673936 5048 95476
0.00183145 14.568061351776123 19 68.0945945946 29.1766145337 172.0 19.0 68.0945945946 29.1766145337 5039 100515
0.00199065 15.293811321258545 20 67.7866666667 30.7407626595 153.0 18.0 67.7866666667 30.7407626595 5084 105599
0.00176891 16.032551050186157 21 69.4324324324 32.5991548063 191.0 22.0 69.4324324324 32.5991548063 5138 110737
0.00155184 16.763168334960938 22 80.7419354839 42.707533325 200.0 15.0 80.7419354839 42.707533325 5006 115743
0.00180935 17.502472639083862 23 84.7166666667 41.4142051582 200.0 18.0 84.7166666667 41.4142051582 5083 120826
0.0019641 18.22032403945923 24 83.6666666667 33.9679587585 177.0 28.0 83.6666666667 33.9679587585 5020 125846
0.00253778 18.955332279205322 25 97.5769230769 42.6110973961 200.0 18.0 97.5769230769 42.6110973961 5074 130920
0.00259729 19.680816411972046 26 104.625 48.3923310901 200.0 20.0 104.625 48.3923310901 5022 135942
0.00350496 20.41430902481079 27 110.5 46.2299310159 200.0 39.0 110.5 46.2299310159 5083 141025
0.00389458 21.13617730140686 28 138.944444444 46.7457332839 200.0 51.0 138.944444444 46.7457332839 5002 146027
0.00237697 21.886387825012207 29 136.131578947 48.3153953086 200.0 36.0 136.131578947 48.3153953086 5173 151200
0.000498984 22.636456727981567 30 162.3125 49.2553534527 200.0 28.0 162.3125 49.2553534527 5194 156394
0.00202765 23.387754917144775 31 143.833333333 57.0026802489 200.0 21.0 143.833333333 57.0026802489 5178 161572
0.000218194 24.134782791137695 32 159.4375 53.6026687185 200.0 22.0 159.4375 53.6026687185 5102 166674
0.000243789 24.873219966888428 33 157.4375 49.7474481129 200.0 20.0 157.4375 49.7474481129 5038 171712
0.000283616 25.60975217819214 34 148.911764706 56.1559633034 200.0 22.0 148.911764706 56.1559633034 5063 176775
0.000441037 26.356652975082397 35 156.909090909 46.4858164334 200.0 26.0 156.909090909 46.4858164334 5178 181953
0.000223555 27.113117694854736 36 152.205882353 56.6146828865 200.0 23.0 152.205882353 56.6146828865 5175 187128
0.00043323 27.85383176803589 37 158.46875 48.2629415125 200.0 28.0 158.46875 48.2629415125 5071 192199
0.000640237 28.60311794281006 38 160.9375 55.9675896725 200.0 15.0 160.9375 55.9675896725 5150 197349
0.000535054 29.35600757598877 39 171.5 34.490336811 200.0 106.0 171.5 34.490336811 5145 202494
0.000432309 30.103681802749634 40 165.64516129 46.7274516173 200.0 33.0 165.64516129 46.7274516173 5135 207629
0.000874796 30.840723037719727 41 157.78125 51.3357419196 200.0 45.0 157.78125 51.3357419196 5049 212678
0.000280771 31.570555210113525 42 167.266666667 51.7035997028 200.0 19.0 167.266666667 51.7035997028 5018 217696
0.000380246 32.308385372161865 43 180.607142857 34.7566430297 200.0 65.0 180.607142857 34.7566430297 5057 222753
0.000174211 33.057018756866455 44 170.833333333 33.9107488695 200.0 90.0 170.833333333 33.9107488695 5125 227878
0.000165154 33.78743553161621 45 194.153846154 18.4738740839 200.0 106.0 194.153846154 18.4738740839 5048 232926
0.000417496 34.53668475151062 46 190.37037037 24.1448532176 200.0 115.0 190.37037037 24.1448532176 5140 238066
4.32557e-05 35.29369115829468 47 192.0 17.2089554636 200.0 133.0 192.0 17.2089554636 5184 243250
0.000670531 36.021838426589966 48 187.0 31.379398762 200.0 53.0 187.0 31.379398762 5049 248299
0.000606308 36.755168199539185 49 193.115384615 16.2819553803 200.0 130.0 193.115384615 16.2819553803 5021 253320
-0.000237477 37.48416996002197 50 186.0 22.6666666667 200.0 113.0 186.0 22.6666666667 5022 258342
5.38139e-05 38.232895612716675 51 189.444444444 29.7873119065 200.0 51.0 189.444444444 29.7873119065 5115 263457
6.02445e-05 38.972782611846924 52 183.321428571 32.2369060588 200.0 74.0 183.321428571 32.2369060588 5133 268590
3.29029e-05 39.70886754989624 53 189.851851852 19.5631999649 200.0 127.0 189.851851852 19.5631999649 5126 273716
0.000112119 40.44668245315552 54 181.678571429 38.4643188752 200.0 34.0 181.678571429 38.4643188752 5087 278803
0.000247866 41.20482134819031 55 185.142857143 19.3736092325 200.0 138.0 185.142857143 19.3736092325 5184 283987
0.000507317 41.954840421676636 56 188.814814815 28.8431737056 200.0 85.0 188.814814815 28.8431737056 5098 289085
0.00126268 42.69411873817444 57 189.888888889 21.2782854596 200.0 124.0 189.888888889 21.2782854596 5127 294212
0.000463803 43.4340398311615 58 194.307692308 15.1219891619 200.0 135.0 194.307692308 15.1219891619 5052 299264
0.000152758 44.17498803138733 59 188.888888889 23.980444708 200.0 104.0 188.888888889 23.980444708 5100 304364
0.000326727 44.912776470184326 60 193.923076923 18.8881792031 200.0 105.0 193.923076923 18.8881792031 5042 309406
-0.000265968 45.6757116317749 61 191.962962963 23.3848344042 200.0 86.0 191.962962963 23.3848344042 5183 314589
2.7711e-05 46.42876410484314 62 196.769230769 10.4230059606 200.0 158.0 196.769230769 10.4230059606 5116 319705
0.000235483 47.18703007698059 63 185.535714286 33.4284760377 200.0 88.0 185.535714286 33.4284760377 5195 324900
0.000480677 47.944849491119385 64 189.481481481 25.8419274169 200.0 110.0 189.481481481 25.8419274169 5116 330016
0.000265057 48.70005989074707 65 191.333333333 27.7261742897 200.0 57.0 191.333333333 27.7261742897 5166 335182
0.000443841 49.4328556060791 66 194.615384615 17.5982449367 200.0 126.0 194.615384615 17.5982449367 5060 340242
0.000159204 50.19224238395691 67 191.814814815 18.8798090014 200.0 127.0 191.814814815 18.8798090014 5179 345421
-0.00020037 50.93405604362488 68 195.076923077 12.1177653339 200.0 149.0 195.076923077 12.1177653339 5072 350493
8.028e-05 51.669798851013184 69 186.777777778 23.3179843696 200.0 106.0 186.777777778 23.3179843696 5043 355536
2.8835e-05 52.4196891784668 70 187.222222222 30.1739811063 200.0 74.0 187.222222222 30.1739811063 5055 360591
-5.89539e-06 53.1559202671051 71 193.807692308 13.2607553758 200.0 155.0 193.807692308 13.2607553758 5039 365630
0.000195592 53.88532018661499 72 194.269230769 24.080885641 200.0 75.0 194.269230769 24.080885641 5051 370681
2.2406e-05 54.6334388256073 73 191.407407407 14.7504155855 200.0 138.0 191.407407407 14.7504155855 5168 375849
0.000375032 55.37854981422424 74 188.0 25.5458918927 200.0 95.0 188.0 25.5458918927 5076 380925
-1.61696e-05 56.1242356300354 75 197.423076923 5.82549487448 200.0 180.0 197.423076923 5.82549487448 5133 386058
5.60214e-05 56.875747203826904 76 191.333333333 22.9217671092 200.0 86.0 191.333333333 22.9217671092 5166 391224
0.000465973 57.60997676849365 77 192.807692308 14.0329810166 200.0 151.0 192.807692308 14.0329810166 5013 396237
0.000399933 58.356170415878296 78 197.384615385 7.70652532237 200.0 168.0 197.384615385 7.70652532237 5132 401369
-4.94265e-05 59.09893870353699 79 194.307692308 19.5207369635 200.0 110.0 194.307692308 19.5207369635 5052 406421
0.000349051 59.829442262649536 80 194.269230769 19.9606491576 200.0 118.0 194.269230769 19.9606491576 5051 411472
0.000119704 60.58124279975891 81 200.0 0.0 200.0 200.0 200.0 0.0 5200 416672
2.51583e-05 61.32762813568115 82 190.111111111 23.4810141325 200.0 114.0 190.111111111 23.4810141325 5133 421805
9.835e-05 62.06961417198181 83 194.076923077 16.475910333 200.0 144.0 194.076923077 16.475910333 5046 426851
0.000191644 62.80648970603943 84 193.615384615 18.178763864 200.0 128.0 193.615384615 18.178763864 5034 431885
-4.45616e-05 63.53690314292908 85 195.538461538 12.5214608672 200.0 149.0 195.538461538 12.5214608672 5084 436969
3.9747e-05 64.28857588768005 86 190.259259259 33.418327853 200.0 39.0 190.259259259 33.418327853 5137 442106
2.77776e-05 65.041579246521 87 192.481481481 22.5542479704 200.0 99.0 192.481481481 22.5542479704 5197 447303
0.0001155 65.78626799583435 88 200.0 0.0 200.0 200.0 200.0 0.0 5200 452503
4.85589e-05 66.5203206539154 89 194.038461538 16.8442657881 200.0 139.0 194.038461538 16.8442657881 5045 457548
4.08392e-05 67.24556422233582 90 192.961538462 24.4138686457 200.0 104.0 192.961538462 24.4138686457 5017 462565
0.000158427 68.00647282600403 91 200.0 0.0 200.0 200.0 200.0 0.0 5200 467765
0.000122844 68.76256394386292 92 199.230769231 3.84615384615 200.0 180.0 199.230769231 3.84615384615 5180 472945
0.000283671 69.51735806465149 93 198.769230769 6.15384615385 200.0 168.0 198.769230769 6.15384615385 5168 478113
5.91223e-05 70.24814748764038 94 193.846153846 19.0378010763 200.0 128.0 193.846153846 19.0378010763 5040 483153
-4.38471e-05 70.9946870803833 95 193.730769231 25.545672059 200.0 70.0 193.730769231 25.545672059 5037 488190
9.31771e-06 71.75398063659668 96 199.346153846 3.26923076923 200.0 183.0 199.346153846 3.26923076923 5183 493373
2.70125e-05 72.5127022266388 97 200.0 0.0 200.0 200.0 200.0 0.0 5200 498573
0.000312497 73.25572323799133 98 191.148148148 31.7824826009 200.0 56.0 191.148148148 31.7824826009 5161 503734
0.000137682 74.01744294166565 99 198.846153846 5.76923076923 200.0 170.0 198.846153846 5.76923076923 5170 508904
================================================
FILE: hw2/data/lb_rtg_na_CartPole-v0_24-01-2018_09-11-55/41/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "lb_rtg_na",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/lb_rtg_na_CartPole-v0_24-01-2018_09-11-55/41",
"max_path_length" : null,
"min_timesteps_per_batch" : 5000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 41,
"size" : 32}
================================================
FILE: hw2/data/sb_no_rtg_dna_CartPole-v0_24-01-2018_09-00-15/1/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0695553 0.26676321029663086 0 26.6578947368 14.9036843128 79.0 11.0 26.6578947368 14.9036843128 1013 1013
0.0533085 0.41727161407470703 1 28.0833333333 16.4340010006 92.0 11.0 28.0833333333 16.4340010006 1011 2024
0.0602245 0.5715935230255127 2 27.8888888889 18.500417079 107.0 10.0 27.8888888889 18.500417079 1004 3028
-0.0189342 0.7305214405059814 3 30.0294117647 15.9622445976 79.0 11.0 30.0294117647 15.9622445976 1021 4049
0.0398769 0.8914153575897217 4 31.78125 10.3915060717 54.0 13.0 31.78125 10.3915060717 1017 5066
0.0805664 1.0477454662322998 5 32.09375 14.8394730681 59.0 9.0 32.09375 14.8394730681 1027 6093
0.0129929 1.2096054553985596 6 33.5161290323 17.6833637286 70.0 10.0 33.5161290323 17.6833637286 1039 7132
0.046114 1.3674907684326172 7 36.4642857143 20.0008609509 97.0 11.0 36.4642857143 20.0008609509 1021 8153
0.0752792 1.5339980125427246 8 44.5833333333 20.7683988042 95.0 11.0 44.5833333333 20.7683988042 1070 9223
0.0371647 1.6910979747772217 9 36.6071428571 17.5912707364 89.0 14.0 36.6071428571 17.5912707364 1025 10248
0.0715485 1.8526866436004639 10 43.2083333333 21.1994087313 108.0 16.0 43.2083333333 21.1994087313 1037 11285
0.0465164 2.0146539211273193 11 40.1538461538 18.8122143376 86.0 13.0 40.1538461538 18.8122143376 1044 12329
0.0306664 2.172661781311035 12 43.6086956522 20.0363563693 122.0 23.0 43.6086956522 20.0363563693 1003 13332
-0.00780487 2.3179891109466553 13 45.5 24.728985569 130.0 15.0 45.5 24.728985569 1001 14333
-0.00870895 2.475621461868286 14 44.4782608696 16.3357957585 86.0 15.0 44.4782608696 16.3357957585 1023 15356
-0.0352325 2.6381564140319824 15 49.0476190476 20.9113234089 93.0 19.0 49.0476190476 20.9113234089 1030 16386
0.0377846 2.80056095123291 16 54.0526315789 25.7119134464 110.0 23.0 54.0526315789 25.7119134464 1027 17413
0.0641212 2.96364426612854 17 57.0526315789 20.9698371959 116.0 21.0 57.0526315789 20.9698371959 1084 18497
0.0112648 3.125338554382324 18 64.75 25.3414186659 136.0 30.0 64.75 25.3414186659 1036 19533
0.0274391 3.298767566680908 19 52.7142857143 27.4593081749 119.0 12.0 52.7142857143 27.4593081749 1107 20640
0.0264282 3.4619064331054688 20 54.5789473684 25.852447282 125.0 24.0 54.5789473684 25.852447282 1037 21677
-0.00576782 3.62321138381958 21 56.2777777778 23.3352512439 99.0 15.0 56.2777777778 23.3352512439 1013 22690
0.0719986 3.786242723464966 22 59.7058823529 20.3492006083 101.0 35.0 59.7058823529 20.3492006083 1015 23705
0.0848007 3.958007574081421 23 56.55 30.6536702533 150.0 28.0 56.55 30.6536702533 1131 24836
-0.00126648 4.122899293899536 24 55.2105263158 20.9901705 110.0 29.0 55.2105263158 20.9901705 1049 25885
0.0188637 4.277575731277466 25 56.7222222222 25.9653734285 109.0 20.0 56.7222222222 25.9653734285 1021 26906
0.00832367 4.436223268508911 26 64.75 23.6709209791 109.0 30.0 64.75 23.6709209791 1036 27942
0.0001297 4.586613178253174 27 59.0 20.2745856562 89.0 23.0 59.0 20.2745856562 1003 28945
0.00129318 4.751018047332764 28 56.3888888889 25.7102203822 113.0 17.0 56.3888888889 25.7102203822 1015 29960
-0.00964737 4.911317825317383 29 55.2105263158 21.0727535417 120.0 31.0 55.2105263158 21.0727535417 1049 31009
0.0236092 5.077770948410034 30 61.8235294118 23.5202923504 121.0 28.0 61.8235294118 23.5202923504 1051 32060
-0.00970268 5.245162010192871 31 51.5 10.7819293264 73.0 34.0 51.5 10.7819293264 1030 33090
0.0633125 5.4280171394348145 32 58.3333333333 26.4764045897 117.0 19.0 58.3333333333 26.4764045897 1050 34140
0.0119247 5.60162878036499 33 56.3333333333 22.9975844142 106.0 27.0 56.3333333333 22.9975844142 1014 35154
0.0304298 5.767058372497559 34 68.375 23.4943477245 109.0 23.0 68.375 23.4943477245 1094 36248
0.0348129 5.9209303855896 35 64.375 21.5779835712 116.0 42.0 64.375 21.5779835712 1030 37278
0.0223694 6.085963487625122 36 59.2777777778 22.7957246371 115.0 28.0 59.2777777778 22.7957246371 1067 38345
0.00432587 6.242608308792114 37 64.375 28.0220337413 141.0 34.0 64.375 28.0220337413 1030 39375
0.0951729 6.404228210449219 38 78.1428571429 34.3633050607 148.0 30.0 78.1428571429 34.3633050607 1094 40469
0.0411072 6.559280157089233 39 62.2352941176 17.1448136962 104.0 26.0 62.2352941176 17.1448136962 1058 41527
0.0350914 6.724547863006592 40 80.5384615385 35.5432897153 178.0 44.0 80.5384615385 35.5432897153 1047 42574
0.0104637 6.885917901992798 41 77.3571428571 21.8325024508 124.0 46.0 77.3571428571 21.8325024508 1083 43657
0.0298309 7.04845404624939 42 78.0714285714 26.2908574161 138.0 47.0 78.0714285714 26.2908574161 1093 44750
0.00150299 7.204078197479248 43 78.7692307692 49.2421861762 190.0 30.0 78.7692307692 49.2421861762 1024 45774
0.0109482 7.387624025344849 44 73.6875 38.8823847488 186.0 20.0 73.6875 38.8823847488 1179 46953
0.0320778 7.537585258483887 45 71.7857142857 29.0619500167 132.0 40.0 71.7857142857 29.0619500167 1005 47958
0.00949097 7.698730945587158 46 74.9285714286 17.1650154414 111.0 53.0 74.9285714286 17.1650154414 1049 49007
0.0549698 7.8582258224487305 47 71.6 28.0233236192 124.0 32.0 71.6 28.0233236192 1074 50081
0.0267181 8.013083457946777 48 74.2142857143 17.9251561915 113.0 53.0 74.2142857143 17.9251561915 1039 51120
0.0127373 8.165893316268921 49 73.2142857143 28.025953715 138.0 23.0 73.2142857143 28.025953715 1025 52145
0.0144615 8.321085214614868 50 74.0 31.1517025446 129.0 18.0 74.0 31.1517025446 1036 53181
0.0961761 8.489903211593628 51 83.8461538462 16.6910669514 112.0 56.0 83.8461538462 16.6910669514 1090 54271
0.0512886 8.644263744354248 52 94.6363636364 19.5041847597 122.0 63.0 94.6363636364 19.5041847597 1041 55312
0.164398 8.797695875167847 53 85.0833333333 22.8270976887 129.0 51.0 85.0833333333 22.8270976887 1021 56333
-0.0353851 8.951859474182129 54 93.0 33.9438038261 162.0 55.0 93.0 33.9438038261 1023 57356
0.0178337 9.109771966934204 55 82.3076923077 32.4923295454 177.0 50.0 82.3076923077 32.4923295454 1070 58426
0.00475311 9.274336099624634 56 82.6923076923 32.9273900841 150.0 23.0 82.6923076923 32.9273900841 1075 59501
-0.00341797 9.448599338531494 57 98.4166666667 34.841207244 194.0 64.0 98.4166666667 34.841207244 1181 60682
0.223412 9.602488279342651 58 86.8333333333 37.0311430495 181.0 43.0 86.8333333333 37.0311430495 1042 61724
-0.0367966 9.767964601516724 59 107.1 29.8377277955 174.0 73.0 107.1 29.8377277955 1071 62795
0.0714378 9.933268308639526 60 95.0909090909 39.2021672533 167.0 56.0 95.0909090909 39.2021672533 1046 63841
0.25898 10.088018894195557 61 129.375 50.3610402494 200.0 71.0 129.375 50.3610402494 1035 64876
-0.140133 10.244887828826904 62 94.8181818182 47.5830722036 200.0 29.0 94.8181818182 47.5830722036 1043 65919
0.0602951 10.407527446746826 63 119.888888889 36.3178696281 200.0 67.0 119.888888889 36.3178696281 1079 66998
0.0680237 10.566007852554321 64 81.5384615385 20.5112178861 120.0 45.0 81.5384615385 20.5112178861 1060 68058
-0.103096 10.724847316741943 65 89.6666666667 38.7327022324 157.0 45.0 89.6666666667 38.7327022324 1076 69134
0.0221062 10.889755487442017 66 95.7272727273 48.9008103839 200.0 45.0 95.7272727273 48.9008103839 1053 70187
0.127556 11.049236536026001 67 134.25 39.2929701092 200.0 89.0 134.25 39.2929701092 1074 71261
0.112709 11.212120771408081 68 116.444444444 34.1047768277 200.0 74.0 116.444444444 34.1047768277 1048 72309
0.185966 11.361629486083984 69 169.833333333 25.0693482608 200.0 137.0 169.833333333 25.0693482608 1019 73328
-0.204842 11.520984649658203 70 118.0 38.8587184555 200.0 68.0 118.0 38.8587184555 1062 74390
-0.0571518 11.69093108177185 71 163.285714286 30.3866243399 200.0 97.0 163.285714286 30.3866243399 1143 75533
-0.206757 11.837202310562134 72 125.875 37.0116113537 180.0 66.0 125.875 37.0116113537 1007 76540
0.0371017 11.99167513847351 73 148.857142857 36.945630213 200.0 83.0 148.857142857 36.945630213 1042 77582
0.0196075 12.162638902664185 74 163.142857143 29.7917945147 200.0 114.0 163.142857143 29.7917945147 1142 78724
0.0293808 12.333854675292969 75 158.857142857 35.9023619256 200.0 120.0 158.857142857 35.9023619256 1112 79836
0.107483 12.499439477920532 76 157.714285714 33.3454399783 200.0 113.0 157.714285714 33.3454399783 1104 80940
0.116196 12.65304446220398 77 173.333333333 37.8843268677 200.0 102.0 173.333333333 37.8843268677 1040 81980
0.0306549 12.817165851593018 78 175.0 23.4662878757 200.0 132.0 175.0 23.4662878757 1050 83030
-0.146461 12.982083082199097 79 185.666666667 20.4749169039 200.0 152.0 185.666666667 20.4749169039 1114 84144
0.112328 13.138765096664429 80 170.0 27.5136329844 200.0 126.0 170.0 27.5136329844 1020 85164
0.123535 13.29263162612915 81 145.0 32.518126813 200.0 108.0 145.0 32.518126813 1015 86179
0.0492401 13.459388732910156 82 183.5 16.6207701386 200.0 163.0 183.5 16.6207701386 1101 87280
-0.0250854 13.622073411941528 83 178.166666667 20.0201287597 200.0 138.0 178.166666667 20.0201287597 1069 88349
0.121941 13.77689790725708 84 167.166666667 23.8356642217 200.0 144.0 167.166666667 23.8356642217 1003 89352
0.148788 13.94554591178894 85 180.333333333 28.1937739384 200.0 133.0 180.333333333 28.1937739384 1082 90434
0.0373688 14.119234323501587 86 184.0 24.2280828792 200.0 137.0 184.0 24.2280828792 1104 91538
0.105103 14.293591022491455 87 188.5 21.1797859605 200.0 142.0 188.5 21.1797859605 1131 92669
0.09272 14.468586921691895 88 178.5 26.8995043325 200.0 129.0 178.5 26.8995043325 1071 93740
0.218491 14.635220766067505 89 179.333333333 29.5616117438 200.0 118.0 179.333333333 29.5616117438 1076 94816
0.140396 14.8213951587677 90 192.333333333 8.51795489279 200.0 176.0 192.333333333 8.51795489279 1154 95970
0.030838 14.988796710968018 91 176.166666667 26.7358477621 200.0 136.0 176.166666667 26.7358477621 1057 97027
0.0551605 15.1516592502594 92 173.833333333 22.7992446269 200.0 143.0 173.833333333 22.7992446269 1043 98070
0.0159683 15.30609655380249 93 167.5 34.1357583774 200.0 117.0 167.5 34.1357583774 1005 99075
-0.21524 15.466354608535767 94 169.833333333 28.2985080094 200.0 126.0 169.833333333 28.2985080094 1019 100094
-0.0805359 15.62272596359253 95 171.166666667 18.8185782909 200.0 138.0 171.166666667 18.8185782909 1027 101121
0.445854 15.782602787017822 96 171.333333333 34.1060437785 200.0 100.0 171.333333333 34.1060437785 1028 102149
0.3181 15.953724384307861 97 162.0 30.8961393797 200.0 111.0 162.0 30.8961393797 1134 103283
-0.101921 16.131590843200684 98 163.857142857 30.0923747884 200.0 127.0 163.857142857 30.0923747884 1147 104430
-0.192337 16.310768842697144 99 167.0 35.7571171737 200.0 112.0 167.0 35.7571171737 1169 105599
================================================
FILE: hw2/data/sb_no_rtg_dna_CartPole-v0_24-01-2018_09-00-15/1/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_no_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_no_rtg_dna_CartPole-v0_24-01-2018_09-00-15/1",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : false,
"seed" : 1,
"size" : 32}
================================================
FILE: hw2/data/sb_no_rtg_dna_CartPole-v0_24-01-2018_09-00-15/11/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
-0.00512409 0.24531316757202148 0 16.4918032787 6.88220073175 44.0 9.0 16.4918032787 6.88220073175 1006 1006
0.0635548 0.40613698959350586 1 19.1698113208 9.49028470268 46.0 8.0 19.1698113208 9.49028470268 1016 2022
0.0255032 0.5590510368347168 2 19.0188679245 8.25190787782 52.0 10.0 19.0188679245 8.25190787782 1008 3030
0.0534401 0.7072939872741699 3 20.5918367347 8.61398570278 50.0 10.0 20.5918367347 8.61398570278 1009 4039
0.0738297 0.8556599617004395 4 28.6285714286 16.5219952346 97.0 8.0 28.6285714286 16.5219952346 1002 5041
0.00234222 1.001749038696289 5 27.8888888889 20.2275633972 116.0 11.0 27.8888888889 20.2275633972 1004 6045
0.0697784 1.1574296951293945 6 31.1818181818 16.7882616738 78.0 10.0 31.1818181818 16.7882616738 1029 7074
-0.0150452 1.3107523918151855 7 28.7428571429 14.0455236532 68.0 9.0 28.7428571429 14.0455236532 1006 8080
0.0642204 1.4599130153656006 8 36.9285714286 17.6168113124 70.0 10.0 36.9285714286 17.6168113124 1034 9114
0.000818253 1.61649489402771 9 31.0606060606 13.6046769898 59.0 12.0 31.0606060606 13.6046769898 1025 10139
0.0203362 1.765744686126709 10 37.1111111111 13.8171480504 73.0 18.0 37.1111111111 13.8171480504 1002 11141
0.0524025 1.917654037475586 11 42.875 22.6868399812 99.0 16.0 42.875 22.6868399812 1029 12170
0.0946121 2.073711395263672 12 41.8 29.0406611495 127.0 11.0 41.8 29.0406611495 1045 13215
-0.0120049 2.229515552520752 13 44.2608695652 19.5430792627 86.0 13.0 44.2608695652 19.5430792627 1018 14233
-0.01828 2.373249053955078 14 38.6923076923 18.1463478647 79.0 12.0 38.6923076923 18.1463478647 1006 15239
0.00722122 2.5305798053741455 15 42.0833333333 24.6659628278 94.0 13.0 42.0833333333 24.6659628278 1010 16249
0.0697861 2.687572717666626 16 54.0 24.8765372442 113.0 20.0 54.0 24.8765372442 1026 17275
0.0720329 2.842419385910034 17 53.5789473684 30.0986374748 150.0 15.0 53.5789473684 30.0986374748 1018 18293
-0.0314293 2.998635768890381 18 40.1538461538 12.996130512 67.0 21.0 40.1538461538 12.996130512 1044 19337
0.04002 3.1500773429870605 19 50.45 17.3881425115 97.0 25.0 50.45 17.3881425115 1009 20346
0.0169601 3.300119400024414 20 40.88 20.4906222453 105.0 20.0 40.88 20.4906222453 1022 21368
0.0726242 3.452993392944336 21 54.9473684211 21.7363960704 99.0 24.0 54.9473684211 21.7363960704 1044 22412
-0.00358582 3.6137313842773438 22 50.8571428571 18.5402668966 88.0 20.0 50.8571428571 18.5402668966 1068 23480
0.0382233 3.771916389465332 23 54.1052631579 24.2961871318 119.0 19.0 54.1052631579 24.2961871318 1028 24508
0.0485229 3.9179751873016357 24 57.0 30.0906039229 146.0 20.0 57.0 30.0906039229 1026 25534
0.0298157 4.073188543319702 25 52.6842105263 20.6653858359 94.0 13.0 52.6842105263 20.6653858359 1001 26535
0.0353813 4.229984998703003 26 54.7368421053 29.8114109295 150.0 25.0 54.7368421053 29.8114109295 1040 27575
0.0338936 4.384675025939941 27 59.8823529412 19.9613814002 93.0 24.0 59.8823529412 19.9613814002 1018 28593
0.00600433 4.5373406410217285 28 59.4117647059 21.3570730081 124.0 29.0 59.4117647059 21.3570730081 1010 29603
0.0986519 4.700197696685791 29 53.05 14.5068087462 82.0 31.0 53.05 14.5068087462 1061 30664
-0.00643158 4.8460917472839355 30 50.2 13.1171643277 75.0 32.0 50.2 13.1171643277 1004 31668
0.0289154 5.004489183425903 31 60.2222222222 22.3620600213 100.0 17.0 60.2222222222 22.3620600213 1084 32752
0.0162506 5.149889945983887 32 56.2222222222 21.3139379425 106.0 29.0 56.2222222222 21.3139379425 1012 33764
0.0131226 5.3100059032440186 33 55.0 26.219719377 146.0 26.0 55.0 26.219719377 1045 34809
0.025032 5.459545612335205 34 57.3333333333 20.5831646417 107.0 21.0 57.3333333333 20.5831646417 1032 35841
0.0162392 5.611032485961914 35 64.6875 31.063883269 163.0 18.0 64.6875 31.063883269 1035 36876
0.0741539 5.769460201263428 36 70.9333333333 38.7633274572 188.0 24.0 70.9333333333 38.7633274572 1064 37940
-0.0285721 5.920390367507935 37 64.9375 23.8706638733 101.0 26.0 64.9375 23.8706638733 1039 38979
-0.00234985 6.076663255691528 38 62.1764705882 20.1763848395 104.0 29.0 62.1764705882 20.1763848395 1057 40036
0.0674629 6.230109691619873 39 58.3333333333 30.1293507693 149.0 26.0 58.3333333333 30.1293507693 1050 41086
-0.0244675 6.381539821624756 40 64.625 26.4572178243 132.0 33.0 64.625 26.4572178243 1034 42120
0.0077095 6.541299343109131 41 61.2941176471 31.663236626 148.0 21.0 61.2941176471 31.663236626 1042 43162
0.0532875 6.7038915157318115 42 61.4705882353 28.9484687131 124.0 25.0 61.4705882353 28.9484687131 1045 44207
0.0123177 6.855281591415405 43 59.0588235294 17.2233445827 89.0 33.0 59.0588235294 17.2233445827 1004 45211
0.0430298 7.007343530654907 44 65.75 33.1558818311 143.0 21.0 65.75 33.1558818311 1052 46263
0.18214 7.157165288925171 45 72.2142857143 32.761428914 160.0 33.0 72.2142857143 32.761428914 1011 47274
0.12225 7.309115886688232 46 73.4285714286 42.3838147776 200.0 33.0 73.4285714286 42.3838147776 1028 48302
-0.00220871 7.4603729248046875 47 83.5 42.2384106393 161.0 32.0 83.5 42.2384106393 1002 49304
-0.0353432 7.6135101318359375 48 75.6428571429 18.733496138 108.0 41.0 75.6428571429 18.733496138 1059 50363
-0.043251 7.77314305305481 49 68.125 35.7943343981 149.0 31.0 68.125 35.7943343981 1090 51453
0.0546303 7.923423528671265 50 93.2727272727 33.5019427092 166.0 48.0 93.2727272727 33.5019427092 1026 52479
0.0488052 8.073715925216675 51 83.6666666667 18.3318181192 115.0 60.0 83.6666666667 18.3318181192 1004 53483
0.124737 8.21993637084961 52 78.4615384615 32.0327125694 132.0 47.0 78.4615384615 32.0327125694 1020 54503
0.00512695 8.376291513442993 53 79.3846153846 20.9524680446 125.0 59.0 79.3846153846 20.9524680446 1032 55535
0.0900078 8.523650169372559 54 78.0 29.6362563815 155.0 38.0 78.0 29.6362563815 1014 56549
-0.0854263 8.691274404525757 55 75.2857142857 27.3820289643 137.0 29.0 75.2857142857 27.3820289643 1054 57603
0.0259819 8.843250751495361 56 78.1538461538 33.6882681105 157.0 22.0 78.1538461538 33.6882681105 1016 58619
-0.0107193 9.000697612762451 57 69.2 26.1258492685 130.0 38.0 69.2 26.1258492685 1038 59657
0.000843048 9.175877571105957 58 86.3846153846 34.7530595477 134.0 43.0 86.3846153846 34.7530595477 1123 60780
0.227783 9.331747770309448 59 88.1666666667 33.5803348537 143.0 35.0 88.1666666667 33.5803348537 1058 61838
-0.00689316 9.484697580337524 60 88.4166666667 32.9885291511 155.0 34.0 88.4166666667 32.9885291511 1061 62899
-0.00553131 9.63588547706604 61 77.0769230769 28.7093164682 131.0 38.0 77.0769230769 28.7093164682 1002 63901
0.0858879 9.810664653778076 62 87.1538461538 40.0304617738 154.0 33.0 87.1538461538 40.0304617738 1133 65034
-0.0164948 9.959284543991089 63 72.7142857143 29.9223484836 137.0 37.0 72.7142857143 29.9223484836 1018 66052
-0.00383377 10.113429307937622 64 78.6153846154 26.6387180956 151.0 42.0 78.6153846154 26.6387180956 1022 67074
-0.00390625 10.277899026870728 65 79.4615384615 32.2886390704 129.0 33.0 79.4615384615 32.2886390704 1033 68107
0.0369797 10.444634199142456 66 110.9 46.9711613652 200.0 46.0 110.9 46.9711613652 1109 69216
0.196167 10.613716840744019 67 112.1 30.332985346 163.0 65.0 112.1 30.332985346 1121 70337
0.0848923 10.77668571472168 68 117.666666667 52.5208953127 200.0 46.0 117.666666667 52.5208953127 1059 71396
-0.0565033 10.930248022079468 69 126.75 50.0668303371 190.0 42.0 126.75 50.0668303371 1014 72410
-0.00730133 11.088855743408203 70 108.7 39.9150347614 200.0 40.0 108.7 39.9150347614 1087 73497
0.040741 11.246061563491821 71 106.2 44.9306131719 193.0 45.0 106.2 44.9306131719 1062 74559
-0.0693817 11.401721239089966 72 131.0 44.9388473372 200.0 63.0 131.0 44.9388473372 1048 75607
0.143494 11.564889430999756 73 179.5 22.2766694099 200.0 145.0 179.5 22.2766694099 1077 76684
-0.0691681 11.736059188842773 74 140.375 43.7033680052 200.0 73.0 140.375 43.7033680052 1123 77807
0.148529 11.896079301834106 75 145.0 23.6099252737 191.0 109.0 145.0 23.6099252737 1015 78822
0.134094 12.05600881576538 76 170.5 41.7202988164 200.0 111.0 170.5 41.7202988164 1023 79845
-0.0364227 12.22243332862854 77 179.5 27.2136607852 200.0 128.0 179.5 27.2136607852 1077 80922
0.171593 12.37983512878418 78 168.333333333 33.4149002027 200.0 119.0 168.333333333 33.4149002027 1010 81932
0.0803986 12.533734798431396 79 171.0 39.8998746865 200.0 101.0 171.0 39.8998746865 1026 82958
-0.0387192 12.697980642318726 80 184.166666667 22.7773035181 200.0 136.0 184.166666667 22.7773035181 1105 84063
-0.0324173 12.87848973274231 81 194.0 10.2632028789 200.0 172.0 194.0 10.2632028789 1164 85227
0.0793839 13.043092250823975 82 186.833333333 22.7040133506 200.0 138.0 186.833333333 22.7040133506 1121 86348
0.0436401 13.220946550369263 83 196.0 8.94427191 200.0 176.0 196.0 8.94427191 1176 87524
-0.087738 13.38306975364685 84 178.333333333 33.1695978604 200.0 113.0 178.333333333 33.1695978604 1070 88594
0.123421 13.562474966049194 85 171.0 29.5151292923 200.0 122.0 171.0 29.5151292923 1197 89791
0.189339 13.716761350631714 86 172.0 23.7977589981 200.0 132.0 172.0 23.7977589981 1032 90823
-0.0461349 13.89915156364441 87 194.833333333 11.5530178837 200.0 169.0 194.833333333 11.5530178837 1169 91992
0.0202332 14.048897504806519 88 143.428571429 43.8564448525 200.0 72.0 143.428571429 43.8564448525 1004 92996
0.0436859 14.218897581100464 89 182.5 18.3643676722 200.0 154.0 182.5 18.3643676722 1095 94091
0.00720215 14.40112829208374 90 169.857142857 27.9562340169 200.0 126.0 169.857142857 27.9562340169 1189 95280
-0.0312271 14.559978008270264 91 146.857142857 56.0877592233 200.0 28.0 146.857142857 56.0877592233 1028 96308
-5.34058e-05 14.719226121902466 92 149.857142857 45.1993317632 200.0 88.0 149.857142857 45.1993317632 1049 97357
0.0502853 14.900869369506836 93 168.142857143 34.236273877 200.0 116.0 168.142857143 34.236273877 1177 98534
0.185455 15.074780464172363 94 163.857142857 41.9231561361 200.0 83.0 163.857142857 41.9231561361 1147 99681
0.101822 15.245348453521729 95 159.857142857 51.4793400208 200.0 50.0 159.857142857 51.4793400208 1119 100800
0.00431061 15.416551351547241 96 158.285714286 30.0129223869 200.0 120.0 158.285714286 30.0129223869 1108 101908
-0.104431 15.580619812011719 97 181.333333333 27.9682359512 200.0 128.0 181.333333333 27.9682359512 1088 102996
0.216705 15.75987458229065 98 185.666666667 15.5848929701 200.0 160.0 185.666666667 15.5848929701 1114 104110
-0.193115 15.948319673538208 99 195.166666667 10.8076618912 200.0 171.0 195.166666667 10.8076618912 1171 105281
================================================
FILE: hw2/data/sb_no_rtg_dna_CartPole-v0_24-01-2018_09-00-15/11/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_no_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_no_rtg_dna_CartPole-v0_24-01-2018_09-00-15/11",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : false,
"seed" : 11,
"size" : 32}
================================================
FILE: hw2/data/sb_no_rtg_dna_CartPole-v0_24-01-2018_09-00-15/21/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.127224 0.24825334548950195 0 22.7111111111 11.7636393126 64.0 9.0 22.7111111111 11.7636393126 1022 1022
0.0355492 0.3956305980682373 1 22.75 9.66983359827 52.0 9.0 22.75 9.66983359827 1001 2023
0.145908 0.5476939678192139 2 26.3684210526 13.9348503904 76.0 9.0 26.3684210526 13.9348503904 1002 3025
0.0449734 0.69586181640625 3 30.3333333333 15.6295498426 77.0 10.0 30.3333333333 15.6295498426 1001 4026
0.0844555 0.851891279220581 4 25.175 18.7535163369 105.0 10.0 25.175 18.7535163369 1007 5033
0.0250015 1.0081052780151367 5 26.6578947368 16.301882868 98.0 13.0 26.6578947368 16.301882868 1013 6046
0.127935 1.173598289489746 6 34.3548387097 21.0108242259 84.0 11.0 34.3548387097 21.0108242259 1065 7111
0.0802937 1.32609224319458 7 32.5806451613 18.6716521265 82.0 11.0 32.5806451613 18.6716521265 1010 8121
-0.0135117 1.4742002487182617 8 35.75 18.0586841001 78.0 12.0 35.75 18.0586841001 1001 9122
0.0420055 1.6327002048492432 9 36.0344827586 17.9164396837 84.0 16.0 36.0344827586 17.9164396837 1045 10167
0.156075 1.7924294471740723 10 50.7619047619 35.2418916874 142.0 17.0 50.7619047619 35.2418916874 1066 11233
0.0586586 1.9487698078155518 11 43.6666666667 18.7520369264 89.0 16.0 43.6666666667 18.7520369264 1048 12281
0.0249443 2.0962331295013428 12 43.7391304348 20.0287128487 79.0 14.0 43.7391304348 20.0287128487 1006 13287
0.103291 2.253335952758789 13 46.4090909091 27.289123859 136.0 10.0 46.4090909091 27.289123859 1021 14308
0.0521851 2.4151957035064697 14 47.3181818182 20.3165547447 89.0 13.0 47.3181818182 20.3165547447 1041 15349
0.0149422 2.5664660930633545 15 40.04 19.7189857751 81.0 16.0 40.04 19.7189857751 1001 16350
-0.0122757 2.723844528198242 16 67.8 25.7997416008 114.0 22.0 67.8 25.7997416008 1017 17367
0.0217094 2.878793716430664 17 51.25 24.1223444134 117.0 21.0 51.25 24.1223444134 1025 18392
0.0463638 3.03745436668396 18 54.2631578947 31.5825436549 143.0 14.0 54.2631578947 31.5825436549 1031 19423
0.0266075 3.191992998123169 19 53.7 21.2087246198 99.0 22.0 53.7 21.2087246198 1074 20497
-0.0139618 3.345797061920166 20 46.7272727273 20.356329858 91.0 17.0 46.7272727273 20.356329858 1028 21525
0.00762939 3.4980955123901367 21 53.8421052632 34.3070702517 173.0 17.0 53.8421052632 34.3070702517 1023 22548
0.007267 3.6499991416931152 22 60.1764705882 27.0429621031 119.0 22.0 60.1764705882 27.0429621031 1023 23571
0.033783 3.8080263137817383 23 64.875 39.7238514623 194.0 21.0 64.875 39.7238514623 1038 24609
0.0575562 3.9673943519592285 24 64.875 27.3104261226 120.0 31.0 64.875 27.3104261226 1038 25647
0.066494 4.131205081939697 25 75.2142857143 43.762636659 168.0 14.0 75.2142857143 43.762636659 1053 26700
0.0750923 4.294355630874634 26 72.0 25.1343059051 123.0 31.0 72.0 25.1343059051 1080 27780
0.00760651 4.4403345584869385 27 66.7333333333 41.919711619 200.0 14.0 66.7333333333 41.919711619 1001 28781
0.0697861 4.606956720352173 28 81.9230769231 42.8924622004 184.0 18.0 81.9230769231 42.8924622004 1065 29846
0.123104 4.766654014587402 29 72.4285714286 33.9867921525 154.0 26.0 72.4285714286 33.9867921525 1014 30860
0.0179214 4.929851055145264 30 87.0 32.1429100529 151.0 45.0 87.0 32.1429100529 1044 31904
0.159489 5.0865044593811035 31 93.5454545455 31.517278483 146.0 28.0 93.5454545455 31.517278483 1029 32933
-0.0285606 5.259975910186768 32 71.6 26.333248945 120.0 25.0 71.6 26.333248945 1074 34007
0.235893 5.415209770202637 33 84.0 44.7008575608 160.0 21.0 84.0 44.7008575608 1008 35015
-0.0416565 5.590892791748047 34 84.1538461538 41.6502768554 182.0 25.0 84.1538461538 41.6502768554 1094 36109
-0.0412064 5.766493082046509 35 124.666666667 35.1820661386 181.0 55.0 124.666666667 35.1820661386 1122 37231
0.0682449 5.939498424530029 36 100.636363636 56.2127011324 189.0 22.0 100.636363636 56.2127011324 1107 38338
-0.0410194 6.098473310470581 37 92.9090909091 31.8903078621 150.0 36.0 92.9090909091 31.8903078621 1022 39360
0.293282 6.264788389205933 38 136.375 48.6182514597 200.0 43.0 136.375 48.6182514597 1091 40451
-0.100487 6.433950185775757 39 107.7 42.8976689343 173.0 43.0 107.7 42.8976689343 1077 41528
0.218277 6.588805913925171 40 127.625 52.3233635673 200.0 44.0 127.625 52.3233635673 1021 42549
-0.0609665 6.745396137237549 41 125.625 39.015822111 200.0 84.0 125.625 39.015822111 1005 43554
0.19545 6.906362533569336 42 146.714285714 45.9027365686 200.0 49.0 146.714285714 45.9027365686 1027 44581
0.036705 7.082053184509277 43 143.25 45.0242989951 200.0 82.0 143.25 45.0242989951 1146 45727
0.0390778 7.253217697143555 44 157.857142857 28.5828548581 200.0 126.0 157.857142857 28.5828548581 1105 46832
0.0290222 7.432849884033203 45 149.0 51.9350555983 200.0 61.0 149.0 51.9350555983 1192 48024
0.0818787 7.59984016418457 46 178.833333333 30.9322736887 200.0 123.0 178.833333333 30.9322736887 1073 49097
0.10302 7.7628068923950195 47 172.166666667 42.4437536302 200.0 89.0 172.166666667 42.4437536302 1033 50130
-0.0214462 7.944441556930542 48 157.285714286 45.9431769712 200.0 56.0 157.285714286 45.9431769712 1101 51231
-0.112823 8.118605613708496 49 177.166666667 25.7773587131 200.0 137.0 177.166666667 25.7773587131 1063 52294
-0.0194626 8.284399509429932 50 155.571428571 51.7020506442 200.0 62.0 155.571428571 51.7020506442 1089 53383
0.04776 8.44839882850647 51 97.1818181818 33.905800474 151.0 29.0 97.1818181818 33.905800474 1069 54452
0.215149 8.627105236053467 52 162.571428571 49.149501212 200.0 71.0 162.571428571 49.149501212 1138 55590
-0.00525665 8.803398609161377 53 146.875 53.0269683746 200.0 54.0 146.875 53.0269683746 1175 56765
0.116333 8.964084148406982 54 135.75 59.1433639557 200.0 49.0 135.75 59.1433639557 1086 57851
0.0122528 9.120773315429688 55 112.0 29.4316534062 171.0 74.0 112.0 29.4316534062 1008 58859
0.0180054 9.281006097793579 56 129.625 43.5859424012 200.0 92.0 129.625 43.5859424012 1037 59896
0.0564804 9.44934606552124 57 123.111111111 41.2295590955 200.0 73.0 123.111111111 41.2295590955 1108 61004
-0.0479202 9.612768173217773 58 169.666666667 26.8679900418 200.0 126.0 169.666666667 26.8679900418 1018 62022
-0.00257111 9.777464628219604 59 127.25 44.1071139387 199.0 58.0 127.25 44.1071139387 1018 63040
0.144714 9.94826364517212 60 151.142857143 44.4118020718 200.0 90.0 151.142857143 44.4118020718 1058 64098
0.0379715 10.13560152053833 61 131.444444444 55.5999822364 200.0 12.0 131.444444444 55.5999822364 1183 65281
0.0575562 10.304075956344604 62 152.714285714 47.9544852236 200.0 64.0 152.714285714 47.9544852236 1069 66350
0.0810928 10.491063356399536 63 148.375 31.6264821787 200.0 106.0 148.375 31.6264821787 1187 67537
-0.00558472 10.65860104560852 64 153.285714286 35.9909285623 200.0 83.0 153.285714286 35.9909285623 1073 68610
0.158897 10.821058750152588 65 176.0 30.9892454463 200.0 113.0 176.0 30.9892454463 1056 69666
-0.0596466 10.984571933746338 66 150.857142857 44.1472489725 200.0 89.0 150.857142857 44.1472489725 1056 70722
0.0832291 11.142368793487549 67 166.833333333 47.012114278 200.0 95.0 166.833333333 47.012114278 1001 71723
0.106728 11.310542345046997 68 184.833333333 31.3071699278 200.0 115.0 184.833333333 31.3071699278 1109 72832
-0.0823593 11.474363803863525 69 173.333333333 39.6260296046 200.0 90.0 173.333333333 39.6260296046 1040 73872
0.0173645 11.638144254684448 70 174.0 32.5627599158 200.0 125.0 174.0 32.5627599158 1044 74916
0.0617523 11.821269512176514 71 168.142857143 46.430988948 200.0 65.0 168.142857143 46.430988948 1177 76093
-0.0535049 11.993802309036255 72 143.714285714 36.9196590516 200.0 104.0 143.714285714 36.9196590516 1006 77099
0.15992 12.156002521514893 73 173.0 30.2379452565 200.0 120.0 173.0 30.2379452565 1038 78137
0.0487747 12.340272665023804 74 200.0 0.0 200.0 200.0 200.0 0.0 1200 79337
-0.0502625 12.512109518051147 75 178.333333333 30.776975521 200.0 130.0 178.333333333 30.776975521 1070 80407
0.192245 12.674657821655273 76 177.333333333 23.1060357675 200.0 146.0 177.333333333 23.1060357675 1064 81471
0.125061 12.851359367370605 77 186.0 20.7926268983 200.0 147.0 186.0 20.7926268983 1116 82587
-0.110649 13.03730821609497 78 200.0 0.0 200.0 200.0 200.0 0.0 1200 83787
0.12838 13.214504957199097 79 167.428571429 31.1670941074 200.0 120.0 167.428571429 31.1670941074 1172 84959
-0.151451 13.38013219833374 80 156.714285714 46.222178615 200.0 71.0 156.714285714 46.222178615 1097 86056
0.151161 13.5490083694458 81 161.142857143 26.4598270777 200.0 127.0 161.142857143 26.4598270777 1128 87184
-0.16169 13.709528684616089 82 154.285714286 37.5336583642 200.0 79.0 154.285714286 37.5336583642 1080 88264
0.00814056 13.885880470275879 83 145.625 36.9423114464 200.0 84.0 145.625 36.9423114464 1165 89429
-0.140816 14.045114994049072 84 173.833333333 37.4985184893 200.0 111.0 173.833333333 37.4985184893 1043 90472
-0.0780334 14.216510772705078 85 140.0 45.6919030026 200.0 78.0 140.0 45.6919030026 1120 91592
-0.0188904 14.374228477478027 86 130.875 31.5849548836 175.0 89.0 130.875 31.5849548836 1047 92639
0.0242615 14.546939373016357 87 126.555555556 37.2711121711 200.0 64.0 126.555555556 37.2711121711 1139 93778
0.151283 14.703302145004272 88 143.285714286 37.3619909446 200.0 91.0 143.285714286 37.3619909446 1003 94781
-0.00479889 14.864612579345703 89 133.125 31.2347462772 200.0 100.0 133.125 31.2347462772 1065 95846
0.0864182 15.019819498062134 90 148.285714286 43.2656719276 200.0 91.0 148.285714286 43.2656719276 1038 96884
0.397087 15.189021348953247 91 144.714285714 39.2636301564 200.0 90.0 144.714285714 39.2636301564 1013 97897
0.0472336 15.367772579193115 92 175.166666667 35.3195727922 200.0 119.0 175.166666667 35.3195727922 1051 98948
-0.119873 15.569477558135986 93 166.285714286 39.5138828613 200.0 97.0 166.285714286 39.5138828613 1164 100112
-0.0447845 15.727983474731445 94 152.428571429 27.4999072355 200.0 117.0 152.428571429 27.4999072355 1067 101179
0.130463 15.883777379989624 95 171.5 22.9183332727 200.0 136.0 171.5 22.9183332727 1029 102208
0.0085144 16.06430745124817 96 171.428571429 30.1323610703 200.0 113.0 171.428571429 30.1323610703 1200 103408
-0.11972 16.22447681427002 97 173.0 29.2973263854 200.0 130.0 173.0 29.2973263854 1038 104446
0.136795 16.393552780151367 98 182.166666667 24.6537128148 200.0 131.0 182.166666667 24.6537128148 1093 105539
-0.0336685 16.55085301399231 99 175.833333333 21.1535392363 200.0 141.0 175.833333333 21.1535392363 1055 106594
================================================
FILE: hw2/data/sb_no_rtg_dna_CartPole-v0_24-01-2018_09-00-15/21/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_no_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_no_rtg_dna_CartPole-v0_24-01-2018_09-00-15/21",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : false,
"seed" : 21,
"size" : 32}
================================================
FILE: hw2/data/sb_no_rtg_dna_CartPole-v0_24-01-2018_09-00-15/31/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.144505 0.2521638870239258 0 23.9761904762 12.9807331498 63.0 10.0 23.9761904762 12.9807331498 1007 1007
0.0624466 0.41129064559936523 1 23.8604651163 10.9493153558 56.0 10.0 23.8604651163 10.9493153558 1026 2033
0.00043869 0.5695617198944092 2 24.4047619048 12.9579163592 73.0 11.0 24.4047619048 12.9579163592 1025 3058
0.0165443 0.7176158428192139 3 28.0277777778 14.0366308697 61.0 12.0 28.0277777778 14.0366308697 1009 4067
0.0421333 0.8682734966278076 4 26.6842105263 12.6867217431 62.0 10.0 26.6842105263 12.6867217431 1014 5081
0.00756264 1.018404245376587 5 29.6176470588 20.8989370767 95.0 10.0 29.6176470588 20.8989370767 1007 6088
0.0137215 1.1738612651824951 6 33.3548387097 19.8746854503 97.0 10.0 33.3548387097 19.8746854503 1034 7122
0.0576801 1.318882942199707 7 33.7333333333 14.0592397455 73.0 11.0 33.7333333333 14.0592397455 1012 8134
0.071312 1.470320463180542 8 46.0454545455 30.2075807354 130.0 13.0 46.0454545455 30.2075807354 1013 9147
0.0240631 1.6288890838623047 9 35.0 19.6591647488 116.0 15.0 35.0 19.6591647488 1015 10162
0.0359039 1.7904996871948242 10 43.1666666667 17.9528703988 91.0 17.0 43.1666666667 17.9528703988 1036 11198
0.0920067 1.934124231338501 11 50.35 35.4884136022 134.0 17.0 50.35 35.4884136022 1007 12205
0.0759811 2.090627670288086 12 42.25 29.2022402109 134.0 13.0 42.25 29.2022402109 1014 13219
0.019989 2.2420554161071777 13 48.1363636364 22.4728026624 97.0 15.0 48.1363636364 22.4728026624 1059 14278
0.00758362 2.403862953186035 14 64.0588235294 39.8267875981 174.0 21.0 64.0588235294 39.8267875981 1089 15367
0.0340919 2.557589530944824 15 52.55 27.9078394004 124.0 18.0 52.55 27.9078394004 1051 16418
-0.0420609 2.720651865005493 16 51.0952380952 25.599302003 118.0 12.0 51.0952380952 25.599302003 1073 17491
0.0309029 2.8725504875183105 17 63.6875 27.723452955 124.0 25.0 63.6875 27.723452955 1019 18510
0.0385361 3.0242555141448975 18 53.0526315789 24.0929639963 94.0 22.0 53.0526315789 24.0929639963 1008 19518
0.123775 3.1752729415893555 19 73.2857142857 42.5901205369 180.0 22.0 73.2857142857 42.5901205369 1026 20544
-0.0174332 3.3432321548461914 20 57.8333333333 23.164268461 115.0 19.0 57.8333333333 23.164268461 1041 21585
0.00173187 3.4917185306549072 21 63.0625 31.9755155353 152.0 20.0 63.0625 31.9755155353 1009 22594
-0.0250473 3.6495962142944336 22 57.3333333333 25.6493448043 128.0 13.0 57.3333333333 25.6493448043 1032 23626
0.0377617 3.800271987915039 23 73.5714285714 32.5614019655 135.0 34.0 73.5714285714 32.5614019655 1030 24656
0.0517387 3.9629733562469482 24 69.8 40.1965172621 157.0 26.0 69.8 40.1965172621 1047 25703
0.047451 4.111782073974609 25 78.0 33.9705755029 158.0 29.0 78.0 33.9705755029 1014 26717
0.218624 4.2690887451171875 26 78.3846153846 37.0540944723 178.0 27.0 78.3846153846 37.0540944723 1019 27736
-0.0270004 4.426061391830444 27 66.4375 33.4289708748 134.0 16.0 66.4375 33.4289708748 1063 28799
0.0207291 4.57614278793335 28 77.3076923077 29.1320194325 138.0 39.0 77.3076923077 29.1320194325 1005 29804
0.0141563 4.727544784545898 29 71.7142857143 30.1222000985 130.0 30.0 71.7142857143 30.1222000985 1004 30808
0.0134125 4.8886353969573975 30 79.6153846154 36.0907796909 167.0 28.0 79.6153846154 36.0907796909 1035 31843
0.0094223 5.0403831005096436 31 81.8461538462 49.9351058164 200.0 27.0 81.8461538462 49.9351058164 1064 32907
0.0825043 5.200412273406982 32 117.0 33.7111916794 163.0 49.0 117.0 33.7111916794 1053 33960
0.0787354 5.376931667327881 33 102.454545455 41.2230377699 185.0 51.0 102.454545455 41.2230377699 1127 35087
0.021019 5.544047594070435 34 124.111111111 52.4032323949 199.0 52.0 124.111111111 52.4032323949 1117 36204
0.0688019 5.717339038848877 35 99.5833333333 58.8422443676 200.0 34.0 99.5833333333 58.8422443676 1195 37399
0.113373 5.869815826416016 36 114.555555556 43.764803492 160.0 26.0 114.555555556 43.764803492 1031 38430
0.092865 6.033387899398804 37 121.555555556 45.8478428212 197.0 42.0 121.555555556 45.8478428212 1094 39524
0.099411 6.2116429805755615 38 125.555555556 69.5638972634 200.0 26.0 125.555555556 69.5638972634 1130 40654
0.187187 6.377261161804199 39 139.625 61.89494628 200.0 48.0 139.625 61.89494628 1117 41771
-0.0534439 6.5344085693359375 40 127.75 48.0149716234 200.0 50.0 127.75 48.0149716234 1022 42793
0.116745 6.692571401596069 41 151.428571429 42.8080671398 200.0 57.0 151.428571429 42.8080671398 1060 43853
0.171021 6.862926959991455 42 132.375 47.536663482 200.0 65.0 132.375 47.536663482 1059 44912
0.191711 7.024964332580566 43 150.285714286 50.4231077574 200.0 66.0 150.285714286 50.4231077574 1052 45964
0.023262 7.1877477169036865 44 126.375 58.6875998402 200.0 22.0 126.375 58.6875998402 1011 46975
-0.0498466 7.349262714385986 45 81.0769230769 43.3242897558 200.0 37.0 81.0769230769 43.3242897558 1054 48029
0.0224304 7.520627498626709 46 109.7 61.1 200.0 23.0 109.7 61.1 1097 49126
0.0703354 7.680565595626831 47 134.5 55.0318089835 200.0 54.0 134.5 55.0318089835 1076 50202
0.0522766 7.852791786193848 48 129.0 60.0906722286 200.0 43.0 129.0 60.0906722286 1161 51363
0.0723877 8.024983167648315 49 167.428571429 25.7230143915 200.0 118.0 167.428571429 25.7230143915 1172 52535
0.0977173 8.1889328956604 50 128.25 70.9379129944 200.0 51.0 128.25 70.9379129944 1026 53561
-0.0116882 8.347144842147827 51 98.7272727273 43.6433706495 200.0 27.0 98.7272727273 43.6433706495 1086 54647
0.00474548 8.518024444580078 52 118.888888889 53.342591789 200.0 42.0 118.888888889 53.342591789 1070 55717
0.392014 8.672571897506714 53 146.0 51.1580185029 200.0 49.0 146.0 51.1580185029 1022 56739
0.246475 8.840925931930542 54 140.25 51.0018382022 200.0 49.0 140.25 51.0018382022 1122 57861
-0.0916824 8.994431495666504 55 175.833333333 36.7759734368 200.0 99.0 175.833333333 36.7759734368 1055 58916
0.195381 9.159648180007935 56 119.0 41.1906138176 200.0 39.0 119.0 41.1906138176 1071 59987
0.0533981 9.31280255317688 57 117.777777778 65.5384158385 200.0 24.0 117.777777778 65.5384158385 1060 61047
-0.0150833 9.473615884780884 58 152.428571429 42.1522991844 200.0 98.0 152.428571429 42.1522991844 1067 62114
0.151924 9.638584852218628 59 180.833333333 19.3512847693 200.0 159.0 180.833333333 19.3512847693 1085 63199
-0.0231781 9.80607533454895 60 159.714285714 54.1709312816 200.0 44.0 159.714285714 54.1709312816 1118 64317
0.00574493 9.986761331558228 61 169.0 52.2165819311 200.0 46.0 169.0 52.2165819311 1183 65500
0.111641 10.146838426589966 62 153.0 50.4210840253 200.0 61.0 153.0 50.4210840253 1071 66571
0.0608597 10.301918506622314 63 175.333333333 17.904065336 200.0 152.0 175.333333333 17.904065336 1052 67623
-0.0611725 10.45662784576416 64 172.5 32.6585874363 200.0 120.0 172.5 32.6585874363 1035 68658
-0.00627136 10.614657878875732 65 177.333333333 19.0583898119 200.0 146.0 177.333333333 19.0583898119 1064 69722
0.0120316 10.791270017623901 66 188.5 10.1283430695 200.0 174.0 188.5 10.1283430695 1131 70853
0.0520706 10.95199728012085 67 182.0 30.1385688667 200.0 116.0 182.0 30.1385688667 1092 71945
0.326073 11.111455917358398 68 178.666666667 28.3294114933 200.0 120.0 178.666666667 28.3294114933 1072 73017
0.0831833 11.285653352737427 69 190.333333333 14.4529889258 200.0 161.0 190.333333333 14.4529889258 1142 74159
0.108009 11.45212173461914 70 157.0 39.3591521395 200.0 109.0 157.0 39.3591521395 1099 75258
-0.0659943 11.618270635604858 71 184.666666667 18.5801566792 200.0 145.0 184.666666667 18.5801566792 1108 76366
0.0102844 11.799455404281616 72 164.571428571 55.5848312887 200.0 43.0 164.571428571 55.5848312887 1152 77518
-0.0520782 11.983135223388672 73 169.285714286 30.4898778788 200.0 123.0 169.285714286 30.4898778788 1185 78703
-0.0490799 12.13831615447998 74 143.714285714 26.4829556276 200.0 120.0 143.714285714 26.4829556276 1006 79709
0.0246811 12.318784952163696 75 159.142857143 31.9393558009 200.0 116.0 159.142857143 31.9393558009 1114 80823
-0.0184402 12.48039722442627 76 147.857142857 41.346717166 200.0 66.0 147.857142857 41.346717166 1035 81858
0.0798798 12.65744423866272 77 169.142857143 36.5920700677 200.0 119.0 169.142857143 36.5920700677 1184 83042
0.00389099 12.814390659332275 78 132.5 37.1012129182 196.0 83.0 132.5 37.1012129182 1060 84102
0.0345078 12.980849027633667 79 158.714285714 37.8557951243 200.0 94.0 158.714285714 37.8557951243 1111 85213
0.106895 13.140302181243896 80 146.857142857 32.6646535545 200.0 97.0 146.857142857 32.6646535545 1028 86241
-0.0126877 13.313060760498047 81 160.571428571 29.3396715478 200.0 120.0 160.571428571 29.3396715478 1124 87365
0.170555 13.48175573348999 82 137.25 28.3405628032 200.0 108.0 137.25 28.3405628032 1098 88463
0.170135 13.647441387176514 83 138.75 27.8107443266 175.0 94.0 138.75 27.8107443266 1110 89573
-0.108597 13.812865018844604 84 135.375 21.4005695018 170.0 95.0 135.375 21.4005695018 1083 90656
-0.00518036 13.968695163726807 85 135.25 15.7539677542 157.0 106.0 135.25 15.7539677542 1082 91738
0.0238571 14.121616840362549 86 148.285714286 38.7066413117 200.0 84.0 148.285714286 38.7066413117 1038 92776
0.0117493 14.286812782287598 87 153.428571429 44.3810034743 200.0 100.0 153.428571429 44.3810034743 1074 93850
0.0768661 14.446006059646606 88 151.714285714 50.1190419636 200.0 58.0 151.714285714 50.1190419636 1062 94912
0.063736 14.598016500473022 89 173.0 28.5540423291 200.0 115.0 173.0 28.5540423291 1038 95950
-0.0162277 14.756766557693481 90 134.375 30.7121209785 200.0 89.0 134.375 30.7121209785 1075 97025
0.045372 14.919553756713867 91 179.833333333 29.1571413017 200.0 129.0 179.833333333 29.1571413017 1079 98104
0.0592194 15.086693048477173 92 159.571428571 24.6278422166 200.0 124.0 159.571428571 24.6278422166 1117 99221
0.0805206 15.25587010383606 93 142.75 29.7226765282 200.0 105.0 142.75 29.7226765282 1142 100363
0.121323 15.412774801254272 94 173.0 31.2143129563 200.0 113.0 173.0 31.2143129563 1038 101401
0.236595 15.569407224655151 95 171.333333333 47.7586525029 200.0 68.0 171.333333333 47.7586525029 1028 102429
0.0257339 15.735109567642212 96 180.666666667 27.6385399196 200.0 135.0 180.666666667 27.6385399196 1084 103513
0.0916519 15.906312942504883 97 186.166666667 30.9322736887 200.0 117.0 186.166666667 30.9322736887 1117 104630
0.0183792 16.086841821670532 98 165.571428571 40.4151921324 200.0 80.0 165.571428571 40.4151921324 1159 105789
-0.0629044 16.265729665756226 99 193.833333333 13.7890858612 200.0 163.0 193.833333333 13.7890858612 1163 106952
================================================
FILE: hw2/data/sb_no_rtg_dna_CartPole-v0_24-01-2018_09-00-15/31/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_no_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_no_rtg_dna_CartPole-v0_24-01-2018_09-00-15/31",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : false,
"seed" : 31,
"size" : 32}
================================================
FILE: hw2/data/sb_no_rtg_dna_CartPole-v0_24-01-2018_09-00-15/41/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.125916 0.2505974769592285 0 25.05 11.1016890607 60.0 9.0 25.05 11.1016890607 1002 1002
0.111948 0.4135293960571289 1 26.6578947368 21.2853746623 122.0 9.0 26.6578947368 21.2853746623 1013 2015
0.0877571 0.5624969005584717 2 30.696969697 21.0604970566 86.0 10.0 30.696969697 21.0604970566 1013 3028
0.0478535 0.724611759185791 3 29.2777777778 17.4413479205 88.0 11.0 29.2777777778 17.4413479205 1054 4082
0.0783234 0.8706352710723877 4 28.6285714286 15.5913633863 79.0 13.0 28.6285714286 15.5913633863 1002 5084
0.132584 1.0197343826293945 5 37.2962962963 18.5568492193 94.0 14.0 37.2962962963 18.5568492193 1007 6091
-0.0312691 1.1679770946502686 6 35.8928571429 22.7255980366 127.0 11.0 35.8928571429 22.7255980366 1005 7096
0.052742 1.3246865272521973 7 40.12 22.7654475027 80.0 14.0 40.12 22.7654475027 1003 8099
0.00450897 1.4705824851989746 8 42.2083333333 22.3513220464 99.0 18.0 42.2083333333 22.3513220464 1013 9112
0.0656376 1.6298649311065674 9 39.9230769231 19.5427009332 89.0 11.0 39.9230769231 19.5427009332 1038 10150
0.00940323 1.782789707183838 10 44.2608695652 24.3510867382 98.0 12.0 44.2608695652 24.3510867382 1018 11168
0.0812111 1.9299135208129883 11 47.6666666667 20.9087207446 90.0 17.0 47.6666666667 20.9087207446 1001 12169
0.0373497 2.082848310470581 12 45.0 22.2847188821 100.0 15.0 45.0 22.2847188821 1035 13204
-0.0114822 2.2387964725494385 13 48.1428571429 23.6427492445 102.0 18.0 48.1428571429 23.6427492445 1011 14215
0.033905 2.387507677078247 14 45.7272727273 16.175688318 69.0 19.0 45.7272727273 16.175688318 1006 15221
0.0234871 2.5513038635253906 15 54.3 30.5681206488 150.0 26.0 54.3 30.5681206488 1086 16307
0.0283051 2.6975746154785156 16 56.5 19.7659921189 99.0 22.0 56.5 19.7659921189 1017 17324
0.000244141 2.8440873622894287 17 59.3529411765 23.807910639 104.0 34.0 59.3529411765 23.807910639 1009 18333
0.0140457 2.999793529510498 18 62.9375 26.1353896805 108.0 22.0 62.9375 26.1353896805 1007 19340
0.0527191 3.157583475112915 19 58.0555555556 18.2101077617 100.0 34.0 58.0555555556 18.2101077617 1045 20385
0.0731888 3.3134326934814453 20 58.1111111111 18.1226956815 100.0 20.0 58.1111111111 18.1226956815 1046 21431
0.0965652 3.4730634689331055 21 64.0625 37.1407268877 161.0 11.0 64.0625 37.1407268877 1025 22456
0.106953 3.620211601257324 22 56.0555555556 20.600626264 98.0 21.0 56.0555555556 20.600626264 1009 23465
0.0470581 3.781092882156372 23 69.6 27.3856410064 119.0 19.0 69.6 27.3856410064 1044 24509
0.0901299 3.950429916381836 24 73.6 37.0077469367 164.0 28.0 73.6 37.0077469367 1104 25613
0.109577 4.115303993225098 25 71.0 29.522872489 135.0 26.0 71.0 29.522872489 1065 26678
0.185406 4.272083520889282 26 71.9285714286 25.4851897768 112.0 22.0 71.9285714286 25.4851897768 1007 27685
0.0847168 4.4271979331970215 27 105.6 45.2375949847 200.0 49.0 105.6 45.2375949847 1056 28741
-0.0110512 4.580373764038086 28 67.8666666667 24.2510939043 111.0 17.0 67.8666666667 24.2510939043 1018 29759
-0.00197601 4.736642837524414 29 93.6363636364 33.9686291833 165.0 49.0 93.6363636364 33.9686291833 1030 30789
-0.0214996 4.894640684127808 30 86.4166666667 22.1263731526 120.0 45.0 86.4166666667 22.1263731526 1037 31826
0.00163269 5.054884672164917 31 96.0 45.1643463566 172.0 43.0 96.0 45.1643463566 1056 32882
0.0193176 5.217885971069336 32 86.3846153846 45.6871273935 177.0 29.0 86.3846153846 45.6871273935 1123 34005
0.0336075 5.405492782592773 33 108.818181818 44.0388633777 200.0 45.0 108.818181818 44.0388633777 1197 35202
0.0355301 5.568437337875366 34 114.222222222 41.5017476949 200.0 68.0 114.222222222 41.5017476949 1028 36230
0.120415 5.736985683441162 35 110.3 32.1715713014 147.0 49.0 110.3 32.1715713014 1103 37333
-0.017601 5.912489652633667 36 112.8 37.9362623357 200.0 78.0 112.8 37.9362623357 1128 38461
0.00502777 6.075066328048706 37 91.3333333333 44.9339020736 182.0 28.0 91.3333333333 44.9339020736 1096 39557
0.00676727 6.2297351360321045 38 102.6 13.0399386502 122.0 75.0 102.6 13.0399386502 1026 40583
0.0233459 6.397600412368774 39 98.5454545455 40.3470481884 160.0 25.0 98.5454545455 40.3470481884 1084 41667
0.0567932 6.571632623672485 40 128.888888889 46.7153185546 200.0 74.0 128.888888889 46.7153185546 1160 42827
0.118164 6.736852407455444 41 134.875 48.5011275642 200.0 39.0 134.875 48.5011275642 1079 43906
0.127281 6.899658203125 42 131.0 40.3422855079 200.0 61.0 131.0 40.3422855079 1048 44954
0.0315094 7.068284511566162 43 123.777777778 41.9491167376 196.0 56.0 123.777777778 41.9491167376 1114 46068
0.0341492 7.241614580154419 44 165.285714286 23.1992258843 200.0 125.0 165.285714286 23.1992258843 1157 47225
0.0812683 7.4060821533203125 45 130.375 46.6929799327 190.0 48.0 130.375 46.6929799327 1043 48268
-0.0473404 7.580517530441284 46 144.75 29.7058495923 188.0 101.0 144.75 29.7058495923 1158 49426
0.399933 7.763719081878662 47 169.285714286 37.7461986193 200.0 100.0 169.285714286 37.7461986193 1185 50611
-0.114853 7.918586015701294 48 145.857142857 18.8333182831 168.0 106.0 145.857142857 18.8333182831 1021 51632
0.0239334 8.092004537582397 49 140.125 51.8493912693 200.0 32.0 140.125 51.8493912693 1121 52753
0.224663 8.265684366226196 50 144.375 48.1402573217 200.0 61.0 144.375 48.1402573217 1155 53908
-0.131866 8.44176721572876 51 164.142857143 21.0606509968 200.0 140.0 164.142857143 21.0606509968 1149 55057
0.0345459 8.60806918144226 52 181.666666667 25.9272486435 200.0 145.0 181.666666667 25.9272486435 1090 56147
-0.068779 8.76414680480957 53 167.166666667 27.278909232 200.0 133.0 167.166666667 27.278909232 1003 57150
-0.0260391 8.93677568435669 54 183.5 23.1210582226 200.0 138.0 183.5 23.1210582226 1101 58251
-0.0272217 9.111738920211792 55 191.5 9.65660395791 200.0 174.0 191.5 9.65660395791 1149 59400
0.138466 9.285842657089233 56 193.0 10.1653004547 200.0 175.0 193.0 10.1653004547 1158 60558
0.08255 9.44937014579773 57 175.166666667 30.6997104583 200.0 117.0 175.166666667 30.6997104583 1051 61609
0.0735321 9.62963342666626 58 167.142857143 51.5597533282 200.0 51.0 167.142857143 51.5597533282 1170 62779
-0.0698395 9.8151113986969 59 200.0 0.0 200.0 200.0 200.0 0.0 1200 63979
0.130074 10.003267765045166 60 200.0 0.0 200.0 200.0 200.0 0.0 1200 65179
-0.0414124 10.182382822036743 61 193.0 10.9239797388 200.0 171.0 193.0 10.9239797388 1158 66337
0.00291443 10.358822107315063 62 185.0 30.5177543953 200.0 117.0 185.0 30.5177543953 1110 67447
0.0998306 10.540348291397095 63 200.0 0.0 200.0 200.0 200.0 0.0 1200 68647
0.00196075 10.707365989685059 64 183.333333333 28.3881822047 200.0 121.0 183.333333333 28.3881822047 1100 69747
0.268822 10.885679960250854 65 194.5 8.40138877409 200.0 178.0 194.5 8.40138877409 1167 70914
0.212479 11.046054124832153 66 169.0 34.8711915483 200.0 106.0 169.0 34.8711915483 1014 71928
-0.104195 11.218170881271362 67 187.0 15.3622914957 200.0 158.0 187.0 15.3622914957 1122 73050
0.035759 11.395460605621338 68 194.0 13.416407865 200.0 164.0 194.0 13.416407865 1164 74214
-0.00205231 11.569234609603882 69 192.666666667 16.397831835 200.0 156.0 192.666666667 16.397831835 1156 75370
-0.0817337 11.745209217071533 70 188.833333333 24.9694257487 200.0 133.0 188.833333333 24.9694257487 1133 76503
0.0969543 11.93280029296875 71 189.833333333 22.7333577712 200.0 139.0 189.833333333 22.7333577712 1139 77642
0.178162 12.108734607696533 72 200.0 0.0 200.0 200.0 200.0 0.0 1200 78842
-0.0113525 12.275990962982178 73 180.5 43.6033255612 200.0 83.0 180.5 43.6033255612 1083 79925
-0.00179291 12.464891195297241 74 200.0 0.0 200.0 200.0 200.0 0.0 1200 81125
0.102974 12.638292789459229 75 192.333333333 17.1431878275 200.0 154.0 192.333333333 17.1431878275 1154 82279
0.0342102 12.822158575057983 76 200.0 0.0 200.0 200.0 200.0 0.0 1200 83479
-0.029953 12.997734308242798 77 189.166666667 16.6974715318 200.0 156.0 189.166666667 16.6974715318 1135 84614
0.193146 13.17650294303894 78 191.666666667 18.6338998125 200.0 150.0 191.666666667 18.6338998125 1150 85764
0.236183 13.351174354553223 79 188.666666667 25.342103745 200.0 132.0 188.666666667 25.342103745 1132 86896
-0.03862 13.521106481552124 80 184.166666667 35.4044096437 200.0 105.0 184.166666667 35.4044096437 1105 88001
0.0165558 13.704911708831787 81 200.0 0.0 200.0 200.0 200.0 0.0 1200 89201
0.0387726 13.891655206680298 82 200.0 0.0 200.0 200.0 200.0 0.0 1200 90401
-0.0175858 14.080732822418213 83 196.5 5.88075958813 200.0 184.0 196.5 5.88075958813 1179 91580
-0.0390091 14.270209312438965 84 200.0 0.0 200.0 200.0 200.0 0.0 1200 92780
0.0600128 14.457867622375488 85 200.0 0.0 200.0 200.0 200.0 0.0 1200 93980
0.298447 14.641980409622192 86 193.833333333 13.7890858612 200.0 163.0 193.833333333 13.7890858612 1163 95143
-0.057663 14.827941656112671 87 196.666666667 7.453559925 200.0 180.0 196.666666667 7.453559925 1180 96323
-0.082016 14.993478775024414 88 182.833333333 24.2790490387 200.0 148.0 182.833333333 24.2790490387 1097 97420
-0.0603867 15.1760413646698 89 198.333333333 2.62466929134 200.0 193.0 198.333333333 2.62466929134 1190 98610
0.0923996 15.361606121063232 90 200.0 0.0 200.0 200.0 200.0 0.0 1200 99810
-0.0546036 15.535207509994507 91 189.333333333 19.3534378227 200.0 147.0 189.333333333 19.3534378227 1136 100946
0.0926514 15.70313549041748 92 179.666666667 20.4830553276 200.0 143.0 179.666666667 20.4830553276 1078 102024
0.0266571 15.868555307388306 93 180.166666667 17.4682251213 200.0 150.0 180.166666667 17.4682251213 1081 103105
0.0873642 16.04865050315857 94 193.666666667 14.1617638575 200.0 162.0 193.666666667 14.1617638575 1162 104267
0.0157471 16.216988563537598 95 176.833333333 23.4621444506 200.0 149.0 176.833333333 23.4621444506 1061 105328
0.163277 16.41885805130005 96 200.0 0.0 200.0 200.0 200.0 0.0 1200 106528
0.219139 16.577938318252563 97 170.0 41.2956817759 200.0 104.0 170.0 41.2956817759 1020 107548
-0.020668 16.751195430755615 98 193.166666667 15.2797978462 200.0 159.0 193.166666667 15.2797978462 1159 108707
0.041153 16.925679445266724 99 185.833333333 31.6776296812 200.0 115.0 185.833333333 31.6776296812 1115 109822
================================================
FILE: hw2/data/sb_no_rtg_dna_CartPole-v0_24-01-2018_09-00-15/41/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_no_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_no_rtg_dna_CartPole-v0_24-01-2018_09-00-15/41",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : false,
"seed" : 41,
"size" : 32}
================================================
FILE: hw2/data/sb_rtg_dna_CartPole-v0_24-01-2018_09-04-19/1/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0517235 0.2473735809326172 0 22.5434782609 11.7004394599 59.0 9.0 22.5434782609 11.7004394599 1037 1037
0.0505962 0.4076406955718994 1 25.512195122 15.2317414907 75.0 10.0 25.512195122 15.2317414907 1046 2083
0.0614481 0.5628316402435303 2 29.6764705882 16.4544300994 74.0 9.0 29.6764705882 16.4544300994 1009 3092
0.036849 0.709326982498169 3 32.6129032258 16.0154711881 77.0 12.0 32.6129032258 16.0154711881 1011 4103
0.0528259 0.8591880798339844 4 32.3125 16.3848968184 73.0 11.0 32.3125 16.3848968184 1034 5137
0.0605001 1.0083670616149902 5 36.25 15.488763208 67.0 12.0 36.25 15.488763208 1015 6152
0.0430164 1.1580829620361328 6 42.1666666667 24.5944889943 123.0 10.0 42.1666666667 24.5944889943 1012 7164
0.0366039 1.3041014671325684 7 38.1851851852 14.6110993757 73.0 15.0 38.1851851852 14.6110993757 1031 8195
0.0697365 1.4600348472595215 8 39.9230769231 22.4772073904 94.0 14.0 39.9230769231 22.4772073904 1038 9233
0.0649738 1.6097497940063477 9 45.5 28.6257195225 111.0 11.0 45.5 28.6257195225 1001 10234
0.0478954 1.763127088546753 10 54.1052631579 25.6040595812 97.0 17.0 54.1052631579 25.6040595812 1028 11262
0.0592117 1.9278223514556885 11 47.9565217391 26.3347650221 131.0 21.0 47.9565217391 26.3347650221 1103 12365
0.0307026 2.0769340991973877 12 47.7619047619 18.2415140399 91.0 19.0 47.7619047619 18.2415140399 1003 13368
0.0122509 2.2294259071350098 13 51.8 20.7740222393 104.0 19.0 51.8 20.7740222393 1036 14404
0.0115509 2.4055566787719727 14 47.2272727273 23.7083257685 133.0 16.0 47.2272727273 23.7083257685 1039 15443
0.0195656 2.5540592670440674 15 53.2105263158 31.3042437805 121.0 22.0 53.2105263158 31.3042437805 1011 16454
0.0370426 2.7169888019561768 16 55.9473684211 12.6052356884 75.0 27.0 55.9473684211 12.6052356884 1063 17517
0.0270367 2.8610479831695557 17 56.2222222222 22.0316831343 110.0 29.0 56.2222222222 22.0316831343 1012 18529
0.015955 3.009582281112671 18 50.3 19.8547223602 90.0 19.0 50.3 19.8547223602 1006 19535
0.0273666 3.156733989715576 19 60.0588235294 24.4021951477 112.0 23.0 60.0588235294 24.4021951477 1021 20556
0.00492477 3.316955804824829 20 49.3333333333 22.0547658889 131.0 26.0 49.3333333333 22.0547658889 1036 21592
0.0321198 3.4606480598449707 21 53.2105263158 18.6366332722 94.0 23.0 53.2105263158 18.6366332722 1011 22603
0.0477161 3.6128222942352295 22 72.0 33.7448408755 150.0 24.0 72.0 33.7448408755 1008 23611
0.0411072 3.7623867988586426 23 72.0 31.4051861049 131.0 26.0 72.0 31.4051861049 1008 24619
0.0298729 3.912607192993164 24 52.8947368421 17.9616396416 91.0 26.0 52.8947368421 17.9616396416 1005 25624
-0.00857353 4.064990997314453 25 69.1333333333 26.3207564903 141.0 38.0 69.1333333333 26.3207564903 1037 26661
0.0512733 4.214077949523926 26 67.3333333333 31.5545383248 143.0 37.0 67.3333333333 31.5545383248 1010 27671
0.017643 4.372330188751221 27 60.0588235294 25.8490427363 124.0 26.0 60.0588235294 25.8490427363 1021 28692
0.0227928 4.524590015411377 28 67.8 26.2022899763 114.0 35.0 67.8 26.2022899763 1017 29709
0.0389977 4.673584222793579 29 59.8235294118 23.1243067791 118.0 36.0 59.8235294118 23.1243067791 1017 30726
0.0696735 4.827871322631836 30 77.5384615385 33.906240371 134.0 24.0 77.5384615385 33.906240371 1008 31734
0.0551453 4.985939025878906 31 76.5714285714 41.1490570725 165.0 19.0 76.5714285714 41.1490570725 1072 32806
0.0870419 5.138609886169434 32 79.1538461538 30.1658139516 137.0 46.0 79.1538461538 30.1658139516 1029 33835
0.0150585 5.298211097717285 33 88.4166666667 40.1070615838 167.0 39.0 88.4166666667 40.1070615838 1061 34896
0.121536 5.463602542877197 34 91.0 40.1974294369 170.0 36.0 91.0 40.1974294369 1092 35988
0.0373764 5.6167333126068115 35 104.1 50.3735049406 200.0 33.0 104.1 50.3735049406 1041 37029
0.117962 5.789015054702759 36 91.1666666667 49.5897054729 177.0 22.0 91.1666666667 49.5897054729 1094 38123
0.178432 5.939866542816162 37 125.625 52.9290503882 200.0 48.0 125.625 52.9290503882 1005 39128
0.00406647 6.0919694900512695 38 126.0 41.0822346033 198.0 45.0 126.0 41.0822346033 1008 40136
0.0680885 6.256884336471558 39 136.875 33.1829681463 200.0 101.0 136.875 33.1829681463 1095 41231
-0.0465012 6.428496360778809 40 105.363636364 53.1161210373 175.0 27.0 105.363636364 53.1161210373 1159 42390
0.0179405 6.578087091445923 41 129.875 49.2047698399 200.0 41.0 129.875 49.2047698399 1039 43429
0.0350342 6.749640226364136 42 137.875 40.290934154 200.0 87.0 137.875 40.290934154 1103 44532
-0.0271378 6.900329113006592 43 130.125 35.5015404595 200.0 67.0 130.125 35.5015404595 1041 45573
0.08778 7.061618804931641 44 153.285714286 49.4388923989 200.0 82.0 153.285714286 49.4388923989 1073 46646
0.0374947 7.214562654495239 45 126.125 51.1650210105 200.0 30.0 126.125 51.1650210105 1009 47655
0.0615578 7.386049270629883 46 124.333333333 33.2899717967 173.0 42.0 124.333333333 33.2899717967 1119 48774
0.0493355 7.556005001068115 47 162.571428571 32.0573465743 200.0 104.0 162.571428571 32.0573465743 1138 49912
0.0133972 7.725847482681274 48 145.375 40.1464117326 200.0 105.0 145.375 40.1464117326 1163 51075
0.0363884 7.884342193603516 49 117.555555556 36.0373605863 181.0 60.0 117.555555556 36.0373605863 1058 52133
-0.00232697 8.037986755371094 50 126.75 31.3199217751 176.0 74.0 126.75 31.3199217751 1014 53147
-0.00113297 8.195262432098389 51 144.714285714 49.8245902735 200.0 75.0 144.714285714 49.8245902735 1013 54160
0.068634 8.353180885314941 52 177.166666667 23.6390684156 200.0 143.0 177.166666667 23.6390684156 1063 55223
0.0652733 8.515519380569458 53 156.428571429 29.9182559789 200.0 124.0 156.428571429 29.9182559789 1095 56318
0.10899 8.682511806488037 54 183.833333333 36.1497656362 200.0 103.0 183.833333333 36.1497656362 1103 57421
0.0405807 8.83873701095581 55 177.5 27.396775966 200.0 136.0 177.5 27.396775966 1065 58486
0.0169258 8.993125915527344 56 149.285714286 47.3519174019 200.0 73.0 149.285714286 47.3519174019 1045 59531
0.0386963 9.160706520080566 57 164.285714286 39.2090160394 200.0 97.0 164.285714286 39.2090160394 1150 60681
0.0594368 9.335328817367554 58 162.0 33.7934904974 200.0 123.0 162.0 33.7934904974 1134 61815
0.148304 9.512524127960205 59 190.333333333 21.6153237825 200.0 142.0 190.333333333 21.6153237825 1142 62957
-0.000232697 9.681550025939941 60 163.285714286 33.67370439 200.0 117.0 163.285714286 33.67370439 1143 64100
-0.0312538 9.842471361160278 61 178.166666667 28.9275915962 200.0 120.0 178.166666667 28.9275915962 1069 65169
-0.0246544 10.025955200195312 62 200.0 0.0 200.0 200.0 200.0 0.0 1200 66369
0.119602 10.194443941116333 63 190.333333333 21.6153237825 200.0 142.0 190.333333333 21.6153237825 1142 67511
-0.0183067 10.371129751205444 64 190.0 12.503332889 200.0 165.0 190.0 12.503332889 1140 68651
0.0982475 10.553912162780762 65 200.0 0.0 200.0 200.0 200.0 0.0 1200 69851
0.00246811 10.740089654922485 66 200.0 0.0 200.0 200.0 200.0 0.0 1200 71051
-0.0554581 10.910332679748535 67 189.5 23.4787137637 200.0 137.0 189.5 23.4787137637 1137 72188
0.0968895 11.095072031021118 68 194.333333333 12.6710518725 200.0 166.0 194.333333333 12.6710518725 1166 73354
-0.00883865 11.245881080627441 69 170.333333333 41.9907397199 200.0 108.0 170.333333333 41.9907397199 1022 74376
0.0580139 11.430721044540405 70 200.0 0.0 200.0 200.0 200.0 0.0 1200 75576
0.000713348 11.593410968780518 71 185.5 32.4229856737 200.0 113.0 185.5 32.4229856737 1113 76689
-0.026371 11.76856255531311 72 198.166666667 4.09945795875 200.0 189.0 198.166666667 4.09945795875 1189 77878
0.0336037 11.937759399414062 73 188.0 26.83281573 200.0 128.0 188.0 26.83281573 1128 79006
-0.0163383 12.118113279342651 74 200.0 0.0 200.0 200.0 200.0 0.0 1200 80206
0.0087204 12.295494079589844 75 200.0 0.0 200.0 200.0 200.0 0.0 1200 81406
0.0401955 12.472760677337646 76 200.0 0.0 200.0 200.0 200.0 0.0 1200 82606
0.0517426 12.654761791229248 77 200.0 0.0 200.0 200.0 200.0 0.0 1200 83806
0.017952 12.836133241653442 78 200.0 0.0 200.0 200.0 200.0 0.0 1200 85006
0.0389977 13.015106678009033 79 200.0 0.0 200.0 200.0 200.0 0.0 1200 86206
-0.00548553 13.199974536895752 80 200.0 0.0 200.0 200.0 200.0 0.0 1200 87406
0.0997162 13.373096466064453 81 200.0 0.0 200.0 200.0 200.0 0.0 1200 88606
0.0158539 13.55326795578003 82 200.0 0.0 200.0 200.0 200.0 0.0 1200 89806
0.0102043 13.734444379806519 83 200.0 0.0 200.0 200.0 200.0 0.0 1200 91006
0.0159378 13.915801525115967 84 200.0 0.0 200.0 200.0 200.0 0.0 1200 92206
0.0170479 14.089951276779175 85 194.166666667 13.0437298687 200.0 165.0 194.166666667 13.0437298687 1165 93371
0.017807 14.271910190582275 86 200.0 0.0 200.0 200.0 200.0 0.0 1200 94571
-0.0176735 14.461371660232544 87 200.0 0.0 200.0 200.0 200.0 0.0 1200 95771
0.00418472 14.643863201141357 88 200.0 0.0 200.0 200.0 200.0 0.0 1200 96971
0.00924301 14.823664903640747 89 200.0 0.0 200.0 200.0 200.0 0.0 1200 98171
0.0527191 15.011042833328247 90 200.0 0.0 200.0 200.0 200.0 0.0 1200 99371
0.0106316 15.186368942260742 91 200.0 0.0 200.0 200.0 200.0 0.0 1200 100571
0.123951 15.370258331298828 92 200.0 0.0 200.0 200.0 200.0 0.0 1200 101771
0.0535965 15.552249908447266 93 196.666666667 7.453559925 200.0 180.0 196.666666667 7.453559925 1180 102951
0.0139694 15.73758578300476 94 200.0 0.0 200.0 200.0 200.0 0.0 1200 104151
0.0449181 15.918290615081787 95 200.0 0.0 200.0 200.0 200.0 0.0 1200 105351
-0.0287437 16.10455822944641 96 198.333333333 3.7267799625 200.0 190.0 198.333333333 3.7267799625 1190 106541
-0.0289497 16.284013748168945 97 200.0 0.0 200.0 200.0 200.0 0.0 1200 107741
0.0246353 16.462838172912598 98 200.0 0.0 200.0 200.0 200.0 0.0 1200 108941
0.0118675 16.640867710113525 99 198.5 3.35410196625 200.0 191.0 198.5 3.35410196625 1191 110132
================================================
FILE: hw2/data/sb_rtg_dna_CartPole-v0_24-01-2018_09-04-19/1/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_rtg_dna_CartPole-v0_24-01-2018_09-04-19/1",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : true,
"seed" : 1,
"size" : 32}
================================================
FILE: hw2/data/sb_rtg_dna_CartPole-v0_24-01-2018_09-04-19/11/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0560846 0.24747061729431152 0 17.6666666667 10.2312444293 48.0 8.0 17.6666666667 10.2312444293 1007 1007
0.0522385 0.4067237377166748 1 19.9230769231 8.35244357116 45.0 8.0 19.9230769231 8.35244357116 1036 2043
0.0650568 0.5607271194458008 2 21.4042553191 10.9964396065 57.0 9.0 21.4042553191 10.9964396065 1006 3049
0.0817289 0.7143452167510986 3 23.6046511628 11.1211918695 52.0 9.0 23.6046511628 11.1211918695 1015 4064
0.0689793 0.8649470806121826 4 27.5405405405 13.9431172493 75.0 10.0 27.5405405405 13.9431172493 1019 5083
0.06989 1.0156357288360596 5 27.1621621622 17.7269279263 88.0 11.0 27.1621621622 17.7269279263 1005 6088
0.0561705 1.1668548583984375 6 30.3939393939 12.9098022282 66.0 14.0 30.3939393939 12.9098022282 1003 7091
0.0819674 1.319521188735962 7 34.8275862069 15.6735423136 67.0 12.0 34.8275862069 15.6735423136 1010 8101
0.0833673 1.4644529819488525 8 38.6538461538 19.3071176746 86.0 11.0 38.6538461538 19.3071176746 1005 9106
0.0219641 1.616746187210083 9 32.3548387097 11.4878572277 62.0 16.0 32.3548387097 11.4878572277 1003 10109
0.0253773 1.7740662097930908 10 35.5172413793 14.2359929699 65.0 16.0 35.5172413793 14.2359929699 1030 11139
0.0485287 1.9319872856140137 11 45.9545454545 17.041332835 95.0 20.0 45.9545454545 17.041332835 1011 12150
0.0407209 2.0876622200012207 12 40.16 12.0819865916 67.0 20.0 40.16 12.0819865916 1004 13154
0.0174236 2.2414391040802 13 40.76 13.2462221029 64.0 15.0 40.76 13.2462221029 1019 14173
0.0245152 2.404252529144287 14 47.7727272727 23.3080786193 123.0 17.0 47.7727272727 23.3080786193 1051 15224
0.0409718 2.5657777786254883 15 48.0454545455 22.0071832751 99.0 21.0 48.0454545455 22.0071832751 1057 16281
0.00781822 2.7151083946228027 16 49.8095238095 17.4372863977 90.0 20.0 49.8095238095 17.4372863977 1046 17327
0.0496655 2.8698432445526123 17 45.2608695652 20.2188405278 99.0 15.0 45.2608695652 20.2188405278 1041 18368
0.0148048 3.017552614212036 18 48.1904761905 15.4907623706 85.0 19.0 48.1904761905 15.4907623706 1012 19380
0.065794 3.1715753078460693 19 61.1764705882 33.7608114171 174.0 30.0 61.1764705882 33.7608114171 1040 20420
0.0767422 3.3273322582244873 20 52.65 26.3709594061 156.0 30.0 52.65 26.3709594061 1053 21473
0.0259609 3.486408233642578 21 58.1666666667 17.8862144309 102.0 33.0 58.1666666667 17.8862144309 1047 22520
0.00663948 3.6447319984436035 22 52.3 14.2867071084 83.0 35.0 52.3 14.2867071084 1046 23566
0.0392265 3.799269437789917 23 59.0 18.0523928854 102.0 25.0 59.0 18.0523928854 1062 24628
0.0630493 3.967003107070923 24 68.2 28.8240640207 128.0 26.0 68.2 28.8240640207 1023 25651
0.0237293 4.123242378234863 25 57.7222222222 23.0574296427 113.0 27.0 57.7222222222 23.0574296427 1039 26690
0.00328827 4.2701239585876465 26 51.75 16.2722924015 105.0 31.0 51.75 16.2722924015 1035 27725
0.00663662 4.418715238571167 27 50.95 12.6628393341 89.0 34.0 50.95 12.6628393341 1019 28744
0.0420361 4.569820165634155 28 61.2352941176 29.7885280164 139.0 32.0 61.2352941176 29.7885280164 1041 29785
0.00323105 4.715519189834595 29 59.0588235294 13.828659874 78.0 36.0 59.0588235294 13.828659874 1004 30789
0.00470352 4.8775763511657715 30 62.6470588235 25.5341551571 118.0 35.0 62.6470588235 25.5341551571 1065 31854
0.0153217 5.0286736488342285 31 57.1111111111 15.5951876085 90.0 35.0 57.1111111111 15.5951876085 1028 32882
0.0339508 5.189091682434082 32 61.9411764706 18.753730886 94.0 41.0 61.9411764706 18.753730886 1053 33935
-0.000564575 5.337356090545654 33 77.3076923077 28.7358918304 129.0 38.0 77.3076923077 28.7358918304 1005 34940
-0.00799561 5.496536493301392 34 69.4666666667 29.9574513083 153.0 34.0 69.4666666667 29.9574513083 1042 35982
0.0151939 5.644292831420898 35 68.1333333333 22.538460955 119.0 41.0 68.1333333333 22.538460955 1022 37004
0.01441 5.8214592933654785 36 73.0 37.658000478 200.0 36.0 73.0 37.658000478 1168 38172
0.00949669 5.967486143112183 37 59.0588235294 10.2352941176 75.0 40.0 59.0588235294 10.2352941176 1004 39176
0.0167637 6.116281270980835 38 71.5714285714 14.3662018328 104.0 43.0 71.5714285714 14.3662018328 1002 40178
0.0148201 6.263565540313721 39 77.0 26.4894754137 139.0 46.0 77.0 26.4894754137 1001 41179
0.0235901 6.415862321853638 40 72.1428571429 12.6990277629 93.0 52.0 72.1428571429 12.6990277629 1010 42189
0.0259552 6.565152168273926 41 80.8461538462 25.96994166 134.0 43.0 80.8461538462 25.96994166 1051 43240
0.0265636 6.730162143707275 42 89.4166666667 18.7459254832 124.0 58.0 89.4166666667 18.7459254832 1073 44313
0.0175476 6.879726409912109 43 68.3333333333 26.3506272327 129.0 42.0 68.3333333333 26.3506272327 1025 45338
0.0266113 7.030785799026489 44 80.0 22.2710574513 107.0 40.0 80.0 22.2710574513 1040 46378
0.0354214 7.182101726531982 45 73.5714285714 31.0108605071 161.0 40.0 73.5714285714 31.0108605071 1030 47408
0.0248775 7.336759328842163 46 74.0 23.8057616075 129.0 47.0 74.0 23.8057616075 1036 48444
0.000249863 7.492173671722412 47 79.6923076923 31.9311389264 144.0 31.0 79.6923076923 31.9311389264 1036 49480
0.0421658 7.663049936294556 48 87.2307692308 29.5638912973 156.0 49.0 87.2307692308 29.5638912973 1134 50614
0.0328617 7.809016704559326 49 79.0 22.5388553392 125.0 46.0 79.0 22.5388553392 1027 51641
0.0244198 7.96494460105896 50 90.4166666667 33.9201472416 170.0 46.0 90.4166666667 33.9201472416 1085 52726
0.0272751 8.112575054168701 51 91.0 27.8437197097 143.0 48.0 91.0 27.8437197097 1001 53727
0.0365887 8.269129514694214 52 84.6153846154 26.4503554187 145.0 57.0 84.6153846154 26.4503554187 1100 54827
0.138378 8.424699544906616 53 105.0 38.8793004052 191.0 62.0 105.0 38.8793004052 1050 55877
0.0962467 8.601940870285034 54 103.272727273 31.4037951068 166.0 63.0 103.272727273 31.4037951068 1136 57013
0.0429726 8.755515813827515 55 96.3636363636 32.8585749906 149.0 62.0 96.3636363636 32.8585749906 1060 58073
0.00097847 8.925845861434937 56 107.3 34.6238357205 186.0 63.0 107.3 34.6238357205 1073 59146
0.042305 9.12080192565918 57 110.1 30.1212549539 165.0 60.0 110.1 30.1212549539 1101 60247
0.0635948 9.349996566772461 58 129.0 44.4409720866 200.0 69.0 129.0 44.4409720866 1032 61279
0.138325 9.527002811431885 59 125.666666667 27.551971093 169.0 76.0 125.666666667 27.551971093 1131 62410
0.0130157 9.722131729125977 60 157.285714286 53.4701900547 200.0 69.0 157.285714286 53.4701900547 1101 63511
0.0729065 9.904833555221558 61 144.571428571 37.6861366813 200.0 98.0 144.571428571 37.6861366813 1012 64523
-0.0164719 10.06609559059143 62 137.625 40.4998070983 200.0 60.0 137.625 40.4998070983 1101 65624
0.118565 10.215534448623657 63 170.666666667 16.6399786325 200.0 150.0 170.666666667 16.6399786325 1024 66648
-0.0924225 10.379449605941772 64 185.166666667 25.3009661651 200.0 131.0 185.166666667 25.3009661651 1111 67759
0.0472603 10.552871465682983 65 191.833333333 18.2612218162 200.0 151.0 191.833333333 18.2612218162 1151 68910
0.0919342 10.711162328720093 66 171.0 30.8112533554 200.0 127.0 171.0 30.8112533554 1026 69936
-0.0899391 10.87523865699768 67 193.5 14.5344418537 200.0 161.0 193.5 14.5344418537 1161 71097
0.00837708 11.042084693908691 68 189.0 18.0923556601 200.0 151.0 189.0 18.0923556601 1134 72231
0.0837822 11.214411735534668 69 191.166666667 19.7519338012 200.0 147.0 191.166666667 19.7519338012 1147 73378
0.0294876 11.375651597976685 70 176.0 29.2973263854 200.0 119.0 176.0 29.2973263854 1056 74434
0.118164 11.548868179321289 71 195.0 9.50438495292 200.0 174.0 195.0 9.50438495292 1170 75604
-0.0247383 11.712136268615723 72 186.166666667 30.0467228755 200.0 119.0 186.166666667 30.0467228755 1117 76721
0.0748138 11.886616945266724 73 199.833333333 0.37267799625 200.0 199.0 199.833333333 0.37267799625 1199 77920
-0.00621414 12.059775352478027 74 190.0 22.360679775 200.0 140.0 190.0 22.360679775 1140 79060
-0.0260391 12.21758246421814 75 174.5 32.8214868646 200.0 109.0 174.5 32.8214868646 1047 80107
0.0479355 12.387752771377563 76 189.5 15.0748134317 200.0 164.0 189.5 15.0748134317 1137 81244
0.0727615 12.53816032409668 77 171.166666667 43.3528802068 200.0 88.0 171.166666667 43.3528802068 1027 82271
-0.0539207 12.69580626487732 78 177.0 27.8448080139 200.0 124.0 177.0 27.8448080139 1062 83333
0.0346451 12.875293016433716 79 200.0 0.0 200.0 200.0 200.0 0.0 1200 84533
0.11137 13.03992486000061 80 191.166666667 19.7519338012 200.0 147.0 191.166666667 19.7519338012 1147 85680
0.0126305 13.210304737091064 81 192.666666667 16.397831835 200.0 156.0 192.666666667 16.397831835 1156 86836
0.0520782 13.366092205047607 82 178.5 37.3262642117 200.0 98.0 178.5 37.3262642117 1071 87907
-0.0157547 13.534087419509888 83 188.833333333 24.9694257487 200.0 133.0 188.833333333 24.9694257487 1133 89040
0.107243 13.684415340423584 84 171.833333333 41.5909311696 200.0 83.0 171.833333333 41.5909311696 1031 90071
-0.0147896 13.854785919189453 85 191.166666667 19.7519338012 200.0 147.0 191.166666667 19.7519338012 1147 91218
-0.0165367 14.030370712280273 86 200.0 0.0 200.0 200.0 200.0 0.0 1200 92418
0.0284271 14.211261987686157 87 198.0 4.472135955 200.0 188.0 198.0 4.472135955 1188 93606
0.00725174 14.383411884307861 88 195.666666667 9.6896279025 200.0 174.0 195.666666667 9.6896279025 1174 94780
0.00213242 14.54317855834961 89 182.666666667 33.6782158408 200.0 108.0 182.666666667 33.6782158408 1096 95876
0.0134659 14.704779148101807 90 183.5 36.8951216287 200.0 101.0 183.5 36.8951216287 1101 96977
-0.00560379 14.880486488342285 91 200.0 0.0 200.0 200.0 200.0 0.0 1200 98177
0.0367661 15.0493803024292 92 180.166666667 44.3486815537 200.0 81.0 180.166666667 44.3486815537 1081 99258
0.0138893 15.213099002838135 93 176.666666667 33.3199973323 200.0 122.0 176.666666667 33.3199973323 1060 100318
0.00634766 15.378223180770874 94 185.0 25.6580071972 200.0 130.0 185.0 25.6580071972 1110 101428
-0.0087471 15.554834127426147 95 200.0 0.0 200.0 200.0 200.0 0.0 1200 102628
0.0596733 15.732490062713623 96 200.0 0.0 200.0 200.0 200.0 0.0 1200 103828
0.00492096 15.907522916793823 97 186.833333333 29.4415617037 200.0 121.0 186.833333333 29.4415617037 1121 104949
0.0887947 16.083611965179443 98 200.0 0.0 200.0 200.0 200.0 0.0 1200 106149
-0.0168304 16.26010751724243 99 200.0 0.0 200.0 200.0 200.0 0.0 1200 107349
================================================
FILE: hw2/data/sb_rtg_dna_CartPole-v0_24-01-2018_09-04-19/11/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_rtg_dna_CartPole-v0_24-01-2018_09-04-19/11",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : true,
"seed" : 11,
"size" : 32}
================================================
FILE: hw2/data/sb_rtg_dna_CartPole-v0_24-01-2018_09-04-19/21/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0804367 0.2630434036254883 0 22.2826086957 10.7595519615 53.0 9.0 22.2826086957 10.7595519615 1025 1025
0.0743914 0.4383816719055176 1 22.3777777778 15.2523788875 106.0 10.0 22.3777777778 15.2523788875 1007 2032
0.0633535 0.585752010345459 2 21.5957446809 11.5236289616 68.0 8.0 21.5957446809 11.5236289616 1015 3047
0.0733013 0.7593667507171631 3 24.4390243902 13.1761957952 76.0 9.0 24.4390243902 13.1761957952 1002 4049
0.0676899 0.9300620555877686 4 25.6666666667 14.4245754207 68.0 10.0 25.6666666667 14.4245754207 1001 5050
0.041194 1.1082019805908203 5 26.9210526316 15.7653543852 88.0 10.0 26.9210526316 15.7653543852 1023 6073
0.100897 1.2943599224090576 6 32.65625 22.8098243294 94.0 10.0 32.65625 22.8098243294 1045 7118
0.0719452 1.4541172981262207 7 36.1428571429 24.2762586634 118.0 12.0 36.1428571429 24.2762586634 1012 8130
0.0219431 1.6085495948791504 8 32.25 16.0039057733 80.0 12.0 32.25 16.0039057733 1032 9162
0.0229111 1.7736668586730957 9 37.0740740741 13.8321309409 72.0 14.0 37.0740740741 13.8321309409 1001 10163
0.070631 1.9278676509857178 10 42.0 22.0852892216 88.0 16.0 42.0 22.0852892216 1050 11213
0.0836258 2.0831286907196045 11 48.9047619048 27.8258269238 128.0 16.0 48.9047619048 27.8258269238 1027 12240
0.0428429 2.2286934852600098 12 53.3684210526 28.4812228565 131.0 14.0 53.3684210526 28.4812228565 1014 13254
0.0687733 2.381258964538574 13 61.2941176471 21.0427148379 96.0 14.0 61.2941176471 21.0427148379 1042 14296
0.0281582 2.5255908966064453 14 44.6956521739 24.0857792837 100.0 11.0 44.6956521739 24.0857792837 1028 15324
0.0393982 2.6905362606048584 15 44.125 24.8165141589 131.0 17.0 44.125 24.8165141589 1059 16383
0.0342503 2.8417768478393555 16 55.5789473684 23.1319232356 142.0 33.0 55.5789473684 23.1319232356 1056 17439
0.0438633 3.0087358951568604 17 56.05 27.8145195896 123.0 14.0 56.05 27.8145195896 1121 18560
0.0299911 3.1628384590148926 18 53.8947368421 25.5031365189 118.0 16.0 53.8947368421 25.5031365189 1024 19584
0.0634861 3.316136598587036 19 53.2 26.5586144217 106.0 22.0 53.2 26.5586144217 1064 20648
0.0507183 3.465606212615967 20 60.8823529412 30.7970249765 161.0 23.0 60.8823529412 30.7970249765 1035 21683
0.0818539 3.6197800636291504 21 68.2 40.7826760606 169.0 24.0 68.2 40.7826760606 1023 22706
0.0217857 3.7753167152404785 22 69.8666666667 35.7190269869 141.0 24.0 69.8666666667 35.7190269869 1048 23754
0.0480309 3.9414784908294678 23 79.7692307692 22.2715888216 110.0 46.0 79.7692307692 22.2715888216 1037 24791
0.0748959 4.098399877548218 24 72.2666666667 40.1322258983 184.0 21.0 72.2666666667 40.1322258983 1084 25875
0.0686035 4.265009164810181 25 87.1538461538 34.157657445 154.0 37.0 87.1538461538 34.157657445 1133 27008
0.0086441 4.413326978683472 26 59.4705882353 31.2600433688 118.0 18.0 59.4705882353 31.2600433688 1011 28019
0.0224705 4.568598508834839 27 79.0769230769 29.846946857 129.0 29.0 79.0769230769 29.846946857 1028 29047
0.0291519 4.721293687820435 28 85.0833333333 34.5312861362 135.0 26.0 85.0833333333 34.5312861362 1021 30068
0.12265 4.877910614013672 29 86.3333333333 52.1493581509 200.0 24.0 86.3333333333 52.1493581509 1036 31104
0.117599 5.041196584701538 30 133.375 50.497369981 200.0 44.0 133.375 50.497369981 1067 32171
0.101143 5.2245564460754395 31 148.5 39.9186673124 200.0 95.0 148.5 39.9186673124 1188 33359
0.0398331 5.381887197494507 32 128.25 51.2975389273 192.0 34.0 128.25 51.2975389273 1026 34385
-0.061203 5.562531471252441 33 136.5 39.2842207508 171.0 44.0 136.5 39.2842207508 1092 35477
0.079483 5.736581087112427 34 166.0 30.8915152475 200.0 117.0 166.0 30.8915152475 1162 36639
0.00191116 5.913924217224121 35 143.625 44.7155943156 200.0 56.0 143.625 44.7155943156 1149 37788
0.0405579 6.087153673171997 36 164.428571429 23.0146359821 200.0 134.0 164.428571429 23.0146359821 1151 38939
0.092205 6.269052267074585 37 199.5 1.11803398875 200.0 197.0 199.5 1.11803398875 1197 40136
0.0324402 6.437319040298462 38 163.571428571 43.6245577722 200.0 92.0 163.571428571 43.6245577722 1145 41281
0.0197754 6.616912603378296 39 167.0 41.0609303353 200.0 96.0 167.0 41.0609303353 1169 42450
0.0290756 6.7916882038116455 40 200.0 0.0 200.0 200.0 200.0 0.0 1200 43650
0.0747986 6.9611546993255615 41 187.0 26.0640237364 200.0 129.0 187.0 26.0640237364 1122 44772
0.0403709 7.130882740020752 42 166.285714286 53.3310798844 200.0 47.0 166.285714286 53.3310798844 1164 45936
0.0306015 7.290274381637573 43 175.5 38.8662235538 200.0 96.0 175.5 38.8662235538 1053 46989
-0.015625 7.4530158042907715 44 176.0 35.8468966579 200.0 99.0 176.0 35.8468966579 1056 48045
0.0240135 7.644988298416138 45 200.0 0.0 200.0 200.0 200.0 0.0 1200 49245
0.0382309 7.810074329376221 46 180.5 43.6033255612 200.0 83.0 180.5 43.6033255612 1083 50328
0.0256653 7.996330738067627 47 199.333333333 1.490711985 200.0 196.0 199.333333333 1.490711985 1196 51524
-0.0126114 8.179894208908081 48 200.0 0.0 200.0 200.0 200.0 0.0 1200 52724
0.0502052 8.347827196121216 49 187.333333333 21.6307394439 200.0 141.0 187.333333333 21.6307394439 1124 53848
0.0178413 8.50356411933899 50 174.5 46.0135849505 200.0 74.0 174.5 46.0135849505 1047 54895
0.0106773 8.685011148452759 51 200.0 0.0 200.0 200.0 200.0 0.0 1200 56095
-0.00716782 8.865422248840332 52 200.0 0.0 200.0 200.0 200.0 0.0 1200 57295
0.0197258 9.049424648284912 53 200.0 0.0 200.0 200.0 200.0 0.0 1200 58495
0.0246887 9.224299669265747 54 190.166666667 21.9880017787 200.0 141.0 190.166666667 21.9880017787 1141 59636
0.0584297 9.385320663452148 55 173.666666667 42.9327639714 200.0 84.0 173.666666667 42.9327639714 1042 60678
0.0264854 9.566531896591187 56 200.0 0.0 200.0 200.0 200.0 0.0 1200 61878
0.0211067 9.740423917770386 57 191.333333333 19.379255805 200.0 148.0 191.333333333 19.379255805 1148 63026
-0.0302544 9.91178584098816 58 191.666666667 18.6338998125 200.0 150.0 191.666666667 18.6338998125 1150 64176
-0.000259399 10.09289002418518 59 168.428571429 38.6665493782 200.0 101.0 168.428571429 38.6665493782 1179 65355
0.03368 10.271867752075195 60 200.0 0.0 200.0 200.0 200.0 0.0 1200 66555
0.0359497 10.461168050765991 61 200.0 0.0 200.0 200.0 200.0 0.0 1200 67755
0.0533218 10.646152019500732 62 200.0 0.0 200.0 200.0 200.0 0.0 1200 68955
0.0154037 10.83639931678772 63 200.0 0.0 200.0 200.0 200.0 0.0 1200 70155
0.00777054 11.0083327293396 64 162.142857143 51.7643798418 200.0 52.0 162.142857143 51.7643798418 1135 71290
0.0902672 11.17816972732544 65 182.166666667 39.8765455987 200.0 93.0 182.166666667 39.8765455987 1093 72383
-0.00924301 11.357770919799805 66 197.0 6.7082039325 200.0 182.0 197.0 6.7082039325 1182 73565
0.0450668 11.54958200454712 67 200.0 0.0 200.0 200.0 200.0 0.0 1200 74765
0.139648 11.751339197158813 68 194.0 13.416407865 200.0 164.0 194.0 13.416407865 1164 75929
0.068531 11.920081615447998 69 186.166666667 30.9322736887 200.0 117.0 186.166666667 30.9322736887 1117 77046
0.107986 12.084782123565674 70 181.0 42.4852915725 200.0 86.0 181.0 42.4852915725 1086 78132
-0.0674629 12.26409101486206 71 200.0 0.0 200.0 200.0 200.0 0.0 1200 79332
0.145401 12.450555562973022 72 200.0 0.0 200.0 200.0 200.0 0.0 1200 80532
0.00979233 12.6284921169281 73 200.0 0.0 200.0 200.0 200.0 0.0 1200 81732
0.000370026 12.807374477386475 74 197.333333333 5.96284794 200.0 184.0 197.333333333 5.96284794 1184 82916
-0.085495 13.011728286743164 75 200.0 0.0 200.0 200.0 200.0 0.0 1200 84116
0.14653 13.201091051101685 76 192.333333333 17.1431878275 200.0 154.0 192.333333333 17.1431878275 1154 85270
0.0131836 13.402104377746582 77 200.0 0.0 200.0 200.0 200.0 0.0 1200 86470
0.000854492 13.577571153640747 78 186.5 21.0851448497 200.0 144.0 186.5 21.0851448497 1119 87589
0.0833282 13.742826223373413 79 180.666666667 22.6764684689 200.0 144.0 180.666666667 22.6764684689 1084 88673
-0.0150681 13.93411111831665 80 185.166666667 21.6826863854 200.0 146.0 185.166666667 21.6826863854 1111 89784
-0.0366287 14.109923124313354 81 187.5 20.5081284698 200.0 144.0 187.5 20.5081284698 1125 90909
0.0383339 14.307482242584229 82 168.142857143 36.8255678704 200.0 107.0 168.142857143 36.8255678704 1177 92086
0.00806808 14.485284328460693 83 184.166666667 24.1137351363 200.0 137.0 184.166666667 24.1137351363 1105 93191
0.0297203 14.658767700195312 84 192.666666667 11.1305385714 200.0 171.0 192.666666667 11.1305385714 1156 94347
0.0770378 14.830004692077637 85 187.5 27.9508497187 200.0 125.0 187.5 27.9508497187 1125 95472
0.00387192 15.011541604995728 86 200.0 0.0 200.0 200.0 200.0 0.0 1200 96672
-0.0177956 15.17676830291748 87 186.666666667 29.8142397 200.0 120.0 186.666666667 29.8142397 1120 97792
-0.0143814 15.358381509780884 88 200.0 0.0 200.0 200.0 200.0 0.0 1200 98992
-0.0193176 15.545406579971313 89 200.0 0.0 200.0 200.0 200.0 0.0 1200 100192
0.0121231 15.73288106918335 90 200.0 0.0 200.0 200.0 200.0 0.0 1200 101392
-0.0392456 15.936572313308716 91 200.0 0.0 200.0 200.0 200.0 0.0 1200 102592
0.0519562 16.11074471473694 92 193.0 15.6524758425 200.0 158.0 193.0 15.6524758425 1158 103750
-0.0177383 16.308683156967163 93 199.833333333 0.37267799625 200.0 199.0 199.833333333 0.37267799625 1199 104949
0.0211601 16.49505090713501 94 200.0 0.0 200.0 200.0 200.0 0.0 1200 106149
0.0645981 16.677566289901733 95 199.666666667 0.7453559925 200.0 198.0 199.666666667 0.7453559925 1198 107347
-0.0457687 16.845299243927002 96 193.5 14.5344418537 200.0 161.0 193.5 14.5344418537 1161 108508
0.0424271 17.032299518585205 97 200.0 0.0 200.0 200.0 200.0 0.0 1200 109708
0.0103531 17.20780658721924 98 187.166666667 28.6962057112 200.0 123.0 187.166666667 28.6962057112 1123 110831
-0.00744629 17.38323950767517 99 200.0 0.0 200.0 200.0 200.0 0.0 1200 112031
================================================
FILE: hw2/data/sb_rtg_dna_CartPole-v0_24-01-2018_09-04-19/21/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_rtg_dna_CartPole-v0_24-01-2018_09-04-19/21",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : true,
"seed" : 21,
"size" : 32}
================================================
FILE: hw2/data/sb_rtg_dna_CartPole-v0_24-01-2018_09-04-19/31/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0922327 0.25951075553894043 0 22.5777777778 11.8687056093 60.0 9.0 22.5777777778 11.8687056093 1016 1016
0.144267 0.42242932319641113 1 30.3939393939 19.6729923991 104.0 9.0 30.3939393939 19.6729923991 1003 2019
0.0700703 0.568608283996582 2 25.8205128205 14.3631861955 62.0 9.0 25.8205128205 14.3631861955 1007 3026
0.0750561 0.7229616641998291 3 26.6842105263 15.2317280755 90.0 11.0 26.6842105263 15.2317280755 1014 4040
0.0497026 0.8886327743530273 4 26.9210526316 13.0573261931 71.0 10.0 26.9210526316 13.0573261931 1023 5063
0.0567532 1.043156385421753 5 31.0606060606 19.1879687588 97.0 11.0 31.0606060606 19.1879687588 1025 6088
0.0879555 1.1941397190093994 6 41.36 30.0251627806 133.0 11.0 41.36 30.0251627806 1034 7122
0.066865 1.341080665588379 7 35.0689655172 16.0836842461 77.0 11.0 35.0689655172 16.0836842461 1017 8139
0.0793705 1.4887170791625977 8 52.7368421053 30.416135097 124.0 15.0 52.7368421053 30.416135097 1002 9141
0.0359783 1.641453742980957 9 42.5833333333 23.7502923959 110.0 14.0 42.5833333333 23.7502923959 1022 10163
0.0040493 1.7906312942504883 10 48.0952380952 22.5471036296 90.0 16.0 48.0952380952 22.5471036296 1010 11173
0.0577221 1.9450924396514893 11 48.9090909091 24.5632931811 119.0 18.0 48.9090909091 24.5632931811 1076 12249
0.0818729 2.09604811668396 12 53.4736842105 35.8393615149 137.0 14.0 53.4736842105 35.8393615149 1016 13265
0.0182037 2.2449214458465576 13 56.7222222222 29.0015431688 117.0 20.0 56.7222222222 29.0015431688 1021 14286
0.0177269 2.405154228210449 14 47.3181818182 14.94348859 74.0 16.0 47.3181818182 14.94348859 1041 15327
0.0513096 2.5567991733551025 15 61.0588235294 40.612183898 200.0 15.0 61.0588235294 40.612183898 1038 16365
0.0503902 2.703676223754883 16 67.1333333333 29.3118102857 137.0 24.0 67.1333333333 29.3118102857 1007 17372
0.0368938 2.85646915435791 17 65.8125 36.7818208324 178.0 34.0 65.8125 36.7818208324 1053 18425
0.032526 3.008779764175415 18 72.7857142857 33.9730535476 141.0 28.0 72.7857142857 33.9730535476 1019 19444
0.0873413 3.153059482574463 19 91.0909090909 53.9266413253 200.0 18.0 91.0909090909 53.9266413253 1002 20446
0.0450668 3.314424991607666 20 78.0714285714 38.7767682395 151.0 31.0 78.0714285714 38.7767682395 1093 21539
0.0319386 3.467141628265381 21 83.9166666667 38.9603609098 166.0 19.0 83.9166666667 38.9603609098 1007 22546
0.0849247 3.6271862983703613 22 76.6428571429 40.2875506167 183.0 25.0 76.6428571429 40.2875506167 1073 23619
0.0413399 3.7946507930755615 23 106.0 40.0658548801 176.0 40.0 106.0 40.0658548801 1166 24785
0.0276203 3.9497954845428467 24 75.2857142857 35.5154464814 138.0 32.0 75.2857142857 35.5154464814 1054 25839
0.0282211 4.1090614795684814 25 99.3636363636 41.2911452697 158.0 28.0 99.3636363636 41.2911452697 1093 26932
0.0195465 4.272621393203735 26 98.4545454545 49.6503476805 189.0 40.0 98.4545454545 49.6503476805 1083 28015
0.0835724 4.439011335372925 27 143.0 66.6033032214 200.0 21.0 143.0 66.6033032214 1144 29159
0.066803 4.618239641189575 28 147.75 58.276817861 200.0 38.0 147.75 58.276817861 1182 30341
0.056839 4.786418199539185 29 124.888888889 49.2283668099 200.0 16.0 124.888888889 49.2283668099 1124 31465
0.0275841 4.94498085975647 30 137.75 33.7925657505 200.0 102.0 137.75 33.7925657505 1102 32567
0.0345192 5.107569217681885 31 122.0 57.0029239016 200.0 29.0 122.0 57.0029239016 1098 33665
0.07061 5.260327577590942 32 168.666666667 41.2094918947 200.0 88.0 168.666666667 41.2094918947 1012 34677
0.0313301 5.4363226890563965 33 170.285714286 31.2808215352 200.0 109.0 170.285714286 31.2808215352 1192 35869
0.0311813 5.60206937789917 34 158.857142857 43.7735359433 200.0 86.0 158.857142857 43.7735359433 1112 36981
0.0739174 5.762478590011597 35 152.714285714 47.4483607596 200.0 78.0 152.714285714 47.4483607596 1069 38050
0.0177307 5.918854713439941 36 155.857142857 47.2423193196 200.0 78.0 155.857142857 47.2423193196 1091 39141
-0.00275421 6.079730749130249 37 159.857142857 57.2099605999 200.0 24.0 159.857142857 57.2099605999 1119 40260
0.0206718 6.236000061035156 38 154.857142857 58.264001558 200.0 23.0 154.857142857 58.264001558 1084 41344
0.0508842 6.391687393188477 39 151.428571429 63.7715949819 200.0 25.0 151.428571429 63.7715949819 1060 42404
0.036705 6.569853782653809 40 200.0 0.0 200.0 200.0 200.0 0.0 1200 43604
0.0385284 6.72409200668335 41 172.0 48.3321838944 200.0 68.0 172.0 48.3321838944 1032 44636
0.00518417 6.899214029312134 42 200.0 0.0 200.0 200.0 200.0 0.0 1200 45836
0.0338135 7.06645941734314 43 189.333333333 17.1139968707 200.0 154.0 189.333333333 17.1139968707 1136 46972
0.00533295 7.2301270961761475 44 178.666666667 35.0792752997 200.0 105.0 178.666666667 35.0792752997 1072 48044
0.0262604 7.3770270347595215 45 168.5 49.8455949241 200.0 60.0 168.5 49.8455949241 1011 49055
0.0402718 7.542575120925903 46 184.0 35.77708764 200.0 104.0 184.0 35.77708764 1104 50159
-0.00328064 7.6897783279418945 47 167.5 46.1148927499 200.0 96.0 167.5 46.1148927499 1005 51164
0.0607643 7.852436304092407 48 186.0 31.304951685 200.0 116.0 186.0 31.304951685 1116 52280
0.132626 8.025545358657837 49 200.0 0.0 200.0 200.0 200.0 0.0 1200 53480
0.00187683 8.184115648269653 50 174.833333333 52.3527034217 200.0 58.0 174.833333333 52.3527034217 1049 54529
0.0518074 8.352983474731445 51 181.833333333 25.7708922796 200.0 142.0 181.833333333 25.7708922796 1091 55620
0.183983 8.53017544746399 52 196.166666667 8.1325819325 200.0 178.0 196.166666667 8.1325819325 1177 56797
0.000579834 8.708232164382935 53 200.0 0.0 200.0 200.0 200.0 0.0 1200 57997
-0.0427742 8.887701511383057 54 194.166666667 13.0437298687 200.0 165.0 194.166666667 13.0437298687 1165 59162
0.0220566 9.06435775756836 55 192.5 12.2167917229 200.0 167.0 192.5 12.2167917229 1155 60317
-0.00934982 9.248148441314697 56 187.0 29.0688837075 200.0 122.0 187.0 29.0688837075 1122 61439
-0.00265121 9.405418634414673 57 166.833333333 42.2153868736 200.0 86.0 166.833333333 42.2153868736 1001 62440
-0.00695419 9.581432580947876 58 180.833333333 27.6551180716 200.0 133.0 180.833333333 27.6551180716 1085 63525
0.0322685 9.742971420288086 59 176.333333333 28.0752955857 200.0 125.0 176.333333333 28.0752955857 1058 64583
0.0789948 9.906214237213135 60 180.666666667 14.1852818873 200.0 165.0 180.666666667 14.1852818873 1084 65667
-0.0416718 10.06734037399292 61 183.5 15.2616076043 200.0 160.0 183.5 15.2616076043 1101 66768
-0.0124207 10.245781421661377 62 187.333333333 25.7336787542 200.0 130.0 187.333333333 25.7336787542 1124 67892
0.00843048 10.415621042251587 63 178.0 16.7630546142 200.0 161.0 178.0 16.7630546142 1068 68960
0.00535965 10.57919454574585 64 175.0 21.1187120819 200.0 136.0 175.0 21.1187120819 1050 70010
0.14888 10.746005773544312 65 187.0 12.1655250606 200.0 165.0 187.0 12.1655250606 1122 71132
0.0265503 10.92262578010559 66 195.0 11.1803398875 200.0 170.0 195.0 11.1803398875 1170 72302
-0.00840759 11.077533721923828 67 179.333333333 21.2262939666 200.0 149.0 179.333333333 21.2262939666 1076 73378
-0.00979233 11.229599952697754 68 174.666666667 25.7531012156 200.0 129.0 174.666666667 25.7531012156 1048 74426
-0.00772476 11.39327883720398 69 173.333333333 23.3785276601 200.0 140.0 173.333333333 23.3785276601 1040 75466
0.00301743 11.57274341583252 70 186.166666667 14.1470452353 200.0 168.0 186.166666667 14.1470452353 1117 76583
0.0156593 11.74487829208374 71 193.666666667 14.1617638575 200.0 162.0 193.666666667 14.1617638575 1162 77745
0.000686646 11.911642789840698 72 186.666666667 18.8650175958 200.0 159.0 186.666666667 18.8650175958 1120 78865
0.0488281 12.09498143196106 73 196.666666667 5.24933858267 200.0 186.0 196.666666667 5.24933858267 1180 80045
0.00513077 12.274259328842163 74 182.333333333 17.518244458 200.0 150.0 182.333333333 17.518244458 1094 81139
0.00686646 12.435225486755371 75 187.166666667 13.2465928533 200.0 168.0 187.166666667 13.2465928533 1123 82262
0.00150299 12.616610765457153 76 196.333333333 8.1989159175 200.0 178.0 196.333333333 8.1989159175 1178 83440
0.0229912 12.804043769836426 77 192.833333333 12.1163342458 200.0 167.0 192.833333333 12.1163342458 1157 84597
0.0117416 12.964002132415771 78 173.333333333 24.8573709167 200.0 127.0 173.333333333 24.8573709167 1040 85637
0.00468063 13.132283926010132 79 187.166666667 26.497903481 200.0 128.0 187.166666667 26.497903481 1123 86760
0.0417786 13.3091402053833 80 195.333333333 10.434983895 200.0 172.0 195.333333333 10.434983895 1172 87932
0.0653954 13.482739925384521 81 193.833333333 13.7890858612 200.0 163.0 193.833333333 13.7890858612 1163 89095
-0.0257797 13.653413534164429 82 196.166666667 5.78551831924 200.0 185.0 196.166666667 5.78551831924 1177 90272
0.000835419 13.824819564819336 83 194.5 12.2983738762 200.0 167.0 194.5 12.2983738762 1167 91439
0.00411224 13.999768018722534 84 185.0 21.2837966538 200.0 152.0 185.0 21.2837966538 1110 92549
0.0538254 14.179962396621704 85 194.666666667 11.92569588 200.0 168.0 194.666666667 11.92569588 1168 93717
0.00869751 14.356690883636475 86 193.833333333 8.87724932372 200.0 176.0 193.833333333 8.87724932372 1163 94880
0.0118217 14.531358003616333 87 196.166666667 5.48988969733 200.0 187.0 196.166666667 5.48988969733 1177 96057
-0.00819397 14.704313039779663 88 193.166666667 15.2797978462 200.0 159.0 193.166666667 15.2797978462 1159 97216
-0.000312805 14.868470430374146 89 191.0 13.0511813003 200.0 168.0 191.0 13.0511813003 1146 98362
0.0205765 15.037622451782227 90 192.333333333 12.2836838485 200.0 167.0 192.333333333 12.2836838485 1154 99516
0.0761223 15.49088430404663 91 192.666666667 8.71142289691 200.0 176.0 192.666666667 8.71142289691 1156 100672
0.00380325 15.67374849319458 92 199.666666667 0.7453559925 200.0 198.0 199.666666667 0.7453559925 1198 101870
0.0312119 15.859309673309326 93 193.666666667 14.1617638575 200.0 162.0 193.666666667 14.1617638575 1162 103032
0.122932 16.028408765792847 94 189.166666667 19.6334465192 200.0 146.0 189.166666667 19.6334465192 1135 104167
-0.0402489 16.205116510391235 95 196.5 7.82623792125 200.0 179.0 196.5 7.82623792125 1179 105346
0.041317 16.36110758781433 96 174.5 30.7828415409 200.0 115.0 174.5 30.7828415409 1047 106393
-0.034687 16.54116678237915 97 195.833333333 9.31694990625 200.0 175.0 195.833333333 9.31694990625 1175 107568
-0.00534439 16.70838165283203 98 179.333333333 29.5051784532 200.0 131.0 179.333333333 29.5051784532 1076 108644
0.0550194 16.875582218170166 99 180.0 19.8326330409 200.0 148.0 180.0 19.8326330409 1080 109724
================================================
FILE: hw2/data/sb_rtg_dna_CartPole-v0_24-01-2018_09-04-19/31/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_rtg_dna_CartPole-v0_24-01-2018_09-04-19/31",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : true,
"seed" : 31,
"size" : 32}
================================================
FILE: hw2/data/sb_rtg_dna_CartPole-v0_24-01-2018_09-04-19/41/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0855274 0.27823615074157715 0 24.5853658537 13.0346173422 66.0 10.0 24.5853658537 13.0346173422 1008 1008
0.0412092 0.42835569381713867 1 22.2444444444 10.9242961747 75.0 10.0 22.2444444444 10.9242961747 1001 2009
0.0765142 0.5887923240661621 2 29.0857142857 17.3656005261 96.0 10.0 29.0857142857 17.3656005261 1018 3027
0.0511522 0.7392137050628662 3 27.5405405405 14.2915484278 67.0 10.0 27.5405405405 14.2915484278 1019 4046
0.07265 0.8891897201538086 4 32.5483870968 14.1097968932 69.0 12.0 32.5483870968 14.1097968932 1009 5055
0.0670586 1.0321052074432373 5 33.7666666667 18.0068196958 72.0 11.0 33.7666666667 18.0068196958 1013 6068
0.0329132 1.1883714199066162 6 39.5 26.5203115192 111.0 12.0 39.5 26.5203115192 1027 7095
0.0359764 1.335862398147583 7 42.4583333333 23.7223157362 103.0 13.0 42.4583333333 23.7223157362 1019 8114
0.0462704 1.4828667640686035 8 38.6538461538 23.2510418422 115.0 11.0 38.6538461538 23.2510418422 1005 9119
0.0588169 1.6358156204223633 9 56.5555555556 24.379459073 102.0 16.0 56.5555555556 24.379459073 1018 10137
0.0352058 1.7830684185028076 10 54.3157894737 28.4254382581 125.0 16.0 54.3157894737 28.4254382581 1032 11169
0.0499477 1.9346129894256592 11 51.7 25.9154394136 129.0 18.0 51.7 25.9154394136 1034 12203
0.0317516 2.091053009033203 12 62.5294117647 32.2857055368 153.0 19.0 62.5294117647 32.2857055368 1063 13266
0.0139465 2.235746145248413 13 45.7727272727 29.2418315217 136.0 10.0 45.7727272727 29.2418315217 1007 14273
0.0290947 2.3876383304595947 14 60.5294117647 31.9413389661 155.0 24.0 60.5294117647 31.9413389661 1029 15302
0.0329075 2.5388095378875732 15 52.8947368421 34.1373306033 144.0 20.0 52.8947368421 34.1373306033 1005 16307
0.0515671 2.6878342628479004 16 59.1176470588 18.892520627 102.0 14.0 59.1176470588 18.892520627 1005 17312
0.0340118 2.8331494331359863 17 54.7368421053 28.7747003373 122.0 18.0 54.7368421053 28.7747003373 1040 18352
0.0251579 2.9898648262023926 18 52.15 23.0657213197 92.0 16.0 52.15 23.0657213197 1043 19395
0.0395718 3.144059181213379 19 75.0 42.3522642336 176.0 36.0 75.0 42.3522642336 1050 20445
0.0918884 3.2993767261505127 20 88.5 44.1030989085 192.0 35.0 88.5 44.1030989085 1062 21507
0.132523 3.450077772140503 21 85.1666666667 40.9162423603 187.0 32.0 85.1666666667 40.9162423603 1022 22529
0.0916824 3.6017138957977295 22 74.1428571429 35.9500787658 132.0 20.0 74.1428571429 35.9500787658 1038 23567
0.116344 3.7574002742767334 23 106.1 55.100725948 198.0 36.0 106.1 55.100725948 1061 24628
0.0560226 3.910435438156128 24 112.666666667 43.3640916479 200.0 38.0 112.666666667 43.3640916479 1014 25642
-0.0138817 4.063228130340576 25 114.555555556 47.3171594693 197.0 46.0 114.555555556 47.3171594693 1031 26673
0.0299835 4.227828502655029 26 117.666666667 57.7985005573 200.0 34.0 117.666666667 57.7985005573 1059 27732
0.0331268 4.37715482711792 27 127.875 57.3398585192 200.0 26.0 127.875 57.3398585192 1023 28755
0.026413 4.539777994155884 28 140.625 51.6452744692 200.0 38.0 140.625 51.6452744692 1125 29880
0.00834274 4.699289321899414 29 110.4 37.3850237395 161.0 38.0 110.4 37.3850237395 1104 30984
0.0473862 4.855970621109009 30 119.666666667 63.9895824855 200.0 22.0 119.666666667 63.9895824855 1077 32061
0.0482101 5.011845827102661 31 107.9 64.2813347715 200.0 22.0 107.9 64.2813347715 1079 33140
0.0949554 5.169280290603638 32 129.625 58.668427412 200.0 30.0 129.625 58.668427412 1037 34177
0.025589 5.349197149276733 33 143.875 56.9219586364 200.0 59.0 143.875 56.9219586364 1151 35328
0.00126266 5.517951726913452 34 117.777777778 46.6566126736 200.0 28.0 117.777777778 46.6566126736 1060 36388
0.0452347 5.687227964401245 35 155.857142857 44.4407424762 200.0 84.0 155.857142857 44.4407424762 1091 37479
0.033802 5.8594276905059814 36 187.5 24.1505693515 200.0 134.0 187.5 24.1505693515 1125 38604
0.0601044 6.0198822021484375 37 181.5 37.4866642955 200.0 98.0 181.5 37.4866642955 1089 39693
0.0114403 6.196885585784912 38 165.142857143 49.1133632424 200.0 82.0 165.142857143 49.1133632424 1156 40849
0.00652695 6.345746278762817 39 143.857142857 63.0972686106 200.0 24.0 143.857142857 63.0972686106 1007 41856
0.0491638 6.520198106765747 40 167.571428571 34.8173074484 200.0 113.0 167.571428571 34.8173074484 1173 43029
0.0170059 6.694750070571899 41 171.142857143 52.0862706655 200.0 52.0 171.142857143 52.0862706655 1198 44227
0.0422173 6.853736639022827 42 173.5 50.06579005 200.0 63.0 173.5 50.06579005 1041 45268
0.113422 7.039259672164917 43 199.666666667 0.7453559925 200.0 198.0 199.666666667 0.7453559925 1198 46466
0.0912743 7.223822593688965 44 200.0 0.0 200.0 200.0 200.0 0.0 1200 47666
-0.0498238 7.402947425842285 45 196.5 7.82623792125 200.0 179.0 196.5 7.82623792125 1179 48845
-0.0342903 7.601095199584961 46 195.166666667 10.8076618912 200.0 171.0 195.166666667 10.8076618912 1171 50016
0.0145302 7.799468517303467 47 200.0 0.0 200.0 200.0 200.0 0.0 1200 51216
-0.0102196 8.015951871871948 48 198.666666667 2.98142397 200.0 192.0 198.666666667 2.98142397 1192 52408
0.0525665 8.339295387268066 49 199.833333333 0.37267799625 200.0 199.0 199.833333333 0.37267799625 1199 53607
0.13628 8.894888639450073 50 196.333333333 8.1989159175 200.0 178.0 196.333333333 8.1989159175 1178 54785
-0.0158806 9.06509804725647 51 192.166666667 17.5158658237 200.0 153.0 192.166666667 17.5158658237 1153 55938
-0.000595093 9.241004943847656 52 183.5 23.3505888577 200.0 149.0 183.5 23.3505888577 1101 57039
0.0642281 9.407284259796143 53 182.333333333 30.4010233746 200.0 117.0 182.333333333 30.4010233746 1094 58133
-0.0417595 9.57451319694519 54 182.666666667 25.3223660471 200.0 137.0 182.666666667 25.3223660471 1096 59229
0.0443878 9.750059604644775 55 200.0 0.0 200.0 200.0 200.0 0.0 1200 60429
-0.00840378 9.929886817932129 56 200.0 0.0 200.0 200.0 200.0 0.0 1200 61629
0.0609322 10.10128927230835 57 195.666666667 9.6896279025 200.0 174.0 195.666666667 9.6896279025 1174 62803
0.00229263 10.281039714813232 58 195.166666667 7.31247032283 200.0 181.0 195.166666667 7.31247032283 1171 63974
0.0529938 10.464292287826538 59 200.0 0.0 200.0 200.0 200.0 0.0 1200 65174
0.0247307 10.641376495361328 60 195.0 11.1803398875 200.0 170.0 195.0 11.1803398875 1170 66344
0.118061 10.798985958099365 61 180.5 27.8313372538 200.0 135.0 180.5 27.8313372538 1083 67427
0.0173988 10.976282596588135 62 193.333333333 14.90711985 200.0 160.0 193.333333333 14.90711985 1160 68587
0.00104141 11.129475355148315 63 169.666666667 33.3499958354 200.0 112.0 169.666666667 33.3499958354 1018 69605
0.035717 11.284462451934814 64 174.166666667 28.7774024 200.0 123.0 174.166666667 28.7774024 1045 70650
-0.00825119 11.446407556533813 65 184.333333333 35.0317316475 200.0 106.0 184.333333333 35.0317316475 1106 71756
-0.0168571 11.601016521453857 66 168.833333333 48.3680909508 200.0 72.0 168.833333333 48.3680909508 1013 72769
0.0561485 11.776716470718384 67 200.0 0.0 200.0 200.0 200.0 0.0 1200 73969
-0.0069046 11.956775188446045 68 196.333333333 8.1989159175 200.0 178.0 196.333333333 8.1989159175 1178 75147
0.0339317 12.126981496810913 69 164.714285714 47.2583002104 200.0 68.0 164.714285714 47.2583002104 1153 76300
0.0560112 12.283555030822754 70 169.333333333 53.4124413305 200.0 54.0 169.333333333 53.4124413305 1016 77316
0.0300255 12.46398639678955 71 200.0 0.0 200.0 200.0 200.0 0.0 1200 78516
0.000415802 12.641393899917603 72 191.0 20.1246117975 200.0 146.0 191.0 20.1246117975 1146 79662
0.0649223 12.80258321762085 73 174.5 40.1320736236 200.0 93.0 174.5 40.1320736236 1047 80709
0.150967 12.97641897201538 74 183.333333333 37.267799625 200.0 100.0 183.333333333 37.267799625 1100 81809
0.0328064 13.145051956176758 75 182.666666667 38.75851161 200.0 96.0 182.666666667 38.75851161 1096 82905
0.0782661 13.322587728500366 76 194.833333333 11.5530178837 200.0 169.0 194.833333333 11.5530178837 1169 84074
0.0213852 13.498681545257568 77 200.0 0.0 200.0 200.0 200.0 0.0 1200 85274
0.0285187 13.668691158294678 78 181.833333333 40.6219015912 200.0 91.0 181.833333333 40.6219015912 1091 86365
0.0975838 13.834267139434814 79 189.333333333 23.85139176 200.0 136.0 189.333333333 23.85139176 1136 87501
-0.000534058 14.025714874267578 80 200.0 0.0 200.0 200.0 200.0 0.0 1200 88701
0.0521393 14.204215049743652 81 199.5 1.11803398875 200.0 197.0 199.5 1.11803398875 1197 89898
-0.0167313 14.375050067901611 82 189.833333333 22.7333577712 200.0 139.0 189.833333333 22.7333577712 1139 91037
0.00638962 14.553272724151611 83 200.0 0.0 200.0 200.0 200.0 0.0 1200 92237
0.0354805 14.718742609024048 84 184.333333333 25.5386417458 200.0 131.0 184.333333333 25.5386417458 1106 93343
0.00901794 14.90030837059021 85 198.0 3.0550504633 200.0 192.0 198.0 3.0550504633 1188 94531
0.0714188 15.08115291595459 86 197.333333333 5.96284794 200.0 184.0 197.333333333 5.96284794 1184 95715
-0.0259743 15.246641159057617 87 193.166666667 7.6029964853 200.0 183.0 193.166666667 7.6029964853 1159 96874
-0.0247803 15.432433605194092 88 197.0 4.28174419289 200.0 190.0 197.0 4.28174419289 1182 98056
-0.00884628 15.600127220153809 89 186.5 19.267848868 200.0 155.0 186.5 19.267848868 1119 99175
0.0173416 15.769906759262085 90 192.5 16.7705098312 200.0 155.0 192.5 16.7705098312 1155 100330
0.0281639 15.94014024734497 91 193.666666667 10.9797793947 200.0 170.0 193.666666667 10.9797793947 1162 101492
-0.00961304 16.112197160720825 92 189.833333333 10.9607886983 200.0 172.0 189.833333333 10.9607886983 1139 102631
0.0343285 16.286952018737793 93 197.333333333 5.96284794 200.0 184.0 197.333333333 5.96284794 1184 103815
0.11298 16.46646285057068 94 198.666666667 2.98142397 200.0 192.0 198.666666667 2.98142397 1192 105007
-0.00617218 16.63081192970276 95 186.833333333 27.2666870416 200.0 126.0 186.833333333 27.2666870416 1121 106128
-0.0469208 16.800034284591675 96 192.666666667 13.1487219489 200.0 164.0 192.666666667 13.1487219489 1156 107284
0.0395203 16.965912580490112 97 191.666666667 18.1903515329 200.0 151.0 191.666666667 18.1903515329 1150 108434
0.0354996 17.133029222488403 98 181.666666667 18.9179514982 200.0 156.0 181.666666667 18.9179514982 1090 109524
-0.0222359 17.310266971588135 99 198.833333333 2.60874597375 200.0 193.0 198.833333333 2.60874597375 1193 110717
================================================
FILE: hw2/data/sb_rtg_dna_CartPole-v0_24-01-2018_09-04-19/41/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_rtg_dna",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_rtg_dna_CartPole-v0_24-01-2018_09-04-19/41",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : false,
"reward_to_go" : true,
"seed" : 41,
"size" : 32}
================================================
FILE: hw2/data/sb_rtg_na_CartPole-v0_24-01-2018_09-08-49/1/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.00480941 0.24747347831726074 0 28.4444444444 13.8673165802 58.0 10.0 28.4444444444 13.8673165802 1024 1024
0.00398796 0.3974301815032959 1 28.2222222222 19.2312117708 100.0 9.0 28.2222222222 19.2312117708 1016 2040
0.00475816 0.554685115814209 2 27.6052631579 15.0149740587 91.0 9.0 27.6052631579 15.0149740587 1049 3089
0.0045335 0.6984961032867432 3 32.7096774194 17.5649826651 72.0 12.0 32.7096774194 17.5649826651 1014 4103
0.0028862 0.8492703437805176 4 41.52 22.0492539556 105.0 13.0 41.52 22.0492539556 1038 5141
0.0035779 0.9991872310638428 5 36.7142857143 15.2335558715 68.0 12.0 36.7142857143 15.2335558715 1028 6169
0.00501709 1.1507234573364258 6 29.7352941176 14.1760129289 70.0 10.0 29.7352941176 14.1760129289 1011 7180
0.00128735 1.296959400177002 7 48.5238095238 23.6313332103 100.0 19.0 48.5238095238 23.6313332103 1019 8199
0.00284239 1.4517743587493896 8 37.7407407407 16.9718559901 69.0 15.0 37.7407407407 16.9718559901 1019 9218
0.00094862 1.6027514934539795 9 52.6842105263 31.7092923979 161.0 18.0 52.6842105263 31.7092923979 1001 10219
0.00187416 1.759084701538086 10 53.6315789474 25.5429679814 145.0 26.0 53.6315789474 25.5429679814 1019 11238
0.00187252 1.9094359874725342 11 41.9583333333 19.6796831925 100.0 16.0 41.9583333333 19.6796831925 1007 12245
0.00160479 2.0684032440185547 12 47.5909090909 24.2705565934 112.0 13.0 47.5909090909 24.2705565934 1047 13292
0.00249054 2.227316379547119 13 48.9523809524 24.0900615557 115.0 18.0 48.9523809524 24.0900615557 1028 14320
0.000635797 2.380065441131592 14 50.45 19.7875592229 94.0 21.0 50.45 19.7875592229 1009 15329
0.00142346 2.533665180206299 15 50.95 17.5341809047 76.0 20.0 50.95 17.5341809047 1019 16348
0.00126756 2.693100690841675 16 53.45 21.6874963977 99.0 20.0 53.45 21.6874963977 1069 17417
0.000969923 2.84407114982605 17 50.95 15.2133986998 87.0 26.0 50.95 15.2133986998 1019 18436
0.00158494 3.0024805068969727 18 67.0666666667 32.6771411778 136.0 17.0 67.0666666667 32.6771411778 1006 19442
0.000308974 3.150132417678833 19 59.4705882353 25.5690935841 127.0 26.0 59.4705882353 25.5690935841 1011 20453
-6.63158e-05 3.300474166870117 20 72.2857142857 22.0467962409 107.0 36.0 72.2857142857 22.0467962409 1012 21465
0.00101552 3.446685552597046 21 53.0 19.6683020432 98.0 22.0 53.0 19.6683020432 1007 22472
0.00106945 3.6099536418914795 22 59.3333333333 14.2828568571 95.0 33.0 59.3333333333 14.2828568571 1068 23540
0.000980014 3.7606923580169678 23 57.3888888889 21.5384382207 114.0 28.0 57.3888888889 21.5384382207 1033 24573
0.00128772 3.926046371459961 24 66.0 32.3419232576 150.0 32.0 66.0 32.3419232576 1122 25695
0.000968087 4.0851805210113525 25 55.7894736842 21.7705231602 85.0 19.0 55.7894736842 21.7705231602 1060 26755
0.000435282 4.251563549041748 26 71.8666666667 31.1637966593 148.0 30.0 71.8666666667 31.1637966593 1078 27833
0.000817629 4.403843641281128 27 65.375 31.246749831 168.0 22.0 65.375 31.246749831 1046 28879
0.00126023 4.551861047744751 28 66.8666666667 20.841838264 107.0 35.0 66.8666666667 20.841838264 1003 29882
0.00188065 4.705373048782349 29 93.5454545455 38.985693498 165.0 55.0 93.5454545455 38.985693498 1029 30911
0.00119616 4.856449127197266 30 84.1666666667 32.7409868853 157.0 33.0 84.1666666667 32.7409868853 1010 31921
0.00163613 5.008488178253174 31 77.0 39.9942303531 167.0 23.0 77.0 39.9942303531 1001 32922
0.0021601 5.1712329387664795 32 86.5833333333 38.0711140134 168.0 48.0 86.5833333333 38.0711140134 1039 33961
0.000987219 5.330045938491821 33 85.6666666667 31.398867637 137.0 32.0 85.6666666667 31.398867637 1028 34989
0.00216268 5.4810144901275635 34 84.4166666667 24.4794414878 121.0 36.0 84.4166666667 24.4794414878 1013 36002
0.00202927 5.631742000579834 35 71.5714285714 32.0662579351 145.0 26.0 71.5714285714 32.0662579351 1002 37004
0.00351748 5.787864685058594 36 93.0 30.3105142274 155.0 56.0 93.0 30.3105142274 1023 38027
0.00338574 5.954035520553589 37 121.888888889 54.3557100025 200.0 29.0 121.888888889 54.3557100025 1097 39124
0.000864574 6.116301774978638 38 116.111111111 37.9281321696 200.0 70.0 116.111111111 37.9281321696 1045 40169
0.00172279 6.294809341430664 39 147.875 52.539122328 200.0 67.0 147.875 52.539122328 1183 41352
0.00218873 6.459815740585327 40 134.875 58.6737537149 200.0 33.0 134.875 58.6737537149 1079 42431
0.00107869 6.618666648864746 41 152.428571429 50.9000621466 200.0 50.0 152.428571429 50.9000621466 1067 43498
0.00242138 6.796366930007935 42 168.142857143 31.8273403199 200.0 119.0 168.142857143 31.8273403199 1177 44675
2.11e-05 6.960450649261475 43 153.714285714 53.4888887947 200.0 72.0 153.714285714 53.4888887947 1076 45751
0.0002389 7.1186723709106445 44 147.714285714 58.1149459156 200.0 21.0 147.714285714 58.1149459156 1034 46785
-7.24321e-05 7.278601408004761 45 119.666666667 31.9443961352 200.0 88.0 119.666666667 31.9443961352 1077 47862
0.000519131 7.457162141799927 46 123.444444444 39.8806862504 200.0 72.0 123.444444444 39.8806862504 1111 48973
0.000328063 7.617704629898071 47 151.571428571 39.0049709025 200.0 99.0 151.571428571 39.0049709025 1061 50034
0.000736368 7.779310703277588 48 136.875 35.9215725574 200.0 103.0 136.875 35.9215725574 1095 51129
0.000772228 7.948662996292114 49 142.375 48.1454502004 200.0 82.0 142.375 48.1454502004 1139 52268
0.00103454 8.107398748397827 50 152.428571429 41.6202462506 200.0 79.0 152.428571429 41.6202462506 1067 53335
0.00194993 8.276415586471558 51 163.0 36.3318042492 200.0 117.0 163.0 36.3318042492 1141 54476
0.000944015 8.440730810165405 52 161.142857143 47.1575734606 200.0 78.0 161.142857143 47.1575734606 1128 55604
0.000745059 8.599162817001343 53 174.333333333 37.1872140512 200.0 109.0 174.333333333 37.1872140512 1046 56650
0.00281249 8.771811962127686 54 163.0 35.0020407568 200.0 121.0 163.0 35.0020407568 1141 57791
0.00257634 8.941521406173706 55 187.166666667 28.6962057112 200.0 123.0 187.166666667 28.6962057112 1123 58914
0.000299769 9.096029281616211 56 175.0 26.7457161679 200.0 131.0 175.0 26.7457161679 1050 59964
-0.000398773 9.25968313217163 57 185.166666667 21.7747305124 200.0 140.0 185.166666667 21.7747305124 1111 61075
0.000374576 9.422043800354004 58 183.666666667 29.9425375604 200.0 118.0 183.666666667 29.9425375604 1102 62177
0.000519773 9.589643955230713 59 183.833333333 36.1497656362 200.0 103.0 183.833333333 36.1497656362 1103 63280
0.000170033 9.754941701889038 60 178.833333333 27.2361075698 200.0 125.0 178.833333333 27.2361075698 1073 64353
0.000340193 9.928677082061768 61 198.166666667 4.09945795875 200.0 189.0 198.166666667 4.09945795875 1189 65542
0.00030476 10.107715129852295 62 200.0 0.0 200.0 200.0 200.0 0.0 1200 66742
0.00170623 10.262787580490112 63 176.5 17.604450195 200.0 147.0 176.5 17.604450195 1059 67801
0.000761918 10.427194595336914 64 181.333333333 35.0745238346 200.0 104.0 181.333333333 35.0745238346 1088 68889
0.000728345 10.60011339187622 65 193.666666667 14.1617638575 200.0 162.0 193.666666667 14.1617638575 1162 70051
0.000509522 10.781935930252075 66 195.333333333 10.434983895 200.0 172.0 195.333333333 10.434983895 1172 71223
-0.000308868 10.949552536010742 67 187.166666667 28.6962057112 200.0 123.0 187.166666667 28.6962057112 1123 72346
0.000129679 11.115353345870972 68 183.666666667 23.1636688708 200.0 148.0 183.666666667 23.1636688708 1102 73448
0.000962017 11.310680389404297 69 200.0 0.0 200.0 200.0 200.0 0.0 1200 74648
0.000455629 11.493396520614624 70 169.857142857 48.3748121338 200.0 79.0 169.857142857 48.3748121338 1189 75837
-0.000413501 11.677903175354004 71 200.0 0.0 200.0 200.0 200.0 0.0 1200 77037
-9.95384e-05 11.848168849945068 72 184.166666667 35.4044096437 200.0 105.0 184.166666667 35.4044096437 1105 78142
0.000168806 12.03431248664856 73 200.0 0.0 200.0 200.0 200.0 0.0 1200 79342
0.00022383 12.224358081817627 74 180.833333333 42.8579695687 200.0 85.0 180.833333333 42.8579695687 1085 80427
0.000467435 12.440301656723022 75 200.0 0.0 200.0 200.0 200.0 0.0 1200 81627
-0.000121416 12.625021934509277 76 177.5 50.3115294937 200.0 65.0 177.5 50.3115294937 1065 82692
5.26416e-05 12.782443761825562 77 173.0 29.0860791445 200.0 125.0 173.0 29.0860791445 1038 83730
0.000398187 12.961154460906982 78 192.333333333 10.8576649833 200.0 176.0 192.333333333 10.8576649833 1154 84884
0.000300654 13.142096519470215 79 200.0 0.0 200.0 200.0 200.0 0.0 1200 86084
2.28034e-05 13.339231729507446 80 189.0 23.2808934536 200.0 137.0 189.0 23.2808934536 1134 87218
0.000411661 13.5240638256073 81 200.0 0.0 200.0 200.0 200.0 0.0 1200 88418
9.98899e-05 13.701310157775879 82 182.833333333 38.3858336137 200.0 97.0 182.833333333 38.3858336137 1097 89515
0.000279716 13.879648208618164 83 191.666666667 14.2906340735 200.0 161.0 191.666666667 14.2906340735 1150 90665
6.87452e-05 14.062466144561768 84 200.0 0.0 200.0 200.0 200.0 0.0 1200 91865
0.000369976 14.244475841522217 85 200.0 0.0 200.0 200.0 200.0 0.0 1200 93065
0.00105782 14.409528970718384 86 181.833333333 40.6219015912 200.0 91.0 181.833333333 40.6219015912 1091 94156
0.000368527 14.585410356521606 87 200.0 0.0 200.0 200.0 200.0 0.0 1200 95356
0.000709432 14.771689653396606 88 200.0 0.0 200.0 200.0 200.0 0.0 1200 96556
-2.06926e-05 14.94533371925354 89 199.666666667 0.7453559925 200.0 198.0 199.666666667 0.7453559925 1198 97754
0.000177479 15.13055419921875 90 200.0 0.0 200.0 200.0 200.0 0.0 1200 98954
7.83689e-05 15.305435180664062 91 192.833333333 16.0251538387 200.0 157.0 192.833333333 16.0251538387 1157 100111
0.000466223 15.484735488891602 92 200.0 0.0 200.0 200.0 200.0 0.0 1200 101311
0.000732207 15.659429788589478 93 198.5 3.35410196625 200.0 191.0 198.5 3.35410196625 1191 102502
0.000417635 15.846064567565918 94 200.0 0.0 200.0 200.0 200.0 0.0 1200 103702
-0.000292371 16.0247220993042 95 199.5 1.11803398875 200.0 197.0 199.5 1.11803398875 1197 104899
0.000305324 16.19804334640503 96 189.0 17.272328544 200.0 154.0 189.0 17.272328544 1134 106033
0.000190972 16.38248085975647 97 199.0 2.2360679775 200.0 194.0 199.0 2.2360679775 1194 107227
0.000414957 16.543591499328613 98 180.833333333 42.8579695687 200.0 85.0 180.833333333 42.8579695687 1085 108312
0.000201463 16.715467929840088 99 187.166666667 28.6962057112 200.0 123.0 187.166666667 28.6962057112 1123 109435
================================================
FILE: hw2/data/sb_rtg_na_CartPole-v0_24-01-2018_09-08-49/1/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_rtg_na",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_rtg_na_CartPole-v0_24-01-2018_09-08-49/1",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 1,
"size" : 32}
================================================
FILE: hw2/data/sb_rtg_na_CartPole-v0_24-01-2018_09-08-49/11/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0142561 0.24705934524536133 0 19.0377358491 10.7210993948 66.0 8.0 19.0377358491 10.7210993948 1009 1009
0.0116773 0.4041616916656494 1 20.0 9.85582340051 47.0 9.0 20.0 9.85582340051 1020 2029
0.0084575 0.5580532550811768 2 21.306122449 12.5213353947 61.0 9.0 21.306122449 12.5213353947 1044 3073
0.00245941 0.7164516448974609 3 26.25 14.7338895068 94.0 11.0 26.25 14.7338895068 1050 4123
0.00321895 0.8672351837158203 4 32.8387096774 26.2679699158 132.0 13.0 32.8387096774 26.2679699158 1018 5141
0.00677172 1.0171709060668945 5 27.0263157895 15.597717178 82.0 11.0 27.0263157895 15.597717178 1027 6168
0.0058472 1.1694352626800537 6 25.15 12.1912878729 72.0 10.0 25.15 12.1912878729 1006 7174
0.00517159 1.3198444843292236 7 30.3939393939 14.6741153137 86.0 11.0 30.3939393939 14.6741153137 1003 8177
0.00335795 1.4679973125457764 8 35.1724137931 14.3432525661 70.0 10.0 35.1724137931 14.3432525661 1020 9197
0.00369814 1.6157870292663574 9 33.4666666667 14.4539114276 75.0 14.0 33.4666666667 14.4539114276 1004 10201
0.00284203 1.7661349773406982 10 39.9615384615 18.4942418674 90.0 14.0 39.9615384615 18.4942418674 1039 11240
0.00315079 1.9241421222686768 11 37.5185185185 20.3604016012 92.0 11.0 37.5185185185 20.3604016012 1013 12253
0.00219943 2.0775022506713867 12 40.4615384615 19.2198430499 85.0 15.0 40.4615384615 19.2198430499 1052 13305
0.00189064 2.226154327392578 13 40.8 12.5443214245 68.0 17.0 40.8 12.5443214245 1020 14325
0.000985871 2.376418352127075 14 45.8181818182 15.9904413596 100.0 22.0 45.8181818182 15.9904413596 1008 15333
0.000695865 2.5312235355377197 15 46.3636363636 17.5072594152 97.0 24.0 46.3636363636 17.5072594152 1020 16353
0.0024779 2.6801462173461914 16 48.619047619 24.423790491 97.0 11.0 48.619047619 24.423790491 1021 17374
0.0012376 2.833451747894287 17 45.8636363636 18.3830343092 86.0 16.0 45.8636363636 18.3830343092 1009 18383
0.000886392 2.9843883514404297 18 42.1666666667 19.3835554587 96.0 21.0 42.1666666667 19.3835554587 1012 19395
0.00139896 3.138176441192627 19 45.2173913043 16.1621041509 86.0 24.0 45.2173913043 16.1621041509 1040 20435
0.000811036 3.2884371280670166 20 64.4375 27.5634920456 120.0 22.0 64.4375 27.5634920456 1031 21466
0.000996872 3.441293716430664 21 58.1666666667 31.3851521866 148.0 26.0 58.1666666667 31.3851521866 1047 22513
0.000510582 3.593127727508545 22 53.3157894737 25.9088536617 122.0 19.0 53.3157894737 25.9088536617 1013 23526
0.000751855 3.752065420150757 23 51.0476190476 24.9007098588 115.0 20.0 51.0476190476 24.9007098588 1072 24598
0.000274135 3.901522159576416 24 48.6666666667 24.8583287438 126.0 16.0 48.6666666667 24.8583287438 1022 25620
0.000661582 4.053774118423462 25 51.2 18.0072207739 94.0 23.0 51.2 18.0072207739 1024 26644
0.000705907 4.208277940750122 26 61.3529411765 35.4084422909 172.0 23.0 61.3529411765 35.4084422909 1043 27687
0.000123014 4.381975173950195 27 67.375 31.9724002071 148.0 24.0 67.375 31.9724002071 1078 28765
0.000700861 4.540834426879883 28 55.5789473684 21.0145708585 113.0 32.0 55.5789473684 21.0145708585 1056 29821
0.000927114 4.694843530654907 29 64.125 34.1391911884 129.0 30.0 64.125 34.1391911884 1026 30847
0.00129522 4.850174188613892 30 60.6470588235 23.3034740568 115.0 29.0 60.6470588235 23.3034740568 1031 31878
0.000250355 5.000100135803223 31 63.1875 31.3313316626 141.0 32.0 63.1875 31.3313316626 1011 32889
0.000407415 5.152092218399048 32 64.625 20.8172854859 114.0 36.0 64.625 20.8172854859 1034 33923
0.000613602 5.32366156578064 33 66.8666666667 19.6837214187 96.0 18.0 66.8666666667 19.6837214187 1003 34926
0.000408163 5.47523832321167 34 57.1666666667 18.6137643217 85.0 20.0 57.1666666667 18.6137643217 1029 35955
0.000889479 5.637005090713501 35 62.5294117647 28.2595484062 131.0 27.0 62.5294117647 28.2595484062 1063 37018
0.000472612 5.800975322723389 36 65.4705882353 25.5874915375 119.0 36.0 65.4705882353 25.5874915375 1113 38131
0.000706941 5.950497150421143 37 71.8571428571 18.9241234666 100.0 34.0 71.8571428571 18.9241234666 1006 39137
0.00142736 6.105777740478516 38 59.4117647059 19.041931512 96.0 32.0 59.4117647059 19.041931512 1010 40147
0.000711303 6.260436773300171 39 67.0666666667 25.4413486714 124.0 27.0 67.0666666667 25.4413486714 1006 41153
0.000719528 6.420697212219238 40 72.2 31.8479722013 131.0 30.0 72.2 31.8479722013 1083 42236
0.00056165 6.586812973022461 41 67.1875 23.4713089484 133.0 37.0 67.1875 23.4713089484 1075 43311
0.000764537 6.753142356872559 42 73.5 34.5579223913 157.0 41.0 73.5 34.5579223913 1029 44340
0.000398017 6.920337915420532 43 65.5 18.5539753153 99.0 30.0 65.5 18.5539753153 1048 45388
0.000583856 7.070646047592163 44 71.9285714286 27.79122237 125.0 22.0 71.9285714286 27.79122237 1007 46395
-0.000239012 7.22806191444397 45 77.6923076923 35.7155097001 167.0 40.0 77.6923076923 35.7155097001 1010 47405
0.000352251 7.4071245193481445 46 73.7857142857 22.9290164621 108.0 38.0 73.7857142857 22.9290164621 1033 48438
0.000372937 7.559201955795288 47 78.0 16.0767390494 100.0 48.0 78.0 16.0767390494 1014 49452
0.000861595 7.708811521530151 48 67.5333333333 27.531476935 130.0 26.0 67.5333333333 27.531476935 1013 50465
0.000564077 7.865278959274292 49 85.5 22.4295192399 130.0 55.0 85.5 22.4295192399 1026 51491
0.00142504 8.054844379425049 50 79.8461538462 25.6000184911 131.0 41.0 79.8461538462 25.6000184911 1038 52529
0.00108914 8.237805366516113 51 96.0 38.323977778 200.0 47.0 96.0 38.323977778 1056 53585
0.0025319 8.393376588821411 52 72.5714285714 35.1236881518 188.0 39.0 72.5714285714 35.1236881518 1016 54601
0.00156362 8.55789303779602 53 80.4615384615 21.1718804245 136.0 50.0 80.4615384615 21.1718804245 1046 55647
0.00268342 8.719959497451782 54 90.0833333333 30.2061206086 132.0 25.0 90.0833333333 30.2061206086 1081 56728
0.00189988 8.900476217269897 55 102.545454545 51.0834675914 188.0 50.0 102.545454545 51.0834675914 1128 57856
0.00386416 9.07123064994812 56 89.1666666667 33.0475247014 149.0 48.0 89.1666666667 33.0475247014 1070 58926
0.00321337 9.252472400665283 57 116.8 39.6529948428 200.0 57.0 116.8 39.6529948428 1168 60094
0.00426169 9.422834634780884 58 124.555555556 48.3577205398 200.0 72.0 124.555555556 48.3577205398 1121 61215
0.0036183 9.585395097732544 59 117.222222222 35.9560774581 200.0 72.0 117.222222222 35.9560774581 1055 62270
0.0057707 9.74342656135559 60 152.285714286 37.1933722426 200.0 98.0 152.285714286 37.1933722426 1066 63336
0.00384757 9.921916246414185 61 147.0 31.3647891751 200.0 116.0 147.0 31.3647891751 1176 64512
0.000272295 10.096133708953857 62 149.125 43.3054196955 200.0 79.0 149.125 43.3054196955 1193 65705
6.44065e-05 10.25418210029602 63 150.857142857 53.5708571398 200.0 42.0 150.857142857 53.5708571398 1056 66761
0.000180196 10.408973455429077 64 173.666666667 33.7918464853 200.0 106.0 173.666666667 33.7918464853 1042 67803
0.00112128 10.567299365997314 65 172.666666667 39.1734036759 200.0 107.0 172.666666667 39.1734036759 1036 68839
0.00124025 10.74425220489502 66 148.625 42.5732824081 200.0 107.0 148.625 42.5732824081 1189 70028
-4.50667e-05 10.902202844619751 67 156.571428571 42.5469728413 200.0 87.0 156.571428571 42.5469728413 1096 71124
-1.21295e-05 11.054672718048096 68 146.0 48.0743471837 200.0 83.0 146.0 48.0743471837 1022 72146
-7.81985e-05 11.211773157119751 69 175.333333333 55.156343445 200.0 52.0 175.333333333 55.156343445 1052 73198
0.00029188 11.386259078979492 70 183.666666667 36.5224436325 200.0 102.0 183.666666667 36.5224436325 1102 74300
0.00143101 11.5547456741333 71 174.833333333 23.6461178397 200.0 145.0 174.833333333 23.6461178397 1049 75349
0.000600522 11.733030319213867 72 196.0 8.94427191 200.0 176.0 196.0 8.94427191 1176 76525
0.00262281 11.91745662689209 73 175.666666667 24.4722064573 200.0 147.0 175.666666667 24.4722064573 1054 77579
0.000710769 12.09386396408081 74 194.5 12.2983738762 200.0 167.0 194.5 12.2983738762 1167 78746
-3.54666e-05 12.273606061935425 75 193.666666667 14.1617638575 200.0 162.0 193.666666667 14.1617638575 1162 79908
0.000775296 12.462098836898804 76 200.0 0.0 200.0 200.0 200.0 0.0 1200 81108
-0.000219041 12.633396863937378 77 180.166666667 32.8147155337 200.0 111.0 180.166666667 32.8147155337 1081 82189
0.00136245 12.808267593383789 78 191.166666667 19.7519338012 200.0 147.0 191.166666667 19.7519338012 1147 83336
0.000382201 12.989602088928223 79 198.5 3.35410196625 200.0 191.0 198.5 3.35410196625 1191 84527
0.000266127 13.144181489944458 80 170.666666667 29.4316534062 200.0 138.0 170.666666667 29.4316534062 1024 85551
0.0013313 13.330495119094849 81 197.333333333 3.81517438075 200.0 191.0 197.333333333 3.81517438075 1184 86735
0.000171861 13.521204233169556 82 148.75 58.6637665003 200.0 24.0 148.75 58.6637665003 1190 87925
0.000645332 13.713515520095825 83 165.0 61.9146878489 200.0 18.0 165.0 61.9146878489 1155 89080
0.00121849 13.895610570907593 84 178.666666667 19.1543438647 200.0 143.0 178.666666667 19.1543438647 1072 90152
0.00115804 14.083674669265747 85 195.833333333 9.31694990625 200.0 175.0 195.833333333 9.31694990625 1175 91327
-7.05349e-05 14.266534090042114 86 198.666666667 2.98142397 200.0 192.0 198.666666667 2.98142397 1192 92519
0.00151709 14.43372654914856 87 179.333333333 16.6099033377 200.0 157.0 179.333333333 16.6099033377 1076 93595
0.00202253 14.598793029785156 88 186.333333333 30.5595956925 200.0 118.0 186.333333333 30.5595956925 1118 94713
0.00183562 14.773259401321411 89 193.5 12.433154601 200.0 166.0 193.5 12.433154601 1161 95874
-3.52808e-05 14.942201375961304 90 181.833333333 40.6219015912 200.0 91.0 181.833333333 40.6219015912 1091 96965
0.000959775 15.140976428985596 91 189.333333333 23.85139176 200.0 136.0 189.333333333 23.85139176 1136 98101
0.000608654 15.318247079849243 92 193.0 15.6524758425 200.0 158.0 193.0 15.6524758425 1158 99259
-0.000202594 15.497327089309692 93 194.833333333 11.5530178837 200.0 169.0 194.833333333 11.5530178837 1169 100428
-0.000302646 15.666409254074097 94 181.666666667 27.1579740694 200.0 131.0 181.666666667 27.1579740694 1090 101518
5.12111e-07 15.833762645721436 95 187.5 27.9508497187 200.0 125.0 187.5 27.9508497187 1125 102643
2.21608e-05 15.998656272888184 96 183.166666667 37.6404776212 200.0 99.0 183.166666667 37.6404776212 1099 103742
0.000655425 16.16669225692749 97 180.333333333 36.5224436325 200.0 100.0 180.333333333 36.5224436325 1082 104824
0.00018685 16.345892906188965 98 200.0 0.0 200.0 200.0 200.0 0.0 1200 106024
-2.79865e-05 16.504945516586304 99 178.0 49.193495505 200.0 68.0 178.0 49.193495505 1068 107092
================================================
FILE: hw2/data/sb_rtg_na_CartPole-v0_24-01-2018_09-08-49/11/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_rtg_na",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_rtg_na_CartPole-v0_24-01-2018_09-08-49/11",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 11,
"size" : 32}
================================================
FILE: hw2/data/sb_rtg_na_CartPole-v0_24-01-2018_09-08-49/21/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.00479425 0.2465076446533203 0 22.5777777778 8.99750308299 48.0 9.0 22.5777777778 8.99750308299 1016 1016
0.00603426 0.4021730422973633 1 25.15 14.7488135116 74.0 11.0 25.15 14.7488135116 1006 2022
0.0049098 0.5576772689819336 2 26.3421052632 14.8151350702 74.0 9.0 26.3421052632 14.8151350702 1001 3023
0.0045914 0.7074406147003174 3 25.825 17.7832610901 92.0 12.0 25.825 17.7832610901 1033 4056
0.00694537 0.8602461814880371 4 24.6829268293 13.0055129481 61.0 11.0 24.6829268293 13.0055129481 1012 5068
0.00774428 1.0108981132507324 5 27.1351351351 14.5883369968 79.0 10.0 27.1351351351 14.5883369968 1004 6072
0.00251003 1.1654856204986572 6 38.7037037037 20.0070632247 83.0 9.0 38.7037037037 20.0070632247 1045 7117
0.0051026 1.3125503063201904 7 34.5517241379 18.5446083007 89.0 12.0 34.5517241379 18.5446083007 1002 8119
0.00467114 1.4618966579437256 8 31.5 16.566155257 74.0 12.0 31.5 16.566155257 1008 9127
0.0016044 1.6141607761383057 9 43.0833333333 22.0886785984 99.0 18.0 43.0833333333 22.0886785984 1034 10161
0.00246593 1.7748239040374756 10 43.5416666667 21.9164686303 105.0 18.0 43.5416666667 21.9164686303 1045 11206
0.00147551 1.9324414730072021 11 37.0 22.2323157154 103.0 12.0 37.0 22.2323157154 1073 12279
0.00128036 2.08512020111084 12 42.0 29.3385412044 134.0 14.0 42.0 29.3385412044 1008 13287
0.00152306 2.240088701248169 13 52.3 33.9427459113 142.0 12.0 52.3 33.9427459113 1046 14333
0.0024662 2.3942222595214844 14 52.7 24.7832604796 96.0 14.0 52.7 24.7832604796 1054 15387
0.00287267 2.542656898498535 15 38.0 21.5148527508 89.0 13.0 38.0 21.5148527508 1026 16413
0.000645325 2.6992714405059814 16 51.75 21.2223349328 95.0 28.0 51.75 21.2223349328 1035 17448
0.00206066 2.8509788513183594 17 45.0 19.0422870384 84.0 14.0 45.0 19.0422870384 1035 18483
0.00161582 3.009176015853882 18 55.1578947368 35.8450806401 151.0 18.0 55.1578947368 35.8450806401 1048 19531
0.00213015 3.1567375659942627 19 51.05 18.4647637407 96.0 24.0 51.05 18.4647637407 1021 20552
0.00136999 3.314149856567383 20 60.3529411765 30.2906337231 123.0 21.0 60.3529411765 30.2906337231 1026 21578
0.0017231 3.467677354812622 21 57.0 29.458068127 126.0 15.0 57.0 29.458068127 1026 22604
0.00180968 3.6340725421905518 22 60.7777777778 27.7099171087 101.0 18.0 60.7777777778 27.7099171087 1094 23698
0.00121809 3.8184120655059814 23 64.0625 17.9703531894 92.0 29.0 64.0625 17.9703531894 1025 24723
0.00173285 3.9919352531433105 24 65.8125 24.3239047801 117.0 34.0 65.8125 24.3239047801 1053 25776
0.00137878 4.159661293029785 25 70.0 27.256803432 147.0 33.0 70.0 27.256803432 1050 26826
0.00297938 4.3123252391815186 26 73.1428571429 21.2967373184 104.0 37.0 73.1428571429 21.2967373184 1024 27850
0.00214699 4.465362071990967 27 79.6923076923 18.8532168868 124.0 56.0 79.6923076923 18.8532168868 1036 28886
0.00211714 4.622853517532349 28 79.2307692308 38.3348683339 200.0 32.0 79.2307692308 38.3348683339 1030 29916
0.000698995 4.775589227676392 29 81.3076923077 47.4201914401 200.0 22.0 81.3076923077 47.4201914401 1057 30973
0.00225569 4.925623655319214 30 92.5454545455 36.7531412049 188.0 47.0 92.5454545455 36.7531412049 1018 31991
0.00149778 5.07654333114624 31 112.0 55.403569881 200.0 17.0 112.0 55.403569881 1008 32999
0.00376229 5.230620622634888 32 128.0 53.4392178086 200.0 64.0 128.0 53.4392178086 1024 34023
0.00332601 5.384783983230591 33 114.333333333 48.3413786408 200.0 54.0 114.333333333 48.3413786408 1029 35052
0.00244591 5.5458784103393555 34 107.5 54.4779772018 180.0 24.0 107.5 54.4779772018 1075 36127
0.00554324 5.705430746078491 35 137.0 54.9727205075 200.0 13.0 137.0 54.9727205075 1096 37223
0.00202339 5.856726408004761 36 144.0 33.9579571992 200.0 100.0 144.0 33.9579571992 1008 38231
-0.000765222 6.024054288864136 37 165.0 37.0328039909 200.0 90.0 165.0 37.0328039909 1155 39386
0.000360166 6.192110538482666 38 146.0 65.6505902487 200.0 30.0 146.0 65.6505902487 1022 40408
-0.000193451 6.360998868942261 39 142.875 48.6452400035 200.0 86.0 142.875 48.6452400035 1143 41551
0.0005612 6.552560091018677 40 138.0 38.8104367407 200.0 100.0 138.0 38.8104367407 1104 42655
0.000289353 6.731957912445068 41 167.428571429 25.527895906 200.0 129.0 167.428571429 25.527895906 1172 43827
0.0013797 6.9623613357543945 42 134.75 47.6989255644 200.0 58.0 134.75 47.6989255644 1078 44905
0.000393599 7.183218240737915 43 167.857142857 33.476766235 200.0 98.0 167.857142857 33.476766235 1175 46080
0.000221649 7.373448371887207 44 155.857142857 52.8162003594 200.0 57.0 155.857142857 52.8162003594 1091 47171
0.00083138 7.5389323234558105 45 154.714285714 60.9208251649 200.0 45.0 154.714285714 60.9208251649 1083 48254
0.00054661 7.701229572296143 46 183.166666667 29.2712411004 200.0 120.0 183.166666667 29.2712411004 1099 49353
0.00132122 7.863469362258911 47 176.833333333 42.5692246686 200.0 83.0 176.833333333 42.5692246686 1061 50414
0.000166757 8.045456647872925 48 168.285714286 28.3484153536 200.0 122.0 168.285714286 28.3484153536 1178 51592
-0.000281752 8.213683128356934 49 186.5 20.4103731797 200.0 147.0 186.5 20.4103731797 1119 52711
0.00015159 8.384856462478638 50 190.166666667 21.9880017787 200.0 141.0 190.166666667 21.9880017787 1141 53852
0.000542396 8.55822467803955 51 186.0 19.9332218503 200.0 154.0 186.0 19.9332218503 1116 54968
0.000403405 8.737705945968628 52 200.0 0.0 200.0 200.0 200.0 0.0 1200 56168
0.000913747 8.901195287704468 53 179.333333333 46.212071535 200.0 76.0 179.333333333 46.212071535 1076 57244
0.00157027 9.075546503067017 54 193.333333333 9.5858692297 200.0 177.0 193.333333333 9.5858692297 1160 58404
0.000594884 9.266031503677368 55 200.0 0.0 200.0 200.0 200.0 0.0 1200 59604
-9.62671e-05 9.435145616531372 56 185.5 32.4229856737 200.0 113.0 185.5 32.4229856737 1113 60717
-0.000146272 9.608114242553711 57 189.0 24.5967477525 200.0 134.0 189.0 24.5967477525 1134 61851
0.000419399 9.766502618789673 58 174.0 27.0616579931 200.0 135.0 174.0 27.0616579931 1044 62895
0.000179654 9.93018388748169 59 179.833333333 27.8951409548 200.0 137.0 179.833333333 27.8951409548 1079 63974
0.000144515 10.103277444839478 60 190.666666667 20.86996779 200.0 144.0 190.666666667 20.86996779 1144 65118
6.94357e-05 10.282790184020996 61 200.0 0.0 200.0 200.0 200.0 0.0 1200 66318
6.16573e-05 10.46010422706604 62 200.0 0.0 200.0 200.0 200.0 0.0 1200 67518
0.0018175 10.636124610900879 63 194.166666667 13.0437298687 200.0 165.0 194.166666667 13.0437298687 1165 68683
0.000390317 10.804441213607788 64 195.5 10.0623058987 200.0 173.0 195.5 10.0623058987 1173 69856
0.000516 10.981313228607178 65 193.0 15.6524758425 200.0 158.0 193.0 15.6524758425 1158 71014
-0.000177296 11.145885229110718 66 185.5 20.5081284698 200.0 156.0 185.5 20.5081284698 1113 72127
0.000458768 11.327102899551392 67 200.0 0.0 200.0 200.0 200.0 0.0 1200 73327
0.000603623 11.502221822738647 68 195.833333333 8.45412456865 200.0 177.0 195.833333333 8.45412456865 1175 74502
-0.000338446 11.653526306152344 69 173.333333333 30.263656238 200.0 120.0 173.333333333 30.263656238 1040 75542
0.000371282 11.821753978729248 70 184.0 24.0277617213 200.0 138.0 184.0 24.0277617213 1104 76646
0.000513126 11.996490001678467 71 192.5 16.7705098312 200.0 155.0 192.5 16.7705098312 1155 77801
0.00020868 12.16333532333374 72 191.166666667 19.7519338012 200.0 147.0 191.166666667 19.7519338012 1147 78948
0.000193005 12.346053123474121 73 200.0 0.0 200.0 200.0 200.0 0.0 1200 80148
0.000223165 12.513463735580444 74 189.833333333 14.8595274338 200.0 163.0 189.833333333 14.8595274338 1139 81287
0.000202307 12.692771911621094 75 200.0 0.0 200.0 200.0 200.0 0.0 1200 82487
0.000254435 12.866792678833008 76 191.666666667 18.6338998125 200.0 150.0 191.666666667 18.6338998125 1150 83637
-4.42322e-05 13.042473077774048 77 185.0 33.5410196625 200.0 110.0 185.0 33.5410196625 1110 84747
0.00066874 13.207813262939453 78 186.0 30.859898466 200.0 117.0 186.0 30.859898466 1116 85863
1.64099e-06 13.38991641998291 79 195.833333333 9.31694990625 200.0 175.0 195.833333333 9.31694990625 1175 87038
0.000611797 13.563647985458374 80 193.5 14.5344418537 200.0 161.0 193.5 14.5344418537 1161 88199
0.000605094 13.746007442474365 81 200.0 0.0 200.0 200.0 200.0 0.0 1200 89399
0.000126553 13.926521301269531 82 200.0 0.0 200.0 200.0 200.0 0.0 1200 90599
0.00264337 14.095755815505981 83 185.0 33.5410196625 200.0 110.0 185.0 33.5410196625 1110 91709
-0.000520775 14.263795614242554 84 193.333333333 13.6096371084 200.0 163.0 193.333333333 13.6096371084 1160 92869
0.00155796 14.417569398880005 85 169.0 45.0555213043 200.0 89.0 169.0 45.0555213043 1014 93883
0.000919782 14.593942642211914 86 200.0 0.0 200.0 200.0 200.0 0.0 1200 95083
-8.14223e-05 14.770110368728638 87 196.333333333 8.1989159175 200.0 178.0 196.333333333 8.1989159175 1178 96261
0.00130043 14.951037168502808 88 195.0 11.1803398875 200.0 170.0 195.0 11.1803398875 1170 97431
-0.00013279 15.12278151512146 89 188.666666667 15.9547972584 200.0 154.0 188.666666667 15.9547972584 1132 98563
-7.54719e-05 15.287960052490234 90 186.5 23.0922064775 200.0 137.0 186.5 23.0922064775 1119 99682
0.000157872 15.456940174102783 91 184.5 27.0662766803 200.0 126.0 184.5 27.0662766803 1107 100789
0.000106156 15.633591413497925 92 197.0 5.85946527708 200.0 184.0 197.0 5.85946527708 1182 101971
-4.71212e-05 15.803099155426025 93 191.0 15.0775771705 200.0 159.0 191.0 15.0775771705 1146 103117
0.000147618 15.95608139038086 94 172.666666667 28.0337098667 200.0 129.0 172.666666667 28.0337098667 1036 104153
4.80965e-05 16.12983775138855 95 187.166666667 14.1234635349 200.0 167.0 187.166666667 14.1234635349 1123 105276
0.000319117 16.29371976852417 96 179.666666667 29.0382888997 200.0 132.0 179.666666667 29.0382888997 1078 106354
0.000672913 16.47292947769165 97 168.857142857 50.2178925752 200.0 49.0 168.857142857 50.2178925752 1182 107536
0.00106766 16.636366605758667 98 188.333333333 11.685698762 200.0 176.0 188.333333333 11.685698762 1130 108666
8.35868e-05 16.821049451828003 99 200.0 0.0 200.0 200.0 200.0 0.0 1200 109866
================================================
FILE: hw2/data/sb_rtg_na_CartPole-v0_24-01-2018_09-08-49/21/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_rtg_na",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_rtg_na_CartPole-v0_24-01-2018_09-08-49/21",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 21,
"size" : 32}
================================================
FILE: hw2/data/sb_rtg_na_CartPole-v0_24-01-2018_09-08-49/31/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.00883745 0.25073981285095215 0 20.7142857143 8.96933551562 49.0 10.0 20.7142857143 8.96933551562 1015 1015
0.00567042 0.4047391414642334 1 24.512195122 12.5933043596 67.0 10.0 24.512195122 12.5933043596 1005 2020
0.00800618 0.5561871528625488 2 22.8863636364 12.0947319657 58.0 9.0 22.8863636364 12.0947319657 1007 3027
0.00431195 0.701714038848877 3 31.5625 20.6487552591 114.0 12.0 31.5625 20.6487552591 1010 4037
0.00539121 0.8594069480895996 4 30.5142857143 18.5724395329 105.0 12.0 30.5142857143 18.5724395329 1068 5105
0.00382969 1.01590895652771 5 29.4285714286 14.6585630056 69.0 11.0 29.4285714286 14.6585630056 1030 6135
0.00293124 1.1703221797943115 6 40.72 18.2855571422 99.0 11.0 40.72 18.2855571422 1018 7153
0.00262484 1.3224537372589111 7 39.3461538462 21.1695396333 103.0 10.0 39.3461538462 21.1695396333 1023 8176
0.00393221 1.4741873741149902 8 42.0833333333 20.2359347586 85.0 13.0 42.0833333333 20.2359347586 1010 9186
0.00342541 1.6281874179840088 9 36.5357142857 24.4372112959 122.0 13.0 36.5357142857 24.4372112959 1023 10209
0.00198307 1.7805883884429932 10 49.2380952381 24.6748469613 111.0 18.0 49.2380952381 24.6748469613 1034 11243
0.00333155 1.9339792728424072 11 50.5 32.3504250358 124.0 15.0 50.5 32.3504250358 1010 12253
0.0037829 2.089681625366211 12 54.3684210526 32.5935261998 160.0 14.0 54.3684210526 32.5935261998 1033 13286
0.000479399 2.2435524463653564 13 70.1333333333 50.3942677516 200.0 24.0 70.1333333333 50.3942677516 1052 14338
0.0012425 2.396660804748535 14 55.7222222222 22.7664606032 100.0 22.0 55.7222222222 22.7664606032 1003 15341
0.00261868 2.551055669784546 15 55.3157894737 26.6498792958 101.0 17.0 55.3157894737 26.6498792958 1051 16392
0.00239219 2.7057573795318604 16 53.6315789474 22.3446932975 104.0 16.0 53.6315789474 22.3446932975 1019 17411
0.00159679 2.8612937927246094 17 61.7647058824 31.4091208405 150.0 14.0 61.7647058824 31.4091208405 1050 18461
0.00218652 3.0354888439178467 18 70.0625 29.3821135004 136.0 22.0 70.0625 29.3821135004 1121 19582
0.000335442 3.1907660961151123 19 68.8666666667 34.9396940774 182.0 34.0 68.8666666667 34.9396940774 1033 20615
0.00184033 3.3528733253479004 20 63.2352941176 23.5135240478 98.0 19.0 63.2352941176 23.5135240478 1075 21690
0.000629821 3.5001630783081055 21 91.3636363636 37.4755016396 189.0 50.0 91.3636363636 37.4755016396 1005 22695
0.00225155 3.6703391075134277 22 71.8666666667 43.3787454355 177.0 17.0 71.8666666667 43.3787454355 1078 23773
0.00166228 3.8171329498291016 23 77.9230769231 33.4053462752 154.0 43.0 77.9230769231 33.4053462752 1013 24786
0.00235418 3.980872869491577 24 99.7272727273 42.1643772721 200.0 39.0 99.7272727273 42.1643772721 1097 25883
0.0018419 4.1351470947265625 25 113.555555556 50.8988345449 200.0 49.0 113.555555556 50.8988345449 1022 26905
0.000151323 4.292297601699829 26 148.142857143 57.865431505 200.0 25.0 148.142857143 57.865431505 1037 27942
0.00311965 4.441494464874268 27 93.8181818182 44.9278576909 200.0 21.0 93.8181818182 44.9278576909 1032 28974
0.00139556 4.599090576171875 28 129.5 31.6662280671 200.0 86.0 129.5 31.6662280671 1036 30010
0.00116415 4.767218112945557 29 112.8 56.1066840938 200.0 36.0 112.8 56.1066840938 1128 31138
0.00147527 4.940382480621338 30 125.0 65.159633039 200.0 15.0 125.0 65.159633039 1125 32263
0.00184287 5.092169761657715 31 111.888888889 40.9076044124 184.0 45.0 111.888888889 40.9076044124 1007 33270
0.00165619 5.254024267196655 32 148.714285714 53.3658914228 200.0 40.0 148.714285714 53.3658914228 1041 34311
0.000249458 5.404348134994507 33 147.285714286 56.3096395851 200.0 31.0 147.285714286 56.3096395851 1031 35342
0.000490461 5.557968616485596 34 148.142857143 53.0913729108 200.0 61.0 148.142857143 53.0913729108 1037 36379
0.00118322 5.712055683135986 35 152.714285714 39.0044476794 200.0 97.0 152.714285714 39.0044476794 1069 37448
0.00226366 5.873911380767822 36 133.125 42.7446999639 200.0 78.0 133.125 42.7446999639 1065 38513
-2.25085e-05 6.033689737319946 37 172.833333333 40.7448019861 200.0 95.0 172.833333333 40.7448019861 1037 39550
-0.000233417 6.218158483505249 38 166.714285714 48.2396229721 200.0 69.0 166.714285714 48.2396229721 1167 40717
0.000430025 6.387474775314331 39 160.714285714 45.4586602961 200.0 103.0 160.714285714 45.4586602961 1125 41842
0.00012991 6.567670822143555 40 184.5 30.809901006 200.0 116.0 184.5 30.809901006 1107 42949
0.00019688 6.726837396621704 41 171.0 39.6400470905 200.0 101.0 171.0 39.6400470905 1026 43975
0.00101742 6.90242862701416 42 168.571428571 51.8978588682 200.0 62.0 168.571428571 51.8978588682 1180 45155
-6.14952e-06 7.059270620346069 43 147.857142857 34.4152315591 200.0 102.0 147.857142857 34.4152315591 1035 46190
0.000377995 7.239036321640015 44 193.333333333 14.90711985 200.0 160.0 193.333333333 14.90711985 1160 47350
9.65083e-06 7.400021314620972 45 155.571428571 51.6882333746 200.0 57.0 155.571428571 51.6882333746 1089 48439
0.000217166 7.5515666007995605 46 167.333333333 33.5741302527 200.0 125.0 167.333333333 33.5741302527 1004 49443
-4.93135e-07 7.735399484634399 47 200.0 0.0 200.0 200.0 200.0 0.0 1200 50643
0.000168743 7.888943672180176 48 171.5 33.2051702801 200.0 113.0 171.5 33.2051702801 1029 51672
0.000692509 8.065997838973999 49 170.142857143 57.1324990612 200.0 32.0 170.142857143 57.1324990612 1191 52863
0.00109534 8.219223737716675 50 169.666666667 40.2064118712 200.0 110.0 169.666666667 40.2064118712 1018 53881
5.50337e-05 8.369608640670776 51 168.333333333 49.1313432433 200.0 70.0 168.333333333 49.1313432433 1010 54891
0.000382894 8.545758485794067 52 193.5 8.63616427202 200.0 179.0 193.5 8.63616427202 1161 56052
0.000741006 8.709439039230347 53 180.666666667 20.0138840697 200.0 151.0 180.666666667 20.0138840697 1084 57136
0.00077139 8.910059690475464 54 200.0 0.0 200.0 200.0 200.0 0.0 1200 58336
0.000593724 9.073140382766724 55 185.666666667 16.6799946709 200.0 156.0 185.666666667 16.6799946709 1114 59450
0.00103941 9.242961168289185 56 178.5 31.5370152889 200.0 121.0 178.5 31.5370152889 1071 60521
0.000499595 9.419331073760986 57 170.571428571 49.0301864536 200.0 63.0 170.571428571 49.0301864536 1194 61715
-0.000319519 9.596462965011597 58 195.166666667 10.8076618912 200.0 171.0 195.166666667 10.8076618912 1171 62886
0.000159797 9.77476716041565 59 200.0 0.0 200.0 200.0 200.0 0.0 1200 64086
0.000134757 9.946938276290894 60 200.0 0.0 200.0 200.0 200.0 0.0 1200 65286
0.000267318 10.12351655960083 61 195.833333333 9.31694990625 200.0 175.0 195.833333333 9.31694990625 1175 66461
0.000243487 10.308374643325806 62 200.0 0.0 200.0 200.0 200.0 0.0 1200 67661
0.00111966 10.481060981750488 63 167.714285714 37.3887465335 200.0 103.0 167.714285714 37.3887465335 1174 68835
0.000226256 10.657294273376465 64 199.333333333 1.490711985 200.0 196.0 199.333333333 1.490711985 1196 70031
0.000300307 10.815518617630005 65 174.666666667 49.8352842427 200.0 64.0 174.666666667 49.8352842427 1048 71079
0.000124089 10.990320444107056 66 198.833333333 2.60874597375 200.0 193.0 198.833333333 2.60874597375 1193 72272
0.00032704 11.161742687225342 67 191.0 20.1246117975 200.0 146.0 191.0 20.1246117975 1146 73418
0.00033592 11.337126016616821 68 192.333333333 8.73053390247 200.0 178.0 192.333333333 8.73053390247 1154 74572
0.000381771 11.508223533630371 69 191.166666667 19.7519338012 200.0 147.0 191.166666667 19.7519338012 1147 75719
3.25248e-05 11.690587282180786 70 198.833333333 2.60874597375 200.0 193.0 198.833333333 2.60874597375 1193 76912
0.000167413 11.859943628311157 71 181.0 42.4852915725 200.0 86.0 181.0 42.4852915725 1086 77998
0.000505534 12.037244081497192 72 197.666666667 5.2174919475 200.0 186.0 197.666666667 5.2174919475 1186 79184
0.000369821 12.2175874710083 73 200.0 0.0 200.0 200.0 200.0 0.0 1200 80384
0.000419029 12.399224519729614 74 200.0 0.0 200.0 200.0 200.0 0.0 1200 81584
-0.000149769 12.577735424041748 75 199.666666667 0.7453559925 200.0 198.0 199.666666667 0.7453559925 1198 82782
0.00106761 12.767666101455688 76 193.166666667 10.1721296798 200.0 174.0 193.166666667 10.1721296798 1159 83941
-6.74673e-05 12.932788133621216 77 186.0 26.6895734948 200.0 127.0 186.0 26.6895734948 1116 85057
-2.04369e-05 13.114922285079956 78 198.833333333 2.60874597375 200.0 193.0 198.833333333 2.60874597375 1193 86250
-4.72278e-05 13.29336929321289 79 200.0 0.0 200.0 200.0 200.0 0.0 1200 87450
0.000523983 13.480352640151978 80 199.5 1.11803398875 200.0 197.0 199.5 1.11803398875 1197 88647
8.78274e-05 13.644331216812134 81 187.833333333 27.2054937262 200.0 127.0 187.833333333 27.2054937262 1127 89774
0.00043476 13.828377485275269 82 200.0 0.0 200.0 200.0 200.0 0.0 1200 90974
0.00020442 13.999136209487915 83 187.5 27.9508497187 200.0 125.0 187.5 27.9508497187 1125 92099
-0.000159319 14.180325984954834 84 200.0 0.0 200.0 200.0 200.0 0.0 1200 93299
0.000409597 14.356478214263916 85 200.0 0.0 200.0 200.0 200.0 0.0 1200 94499
0.000406532 14.537357091903687 86 200.0 0.0 200.0 200.0 200.0 0.0 1200 95699
2.37161e-06 14.704456090927124 87 184.166666667 35.4044096437 200.0 105.0 184.166666667 35.4044096437 1105 96804
0.000192624 14.894426584243774 88 200.0 0.0 200.0 200.0 200.0 0.0 1200 98004
0.000508273 15.06406021118164 89 190.333333333 12.7888840622 200.0 166.0 190.333333333 12.7888840622 1142 99146
0.000391994 15.232478857040405 90 190.166666667 14.7469394188 200.0 162.0 190.166666667 14.7469394188 1141 100287
0.000145826 15.406529903411865 91 192.166666667 17.5158658237 200.0 153.0 192.166666667 17.5158658237 1153 101440
0.000291496 15.579617738723755 92 191.833333333 18.2612218162 200.0 151.0 191.833333333 18.2612218162 1151 102591
-9.35062e-05 15.758772850036621 93 200.0 0.0 200.0 200.0 200.0 0.0 1200 103791
8.22428e-06 15.941427946090698 94 200.0 0.0 200.0 200.0 200.0 0.0 1200 104991
0.00206869 16.122079849243164 95 200.0 0.0 200.0 200.0 200.0 0.0 1200 106191
5.20216e-05 16.302594900131226 96 200.0 0.0 200.0 200.0 200.0 0.0 1200 107391
0.00101099 16.473968744277954 97 191.5 19.0065778087 200.0 149.0 191.5 19.0065778087 1149 108540
0.00056951 16.630234241485596 98 171.833333333 62.9825813662 200.0 31.0 171.833333333 62.9825813662 1031 109571
-0.000353025 16.808606147766113 99 200.0 0.0 200.0 200.0 200.0 0.0 1200 110771
================================================
FILE: hw2/data/sb_rtg_na_CartPole-v0_24-01-2018_09-08-49/31/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_rtg_na",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_rtg_na_CartPole-v0_24-01-2018_09-08-49/31",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 31,
"size" : 32}
================================================
FILE: hw2/data/sb_rtg_na_CartPole-v0_24-01-2018_09-08-49/41/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.00462592 0.24625492095947266 0 23.2790697674 9.26690932496 51.0 10.0 23.2790697674 9.26690932496 1001 1001
0.00787634 0.407470703125 1 26.7368421053 15.3548967169 72.0 9.0 26.7368421053 15.3548967169 1016 2017
0.00793208 0.558539867401123 2 27.5135135135 13.9876811084 62.0 9.0 27.5135135135 13.9876811084 1018 3035
0.00431377 0.7302095890045166 3 36.8387096774 28.3868401748 164.0 12.0 36.8387096774 28.3868401748 1142 4177
0.00336948 0.8775625228881836 4 31.3636363636 17.955868766 98.0 11.0 31.3636363636 17.955868766 1035 5212
0.00361373 1.0323545932769775 5 46.5909090909 27.1170176205 102.0 15.0 46.5909090909 27.1170176205 1025 6237
0.00451844 1.1831212043762207 6 32.7741935484 15.2394007109 68.0 10.0 32.7741935484 15.2394007109 1016 7253
0.00237312 1.3375887870788574 7 38.037037037 23.2896121837 99.0 13.0 38.037037037 23.2896121837 1027 8280
0.00343542 1.4869275093078613 8 38.9230769231 25.571803999 109.0 11.0 38.9230769231 25.571803999 1012 9292
0.00279298 1.6423804759979248 9 43.652173913 19.1415975337 87.0 17.0 43.652173913 19.1415975337 1004 10296
0.00397197 1.7906444072723389 10 46.2727272727 23.4214001177 94.0 18.0 46.2727272727 23.4214001177 1018 11314
0.00116489 1.942472219467163 11 50.5 25.8311827062 134.0 23.0 50.5 25.8311827062 1010 12324
0.00114964 2.0967769622802734 12 57.5555555556 28.8274988745 109.0 21.0 57.5555555556 28.8274988745 1036 13360
0.00160355 2.2483808994293213 13 48.619047619 24.2790840623 116.0 21.0 48.619047619 24.2790840623 1021 14381
0.00118999 2.39593243598938 14 67.1333333333 33.6984008852 124.0 25.0 67.1333333333 33.6984008852 1007 15388
0.00159406 2.547797918319702 15 57.0555555556 26.0778156512 123.0 23.0 57.0555555556 26.0778156512 1027 16415
0.00105363 2.701261520385742 16 70.5333333333 36.7275857572 145.0 24.0 70.5333333333 36.7275857572 1058 17473
0.00129869 2.8617990016937256 17 56.3157894737 40.216588135 183.0 19.0 56.3157894737 40.216588135 1070 18543
0.00142006 3.0115365982055664 18 65.375 32.2739736475 140.0 18.0 65.375 32.2739736475 1046 19589
0.00183002 3.174706220626831 19 77.8571428571 34.5147114449 129.0 19.0 77.8571428571 34.5147114449 1090 20679
0.00125357 3.341658353805542 20 88.8461538462 41.2158411552 166.0 31.0 88.8461538462 41.2158411552 1155 21834
0.00194701 3.5047221183776855 21 107.2 36.1297661216 179.0 59.0 107.2 36.1297661216 1072 22906
0.00200745 3.6572628021240234 22 74.5714285714 48.7511381343 200.0 16.0 74.5714285714 48.7511381343 1044 23950
0.00229249 3.8179497718811035 23 96.9090909091 30.347845649 160.0 44.0 96.9090909091 30.347845649 1066 25016
0.000767032 3.9904606342315674 24 115.1 53.9619310255 199.0 30.0 115.1 53.9619310255 1151 26167
0.00265203 4.149593353271484 25 98.6363636364 41.326356827 200.0 52.0 98.6363636364 41.326356827 1085 27252
0.00200076 4.313106298446655 26 125.625 40.8379036558 195.0 53.0 125.625 40.8379036558 1005 28257
0.00167603 4.471167087554932 27 126.0 55.2697928348 198.0 31.0 126.0 55.2697928348 1008 29265
0.00220415 4.620725393295288 28 144.0 59.8307135651 200.0 27.0 144.0 59.8307135651 1008 30273
0.00132375 4.778595924377441 29 151.428571429 38.7698599535 200.0 66.0 151.428571429 38.7698599535 1060 31333
0.0015631 4.931822061538696 30 148.714285714 49.9191182549 200.0 43.0 148.714285714 49.9191182549 1041 32374
0.00202806 5.097517013549805 31 157.428571429 46.0181862896 200.0 57.0 157.428571429 46.0181862896 1102 33476
-0.000492523 5.26200270652771 32 139.5 59.6447818338 200.0 33.0 139.5 59.6447818338 1116 34592
-4.10242e-05 5.421496391296387 33 175.0 36.5422130328 200.0 109.0 175.0 36.5422130328 1050 35642
0.000413074 5.578633546829224 34 134.25 32.4798014156 200.0 101.0 134.25 32.4798014156 1074 36716
0.000496317 5.738692998886108 35 153.142857143 33.5108876611 200.0 118.0 153.142857143 33.5108876611 1072 37788
0.00048885 5.897671699523926 36 155.285714286 35.9988661953 200.0 114.0 155.285714286 35.9988661953 1087 38875
0.000493216 6.066619396209717 37 159.857142857 38.4129017442 200.0 98.0 159.857142857 38.4129017442 1119 39994
0.000544152 6.231752395629883 38 163.142857143 39.9014091102 200.0 88.0 163.142857143 39.9014091102 1142 41136
0.00157175 6.404597043991089 39 165.285714286 60.0825962101 200.0 20.0 165.285714286 60.0825962101 1157 42293
0.000882061 6.566243410110474 40 179.5 22.7504578709 200.0 141.0 179.5 22.7504578709 1077 43370
-8.62782e-05 6.736226320266724 41 157.714285714 42.6772414616 200.0 71.0 157.714285714 42.6772414616 1104 44474
0.000741813 6.899214267730713 42 182.166666667 30.4325301099 200.0 117.0 182.166666667 30.4325301099 1093 45567
0.000105388 7.063089609146118 43 182.666666667 13.8764388643 200.0 165.0 182.666666667 13.8764388643 1096 46663
0.000545511 7.231231212615967 44 163.0 50.0685244725 200.0 59.0 163.0 50.0685244725 1141 47804
0.000336857 7.405108451843262 45 190.0 14.4337567297 200.0 165.0 190.0 14.4337567297 1140 48944
0.00088921 7.557142496109009 46 169.166666667 29.1457067546 200.0 118.0 169.166666667 29.1457067546 1015 49959
0.000169512 7.710595369338989 47 173.333333333 46.1254328495 200.0 74.0 173.333333333 46.1254328495 1040 50999
0.000709097 7.8576390743255615 48 168.333333333 55.661676423 200.0 46.0 168.333333333 55.661676423 1010 52009
0.000673859 8.033063650131226 49 167.142857143 26.7284149037 200.0 117.0 167.142857143 26.7284149037 1170 53179
0.00134893 8.197030067443848 50 185.666666667 26.6624996744 200.0 127.0 185.666666667 26.6624996744 1114 54293
0.000626116 8.356498718261719 51 176.333333333 37.1019616133 200.0 95.0 176.333333333 37.1019616133 1058 55351
0.000449105 8.507216691970825 52 172.333333333 45.1429827203 200.0 78.0 172.333333333 45.1429827203 1034 56385
0.000696128 8.67772102355957 53 186.166666667 30.9322736887 200.0 117.0 186.166666667 30.9322736887 1117 57502
-0.000152225 8.848429441452026 54 195.166666667 10.8076618912 200.0 171.0 195.166666667 10.8076618912 1171 58673
-0.000407575 9.020382165908813 55 187.666666667 18.767584347 200.0 151.0 187.666666667 18.767584347 1126 59799
0.000463196 9.18047571182251 56 180.666666667 27.0287912337 200.0 124.0 180.666666667 27.0287912337 1084 60883
0.000330883 9.362079858779907 57 169.285714286 38.0026851898 200.0 108.0 169.285714286 38.0026851898 1185 62068
0.000423431 9.529696464538574 58 128.888888889 55.8817092804 200.0 50.0 128.888888889 55.8817092804 1160 63228
0.00166657 9.705957651138306 59 191.833333333 16.955005816 200.0 154.0 191.833333333 16.955005816 1151 64379
0.000157177 9.883155345916748 60 194.0 9.16515138991 200.0 176.0 194.0 9.16515138991 1164 65543
0.000563943 10.061413288116455 61 189.5 23.4787137637 200.0 137.0 189.5 23.4787137637 1137 66680
0.00110061 10.218953609466553 62 175.333333333 34.960294939 200.0 122.0 175.333333333 34.960294939 1052 67732
-5.78072e-05 10.381412506103516 63 178.833333333 33.273696652 200.0 108.0 178.833333333 33.273696652 1073 68805
0.00104657 10.534621238708496 64 175.5 50.443863188 200.0 63.0 175.5 50.443863188 1053 69858
-9.0553e-05 10.714291095733643 65 167.714285714 33.3668538939 200.0 108.0 167.714285714 33.3668538939 1174 71032
1.98078e-05 10.861799240112305 66 169.0 31.4006369362 200.0 114.0 169.0 31.4006369362 1014 72046
0.000379285 11.040544033050537 67 168.0 51.6443884381 200.0 58.0 168.0 51.6443884381 1176 73222
0.000231508 11.202308654785156 68 182.833333333 18.9773256517 200.0 152.0 182.833333333 18.9773256517 1097 74319
0.000843979 11.37189269065857 69 158.857142857 40.9648928838 200.0 66.0 158.857142857 40.9648928838 1112 75431
-0.000150803 11.532339572906494 70 185.166666667 20.9794873362 200.0 155.0 185.166666667 20.9794873362 1111 76542
0.000560503 11.703953266143799 71 191.0 11.7189305542 200.0 167.0 191.0 11.7189305542 1146 77688
0.000163141 11.873148441314697 72 191.0 16.8027775482 200.0 154.0 191.0 16.8027775482 1146 78834
0.000653028 12.056387662887573 73 198.166666667 4.09945795875 200.0 189.0 198.166666667 4.09945795875 1189 80023
2.68543e-05 12.236918687820435 74 200.0 0.0 200.0 200.0 200.0 0.0 1200 81223
-0.000130831 12.415472984313965 75 197.333333333 5.52770798393 200.0 185.0 197.333333333 5.52770798393 1184 82407
0.000719839 12.58687448501587 76 189.5 23.4787137637 200.0 137.0 189.5 23.4787137637 1137 83544
0.000468175 12.763381958007812 77 198.5 3.35410196625 200.0 191.0 198.5 3.35410196625 1191 84735
0.000621873 12.936400413513184 78 199.333333333 1.490711985 200.0 196.0 199.333333333 1.490711985 1196 85931
-0.000127804 13.119216680526733 79 198.0 4.472135955 200.0 188.0 198.0 4.472135955 1188 87119
-0.000102415 13.29643702507019 80 200.0 0.0 200.0 200.0 200.0 0.0 1200 88319
0.00028918 13.47966456413269 81 200.0 0.0 200.0 200.0 200.0 0.0 1200 89519
0.000191501 13.651368618011475 82 191.5 19.0065778087 200.0 149.0 191.5 19.0065778087 1149 90668
0.000432948 13.835744142532349 83 200.0 0.0 200.0 200.0 200.0 0.0 1200 91868
-3.80499e-05 14.00757646560669 84 196.666666667 7.453559925 200.0 180.0 196.666666667 7.453559925 1180 93048
0.000663097 14.18881106376648 85 200.0 0.0 200.0 200.0 200.0 0.0 1200 94248
0.000220837 14.370300054550171 86 200.0 0.0 200.0 200.0 200.0 0.0 1200 95448
0.000462608 14.542062044143677 87 191.166666667 19.7519338012 200.0 147.0 191.166666667 19.7519338012 1147 96595
0.000183106 14.700886487960815 88 177.333333333 50.68420749 200.0 64.0 177.333333333 50.68420749 1064 97659
0.000165548 14.879271745681763 89 200.0 0.0 200.0 200.0 200.0 0.0 1200 98859
0.000112252 15.055887699127197 90 200.0 0.0 200.0 200.0 200.0 0.0 1200 100059
5.62079e-05 15.241909742355347 91 199.833333333 0.37267799625 200.0 199.0 199.833333333 0.37267799625 1199 101258
0.00020211 15.40045952796936 92 176.5 34.4177764147 200.0 114.0 176.5 34.4177764147 1059 102317
7.94427e-05 15.56316065788269 93 184.833333333 33.9136976587 200.0 109.0 184.833333333 33.9136976587 1109 103426
0.000286612 15.73482871055603 94 190.833333333 20.4972897937 200.0 145.0 190.833333333 20.4972897937 1145 104571
0.000190057 15.916443109512329 95 199.833333333 0.37267799625 200.0 199.0 199.833333333 0.37267799625 1199 105770
0.00103444 16.070422649383545 96 170.666666667 65.59132734 200.0 24.0 170.666666667 65.59132734 1024 106794
0.000210208 16.236408233642578 97 188.5 25.7147817412 200.0 131.0 188.5 25.7147817412 1131 107925
0.000108399 16.413623332977295 98 200.0 0.0 200.0 200.0 200.0 0.0 1200 109125
0.000537398 16.593384265899658 99 200.0 0.0 200.0 200.0 200.0 0.0 1200 110325
================================================
FILE: hw2/data/sb_rtg_na_CartPole-v0_24-01-2018_09-08-49/41/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_rtg_na",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_rtg_na_CartPole-v0_24-01-2018_09-08-49/41",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 1,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 41,
"size" : 32}
================================================
FILE: hw2/data/sb_rtg_na_l2_CartPole-v0_25-01-2018_09-22-07/1/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0297411 0.2738494873046875 0 20.4285714286 10.1075845436 53.0 8.0 20.4285714286 10.1075845436 1001 1001
0.0233106 0.43636584281921387 1 26.1538461538 12.7973123411 80.0 12.0 26.1538461538 12.7973123411 1020 2021
0.0130501 0.5960464477539062 2 32.1875 21.285907163 115.0 11.0 32.1875 21.285907163 1030 3051
0.00747302 0.7620019912719727 3 36.5172413793 18.5706863737 89.0 14.0 36.5172413793 18.5706863737 1059 4110
0.00767283 0.9182331562042236 4 42.125 23.3064949817 125.0 14.0 42.125 23.3064949817 1011 5121
0.0013497 1.079437255859375 5 46.5 21.9083836174 112.0 20.0 46.5 21.9083836174 1023 6144
0.00425325 1.255228042602539 6 51.8 25.4982352331 110.0 22.0 51.8 25.4982352331 1036 7180
0.00594851 1.4100420475006104 7 49.3333333333 23.9768406778 120.0 18.0 49.3333333333 23.9768406778 1036 8216
0.00215361 1.567640781402588 8 57.6666666667 21.6974140804 92.0 26.0 57.6666666667 21.6974140804 1038 9254
0.00557929 1.7271664142608643 9 57.6666666667 20.499322482 114.0 31.0 57.6666666667 20.499322482 1038 10292
0.00471706 1.8895316123962402 10 72.7142857143 22.3652427135 126.0 37.0 72.7142857143 22.3652427135 1018 11310
0.00344061 2.0572469234466553 11 85.5 37.2211857235 187.0 43.0 85.5 37.2211857235 1026 12336
0.00308227 2.22798228263855 12 73.8571428571 26.1366112757 147.0 44.0 73.8571428571 26.1366112757 1034 13370
0.00317727 2.3944168090820312 13 102.9 46.9881900056 196.0 35.0 102.9 46.9881900056 1029 14399
0.0061744 2.573777675628662 14 121.777777778 38.6717748861 181.0 73.0 121.777777778 38.6717748861 1096 15495
0.00462804 2.749849319458008 15 130.375 48.7645811527 200.0 57.0 130.375 48.7645811527 1043 16538
0.00715565 2.9197428226470947 16 153.571428571 31.5814463744 200.0 97.0 153.571428571 31.5814463744 1075 17613
-0.000599818 3.0959291458129883 17 149.428571429 34.6404270134 200.0 116.0 149.428571429 34.6404270134 1046 18659
0.00117321 3.2602367401123047 18 134.625 35.5982355602 200.0 90.0 134.625 35.5982355602 1077 19736
0.000237366 3.432468891143799 19 128.0 24.2641711171 164.0 87.0 128.0 24.2641711171 1024 20760
0.000571055 3.6008458137512207 20 156.0 24.2310308725 200.0 120.0 156.0 24.2310308725 1092 21852
0.00220436 3.7624785900115967 21 130.125 23.9710111385 178.0 100.0 130.125 23.9710111385 1041 22893
0.0010067 3.917999744415283 22 149.857142857 31.2109347662 200.0 115.0 149.857142857 31.2109347662 1049 23942
0.0007073 4.079175233840942 23 151.714285714 30.1979861472 199.0 104.0 151.714285714 30.1979861472 1062 25004
0.000905318 4.247323513031006 24 179.5 33.920249606 200.0 108.0 179.5 33.920249606 1077 26081
0.000582449 4.423315763473511 25 185.0 25.9871763247 200.0 129.0 185.0 25.9871763247 1110 27191
0.000999221 4.615762233734131 26 194.166666667 8.37489635093 200.0 180.0 194.166666667 8.37489635093 1165 28356
0.0025611 4.792246580123901 27 186.5 25.5848262322 200.0 130.0 186.5 25.5848262322 1119 29475
-0.000209701 4.958414077758789 28 170.333333333 38.4476556141 200.0 93.0 170.333333333 38.4476556141 1022 30497
0.00274517 5.131874322891235 29 158.142857143 41.5706921879 200.0 86.0 158.142857143 41.5706921879 1107 31604
0.00270655 5.307544708251953 30 184.833333333 21.011240378 200.0 139.0 184.833333333 21.011240378 1109 32713
0.00541658 5.487026929855347 31 190.166666667 10.5580406431 200.0 173.0 190.166666667 10.5580406431 1141 33854
0.00907868 5.656525611877441 32 184.833333333 29.6671348278 200.0 119.0 184.833333333 29.6671348278 1109 34963
0.00186763 5.84074854850769 33 197.166666667 6.33552593625 200.0 183.0 197.166666667 6.33552593625 1183 36146
-0.000414998 6.017326831817627 34 176.333333333 34.1792659696 200.0 117.0 176.333333333 34.1792659696 1058 37204
0.00200507 6.205365896224976 35 190.0 22.360679775 200.0 140.0 190.0 22.360679775 1140 38344
0.00369556 6.390219449996948 36 188.166666667 26.0154868406 200.0 130.0 188.166666667 26.0154868406 1129 39473
0.00344653 6.5546183586120605 37 154.285714286 27.6132177755 200.0 120.0 154.285714286 27.6132177755 1080 40553
0.00652507 6.742540597915649 38 168.428571429 32.6490303634 200.0 119.0 168.428571429 32.6490303634 1179 41732
-0.000310714 6.9120166301727295 39 176.5 30.5709557151 200.0 131.0 176.5 30.5709557151 1059 42791
-0.000290758 7.088715553283691 40 159.714285714 31.6350361183 200.0 119.0 159.714285714 31.6350361183 1118 43909
0.00069542 7.246915578842163 41 143.142857143 21.4637805978 184.0 121.0 143.142857143 21.4637805978 1002 44911
0.00143981 7.410435199737549 42 169.333333333 40.0236041467 200.0 93.0 169.333333333 40.0236041467 1016 45927
0.000587553 7.589028358459473 43 156.571428571 26.4026900299 200.0 124.0 156.571428571 26.4026900299 1096 47023
0.000443079 7.7635886669158936 44 180.166666667 27.7213315377 200.0 139.0 180.166666667 27.7213315377 1081 48104
0.000448407 7.929457426071167 45 167.333333333 38.3912605796 200.0 114.0 167.333333333 38.3912605796 1004 49108
0.00187229 8.104476690292358 46 184.0 19.4164878389 200.0 157.0 184.0 19.4164878389 1104 50212
0.00297906 8.276952981948853 47 178.666666667 20.2374789822 200.0 149.0 178.666666667 20.2374789822 1072 51284
0.0123869 8.446804285049438 48 184.333333333 13.2999582288 200.0 167.0 184.333333333 13.2999582288 1106 52390
-0.000504829 8.626853227615356 49 198.666666667 2.98142397 200.0 192.0 198.666666667 2.98142397 1192 53582
0.00131158 8.788495540618896 50 172.5 28.2001773044 200.0 136.0 172.5 28.2001773044 1035 54617
0.00331342 8.96923017501831 51 168.428571429 26.6718532371 200.0 131.0 168.428571429 26.6718532371 1179 55796
-5.86174e-05 9.137726306915283 52 178.666666667 18.7053171288 200.0 151.0 178.666666667 18.7053171288 1072 56868
0.00314124 9.302778482437134 53 156.857142857 20.7118225136 200.0 135.0 156.857142857 20.7118225136 1098 57966
-0.000242811 9.485538005828857 54 168.428571429 31.6311652053 200.0 125.0 168.428571429 31.6311652053 1179 59145
1.00834e-05 9.647492170333862 55 146.0 48.1693441339 200.0 88.0 146.0 48.1693441339 1022 60167
0.000583058 9.82451844215393 56 157.571428571 31.9054726289 200.0 115.0 157.571428571 31.9054726289 1103 61270
0.00202361 9.98776626586914 57 152.285714286 31.3902363606 200.0 120.0 152.285714286 31.3902363606 1066 62336
-0.000194807 10.15540075302124 58 130.5 25.3179778023 182.0 99.0 130.5 25.3179778023 1044 63380
0.00493132 10.325190782546997 59 156.714285714 24.7773761191 200.0 120.0 156.714285714 24.7773761191 1097 64477
0.00158266 10.488326787948608 60 152.428571429 36.4568517678 200.0 108.0 152.428571429 36.4568517678 1067 65544
0.000867297 10.665531635284424 61 164.0 34.0210019169 200.0 106.0 164.0 34.0210019169 1148 66692
0.000391759 10.847568273544312 62 162.857142857 30.9581679572 200.0 120.0 162.857142857 30.9581679572 1140 67832
0.00214971 11.032941102981567 63 169.285714286 21.3789902589 200.0 128.0 169.285714286 21.3789902589 1185 69017
0.00594357 11.193595170974731 64 149.142857143 29.6524080999 200.0 121.0 149.142857143 29.6524080999 1044 70061
0.0137683 11.357276916503906 65 150.285714286 41.9173141374 200.0 98.0 150.285714286 41.9173141374 1052 71113
0.00729149 11.527208089828491 66 177.833333333 21.7747305124 200.0 140.0 177.833333333 21.7747305124 1067 72180
-0.000150345 11.703615427017212 67 163.142857143 15.1320716307 185.0 135.0 163.142857143 15.1320716307 1142 73322
0.00729428 11.898504495620728 68 167.142857143 16.3918845027 193.0 142.0 167.142857143 16.3918845027 1170 74492
0.00262323 12.058084487915039 69 174.333333333 19.1630431357 200.0 143.0 174.333333333 19.1630431357 1046 75538
0.00113076 12.24113917350769 70 198.0 4.472135955 200.0 188.0 198.0 4.472135955 1188 76726
0.00162139 12.42531967163086 71 193.166666667 11.4078433058 200.0 169.0 193.166666667 11.4078433058 1159 77885
0.00512113 12.615572690963745 72 200.0 0.0 200.0 200.0 200.0 0.0 1200 79085
0.000964399 12.804637908935547 73 200.0 0.0 200.0 200.0 200.0 0.0 1200 80285
0.000440324 12.989214181900024 74 200.0 0.0 200.0 200.0 200.0 0.0 1200 81485
4.79524e-05 13.178807735443115 75 200.0 0.0 200.0 200.0 200.0 0.0 1200 82685
-0.000605541 13.369292736053467 76 200.0 0.0 200.0 200.0 200.0 0.0 1200 83885
0.000264856 13.560556173324585 77 200.0 0.0 200.0 200.0 200.0 0.0 1200 85085
0.000415674 13.754238843917847 78 197.5 3.5472994423 200.0 192.0 197.5 3.5472994423 1185 86270
0.00197249 13.963247537612915 79 200.0 0.0 200.0 200.0 200.0 0.0 1200 87470
0.00327826 14.182824850082397 80 200.0 0.0 200.0 200.0 200.0 0.0 1200 88670
0.00175992 14.447917461395264 81 200.0 0.0 200.0 200.0 200.0 0.0 1200 89870
-0.000596587 14.699072122573853 82 200.0 0.0 200.0 200.0 200.0 0.0 1200 91070
8.64299e-05 14.901156902313232 83 200.0 0.0 200.0 200.0 200.0 0.0 1200 92270
-3.0349e-05 15.114067316055298 84 200.0 0.0 200.0 200.0 200.0 0.0 1200 93470
0.00054246 15.30038046836853 85 200.0 0.0 200.0 200.0 200.0 0.0 1200 94670
0.000567584 15.486225605010986 86 200.0 0.0 200.0 200.0 200.0 0.0 1200 95870
0.00199936 15.67517614364624 87 200.0 0.0 200.0 200.0 200.0 0.0 1200 97070
-0.000158963 15.865771770477295 88 200.0 0.0 200.0 200.0 200.0 0.0 1200 98270
0.00403164 16.053476572036743 89 200.0 0.0 200.0 200.0 200.0 0.0 1200 99470
-0.000303754 16.245378971099854 90 200.0 0.0 200.0 200.0 200.0 0.0 1200 100670
-0.000430025 16.43127989768982 91 200.0 0.0 200.0 200.0 200.0 0.0 1200 101870
0.000846631 16.621138095855713 92 200.0 0.0 200.0 200.0 200.0 0.0 1200 103070
-0.000367484 16.806685209274292 93 200.0 0.0 200.0 200.0 200.0 0.0 1200 104270
0.000590047 16.99510908126831 94 200.0 0.0 200.0 200.0 200.0 0.0 1200 105470
0.000378992 17.180333375930786 95 200.0 0.0 200.0 200.0 200.0 0.0 1200 106670
0.00138973 17.36830735206604 96 200.0 0.0 200.0 200.0 200.0 0.0 1200 107870
-0.000394467 17.553545713424683 97 200.0 0.0 200.0 200.0 200.0 0.0 1200 109070
0.00111275 17.73904585838318 98 200.0 0.0 200.0 200.0 200.0 0.0 1200 110270
0.00102996 17.920087099075317 99 200.0 0.0 200.0 200.0 200.0 0.0 1200 111470
================================================
FILE: hw2/data/sb_rtg_na_l2_CartPole-v0_25-01-2018_09-22-07/1/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_rtg_na_l2",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_rtg_na_l2_CartPole-v0_25-01-2018_09-22-07/1",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 2,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 1,
"size" : 32}
================================================
FILE: hw2/data/sb_rtg_na_l2_CartPole-v0_25-01-2018_09-22-07/11/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0206946 0.28758668899536133 0 26.0 15.4842469872 93.0 9.0 26.0 15.4842469872 1092 1092
0.025037 0.4448051452636719 1 23.9523809524 12.5013377969 66.0 11.0 23.9523809524 12.5013377969 1006 2098
0.00756227 0.6088206768035889 2 35.4 21.0754201223 128.0 15.0 35.4 21.0754201223 1062 3160
0.00795573 0.7621123790740967 3 44.347826087 21.8186372181 102.0 17.0 44.347826087 21.8186372181 1020 4180
0.00668644 0.917290449142456 4 51.25 18.4874957742 92.0 28.0 51.25 18.4874957742 1025 5205
0.00404803 1.0746409893035889 5 49.1428571429 22.756026338 112.0 19.0 49.1428571429 22.756026338 1032 6237
0.00454463 1.242227554321289 6 56.6315789474 26.2602571966 130.0 18.0 56.6315789474 26.2602571966 1076 7313
-0.000251715 1.402787685394287 7 67.8 25.7221046314 113.0 37.0 67.8 25.7221046314 1017 8330
0.00194431 1.5696744918823242 8 75.2142857143 39.6091233564 182.0 27.0 75.2142857143 39.6091233564 1053 9383
0.00310531 1.721327304840088 9 71.7142857143 31.0286240463 134.0 26.0 71.7142857143 31.0286240463 1004 10387
0.00640435 1.883497714996338 10 57.7222222222 22.8687208882 122.0 23.0 57.7222222222 22.8687208882 1039 11426
0.00307966 2.0428307056427 11 86.0 38.9957262616 178.0 39.0 86.0 38.9957262616 1032 12458
0.000601108 2.209526300430298 12 61.5294117647 18.0949055133 100.0 32.0 61.5294117647 18.0949055133 1046 13504
0.00305813 2.3702616691589355 13 68.3333333333 28.0134888144 151.0 39.0 68.3333333333 28.0134888144 1025 14529
0.00390114 2.533271074295044 14 80.5384615385 23.6630688712 128.0 45.0 80.5384615385 23.6630688712 1047 15576
0.000209407 2.691526174545288 15 81.3076923077 24.411172144 146.0 56.0 81.3076923077 24.411172144 1057 16633
0.00292887 2.874882459640503 16 102.727272727 31.6718714006 171.0 63.0 102.727272727 31.6718714006 1130 17763
0.00264235 3.044787883758545 17 77.5 29.5773803534 146.0 44.0 77.5 29.5773803534 1085 18848
0.00337922 3.2282650470733643 18 120.555555556 36.5942044929 170.0 70.0 120.555555556 36.5942044929 1085 19933
0.00181695 3.443718194961548 19 86.8333333333 28.0945823168 172.0 57.0 86.8333333333 28.0945823168 1042 20975
0.00244825 3.6462290287017822 20 102.5 36.8680078117 166.0 56.0 102.5 36.8680078117 1025 22000
0.00563196 3.829800844192505 21 106.3 36.5596772415 174.0 53.0 106.3 36.5596772415 1063 23063
0.0120955 4.011653900146484 22 108.1 28.539271189 154.0 76.0 108.1 28.539271189 1081 24144
0.0120318 4.184046983718872 23 137.25 44.6423285683 200.0 72.0 137.25 44.6423285683 1098 25242
0.00854782 4.379508972167969 24 158.0 37.9623874005 200.0 88.0 158.0 37.9623874005 1106 26348
0.0149991 4.560900449752808 25 184.333333333 19.8214249964 200.0 147.0 184.333333333 19.8214249964 1106 27454
0.00458817 4.7249133586883545 26 170.5 29.9930547516 200.0 125.0 170.5 29.9930547516 1023 28477
0.00374665 4.910247087478638 27 192.333333333 15.0185071014 200.0 159.0 192.333333333 15.0185071014 1154 29631
0.00945275 5.096621990203857 28 197.166666667 6.33552593625 200.0 183.0 197.166666667 6.33552593625 1183 30814
-0.00196516 5.292685031890869 29 196.0 6.11010092661 200.0 184.0 196.0 6.11010092661 1176 31990
0.00238036 5.481768846511841 30 184.333333333 29.9870342352 200.0 118.0 184.333333333 29.9870342352 1106 33096
-0.000125125 5.665477752685547 31 181.5 41.3672575837 200.0 89.0 181.5 41.3672575837 1089 34185
0.000143004 5.833615064620972 32 177.833333333 18.0685423381 200.0 154.0 177.833333333 18.0685423381 1067 35252
-0.000182613 6.011283874511719 33 188.166666667 19.5483730497 200.0 147.0 188.166666667 19.5483730497 1129 36381
0.000889485 6.190839767456055 34 200.0 0.0 200.0 200.0 200.0 0.0 1200 37581
0.000179464 6.37889552116394 35 198.0 4.472135955 200.0 188.0 198.0 4.472135955 1188 38769
0.00123013 6.543935775756836 36 178.333333333 30.3021818063 200.0 118.0 178.333333333 30.3021818063 1070 39839
0.000362356 6.722923517227173 37 196.666666667 6.59966329107 200.0 182.0 196.666666667 6.59966329107 1180 41019
0.00133589 6.900536060333252 38 191.833333333 18.2612218162 200.0 151.0 191.833333333 18.2612218162 1151 42170
0.00268704 7.079986572265625 39 189.333333333 11.5277443105 200.0 170.0 189.333333333 11.5277443105 1136 43306
0.00190272 7.260222673416138 40 200.0 0.0 200.0 200.0 200.0 0.0 1200 44506
0.00027918 7.444690942764282 41 199.666666667 0.7453559925 200.0 198.0 199.666666667 0.7453559925 1198 45704
-0.000139048 7.619645833969116 42 189.333333333 23.85139176 200.0 136.0 189.333333333 23.85139176 1136 46840
-0.000115809 7.807140827178955 43 200.0 0.0 200.0 200.0 200.0 0.0 1200 48040
0.00114991 7.9965620040893555 44 200.0 0.0 200.0 200.0 200.0 0.0 1200 49240
0.00319547 8.172533512115479 45 185.666666667 32.0503076775 200.0 114.0 185.666666667 32.0503076775 1114 50354
0.000316211 8.358727931976318 46 200.0 0.0 200.0 200.0 200.0 0.0 1200 51554
0.00229276 8.544351577758789 47 198.5 3.35410196625 200.0 191.0 198.5 3.35410196625 1191 52745
0.000491757 8.73495078086853 48 200.0 0.0 200.0 200.0 200.0 0.0 1200 53945
-0.000186199 8.921234369277954 49 196.666666667 7.453559925 200.0 180.0 196.666666667 7.453559925 1180 55125
0.000673436 9.093317985534668 50 185.0 21.9848432638 200.0 145.0 185.0 21.9848432638 1110 56235
0.00109387 9.272379398345947 51 190.5 21.2426457862 200.0 143.0 190.5 21.2426457862 1143 57378
0.00140656 9.4656400680542 52 198.833333333 2.60874597375 200.0 193.0 198.833333333 2.60874597375 1193 58571
0.00879694 9.649205684661865 53 191.166666667 12.889487534 200.0 168.0 191.166666667 12.889487534 1147 59718
0.00631824 9.823894023895264 54 189.666666667 23.1060357675 200.0 138.0 189.666666667 23.1060357675 1138 60856
0.00671234 10.003519058227539 55 193.5 12.8290035986 200.0 165.0 193.5 12.8290035986 1161 62017
0.00101014 10.176324367523193 56 186.333333333 25.5712512187 200.0 130.0 186.333333333 25.5712512187 1118 63135
0.00652815 10.346964836120605 57 188.0 16.4620776332 200.0 157.0 188.0 16.4620776332 1128 64263
0.0143417 10.503143310546875 58 168.5 21.7696271596 195.0 143.0 168.5 21.7696271596 1011 65274
0.0138818 10.67241096496582 59 187.833333333 17.742760652 200.0 156.0 187.833333333 17.742760652 1127 66401
0.00863017 10.834807634353638 60 144.857142857 29.3521893631 196.0 98.0 144.857142857 29.3521893631 1014 67415
-0.000210535 10.99759316444397 61 129.25 12.4172259382 154.0 111.0 129.25 12.4172259382 1034 68449
0.000982554 11.153739213943481 62 115.666666667 23.3713975239 158.0 87.0 115.666666667 23.3713975239 1041 69490
-4.29018e-05 11.314640045166016 63 145.428571429 33.9615629072 200.0 100.0 145.428571429 33.9615629072 1018 70508
0.00139728 11.477730751037598 64 153.285714286 26.911040144 200.0 123.0 153.285714286 26.911040144 1073 71581
0.00237733 11.643383026123047 65 152.714285714 24.574750606 200.0 119.0 152.714285714 24.574750606 1069 72650
0.00229348 11.816298961639404 66 161.571428571 41.0882574218 200.0 87.0 161.571428571 41.0882574218 1131 73781
0.00162105 11.987894535064697 67 180.166666667 14.2292734257 200.0 167.0 180.166666667 14.2292734257 1081 74862
0.00398309 12.151353359222412 68 174.833333333 23.6531651629 200.0 134.0 174.833333333 23.6531651629 1049 75911
0.00424945 12.332323789596558 69 193.833333333 10.3829454181 200.0 171.0 193.833333333 10.3829454181 1163 77074
0.00153808 12.511353731155396 70 186.833333333 17.8924254613 200.0 150.0 186.833333333 17.8924254613 1121 78195
0.00343174 12.69641900062561 71 197.0 3.36650164612 200.0 191.0 197.0 3.36650164612 1182 79377
0.000847099 12.88131046295166 72 200.0 0.0 200.0 200.0 200.0 0.0 1200 80577
0.00341371 13.070935726165771 73 195.666666667 8.41955396021 200.0 177.0 195.666666667 8.41955396021 1174 81751
0.00278472 13.257331132888794 74 194.5 12.2983738762 200.0 167.0 194.5 12.2983738762 1167 82918
0.00727875 13.447278022766113 75 194.166666667 8.29491142542 200.0 181.0 194.166666667 8.29491142542 1165 84083
0.0115109 13.626573324203491 76 191.666666667 10.482790129 200.0 176.0 191.666666667 10.482790129 1150 85233
-0.000123346 13.809036493301392 77 198.333333333 3.7267799625 200.0 190.0 198.333333333 3.7267799625 1190 86423
-0.00103103 14.001115083694458 78 200.0 0.0 200.0 200.0 200.0 0.0 1200 87623
0.00221476 14.185184955596924 79 200.0 0.0 200.0 200.0 200.0 0.0 1200 88823
0.000356326 14.366669416427612 80 197.833333333 4.84481395125 200.0 187.0 197.833333333 4.84481395125 1187 90010
-0.000329101 14.55838418006897 81 197.0 6.7082039325 200.0 182.0 197.0 6.7082039325 1182 91192
0.00131984 14.741335391998291 82 192.166666667 17.5158658237 200.0 153.0 192.166666667 17.5158658237 1153 92345
0.00137688 14.914815187454224 83 188.333333333 8.6922698736 200.0 177.0 188.333333333 8.6922698736 1130 93475
0.00248728 15.084624290466309 84 184.5 12.6852933221 200.0 165.0 184.5 12.6852933221 1107 94582
0.00267883 15.257422924041748 85 185.833333333 12.0611866009 200.0 166.0 185.833333333 12.0611866009 1115 95697
0.00116144 15.432630062103271 86 191.333333333 7.9092070118 200.0 179.0 191.333333333 7.9092070118 1148 96845
0.00739675 15.614603281021118 87 192.333333333 12.4186240068 200.0 165.0 192.333333333 12.4186240068 1154 97999
0.00128253 15.774771690368652 88 172.166666667 13.8734358478 185.0 143.0 172.166666667 13.8734358478 1033 99032
0.00396698 15.949145078659058 89 183.666666667 25.7983634279 200.0 128.0 183.666666667 25.7983634279 1102 100134
0.0118814 16.138906002044678 90 200.0 0.0 200.0 200.0 200.0 0.0 1200 101334
0.00130429 16.3238582611084 91 200.0 0.0 200.0 200.0 200.0 0.0 1200 102534
-0.000607658 16.511952877044678 92 200.0 0.0 200.0 200.0 200.0 0.0 1200 103734
0.00240771 16.694143056869507 93 200.0 0.0 200.0 200.0 200.0 0.0 1200 104934
0.00199033 16.888094186782837 94 200.0 0.0 200.0 200.0 200.0 0.0 1200 106134
0.000486695 17.07412314414978 95 200.0 0.0 200.0 200.0 200.0 0.0 1200 107334
-0.000315046 17.26404094696045 96 200.0 0.0 200.0 200.0 200.0 0.0 1200 108534
0.00053397 17.449957370758057 97 200.0 0.0 200.0 200.0 200.0 0.0 1200 109734
-0.000108815 17.635493755340576 98 200.0 0.0 200.0 200.0 200.0 0.0 1200 110934
-5.9722e-05 17.81979990005493 99 200.0 0.0 200.0 200.0 200.0 0.0 1200 112134
================================================
FILE: hw2/data/sb_rtg_na_l2_CartPole-v0_25-01-2018_09-22-07/11/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_rtg_na_l2",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_rtg_na_l2_CartPole-v0_25-01-2018_09-22-07/11",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 2,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 11,
"size" : 32}
================================================
FILE: hw2/data/sb_rtg_na_l2_CartPole-v0_25-01-2018_09-22-07/21/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0282026 0.28131937980651855 0 21.2978723404 10.2519637841 51.0 9.0 21.2978723404 10.2519637841 1001 1001
0.0149536 0.44125962257385254 1 26.1538461538 13.6561030999 74.0 10.0 26.1538461538 13.6561030999 1020 2021
0.00975196 0.5968029499053955 2 29.3428571429 16.8233559709 95.0 11.0 29.3428571429 16.8233559709 1027 3048
0.0117387 0.7545104026794434 3 36.0689655172 23.7471320003 93.0 11.0 36.0689655172 23.7471320003 1046 4094
0.00612505 0.9124977588653564 4 39.0 16.8317465614 80.0 14.0 39.0 16.8317465614 1014 5108
0.00755946 1.0748202800750732 5 52.2 32.9690764202 146.0 14.0 52.2 32.9690764202 1044 6152
0.00456019 1.236602783203125 6 52.35 23.1824826108 119.0 20.0 52.35 23.1824826108 1047 7199
0.00659087 1.39347243309021 7 53.2631578947 26.2434796017 101.0 14.0 53.2631578947 26.2434796017 1012 8211
0.00483758 1.5548596382141113 8 69.4 30.0528423503 121.0 23.0 69.4 30.0528423503 1041 9252
0.00442448 1.7206339836120605 9 67.0625 27.5464806055 124.0 24.0 67.0625 27.5464806055 1073 10325
0.00476142 1.887361764907837 10 88.5833333333 45.8683956796 189.0 26.0 88.5833333333 45.8683956796 1063 11388
0.00734609 2.0537869930267334 11 115.888888889 50.9039279088 199.0 43.0 115.888888889 50.9039279088 1043 12431
0.00376882 2.230933427810669 12 101.0 28.210249588 136.0 35.0 101.0 28.210249588 1111 13542
0.00391844 2.3996527194976807 13 114.4 40.2174091657 178.0 36.0 114.4 40.2174091657 1144 14686
0.000417117 2.5710103511810303 14 138.75 52.634945616 200.0 37.0 138.75 52.634945616 1110 15796
0.00186821 2.7520387172698975 15 109.6 27.1447969232 172.0 74.0 109.6 27.1447969232 1096 16892
0.00103666 2.9190480709075928 16 133.375 41.6741451622 200.0 92.0 133.375 41.6741451622 1067 17959
0.00088278 3.0840513706207275 17 128.125 29.8011639873 197.0 101.0 128.125 29.8011639873 1025 18984
0.00210262 3.251082420349121 18 150.857142857 48.0340015627 200.0 80.0 150.857142857 48.0340015627 1056 20040
0.00314462 3.412986993789673 19 146.142857143 35.0568052143 200.0 99.0 146.142857143 35.0568052143 1023 21063
0.00264375 3.592501163482666 20 165.714285714 36.6594921862 200.0 107.0 165.714285714 36.6594921862 1160 22223
0.00145894 3.7774670124053955 21 190.833333333 20.4972897937 200.0 145.0 190.833333333 20.4972897937 1145 23368
0.000345038 3.9517929553985596 22 184.333333333 16.7796172649 200.0 157.0 184.333333333 16.7796172649 1106 24474
0.00317835 4.138461112976074 23 194.5 12.2983738762 200.0 167.0 194.5 12.2983738762 1167 25641
0.00661078 4.314741849899292 24 181.166666667 20.1114947784 200.0 151.0 181.166666667 20.1114947784 1087 26728
0.000972615 4.4996209144592285 25 188.166666667 16.757253819 200.0 163.0 188.166666667 16.757253819 1129 27857
0.00122897 4.6795408725738525 26 189.166666667 18.676336781 200.0 149.0 189.166666667 18.676336781 1135 28992
-0.000497062 4.86600923538208 27 189.166666667 24.2240697562 200.0 135.0 189.166666667 24.2240697562 1135 30127
0.00640376 5.0448315143585205 28 163.571428571 32.5043168248 200.0 110.0 163.571428571 32.5043168248 1145 31272
-0.000923149 5.219114780426025 29 185.333333333 21.0290803941 200.0 150.0 185.333333333 21.0290803941 1112 32384
0.000252485 5.387106657028198 30 182.166666667 25.8096665784 200.0 137.0 182.166666667 25.8096665784 1093 33477
0.00260774 5.560362100601196 31 178.333333333 22.9685775693 200.0 145.0 178.333333333 22.9685775693 1070 34547
0.00171908 5.735253095626831 32 159.571428571 16.7831305002 181.0 127.0 159.571428571 16.7831305002 1117 35664
0.0086055 5.915650129318237 33 191.0 14.5028732785 200.0 160.0 191.0 14.5028732785 1146 36810
-0.000130461 6.093614101409912 34 187.5 17.6988700204 200.0 161.0 187.5 17.6988700204 1125 37935
0.00469952 6.283750534057617 35 200.0 0.0 200.0 200.0 200.0 0.0 1200 39135
0.000261916 6.466552257537842 36 196.833333333 7.08088192875 200.0 181.0 196.833333333 7.08088192875 1181 40316
0.00217476 6.649599552154541 37 200.0 0.0 200.0 200.0 200.0 0.0 1200 41516
0.000346309 6.83262825012207 38 200.0 0.0 200.0 200.0 200.0 0.0 1200 42716
-0.000619562 7.010689973831177 39 200.0 0.0 200.0 200.0 200.0 0.0 1200 43916
0.00216318 7.198332071304321 40 200.0 0.0 200.0 200.0 200.0 0.0 1200 45116
0.000567384 7.381340026855469 41 200.0 0.0 200.0 200.0 200.0 0.0 1200 46316
0.000485561 7.56649923324585 42 200.0 0.0 200.0 200.0 200.0 0.0 1200 47516
0.00109838 7.747800350189209 43 200.0 0.0 200.0 200.0 200.0 0.0 1200 48716
0.0024098 7.932310342788696 44 200.0 0.0 200.0 200.0 200.0 0.0 1200 49916
0.00271393 8.118601083755493 45 200.0 0.0 200.0 200.0 200.0 0.0 1200 51116
-0.000823938 8.3074791431427 46 200.0 0.0 200.0 200.0 200.0 0.0 1200 52316
-0.000706685 8.49429988861084 47 200.0 0.0 200.0 200.0 200.0 0.0 1200 53516
0.00264374 8.679890632629395 48 199.666666667 0.7453559925 200.0 198.0 199.666666667 0.7453559925 1198 54714
-0.000672976 8.873402833938599 49 197.666666667 3.4960294939 200.0 191.0 197.666666667 3.4960294939 1186 55900
0.000894078 9.04286813735962 50 181.833333333 40.6219015912 200.0 91.0 181.833333333 40.6219015912 1091 56991
0.000651397 9.224980115890503 51 194.166666667 10.237458452 200.0 172.0 194.166666667 10.237458452 1165 58156
9.84585e-05 9.396469354629517 52 182.833333333 38.3858336137 200.0 97.0 182.833333333 38.3858336137 1097 59253
0.00176051 9.57738733291626 53 164.142857143 37.1845919374 200.0 95.0 164.142857143 37.1845919374 1149 60402
0.000774221 9.76040768623352 54 195.5 10.0623058987 200.0 173.0 195.5 10.0623058987 1173 61575
0.000416572 9.952063083648682 55 200.0 0.0 200.0 200.0 200.0 0.0 1200 62775
0.00189362 10.127577304840088 56 184.166666667 35.4044096437 200.0 105.0 184.166666667 35.4044096437 1105 63880
0.000660424 10.311824083328247 57 168.142857143 43.4656796349 200.0 88.0 168.142857143 43.4656796349 1177 65057
0.00154621 10.479266166687012 58 177.5 36.0913193626 200.0 103.0 177.5 36.0913193626 1065 66122
0.00254398 10.6714346408844 59 200.0 0.0 200.0 200.0 200.0 0.0 1200 67322
0.000522495 10.840547323226929 60 185.166666667 24.9827718416 200.0 132.0 185.166666667 24.9827718416 1111 68433
-0.000575392 11.025654077529907 61 197.666666667 5.2174919475 200.0 186.0 197.666666667 5.2174919475 1186 69619
0.000208772 11.186293363571167 62 170.166666667 30.4599007805 200.0 112.0 170.166666667 30.4599007805 1021 70640
0.00080723 11.343485355377197 63 170.333333333 42.3188951757 200.0 84.0 170.333333333 42.3188951757 1022 71662
0.00114605 11.5041184425354 64 175.166666667 42.3179105764 200.0 82.0 175.166666667 42.3179105764 1051 72713
0.0014077 11.683966636657715 65 167.714285714 44.5444057277 200.0 72.0 167.714285714 44.5444057277 1174 73887
0.00134694 11.857315063476562 66 180.666666667 27.5600354781 200.0 136.0 180.666666667 27.5600354781 1084 74971
0.00069999 12.043684482574463 67 194.833333333 9.87280214641 200.0 173.0 194.833333333 9.87280214641 1169 76140
0.00202999 12.235471248626709 68 200.0 0.0 200.0 200.0 200.0 0.0 1200 77340
0.00130729 12.419071435928345 69 200.0 0.0 200.0 200.0 200.0 0.0 1200 78540
0.00105788 12.607258319854736 70 200.0 0.0 200.0 200.0 200.0 0.0 1200 79740
0.000608647 12.796462297439575 71 200.0 0.0 200.0 200.0 200.0 0.0 1200 80940
0.000403558 12.982543706893921 72 200.0 0.0 200.0 200.0 200.0 0.0 1200 82140
0.00122185 13.17354679107666 73 200.0 0.0 200.0 200.0 200.0 0.0 1200 83340
0.00131535 13.361554622650146 74 200.0 0.0 200.0 200.0 200.0 0.0 1200 84540
0.0018515 13.54215669631958 75 200.0 0.0 200.0 200.0 200.0 0.0 1200 85740
0.001152 13.721238613128662 76 200.0 0.0 200.0 200.0 200.0 0.0 1200 86940
0.0042862 13.901626348495483 77 200.0 0.0 200.0 200.0 200.0 0.0 1200 88140
0.00903519 14.088966131210327 78 200.0 0.0 200.0 200.0 200.0 0.0 1200 89340
0.00217568 14.279349565505981 79 200.0 0.0 200.0 200.0 200.0 0.0 1200 90540
0.0016027 14.46153998374939 80 192.166666667 9.11805291106 200.0 177.0 192.166666667 9.11805291106 1153 91693
0.00138174 14.635315418243408 81 190.5 11.8145390656 200.0 173.0 190.5 11.8145390656 1143 92836
0.00189734 14.820132970809937 82 196.166666667 8.57159391375 200.0 177.0 196.166666667 8.57159391375 1177 94013
-0.000120589 14.99648642539978 83 194.5 11.0113577728 200.0 170.0 194.5 11.0113577728 1167 95180
0.000976826 15.181550741195679 84 200.0 0.0 200.0 200.0 200.0 0.0 1200 96380
0.00219317 15.355873107910156 85 191.666666667 8.57645355351 200.0 177.0 191.666666667 8.57645355351 1150 97530
-0.000328364 15.543027877807617 86 200.0 0.0 200.0 200.0 200.0 0.0 1200 98730
0.00460324 15.721702337265015 87 194.666666667 11.92569588 200.0 168.0 194.666666667 11.92569588 1168 99898
0.000459549 15.902788639068604 88 198.666666667 2.98142397 200.0 192.0 198.666666667 2.98142397 1192 101090
0.000570928 16.087016582489014 89 200.0 0.0 200.0 200.0 200.0 0.0 1200 102290
0.00093408 16.27689504623413 90 200.0 0.0 200.0 200.0 200.0 0.0 1200 103490
-0.000755497 16.466399908065796 91 200.0 0.0 200.0 200.0 200.0 0.0 1200 104690
0.000834231 16.648562908172607 92 200.0 0.0 200.0 200.0 200.0 0.0 1200 105890
0.00140358 16.836161136627197 93 200.0 0.0 200.0 200.0 200.0 0.0 1200 107090
0.000144104 17.02006220817566 94 200.0 0.0 200.0 200.0 200.0 0.0 1200 108290
-0.000188936 17.205231189727783 95 200.0 0.0 200.0 200.0 200.0 0.0 1200 109490
0.000166349 17.39383554458618 96 200.0 0.0 200.0 200.0 200.0 0.0 1200 110690
0.00103515 17.5767080783844 97 200.0 0.0 200.0 200.0 200.0 0.0 1200 111890
0.000146966 17.76569938659668 98 200.0 0.0 200.0 200.0 200.0 0.0 1200 113090
0.000937825 17.953417539596558 99 200.0 0.0 200.0 200.0 200.0 0.0 1200 114290
================================================
FILE: hw2/data/sb_rtg_na_l2_CartPole-v0_25-01-2018_09-22-07/21/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_rtg_na_l2",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_rtg_na_l2_CartPole-v0_25-01-2018_09-22-07/21",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 2,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 21,
"size" : 32}
================================================
FILE: hw2/data/sb_rtg_na_l2_CartPole-v0_25-01-2018_09-22-07/31/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0571144 0.27991414070129395 0 19.0925925926 8.70774138024 47.0 8.0 19.0925925926 8.70774138024 1031 1031
0.02172 0.44403719902038574 1 22.4666666667 10.4745193472 53.0 10.0 22.4666666667 10.4745193472 1011 2042
0.0122367 0.5973637104034424 2 29.4411764706 17.9184282013 86.0 10.0 29.4411764706 17.9184282013 1001 3043
0.00885413 0.7490577697753906 3 58.8823529412 34.3475015838 158.0 18.0 58.8823529412 34.3475015838 1001 4044
0.00841376 0.9124112129211426 4 43.9583333333 19.620310834 91.0 14.0 43.9583333333 19.620310834 1055 5099
0.00871168 1.075624942779541 5 58.3888888889 25.7296605516 121.0 26.0 58.3888888889 25.7296605516 1051 6150
0.00273845 1.3059628009796143 6 60.6470588235 26.5550287172 113.0 18.0 60.6470588235 26.5550287172 1031 7181
0.0078359 1.4661099910736084 7 76.1428571429 32.3813375327 133.0 15.0 76.1428571429 32.3813375327 1066 8247
0.00467501 1.6512477397918701 8 85.3333333333 38.8272527428 159.0 35.0 85.3333333333 38.8272527428 1024 9271
0.00299164 1.8045504093170166 9 85.75 43.4916179664 197.0 36.0 85.75 43.4916179664 1029 10300
0.00489115 1.9593210220336914 10 129.625 54.5502921624 200.0 57.0 129.625 54.5502921624 1037 11337
0.00180701 2.137446641921997 11 143.625 48.0570949497 195.0 43.0 143.625 48.0570949497 1149 12486
0.00217947 2.2948157787323 12 129.75 44.5638586749 200.0 44.0 129.75 44.5638586749 1038 13524
0.0026045 2.4664101600646973 13 140.0 32.2412778903 200.0 95.0 140.0 32.2412778903 1120 14644
0.00307667 2.6345479488372803 14 124.222222222 58.4157090321 200.0 36.0 124.222222222 58.4157090321 1118 15762
0.00472138 2.8169374465942383 15 165.571428571 48.4262536319 200.0 60.0 165.571428571 48.4262536319 1159 16921
0.00408657 2.9953556060791016 16 191.166666667 12.4955547652 200.0 173.0 191.166666667 12.4955547652 1147 18068
0.000656419 3.1721768379211426 17 191.833333333 18.2612218162 200.0 151.0 191.833333333 18.2612218162 1151 19219
0.00368921 3.3343918323516846 18 181.166666667 30.1574571578 200.0 119.0 181.166666667 30.1574571578 1087 20306
0.0010569 3.5237417221069336 19 199.666666667 0.7453559925 200.0 198.0 199.666666667 0.7453559925 1198 21504
0.00093811 3.708292245864868 20 200.0 0.0 200.0 200.0 200.0 0.0 1200 22704
-0.00065037 3.891042709350586 21 200.0 0.0 200.0 200.0 200.0 0.0 1200 23904
0.00110094 4.07707142829895 22 200.0 0.0 200.0 200.0 200.0 0.0 1200 25104
0.00143954 4.258812665939331 23 200.0 0.0 200.0 200.0 200.0 0.0 1200 26304
0.00143368 4.436873197555542 24 194.333333333 12.6710518725 200.0 166.0 194.333333333 12.6710518725 1166 27470
0.00173543 4.621265649795532 25 200.0 0.0 200.0 200.0 200.0 0.0 1200 28670
0.00210707 4.802314043045044 26 200.0 0.0 200.0 200.0 200.0 0.0 1200 29870
0.000323564 4.984148025512695 27 200.0 0.0 200.0 200.0 200.0 0.0 1200 31070
0.00141371 5.17236852645874 28 200.0 0.0 200.0 200.0 200.0 0.0 1200 32270
0.000248464 5.353612899780273 29 200.0 0.0 200.0 200.0 200.0 0.0 1200 33470
-0.000112597 5.54021143913269 30 200.0 0.0 200.0 200.0 200.0 0.0 1200 34670
6.52844e-05 5.7179741859436035 31 189.833333333 22.7333577712 200.0 139.0 189.833333333 22.7333577712 1139 35809
0.0012624 5.9067137241363525 32 200.0 0.0 200.0 200.0 200.0 0.0 1200 37009
9.15735e-05 6.0930023193359375 33 200.0 0.0 200.0 200.0 200.0 0.0 1200 38209
0.000859255 6.274360656738281 34 194.5 12.2983738762 200.0 167.0 194.5 12.2983738762 1167 39376
-0.000306577 6.4634175300598145 35 200.0 0.0 200.0 200.0 200.0 0.0 1200 40576
0.000305534 6.644943714141846 36 200.0 0.0 200.0 200.0 200.0 0.0 1200 41776
0.00042062 6.82576847076416 37 200.0 0.0 200.0 200.0 200.0 0.0 1200 42976
0.000294425 7.010704278945923 38 200.0 0.0 200.0 200.0 200.0 0.0 1200 44176
2.63602e-05 7.19327712059021 39 200.0 0.0 200.0 200.0 200.0 0.0 1200 45376
0.00062371 7.377438545227051 40 200.0 0.0 200.0 200.0 200.0 0.0 1200 46576
-1.66507e-05 7.561534404754639 41 200.0 0.0 200.0 200.0 200.0 0.0 1200 47776
0.000692612 7.740008115768433 42 192.166666667 17.5158658237 200.0 153.0 192.166666667 17.5158658237 1153 48929
0.000736732 7.928375482559204 43 200.0 0.0 200.0 200.0 200.0 0.0 1200 50129
0.00168645 8.11709189414978 44 200.0 0.0 200.0 200.0 200.0 0.0 1200 51329
0.0021812 8.298892974853516 45 197.5 5.59016994375 200.0 185.0 197.5 5.59016994375 1185 52514
-0.000516962 8.478404521942139 46 195.333333333 10.434983895 200.0 172.0 195.333333333 10.434983895 1172 53686
0.000110081 8.655495643615723 47 200.0 0.0 200.0 200.0 200.0 0.0 1200 54886
-0.00062053 8.839212417602539 48 200.0 0.0 200.0 200.0 200.0 0.0 1200 56086
3.05097e-05 9.023950576782227 49 200.0 0.0 200.0 200.0 200.0 0.0 1200 57286
0.000828382 9.196184873580933 50 183.666666667 36.5224436325 200.0 102.0 183.666666667 36.5224436325 1102 58388
0.00181168 9.360637187957764 51 179.166666667 32.9363864982 200.0 112.0 179.166666667 32.9363864982 1075 59463
0.00088371 9.552984476089478 52 200.0 0.0 200.0 200.0 200.0 0.0 1200 60663
-6.62375e-05 9.733689069747925 53 200.0 0.0 200.0 200.0 200.0 0.0 1200 61863
0.00250517 9.919452667236328 54 200.0 0.0 200.0 200.0 200.0 0.0 1200 63063
0.00162229 10.106382846832275 55 198.666666667 2.98142397 200.0 192.0 198.666666667 2.98142397 1192 64255
0.000265208 10.283380270004272 56 186.166666667 30.9322736887 200.0 117.0 186.166666667 30.9322736887 1117 65372
0.00101419 10.465505599975586 57 199.5 1.11803398875 200.0 197.0 199.5 1.11803398875 1197 66569
0.000886809 10.653285503387451 58 196.166666667 8.57159391375 200.0 177.0 196.166666667 8.57159391375 1177 67746
-0.000853779 10.841053009033203 59 200.0 0.0 200.0 200.0 200.0 0.0 1200 68946
0.00215735 11.021432876586914 60 200.0 0.0 200.0 200.0 200.0 0.0 1200 70146
0.000837134 11.206451654434204 61 200.0 0.0 200.0 200.0 200.0 0.0 1200 71346
0.000701312 11.378507852554321 62 182.666666667 22.9177272482 200.0 137.0 182.666666667 22.9177272482 1096 72442
0.00132488 11.56203293800354 63 200.0 0.0 200.0 200.0 200.0 0.0 1200 73642
-0.00037279 11.741410493850708 64 191.333333333 19.379255805 200.0 148.0 191.333333333 19.379255805 1148 74790
6.59651e-05 11.925151586532593 65 192.833333333 16.0251538387 200.0 157.0 192.833333333 16.0251538387 1157 75947
0.000382308 12.109921216964722 66 200.0 0.0 200.0 200.0 200.0 0.0 1200 77147
0.000127486 12.295219421386719 67 200.0 0.0 200.0 200.0 200.0 0.0 1200 78347
0.00241688 12.487218379974365 68 200.0 0.0 200.0 200.0 200.0 0.0 1200 79547
-0.000291884 12.6644446849823 69 194.833333333 11.5530178837 200.0 169.0 194.833333333 11.5530178837 1169 80716
0.000707649 12.83349895477295 70 181.5 38.3220998033 200.0 96.0 181.5 38.3220998033 1089 81805
8.85031e-05 13.016446352005005 71 191.0 20.1246117975 200.0 146.0 191.0 20.1246117975 1146 82951
9.51993e-05 13.192869663238525 72 191.833333333 18.2612218162 200.0 151.0 191.833333333 18.2612218162 1151 84102
-7.8747e-05 13.36913275718689 73 193.666666667 14.1617638575 200.0 162.0 193.666666667 14.1617638575 1162 85264
0.00100637 13.546857595443726 74 194.666666667 11.92569588 200.0 168.0 194.666666667 11.92569588 1168 86432
0.000662854 13.72230839729309 75 196.0 8.94427191 200.0 176.0 196.0 8.94427191 1176 87608
0.000909359 13.882031679153442 76 177.333333333 35.7475717901 200.0 101.0 177.333333333 35.7475717901 1064 88672
0.000903603 14.061309337615967 77 196.666666667 7.453559925 200.0 180.0 196.666666667 7.453559925 1180 89852
-1.64369e-05 14.24147891998291 78 195.333333333 10.434983895 200.0 172.0 195.333333333 10.434983895 1172 91024
0.00157893 14.432033777236938 79 200.0 0.0 200.0 200.0 200.0 0.0 1200 92224
0.000983809 14.615539073944092 80 200.0 0.0 200.0 200.0 200.0 0.0 1200 93424
0.000427586 14.791681051254272 81 197.166666667 6.33552593625 200.0 183.0 197.166666667 6.33552593625 1183 94607
0.00133424 14.971085786819458 82 197.0 6.7082039325 200.0 182.0 197.0 6.7082039325 1182 95789
0.00125146 15.153594255447388 83 200.0 0.0 200.0 200.0 200.0 0.0 1200 96989
0.00381351 15.339380264282227 84 200.0 0.0 200.0 200.0 200.0 0.0 1200 98189
-0.000887808 15.511060237884521 85 187.333333333 28.323527715 200.0 124.0 187.333333333 28.323527715 1124 99313
0.000451962 15.696794748306274 86 200.0 0.0 200.0 200.0 200.0 0.0 1200 100513
-3.97558e-05 15.876044511795044 87 194.666666667 11.92569588 200.0 168.0 194.666666667 11.92569588 1168 101681
0.00159402 16.063766479492188 88 200.0 0.0 200.0 200.0 200.0 0.0 1200 102881
0.00363665 16.24856972694397 89 200.0 0.0 200.0 200.0 200.0 0.0 1200 104081
-0.000583416 16.436522483825684 90 200.0 0.0 200.0 200.0 200.0 0.0 1200 105281
-0.000223103 16.620957851409912 91 200.0 0.0 200.0 200.0 200.0 0.0 1200 106481
0.000672055 16.796754598617554 92 200.0 0.0 200.0 200.0 200.0 0.0 1200 107681
0.000759681 16.977147579193115 93 200.0 0.0 200.0 200.0 200.0 0.0 1200 108881
0.00769686 17.162957191467285 94 200.0 0.0 200.0 200.0 200.0 0.0 1200 110081
0.00597248 17.34579086303711 95 200.0 0.0 200.0 200.0 200.0 0.0 1200 111281
0.0149719 17.533146619796753 96 200.0 0.0 200.0 200.0 200.0 0.0 1200 112481
0.0138548 17.71477961540222 97 194.5 8.92094912738 200.0 175.0 194.5 8.92094912738 1167 113648
-0.000266192 17.876797914505005 98 178.166666667 8.64902049689 195.0 171.0 178.166666667 8.64902049689 1069 114717
-0.000283511 18.031185150146484 99 167.666666667 14.4414526816 189.0 149.0 167.666666667 14.4414526816 1006 115723
================================================
FILE: hw2/data/sb_rtg_na_l2_CartPole-v0_25-01-2018_09-22-07/31/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_rtg_na_l2",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_rtg_na_l2_CartPole-v0_25-01-2018_09-22-07/31",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 2,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 31,
"size" : 32}
================================================
FILE: hw2/data/sb_rtg_na_l2_CartPole-v0_25-01-2018_09-22-07/41/log.txt
================================================
LossDelta Time Iteration AverageReturn StdReturn MaxReturn MinReturn EpLenMean EpLenStd TimestepsThisBatch TimestepsSoFar
0.0240665 0.2724125385284424 0 21.9130434783 12.1759315097 61.0 10.0 21.9130434783 12.1759315097 1008 1008
0.0191814 0.4369683265686035 1 23.4651162791 12.8377148535 63.0 10.0 23.4651162791 12.8377148535 1009 2017
0.0142603 0.5918362140655518 2 41.0 26.9414179285 145.0 11.0 41.0 26.9414179285 1025 3042
0.0161849 0.7480564117431641 3 43.8695652174 18.4515920082 86.0 22.0 43.8695652174 18.4515920082 1009 4051
0.00303223 0.8936238288879395 4 66.8666666667 38.3803190306 169.0 14.0 66.8666666667 38.3803190306 1003 5054
0.00739272 1.0534791946411133 5 78.2307692308 28.0416005418 125.0 24.0 78.2307692308 28.0416005418 1017 6071
0.00558814 1.2160682678222656 6 86.9166666667 53.3064385313 181.0 20.0 86.9166666667 53.3064385313 1043 7114
0.00998791 1.3846797943115234 7 84.6153846154 36.4154203633 135.0 20.0 84.6153846154 36.4154203633 1100 8214
0.00548161 1.5466818809509277 8 137.875 38.5662984353 163.0 40.0 137.875 38.5662984353 1103 9317
0.00547876 1.7158620357513428 9 168.666666667 54.9777732866 200.0 47.0 168.666666667 54.9777732866 1012 10329
0.00446923 1.8750333786010742 10 133.75 60.6666094322 200.0 28.0 133.75 60.6666094322 1070 11399
0.00223307 2.055856943130493 11 184.5 15.9973956214 200.0 162.0 184.5 15.9973956214 1107 12506
0.00134373 2.2368900775909424 12 192.166666667 17.5158658237 200.0 153.0 192.166666667 17.5158658237 1153 13659
0.00124597 2.4215517044067383 13 186.166666667 19.8193227825 200.0 153.0 186.166666667 19.8193227825 1117 14776
0.00145733 2.6035101413726807 14 196.833333333 5.177408189 200.0 186.0 196.833333333 5.177408189 1181 15957
0.00251378 2.7715864181518555 15 170.5 41.8001196171 200.0 107.0 170.5 41.8001196171 1023 16980
0.00138271 2.952169895172119 16 188.666666667 14.4645159692 200.0 161.0 188.666666667 14.4645159692 1132 18112
-6.74652e-05 3.145519733428955 17 192.833333333 10.6209959776 200.0 173.0 192.833333333 10.6209959776 1157 19269
0.00192012 3.3173272609710693 18 185.833333333 15.1703292281 200.0 159.0 185.833333333 15.1703292281 1115 20384
0.00023939 3.5140669345855713 19 200.0 0.0 200.0 200.0 200.0 0.0 1200 21584
-0.00037027 3.6911509037017822 20 196.0 8.94427191 200.0 176.0 196.0 8.94427191 1176 22760
0.000997769 3.8583834171295166 21 168.666666667 44.3721634461 200.0 102.0 168.666666667 44.3721634461 1012 23772
0.000196372 4.026484489440918 22 179.166666667 32.4366904737 200.0 114.0 179.166666667 32.4366904737 1075 24847
0.000625191 4.2131028175354 23 200.0 0.0 200.0 200.0 200.0 0.0 1200 26047
0.000741529 4.3935956954956055 24 194.166666667 13.0437298687 200.0 165.0 194.166666667 13.0437298687 1165 27212
-0.000160483 4.584748983383179 25 200.0 0.0 200.0 200.0 200.0 0.0 1200 28412
0.000807466 4.767037630081177 26 197.166666667 6.33552593625 200.0 183.0 197.166666667 6.33552593625 1183 29595
0.000266545 4.960889101028442 27 200.0 0.0 200.0 200.0 200.0 0.0 1200 30795
0.000694204 5.147199869155884 28 200.0 0.0 200.0 200.0 200.0 0.0 1200 31995
0.00127902 5.33878231048584 29 200.0 0.0 200.0 200.0 200.0 0.0 1200 33195
0.00135321 5.524590969085693 30 200.0 0.0 200.0 200.0 200.0 0.0 1200 34395
-0.00037003 5.709272861480713 31 200.0 0.0 200.0 200.0 200.0 0.0 1200 35595
0.000786842 5.8937907218933105 32 200.0 0.0 200.0 200.0 200.0 0.0 1200 36795
0.00352819 6.081728219985962 33 200.0 0.0 200.0 200.0 200.0 0.0 1200 37995
0.00458174 6.260660171508789 34 195.833333333 7.31247032283 200.0 180.0 195.833333333 7.31247032283 1175 39170
0.0048685 6.449543476104736 35 200.0 0.0 200.0 200.0 200.0 0.0 1200 40370
0.00105708 6.6329967975616455 36 200.0 0.0 200.0 200.0 200.0 0.0 1200 41570
0.00131097 6.807498216629028 37 190.666666667 13.646326327 200.0 166.0 190.666666667 13.646326327 1144 42714
0.00164302 6.971754789352417 38 180.0 27.5015151098 200.0 123.0 180.0 27.5015151098 1080 43794
0.00182745 7.147618055343628 39 161.857142857 25.8204159058 196.0 119.0 161.857142857 25.8204159058 1133 44927
0.000121372 7.315327405929565 40 160.857142857 23.942959427 200.0 135.0 160.857142857 23.942959427 1126 46053
0.00120265 7.48945426940918 41 157.142857143 32.7694481903 200.0 105.0 157.142857143 32.7694481903 1100 47153
0.00528999 7.666618824005127 42 163.857142857 24.4331658169 200.0 137.0 163.857142857 24.4331658169 1147 48300
4.2649e-05 7.850505113601685 43 196.0 5.7735026919 200.0 186.0 196.0 5.7735026919 1176 49476
0.00245808 8.01331090927124 44 177.666666667 20.4830553276 200.0 146.0 177.666666667 20.4830553276 1066 50542
0.000396917 8.19615125656128 45 165.142857143 15.7881381462 200.0 145.0 165.142857143 15.7881381462 1156 51698
0.0109803 8.368581295013428 46 182.333333333 19.4650684275 200.0 145.0 182.333333333 19.4650684275 1094 52792
-0.00085239 8.552619457244873 47 193.833333333 8.85845484395 200.0 175.0 193.833333333 8.85845484395 1163 53955
0.000555387 8.728998899459839 48 185.833333333 15.2361047807 200.0 161.0 185.833333333 15.2361047807 1115 55070
0.00103712 8.906359434127808 49 187.666666667 17.7826382245 200.0 157.0 187.666666667 17.7826382245 1126 56196
0.00022864 9.089834213256836 50 197.5 5.59016994375 200.0 185.0 197.5 5.59016994375 1185 57381
9.25642e-05 9.276720523834229 51 192.166666667 17.5158658237 200.0 153.0 192.166666667 17.5158658237 1153 58534
0.000179507 9.467637777328491 52 200.0 0.0 200.0 200.0 200.0 0.0 1200 59734
0.00139582 9.65289306640625 53 196.5 7.82623792125 200.0 179.0 196.5 7.82623792125 1179 60913
0.000837676 9.848459243774414 54 197.0 6.7082039325 200.0 182.0 197.0 6.7082039325 1182 62095
0.00544752 10.035583734512329 55 200.0 0.0 200.0 200.0 200.0 0.0 1200 63295
0.00300558 10.219515085220337 56 200.0 0.0 200.0 200.0 200.0 0.0 1200 64495
-0.000545919 10.421415567398071 57 200.0 0.0 200.0 200.0 200.0 0.0 1200 65695
0.0011318 10.609416723251343 58 200.0 0.0 200.0 200.0 200.0 0.0 1200 66895
-0.000174001 10.795814037322998 59 200.0 0.0 200.0 200.0 200.0 0.0 1200 68095
0.000337193 10.979511737823486 60 200.0 0.0 200.0 200.0 200.0 0.0 1200 69295
-7.08341e-05 11.176418781280518 61 195.833333333 6.98609730504 200.0 181.0 195.833333333 6.98609730504 1175 70470
0.000404237 11.358709812164307 62 197.333333333 5.96284794 200.0 184.0 197.333333333 5.96284794 1184 71654
0.000206726 11.549397230148315 63 200.0 0.0 200.0 200.0 200.0 0.0 1200 72854
0.00156082 11.742408037185669 64 200.0 0.0 200.0 200.0 200.0 0.0 1200 74054
0.00107611 11.935765266418457 65 198.333333333 3.29983164554 200.0 191.0 198.333333333 3.29983164554 1190 75244
-0.000112867 12.123628854751587 66 200.0 0.0 200.0 200.0 200.0 0.0 1200 76444
0.000954127 12.307101011276245 67 197.5 3.5472994423 200.0 192.0 197.5 3.5472994423 1185 77629
-8.43904e-05 12.499125480651855 68 200.0 0.0 200.0 200.0 200.0 0.0 1200 78829
0.000784691 12.689738035202026 69 200.0 0.0 200.0 200.0 200.0 0.0 1200 80029
0.00023875 12.874089479446411 70 200.0 0.0 200.0 200.0 200.0 0.0 1200 81229
-4.6568e-05 13.068577766418457 71 200.0 0.0 200.0 200.0 200.0 0.0 1200 82429
0.000429748 13.262756824493408 72 200.0 0.0 200.0 200.0 200.0 0.0 1200 83629
0.00073573 13.449721097946167 73 200.0 0.0 200.0 200.0 200.0 0.0 1200 84829
0.000611821 13.637718439102173 74 200.0 0.0 200.0 200.0 200.0 0.0 1200 86029
-3.2234e-05 13.82893705368042 75 200.0 0.0 200.0 200.0 200.0 0.0 1200 87229
0.000422445 14.01395559310913 76 200.0 0.0 200.0 200.0 200.0 0.0 1200 88429
-3.717e-05 14.198429822921753 77 194.333333333 12.6710518725 200.0 166.0 194.333333333 12.6710518725 1166 89595
0.000157735 14.385034322738647 78 200.0 0.0 200.0 200.0 200.0 0.0 1200 90795
0.000386722 14.571649551391602 79 195.5 10.0623058987 200.0 173.0 195.5 10.0623058987 1173 91968
0.000226921 14.764421463012695 80 200.0 0.0 200.0 200.0 200.0 0.0 1200 93168
0.000819013 14.952504873275757 81 200.0 0.0 200.0 200.0 200.0 0.0 1200 94368
0.000252897 15.142824649810791 82 200.0 0.0 200.0 200.0 200.0 0.0 1200 95568
0.000894188 15.331052780151367 83 193.833333333 8.952032668 200.0 178.0 193.833333333 8.952032668 1163 96731
0.00227539 15.520310640335083 84 198.833333333 2.60874597375 200.0 193.0 198.833333333 2.60874597375 1193 97924
0.000131884 15.712832927703857 85 200.0 0.0 200.0 200.0 200.0 0.0 1200 99124
0.00468569 15.899184226989746 86 200.0 0.0 200.0 200.0 200.0 0.0 1200 100324
0.00132856 16.09347629547119 87 200.0 0.0 200.0 200.0 200.0 0.0 1200 101524
-0.000395967 16.275988340377808 88 200.0 0.0 200.0 200.0 200.0 0.0 1200 102724
-0.000595023 16.465942859649658 89 200.0 0.0 200.0 200.0 200.0 0.0 1200 103924
-0.000221039 16.651201009750366 90 200.0 0.0 200.0 200.0 200.0 0.0 1200 105124
0.000270594 16.839550495147705 91 200.0 0.0 200.0 200.0 200.0 0.0 1200 106324
0.000642643 17.030698537826538 92 200.0 0.0 200.0 200.0 200.0 0.0 1200 107524
8.9732e-05 17.22258687019348 93 200.0 0.0 200.0 200.0 200.0 0.0 1200 108724
0.00103107 17.403944730758667 94 197.666666667 5.2174919475 200.0 186.0 197.666666667 5.2174919475 1186 109910
0.000932077 17.592918872833252 95 200.0 0.0 200.0 200.0 200.0 0.0 1200 111110
0.000815801 17.783868312835693 96 200.0 0.0 200.0 200.0 200.0 0.0 1200 112310
0.000511491 17.974011421203613 97 200.0 0.0 200.0 200.0 200.0 0.0 1200 113510
0.000476312 18.16336750984192 98 200.0 0.0 200.0 200.0 200.0 0.0 1200 114710
-0.000571645 18.351927757263184 99 200.0 0.0 200.0 200.0 200.0 0.0 1200 115910
================================================
FILE: hw2/data/sb_rtg_na_l2_CartPole-v0_25-01-2018_09-22-07/41/params.json
================================================
{"animate" : false,
"env_name" : "CartPole-v0",
"exp_name" : "sb_rtg_na_l2",
"gamma" : 1.0,
"learning_rate" : 0.005,
"logdir" : "data/sb_rtg_na_l2_CartPole-v0_25-01-2018_09-22-07/41",
"max_path_length" : null,
"min_timesteps_per_batch" : 1000,
"n_iter" : 100,
"n_layers" : 2,
"nn_baseline" : false,
"normalize_advantages" : true,
"reward_to_go" : true,
"seed" : 41,
"size" : 32}
================================================
FILE: hw2/logz.py
================================================
import json
"""
Some simple logging functionality, inspired by rllab's logging.
Assumes that each diagnostic gets logged each iteration
Call logz.configure_output_dir() to start logging to a
tab-separated-values file (some_folder_name/log.txt)
To load the learning curves, you can do, for example
A = np.genfromtxt('/tmp/expt_1468984536/log.txt',delimiter='\t',dtype=None, names=True)
A['EpRewMean']
"""
import os.path as osp, shutil, time, atexit, os, subprocess
import pickle
import tensorflow as tf
color2num = dict(
gray=30,
red=31,
green=32,
yellow=33,
blue=34,
magenta=35,
cyan=36,
white=37,
crimson=38
)
def colorize(string, color, bold=False, highlight=False):
attr = []
num = color2num[color]
if highlight: num += 10
attr.append(str(num))
if bold: attr.append('1')
return '\x1b[%sm%s\x1b[0m' % (';'.join(attr), string)
class G:
output_dir = None
output_file = None
first_row = True
log_headers = []
log_current_row = {}
def configure_output_dir(d=None):
"""
Set output directory to d, or to /tmp/somerandomnumber if d is None
"""
G.output_dir = d or "/tmp/experiments/%i"%int(time.time())
assert not osp.exists(G.output_dir), "Log dir %s already exists! Delete it first or use a different dir"%G.output_dir
os.makedirs(G.output_dir)
G.output_file = open(osp.join(G.output_dir, "log.txt"), 'w')
atexit.register(G.output_file.close)
print(colorize("Logging data to %s"%G.output_file.name, 'green', bold=True))
def log_tabular(key, val):
"""
Log a value of some diagnostic
Call this once for each diagnostic quantity, each iteration
"""
if G.first_row:
G.log_headers.append(key)
else:
assert key in G.log_headers, "Trying to introduce a new key %s that you didn't include in the first iteration"%key
assert key not in G.log_current_row, "You already set %s this iteration. Maybe you forgot to call dump_tabular()"%key
G.log_current_row[key] = val
def save_params(params):
with open(osp.join(G.output_dir, "params.json"), 'w') as out:
out.write(json.dumps(params, separators=(',\n','\t:\t'), sort_keys=True))
def pickle_tf_vars():
"""
Saves tensorflow variables
Requires them to be initialized first, also a default session must exist
"""
_dict = {v.name : v.eval() for v in tf.global_variables()}
with open(osp.join(G.output_dir, "vars.pkl"), 'wb') as f:
pickle.dump(_dict, f)
def dump_tabular():
"""
Write all of the diagnostics from the current iteration
"""
vals = []
key_lens = [len(key) for key in G.log_headers]
max_key_len = max(15,max(key_lens))
keystr = '%'+'%d'%max_key_len
fmt = "| " + keystr + "s | %15s |"
n_slashes = 22 + max_key_len
print("-"*n_slashes)
for key in G.log_headers:
val = G.log_current_row.get(key, "")
if hasattr(val, "__float__"): valstr = "%8.3g"%val
else: valstr = val
print(fmt%(key, valstr))
vals.append(val)
print("-"*n_slashes)
if G.output_file is not None:
if G.first_row:
G.output_file.write("\t".join(G.log_headers))
G.output_file.write("\n")
G.output_file.write("\t".join(map(str,vals)))
G.output_file.write("\n")
G.output_file.flush()
G.log_current_row.clear()
G.first_row=False
================================================
FILE: hw2/plot.py
================================================
import seaborn as sns
import pandas as pd
import matplotlib.pyplot as plt
import json
import numpy as np
import os
"""
Using the plotter:
Call it from the command line, and supply it with logdirs to experiments.
Suppose you ran an experiment with name 'test', and you ran 'test' for 10
random seeds. The runner code stored it in the directory structure
data
L test_EnvName_DateTime
L 0
L log.txt
L params.json
L 1
L log.txt
L params.json
.
.
.
L 9
L log.txt
L params.json
To plot learning curves from the experiment, averaged over all random
seeds, call
python plot.py data/test_EnvName_DateTime --value AverageReturn
and voila. To see a different statistics, change what you put in for
the keyword --value. You can also enter /multiple/ values, and it will
make all of them in order.
Suppose you ran two experiments: 'test1' and 'test2'. In 'test2' you tried
a different set of hyperparameters from 'test1', and now you would like
to compare them -- see their learning curves side-by-side. Just call
python plot.py data/test1 data/test2
and it will plot them both! They will be given titles in the legend according
to their exp_name parameters. If you want to use custom legend titles, use
the --legend flag and then provide a title for each logdir.
"""
def plot_data(data, value="AverageReturn"):
data = [d[10:] for d in data]
if isinstance(data, list):
data = pd.concat(data, ignore_index=True)
sns.set(style="darkgrid", font_scale=1.5)
sns.tsplot(data=data, time="Iteration", value=value, unit="Unit", condition="Condition")
plt.legend(loc='best').draggable()
plt.show()
def get_datasets(fpath, condition=None):
unit = 0
datasets = []
for root, dir, files in os.walk(fpath):
if 'log.txt' in files:
param_path = open(os.path.join(root,'params.json'))
params = json.load(param_path)
exp_name = params['exp_name']
log_path = os.path.join(root,'log.txt')
experiment_data = pd.read_table(log_path)
experiment_data.insert(
len(experiment_data.columns),
'Unit',
unit
)
experiment_data.insert(
len(experiment_data.columns),
'Condition',
condition or exp_name
)
datasets.append(experiment_data)
unit += 1
return datasets
def main():
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('logdir', nargs='*')
parser.add_argument('--legend', nargs='*')
parser.add_argument('--value', default='AverageReturn', nargs='*')
args = parser.parse_args()
use_legend = False
if args.legend is not None:
assert len(args.legend) == len(args.logdir), \
"Must give a legend title for each set of experiments."
use_legend = True
data = []
if use_legend:
for logdir, legend_title in zip(args.logdir, args.legend):
data += get_datasets(logdir, legend_title)
else:
for logdir in args.logdir:
data += get_datasets(logdir)
if isinstance(args.value, list):
values = args.value
else:
values = [args.value]
for value in values:
plot_data(data, value=value)
if __name__ == "__main__":
main()
================================================
FILE: hw2/train_pg.py
================================================
import numpy as np
import tensorflow as tf
import gym
import logz
import scipy.signal
import os
import time
import inspect
from multiprocessing import Process
#============================================================================================#
# Utilities
#============================================================================================#
def build_mlp(
input_placeholder,
output_size,
scope,
n_layers=2,
size=64,
activation=tf.tanh,
output_activation=None
):
#========================================================================================#
# ----------SECTION 3----------
# Network building
#
# Your code should make a feedforward neural network (also called a multilayer perceptron)
# with 'n_layers' hidden layers of size 'size' units.
#
# The output layer should have size 'output_size' and activation 'output_activation'.
#
# Hint: use tf.layers.dense
#========================================================================================#
with tf.variable_scope(scope):
# YOUR_CODE_HERE
layer = input_placeholder
for i in range(n_layers):
layer = tf.layers.dense(layer, size, activation=activation, )
out_layer = tf.layers.dense(layer, output_size, activation=output_activation, )
return out_layer
def pathlength(path):
return len(path["reward"])
#============================================================================================#
# Policy Gradient
#============================================================================================#
def train_PG(exp_name='',
env_name='CartPole-v0',
n_iter=100,
gamma=1.0,
min_timesteps_per_batch=1000,
max_path_length=None,
learning_rate=5e-3,
reward_to_go=True,
animate=True,
logdir=None,
normalize_advantages=True,
nn_baseline=False,
seed=0,
# network arguments
n_layers=1,
size=32
):
start = time.time()
# Configure output directory for logging
logz.configure_output_dir(logdir)
# Log experimental parameters
args = inspect.getargspec(train_PG)[0]
locals_ = locals()
params = {k: locals_[k] if k in locals_ else None for k in args}
logz.save_params(params)
# Set random seeds
tf.set_random_seed(seed)
np.random.seed(seed)
# Make the gym environment
env = gym.make(env_name)
# Is this env continuous, or discrete?
discrete = isinstance(env.action_space, gym.spaces.Discrete)
# Maximum length for episodes
max_path_length = max_path_length or env.spec.max_episode_steps
#========================================================================================#
# Notes on notation:
#
# Symbolic variables have the prefix sy_, to distinguish them from the numerical values
# that are computed later in the function
#
# Prefixes and suffixes:
# ob - observation
# ac - action
# _no - this tensor should have shape (batch size /n/, observation dim)
# _na - this tensor should have shape (batch size /n/, action dim)
# _n - this tensor should have shape (batch size /n/)
#
# Note: batch size /n/ is defined at runtime, and until then, the shape for that axis
# is None
#========================================================================================#
# Observation and action sizes
ob_dim = env.observation_space.shape[0]
ac_dim = env.action_space.n if discrete else env.action_space.shape[0]
#========================================================================================#
# ----------SECTION 4----------
# Placeholders
#
# Need these for batch observations / actions / advantages in policy gradient loss function.
#========================================================================================#
sy_ob_no = tf.placeholder(shape=[None, ob_dim], name="ob", dtype=tf.float32)
if discrete:
sy_ac_na = tf.placeholder(shape=[None], name="ac", dtype=tf.int32)
else:
sy_ac_na = tf.placeholder(shape=[None, ac_dim], name="ac", dtype=tf.float32)
# Define a placeholder for advantages
sy_adv_n = tf.placeholder(shape=[None], name="adv", dtype=tf.float32)
#========================================================================================#
# ----------SECTION 4----------
# Networks
#
# Make symbolic operations for
# 1. Policy network outputs which describe the policy distribution.
# a. For the discrete case, just logits for each action.
#
# b. For the continuous case, the mean / log std of a Gaussian distribution over
# actions.
#
# Hint: use the 'build_mlp' function you defined in utilities.
#
# Note: these ops should be functions of the placeholder 'sy_ob_no'
#
# 2. Producing samples stochastically from the policy distribution.
# a. For the discrete case, an op that takes in logits and produces actions.
#
# Should have shape [None]
#
# b. For the continuous case, use the reparameterization trick:
# The output from a Gaussian distribution with mean 'mu' and std 'sigma' is
#
# mu + sigma * z, z ~ N(0, I)
#
# This reduces the problem to just sampling z. (Hint: use tf.random_normal!)
#
# Should have shape [None, ac_dim]
#
# Note: these ops should be functions of the policy network output ops.
#
# 3. Computing the log probability of a set of actions that were actually taken,
# according to the policy.
#
# Note: these ops should be functions of the placeholder 'sy_ac_na', and the
# policy network output ops.
#
#========================================================================================#
if discrete:
# YOUR_CODE_HERE
sy_logits_na = build_mlp(sy_ob_no, ac_dim, "discrete", n_layers, size) #logit
# noticed tf.multinomial return [batch, numsample] here is [batch, 1], should reshape to [batch]
sy_sampled_ac = tf.reshape(tf.multinomial(sy_logits_na, 1), [-1]) # Hint: Use the tf.multinomial op, choose action by logit(prob)
sy_logprob_n = -tf.nn.sparse_softmax_cross_entropy_with_logits(labels=sy_ac_na, logits=sy_logits_na) # -CE
else:
# YOUR_CODE_HERE
sy_mean = build_mlp(sy_ob_no, ac_dim, "continuous", n_layers, size) #logit
sy_logstd = tf.get_variable("std", [ac_dim], dtype=tf.float32) # logstd should just be a trainable variable, not a network output.
sy_sampled_ac = tf.random_normal(shape=tf.shape(sy_mean), mean=sy_mean, stddev=tf.exp(sy_logstd))
sy_logprob_n = tf.contrib.distributions.MultivariateNormalDiag(loc=sy_mean, scale_diag=tf.exp(sy_logstd)).log_prob(sy_ac_na) # Hint: Use the log probability under a multivariate gaussian.
#========================================================================================#
# ----------SECTION 4----------
# Loss Function and Training Operation
#========================================================================================#
loss = tf.reduce_mean(-sy_logprob_n * sy_adv_n)# Loss function that we'll differentiate to get the policy gradient.
update_op = tf.train.AdamOptimizer(learning_rate).minimize(loss)
#========================================================================================#
# ----------SECTION 5----------
# Optional Baseline
#========================================================================================#
if nn_baseline:
baseline_prediction = tf.squeeze(build_mlp(
sy_ob_no,
1,
"nn_baseline",
n_layers=n_layers,
size=size))
# Define placeholders for targets, a loss function and an update op for fitting a
# neural network baseline. These will be used to fit the neural network baseline.
# YOUR_CODE_HERE
# baseline_targets = norm_q_n
# here loss = l2 (bn - norm_q_n)
baseline_targets = tf.placeholder(shape=[None], name="baseline", dtype=tf.float32)
baseline_loss = tf.nn.l2_loss(baseline_prediction - baseline_targets)
baseline_update_op = tf.train.AdamOptimizer(learning_rate).minimize(baseline_loss)
#========================================================================================#
# Tensorflow Engineering: Config, Session, Variable initialization
#========================================================================================#
tf_config = tf.ConfigProto(inter_op_parallelism_threads=1, intra_op_parallelism_threads=1)
sess = tf.Session(config=tf_config)
sess.__enter__() # equivalent to `with sess:`
tf.global_variables_initializer().run() #pylint: disable=E1101
#========================================================================================#
# Training Loop
#========================================================================================#
total_timesteps = 0
for itr in range(n_iter):
print("********** Iteration %i ************"%itr)
# Collect paths until we have enough timesteps
timesteps_this_batch = 0
paths = []
while True:
ob = env.reset()
obs, acs, rewards = [], [], []
animate_this_episode=(len(paths) == 0 and (itr % 10 == 0) and animate)
steps = 0
while True:
if animate_this_episode:
env.render()
time.sleep(0.05)
obs.append(ob)
ac = sess.run(sy_sampled_ac, feed_dict={sy_ob_no: ob[None]})
ac = ac[0]
acs.append(ac)
ob, rew, done, _ = env.step(ac)
rewards.append(rew)
steps += 1
if done or steps > max_path_length:
break
path = {"observation": np.array(obs),
"reward": np.array(rewards),
"action": np.array(acs)}
paths.append(path)
timesteps_this_batch += pathlength(path)
if timesteps_this_batch > min_timesteps_per_batch:
break
total_timesteps += timesteps_this_batch
# Build arrays for observation, action for the policy gradient update by concatenating
# across paths
ob_no = np.concatenate([path["observation"] for path in paths])
ac_na = np.concatenate([path["action"] for path in paths])
# 我们直接把q_n当做target，用神经网络拟合/hat v(s)，最终的adv=q_n-拟合的v(s)，然后更新actor梯度
# 而V(s)即critic的梯度更新也是q_n-拟合的v(s)(其实这个是TDerror，这个作业里不明显)
#====================================================================================#
# ----------SECTION 4----------
# Computing Q-values
#
# Your code should construct numpy arrays for Q-values which will be used to compute
# advantages (which will in turn be fed to the placeholder you defined above).
#
# Recall that the expression for the policy gradient PG is
#
# PG = E_{tau} [sum_{t=0}^T grad log pi(a_t|s_t) * (Q_t - b_t )]
#
# where
#
# tau=(s_0, a_0, ...) is a trajectory,
# Q_t is the Q-value at time t, Q^{pi}(s_t, a_t),
# and b_t is a baseline which may depend on s_t.
#
# You will write code for two cases, controlled by the flag 'reward_to_go':
#
# Case 1: trajectory-based PG
#
# (reward_to_go = False)
#
# Instead of Q^{pi}(s_t, a_t), we use the total discounted reward summed over
# entire trajectory (regardless of which time step the Q-value should be for).
#
# For this case, the policy gradient estimator is
#
# E_{tau} [sum_{t=0}^T grad log pi(a_t|s_t) * Ret(tau)]
#
# where
#
# Ret(tau) = sum_{t'=0}^T gamma^t' r_{t'}.
#
# Thus, you should compute
#
# Q_t = Ret(tau)
#
# Case 2: reward-to-go PG
#
# (reward_to_go = True)
#
# Here, you estimate Q^{pi}(s_t, a_t) by the discounted sum of rewards starting
# from time step t. Thus, you should compute
#
# Q_t = sum_{t'=t}^T gamma^(t'-t) * r_{t'}
#
#
# Store the Q-values for all timesteps and all trajectories in a variable 'q_n',
# like the 'ob_no' and 'ac_na' above.
#
#====================================================================================#
# YOUR_CODE_HERE
q_n = []
for path in paths:
r = path["reward"]
max_step = len(r)
if reward_to_go:
q = [np.sum(np.power(gamma, np.arange(max_step - t)) * r[t:]) for t in range(max_step)]
else:
q = [np.sum(np.power(gamma, np.arange(max_step)) * r) for t in range(max_step)]
q_n.extend(q)
#====================================================================================#
# ----------SECTION 5----------
# Computing Baselines
#====================================================================================#
if nn_baseline:
# If nn_baseline is True, use your neural network to predict reward-to-go
# at each timestep for each trajectory, and save the result in a variable 'b_n'
# like 'ob_no', 'ac_na', and 'q_n'.
#
# Hint #bl1: rescale the output from the nn_baseline to match the statistics
# (mean and std) of the current or previous batch of Q-values. (Goes with Hint
# #bl2 below.)
b_n = sess.run(baseline_prediction, feed_dict={sy_ob_no: ob_no})
# b_n_norm = b_n - np.mean(b_n, axis=0) / (np.std(b_n, axis=0) + 1e-7)
b_n = b_n * np.std(q_n, axis=0) + np.mean(q_n, axis=0)
adv_n = q_n - b_n
else:
adv_n = q_n.copy()
#====================================================================================#
# ----------SECTION 4----------
# Advantage Normalization
#====================================================================================#
if normalize_advantages:
# On the next line, implement a trick which is known empirically to reduce variance
# in policy gradient methods: normalize adv_n to have mean zero and std=1.
# YOUR_CODE_HERE
adv_mean = np.mean(adv_n, axis=0)
adv_std = np.std(adv_n, axis=0)
adv_n = (adv_n - adv_mean) / (adv_std + 1e-7)
#====================================================================================#
# ----------SECTION 5----------
# Optimizing Neural Network Baseline
#====================================================================================#
if nn_baseline:
# ----------SECTION 5----------
# If a neural network baseline is used, set up the targets and the inputs for the
# baseline.
#
# Fit it to the current batch in order to use for the next iteration. Use the
# baseline_update_op you defined earlier.
#
# Hint #bl2: Instead of trying to target raw Q-values directly, rescale the
# targets to have mean zero and std=1. (Goes with Hint #bl1 above.)
# YOUR_CODE_HERE
q_n_mean = np.mean(q_n, axis=0)
q_n_std = np.std(q_n, axis=0)
q_n = (q_n - q_n_mean) / (q_n_std + 1e-7)
# rew_n = np.concatenate([path["reward"] for path in paths])
# trg_n = rew_n + b_n
# trg_n = (trg_n - np.mean(trg_n)) / np.std(trg_n)
sess.run(baseline_update_op, feed_dict={sy_ob_no: ob_no, baseline_targets: q_n})
#====================================================================================#
# ----------SECTION 4----------
# Performing the Policy Update
#====================================================================================#
# Call the update operation necessary to perform the policy gradient update based on
# the current batch of rollouts.
#
# For debug purposes, you may wish to save the value of the loss function before
# and after an update, and then log them below.
# YOUR_CODE_HERE
feed_dict = {sy_ob_no: ob_no, sy_ac_na: ac_na, sy_adv_n: adv_n}
loss_1 = sess.run(loss, feed_dict)
sess.run(update_op, feed_dict)
loss_2 = sess.run(loss, feed_dict)
# Log diagnostics
returns = [path["reward"].sum() for path in paths]
ep_lengths = [pathlength(path) for path in paths]
logz.log_tabular("LossDelta", loss_1 - loss_2)
logz.log_tabular("Time", time.time() - start)
logz.log_tabular("Iteration", itr)
logz.log_tabular("AverageReturn", np.mean(returns))
logz.log_tabular("StdReturn", np.std(returns))
logz.log_tabular("MaxReturn", np.max(returns))
logz.log_tabular("MinReturn", np.min(returns))
logz.log_tabular("EpLenMean", np.mean(ep_lengths))
logz.log_tabular("EpLenStd", np.std(ep_lengths))
logz.log_tabular("TimestepsThisBatch", timesteps_this_batch)
logz.log_tabular("TimestepsSoFar", total_timesteps)
logz.dump_tabular()
logz.pickle_tf_vars()
def main():
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('env_name', type=str)
parser.add_argument('--exp_name', type=str, default='vpg')
parser.add_argument('--render', action='store_true')
parser.add_argument('--discount', type=float, default=1.0)
parser.add_argument('--n_iter', '-n', type=int, default=100)
parser.add_argument('--batch_size', '-b', type=int, default=1000)
parser.add_argument('--ep_len', '-ep', type=float, default=-1.)
parser.add_argument('--learning_rate', '-lr', type=float, default=5e-3)
parser.add_argument('--reward_to_go', '-rtg', action='store_true')
parser.add_argument('--dont_normalize_advantages', '-dna', action='store_true')
parser.add_argument('--nn_baseline', '-bl', action='store_true')
parser.add_argument('--seed', type=int, default=1)
parser.add_argument('--n_experiments', '-e', type=int, default=1)
parser.add_argument('--n_layers', '-l', type=int, default=1)
parser.add_argument('--size', '-s', type=int, default=32)
args = parser.parse_args()
if not(os.path.exists('data')):
os.makedirs('data')
logdir = args.exp_name + '_' + args.env_name + '_' + time.strftime("%d-%m-%Y_%H-%M-%S")
logdir = os.path.join('data', logdir)
if not(os.path.exists(logdir)):
os.makedirs(logdir)
max_path_length = args.ep_len if args.ep_len > 0 else None
for e in range(args.n_experiments):
seed = args.seed + 10*e
print('Running experiment with seed %d'%seed)
def train_func():
train_PG(
exp_name=args.exp_name,
env_name=args.env_name,
n_iter=args.n_iter,
gamma=args.discount,
min_timesteps_per_batch=args.batch_size,
max_path_length=max_path_length,
learning_rate=args.learning_rate,
reward_to_go=args.reward_to_go,
animate=args.render,
logdir=os.path.join(logdir,'%d'%seed),
normalize_advantages=not(args.dont_normalize_advantages),
nn_baseline=args.nn_baseline,
seed=seed,
n_layers=args.n_layers,
size=args.size
)
# Awkward hacky process runs, because Tensorflow does not like
# repeatedly calling train_PG in the same thread.
p = Process(target=train_func, args=tuple())
p.start()
p.join()
if __name__ == "__main__":
main()
================================================
FILE: hw3/.idea/hw3.iml
================================================
================================================
FILE: hw3/.idea/misc.xml
================================================
================================================
FILE: hw3/.idea/modules.xml
================================================
================================================
FILE: hw3/.idea/workspace.xml
================================================
model_initialized
num_param_updates
AVAILABLE GPUS
1516844406618
1516844406618
================================================
FILE: hw3/README
================================================
See http://rll.berkeley.edu/deeprlcourse/f17docs/hw3.pdf for instructions
The starter code was based on an implementation of Q-learning for Atari
generously provided by Szymon Sidor from OpenAI
================================================
FILE: hw3/atari_wrappers.py
================================================
import cv2
import numpy as np
from collections import deque
import gym
from gym import spaces
class NoopResetEnv(gym.Wrapper):
def __init__(self, env=None, noop_max=30):
"""Sample initial states by taking random number of no-ops on reset.
No-op is assumed to be action 0.
"""
super(NoopResetEnv, self).__init__(env)
self.noop_max = noop_max
assert env.unwrapped.get_action_meanings()[0] == 'NOOP'
def _reset(self):
""" Do no-op action for a number of steps in [1, noop_max]."""
self.env.reset()
noops = np.random.randint(1, self.noop_max + 1)
for _ in range(noops):
obs, _, _, _ = self.env.step(0)
return obs
class FireResetEnv(gym.Wrapper):
def __init__(self, env=None):
"""Take action on reset for environments that are fixed until firing."""
super(FireResetEnv, self).__init__(env)
assert env.unwrapped.get_action_meanings()[1] == 'FIRE'
assert len(env.unwrapped.get_action_meanings()) >= 3
def _reset(self):
self.env.reset()
obs, _, _, _ = self.env.step(1)
obs, _, _, _ = self.env.step(2)
return obs
class EpisodicLifeEnv(gym.Wrapper):
def __init__(self, env=None):
"""Make end-of-life == end-of-episode, but only reset on true game over.
Done by DeepMind for the DQN and co. since it helps value estimation.
"""
super(EpisodicLifeEnv, self).__init__(env)
self.lives = 0
self.was_real_done = True
self.was_real_reset = False
def _step(self, action):
obs, reward, done, info = self.env.step(action)
self.was_real_done = done
# check current lives, make loss of life terminal,
# then update lives to handle bonus lives
lives = self.env.unwrapped.ale.lives()
if lives < self.lives and lives > 0:
# for Qbert somtimes we stay in lives == 0 condtion for a few frames
# so its important to keep lives > 0, so that we only reset once
# the environment advertises done.
done = True
self.lives = lives
return obs, reward, done, info
def _reset(self):
"""Reset only when lives are exhausted.
This way all states are still reachable even though lives are episodic,
and the learner need not know about any of this behind-the-scenes.
"""
if self.was_real_done:
obs = self.env.reset()
self.was_real_reset = True
else:
# no-op step to advance from terminal/lost life state
obs, _, _, _ = self.env.step(0)
self.was_real_reset = False
self.lives = self.env.unwrapped.ale.lives()
return obs
class MaxAndSkipEnv(gym.Wrapper):
def __init__(self, env=None, skip=4):
"""Return only every `skip`-th frame"""
super(MaxAndSkipEnv, self).__init__(env)
# most recent raw observations (for max pooling across time steps)
self._obs_buffer = deque(maxlen=2)
self._skip = skip
def _step(self, action):
total_reward = 0.0
done = None
for _ in range(self._skip):
obs, reward, done, info = self.env.step(action)
self._obs_buffer.append(obs)
total_reward += reward
if done:
break
max_frame = np.max(np.stack(self._obs_buffer), axis=0)
return max_frame, total_reward, done, info
def _reset(self):
"""Clear past frame buffer and init. to first obs. from inner env."""
self._obs_buffer.clear()
obs = self.env.reset()
self._obs_buffer.append(obs)
return obs
def _process_frame84(frame):
img = np.reshape(frame, [210, 160, 3]).astype(np.float32)
img = img[:, :, 0] * 0.299 + img[:, :, 1] * 0.587 + img[:, :, 2] * 0.114
resized_screen = cv2.resize(img, (84, 110), interpolation=cv2.INTER_LINEAR)
x_t = resized_screen[18:102, :]
x_t = np.reshape(x_t, [84, 84, 1])
return x_t.astype(np.uint8)
class ProcessFrame84(gym.Wrapper):
def __init__(self, env=None):
super(ProcessFrame84, self).__init__(env)
self.observation_space = spaces.Box(low=0, high=255, shape=(84, 84, 1))
def _step(self, action):
obs, reward, done, info = self.env.step(action)
return _process_frame84(obs), reward, done, info
def _reset(self):
return _process_frame84(self.env.reset())
class ClippedRewardsWrapper(gym.Wrapper):
def _step(self, action):
obs, reward, done, info = self.env.step(action)
return obs, np.sign(reward), done, info
def wrap_deepmind_ram(env):
env = EpisodicLifeEnv(env)
env = NoopResetEnv(env, noop_max=30)
env = MaxAndSkipEnv(env, skip=4)
if 'FIRE' in env.unwrapped.get_action_meanings():
env = FireResetEnv(env)
env = ClippedRewardsWrapper(env)
return env
def wrap_deepmind(env):
assert 'NoFrameskip' in env.spec.id
env = EpisodicLifeEnv(env)
env = NoopResetEnv(env, noop_max=30)
env = MaxAndSkipEnv(env, skip=4)
if 'FIRE' in env.unwrapped.get_action_meanings():
env = FireResetEnv(env)
env = ProcessFrame84(env)
env = ClippedRewardsWrapper(env)
return env
================================================
FILE: hw3/dqn.py
================================================
import sys
import gym.spaces
import itertools
import numpy as np
import random
import tensorflow as tf
import tensorflow.contrib.layers as layers
from collections import namedtuple
from dqn_utils import *
import logz
OptimizerSpec = namedtuple("OptimizerSpec", ["constructor", "kwargs", "lr_schedule"])
def learn(env,
q_func,
optimizer_spec,
session,
exploration=LinearSchedule(1000000, 0.1),
stopping_criterion=None,
replay_buffer_size=1000000,
batch_size=32,
gamma=0.99,
learning_starts=50000,
learning_freq=4,
frame_history_len=4,
target_update_freq=10000,
grad_norm_clipping=10):
"""Run Deep Q-learning algorithm.
You can specify your own convnet using q_func.
All schedules are w.r.t. total number of steps taken in the environment.
Parameters
----------
env: gym.Env
gym environment to train on.
q_func: function
Model to use for computing the q function. It should accept the
following named arguments:
img_in: tf.Tensor
tensorflow tensor representing the input image
num_actions: int
number of actions
scope: str
scope in which all the model related variables
should be created
reuse: bool
whether previously created variables should be reused.
optimizer_spec: OptimizerSpec
Specifying the constructor and kwargs, as well as learning rate schedule
for the optimizer
session: tf.Session
tensorflow session to use.
exploration: rl_algs.deepq.utils.schedules.Schedule
schedule for probability of chosing random action.
stopping_criterion: (env, t) -> bool
should return true when it's ok for the RL algorithm to stop.
takes in env and the number of steps executed so far.
replay_buffer_size: int
How many memories to store in the replay buffer.
batch_size: int
How many transitions to sample each time experience is replayed.
gamma: float
Discount Factor
learning_starts: int
After how many environment steps to start replaying experiences
learning_freq: int
How many steps of environment to take between every experience replay
frame_history_len: int
How many past frames to include as input to the model.
target_update_freq: int
How many experience replay rounds (not steps!) to perform between
each update to the target Q network
grad_norm_clipping: float or None
If not None gradients' norms are clipped to this value.
"""
assert type(env.observation_space) == gym.spaces.Box
assert type(env.action_space) == gym.spaces.Discrete
###############
# BUILD MODEL #
###############
if len(env.observation_space.shape) == 1:
# This means we are running on low-dimensional observations (e.g. RAM)
input_shape = env.observation_space.shape
else:
img_h, img_w, img_c = env.observation_space.shape
input_shape = (img_h, img_w, frame_history_len * img_c)
num_actions = env.action_space.n
# set up placeholders
# placeholder for current observation (or state)
obs_t_ph = tf.placeholder(tf.uint8, [None] + list(input_shape))
# placeholder for current action
act_t_ph = tf.placeholder(tf.int32, [None])
# placeholder for current reward
rew_t_ph = tf.placeholder(tf.float32, [None])
# placeholder for next observation (or state)
obs_tp1_ph = tf.placeholder(tf.uint8, [None] + list(input_shape))
# placeholder for end of episode mask
# this value is 1 if the next state corresponds to the end of an episode,
# in which case there is no Q-value at the next state; at the end of an
# episode, only the current state reward contributes to the target, not the
# next state Q-value (i.e. target is just rew_t_ph, not rew_t_ph + gamma * q_tp1)
done_mask_ph = tf.placeholder(tf.float32, [None])
# casting to float on GPU ensures lower data transfer times.
obs_t_float = tf.cast(obs_t_ph, tf.float32) / 255.0
obs_tp1_float = tf.cast(obs_tp1_ph, tf.float32) / 255.0
# Here, you should fill in your own code to compute the Bellman error. This requires
# evaluating the current and next Q-values and constructing the corresponding error.
# TensorFlow will differentiate this error for you, you just need to pass it to the
# optimizer. See assignment text for details.
# Your code should produce one scalar-valued tensor: total_error
# This will be passed to the optimizer in the provided code below.
# Your code should also produce two collections of variables:
# q_func_vars
# target_q_func_vars
# These should hold all of the variables of the Q-function network and target network,
# respectively. A convenient way to get these is to make use of TF's "scope" feature.
# For example, you can create your Q-function network with the scope "q_func" like this:
# = q_func(obs_t_float, num_actions, scope="q_func", reuse=False)
# And then you can obtain the variables like this:
# q_func_vars = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='q_func')
# Older versions of TensorFlow may require using "VARIABLES" instead of "GLOBAL_VARIABLES"
######
# YOUR CODE HERE
q = q_func(obs_t_float, num_actions, scope="q_func", reuse=False)
target_q = q_func(obs_tp1_float, num_actions, scope="target_q_func", reuse=False)
Q_samp = rew_t_ph + (1 - done_mask_ph) * gamma * tf.reduce_max(target_q, axis=1)
Q_s = tf.reduce_sum(q * tf.one_hot(act_t_ph, num_actions), axis=1)
total_error = tf.reduce_mean(tf.square(Q_samp - Q_s))
q_func_vars = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='q_func')
target_q_func_vars = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='target_q_func')
######
# construct optimization op (with gradient clipping)
learning_rate = tf.placeholder(tf.float32, (), name="learning_rate")
optimizer = optimizer_spec.constructor(learning_rate=learning_rate, **optimizer_spec.kwargs)
train_fn = minimize_and_clip(optimizer, total_error,
var_list=q_func_vars, clip_val=grad_norm_clipping)
# update_target_fn will be called periodically to copy Q network to target Q network
update_target_fn = []
for var, var_target in zip(sorted(q_func_vars, key=lambda v: v.name),
sorted(target_q_func_vars, key=lambda v: v.name)):
update_target_fn.append(var_target.assign(var))
update_target_fn = tf.group(*update_target_fn)
# construct the replay buffer
replay_buffer = ReplayBuffer(replay_buffer_size, frame_history_len)
###############
# RUN ENV #
###############
model_initialized = False
num_param_updates = 0
mean_episode_reward = -float('nan')
best_mean_episode_reward = -float('inf')
last_obs = env.reset()
LOG_EVERY_N_STEPS = 10000
for t in itertools.count():
### 1. Check stopping criterion
if stopping_criterion is not None and stopping_criterion(env, t):
break
### 2. Step the env and store the transition
# At this point, "last_obs" contains the latest observation that was
# recorded from the simulator. Here, your code needs to store this
# observation and its outcome (reward, next observation, etc.) into
# the replay buffer while stepping the simulator forward one step.
# At the end of this block of code, the simulator should have been
# advanced one step, and the replay buffer should contain one more
# transition.
# Specifically, last_obs must point to the new latest observation.
# Useful functions you'll need to call:
# obs, reward, done, info = env.step(action)
# this steps the environment forward one step
# obs = env.reset()
# this resets the environment if you reached an episode boundary.
# Don't forget to call env.reset() to get a new observation if done
# is true!!
# Note that you cannot use "last_obs" directly as input
# into your network, since it needs to be processed to include context
# from previous frames. You should check out the replay buffer
# implementation in dqn_utils.py to see what functionality the replay
# buffer exposes. The replay buffer has a function called
# encode_recent_observation that will take the latest observation
# that you pushed into the buffer and compute the corresponding
# input that should be given to a Q network by appending some
# previous frames.
# Don't forget to include epsilon greedy exploration!
# And remember that the first time you enter this loop, the model
# may not yet have been initialized (but of course, the first step
# might as well be random, since you haven't trained your net...)
#####
# YOUR CODE HERE
# replay memory stuff
idx = replay_buffer.store_frame(last_obs)
q_input = replay_buffer.encode_recent_observation()
if (np.random.random() < exploration.value(t)) or not model_initialized:
action = env.action_space.sample()
else:
# chose action according to current Q and exploration
action_values = session.run(q, feed_dict={obs_t_ph: [q_input]})[0]
action = np.argmax(action_values)
# perform action in env
new_state, reward, done, info = env.step(action)
# store the transition
replay_buffer.store_effect(idx, action, reward, done)
last_obs = new_state
if done:
last_obs = env.reset()
#####
# at this point, the environment should have been advanced one step (and
# reset if done was true), and last_obs should point to the new latest
# observation
### 3. Perform experience replay and train the network.
# note that this is only done if the replay buffer contains enough samples
# for us to learn something useful -- until then, the model will not be
# initialized and random actions should be taken
if (t > learning_starts and
t % learning_freq == 0 and
replay_buffer.can_sample(batch_size)):
# Here, you should perform training. Training consists of four steps:
# 3.a: use the replay buffer to sample a batch of transitions (see the
# replay buffer code for function definition, each batch that you sample
# should consist of current observations, current actions, rewards,
# next observations, and done indicator).
# 3.b: initialize the model if it has not been initialized yet; to do
# that, call
# initialize_interdependent_variables(session, tf.global_variables(), {
# obs_t_ph: obs_t_batch,
# obs_tp1_ph: obs_tp1_batch,
# })
# where obs_t_batch and obs_tp1_batch are the batches of observations at
# the current and next time step. The boolean variable model_initialized
# indicates whether or not the model has been initialized.
# Remember that you have to update the target network too (see 3.d)!
# 3.c: train the model. To do this, you'll need to use the train_fn and
# total_error ops that were created earlier: total_error is what you
# created to compute the total Bellman error in a batch, and train_fn
# will actually perform a gradient step and update the network parameters
# to reduce total_error. When calling session.run on these you'll need to
# populate the following placeholders:
# obs_t_ph
# act_t_ph
# rew_t_ph
# obs_tp1_ph
# done_mask_ph
# (this is needed for computing total_error)
# learning_rate -- you can get this from optimizer_spec.lr_schedule.value(t)
# (this is needed by the optimizer to choose the learning rate)
# 3.d: periodically update the target network by calling
# session.run(update_target_fn)
# you should update every target_update_freq steps, and you may find the
# variable num_param_updates useful for this (it was initialized to 0)
#####
# YOUR CODE HERE
s_batch, a_batch, r_batch, sp_batch, done_mask_batch = replay_buffer.sample(batch_size)
if not model_initialized:
initialize_interdependent_variables(session, tf.global_variables(),
{obs_t_ph: s_batch, obs_tp1_ph: sp_batch, })
model_initialized = True
feed_dict = {obs_t_ph: s_batch,
act_t_ph: a_batch,
rew_t_ph: r_batch,
obs_tp1_ph: sp_batch,
done_mask_ph: done_mask_batch,
learning_rate: optimizer_spec.lr_schedule.value(t)}
session.run(train_fn, feed_dict=feed_dict)
num_param_updates += 1
if num_param_updates % target_update_freq == 0:
session.run(update_target_fn)
num_param_updates = 0
#####
### 4. Log progress
episode_rewards = get_wrapper_by_name(env, "Monitor").get_episode_rewards()
if len(episode_rewards) > 0:
mean_episode_reward = np.mean(episode_rewards[-100:])
if len(episode_rewards) > 100:
best_mean_episode_reward = max(best_mean_episode_reward, mean_episode_reward)
if t % LOG_EVERY_N_STEPS == 0 and model_initialized:
# print("Timestep %d" % (t,))
# print("mean reward (100 episodes) %f" % mean_episode_reward)
# print("best mean reward %f" % best_mean_episode_reward)
# print("episodes %d" % len(episode_rewards))
# print("exploration %f" % exploration.value(t))
# print("learning_rate %f" % optimizer_spec.lr_schedule.value(t))
logz.log_tabular('Timestep', t)
logz.log_tabular('MeanReward', mean_episode_reward)
logz.log_tabular('BestMeanReward', best_mean_episode_reward)
logz.log_tabular('episodes', len(episode_rewards))
logz.log_tabular('exploration', exploration.value(t))
logz.log_tabular('learning_rate', optimizer_spec.lr_schedule.value(t))
logz.dump_tabular()
sys.stdout.flush()
================================================
FILE: hw3/dqn_utils.py
================================================
"""This file includes a collection of utility functions that are useful for
implementing DQN."""
import gym
import tensorflow as tf
import numpy as np
import random
def huber_loss(x, delta=1.0):
# https://en.wikipedia.org/wiki/Huber_loss
return tf.select(
tf.abs(x) < delta,
tf.square(x) * 0.5,
delta * (tf.abs(x) - 0.5 * delta)
)
def sample_n_unique(sampling_f, n):
"""Helper function. Given a function `sampling_f` that returns
comparable objects, sample n such unique objects.
"""
res = []
while len(res) < n:
candidate = sampling_f()
if candidate not in res:
res.append(candidate)
return res
class Schedule(object):
def value(self, t):
"""Value of the schedule at time t"""
raise NotImplementedError()
class ConstantSchedule(object):
def __init__(self, value):
"""Value remains constant over time.
Parameters
----------
value: float
Constant value of the schedule
"""
self._v = value
def value(self, t):
"""See Schedule.value"""
return self._v
def linear_interpolation(l, r, alpha):
return l + alpha * (r - l)
class PiecewiseSchedule(object):
def __init__(self, endpoints, interpolation=linear_interpolation, outside_value=None):
"""Piecewise schedule.
endpoints: [(int, int)]
list of pairs `(time, value)` meanining that schedule should output
`value` when `t==time`. All the values for time must be sorted in
an increasing order. When t is between two times, e.g. `(time_a, value_a)`
and `(time_b, value_b)`, such that `time_a <= t < time_b` then value outputs
`interpolation(value_a, value_b, alpha)` where alpha is a fraction of
time passed between `time_a` and `time_b` for time `t`.
interpolation: lambda float, float, float: float
a function that takes value to the left and to the right of t according
to the `endpoints`. Alpha is the fraction of distance from left endpoint to
right endpoint that t has covered. See linear_interpolation for example.
outside_value: float
if the value is requested outside of all the intervals sepecified in
`endpoints` this value is returned. If None then AssertionError is
raised when outside value is requested.
"""
idxes = [e[0] for e in endpoints]
assert idxes == sorted(idxes)
self._interpolation = interpolation
self._outside_value = outside_value
self._endpoints = endpoints
def value(self, t):
"""See Schedule.value"""
for (l_t, l), (r_t, r) in zip(self._endpoints[:-1], self._endpoints[1:]):
if l_t <= t and t < r_t:
alpha = float(t - l_t) / (r_t - l_t)
return self._interpolation(l, r, alpha)
# t does not belong to any of the pieces, so doom.
assert self._outside_value is not None
return self._outside_value
class LinearSchedule(object):
def __init__(self, schedule_timesteps, final_p, initial_p=1.0):
"""Linear interpolation between initial_p and final_p over
schedule_timesteps. After this many timesteps pass final_p is
returned.
Parameters
----------
schedule_timesteps: int
Number of timesteps for which to linearly anneal initial_p
to final_p
initial_p: float
initial output value
final_p: float
final output value
"""
self.schedule_timesteps = schedule_timesteps
self.final_p = final_p
self.initial_p = initial_p
def value(self, t):
"""See Schedule.value"""
fraction = min(float(t) / self.schedule_timesteps, 1.0)
return self.initial_p + fraction * (self.final_p - self.initial_p)
def compute_exponential_averages(variables, decay):
"""Given a list of tensorflow scalar variables
create ops corresponding to their exponential
averages
Parameters
----------
variables: [tf.Tensor]
List of scalar tensors.
Returns
-------
averages: [tf.Tensor]
List of scalar tensors corresponding to averages
of al the `variables` (in order)
apply_op: tf.runnable
Op to be run to update the averages with current value
of variables.
"""
averager = tf.train.ExponentialMovingAverage(decay=decay)
apply_op = averager.apply(variables)
return [averager.average(v) for v in variables], apply_op
def minimize_and_clip(optimizer, objective, var_list, clip_val=10):
"""Minimized `objective` using `optimizer` w.r.t. variables in
`var_list` while ensure the norm of the gradients for each
variable is clipped to `clip_val`
"""
gradients = optimizer.compute_gradients(objective, var_list=var_list)
for i, (grad, var) in enumerate(gradients):
if grad is not None:
gradients[i] = (tf.clip_by_norm(grad, clip_val), var)
return optimizer.apply_gradients(gradients)
def initialize_interdependent_variables(session, vars_list, feed_dict):
"""Initialize a list of variables one at a time, which is useful if
initialization of some variables depends on initialization of the others.
"""
vars_left = vars_list
while len(vars_left) > 0:
new_vars_left = []
for v in vars_left:
try:
# If using an older version of TensorFlow, uncomment the line
# below and comment out the line after it.
#session.run(tf.initialize_variables([v]), feed_dict)
session.run(tf.variables_initializer([v]), feed_dict)
except tf.errors.FailedPreconditionError:
new_vars_left.append(v)
if len(new_vars_left) >= len(vars_left):
# This can happend if the variables all depend on each other, or more likely if there's
# another variable outside of the list, that still needs to be initialized. This could be
# detected here, but life's finite.
raise Exception("Cycle in variable dependencies, or extenrnal precondition unsatisfied.")
else:
vars_left = new_vars_left
def get_wrapper_by_name(env, classname):
currentenv = env
while True:
if classname in currentenv.__class__.__name__:
return currentenv
elif isinstance(env, gym.Wrapper):
currentenv = currentenv.env
else:
raise ValueError("Couldn't find wrapper named %s"%classname)
class ReplayBuffer(object):
def __init__(self, size, frame_history_len):
"""This is a memory efficient implementation of the replay buffer.
The sepecific memory optimizations use here are:
- only store each frame once rather than k times
even if every observation normally consists of k last frames
- store frames as np.uint8 (actually it is most time-performance
to cast them back to float32 on GPU to minimize memory transfer
time)
- store frame_t and frame_(t+1) in the same buffer.
For the tipical use case in Atari Deep RL buffer with 1M frames the total
memory footprint of this buffer is 10^6 * 84 * 84 bytes ~= 7 gigabytes
Warning! Assumes that returning frame of zeros at the beginning
of the episode, when there is less frames than `frame_history_len`,
is acceptable.
Parameters
----------
size: int
Max number of transitions to store in the buffer. When the buffer
overflows the old memories are dropped.
frame_history_len: int
Number of memories to be retried for each observation.
"""
self.size = size
self.frame_history_len = frame_history_len
self.next_idx = 0
self.num_in_buffer = 0
self.obs = None
self.action = None
self.reward = None
self.done = None
def can_sample(self, batch_size):
"""Returns true if `batch_size` different transitions can be sampled from the buffer."""
return batch_size + 1 <= self.num_in_buffer
def _encode_sample(self, idxes):
obs_batch = np.concatenate([self._encode_observation(idx)[None] for idx in idxes], 0)
act_batch = self.action[idxes]
rew_batch = self.reward[idxes]
next_obs_batch = np.concatenate([self._encode_observation(idx + 1)[None] for idx in idxes], 0)
done_mask = np.array([1.0 if self.done[idx] else 0.0 for idx in idxes], dtype=np.float32)
return obs_batch, act_batch, rew_batch, next_obs_batch, done_mask
def sample(self, batch_size):
"""Sample `batch_size` different transitions.
i-th sample transition is the following:
when observing `obs_batch[i]`, action `act_batch[i]` was taken,
after which reward `rew_batch[i]` was received and subsequent
observation next_obs_batch[i] was observed, unless the epsiode
was done which is represented by `done_mask[i]` which is equal
to 1 if episode has ended as a result of that action.
Parameters
----------
batch_size: int
How many transitions to sample.
Returns
-------
obs_batch: np.array
Array of shape
(batch_size, img_h, img_w, img_c * frame_history_len)
and dtype np.uint8
act_batch: np.array
Array of shape (batch_size,) and dtype np.int32
rew_batch: np.array
Array of shape (batch_size,) and dtype np.float32
next_obs_batch: np.array
Array of shape
(batch_size, img_h, img_w, img_c * frame_history_len)
and dtype np.uint8
done_mask: np.array
Array of shape (batch_size,) and dtype np.float32
"""
assert self.can_sample(batch_size)
idxes = sample_n_unique(lambda: random.randint(0, self.num_in_buffer - 2), batch_size)
return self._encode_sample(idxes)
def encode_recent_observation(self):
"""Return the most recent `frame_history_len` frames.
Returns
-------
observation: np.array
Array of shape (img_h, img_w, img_c * frame_history_len)
and dtype np.uint8, where observation[:, :, i*img_c:(i+1)*img_c]
encodes frame at time `t - frame_history_len + i`
"""
assert self.num_in_buffer > 0
return self._encode_observation((self.next_idx - 1) % self.size)
def _encode_observation(self, idx):
end_idx = idx + 1 # make noninclusive
start_idx = end_idx - self.frame_history_len
# this checks if we are using low-dimensional observations, such as RAM
# state, in which case we just directly return the latest RAM.
if len(self.obs.shape) == 2:
return self.obs[end_idx-1]
# if there weren't enough frames ever in the buffer for context
if start_idx < 0 and self.num_in_buffer != self.size:
start_idx = 0
for idx in range(start_idx, end_idx - 1):
if self.done[idx % self.size]:
start_idx = idx + 1
missing_context = self.frame_history_len - (end_idx - start_idx)
# if zero padding is needed for missing context
# or we are on the boundry of the buffer
if start_idx < 0 or missing_context > 0:
frames = [np.zeros_like(self.obs[0]) for _ in range(missing_context)]
for idx in range(start_idx, end_idx):
frames.append(self.obs[idx % self.size])
return np.concatenate(frames, 2)
else:
# this optimization has potential to saves about 30% compute time \o/
img_h, img_w = self.obs.shape[1], self.obs.shape[2]
return self.obs[start_idx:end_idx].transpose(1, 2, 0, 3).reshape(img_h, img_w, -1)
def store_frame(self, frame):
"""Store a single frame in the buffer at the next available index, overwriting
old frames if necessary.
Parameters
----------
frame: np.array
Array of shape (img_h, img_w, img_c) and dtype np.uint8
the frame to be stored
Returns
-------
idx: int
Index at which the frame is stored. To be used for `store_effect` later.
"""
if self.obs is None:
self.obs = np.empty([self.size] + list(frame.shape), dtype=np.uint8)
self.action = np.empty([self.size], dtype=np.int32)
self.reward = np.empty([self.size], dtype=np.float32)
self.done = np.empty([self.size], dtype=np.bool)
self.obs[self.next_idx] = frame
ret = self.next_idx
self.next_idx = (self.next_idx + 1) % self.size
self.num_in_buffer = min(self.size, self.num_in_buffer + 1)
return ret
def store_effect(self, idx, action, reward, done):
"""Store effects of action taken after obeserving frame stored
at index idx. The reason `store_frame` and `store_effect` is broken
up into two functions is so that once can call `encode_recent_observation`
in between.
Paramters
---------
idx: int
Index in buffer of recently observed frame (returned by `store_frame`).
action: int
Action that was performed upon observing this frame.
reward: float
Reward that was received when the actions was performed.
done: bool
True if episode was finished after performing that action.
"""
self.action[idx] = action
self.reward[idx] = reward
self.done[idx] = done
================================================
FILE: hw3/log/_RAM_30-01-2018_15-20-56/log.txt
================================================
Timestep MeanReward BestMeanReward episodes exploration learning_rate
60000 -20.69 -20.57 207 0.194 0.0001
70000 -20.72 -20.57 243 0.193 0.0001
80000 -20.79 -20.57 279 0.192 0.0001
90000 -20.79 -20.57 315 0.191 0.0001
100000 -20.76 -20.57 350 0.19 0.0001
110000 -20.71 -20.57 386 0.189 0.0001
120000 -20.72 -20.57 424 0.188 0.0001
130000 -20.76 -20.57 460 0.187 0.0001
140000 -20.84 -20.57 496 0.186 0.0001
150000 -20.72 -20.57 531 0.185 0.0001
160000 -20.71 -20.57 565 0.184 0.0001
170000 -20.59 -20.57 598 0.183 0.0001
180000 -20.56 -20.56 631 0.18200000000000002 0.0001
190000 -20.33 -20.33 663 0.181 0.0001
200000 -20.08 -20.07 693 0.18 0.0001
210000 -19.95 -19.95 724 0.17900000000000002 0.0001
220000 -19.94 -19.94 756 0.17800000000000002 0.0001
230000 -19.94 -19.83 786 0.17700000000000002 0.0001
240000 -19.86 -19.82 815 0.17600000000000002 0.0001
250000 -19.57 -19.57 843 0.17500000000000002 0.0001
260000 -19.55 -19.48 871 0.17400000000000002 0.0001
270000 -19.37 -19.37 897 0.17300000000000001 0.0001
280000 -19.4 -19.36 926 0.17200000000000001 0.0001
290000 -19.32 -19.29 951 0.171 0.0001
300000 -19.16 -19.16 978 0.17 0.0001
310000 -19.11 -19.09 1002 0.169 0.0001
320000 -19.02 -19.01 1027 0.168 0.0001
330000 -19.01 -18.95 1051 0.167 0.0001
340000 -18.81 -18.78 1074 0.166 0.0001
350000 -18.65 -18.65 1098 0.165 0.0001
360000 -18.56 -18.54 1122 0.164 0.0001
370000 -18.55 -18.49 1146 0.163 0.0001
380000 -18.58 -18.42 1168 0.162 0.0001
390000 -18.46 -18.42 1190 0.161 0.0001
400000 -18.54 -18.42 1211 0.16 0.0001
410000 -18.4 -18.4 1234 0.159 0.0001
420000 -18.17 -18.17 1255 0.158 0.0001
430000 -18.18 -18.15 1275 0.157 0.0001
440000 -18.16 -18.06 1296 0.156 0.0001
450000 -17.92 -17.88 1316 0.155 0.0001
460000 -17.74 -17.74 1336 0.154 0.0001
470000 -17.64 -17.61 1356 0.15300000000000002 0.0001
480000 -17.57 -17.57 1378 0.15200000000000002 0.0001
490000 -17.53 -17.49 1398 0.15100000000000002 0.0001
500000 -17.6 -17.45 1419 0.15000000000000002 0.0001
510000 -17.64 -17.45 1440 0.14900000000000002 0.0001
520000 -17.79 -17.45 1460 0.14800000000000002 0.0001
530000 -17.57 -17.45 1479 0.14700000000000002 0.0001
540000 -17.64 -17.45 1500 0.14600000000000002 0.0001
550000 -17.39 -17.39 1518 0.14500000000000002 0.0001
560000 -17.32 -17.32 1536 0.14400000000000002 0.0001
570000 -17.18 -17.13 1555 0.14300000000000002 0.0001
580000 -17.29 -17.08 1574 0.14200000000000002 0.0001
590000 -17.08 -17.08 1591 0.14100000000000001 0.0001
600000 -17.08 -16.99 1610 0.14 0.0001
610000 -17.1 -16.99 1628 0.139 0.0001
620000 -17.01 -16.94 1647 0.138 0.0001
630000 -17.1 -16.94 1667 0.137 0.0001
640000 -17.0 -16.94 1687 0.136 0.0001
650000 -17.12 -16.94 1706 0.135 0.0001
660000 -17.07 -16.94 1724 0.134 0.0001
670000 -17.1 -16.94 1744 0.133 0.0001
680000 -17.02 -16.94 1763 0.132 0.0001
690000 -17.16 -16.94 1783 0.131 0.0001
700000 -17.2 -16.94 1802 0.13 0.0001
710000 -17.47 -16.94 1823 0.129 0.0001
720000 -17.56 -16.94 1842 0.128 0.0001
730000 -17.6 -16.94 1862 0.127 0.0001
740000 -17.5 -16.94 1881 0.126 0.0001
750000 -17.45 -16.94 1900 0.125 0.0001
760000 -17.2 -16.94 1919 0.124 0.0001
770000 -17.12 -16.94 1938 0.123 0.0001
780000 -17.2 -16.94 1957 0.122 0.0001
790000 -17.26 -16.94 1976 0.121 0.0001
800000 -17.21 -16.94 1993 0.12 0.0001
810000 -17.17 -16.94 2011 0.119 0.0001
820000 -17.1 -16.94 2028 0.11800000000000001 0.0001
830000 -16.99 -16.94 2045 0.117 0.0001
840000 -16.7 -16.7 2062 0.116 0.0001
850000 -16.52 -16.52 2078 0.115 0.0001
860000 -16.59 -16.49 2095 0.114 0.0001
870000 -16.69 -16.49 2113 0.113 0.0001
880000 -16.69 -16.49 2130 0.112 0.0001
890000 -16.79 -16.49 2146 0.111 0.0001
900000 -16.9 -16.49 2163 0.11 0.0001
910000 -17.09 -16.49 2181 0.109 0.0001
920000 -17.05 -16.49 2198 0.108 0.0001
930000 -16.97 -16.49 2214 0.107 0.0001
940000 -17.13 -16.49 2232 0.10600000000000001 0.0001
950000 -17.19 -16.49 2249 0.10500000000000001 0.0001
960000 -17.01 -16.49 2265 0.10400000000000001 0.0001
970000 -16.83 -16.49 2280 0.10300000000000001 0.0001
980000 -16.9 -16.49 2298 0.10200000000000001 0.0001
990000 -16.79 -16.49 2314 0.101 0.0001
1000000 -16.73 -16.49 2330 0.1 0.0001
1010000 -16.69 -16.49 2348 0.099775 9.9875e-05
1020000 -16.92 -16.49 2364 0.09955 9.975e-05
1030000 -16.98 -16.49 2381 0.09932500000000001 9.962500000000001e-05
1040000 -16.96 -16.49 2396 0.09910000000000001 9.95e-05
1050000 -17.1 -16.49 2413 0.098875 9.9375e-05
1060000 -16.74 -16.49 2427 0.09865 9.925e-05
1070000 -16.63 -16.49 2443 0.098425 9.912500000000001e-05
1080000 -16.41 -16.41 2459 0.09820000000000001 9.900000000000001e-05
1090000 -16.38 -16.38 2476 0.097975 9.8875e-05
1100000 -16.22 -16.22 2492 0.09775 9.875e-05
1110000 -16.03 -16.03 2508 0.097525 9.8625e-05
1120000 -16.27 -16.03 2523 0.09730000000000001 9.850000000000001e-05
1130000 -16.41 -16.03 2541 0.09707500000000001 9.8375e-05
1140000 -16.44 -16.03 2557 0.09685 9.825e-05
1150000 -16.46 -16.03 2575 0.096625 9.8125e-05
1160000 -16.68 -16.03 2592 0.0964 9.800000000000001e-05
1170000 -16.67 -16.03 2608 0.09617500000000001 9.787500000000001e-05
1180000 -16.7 -16.03 2624 0.09595000000000001 9.775e-05
1190000 -16.74 -16.03 2640 0.095725 9.7625e-05
1200000 -17.03 -16.03 2656 0.0955 9.75e-05
1210000 -16.89 -16.03 2671 0.095275 9.737500000000001e-05
1220000 -17.05 -16.03 2688 0.09505000000000001 9.725e-05
1230000 -17.16 -16.03 2703 0.094825 9.7125e-05
1240000 -17.23 -16.03 2717 0.0946 9.7e-05
1250000 -17.39 -16.03 2734 0.094375 9.687500000000001e-05
1260000 -17.13 -16.03 2748 0.09415000000000001 9.675000000000001e-05
1270000 -16.88 -16.03 2765 0.09392500000000001 9.6625e-05
1280000 -16.82 -16.03 2781 0.0937 9.65e-05
1290000 -16.64 -16.03 2796 0.093475 9.6375e-05
1300000 -16.82 -16.03 2813 0.09325 9.625000000000001e-05
1310000 -16.39 -16.03 2828 0.09302500000000001 9.6125e-05
1320000 -16.05 -16.03 2843 0.09280000000000001 9.6e-05
1330000 -15.95 -15.95 2858 0.092575 9.5875e-05
1340000 -15.85 -15.81 2874 0.09235 9.575000000000001e-05
1350000 -15.84 -15.81 2890 0.09212500000000001 9.562500000000001e-05
1360000 -15.65 -15.63 2905 0.09190000000000001 9.55e-05
1370000 -15.61 -15.42 2921 0.091675 9.5375e-05
1380000 -15.73 -15.42 2936 0.09145 9.525000000000001e-05
1390000 -15.79 -15.42 2951 0.091225 9.512500000000001e-05
1400000 -15.87 -15.42 2965 0.091 9.5e-05
1410000 -15.77 -15.42 2980 0.09077500000000001 9.4875e-05
1420000 -15.77 -15.42 2995 0.09055 9.475e-05
1430000 -15.9 -15.42 3011 0.090325 9.462500000000001e-05
1440000 -15.9 -15.42 3026 0.0901 9.45e-05
1450000 -15.76 -15.42 3040 0.08987500000000001 9.4375e-05
1460000 -15.82 -15.42 3054 0.08965000000000001 9.425e-05
1470000 -15.98 -15.42 3069 0.089425 9.412500000000001e-05
1480000 -16.16 -15.42 3084 0.0892 9.400000000000001e-05
1490000 -16.32 -15.42 3098 0.088975 9.3875e-05
1500000 -16.35 -15.42 3114 0.08875000000000001 9.375e-05
1510000 -16.73 -15.42 3132 0.088525 9.3625e-05
1520000 -16.82 -15.42 3148 0.0883 9.350000000000001e-05
1530000 -16.79 -15.42 3163 0.088075 9.3375e-05
1540000 -16.4 -15.42 3177 0.08785 9.325e-05
1550000 -16.21 -15.42 3193 0.08762500000000001 9.3125e-05
1560000 -16.02 -15.42 3208 0.0874 9.300000000000001e-05
1570000 -15.85 -15.42 3223 0.087175 9.287500000000001e-05
1580000 -15.79 -15.42 3239 0.08695 9.275e-05
1590000 -15.97 -15.42 3254 0.08672500000000001 9.2625e-05
1600000 -15.87 -15.42 3269 0.08650000000000001 9.25e-05
1610000 -15.9 -15.42 3284 0.086275 9.237500000000001e-05
1620000 -15.96 -15.42 3299 0.08605 9.225e-05
1630000 -16.04 -15.42 3314 0.085825 9.2125e-05
1640000 -15.94 -15.42 3328 0.08560000000000001 9.2e-05
1650000 -15.89 -15.42 3343 0.085375 9.1875e-05
1660000 -15.86 -15.42 3358 0.08515 9.175000000000001e-05
1670000 -16.08 -15.42 3374 0.084925 9.1625e-05
1680000 -16.03 -15.42 3389 0.0847 9.15e-05
1690000 -16.01 -15.42 3405 0.08447500000000001 9.137500000000001e-05
1700000 -15.91 -15.42 3419 0.08425 9.125000000000001e-05
1710000 -16.03 -15.42 3434 0.084025 9.1125e-05
1720000 -15.93 -15.42 3449 0.0838 9.1e-05
1730000 -15.6 -15.42 3463 0.08357500000000001 9.0875e-05
1740000 -15.52 -15.42 3477 0.08335000000000001 9.075000000000001e-05
1750000 -15.63 -15.42 3490 0.083125 9.062500000000001e-05
1760000 -15.51 -15.42 3505 0.0829 9.05e-05
1770000 -15.46 -15.3 3519 0.082675 9.0375e-05
1780000 -15.46 -15.3 3534 0.08245 9.025e-05
1790000 -15.29 -15.21 3548 0.082225 9.012500000000001e-05
1800000 -15.3 -15.21 3563 0.082 9e-05
1810000 -15.27 -15.19 3577 0.081775 8.9875e-05
1820000 -15.39 -15.19 3593 0.08155000000000001 8.975e-05
1830000 -15.34 -15.17 3609 0.08132500000000001 8.962500000000001e-05
1840000 -15.44 -15.17 3625 0.0811 8.950000000000001e-05
1850000 -15.43 -15.17 3640 0.080875 8.9375e-05
1860000 -15.73 -15.17 3657 0.08065 8.925e-05
1870000 -16.1 -15.17 3670 0.080425 8.912500000000001e-05
1880000 -16.14 -15.17 3685 0.08020000000000001 8.900000000000001e-05
1890000 -16.26 -15.17 3700 0.079975 8.8875e-05
1900000 -16.19 -15.17 3715 0.07975 8.875e-05
1910000 -16.03 -15.17 3728 0.079525 8.8625e-05
1920000 -16.01 -15.17 3743 0.07930000000000001 8.850000000000001e-05
1930000 -15.81 -15.17 3757 0.079075 8.837500000000001e-05
1940000 -15.93 -15.17 3772 0.07885 8.825e-05
1950000 -16.25 -15.17 3785 0.078625 8.8125e-05
1960000 -16.4 -15.17 3799 0.0784 8.8e-05
1970000 -16.63 -15.17 3813 0.07817500000000001 8.787500000000001e-05
1980000 -16.76 -15.17 3828 0.07795 8.775e-05
1990000 -16.77 -15.17 3843 0.077725 8.7625e-05
2000000 -16.76 -15.17 3857 0.0775 8.75e-05
2010000 -16.44 -15.17 3872 0.07727500000000001 8.737500000000001e-05
2020000 -16.07 -15.17 3886 0.07705000000000001 8.725e-05
2030000 -15.77 -15.17 3900 0.076825 8.7125e-05
2040000 -15.34 -15.17 3913 0.0766 8.7e-05
2050000 -15.25 -15.17 3927 0.076375 8.687500000000001e-05
2060000 -15.3 -15.17 3942 0.07615 8.675000000000001e-05
2070000 -15.39 -15.17 3957 0.075925 8.6625e-05
2080000 -15.49 -15.17 3970 0.0757 8.65e-05
2090000 -15.58 -15.17 3984 0.075475 8.6375e-05
2100000 -15.52 -15.17 3997 0.07525 8.625000000000001e-05
2110000 -15.87 -15.17 4011 0.07502500000000001 8.6125e-05
2120000 -16.01 -15.17 4024 0.0748 8.6e-05
2130000 -15.93 -15.17 4038 0.074575 8.5875e-05
2140000 -16.05 -15.17 4052 0.07435 8.575000000000001e-05
2150000 -16.06 -15.17 4065 0.074125 8.562500000000001e-05
2160000 -16.15 -15.17 4078 0.07390000000000001 8.55e-05
2170000 -16.12 -15.17 4091 0.073675 8.5375e-05
2180000 -16.31 -15.17 4104 0.07345 8.525000000000001e-05
2190000 -15.97 -15.17 4117 0.073225 8.512500000000001e-05
2200000 -15.84 -15.17 4129 0.07300000000000001 8.5e-05
2210000 -15.86 -15.17 4142 0.072775 8.4875e-05
2220000 -15.99 -15.17 4155 0.07255 8.475e-05
2230000 -16.14 -15.17 4168 0.072325 8.462500000000001e-05
2240000 -16.18 -15.17 4179 0.0721 8.450000000000001e-05
2250000 -16.41 -15.17 4193 0.071875 8.4375e-05
2260000 -16.47 -15.17 4206 0.07165 8.425e-05
2270000 -17.06 -15.17 4219 0.071425 8.4125e-05
2280000 -17.53 -15.17 4233 0.0712 8.400000000000001e-05
2290000 -17.83 -15.17 4245 0.070975 8.3875e-05
2300000 -17.67 -15.17 4259 0.07075000000000001 8.375e-05
2310000 -17.41 -15.17 4274 0.070525 8.3625e-05
2320000 -17.16 -15.17 4287 0.0703 8.35e-05
2330000 -16.9 -15.17 4302 0.070075 8.337500000000001e-05
2340000 -16.43 -15.17 4318 0.06985 8.325e-05
2350000 -15.87 -15.17 4331 0.06962499999999999 8.3125e-05
2360000 -15.69 -15.17 4347 0.0694 8.3e-05
2370000 -15.58 -15.17 4362 0.069175 8.2875e-05
2380000 -15.61 -15.17 4378 0.06895000000000001 8.275e-05
2390000 -15.68 -15.17 4393 0.06872500000000001 8.2625e-05
2400000 -15.48 -15.17 4406 0.0685 8.25e-05
2410000 -15.36 -15.17 4421 0.068275 8.237500000000001e-05
2420000 -15.41 -15.17 4437 0.06805 8.225000000000001e-05
2430000 -15.13 -15.13 4450 0.067825 8.2125e-05
2440000 -15.15 -15.05 4464 0.0676 8.2e-05
2450000 -15.01 -15.01 4477 0.067375 8.1875e-05
2460000 -14.93 -14.91 4492 0.06715 8.175000000000001e-05
2470000 -15.15 -14.91 4506 0.06692500000000001 8.1625e-05
2480000 -15.29 -14.91 4521 0.06670000000000001 8.15e-05
2490000 -15.16 -14.91 4536 0.066475 8.1375e-05
2500000 -15.24 -14.91 4550 0.06625 8.125e-05
2510000 -15.42 -14.91 4563 0.066025 8.112500000000001e-05
2520000 -15.94 -14.91 4578 0.0658 8.1e-05
2530000 -16.12 -14.91 4592 0.065575 8.0875e-05
2540000 -16.34 -14.91 4605 0.06534999999999999 8.075000000000001e-05
2550000 -16.52 -14.91 4619 0.065125 8.062500000000001e-05
2560000 -16.81 -14.91 4632 0.0649 8.05e-05
2570000 -16.88 -14.91 4644 0.06467500000000001 8.0375e-05
2580000 -17.11 -14.91 4657 0.06445000000000001 8.025e-05
2590000 -17.13 -14.91 4670 0.064225 8.012500000000001e-05
2600000 -17.18 -14.91 4683 0.064 8e-05
2610000 -17.22 -14.91 4694 0.063775 7.9875e-05
2620000 -17.23 -14.91 4706 0.06355 7.975e-05
2630000 -17.33 -14.91 4719 0.063325 7.9625e-05
2640000 -17.43 -14.91 4731 0.0631 7.950000000000001e-05
2650000 -17.73 -14.91 4745 0.062875 7.9375e-05
2660000 -17.8 -14.91 4758 0.06265000000000001 7.925e-05
2670000 -17.88 -14.91 4771 0.062425 7.912500000000001e-05
2680000 -17.82 -14.91 4784 0.062200000000000005 7.900000000000001e-05
2690000 -17.93 -14.91 4797 0.061975 7.8875e-05
2700000 -17.68 -14.91 4807 0.06175 7.875e-05
2710000 -17.56 -14.91 4819 0.061525 7.8625e-05
2720000 -17.46 -14.91 4832 0.0613 7.850000000000001e-05
2730000 -17.24 -14.91 4844 0.061075000000000004 7.837500000000001e-05
2740000 -16.94 -14.91 4858 0.06085 7.825e-05
2750000 -16.39 -14.91 4871 0.060625 7.8125e-05
2760000 -16.04 -14.91 4884 0.0604 7.8e-05
2770000 -15.81 -14.91 4899 0.060175 7.787500000000001e-05
2780000 -15.66 -14.91 4913 0.05995 7.775e-05
2790000 -15.26 -14.91 4925 0.059725 7.7625e-05
2800000 -15.12 -14.91 4939 0.0595 7.75e-05
2810000 -14.8 -14.8 4953 0.059275 7.7375e-05
2820000 -14.86 -14.74 4965 0.05905 7.725000000000001e-05
2830000 -14.95 -14.74 4978 0.058825 7.7125e-05
2840000 -14.86 -14.74 4991 0.0586 7.7e-05
2850000 -14.72 -14.72 5003 0.058374999999999996 7.6875e-05
2860000 -14.62 -14.57 5017 0.05815 7.675e-05
2870000 -14.91 -14.57 5031 0.057925 7.6625e-05
2880000 -14.89 -14.57 5046 0.0577 7.65e-05
2890000 -14.79 -14.57 5059 0.057475000000000005 7.6375e-05
2900000 -15.01 -14.57 5074 0.05725 7.625000000000001e-05
2910000 -14.87 -14.57 5087 0.057025 7.612500000000001e-05
2920000 -15.03 -14.57 5100 0.0568 7.6e-05
2930000 -15.19 -14.57 5114 0.056575 7.5875e-05
2940000 -15.13 -14.57 5127 0.056350000000000004 7.575e-05
2950000 -15.01 -14.57 5139 0.056125 7.562500000000001e-05
2960000 -15.23 -14.57 5154 0.0559 7.55e-05
2970000 -15.09 -14.57 5166 0.055675 7.5375e-05
2980000 -15.14 -14.57 5181 0.05545 7.525e-05
2990000 -15.11 -14.57 5194 0.055225 7.5125e-05
3000000 -15.01 -14.57 5207 0.055 7.500000000000001e-05
3010000 -14.89 -14.57 5221 0.054775000000000004 7.4875e-05
3020000 -15.12 -14.57 5236 0.05455 7.475e-05
3030000 -15.09 -14.57 5250 0.054325000000000005 7.462500000000001e-05
3040000 -15.05 -14.57 5264 0.0541 7.45e-05
3050000 -15.11 -14.57 5278 0.053875000000000006 7.4375e-05
3060000 -15.04 -14.57 5292 0.053649999999999996 7.425e-05
3070000 -14.96 -14.57 5306 0.053425 7.4125e-05
3080000 -15.13 -14.57 5322 0.0532 7.400000000000001e-05
3090000 -14.77 -14.57 5336 0.052975 7.3875e-05
3100000 -14.86 -14.57 5350 0.05275 7.375e-05
3110000 -14.9 -14.57 5365 0.052525 7.3625e-05
3120000 -14.93 -14.57 5378 0.0523 7.35e-05
3130000 -14.98 -14.57 5392 0.052075 7.337500000000001e-05
3140000 -15.26 -14.57 5407 0.05185 7.325e-05
3150000 -15.13 -14.57 5421 0.051625000000000004 7.3125e-05
3160000 -15.24 -14.57 5435 0.051399999999999994 7.3e-05
3170000 -15.34 -14.57 5450 0.051175 7.2875e-05
3180000 -15.43 -14.57 5464 0.050949999999999995 7.275e-05
3190000 -15.39 -14.57 5477 0.050725 7.2625e-05
3200000 -15.6 -14.57 5492 0.050499999999999996 7.25e-05
3210000 -15.3 -14.57 5504 0.050275 7.237500000000001e-05
3220000 -15.34 -14.57 5516 0.05005 7.225e-05
3230000 -15.32 -14.57 5530 0.049825 7.2125e-05
3240000 -15.1 -14.57 5542 0.0496 7.2e-05
3250000 -14.92 -14.57 5554 0.049375 7.1875e-05
3260000 -14.79 -14.57 5568 0.049150000000000006 7.175000000000001e-05
3270000 -14.71 -14.57 5580 0.048924999999999996 7.1625e-05
3280000 -14.64 -14.57 5594 0.04870000000000001 7.15e-05
3290000 -14.7 -14.57 5607 0.048475 7.1375e-05
3300000 -14.47 -14.47 5619 0.04825 7.125000000000001e-05
3310000 -14.4 -14.4 5631 0.048025 7.112500000000001e-05
3320000 -14.65 -14.4 5641 0.0478 7.1e-05
3330000 -14.88 -14.4 5653 0.047575 7.0875e-05
3340000 -15.23 -14.4 5666 0.04735 7.075000000000001e-05
3350000 -15.67 -14.4 5678 0.047125 7.0625e-05
3360000 -16.0 -14.4 5690 0.046900000000000004 7.05e-05
3370000 -16.39 -14.4 5702 0.046674999999999994 7.0375e-05
3380000 -16.91 -14.4 5714 0.04645 7.025e-05
3390000 -17.33 -14.4 5727 0.046224999999999995 7.0125e-05
3400000 -17.71 -14.4 5740 0.046 7.000000000000001e-05
3410000 -17.85 -14.4 5753 0.045774999999999996 6.9875e-05
3420000 -17.72 -14.4 5765 0.04555 6.975e-05
3430000 -17.37 -14.4 5777 0.045325 6.9625e-05
3440000 -17.06 -14.4 5789 0.0451 6.950000000000001e-05
3450000 -16.67 -14.4 5800 0.044875 6.937499999999999e-05
3460000 -16.27 -14.4 5814 0.04465 6.925e-05
3470000 -15.84 -14.4 5827 0.04442499999999999 6.9125e-05
3480000 -15.31 -14.4 5841 0.044199999999999996 6.9e-05
3490000 -14.7 -14.4 5853 0.04397499999999999 6.887500000000001e-05
3500000 -14.53 -14.4 5866 0.04375 6.875e-05
3510000 -14.5 -14.4 5879 0.043525 6.8625e-05
3520000 -14.61 -14.4 5893 0.0433 6.850000000000001e-05
3530000 -14.85 -14.4 5907 0.043075 6.837500000000001e-05
3540000 -14.84 -14.4 5920 0.04285 6.825e-05
3550000 -14.84 -14.4 5933 0.042625 6.8125e-05
3560000 -14.97 -14.4 5945 0.0424 6.8e-05
3570000 -15.28 -14.4 5957 0.042175000000000004 6.787500000000001e-05
3580000 -15.09 -14.4 5969 0.041949999999999994 6.775e-05
3590000 -15.04 -14.4 5983 0.041725000000000005 6.7625e-05
3600000 -14.96 -14.4 5995 0.041499999999999995 6.75e-05
3610000 -14.86 -14.4 6008 0.041275 6.7375e-05
3620000 -14.91 -14.4 6022 0.041049999999999996 6.725000000000001e-05
3630000 -14.95 -14.4 6035 0.040825 6.7125e-05
3640000 -14.76 -14.4 6048 0.0406 6.7e-05
3650000 -14.77 -14.4 6060 0.040375 6.687500000000001e-05
3660000 -14.87 -14.4 6072 0.04015 6.675e-05
3670000 -14.92 -14.4 6085 0.039925 6.6625e-05
3680000 -14.77 -14.4 6097 0.03969999999999999 6.65e-05
3690000 -14.75 -14.4 6109 0.039474999999999996 6.6375e-05
3700000 -14.62 -14.4 6121 0.03924999999999999 6.625e-05
3710000 -14.4 -14.39 6133 0.039025 6.6125e-05
3720000 -14.51 -14.39 6146 0.038799999999999994 6.6e-05
3730000 -14.62 -14.39 6159 0.038575 6.5875e-05
3740000 -14.52 -14.39 6171 0.038349999999999995 6.575e-05
3750000 -14.4 -14.39 6183 0.038125 6.562500000000001e-05
3760000 -14.41 -14.35 6195 0.0379 6.55e-05
3770000 -14.29 -14.28 6206 0.037675 6.5375e-05
3780000 -14.26 -14.2 6219 0.03745 6.525000000000001e-05
3790000 -14.36 -14.2 6231 0.037224999999999994 6.5125e-05
3800000 -14.22 -14.2 6243 0.037000000000000005 6.500000000000001e-05
3810000 -14.04 -14.03 6255 0.036775 6.4875e-05
3820000 -14.14 -13.99 6267 0.03655 6.475e-05
3830000 -13.98 -13.95 6278 0.036324999999999996 6.462500000000001e-05
3840000 -13.97 -13.85 6289 0.03610000000000001 6.45e-05
3850000 -14.05 -13.85 6300 0.03587499999999999 6.4375e-05
3860000 -14.27 -13.85 6312 0.03565 6.425e-05
3870000 -14.47 -13.85 6325 0.035425 6.4125e-05
3880000 -14.45 -13.85 6335 0.035199999999999995 6.400000000000001e-05
3890000 -14.54 -13.85 6346 0.03497499999999999 6.3875e-05
3900000 -14.66 -13.85 6358 0.03475 6.375e-05
3910000 -14.76 -13.85 6368 0.034525 6.3625e-05
3920000 -15.1 -13.85 6379 0.0343 6.35e-05
3930000 -15.27 -13.85 6390 0.034074999999999994 6.337500000000001e-05
3940000 -15.35 -13.85 6401 0.033850000000000005 6.325e-05
3950000 -15.32 -13.85 6412 0.03362499999999999 6.3125e-05
3960000 -15.42 -13.85 6423 0.0334 6.300000000000001e-05
3970000 -15.48 -13.85 6434 0.033174999999999996 6.2875e-05
3980000 -15.46 -13.85 6447 0.03294999999999999 6.275000000000001e-05
3990000 -15.3 -13.85 6460 0.03272499999999999 6.262499999999999e-05
4000000 -15.26 -13.85 6474 0.0325 6.25e-05
4010000 -15.17 -13.85 6487 0.032275 6.237500000000001e-05
4020000 -15.05 -13.85 6501 0.032049999999999995 6.225e-05
4030000 -14.95 -13.85 6514 0.031825000000000006 6.2125e-05
4040000 -14.53 -13.85 6526 0.0316 6.2e-05
4050000 -14.55 -13.85 6539 0.031375 6.1875e-05
4060000 -14.64 -13.85 6552 0.031149999999999997 6.175000000000001e-05
4070000 -14.64 -13.85 6565 0.030924999999999994 6.162500000000001e-05
4080000 -14.62 -13.85 6578 0.03069999999999999 6.15e-05
4090000 -14.39 -13.85 6591 0.030475000000000002 6.137500000000001e-05
4100000 -14.46 -13.85 6604 0.03025 6.125e-05
4110000 -14.46 -13.85 6617 0.030024999999999996 6.112500000000001e-05
4120000 -14.61 -13.85 6631 0.029799999999999993 6.1e-05
4130000 -14.4 -13.85 6643 0.029575000000000004 6.0875e-05
4140000 -14.36 -13.85 6655 0.02935 6.075e-05
4150000 -14.33 -13.85 6668 0.029124999999999998 6.0625e-05
4160000 -14.4 -13.85 6681 0.028899999999999995 6.05e-05
4170000 -14.51 -13.85 6695 0.028674999999999992 6.0375000000000004e-05
4180000 -14.33 -13.85 6706 0.02844999999999999 6.025e-05
4190000 -14.38 -13.85 6719 0.028225 6.0125000000000005e-05
4200000 -14.34 -13.85 6731 0.027999999999999997 6e-05
4210000 -14.49 -13.85 6744 0.027774999999999994 5.9875000000000005e-05
4220000 -14.4 -13.85 6756 0.02754999999999999 5.975e-05
4230000 -14.3 -13.85 6768 0.027325000000000002 5.9625000000000006e-05
4240000 -14.39 -13.85 6781 0.0271 5.95e-05
4250000 -14.3 -13.85 6794 0.026874999999999996 5.9375e-05
4260000 -14.46 -13.85 6807 0.026650000000000007 5.9250000000000004e-05
4270000 -14.3 -13.85 6820 0.02642499999999999 5.9125e-05
4280000 -14.64 -13.85 6834 0.0262 5.9000000000000004e-05
4290000 -14.52 -13.85 6846 0.025974999999999998 5.8875e-05
4300000 -14.37 -13.85 6857 0.025749999999999995 5.8750000000000005e-05
4310000 -14.23 -13.85 6869 0.025524999999999992 5.8625e-05
4320000 -14.16 -13.85 6882 0.025300000000000003 5.8500000000000006e-05
4330000 -14.26 -13.85 6894 0.025075 5.8375e-05
4340000 -14.11 -13.85 6907 0.024849999999999997 5.8250000000000006e-05
4350000 -14.15 -13.85 6919 0.024624999999999994 5.8125e-05
4360000 -13.77 -13.77 6931 0.024400000000000005 5.800000000000001e-05
4370000 -13.85 -13.74 6943 0.024174999999999988 5.7875000000000004e-05
4380000 -14.08 -13.74 6956 0.02395 5.775e-05
4390000 -14.17 -13.74 6967 0.023724999999999996 5.7625e-05
4400000 -14.26 -13.74 6980 0.023499999999999993 5.75e-05
4410000 -14.28 -13.74 6992 0.02327499999999999 5.7375e-05
4420000 -14.25 -13.74 7004 0.02305 5.725e-05
4430000 -14.02 -13.74 7015 0.022824999999999998 5.7125e-05
4440000 -14.18 -13.74 7027 0.022599999999999995 5.7e-05
4450000 -14.23 -13.74 7039 0.022374999999999992 5.6875e-05
4460000 -14.41 -13.74 7052 0.022150000000000003 5.6750000000000004e-05
4470000 -14.32 -13.74 7066 0.021924999999999986 5.6625e-05
4480000 -14.29 -13.74 7078 0.021699999999999997 5.6500000000000005e-05
4490000 -14.14 -13.74 7090 0.021474999999999994 5.6375e-05
4500000 -14.19 -13.74 7103 0.02124999999999999 5.6250000000000005e-05
4510000 -14.21 -13.74 7115 0.021025000000000002 5.6125e-05
4520000 -14.19 -13.74 7128 0.0208 5.6e-05
4530000 -14.21 -13.74 7140 0.020574999999999996 5.5875e-05
4540000 -13.94 -13.74 7151 0.020349999999999993 5.575e-05
4550000 -13.86 -13.74 7163 0.020125000000000004 5.5625000000000004e-05
4560000 -13.75 -13.74 7174 0.0199 5.55e-05
4570000 -14.06 -13.72 7188 0.019674999999999998 5.5375000000000004e-05
4580000 -13.88 -13.72 7198 0.019449999999999995 5.525e-05
4590000 -13.93 -13.72 7210 0.019225000000000006 5.5125000000000005e-05
4600000 -13.95 -13.72 7221 0.01899999999999999 5.5e-05
4610000 -13.95 -13.72 7232 0.018775 5.4875000000000006e-05
4620000 -13.98 -13.72 7244 0.018549999999999997 5.475e-05
4630000 -14.12 -13.72 7255 0.018324999999999994 5.4625000000000006e-05
4640000 -14.31 -13.72 7267 0.01809999999999999 5.45e-05
4650000 -14.25 -13.72 7279 0.017875000000000002 5.437500000000001e-05
4660000 -14.14 -13.72 7291 0.01765 5.4250000000000004e-05
4670000 -14.06 -13.72 7302 0.017424999999999996 5.4125e-05
4680000 -14.02 -13.72 7313 0.017199999999999993 5.4e-05
4690000 -13.87 -13.72 7324 0.01697499999999999 5.3875e-05
4700000 -14.03 -13.72 7336 0.016749999999999987 5.375e-05
4710000 -14.16 -13.72 7349 0.016524999999999998 5.3625e-05
4720000 -14.05 -13.72 7360 0.016299999999999995 5.35e-05
4730000 -13.98 -13.72 7371 0.016074999999999992 5.3375e-05
4740000 -14.28 -13.72 7383 0.01584999999999999 5.325e-05
4750000 -14.2 -13.72 7394 0.015625 5.3125000000000004e-05
4760000 -14.24 -13.72 7406 0.015399999999999997 5.300000000000001e-05
4770000 -14.02 -13.72 7416 0.015174999999999994 5.2875000000000005e-05
4780000 -14.09 -13.72 7429 0.014950000000000005 5.275000000000001e-05
4790000 -13.96 -13.72 7441 0.014724999999999988 5.2625000000000005e-05
4800000 -13.8 -13.72 7452 0.014499999999999999 5.25e-05
4810000 -13.85 -13.72 7463 0.014274999999999996 5.2375e-05
4820000 -13.75 -13.72 7475 0.014049999999999993 5.225e-05
4830000 -13.62 -13.59 7486 0.01382499999999999 5.2125e-05
4840000 -13.59 -13.58 7497 0.013600000000000001 5.2000000000000004e-05
4850000 -13.41 -13.38 7508 0.013374999999999998 5.1875e-05
4860000 -13.65 -13.38 7519 0.013149999999999995 5.1750000000000004e-05
4870000 -13.51 -13.38 7531 0.012924999999999992 5.1625e-05
4880000 -13.41 -13.38 7541 0.012700000000000003 5.1500000000000005e-05
4890000 -13.31 -13.28 7551 0.012474999999999986 5.1375e-05
4900000 -13.25 -13.23 7562 0.012249999999999997 5.1250000000000006e-05
4910000 -13.21 -13.21 7575 0.012024999999999994 5.1125e-05
4920000 -13.33 -13.11 7586 0.011799999999999991 5.1000000000000006e-05
4930000 -13.28 -13.11 7597 0.011574999999999988 5.0875e-05
4940000 -13.5 -13.11 7610 0.011349999999999999 5.075e-05
4950000 -13.55 -13.11 7622 0.011124999999999996 5.0625e-05
4960000 -13.52 -13.11 7633 0.010899999999999993 5.05e-05
4970000 -13.53 -13.11 7644 0.01067499999999999 5.0375e-05
4980000 -13.53 -13.11 7655 0.010450000000000001 5.025e-05
4990000 -13.52 -13.11 7666 0.010224999999999984 5.0125e-05
5000000 -13.65 -13.11 7678 0.01 5e-05
5010000 -13.77 -13.11 7690 0.01 5e-05
5020000 -13.62 -13.11 7701 0.01 5e-05
5030000 -13.62 -13.11 7713 0.01 5e-05
5040000 -13.58 -13.11 7724 0.01 5e-05
5050000 -13.73 -13.11 7737 0.01 5e-05
5060000 -14.01 -13.11 7749 0.01 5e-05
5070000 -14.26 -13.11 7762 0.01 5e-05
5080000 -14.08 -13.11 7773 0.01 5e-05
5090000 -13.85 -13.11 7784 0.01 5e-05
5100000 -13.73 -13.11 7795 0.01 5e-05
5110000 -13.9 -13.11 7806 0.01 5e-05
5120000 -13.9 -13.11 7818 0.01 5e-05
5130000 -13.8 -13.11 7829 0.01 5e-05
5140000 -13.83 -13.11 7841 0.01 5e-05
5150000 -13.56 -13.11 7852 0.01 5e-05
5160000 -13.59 -13.11 7864 0.01 5e-05
5170000 -13.85 -13.11 7875 0.01 5e-05
5180000 -13.79 -13.11 7885 0.01 5e-05
5190000 -13.83 -13.11 7897 0.01 5e-05
5200000 -13.92 -13.11 7908 0.01 5e-05
5210000 -13.62 -13.11 7919 0.01 5e-05
5220000 -13.65 -13.11 7930 0.01 5e-05
5230000 -13.35 -13.11 7940 0.01 5e-05
5240000 -13.32 -13.11 7951 0.01 5e-05
5250000 -13.24 -13.11 7964 0.01 5e-05
5260000 -13.2 -13.11 7974 0.01 5e-05
5270000 -13.39 -13.11 7986 0.01 5e-05
5280000 -13.36 -13.11 7997 0.01 5e-05
5290000 -13.26 -13.11 8008 0.01 5e-05
5300000 -13.43 -13.11 8019 0.01 5e-05
5310000 -13.46 -13.11 8031 0.01 5e-05
5320000 -13.68 -13.11 8042 0.01 5e-05
5330000 -13.68 -13.11 8053 0.01 5e-05
5340000 -13.61 -13.11 8064 0.01 5e-05
5350000 -13.53 -13.11 8075 0.01 5e-05
5360000 -13.54 -13.11 8086 0.01 5e-05
5370000 -13.52 -13.11 8097 0.01 5e-05
5380000 -13.57 -13.11 8109 0.01 5e-05
5390000 -13.8 -13.11 8121 0.01 5e-05
5400000 -13.7 -13.11 8132 0.01 5e-05
5410000 -13.75 -13.11 8144 0.01 5e-05
5420000 -13.71 -13.11 8155 0.01 5e-05
5430000 -13.66 -13.11 8166 0.01 5e-05
5440000 -13.86 -13.11 8178 0.01 5e-05
5450000 -13.83 -13.11 8190 0.01 5e-05
5460000 -14.02 -13.11 8201 0.01 5e-05
5470000 -13.96 -13.11 8213 0.01 5e-05
5480000 -13.74 -13.11 8224 0.01 5e-05
5490000 -13.93 -13.11 8235 0.01 5e-05
5500000 -14.12 -13.11 8247 0.01 5e-05
5510000 -14.09 -13.11 8259 0.01 5e-05
5520000 -14.17 -13.11 8269 0.01 5e-05
5530000 -14.07 -13.11 8280 0.01 5e-05
5540000 -13.95 -13.11 8291 0.01 5e-05
5550000 -13.8 -13.11 8301 0.01 5e-05
5560000 -13.75 -13.11 8311 0.01 5e-05
5570000 -13.75 -13.11 8322 0.01 5e-05
5580000 -13.75 -13.11 8332 0.01 5e-05
5590000 -13.52 -13.11 8342 0.01 5e-05
5600000 -13.58 -13.11 8354 0.01 5e-05
5610000 -13.59 -13.11 8365 0.01 5e-05
5620000 -13.49 -13.11 8376 0.01 5e-05
5630000 -13.68 -13.11 8387 0.01 5e-05
5640000 -13.8 -13.11 8399 0.01 5e-05
5650000 -13.83 -13.11 8410 0.01 5e-05
5660000 -13.44 -13.11 8419 0.01 5e-05
5670000 -13.32 -13.11 8429 0.01 5e-05
5680000 -13.46 -13.11 8440 0.01 5e-05
5690000 -13.56 -13.11 8451 0.01 5e-05
5700000 -13.39 -13.11 8462 0.01 5e-05
5710000 -13.28 -13.11 8473 0.01 5e-05
5720000 -13.36 -13.11 8484 0.01 5e-05
5730000 -13.04 -13.03 8495 0.01 5e-05
5740000 -13.4 -13.03 8508 0.01 5e-05
5750000 -13.61 -13.03 8519 0.01 5e-05
5760000 -13.77 -13.03 8530 0.01 5e-05
5770000 -13.72 -13.03 8542 0.01 5e-05
5780000 -13.55 -13.03 8553 0.01 5e-05
5790000 -13.72 -13.03 8565 0.01 5e-05
5800000 -13.81 -13.03 8576 0.01 5e-05
5810000 -13.82 -13.03 8587 0.01 5e-05
5820000 -13.85 -13.03 8598 0.01 5e-05
5830000 -13.76 -13.03 8610 0.01 5e-05
5840000 -13.68 -13.03 8621 0.01 5e-05
5850000 -13.75 -13.03 8634 0.01 5e-05
5860000 -13.94 -13.03 8646 0.01 5e-05
5870000 -13.85 -13.03 8656 0.01 5e-05
5880000 -13.79 -13.03 8668 0.01 5e-05
5890000 -13.57 -13.03 8677 0.01 5e-05
5900000 -13.33 -13.03 8687 0.01 5e-05
5910000 -13.25 -13.03 8698 0.01 5e-05
5920000 -13.35 -13.03 8710 0.01 5e-05
5930000 -13.41 -13.03 8721 0.01 5e-05
5940000 -13.3 -13.03 8732 0.01 5e-05
5950000 -13.14 -13.03 8743 0.01 5e-05
5960000 -13.24 -13.03 8754 0.01 5e-05
5970000 -13.19 -13.03 8766 0.01 5e-05
5980000 -13.22 -13.03 8776 0.01 5e-05
5990000 -13.31 -13.03 8787 0.01 5e-05
6000000 -13.31 -13.03 8798 0.01 5e-05
6010000 -13.23 -13.03 8810 0.01 5e-05
6020000 -13.14 -13.03 8821 0.01 5e-05
6030000 -13.18 -13.03 8832 0.01 5e-05
6040000 -13.19 -13.03 8844 0.01 5e-05
6050000 -13.28 -13.01 8855 0.01 5e-05
6060000 -13.24 -13.01 8867 0.01 5e-05
6070000 -13.44 -13.01 8877 0.01 5e-05
6080000 -13.59 -13.01 8889 0.01 5e-05
6090000 -13.79 -13.01 8902 0.01 5e-05
6100000 -13.65 -13.01 8912 0.01 5e-05
6110000 -13.81 -13.01 8924 0.01 5e-05
6120000 -13.69 -13.01 8935 0.01 5e-05
6130000 -13.69 -13.01 8946 0.01 5e-05
6140000 -13.71 -13.01 8958 0.01 5e-05
6150000 -13.9 -13.01 8971 0.01 5e-05
6160000 -14.01 -13.01 8983 0.01 5e-05
6170000 -14.01 -13.01 8995 0.01 5e-05
6180000 -14.08 -13.01 9006 0.01 5e-05
6190000 -14.14 -13.01 9017 0.01 5e-05
6200000 -14.26 -13.01 9029 0.01 5e-05
6210000 -14.41 -13.01 9040 0.01 5e-05
6220000 -14.38 -13.01 9051 0.01 5e-05
6230000 -14.19 -13.01 9063 0.01 5e-05
6240000 -13.94 -13.01 9073 0.01 5e-05
6250000 -13.74 -13.01 9083 0.01 5e-05
6260000 -13.72 -13.01 9094 0.01 5e-05
6270000 -13.53 -13.01 9103 0.01 5e-05
6280000 -13.47 -13.01 9115 0.01 5e-05
6290000 -13.17 -13.01 9125 0.01 5e-05
6300000 -12.97 -12.97 9136 0.01 5e-05
6310000 -13.26 -12.97 9148 0.01 5e-05
6320000 -13.34 -12.97 9159 0.01 5e-05
6330000 -13.21 -12.97 9170 0.01 5e-05
6340000 -13.6 -12.97 9183 0.01 5e-05
6350000 -13.68 -12.97 9194 0.01 5e-05
6360000 -13.76 -12.97 9205 0.01 5e-05
6370000 -13.75 -12.97 9216 0.01 5e-05
6380000 -13.7 -12.97 9225 0.01 5e-05
6390000 -13.81 -12.97 9236 0.01 5e-05
6400000 -13.65 -12.97 9246 0.01 5e-05
6410000 -13.41 -12.97 9255 0.01 5e-05
6420000 -13.64 -12.97 9267 0.01 5e-05
6430000 -13.61 -12.97 9277 0.01 5e-05
6440000 -13.26 -12.97 9287 0.01 5e-05
6450000 -13.23 -12.97 9297 0.01 5e-05
6460000 -13.17 -12.97 9308 0.01 5e-05
6470000 -13.05 -12.97 9318 0.01 5e-05
6480000 -13.31 -12.97 9329 0.01 5e-05
6490000 -13.09 -12.97 9339 0.01 5e-05
6500000 -13.04 -12.97 9349 0.01 5e-05
6510000 -13.19 -12.97 9360 0.01 5e-05
6520000 -13.27 -12.97 9372 0.01 5e-05
6530000 -13.15 -12.97 9382 0.01 5e-05
6540000 -13.48 -12.97 9395 0.01 5e-05
6550000 -13.64 -12.97 9406 0.01 5e-05
6560000 -13.69 -12.97 9416 0.01 5e-05
6570000 -13.63 -12.97 9426 0.01 5e-05
6580000 -13.66 -12.97 9437 0.01 5e-05
6590000 -13.43 -12.97 9447 0.01 5e-05
6600000 -13.67 -12.97 9458 0.01 5e-05
6610000 -13.59 -12.97 9469 0.01 5e-05
6620000 -13.7 -12.97 9480 0.01 5e-05
6630000 -13.49 -12.97 9491 0.01 5e-05
6640000 -13.47 -12.97 9503 0.01 5e-05
6650000 -13.46 -12.97 9512 0.01 5e-05
6660000 -13.24 -12.97 9522 0.01 5e-05
6670000 -13.13 -12.97 9532 0.01 5e-05
6680000 -13.08 -12.97 9543 0.01 5e-05
6690000 -13.18 -12.97 9554 0.01 5e-05
6700000 -13.24 -12.97 9565 0.01 5e-05
6710000 -13.21 -12.97 9576 0.01 5e-05
6720000 -13.27 -12.97 9588 0.01 5e-05
6730000 -13.22 -12.97 9599 0.01 5e-05
6740000 -13.02 -12.97 9608 0.01 5e-05
6750000 -13.3 -12.97 9619 0.01 5e-05
6760000 -13.3 -12.97 9629 0.01 5e-05
6770000 -13.41 -12.97 9640 0.01 5e-05
6780000 -13.45 -12.97 9652 0.01 5e-05
6790000 -13.15 -12.97 9662 0.01 5e-05
6800000 -13.18 -12.97 9673 0.01 5e-05
6810000 -13.4 -12.97 9685 0.01 5e-05
6820000 -13.23 -12.97 9695 0.01 5e-05
6830000 -13.36 -12.97 9706 0.01 5e-05
6840000 -13.29 -12.97 9716 0.01 5e-05
6850000 -13.26 -12.97 9726 0.01 5e-05
6860000 -13.06 -12.97 9735 0.01 5e-05
6870000 -13.19 -12.97 9747 0.01 5e-05
6880000 -13.36 -12.97 9758 0.01 5e-05
6890000 -13.44 -12.97 9768 0.01 5e-05
6900000 -13.05 -12.97 9778 0.01 5e-05
6910000 -13.1 -12.9 9789 0.01 5e-05
6920000 -13.27 -12.9 9801 0.01 5e-05
6930000 -13.27 -12.9 9811 0.01 5e-05
6940000 -13.28 -12.9 9821 0.01 5e-05
6950000 -13.35 -12.9 9832 0.01 5e-05
6960000 -13.17 -12.9 9842 0.01 5e-05
6970000 -13.19 -12.9 9852 0.01 5e-05
6980000 -13.31 -12.9 9863 0.01 5e-05
6990000 -13.28 -12.9 9873 0.01 5e-05
7000000 -13.3 -12.9 9883 0.01 5e-05
7010000 -13.17 -12.9 9892 0.01 5e-05
7020000 -12.96 -12.9 9903 0.01 5e-05
7030000 -12.77 -12.71 9912 0.01 5e-05
7040000 -13.12 -12.71 9924 0.01 5e-05
7050000 -13.1 -12.71 9935 0.01 5e-05
7060000 -13.11 -12.71 9945 0.01 5e-05
7070000 -13.13 -12.71 9956 0.01 5e-05
7080000 -13.04 -12.71 9966 0.01 5e-05
7090000 -13.16 -12.71 9977 0.01 5e-05
7100000 -13.12 -12.71 9987 0.01 5e-05
7110000 -13.06 -12.71 9998 0.01 5e-05
7120000 -13.31 -12.71 10009 0.01 5e-05
7130000 -13.32 -12.71 10021 0.01 5e-05
7140000 -13.37 -12.71 10032 0.01 5e-05
7150000 -13.41 -12.71 10044 0.01 5e-05
7160000 -13.47 -12.71 10055 0.01 5e-05
7170000 -13.45 -12.71 10066 0.01 5e-05
7180000 -13.4 -12.71 10078 0.01 5e-05
7190000 -13.55 -12.71 10089 0.01 5e-05
7200000 -13.64 -12.71 10100 0.01 5e-05
7210000 -13.73 -12.71 10112 0.01 5e-05
7220000 -13.61 -12.71 10122 0.01 5e-05
7230000 -13.63 -12.71 10133 0.01 5e-05
7240000 -13.62 -12.71 10144 0.01 5e-05
7250000 -13.51 -12.71 10155 0.01 5e-05
7260000 -13.55 -12.71 10166 0.01 5e-05
7270000 -13.32 -12.71 10176 0.01 5e-05
7280000 -13.36 -12.71 10189 0.01 5e-05
7290000 -13.44 -12.71 10199 0.01 5e-05
7300000 -13.35 -12.71 10210 0.01 5e-05
7310000 -13.3 -12.71 10221 0.01 5e-05
7320000 -13.42 -12.71 10233 0.01 5e-05
7330000 -13.46 -12.71 10244 0.01 5e-05
7340000 -13.34 -12.71 10254 0.01 5e-05
7350000 -13.34 -12.71 10265 0.01 5e-05
7360000 -13.61 -12.71 10277 0.01 5e-05
7370000 -13.45 -12.71 10287 0.01 5e-05
7380000 -13.55 -12.71 10299 0.01 5e-05
7390000 -13.59 -12.71 10311 0.01 5e-05
7400000 -13.69 -12.71 10321 0.01 5e-05
7410000 -13.5 -12.71 10331 0.01 5e-05
7420000 -13.48 -12.71 10342 0.01 5e-05
7430000 -13.32 -12.71 10351 0.01 5e-05
7440000 -13.32 -12.71 10360 0.01 5e-05
7450000 -13.23 -12.71 10372 0.01 5e-05
7460000 -13.4 -12.71 10383 0.01 5e-05
7470000 -13.25 -12.71 10393 0.01 5e-05
7480000 -13.17 -12.71 10404 0.01 5e-05
7490000 -13.27 -12.71 10415 0.01 5e-05
7500000 -13.44 -12.71 10426 0.01 5e-05
7510000 -13.27 -12.71 10437 0.01 5e-05
7520000 -13.52 -12.71 10449 0.01 5e-05
7530000 -13.8 -12.71 10461 0.01 5e-05
7540000 -13.75 -12.71 10472 0.01 5e-05
7550000 -13.66 -12.71 10483 0.01 5e-05
7560000 -13.81 -12.71 10493 0.01 5e-05
7570000 -13.91 -12.71 10505 0.01 5e-05
7580000 -13.8 -12.71 10516 0.01 5e-05
7590000 -13.98 -12.71 10528 0.01 5e-05
7600000 -14.27 -12.71 10539 0.01 5e-05
7610000 -13.97 -12.71 10548 0.01 5e-05
7620000 -13.76 -12.71 10559 0.01 5e-05
7630000 -13.74 -12.71 10570 0.01 5e-05
7640000 -13.7 -12.71 10581 0.01 5e-05
7650000 -13.6 -12.71 10591 0.01 5e-05
7660000 -13.45 -12.71 10603 0.01 5e-05
7670000 -13.51 -12.71 10613 0.01 5e-05
7680000 -13.21 -12.71 10624 0.01 5e-05
7690000 -13.07 -12.71 10634 0.01 5e-05
7700000 -13.05 -12.71 10644 0.01 5e-05
7710000 -12.93 -12.71 10654 0.01 5e-05
7720000 -13.17 -12.71 10666 0.01 5e-05
7730000 -13.31 -12.71 10679 0.01 5e-05
7740000 -13.44 -12.71 10690 0.01 5e-05
7750000 -13.31 -12.71 10700 0.01 5e-05
7760000 -13.35 -12.71 10711 0.01 5e-05
7770000 -13.36 -12.71 10720 0.01 5e-05
7780000 -13.4 -12.71 10731 0.01 5e-05
7790000 -13.59 -12.71 10742 0.01 5e-05
7800000 -13.83 -12.71 10753 0.01 5e-05
7810000 -13.81 -12.71 10764 0.01 5e-05
7820000 -13.83 -12.71 10775 0.01 5e-05
7830000 -13.69 -12.71 10786 0.01 5e-05
7840000 -14.03 -12.71 10797 0.01 5e-05
7850000 -14.15 -12.71 10807 0.01 5e-05
7860000 -14.21 -12.71 10818 0.01 5e-05
7870000 -14.19 -12.71 10829 0.01 5e-05
7880000 -13.98 -12.71 10839 0.01 5e-05
7890000 -13.76 -12.71 10849 0.01 5e-05
7900000 -13.82 -12.71 10861 0.01 5e-05
7910000 -13.76 -12.71 10873 0.01 5e-05
7920000 -13.67 -12.71 10884 0.01 5e-05
7930000 -13.66 -12.71 10895 0.01 5e-05
7940000 -13.64 -12.71 10905 0.01 5e-05
7950000 -13.55 -12.71 10916 0.01 5e-05
7960000 -13.44 -12.71 10925 0.01 5e-05
7970000 -13.52 -12.71 10935 0.01 5e-05
7980000 -13.67 -12.71 10946 0.01 5e-05
7990000 -13.66 -12.71 10956 0.01 5e-05
8000000 -13.42 -12.71 10966 0.01 5e-05
8010000 -13.25 -12.71 10976 0.01 5e-05
8020000 -13.08 -12.71 10986 0.01 5e-05
8030000 -12.94 -12.71 10996 0.01 5e-05
8040000 -13.01 -12.71 11008 0.01 5e-05
8050000 -13.02 -12.71 11019 0.01 5e-05
8060000 -13.15 -12.71 11030 0.01 5e-05
8070000 -12.97 -12.71 11040 0.01 5e-05
8080000 -12.95 -12.71 11050 0.01 5e-05
8090000 -13.05 -12.71 11062 0.01 5e-05
8100000 -13.14 -12.71 11073 0.01 5e-05
8110000 -13.51 -12.71 11085 0.01 5e-05
8120000 -13.52 -12.71 11096 0.01 5e-05
8130000 -13.32 -12.71 11106 0.01 5e-05
8140000 -13.3 -12.71 11116 0.01 5e-05
8150000 -13.3 -12.71 11126 0.01 5e-05
8160000 -13.52 -12.71 11136 0.01 5e-05
8170000 -13.6 -12.71 11147 0.01 5e-05
8180000 -13.57 -12.71 11158 0.01 5e-05
8190000 -13.25 -12.71 11168 0.01 5e-05
8200000 -13.13 -12.71 11178 0.01 5e-05
8210000 -13.0 -12.71 11188 0.01 5e-05
8220000 -12.96 -12.71 11198 0.01 5e-05
8230000 -12.98 -12.71 11210 0.01 5e-05
8240000 -13.14 -12.71 11221 0.01 5e-05
8250000 -13.25 -12.71 11232 0.01 5e-05
8260000 -13.2 -12.71 11243 0.01 5e-05
8270000 -13.19 -12.71 11253 0.01 5e-05
8280000 -13.08 -12.71 11264 0.01 5e-05
8290000 -13.13 -12.71 11274 0.01 5e-05
8300000 -13.23 -12.71 11285 0.01 5e-05
8310000 -13.27 -12.71 11295 0.01 5e-05
8320000 -13.27 -12.71 11305 0.01 5e-05
8330000 -13.37 -12.71 11316 0.01 5e-05
8340000 -13.09 -12.71 11327 0.01 5e-05
8350000 -12.99 -12.71 11337 0.01 5e-05
8360000 -13.02 -12.71 11347 0.01 5e-05
8370000 -13.12 -12.71 11358 0.01 5e-05
8380000 -13.12 -12.71 11370 0.01 5e-05
8390000 -13.18 -12.71 11381 0.01 5e-05
8400000 -13.29 -12.71 11392 0.01 5e-05
8410000 -13.34 -12.71 11404 0.01 5e-05
8420000 -13.41 -12.71 11414 0.01 5e-05
8430000 -13.53 -12.71 11425 0.01 5e-05
8440000 -13.58 -12.71 11435 0.01 5e-05
8450000 -13.74 -12.71 11446 0.01 5e-05
8460000 -13.65 -12.71 11455 0.01 5e-05
8470000 -13.56 -12.71 11465 0.01 5e-05
8480000 -13.49 -12.71 11474 0.01 5e-05
8490000 -13.47 -12.71 11484 0.01 5e-05
8500000 -13.18 -12.71 11494 0.01 5e-05
8510000 -12.99 -12.71 11503 0.01 5e-05
8520000 -12.7 -12.67 11512 0.01 5e-05
8530000 -12.84 -12.67 11524 0.01 5e-05
8540000 -12.75 -12.67 11533 0.01 5e-05
8550000 -12.6 -12.59 11542 0.01 5e-05
8560000 -12.69 -12.58 11551 0.01 5e-05
8570000 -12.75 -12.58 11561 0.01 5e-05
8580000 -12.86 -12.58 11572 0.01 5e-05
8590000 -12.9 -12.58 11583 0.01 5e-05
8600000 -13.18 -12.58 11593 0.01 5e-05
8610000 -13.28 -12.58 11603 0.01 5e-05
8620000 -13.51 -12.58 11614 0.01 5e-05
8630000 -13.25 -12.58 11624 0.01 5e-05
8640000 -13.29 -12.58 11634 0.01 5e-05
8650000 -13.21 -12.58 11644 0.01 5e-05
8660000 -13.04 -12.58 11654 0.01 5e-05
8670000 -12.99 -12.58 11665 0.01 5e-05
8680000 -12.92 -12.58 11675 0.01 5e-05
8690000 -12.84 -12.58 11686 0.01 5e-05
8700000 -12.7 -12.58 11696 0.01 5e-05
8710000 -12.81 -12.58 11707 0.01 5e-05
8720000 -12.75 -12.58 11717 0.01 5e-05
8730000 -12.96 -12.58 11727 0.01 5e-05
8740000 -12.73 -12.58 11737 0.01 5e-05
8750000 -12.78 -12.58 11747 0.01 5e-05
8760000 -13.0 -12.58 11758 0.01 5e-05
8770000 -12.82 -12.58 11767 0.01 5e-05
8780000 -12.87 -12.58 11778 0.01 5e-05
8790000 -12.92 -12.58 11789 0.01 5e-05
8800000 -12.89 -12.58 11798 0.01 5e-05
8810000 -12.9 -12.58 11809 0.01 5e-05
8820000 -12.98 -12.58 11820 0.01 5e-05
8830000 -12.97 -12.58 11830 0.01 5e-05
8840000 -13.12 -12.58 11840 0.01 5e-05
8850000 -13.11 -12.58 11850 0.01 5e-05
8860000 -13.05 -12.58 11860 0.01 5e-05
8870000 -13.12 -12.58 11870 0.01 5e-05
8880000 -13.08 -12.58 11880 0.01 5e-05
8890000 -13.04 -12.58 11891 0.01 5e-05
8900000 -13.06 -12.58 11902 0.01 5e-05
8910000 -13.01 -12.58 11912 0.01 5e-05
8920000 -12.78 -12.58 11922 0.01 5e-05
8930000 -12.81 -12.58 11933 0.01 5e-05
8940000 -13.01 -12.58 11945 0.01 5e-05
8950000 -13.15 -12.58 11956 0.01 5e-05
8960000 -13.11 -12.58 11966 0.01 5e-05
8970000 -12.83 -12.58 11974 0.01 5e-05
8980000 -12.87 -12.58 11986 0.01 5e-05
8990000 -12.76 -12.58 11995 0.01 5e-05
9000000 -12.81 -12.58 12005 0.01 5e-05
9010000 -12.81 -12.58 12015 0.01 5e-05
9020000 -13.03 -12.58 12026 0.01 5e-05
9030000 -12.99 -12.58 12036 0.01 5e-05
9040000 -12.91 -12.58 12046 0.01 5e-05
9050000 -12.76 -12.58 12056 0.01 5e-05
9060000 -12.89 -12.58 12067 0.01 5e-05
9070000 -12.97 -12.58 12077 0.01 5e-05
9080000 -12.95 -12.58 12087 0.01 5e-05
9090000 -13.1 -12.58 12098 0.01 5e-05
9100000 -12.85 -12.58 12108 0.01 5e-05
9110000 -12.91 -12.58 12119 0.01 5e-05
9120000 -12.87 -12.58 12130 0.01 5e-05
9130000 -13.04 -12.58 12142 0.01 5e-05
9140000 -13.18 -12.58 12153 0.01 5e-05
9150000 -13.02 -12.58 12162 0.01 5e-05
9160000 -12.88 -12.58 12172 0.01 5e-05
9170000 -12.74 -12.58 12181 0.01 5e-05
9180000 -12.93 -12.58 12192 0.01 5e-05
9190000 -13.05 -12.58 12202 0.01 5e-05
9200000 -13.15 -12.58 12214 0.01 5e-05
9210000 -13.25 -12.58 12225 0.01 5e-05
9220000 -13.11 -12.58 12237 0.01 5e-05
9230000 -13.07 -12.58 12248 0.01 5e-05
9240000 -13.01 -12.58 12259 0.01 5e-05
9250000 -13.35 -12.58 12270 0.01 5e-05
9260000 -13.59 -12.58 12282 0.01 5e-05
9270000 -13.51 -12.58 12293 0.01 5e-05
9280000 -13.51 -12.58 12304 0.01 5e-05
9290000 -13.64 -12.58 12316 0.01 5e-05
9300000 -13.51 -12.58 12327 0.01 5e-05
9310000 -13.39 -12.58 12338 0.01 5e-05
9320000 -13.35 -12.58 12348 0.01 5e-05
9330000 -13.62 -12.58 12359 0.01 5e-05
9340000 -13.74 -12.58 12371 0.01 5e-05
9350000 -13.7 -12.58 12382 0.01 5e-05
9360000 -13.82 -12.58 12393 0.01 5e-05
9370000 -13.87 -12.58 12403 0.01 5e-05
9380000 -13.74 -12.58 12413 0.01 5e-05
9390000 -13.85 -12.58 12424 0.01 5e-05
9400000 -13.84 -12.58 12435 0.01 5e-05
9410000 -14.01 -12.58 12445 0.01 5e-05
9420000 -13.87 -12.58 12456 0.01 5e-05
9430000 -13.73 -12.58 12468 0.01 5e-05
9440000 -13.76 -12.58 12479 0.01 5e-05
9450000 -13.68 -12.58 12490 0.01 5e-05
9460000 -13.63 -12.58 12500 0.01 5e-05
9470000 -13.55 -12.58 12510 0.01 5e-05
9480000 -13.48 -12.58 12518 0.01 5e-05
9490000 -13.07 -12.58 12528 0.01 5e-05
9500000 -13.33 -12.58 12540 0.01 5e-05
9510000 -13.38 -12.58 12550 0.01 5e-05
9520000 -13.27 -12.58 12560 0.01 5e-05
9530000 -13.23 -12.58 12569 0.01 5e-05
9540000 -12.97 -12.58 12579 0.01 5e-05
9550000 -13.09 -12.58 12590 0.01 5e-05
9560000 -12.91 -12.58 12601 0.01 5e-05
9570000 -12.87 -12.58 12610 0.01 5e-05
9580000 -12.94 -12.58 12621 0.01 5e-05
9590000 -13.16 -12.58 12632 0.01 5e-05
9600000 -12.92 -12.58 12643 0.01 5e-05
9610000 -12.93 -12.58 12653 0.01 5e-05
9620000 -12.79 -12.58 12663 0.01 5e-05
9630000 -12.92 -12.58 12674 0.01 5e-05
9640000 -12.85 -12.58 12683 0.01 5e-05
9650000 -12.72 -12.58 12691 0.01 5e-05
9660000 -12.71 -12.58 12702 0.01 5e-05
9670000 -12.79 -12.58 12712 0.01 5e-05
9680000 -12.59 -12.58 12722 0.01 5e-05
9690000 -12.44 -12.42 12732 0.01 5e-05
9700000 -12.4 -12.35 12742 0.01 5e-05
9710000 -12.36 -12.28 12753 0.01 5e-05
9720000 -12.24 -12.08 12762 0.01 5e-05
9730000 -12.29 -12.08 12773 0.01 5e-05
9740000 -12.37 -12.08 12783 0.01 5e-05
9750000 -12.51 -12.08 12792 0.01 5e-05
9760000 -12.43 -12.08 12803 0.01 5e-05
9770000 -12.4 -12.08 12812 0.01 5e-05
9780000 -12.43 -12.08 12821 0.01 5e-05
9790000 -12.36 -12.08 12830 0.01 5e-05
9800000 -12.31 -12.08 12840 0.01 5e-05
9810000 -12.11 -12.08 12849 0.01 5e-05
9820000 -12.13 -12.04 12858 0.01 5e-05
9830000 -12.25 -12.04 12868 0.01 5e-05
9840000 -12.04 -12.04 12878 0.01 5e-05
9850000 -12.08 -12.02 12888 0.01 5e-05
9860000 -12.17 -12.02 12899 0.01 5e-05
9870000 -12.18 -11.96 12908 0.01 5e-05
9880000 -12.31 -11.96 12918 0.01 5e-05
9890000 -12.23 -11.96 12927 0.01 5e-05
9900000 -12.12 -11.96 12936 0.01 5e-05
9910000 -12.4 -11.96 12946 0.01 5e-05
9920000 -12.37 -11.96 12954 0.01 5e-05
================================================
FILE: hw3/log/_RAM_30-01-2018_22-29-12/log.txt
================================================
Timestep MeanReward BestMeanReward episodes exploration learning_rate
60000 -20.73 -20.57 208 0.194 0.0001
70000 -20.8 -20.57 247 0.193 0.0001
80000 -20.82 -20.57 285 0.192 0.0001
90000 -20.86 -20.57 325 0.191 0.0001
100000 -20.93 -20.57 365 0.19 0.0001
110000 -20.93 -20.57 404 0.189 0.0001
120000 -20.94 -20.57 444 0.188 0.0001
130000 -20.97 -20.57 483 0.187 0.0001
140000 -20.93 -20.57 523 0.186 0.0001
150000 -20.91 -20.57 562 0.185 0.0001
160000 -20.91 -20.57 602 0.184 0.0001
170000 -20.96 -20.57 641 0.183 0.0001
180000 -20.96 -20.57 681 0.18200000000000002 0.0001
190000 -20.99 -20.57 721 0.181 0.0001
200000 -20.97 -20.57 761 0.18 0.0001
210000 -20.95 -20.57 800 0.17900000000000002 0.0001
220000 -20.95 -20.57 840 0.17800000000000002 0.0001
230000 -20.98 -20.57 880 0.17700000000000002 0.0001
240000 -20.98 -20.57 920 0.17600000000000002 0.0001
250000 -20.97 -20.57 960 0.17500000000000002 0.0001
260000 -20.98 -20.57 1000 0.17400000000000002 0.0001
270000 -20.97 -20.57 1039 0.17300000000000001 0.0001
280000 -20.97 -20.57 1079 0.17200000000000001 0.0001
290000 -20.96 -20.57 1119 0.171 0.0001
300000 -20.98 -20.57 1159 0.17 0.0001
310000 -20.99 -20.57 1199 0.169 0.0001
320000 -20.98 -20.57 1238 0.168 0.0001
330000 -20.99 -20.57 1278 0.167 0.0001
340000 -21.0 -20.57 1318 0.166 0.0001
350000 -21.0 -20.57 1358 0.165 0.0001
360000 -21.0 -20.57 1398 0.164 0.0001
370000 -20.99 -20.57 1438 0.163 0.0001
380000 -20.98 -20.57 1478 0.162 0.0001
390000 -20.98 -20.57 1518 0.161 0.0001
400000 -20.96 -20.57 1557 0.16 0.0001
410000 -20.96 -20.57 1597 0.159 0.0001
420000 -20.95 -20.57 1636 0.158 0.0001
430000 -20.98 -20.57 1676 0.157 0.0001
440000 -20.98 -20.57 1716 0.156 0.0001
450000 -20.95 -20.57 1755 0.155 0.0001
460000 -20.96 -20.57 1795 0.154 0.0001
470000 -20.94 -20.57 1832 0.15300000000000002 0.0001
480000 -20.93 -20.57 1871 0.15200000000000002 0.0001
490000 -20.9 -20.57 1910 0.15100000000000002 0.0001
500000 -20.96 -20.57 1949 0.15000000000000002 0.0001
510000 -20.94 -20.57 1988 0.14900000000000002 0.0001
520000 -20.92 -20.57 2027 0.14800000000000002 0.0001
530000 -20.93 -20.57 2066 0.14700000000000002 0.0001
540000 -20.97 -20.57 2106 0.14600000000000002 0.0001
550000 -20.97 -20.57 2145 0.14500000000000002 0.0001
560000 -20.94 -20.57 2184 0.14400000000000002 0.0001
570000 -20.92 -20.57 2222 0.14300000000000002 0.0001
580000 -20.91 -20.57 2261 0.14200000000000002 0.0001
590000 -20.89 -20.57 2298 0.14100000000000001 0.0001
600000 -20.89 -20.57 2337 0.14 0.0001
610000 -20.92 -20.57 2376 0.139 0.0001
620000 -20.94 -20.57 2415 0.138 0.0001
630000 -20.94 -20.57 2454 0.137 0.0001
640000 -20.97 -20.57 2493 0.136 0.0001
650000 -20.93 -20.57 2532 0.135 0.0001
660000 -20.84 -20.57 2568 0.134 0.0001
670000 -20.75 -20.57 2604 0.133 0.0001
680000 -20.73 -20.57 2637 0.132 0.0001
690000 -20.74 -20.57 2669 0.131 0.0001
700000 -20.76 -20.57 2701 0.13 0.0001
710000 -20.76 -20.57 2733 0.129 0.0001
720000 -20.78 -20.57 2764 0.128 0.0001
730000 -20.73 -20.57 2793 0.127 0.0001
740000 -20.7 -20.57 2825 0.126 0.0001
750000 -20.67 -20.57 2857 0.125 0.0001
760000 -20.67 -20.57 2886 0.124 0.0001
770000 -20.72 -20.57 2918 0.123 0.0001
780000 -20.76 -20.57 2949 0.122 0.0001
790000 -20.82 -20.57 2980 0.121 0.0001
800000 -20.82 -20.57 3009 0.12 0.0001
810000 -20.71 -20.57 3039 0.119 0.0001
820000 -20.68 -20.57 3070 0.11800000000000001 0.0001
830000 -20.63 -20.57 3097 0.117 0.0001
840000 -20.72 -20.57 3128 0.116 0.0001
850000 -20.77 -20.57 3158 0.115 0.0001
860000 -20.82 -20.57 3186 0.114 0.0001
870000 -20.75 -20.57 3212 0.113 0.0001
880000 -20.65 -20.57 3238 0.112 0.0001
890000 -20.52 -20.52 3263 0.111 0.0001
900000 -20.47 -20.47 3290 0.11 0.0001
910000 -20.4 -20.38 3313 0.109 0.0001
920000 -20.35 -20.32 3337 0.108 0.0001
930000 -20.32 -20.31 3360 0.107 0.0001
940000 -20.29 -20.29 3384 0.10600000000000001 0.0001
950000 -20.26 -20.25 3405 0.10500000000000001 0.0001
960000 -20.22 -20.16 3429 0.10400000000000001 0.0001
970000 -20.2 -20.16 3452 0.10300000000000001 0.0001
980000 -19.99 -19.99 3474 0.10200000000000001 0.0001
990000 -19.88 -19.87 3496 0.101 0.0001
1000000 -19.87 -19.84 3518 0.1 0.0001
1010000 -19.73 -19.72 3539 0.099775 9.9875e-05
1020000 -19.63 -19.61 3560 0.09955 9.975e-05
1030000 -19.72 -19.61 3583 0.09932500000000001 9.962500000000001e-05
1040000 -19.72 -19.61 3607 0.09910000000000001 9.95e-05
1050000 -19.95 -19.61 3629 0.098875 9.9375e-05
1060000 -20.07 -19.61 3653 0.09865 9.925e-05
1070000 -20.02 -19.61 3676 0.098425 9.912500000000001e-05
1080000 -19.83 -19.61 3696 0.09820000000000001 9.900000000000001e-05
1090000 -19.76 -19.61 3715 0.097975 9.8875e-05
1100000 -19.54 -19.54 3736 0.09775 9.875e-05
1110000 -19.41 -19.38 3755 0.097525 9.8625e-05
1120000 -19.43 -19.31 3776 0.09730000000000001 9.850000000000001e-05
1130000 -19.37 -19.31 3795 0.09707500000000001 9.8375e-05
1140000 -19.41 -19.31 3814 0.09685 9.825e-05
1150000 -19.46 -19.31 3833 0.096625 9.8125e-05
1160000 -19.39 -19.31 3852 0.0964 9.800000000000001e-05
1170000 -19.33 -19.29 3872 0.09617500000000001 9.787500000000001e-05
1180000 -19.38 -19.26 3892 0.09595000000000001 9.775e-05
1190000 -19.36 -19.26 3911 0.095725 9.7625e-05
1200000 -19.36 -19.26 3930 0.0955 9.75e-05
1210000 -19.5 -19.26 3949 0.095275 9.737500000000001e-05
1220000 -19.49 -19.26 3968 0.09505000000000001 9.725e-05
1230000 -19.62 -19.26 3988 0.094825 9.7125e-05
1240000 -19.63 -19.26 4007 0.0946 9.7e-05
1250000 -19.54 -19.26 4027 0.094375 9.687500000000001e-05
1260000 -19.58 -19.26 4045 0.09415000000000001 9.675000000000001e-05
1270000 -19.36 -19.26 4063 0.09392500000000001 9.6625e-05
1280000 -19.29 -19.21 4081 0.0937 9.65e-05
1290000 -19.31 -19.2 4099 0.093475 9.6375e-05
1300000 -19.14 -19.14 4118 0.09325 9.625000000000001e-05
1310000 -18.95 -18.92 4136 0.09302500000000001 9.6125e-05
1320000 -18.88 -18.83 4154 0.09280000000000001 9.6e-05
1330000 -19.01 -18.83 4171 0.092575 9.5875e-05
1340000 -18.97 -18.83 4190 0.09235 9.575000000000001e-05
1350000 -18.82 -18.79 4207 0.09212500000000001 9.562500000000001e-05
1360000 -18.8 -18.76 4225 0.09190000000000001 9.55e-05
1370000 -18.95 -18.76 4243 0.091675 9.5375e-05
1380000 -18.93 -18.76 4261 0.09145 9.525000000000001e-05
1390000 -19.0 -18.76 4280 0.091225 9.512500000000001e-05
1400000 -19.0 -18.76 4298 0.091 9.5e-05
1410000 -19.12 -18.76 4316 0.09077500000000001 9.4875e-05
1420000 -18.96 -18.76 4334 0.09055 9.475e-05
1430000 -19.02 -18.76 4351 0.090325 9.462500000000001e-05
1440000 -18.95 -18.76 4368 0.0901 9.45e-05
1450000 -18.81 -18.75 4386 0.08987500000000001 9.4375e-05
1460000 -18.86 -18.75 4404 0.08965000000000001 9.425e-05
1470000 -18.75 -18.75 4421 0.089425 9.412500000000001e-05
1480000 -18.65 -18.64 4438 0.0892 9.400000000000001e-05
1490000 -18.54 -18.5 4456 0.088975 9.3875e-05
1500000 -18.5 -18.45 4472 0.08875000000000001 9.375e-05
1510000 -18.38 -18.38 4489 0.088525 9.3625e-05
1520000 -18.24 -18.24 4505 0.0883 9.350000000000001e-05
1530000 -18.42 -18.24 4523 0.088075 9.3375e-05
1540000 -18.57 -18.24 4541 0.08785 9.325e-05
1550000 -18.69 -18.24 4557 0.08762500000000001 9.3125e-05
1560000 -18.68 -18.24 4574 0.0874 9.300000000000001e-05
1570000 -18.65 -18.24 4591 0.087175 9.287500000000001e-05
1580000 -18.84 -18.24 4608 0.08695 9.275e-05
1590000 -18.75 -18.24 4625 0.08672500000000001 9.2625e-05
1600000 -18.74 -18.24 4642 0.08650000000000001 9.25e-05
1610000 -18.71 -18.24 4660 0.086275 9.237500000000001e-05
1620000 -18.72 -18.24 4677 0.08605 9.225e-05
1630000 -18.73 -18.24 4693 0.085825 9.2125e-05
1640000 -18.64 -18.24 4711 0.08560000000000001 9.2e-05
1650000 -18.39 -18.24 4727 0.085375 9.1875e-05
1660000 -18.46 -18.24 4743 0.08515 9.175000000000001e-05
1670000 -18.39 -18.24 4760 0.084925 9.1625e-05
1680000 -18.35 -18.24 4777 0.0847 9.15e-05
1690000 -18.4 -18.24 4794 0.08447500000000001 9.137500000000001e-05
1700000 -18.48 -18.24 4811 0.08425 9.125000000000001e-05
1710000 -18.71 -18.24 4827 0.084025 9.1125e-05
1720000 -18.58 -18.24 4844 0.0838 9.1e-05
1730000 -18.78 -18.24 4861 0.08357500000000001 9.0875e-05
1740000 -18.77 -18.24 4878 0.08335000000000001 9.075000000000001e-05
1750000 -18.83 -18.24 4895 0.083125 9.062500000000001e-05
1760000 -18.8 -18.24 4912 0.0829 9.05e-05
1770000 -18.75 -18.24 4930 0.082675 9.0375e-05
1780000 -18.61 -18.24 4946 0.08245 9.025e-05
1790000 -18.45 -18.24 4963 0.082225 9.012500000000001e-05
1800000 -18.51 -18.24 4981 0.082 9e-05
1810000 -18.36 -18.24 4997 0.081775 8.9875e-05
1820000 -18.36 -18.24 5014 0.08155000000000001 8.975e-05
1830000 -18.42 -18.24 5031 0.08132500000000001 8.962500000000001e-05
1840000 -18.61 -18.24 5047 0.0811 8.950000000000001e-05
1850000 -18.71 -18.24 5064 0.080875 8.9375e-05
1860000 -18.71 -18.24 5081 0.08065 8.925e-05
1870000 -18.7 -18.24 5097 0.080425 8.912500000000001e-05
1880000 -18.77 -18.24 5114 0.08020000000000001 8.900000000000001e-05
1890000 -18.69 -18.24 5131 0.079975 8.8875e-05
1900000 -18.54 -18.24 5147 0.07975 8.875e-05
1910000 -18.46 -18.24 5163 0.079525 8.8625e-05
1920000 -18.31 -18.24 5179 0.07930000000000001 8.850000000000001e-05
1930000 -18.38 -18.24 5196 0.079075 8.837500000000001e-05
1940000 -18.43 -18.24 5213 0.07885 8.825e-05
1950000 -18.47 -18.24 5230 0.078625 8.8125e-05
1960000 -18.45 -18.24 5246 0.0784 8.8e-05
1970000 -18.43 -18.24 5261 0.07817500000000001 8.787500000000001e-05
1980000 -18.53 -18.24 5278 0.07795 8.775e-05
1990000 -18.54 -18.24 5295 0.077725 8.7625e-05
2000000 -18.44 -18.24 5311 0.0775 8.75e-05
2010000 -18.48 -18.24 5327 0.07727500000000001 8.737500000000001e-05
2020000 -18.45 -18.24 5343 0.07705000000000001 8.725e-05
2030000 -18.52 -18.24 5359 0.076825 8.7125e-05
2040000 -18.43 -18.24 5375 0.0766 8.7e-05
2050000 -18.39 -18.24 5391 0.076375 8.687500000000001e-05
2060000 -18.31 -18.24 5407 0.07615 8.675000000000001e-05
2070000 -18.3 -18.21 5425 0.075925 8.6625e-05
2080000 -18.27 -18.19 5441 0.0757 8.65e-05
2090000 -18.27 -18.19 5458 0.075475 8.6375e-05
2100000 -18.22 -18.19 5474 0.07525 8.625000000000001e-05
2110000 -18.3 -18.19 5491 0.07502500000000001 8.6125e-05
2120000 -18.36 -18.19 5507 0.0748 8.6e-05
2130000 -18.28 -18.19 5523 0.074575 8.5875e-05
2140000 -18.2 -18.16 5539 0.07435 8.575000000000001e-05
2150000 -18.08 -18.08 5554 0.074125 8.562500000000001e-05
2160000 -18.09 -18.04 5569 0.07390000000000001 8.55e-05
2170000 -17.96 -17.93 5585 0.073675 8.5375e-05
2180000 -17.89 -17.76 5600 0.07345 8.525000000000001e-05
2190000 -17.85 -17.76 5616 0.073225 8.512500000000001e-05
2200000 -18.02 -17.76 5632 0.07300000000000001 8.5e-05
2210000 -18.23 -17.76 5648 0.072775 8.4875e-05
2220000 -18.28 -17.76 5664 0.07255 8.475e-05
2230000 -18.52 -17.76 5680 0.072325 8.462500000000001e-05
2240000 -18.61 -17.76 5696 0.0721 8.450000000000001e-05
2250000 -18.49 -17.76 5712 0.071875 8.4375e-05
2260000 -18.51 -17.76 5728 0.07165 8.425e-05
2270000 -18.42 -17.76 5743 0.071425 8.4125e-05
2280000 -18.44 -17.76 5759 0.0712 8.400000000000001e-05
2290000 -18.42 -17.76 5774 0.070975 8.3875e-05
2300000 -18.32 -17.76 5789 0.07075000000000001 8.375e-05
2310000 -18.25 -17.76 5804 0.070525 8.3625e-05
2320000 -18.25 -17.76 5820 0.0703 8.35e-05
2330000 -18.19 -17.76 5836 0.070075 8.337500000000001e-05
2340000 -18.24 -17.76 5851 0.06985 8.325e-05
2350000 -18.03 -17.76 5867 0.06962499999999999 8.3125e-05
2360000 -17.93 -17.76 5882 0.0694 8.3e-05
2370000 -17.94 -17.76 5898 0.069175 8.2875e-05
2380000 -17.91 -17.76 5914 0.06895000000000001 8.275e-05
2390000 -17.78 -17.76 5929 0.06872500000000001 8.2625e-05
2400000 -17.82 -17.76 5944 0.0685 8.25e-05
2410000 -17.68 -17.68 5959 0.068275 8.237500000000001e-05
2420000 -17.69 -17.65 5974 0.06805 8.225000000000001e-05
2430000 -18.0 -17.65 5990 0.067825 8.2125e-05
2440000 -17.88 -17.65 6005 0.0676 8.2e-05
2450000 -17.82 -17.65 6020 0.067375 8.1875e-05
2460000 -17.89 -17.65 6036 0.06715 8.175000000000001e-05
2470000 -17.75 -17.65 6052 0.06692500000000001 8.1625e-05
2480000 -17.99 -17.65 6068 0.06670000000000001 8.15e-05
2490000 -17.77 -17.65 6083 0.066475 8.1375e-05
2500000 -17.74 -17.64 6098 0.06625 8.125e-05
2510000 -17.68 -17.64 6113 0.066025 8.112500000000001e-05
2520000 -17.86 -17.64 6129 0.0658 8.1e-05
2530000 -17.79 -17.64 6145 0.065575 8.0875e-05
2540000 -17.84 -17.64 6160 0.06534999999999999 8.075000000000001e-05
2550000 -17.98 -17.64 6176 0.065125 8.062500000000001e-05
2560000 -18.02 -17.64 6190 0.0649 8.05e-05
2570000 -18.01 -17.64 6206 0.06467500000000001 8.0375e-05
2580000 -18.18 -17.64 6221 0.06445000000000001 8.025e-05
2590000 -17.99 -17.64 6236 0.064225 8.012500000000001e-05
2600000 -18.02 -17.64 6252 0.064 8e-05
2610000 -18.09 -17.64 6267 0.063775 7.9875e-05
2620000 -17.97 -17.64 6282 0.06355 7.975e-05
2630000 -18.08 -17.64 6298 0.063325 7.9625e-05
2640000 -18.08 -17.64 6313 0.0631 7.950000000000001e-05
2650000 -18.17 -17.64 6328 0.062875 7.9375e-05
2660000 -18.23 -17.64 6344 0.06265000000000001 7.925e-05
2670000 -18.17 -17.64 6360 0.062425 7.912500000000001e-05
2680000 -18.4 -17.64 6376 0.062200000000000005 7.900000000000001e-05
2690000 -18.17 -17.64 6392 0.061975 7.8875e-05
2700000 -18.03 -17.64 6407 0.06175 7.875e-05
2710000 -18.07 -17.64 6424 0.061525 7.8625e-05
2720000 -18.08 -17.64 6439 0.0613 7.850000000000001e-05
2730000 -17.9 -17.64 6454 0.061075000000000004 7.837500000000001e-05
2740000 -17.95 -17.64 6469 0.06085 7.825e-05
2750000 -17.92 -17.64 6484 0.060625 7.8125e-05
2760000 -17.78 -17.64 6499 0.0604 7.8e-05
2770000 -17.67 -17.64 6514 0.060175 7.787500000000001e-05
2780000 -17.77 -17.58 6530 0.05995 7.775e-05
2790000 -17.65 -17.53 6545 0.059725 7.7625e-05
2800000 -17.52 -17.51 6560 0.0595 7.75e-05
2810000 -17.72 -17.51 6576 0.059275 7.7375e-05
2820000 -17.78 -17.51 6590 0.05905 7.725000000000001e-05
2830000 -17.83 -17.51 6605 0.058825 7.7125e-05
2840000 -18.02 -17.51 6620 0.0586 7.7e-05
2850000 -18.18 -17.51 6636 0.058374999999999996 7.6875e-05
2860000 -17.99 -17.51 6651 0.05815 7.675e-05
2870000 -18.02 -17.51 6666 0.057925 7.6625e-05
2880000 -17.92 -17.51 6680 0.0577 7.65e-05
2890000 -17.72 -17.51 6694 0.057475000000000005 7.6375e-05
2900000 -17.74 -17.51 6709 0.05725 7.625000000000001e-05
2910000 -17.62 -17.51 6724 0.057025 7.612500000000001e-05
2920000 -17.49 -17.49 6739 0.0568 7.6e-05
2930000 -17.39 -17.3 6754 0.056575 7.5875e-05
2940000 -17.36 -17.27 6768 0.056350000000000004 7.575e-05
2950000 -17.42 -17.27 6782 0.056125 7.562500000000001e-05
2960000 -17.45 -17.27 6797 0.0559 7.55e-05
2970000 -17.62 -17.27 6812 0.055675 7.5375e-05
2980000 -17.59 -17.27 6827 0.05545 7.525e-05
2990000 -17.5 -17.27 6841 0.055225 7.5125e-05
3000000 -17.54 -17.27 6856 0.055 7.500000000000001e-05
3010000 -17.45 -17.27 6870 0.054775000000000004 7.4875e-05
3020000 -17.49 -17.27 6886 0.05455 7.475e-05
3030000 -17.64 -17.27 6901 0.054325000000000005 7.462500000000001e-05
3040000 -17.39 -17.27 6915 0.0541 7.45e-05
3050000 -17.35 -17.21 6930 0.053875000000000006 7.4375e-05
3060000 -17.51 -17.21 6945 0.053649999999999996 7.425e-05
3070000 -17.21 -17.21 6958 0.053425 7.4125e-05
3080000 -17.21 -17.21 6972 0.0532 7.400000000000001e-05
3090000 -17.19 -17.1 6987 0.052975 7.3875e-05
3100000 -17.04 -17.04 7000 0.05275 7.375e-05
3110000 -17.06 -16.94 7015 0.052525 7.3625e-05
3120000 -17.13 -16.94 7029 0.0523 7.35e-05
3130000 -16.97 -16.9 7042 0.052075 7.337500000000001e-05
3140000 -16.94 -16.86 7056 0.05185 7.325e-05
3150000 -16.98 -16.86 7070 0.051625000000000004 7.3125e-05
3160000 -16.95 -16.86 7083 0.051399999999999994 7.3e-05
3170000 -16.9 -16.86 7097 0.051175 7.2875e-05
3180000 -16.89 -16.86 7111 0.050949999999999995 7.275e-05
3190000 -16.96 -16.86 7125 0.050725 7.2625e-05
3200000 -17.17 -16.86 7139 0.050499999999999996 7.25e-05
3210000 -17.26 -16.86 7153 0.050275 7.237500000000001e-05
3220000 -17.05 -16.86 7167 0.05005 7.225e-05
3230000 -16.93 -16.86 7180 0.049825 7.2125e-05
3240000 -16.61 -16.61 7193 0.0496 7.2e-05
3250000 -16.64 -16.61 7207 0.049375 7.1875e-05
3260000 -16.59 -16.59 7221 0.049150000000000006 7.175000000000001e-05
3270000 -16.69 -16.55 7235 0.048924999999999996 7.1625e-05
3280000 -16.41 -16.41 7248 0.04870000000000001 7.15e-05
3290000 -16.43 -16.28 7262 0.048475 7.1375e-05
3300000 -16.46 -16.28 7274 0.04825 7.125000000000001e-05
3310000 -16.59 -16.28 7289 0.048025 7.112500000000001e-05
3320000 -16.48 -16.28 7302 0.0478 7.1e-05
3330000 -16.57 -16.28 7317 0.047575 7.0875e-05
3340000 -16.47 -16.28 7330 0.04735 7.075000000000001e-05
3350000 -16.39 -16.28 7343 0.047125 7.0625e-05
3360000 -16.42 -16.28 7356 0.046900000000000004 7.05e-05
3370000 -16.42 -16.28 7370 0.046674999999999994 7.0375e-05
3380000 -16.62 -16.28 7384 0.04645 7.025e-05
3390000 -16.47 -16.28 7397 0.046224999999999995 7.0125e-05
3400000 -16.57 -16.28 7411 0.046 7.000000000000001e-05
3410000 -16.54 -16.28 7425 0.045774999999999996 6.9875e-05
3420000 -16.61 -16.28 7438 0.04555 6.975e-05
3430000 -16.55 -16.28 7451 0.045325 6.9625e-05
3440000 -16.56 -16.28 7464 0.0451 6.950000000000001e-05
3450000 -16.46 -16.28 7477 0.044875 6.937499999999999e-05
3460000 -16.42 -16.28 7490 0.04465 6.925e-05
3470000 -16.19 -16.19 7502 0.04442499999999999 6.9125e-05
3480000 -16.15 -16.12 7514 0.044199999999999996 6.9e-05
3490000 -16.1 -16.05 7527 0.04397499999999999 6.887500000000001e-05
3500000 -16.15 -16.05 7540 0.04375 6.875e-05
3510000 -16.0 -16.0 7553 0.043525 6.8625e-05
3520000 -15.98 -15.97 7566 0.0433 6.850000000000001e-05
3530000 -16.05 -15.97 7579 0.043075 6.837500000000001e-05
3540000 -16.22 -15.97 7593 0.04285 6.825e-05
3550000 -16.35 -15.97 7606 0.042625 6.8125e-05
3560000 -16.47 -15.97 7620 0.0424 6.8e-05
3570000 -16.46 -15.97 7633 0.042175000000000004 6.787500000000001e-05
3580000 -16.45 -15.97 7645 0.041949999999999994 6.775e-05
3590000 -16.7 -15.97 7658 0.041725000000000005 6.7625e-05
3600000 -16.74 -15.97 7671 0.041499999999999995 6.75e-05
3610000 -16.6 -15.97 7684 0.041275 6.7375e-05
3620000 -16.44 -15.97 7696 0.041049999999999996 6.725000000000001e-05
3630000 -16.4 -15.97 7708 0.040825 6.7125e-05
3640000 -16.02 -15.97 7720 0.0406 6.7e-05
3650000 -15.93 -15.87 7733 0.040375 6.687500000000001e-05
3660000 -15.92 -15.87 7746 0.04015 6.675e-05
3670000 -15.81 -15.76 7759 0.039925 6.6625e-05
3680000 -15.73 -15.67 7772 0.03969999999999999 6.65e-05
3690000 -15.83 -15.67 7784 0.039474999999999996 6.6375e-05
3700000 -15.9 -15.67 7797 0.03924999999999999 6.625e-05
3710000 -15.92 -15.67 7809 0.039025 6.6125e-05
3720000 -16.24 -15.67 7822 0.038799999999999994 6.6e-05
3730000 -16.21 -15.67 7834 0.038575 6.5875e-05
3740000 -16.23 -15.67 7847 0.038349999999999995 6.575e-05
3750000 -16.2 -15.67 7858 0.038125 6.562500000000001e-05
3760000 -16.06 -15.67 7870 0.0379 6.55e-05
3770000 -16.02 -15.67 7884 0.037675 6.5375e-05
3780000 -16.07 -15.67 7897 0.03745 6.525000000000001e-05
3790000 -16.03 -15.67 7909 0.037224999999999994 6.5125e-05
3800000 -15.89 -15.67 7921 0.037000000000000005 6.500000000000001e-05
3810000 -15.92 -15.67 7933 0.036775 6.4875e-05
3820000 -15.91 -15.67 7946 0.03655 6.475e-05
3830000 -16.05 -15.67 7959 0.036324999999999996 6.462500000000001e-05
3840000 -16.5 -15.67 7973 0.03610000000000001 6.45e-05
3850000 -16.28 -15.67 7985 0.03587499999999999 6.4375e-05
3860000 -16.2 -15.67 7998 0.03565 6.425e-05
3870000 -16.08 -15.67 8009 0.035425 6.4125e-05
3880000 -16.2 -15.67 8022 0.035199999999999995 6.400000000000001e-05
3890000 -16.49 -15.67 8036 0.03497499999999999 6.3875e-05
3900000 -16.5 -15.67 8048 0.03475 6.375e-05
3910000 -16.58 -15.67 8061 0.034525 6.3625e-05
3920000 -16.37 -15.67 8074 0.0343 6.35e-05
3930000 -16.38 -15.67 8087 0.034074999999999994 6.337500000000001e-05
3940000 -16.14 -15.67 8100 0.033850000000000005 6.325e-05
3950000 -16.16 -15.67 8112 0.03362499999999999 6.3125e-05
3960000 -15.95 -15.67 8124 0.0334 6.300000000000001e-05
3970000 -15.76 -15.67 8137 0.033174999999999996 6.2875e-05
3980000 -15.71 -15.67 8150 0.03294999999999999 6.275000000000001e-05
3990000 -15.5 -15.5 8163 0.03272499999999999 6.262499999999999e-05
4000000 -15.47 -15.36 8175 0.0325 6.25e-05
4010000 -15.47 -15.36 8188 0.032275 6.237500000000001e-05
4020000 -15.83 -15.36 8201 0.032049999999999995 6.225e-05
4030000 -15.73 -15.36 8213 0.031825000000000006 6.2125e-05
4040000 -15.71 -15.36 8224 0.0316 6.2e-05
4050000 -15.36 -15.36 8236 0.031375 6.1875e-05
4060000 -15.5 -15.36 8249 0.031149999999999997 6.175000000000001e-05
4070000 -15.68 -15.36 8262 0.030924999999999994 6.162500000000001e-05
4080000 -15.74 -15.36 8275 0.03069999999999999 6.15e-05
4090000 -15.98 -15.36 8288 0.030475000000000002 6.137500000000001e-05
4100000 -15.63 -15.36 8300 0.03025 6.125e-05
4110000 -15.62 -15.36 8312 0.030024999999999996 6.112500000000001e-05
4120000 -15.93 -15.36 8325 0.029799999999999993 6.1e-05
4130000 -16.26 -15.36 8337 0.029575000000000004 6.0875e-05
4140000 -16.26 -15.36 8351 0.02935 6.075e-05
4150000 -16.07 -15.36 8363 0.029124999999999998 6.0625e-05
4160000 -16.12 -15.36 8375 0.028899999999999995 6.05e-05
4170000 -15.92 -15.36 8387 0.028674999999999992 6.0375000000000004e-05
4180000 -15.95 -15.36 8399 0.02844999999999999 6.025e-05
4190000 -15.81 -15.36 8410 0.028225 6.0125000000000005e-05
4200000 -15.79 -15.36 8423 0.027999999999999997 6e-05
4210000 -15.78 -15.36 8436 0.027774999999999994 5.9875000000000005e-05
4220000 -15.86 -15.36 8448 0.02754999999999999 5.975e-05
4230000 -15.96 -15.36 8461 0.027325000000000002 5.9625000000000006e-05
4240000 -15.77 -15.36 8473 0.0271 5.95e-05
4250000 -15.78 -15.36 8484 0.026874999999999996 5.9375e-05
4260000 -16.01 -15.36 8497 0.026650000000000007 5.9250000000000004e-05
4270000 -16.12 -15.36 8509 0.02642499999999999 5.9125e-05
4280000 -16.02 -15.36 8520 0.0262 5.9000000000000004e-05
4290000 -15.7 -15.36 8532 0.025974999999999998 5.8875e-05
4300000 -15.63 -15.36 8545 0.025749999999999995 5.8750000000000005e-05
4310000 -15.58 -15.36 8558 0.025524999999999992 5.8625e-05
4320000 -15.62 -15.36 8569 0.025300000000000003 5.8500000000000006e-05
4330000 -15.58 -15.36 8582 0.025075 5.8375e-05
4340000 -15.24 -15.24 8593 0.024849999999999997 5.8250000000000006e-05
4350000 -15.39 -15.16 8606 0.024624999999999994 5.8125e-05
4360000 -15.22 -15.16 8617 0.024400000000000005 5.800000000000001e-05
4370000 -15.15 -15.04 8629 0.024174999999999988 5.7875000000000004e-05
4380000 -15.25 -15.04 8642 0.02395 5.775e-05
4390000 -15.34 -15.04 8655 0.023724999999999996 5.7625e-05
4400000 -15.5 -15.04 8669 0.023499999999999993 5.75e-05
4410000 -15.79 -15.04 8682 0.02327499999999999 5.7375e-05
4420000 -15.94 -15.04 8694 0.02305 5.725e-05
4430000 -15.79 -15.04 8706 0.022824999999999998 5.7125e-05
4440000 -16.2 -15.04 8719 0.022599999999999995 5.7e-05
4450000 -16.23 -15.04 8731 0.022374999999999992 5.6875e-05
4460000 -16.42 -15.04 8744 0.022150000000000003 5.6750000000000004e-05
4470000 -16.02 -15.04 8755 0.021924999999999986 5.6625e-05
4480000 -16.05 -15.04 8769 0.021699999999999997 5.6500000000000005e-05
4490000 -15.9 -15.04 8782 0.021474999999999994 5.6375e-05
4500000 -16.16 -15.04 8796 0.02124999999999999 5.6250000000000005e-05
4510000 -16.09 -15.04 8808 0.021025000000000002 5.6125e-05
4520000 -15.92 -15.04 8820 0.0208 5.6e-05
4530000 -16.01 -15.04 8833 0.020574999999999996 5.5875e-05
4540000 -15.82 -15.04 8846 0.020349999999999993 5.575e-05
4550000 -15.8 -15.04 8857 0.020125000000000004 5.5625000000000004e-05
4560000 -15.56 -15.04 8870 0.0199 5.55e-05
4570000 -15.6 -15.04 8883 0.019674999999999998 5.5375000000000004e-05
4580000 -15.48 -15.04 8895 0.019449999999999995 5.525e-05
4590000 -15.74 -15.04 8909 0.019225000000000006 5.5125000000000005e-05
4600000 -15.87 -15.04 8922 0.01899999999999999 5.5e-05
4610000 -15.55 -15.04 8933 0.018775 5.4875000000000006e-05
4620000 -15.62 -15.04 8945 0.018549999999999997 5.475e-05
4630000 -15.59 -15.04 8957 0.018324999999999994 5.4625000000000006e-05
4640000 -15.48 -15.04 8969 0.01809999999999999 5.45e-05
4650000 -15.39 -15.04 8981 0.017875000000000002 5.437500000000001e-05
4660000 -15.29 -15.04 8993 0.01765 5.4250000000000004e-05
4670000 -15.08 -15.04 9005 0.017424999999999996 5.4125e-05
4680000 -14.86 -14.84 9017 0.017199999999999993 5.4e-05
4690000 -15.04 -14.84 9029 0.01697499999999999 5.3875e-05
4700000 -15.07 -14.84 9041 0.016749999999999987 5.375e-05
4710000 -15.14 -14.84 9053 0.016524999999999998 5.3625e-05
4720000 -15.23 -14.84 9066 0.016299999999999995 5.35e-05
4730000 -15.19 -14.84 9078 0.016074999999999992 5.3375e-05
4740000 -14.98 -14.84 9089 0.01584999999999999 5.325e-05
4750000 -15.13 -14.84 9101 0.015625 5.3125000000000004e-05
4760000 -15.18 -14.84 9113 0.015399999999999997 5.300000000000001e-05
4770000 -14.91 -14.84 9124 0.015174999999999994 5.2875000000000005e-05
4780000 -14.88 -14.83 9135 0.014950000000000005 5.275000000000001e-05
4790000 -14.9 -14.77 9146 0.014724999999999988 5.2625000000000005e-05
4800000 -14.67 -14.6 9158 0.014499999999999999 5.25e-05
4810000 -14.82 -14.6 9171 0.014274999999999996 5.2375e-05
4820000 -14.83 -14.6 9182 0.014049999999999993 5.225e-05
4830000 -14.8 -14.6 9194 0.01382499999999999 5.2125e-05
4840000 -14.91 -14.6 9207 0.013600000000000001 5.2000000000000004e-05
4850000 -14.82 -14.6 9217 0.013374999999999998 5.1875e-05
4860000 -14.69 -14.59 9229 0.013149999999999995 5.1750000000000004e-05
4870000 -14.72 -14.59 9240 0.012924999999999992 5.1625e-05
4880000 -14.87 -14.59 9253 0.012700000000000003 5.1500000000000005e-05
4890000 -14.66 -14.59 9264 0.012474999999999986 5.1375e-05
4900000 -14.82 -14.54 9277 0.012249999999999997 5.1250000000000006e-05
4910000 -14.76 -14.54 9288 0.012024999999999994 5.1125e-05
4920000 -14.83 -14.54 9300 0.011799999999999991 5.1000000000000006e-05
4930000 -14.41 -14.38 9311 0.011574999999999988 5.0875e-05
4940000 -14.72 -14.38 9323 0.011349999999999999 5.075e-05
4950000 -14.6 -14.38 9334 0.011124999999999996 5.0625e-05
4960000 -14.54 -14.38 9346 0.010899999999999993 5.05e-05
4970000 -14.44 -14.38 9358 0.01067499999999999 5.0375e-05
4980000 -14.41 -14.34 9370 0.010450000000000001 5.025e-05
4990000 -14.54 -14.31 9382 0.010224999999999984 5.0125e-05
5000000 -14.48 -14.31 9394 0.01 5e-05
5010000 -14.57 -14.3 9406 0.01 5e-05
5020000 -14.4 -14.3 9417 0.01 5e-05
5030000 -14.61 -14.3 9429 0.01 5e-05
5040000 -14.72 -14.3 9441 0.01 5e-05
5050000 -14.74 -14.3 9453 0.01 5e-05
5060000 -14.89 -14.3 9465 0.01 5e-05
5070000 -14.92 -14.3 9477 0.01 5e-05
5080000 -14.94 -14.3 9488 0.01 5e-05
5090000 -15.17 -14.3 9499 0.01 5e-05
5100000 -15.38 -14.3 9510 0.01 5e-05
5110000 -15.39 -14.3 9522 0.01 5e-05
5120000 -15.3 -14.3 9534 0.01 5e-05
5130000 -15.46 -14.3 9546 0.01 5e-05
5140000 -15.63 -14.3 9557 0.01 5e-05
5150000 -15.38 -14.3 9569 0.01 5e-05
5160000 -15.26 -14.3 9580 0.01 5e-05
5170000 -15.05 -14.3 9591 0.01 5e-05
5180000 -14.69 -14.3 9602 0.01 5e-05
5190000 -14.41 -14.3 9613 0.01 5e-05
5200000 -14.28 -14.25 9624 0.01 5e-05
5210000 -14.08 -14.05 9635 0.01 5e-05
5220000 -13.96 -13.84 9646 0.01 5e-05
5230000 -13.66 -13.66 9657 0.01 5e-05
5240000 -13.67 -13.66 9668 0.01 5e-05
5250000 -13.56 -13.54 9679 0.01 5e-05
5260000 -13.59 -13.54 9691 0.01 5e-05
5270000 -13.77 -13.54 9702 0.01 5e-05
5280000 -13.91 -13.54 9714 0.01 5e-05
5290000 -14.27 -13.54 9728 0.01 5e-05
5300000 -14.57 -13.54 9740 0.01 5e-05
5310000 -14.56 -13.54 9752 0.01 5e-05
5320000 -14.86 -13.54 9764 0.01 5e-05
5330000 -15.18 -13.54 9778 0.01 5e-05
5340000 -15.28 -13.54 9791 0.01 5e-05
5350000 -15.67 -13.54 9804 0.01 5e-05
5360000 -15.56 -13.54 9816 0.01 5e-05
5370000 -15.31 -13.54 9828 0.01 5e-05
5380000 -15.18 -13.54 9841 0.01 5e-05
5390000 -15.23 -13.54 9853 0.01 5e-05
5400000 -15.48 -13.54 9866 0.01 5e-05
5410000 -15.23 -13.54 9878 0.01 5e-05
5420000 -15.33 -13.54 9890 0.01 5e-05
5430000 -15.43 -13.54 9904 0.01 5e-05
5440000 -15.46 -13.54 9917 0.01 5e-05
5450000 -15.38 -13.54 9928 0.01 5e-05
5460000 -15.33 -13.54 9940 0.01 5e-05
5470000 -15.3 -13.54 9951 0.01 5e-05
5480000 -15.05 -13.54 9962 0.01 5e-05
5490000 -14.72 -13.54 9973 0.01 5e-05
5500000 -14.67 -13.54 9985 0.01 5e-05
5510000 -14.27 -13.54 9997 0.01 5e-05
5520000 -14.27 -13.54 10009 0.01 5e-05
5530000 -14.12 -13.54 10020 0.01 5e-05
5540000 -14.03 -13.54 10032 0.01 5e-05
5550000 -14.06 -13.54 10044 0.01 5e-05
5560000 -13.84 -13.54 10055 0.01 5e-05
5570000 -14.16 -13.54 10067 0.01 5e-05
5580000 -14.18 -13.54 10078 0.01 5e-05
5590000 -14.18 -13.54 10089 0.01 5e-05
5600000 -14.24 -13.54 10101 0.01 5e-05
5610000 -14.18 -13.54 10114 0.01 5e-05
5620000 -14.39 -13.54 10125 0.01 5e-05
5630000 -14.47 -13.54 10137 0.01 5e-05
5640000 -14.44 -13.54 10149 0.01 5e-05
5650000 -14.76 -13.54 10161 0.01 5e-05
5660000 -14.54 -13.54 10172 0.01 5e-05
5670000 -14.81 -13.54 10184 0.01 5e-05
5680000 -14.88 -13.54 10196 0.01 5e-05
5690000 -14.68 -13.54 10208 0.01 5e-05
5700000 -14.65 -13.54 10219 0.01 5e-05
5710000 -14.7 -13.54 10231 0.01 5e-05
5720000 -14.72 -13.54 10242 0.01 5e-05
5730000 -14.4 -13.54 10254 0.01 5e-05
5740000 -14.16 -13.54 10265 0.01 5e-05
5750000 -14.42 -13.54 10276 0.01 5e-05
5760000 -14.48 -13.54 10289 0.01 5e-05
5770000 -14.29 -13.54 10299 0.01 5e-05
5780000 -14.44 -13.54 10311 0.01 5e-05
5790000 -14.72 -13.54 10323 0.01 5e-05
5800000 -14.36 -13.54 10334 0.01 5e-05
5810000 -14.58 -13.54 10347 0.01 5e-05
5820000 -14.69 -13.54 10358 0.01 5e-05
5830000 -14.78 -13.54 10369 0.01 5e-05
5840000 -14.48 -13.54 10380 0.01 5e-05
5850000 -14.58 -13.54 10392 0.01 5e-05
5860000 -14.93 -13.54 10404 0.01 5e-05
5870000 -14.8 -13.54 10415 0.01 5e-05
5880000 -14.78 -13.54 10427 0.01 5e-05
5890000 -14.81 -13.54 10438 0.01 5e-05
5900000 -14.79 -13.54 10450 0.01 5e-05
5910000 -14.71 -13.54 10462 0.01 5e-05
5920000 -14.49 -13.54 10472 0.01 5e-05
5930000 -14.7 -13.54 10485 0.01 5e-05
5940000 -14.63 -13.54 10497 0.01 5e-05
5950000 -14.53 -13.54 10509 0.01 5e-05
5960000 -14.46 -13.54 10521 0.01 5e-05
5970000 -14.38 -13.54 10533 0.01 5e-05
5980000 -14.62 -13.54 10544 0.01 5e-05
5990000 -14.44 -13.54 10556 0.01 5e-05
6000000 -14.61 -13.54 10567 0.01 5e-05
6010000 -14.78 -13.54 10580 0.01 5e-05
6020000 -14.66 -13.54 10591 0.01 5e-05
6030000 -14.66 -13.54 10603 0.01 5e-05
6040000 -14.74 -13.54 10615 0.01 5e-05
6050000 -14.92 -13.54 10628 0.01 5e-05
6060000 -14.92 -13.54 10641 0.01 5e-05
6070000 -15.06 -13.54 10654 0.01 5e-05
6080000 -14.89 -13.54 10665 0.01 5e-05
6090000 -14.82 -13.54 10678 0.01 5e-05
6100000 -14.73 -13.54 10690 0.01 5e-05
6110000 -14.68 -13.54 10702 0.01 5e-05
6120000 -14.3 -13.54 10714 0.01 5e-05
6130000 -13.95 -13.54 10728 0.01 5e-05
6140000 -13.5 -13.5 10741 0.01 5e-05
6150000 -13.23 -13.23 10753 0.01 5e-05
6160000 -13.22 -13.11 10765 0.01 5e-05
6170000 -13.04 -13.01 10776 0.01 5e-05
6180000 -13.12 -12.94 10788 0.01 5e-05
6190000 -13.1 -12.94 10800 0.01 5e-05
6200000 -13.4 -12.94 10814 0.01 5e-05
6210000 -13.13 -12.94 10826 0.01 5e-05
6220000 -13.04 -12.94 10837 0.01 5e-05
6230000 -13.01 -12.94 10849 0.01 5e-05
6240000 -13.13 -12.94 10861 0.01 5e-05
6250000 -12.94 -12.91 10873 0.01 5e-05
6260000 -12.68 -12.63 10886 0.01 5e-05
6270000 -12.41 -12.32 10898 0.01 5e-05
6280000 -12.12 -12.12 10912 0.01 5e-05
6290000 -12.3 -12.07 10925 0.01 5e-05
6300000 -12.44 -12.07 10938 0.01 5e-05
6310000 -12.52 -12.07 10952 0.01 5e-05
6320000 -12.37 -12.07 10965 0.01 5e-05
6330000 -12.59 -12.07 10979 0.01 5e-05
6340000 -12.96 -12.07 10994 0.01 5e-05
6350000 -12.75 -12.07 11007 0.01 5e-05
6360000 -12.88 -12.07 11021 0.01 5e-05
6370000 -12.71 -12.07 11034 0.01 5e-05
6380000 -12.64 -12.07 11048 0.01 5e-05
6390000 -12.94 -12.07 11063 0.01 5e-05
6400000 -12.8 -12.07 11077 0.01 5e-05
6410000 -12.37 -12.07 11090 0.01 5e-05
6420000 -12.26 -12.07 11104 0.01 5e-05
6430000 -12.49 -12.07 11118 0.01 5e-05
6440000 -12.48 -12.07 11133 0.01 5e-05
6450000 -12.72 -12.07 11147 0.01 5e-05
6460000 -12.51 -12.07 11161 0.01 5e-05
6470000 -12.28 -12.07 11173 0.01 5e-05
6480000 -12.71 -12.07 11186 0.01 5e-05
6490000 -12.67 -12.07 11199 0.01 5e-05
6500000 -12.59 -12.07 11212 0.01 5e-05
6510000 -12.48 -12.07 11225 0.01 5e-05
6520000 -12.42 -12.07 11238 0.01 5e-05
6530000 -12.34 -12.07 11252 0.01 5e-05
6540000 -12.26 -12.07 11264 0.01 5e-05
6550000 -12.68 -12.07 11277 0.01 5e-05
6560000 -12.26 -12.07 11289 0.01 5e-05
6570000 -12.39 -12.07 11303 0.01 5e-05
6580000 -12.58 -12.07 11316 0.01 5e-05
6590000 -12.28 -12.07 11329 0.01 5e-05
6600000 -12.12 -12.07 11341 0.01 5e-05
6610000 -11.98 -11.96 11354 0.01 5e-05
6620000 -11.81 -11.81 11367 0.01 5e-05
6630000 -11.76 -11.63 11379 0.01 5e-05
6640000 -11.99 -11.63 11393 0.01 5e-05
6650000 -11.8 -11.63 11406 0.01 5e-05
6660000 -11.87 -11.63 11420 0.01 5e-05
6670000 -12.02 -11.63 11433 0.01 5e-05
6680000 -12.38 -11.63 11447 0.01 5e-05
6690000 -12.51 -11.63 11461 0.01 5e-05
6700000 -12.8 -11.63 11474 0.01 5e-05
6710000 -12.65 -11.63 11488 0.01 5e-05
6720000 -12.96 -11.63 11502 0.01 5e-05
6730000 -13.04 -11.63 11515 0.01 5e-05
6740000 -12.93 -11.63 11529 0.01 5e-05
6750000 -12.95 -11.63 11541 0.01 5e-05
6760000 -12.66 -11.63 11556 0.01 5e-05
6770000 -12.66 -11.63 11569 0.01 5e-05
6780000 -12.73 -11.63 11582 0.01 5e-05
6790000 -12.78 -11.63 11596 0.01 5e-05
6800000 -12.6 -11.63 11609 0.01 5e-05
6810000 -12.57 -11.63 11623 0.01 5e-05
6820000 -12.65 -11.63 11637 0.01 5e-05
6830000 -12.59 -11.63 11651 0.01 5e-05
6840000 -12.62 -11.63 11664 0.01 5e-05
6850000 -12.5 -11.63 11677 0.01 5e-05
6860000 -12.43 -11.63 11691 0.01 5e-05
6870000 -12.28 -11.63 11704 0.01 5e-05
6880000 -12.49 -11.63 11717 0.01 5e-05
6890000 -12.09 -11.63 11730 0.01 5e-05
6900000 -11.87 -11.63 11743 0.01 5e-05
6910000 -12.09 -11.63 11755 0.01 5e-05
6920000 -11.94 -11.63 11768 0.01 5e-05
6930000 -12.04 -11.63 11781 0.01 5e-05
6940000 -12.06 -11.63 11795 0.01 5e-05
6950000 -12.0 -11.63 11807 0.01 5e-05
6960000 -11.6 -11.6 11818 0.01 5e-05
6970000 -11.36 -11.32 11831 0.01 5e-05
6980000 -11.34 -11.15 11844 0.01 5e-05
6990000 -11.58 -11.15 11858 0.01 5e-05
7000000 -11.72 -11.15 11871 0.01 5e-05
7010000 -11.49 -11.15 11884 0.01 5e-05
7020000 -11.52 -11.15 11897 0.01 5e-05
7030000 -11.59 -11.15 11910 0.01 5e-05
7040000 -11.73 -11.15 11922 0.01 5e-05
7050000 -11.92 -11.15 11935 0.01 5e-05
7060000 -11.87 -11.15 11948 0.01 5e-05
7070000 -11.6 -11.15 11961 0.01 5e-05
7080000 -11.59 -11.15 11974 0.01 5e-05
7090000 -11.59 -11.15 11987 0.01 5e-05
7100000 -11.76 -11.15 12001 0.01 5e-05
7110000 -12.08 -11.15 12014 0.01 5e-05
7120000 -11.92 -11.15 12026 0.01 5e-05
7130000 -11.37 -11.15 12038 0.01 5e-05
7140000 -11.42 -11.15 12050 0.01 5e-05
7150000 -11.39 -11.15 12063 0.01 5e-05
7160000 -11.35 -11.15 12075 0.01 5e-05
7170000 -11.42 -11.15 12089 0.01 5e-05
7180000 -11.04 -11.04 12101 0.01 5e-05
7190000 -10.82 -10.82 12113 0.01 5e-05
7200000 -10.68 -10.67 12125 0.01 5e-05
7210000 -11.18 -10.51 12138 0.01 5e-05
7220000 -11.26 -10.51 12151 0.01 5e-05
7230000 -11.34 -10.51 12164 0.01 5e-05
7240000 -11.66 -10.51 12178 0.01 5e-05
7250000 -11.36 -10.51 12192 0.01 5e-05
7260000 -11.74 -10.51 12205 0.01 5e-05
7270000 -12.21 -10.51 12219 0.01 5e-05
7280000 -12.43 -10.51 12232 0.01 5e-05
7290000 -12.75 -10.51 12246 0.01 5e-05
7300000 -12.82 -10.51 12259 0.01 5e-05
7310000 -12.46 -10.51 12272 0.01 5e-05
7320000 -12.42 -10.51 12284 0.01 5e-05
7330000 -12.27 -10.51 12297 0.01 5e-05
7340000 -12.12 -10.51 12310 0.01 5e-05
7350000 -12.08 -10.51 12323 0.01 5e-05
7360000 -11.74 -10.51 12335 0.01 5e-05
7370000 -11.8 -10.51 12349 0.01 5e-05
7380000 -11.52 -10.51 12362 0.01 5e-05
7390000 -11.58 -10.51 12375 0.01 5e-05
7400000 -11.95 -10.51 12389 0.01 5e-05
7410000 -12.21 -10.51 12402 0.01 5e-05
7420000 -12.11 -10.51 12416 0.01 5e-05
7430000 -12.04 -10.51 12427 0.01 5e-05
7440000 -12.16 -10.51 12440 0.01 5e-05
7450000 -12.11 -10.51 12454 0.01 5e-05
7460000 -12.09 -10.51 12466 0.01 5e-05
7470000 -12.1 -10.51 12480 0.01 5e-05
7480000 -11.98 -10.51 12492 0.01 5e-05
7490000 -11.73 -10.51 12505 0.01 5e-05
7500000 -11.74 -10.51 12518 0.01 5e-05
7510000 -12.01 -10.51 12531 0.01 5e-05
7520000 -12.0 -10.51 12544 0.01 5e-05
7530000 -11.78 -10.51 12556 0.01 5e-05
7540000 -11.98 -10.51 12570 0.01 5e-05
7550000 -11.63 -10.51 12581 0.01 5e-05
7560000 -11.78 -10.51 12594 0.01 5e-05
7570000 -11.77 -10.51 12607 0.01 5e-05
7580000 -11.67 -10.51 12621 0.01 5e-05
7590000 -11.56 -10.51 12633 0.01 5e-05
7600000 -11.43 -10.51 12646 0.01 5e-05
7610000 -11.5 -10.51 12658 0.01 5e-05
7620000 -11.44 -10.51 12671 0.01 5e-05
7630000 -11.65 -10.51 12684 0.01 5e-05
7640000 -11.68 -10.51 12697 0.01 5e-05
7650000 -11.75 -10.51 12710 0.01 5e-05
7660000 -11.69 -10.51 12722 0.01 5e-05
7670000 -11.74 -10.51 12734 0.01 5e-05
7680000 -11.84 -10.51 12747 0.01 5e-05
7690000 -11.95 -10.51 12760 0.01 5e-05
7700000 -12.04 -10.51 12773 0.01 5e-05
7710000 -12.06 -10.51 12785 0.01 5e-05
7720000 -12.11 -10.51 12799 0.01 5e-05
7730000 -12.04 -10.51 12812 0.01 5e-05
7740000 -11.99 -10.51 12824 0.01 5e-05
7750000 -12.19 -10.51 12837 0.01 5e-05
7760000 -12.16 -10.51 12850 0.01 5e-05
7770000 -12.2 -10.51 12863 0.01 5e-05
7780000 -12.1 -10.51 12876 0.01 5e-05
7790000 -11.99 -10.51 12889 0.01 5e-05
7800000 -11.9 -10.51 12902 0.01 5e-05
7810000 -11.86 -10.51 12915 0.01 5e-05
7820000 -11.97 -10.51 12928 0.01 5e-05
7830000 -11.93 -10.51 12940 0.01 5e-05
7840000 -12.0 -10.51 12953 0.01 5e-05
7850000 -11.91 -10.51 12965 0.01 5e-05
7860000 -12.01 -10.51 12978 0.01 5e-05
7870000 -12.22 -10.51 12992 0.01 5e-05
7880000 -12.0 -10.51 13004 0.01 5e-05
7890000 -12.06 -10.51 13016 0.01 5e-05
7900000 -12.08 -10.51 13029 0.01 5e-05
7910000 -11.97 -10.51 13042 0.01 5e-05
7920000 -11.67 -10.51 13054 0.01 5e-05
7930000 -11.79 -10.51 13068 0.01 5e-05
7940000 -11.97 -10.51 13081 0.01 5e-05
7950000 -11.68 -10.51 13094 0.01 5e-05
7960000 -11.8 -10.51 13105 0.01 5e-05
7970000 -11.86 -10.51 13117 0.01 5e-05
7980000 -12.12 -10.51 13131 0.01 5e-05
7990000 -12.13 -10.51 13144 0.01 5e-05
8000000 -12.15 -10.51 13157 0.01 5e-05
8010000 -11.98 -10.51 13170 0.01 5e-05
8020000 -11.98 -10.51 13183 0.01 5e-05
8030000 -12.23 -10.51 13196 0.01 5e-05
8040000 -12.37 -10.51 13209 0.01 5e-05
8050000 -12.46 -10.51 13221 0.01 5e-05
8060000 -12.21 -10.51 13234 0.01 5e-05
8070000 -12.16 -10.51 13246 0.01 5e-05
8080000 -12.09 -10.51 13259 0.01 5e-05
8090000 -12.19 -10.51 13272 0.01 5e-05
8100000 -11.88 -10.51 13284 0.01 5e-05
8110000 -11.81 -10.51 13297 0.01 5e-05
8120000 -11.78 -10.51 13310 0.01 5e-05
8130000 -11.72 -10.51 13323 0.01 5e-05
8140000 -11.96 -10.51 13336 0.01 5e-05
8150000 -12.37 -10.51 13351 0.01 5e-05
8160000 -12.76 -10.51 13364 0.01 5e-05
8170000 -12.99 -10.51 13377 0.01 5e-05
8180000 -12.78 -10.51 13388 0.01 5e-05
8190000 -12.61 -10.51 13401 0.01 5e-05
8200000 -12.56 -10.51 13414 0.01 5e-05
8210000 -12.43 -10.51 13426 0.01 5e-05
8220000 -12.0 -10.51 13439 0.01 5e-05
8230000 -12.07 -10.51 13452 0.01 5e-05
8240000 -11.74 -10.51 13464 0.01 5e-05
8250000 -11.48 -10.51 13477 0.01 5e-05
8260000 -11.95 -10.51 13491 0.01 5e-05
8270000 -11.98 -10.51 13505 0.01 5e-05
8280000 -12.0 -10.51 13518 0.01 5e-05
8290000 -11.98 -10.51 13529 0.01 5e-05
8300000 -11.77 -10.51 13542 0.01 5e-05
8310000 -11.33 -10.51 13555 0.01 5e-05
8320000 -11.8 -10.51 13569 0.01 5e-05
8330000 -11.63 -10.51 13582 0.01 5e-05
8340000 -11.66 -10.51 13596 0.01 5e-05
8350000 -11.94 -10.51 13609 0.01 5e-05
8360000 -12.02 -10.51 13623 0.01 5e-05
8370000 -12.11 -10.51 13635 0.01 5e-05
8380000 -11.9 -10.51 13647 0.01 5e-05
8390000 -11.91 -10.51 13660 0.01 5e-05
8400000 -11.71 -10.51 13672 0.01 5e-05
8410000 -11.53 -10.51 13685 0.01 5e-05
8420000 -11.46 -10.51 13698 0.01 5e-05
8430000 -11.63 -10.51 13712 0.01 5e-05
8440000 -11.7 -10.51 13725 0.01 5e-05
8450000 -11.67 -10.51 13738 0.01 5e-05
8460000 -11.96 -10.51 13752 0.01 5e-05
8470000 -12.0 -10.51 13766 0.01 5e-05
8480000 -12.46 -10.51 13780 0.01 5e-05
8490000 -12.51 -10.51 13794 0.01 5e-05
8500000 -12.35 -10.51 13807 0.01 5e-05
8510000 -12.54 -10.51 13822 0.01 5e-05
8520000 -12.64 -10.51 13835 0.01 5e-05
8530000 -12.79 -10.51 13848 0.01 5e-05
8540000 -13.06 -10.51 13862 0.01 5e-05
8550000 -12.99 -10.51 13876 0.01 5e-05
8560000 -12.87 -10.51 13889 0.01 5e-05
8570000 -12.91 -10.51 13903 0.01 5e-05
8580000 -12.88 -10.51 13916 0.01 5e-05
8590000 -12.48 -10.51 13930 0.01 5e-05
8600000 -12.51 -10.51 13944 0.01 5e-05
8610000 -12.43 -10.51 13957 0.01 5e-05
8620000 -12.08 -10.51 13970 0.01 5e-05
8630000 -12.07 -10.51 13983 0.01 5e-05
8640000 -11.74 -10.51 13996 0.01 5e-05
8650000 -11.66 -10.51 14009 0.01 5e-05
8660000 -11.68 -10.51 14022 0.01 5e-05
8670000 -11.45 -10.51 14035 0.01 5e-05
8680000 -11.31 -10.51 14048 0.01 5e-05
8690000 -11.4 -10.51 14061 0.01 5e-05
8700000 -12.0 -10.51 14074 0.01 5e-05
8710000 -11.93 -10.51 14088 0.01 5e-05
8720000 -12.29 -10.51 14102 0.01 5e-05
8730000 -12.43 -10.51 14116 0.01 5e-05
8740000 -12.51 -10.51 14130 0.01 5e-05
8750000 -12.82 -10.51 14143 0.01 5e-05
8760000 -12.86 -10.51 14156 0.01 5e-05
8770000 -12.83 -10.51 14170 0.01 5e-05
8780000 -12.72 -10.51 14183 0.01 5e-05
8790000 -12.47 -10.51 14195 0.01 5e-05
8800000 -12.52 -10.51 14209 0.01 5e-05
8810000 -12.01 -10.51 14221 0.01 5e-05
8820000 -12.06 -10.51 14235 0.01 5e-05
8830000 -12.16 -10.51 14249 0.01 5e-05
8840000 -12.18 -10.51 14262 0.01 5e-05
8850000 -12.44 -10.51 14276 0.01 5e-05
8860000 -12.42 -10.51 14289 0.01 5e-05
8870000 -12.36 -10.51 14302 0.01 5e-05
8880000 -12.15 -10.51 14314 0.01 5e-05
8890000 -12.22 -10.51 14326 0.01 5e-05
8900000 -11.87 -10.51 14338 0.01 5e-05
8910000 -11.7 -10.51 14351 0.01 5e-05
8920000 -11.62 -10.51 14363 0.01 5e-05
8930000 -11.1 -10.51 14376 0.01 5e-05
8940000 -10.76 -10.51 14387 0.01 5e-05
8950000 -10.77 -10.51 14401 0.01 5e-05
8960000 -11.02 -10.51 14413 0.01 5e-05
8970000 -11.39 -10.51 14427 0.01 5e-05
8980000 -11.24 -10.51 14439 0.01 5e-05
8990000 -11.05 -10.51 14451 0.01 5e-05
9000000 -11.22 -10.51 14464 0.01 5e-05
9010000 -11.41 -10.51 14477 0.01 5e-05
9020000 -11.4 -10.51 14489 0.01 5e-05
9030000 -11.27 -10.51 14501 0.01 5e-05
9040000 -11.39 -10.51 14515 0.01 5e-05
9050000 -11.22 -10.51 14528 0.01 5e-05
9060000 -11.54 -10.51 14541 0.01 5e-05
9070000 -11.83 -10.51 14554 0.01 5e-05
9080000 -11.68 -10.51 14566 0.01 5e-05
9090000 -11.82 -10.51 14579 0.01 5e-05
9100000 -11.94 -10.51 14592 0.01 5e-05
9110000 -11.93 -10.51 14605 0.01 5e-05
9120000 -11.84 -10.51 14618 0.01 5e-05
9130000 -11.72 -10.51 14631 0.01 5e-05
9140000 -11.71 -10.51 14644 0.01 5e-05
9150000 -11.45 -10.51 14657 0.01 5e-05
9160000 -11.47 -10.51 14668 0.01 5e-05
9170000 -11.12 -10.51 14680 0.01 5e-05
9180000 -11.16 -10.51 14693 0.01 5e-05
9190000 -11.51 -10.51 14707 0.01 5e-05
9200000 -11.35 -10.51 14719 0.01 5e-05
9210000 -11.4 -10.51 14732 0.01 5e-05
9220000 -11.41 -10.51 14745 0.01 5e-05
9230000 -11.62 -10.51 14757 0.01 5e-05
9240000 -11.8 -10.51 14771 0.01 5e-05
9250000 -12.08 -10.51 14784 0.01 5e-05
9260000 -11.79 -10.51 14795 0.01 5e-05
9270000 -11.21 -10.51 14807 0.01 5e-05
9280000 -11.42 -10.51 14820 0.01 5e-05
9290000 -11.4 -10.51 14832 0.01 5e-05
9300000 -11.46 -10.51 14846 0.01 5e-05
9310000 -11.49 -10.51 14858 0.01 5e-05
9320000 -11.31 -10.51 14871 0.01 5e-05
9330000 -11.35 -10.51 14884 0.01 5e-05
9340000 -11.73 -10.51 14896 0.01 5e-05
9350000 -12.01 -10.51 14908 0.01 5e-05
9360000 -11.82 -10.51 14921 0.01 5e-05
9370000 -11.81 -10.51 14934 0.01 5e-05
9380000 -11.61 -10.51 14946 0.01 5e-05
9390000 -11.56 -10.51 14958 0.01 5e-05
9400000 -11.59 -10.51 14970 0.01 5e-05
9410000 -11.43 -10.51 14983 0.01 5e-05
9420000 -11.68 -10.51 14996 0.01 5e-05
9430000 -11.41 -10.51 15008 0.01 5e-05
9440000 -11.19 -10.51 15020 0.01 5e-05
9450000 -11.07 -10.51 15032 0.01 5e-05
9460000 -11.05 -10.51 15044 0.01 5e-05
9470000 -11.09 -10.51 15056 0.01 5e-05
9480000 -11.05 -10.51 15070 0.01 5e-05
9490000 -11.24 -10.51 15083 0.01 5e-05
9500000 -11.06 -10.51 15096 0.01 5e-05
9510000 -11.22 -10.51 15109 0.01 5e-05
9520000 -11.37 -10.51 15122 0.01 5e-05
9530000 -11.52 -10.51 15134 0.01 5e-05
9540000 -11.86 -10.51 15147 0.01 5e-05
9550000 -11.99 -10.51 15161 0.01 5e-05
9560000 -11.8 -10.51 15173 0.01 5e-05
9570000 -11.34 -10.51 15184 0.01 5e-05
9580000 -11.23 -10.51 15197 0.01 5e-05
9590000 -11.45 -10.51 15210 0.01 5e-05
9600000 -11.45 -10.51 15223 0.01 5e-05
9610000 -11.49 -10.51 15235 0.01 5e-05
9620000 -11.3 -10.51 15248 0.01 5e-05
9630000 -11.34 -10.51 15260 0.01 5e-05
9640000 -11.5 -10.51 15273 0.01 5e-05
9650000 -11.92 -10.51 15287 0.01 5e-05
9660000 -12.19 -10.51 15300 0.01 5e-05
9670000 -11.98 -10.51 15312 0.01 5e-05
9680000 -11.77 -10.51 15325 0.01 5e-05
9690000 -11.82 -10.51 15337 0.01 5e-05
9700000 -11.67 -10.51 15350 0.01 5e-05
9710000 -11.69 -10.51 15363 0.01 5e-05
9720000 -11.74 -10.51 15377 0.01 5e-05
9730000 -11.64 -10.51 15389 0.01 5e-05
9740000 -11.28 -10.51 15401 0.01 5e-05
9750000 -11.33 -10.51 15413 0.01 5e-05
9760000 -11.36 -10.51 15426 0.01 5e-05
9770000 -11.37 -10.51 15439 0.01 5e-05
9780000 -11.7 -10.51 15452 0.01 5e-05
9790000 -11.45 -10.51 15464 0.01 5e-05
9800000 -11.22 -10.51 15476 0.01 5e-05
9810000 -11.36 -10.51 15488 0.01 5e-05
9820000 -11.48 -10.51 15501 0.01 5e-05
9830000 -11.31 -10.51 15512 0.01 5e-05
9840000 -11.27 -10.51 15525 0.01 5e-05
9850000 -10.76 -10.51 15537 0.01 5e-05
9860000 -10.53 -10.51 15549 0.01 5e-05
9870000 -10.29 -10.29 15561 0.01 5e-05
9880000 -10.29 -10.28 15573 0.01 5e-05
9890000 -10.33 -10.2 15587 0.01 5e-05
9900000 -10.25 -10.17 15598 0.01 5e-05
9910000 -9.97 -9.84 15611 0.01 5e-05
================================================
FILE: hw3/log/_RAM_31-01-2018_08-28-28/log.txt
================================================
Timestep MeanReward BestMeanReward episodes exploration learning_rate
60000 -20.72 -20.57 207 0.194 0.0001
70000 -20.74 -20.57 242 0.193 0.0001
80000 -20.71 -20.57 276 0.192 0.0001
90000 -20.53 -20.52 308 0.191 0.0001
100000 -20.4 -20.4 341 0.19 0.0001
110000 -20.22 -20.22 372 0.189 0.0001
120000 -20.2 -20.18 405 0.188 0.0001
130000 -20.11 -20.11 436 0.187 0.0001
140000 -20.19 -20.09 467 0.186 0.0001
150000 -20.02 -20.02 496 0.185 0.0001
160000 -19.88 -19.86 526 0.184 0.0001
170000 -19.73 -19.73 554 0.183 0.0001
180000 -19.44 -19.44 581 0.18200000000000002 0.0001
190000 -19.34 -19.34 607 0.181 0.0001
200000 -19.13 -19.13 633 0.18 0.0001
210000 -19.14 -19.0 661 0.17900000000000002 0.0001
220000 -19.27 -19.0 688 0.17800000000000002 0.0001
230000 -19.08 -19.0 714 0.17700000000000002 0.0001
240000 -18.94 -18.94 739 0.17600000000000002 0.0001
250000 -18.89 -18.85 765 0.17500000000000002 0.0001
260000 -18.55 -18.55 789 0.17400000000000002 0.0001
270000 -18.63 -18.54 813 0.17300000000000001 0.0001
280000 -18.52 -18.45 837 0.17200000000000001 0.0001
290000 -18.13 -18.13 860 0.171 0.0001
300000 -18.24 -18.01 886 0.17 0.0001
310000 -18.09 -18.01 909 0.169 0.0001
320000 -17.91 -17.86 932 0.168 0.0001
330000 -17.86 -17.86 955 0.167 0.0001
340000 -17.67 -17.67 977 0.166 0.0001
350000 -17.68 -17.51 1000 0.165 0.0001
360000 -18.05 -17.51 1025 0.164 0.0001
370000 -17.99 -17.51 1048 0.163 0.0001
380000 -18.11 -17.51 1071 0.162 0.0001
390000 -18.05 -17.51 1094 0.161 0.0001
400000 -17.78 -17.51 1116 0.16 0.0001
410000 -17.59 -17.51 1139 0.159 0.0001
420000 -17.55 -17.51 1161 0.158 0.0001
430000 -17.51 -17.43 1183 0.157 0.0001
440000 -17.6 -17.43 1206 0.156 0.0001
450000 -17.37 -17.32 1228 0.155 0.0001
460000 -17.53 -17.32 1251 0.154 0.0001
470000 -17.55 -17.32 1273 0.15300000000000002 0.0001
480000 -17.4 -17.32 1296 0.15200000000000002 0.0001
490000 -17.33 -17.32 1318 0.15100000000000002 0.0001
500000 -17.27 -17.26 1339 0.15000000000000002 0.0001
510000 -17.17 -17.04 1360 0.14900000000000002 0.0001
520000 -17.1 -16.9 1382 0.14800000000000002 0.0001
530000 -16.95 -16.9 1404 0.14700000000000002 0.0001
540000 -17.21 -16.86 1427 0.14600000000000002 0.0001
550000 -17.23 -16.86 1449 0.14500000000000002 0.0001
560000 -17.38 -16.86 1471 0.14400000000000002 0.0001
570000 -17.44 -16.86 1495 0.14300000000000002 0.0001
580000 -17.33 -16.86 1516 0.14200000000000002 0.0001
590000 -17.03 -16.86 1537 0.14100000000000001 0.0001
600000 -17.02 -16.86 1559 0.14 0.0001
610000 -17.12 -16.86 1582 0.139 0.0001
620000 -17.18 -16.86 1604 0.138 0.0001
630000 -17.14 -16.86 1625 0.137 0.0001
640000 -17.23 -16.86 1647 0.136 0.0001
650000 -17.24 -16.86 1669 0.135 0.0001
660000 -17.09 -16.86 1689 0.134 0.0001
670000 -17.02 -16.86 1711 0.133 0.0001
680000 -17.04 -16.86 1732 0.132 0.0001
690000 -17.06 -16.86 1753 0.131 0.0001
700000 -16.99 -16.86 1775 0.13 0.0001
710000 -17.03 -16.8 1796 0.129 0.0001
720000 -17.02 -16.8 1818 0.128 0.0001
730000 -16.97 -16.8 1838 0.127 0.0001
740000 -16.75 -16.75 1858 0.126 0.0001
750000 -16.83 -16.6 1879 0.125 0.0001
760000 -16.64 -16.6 1900 0.124 0.0001
770000 -16.81 -16.6 1922 0.123 0.0001
780000 -16.89 -16.6 1942 0.122 0.0001
790000 -16.93 -16.6 1963 0.121 0.0001
800000 -16.82 -16.6 1983 0.12 0.0001
810000 -16.78 -16.6 2004 0.119 0.0001
820000 -16.4 -16.4 2023 0.11800000000000001 0.0001
830000 -16.41 -16.36 2043 0.117 0.0001
840000 -16.49 -16.34 2064 0.116 0.0001
850000 -16.32 -16.3 2082 0.115 0.0001
860000 -16.18 -16.16 2102 0.114 0.0001
870000 -16.43 -16.12 2121 0.113 0.0001
880000 -16.24 -16.12 2141 0.112 0.0001
890000 -16.25 -16.1 2160 0.111 0.0001
900000 -16.45 -16.1 2180 0.11 0.0001
910000 -16.41 -16.1 2198 0.109 0.0001
920000 -16.37 -16.1 2217 0.108 0.0001
930000 -16.33 -16.1 2235 0.107 0.0001
940000 -16.46 -16.1 2255 0.10600000000000001 0.0001
950000 -16.1 -16.04 2274 0.10500000000000001 0.0001
960000 -16.15 -16.03 2293 0.10400000000000001 0.0001
970000 -16.2 -16.03 2313 0.10300000000000001 0.0001
980000 -16.17 -16.01 2333 0.10200000000000001 0.0001
990000 -15.9 -15.9 2352 0.101 0.0001
1000000 -16.14 -15.88 2371 0.1 0.0001
1010000 -16.09 -15.88 2391 0.099775 9.9875e-05
1020000 -16.07 -15.88 2410 0.09955 9.975e-05
1030000 -16.1 -15.88 2430 0.09932500000000001 9.962500000000001e-05
1040000 -15.91 -15.88 2448 0.09910000000000001 9.95e-05
1050000 -15.84 -15.79 2468 0.098875 9.9375e-05
1060000 -15.71 -15.71 2486 0.09865 9.925e-05
1070000 -15.85 -15.58 2506 0.098425 9.912500000000001e-05
1080000 -15.86 -15.58 2525 0.09820000000000001 9.900000000000001e-05
1090000 -15.85 -15.58 2543 0.097975 9.8875e-05
1100000 -15.73 -15.58 2562 0.09775 9.875e-05
1110000 -15.82 -15.58 2580 0.097525 9.8625e-05
1120000 -15.8 -15.58 2599 0.09730000000000001 9.850000000000001e-05
1130000 -15.64 -15.58 2618 0.09707500000000001 9.8375e-05
1140000 -15.52 -15.47 2636 0.09685 9.825e-05
1150000 -15.69 -15.47 2655 0.096625 9.8125e-05
1160000 -15.75 -15.47 2673 0.0964 9.800000000000001e-05
1170000 -15.75 -15.47 2692 0.09617500000000001 9.787500000000001e-05
1180000 -15.64 -15.47 2711 0.09595000000000001 9.775e-05
1190000 -15.51 -15.47 2728 0.095725 9.7625e-05
1200000 -15.52 -15.47 2746 0.0955 9.75e-05
1210000 -15.57 -15.41 2764 0.095275 9.737500000000001e-05
1220000 -15.35 -15.35 2782 0.09505000000000001 9.725e-05
1230000 -15.54 -15.33 2802 0.094825 9.7125e-05
1240000 -15.7 -15.33 2821 0.0946 9.7e-05
1250000 -15.83 -15.33 2840 0.094375 9.687500000000001e-05
1260000 -15.95 -15.33 2859 0.09415000000000001 9.675000000000001e-05
1270000 -15.86 -15.33 2877 0.09392500000000001 9.6625e-05
1280000 -15.66 -15.33 2894 0.0937 9.65e-05
1290000 -15.41 -15.33 2911 0.093475 9.6375e-05
1300000 -15.16 -15.14 2928 0.09325 9.625000000000001e-05
1310000 -15.34 -15.14 2946 0.09302500000000001 9.6125e-05
1320000 -15.06 -15.01 2963 0.09280000000000001 9.6e-05
1330000 -15.19 -14.97 2981 0.092575 9.5875e-05
1340000 -15.01 -14.97 3000 0.09235 9.575000000000001e-05
1350000 -15.05 -14.9 3017 0.09212500000000001 9.562500000000001e-05
1360000 -14.92 -14.9 3035 0.09190000000000001 9.55e-05
1370000 -14.95 -14.73 3054 0.091675 9.5375e-05
1380000 -15.12 -14.73 3073 0.09145 9.525000000000001e-05
1390000 -15.15 -14.73 3091 0.091225 9.512500000000001e-05
1400000 -15.34 -14.73 3109 0.091 9.5e-05
1410000 -15.58 -14.73 3128 0.09077500000000001 9.4875e-05
1420000 -15.73 -14.73 3146 0.09055 9.475e-05
1430000 -15.55 -14.73 3163 0.090325 9.462500000000001e-05
1440000 -15.65 -14.73 3181 0.0901 9.45e-05
1450000 -15.59 -14.73 3198 0.08987500000000001 9.4375e-05
1460000 -15.36 -14.73 3215 0.08965000000000001 9.425e-05
1470000 -15.28 -14.73 3232 0.089425 9.412500000000001e-05
1480000 -15.35 -14.73 3251 0.0892 9.400000000000001e-05
1490000 -15.53 -14.73 3269 0.088975 9.3875e-05
1500000 -15.47 -14.73 3287 0.08875000000000001 9.375e-05
1510000 -15.36 -14.73 3305 0.088525 9.3625e-05
1520000 -15.49 -14.73 3322 0.0883 9.350000000000001e-05
1530000 -15.38 -14.73 3340 0.088075 9.3375e-05
1540000 -15.22 -14.73 3358 0.08785 9.325e-05
1550000 -15.17 -14.73 3376 0.08762500000000001 9.3125e-05
1560000 -15.17 -14.73 3393 0.0874 9.300000000000001e-05
1570000 -15.13 -14.73 3410 0.087175 9.287500000000001e-05
1580000 -15.19 -14.73 3426 0.08695 9.275e-05
1590000 -15.57 -14.73 3443 0.08672500000000001 9.2625e-05
1600000 -15.53 -14.73 3459 0.08650000000000001 9.25e-05
1610000 -15.62 -14.73 3476 0.086275 9.237500000000001e-05
1620000 -15.65 -14.73 3494 0.08605 9.225e-05
1630000 -15.65 -14.73 3512 0.085825 9.2125e-05
1640000 -15.27 -14.73 3529 0.08560000000000001 9.2e-05
1650000 -15.3 -14.73 3549 0.085375 9.1875e-05
1660000 -15.29 -14.73 3566 0.08515 9.175000000000001e-05
1670000 -15.05 -14.73 3583 0.084925 9.1625e-05
1680000 -15.21 -14.73 3601 0.0847 9.15e-05
1690000 -15.32 -14.73 3618 0.08447500000000001 9.137500000000001e-05
1700000 -15.27 -14.73 3635 0.08425 9.125000000000001e-05
1710000 -15.23 -14.73 3653 0.084025 9.1125e-05
1720000 -15.46 -14.73 3671 0.0838 9.1e-05
1730000 -15.34 -14.73 3688 0.08357500000000001 9.0875e-05
1740000 -15.51 -14.73 3706 0.08335000000000001 9.075000000000001e-05
1750000 -15.5 -14.73 3722 0.083125 9.062500000000001e-05
1760000 -15.42 -14.73 3740 0.0829 9.05e-05
1770000 -15.4 -14.73 3757 0.082675 9.0375e-05
1780000 -15.37 -14.73 3774 0.08245 9.025e-05
1790000 -15.46 -14.73 3792 0.082225 9.012500000000001e-05
1800000 -15.22 -14.73 3809 0.082 9e-05
1810000 -15.24 -14.73 3825 0.081775 8.9875e-05
1820000 -15.04 -14.73 3842 0.08155000000000001 8.975e-05
1830000 -15.12 -14.73 3860 0.08132500000000001 8.962500000000001e-05
1840000 -15.19 -14.73 3876 0.0811 8.950000000000001e-05
1850000 -15.2 -14.73 3892 0.080875 8.9375e-05
1860000 -15.41 -14.73 3910 0.08065 8.925e-05
1870000 -15.71 -14.73 3927 0.080425 8.912500000000001e-05
1880000 -15.82 -14.73 3943 0.08020000000000001 8.900000000000001e-05
1890000 -15.71 -14.73 3959 0.079975 8.8875e-05
1900000 -15.78 -14.73 3977 0.07975 8.875e-05
1910000 -15.74 -14.73 3995 0.079525 8.8625e-05
1920000 -15.6 -14.73 4011 0.07930000000000001 8.850000000000001e-05
1930000 -15.57 -14.73 4028 0.079075 8.837500000000001e-05
1940000 -15.26 -14.73 4045 0.07885 8.825e-05
1950000 -15.38 -14.73 4062 0.078625 8.8125e-05
1960000 -15.5 -14.73 4080 0.0784 8.8e-05
1970000 -15.48 -14.73 4098 0.07817500000000001 8.787500000000001e-05
1980000 -15.48 -14.73 4115 0.07795 8.775e-05
1990000 -15.64 -14.73 4134 0.077725 8.7625e-05
2000000 -15.75 -14.73 4150 0.0775 8.75e-05
2010000 -15.62 -14.73 4167 0.07727500000000001 8.737500000000001e-05
2020000 -15.48 -14.73 4184 0.07705000000000001 8.725e-05
2030000 -15.64 -14.73 4201 0.076825 8.7125e-05
2040000 -15.45 -14.73 4217 0.0766 8.7e-05
2050000 -15.18 -14.73 4233 0.076375 8.687500000000001e-05
2060000 -15.0 -14.73 4249 0.07615 8.675000000000001e-05
2070000 -14.99 -14.73 4266 0.075925 8.6625e-05
2080000 -14.88 -14.73 4283 0.0757 8.65e-05
2090000 -14.79 -14.73 4300 0.075475 8.6375e-05
2100000 -14.71 -14.68 4316 0.07525 8.625000000000001e-05
2110000 -14.71 -14.68 4333 0.07502500000000001 8.6125e-05
2120000 -14.89 -14.68 4349 0.0748 8.6e-05
2130000 -15.01 -14.68 4366 0.074575 8.5875e-05
2140000 -15.13 -14.68 4384 0.07435 8.575000000000001e-05
2150000 -15.17 -14.68 4401 0.074125 8.562500000000001e-05
2160000 -15.42 -14.68 4419 0.07390000000000001 8.55e-05
2170000 -15.39 -14.68 4436 0.073675 8.5375e-05
2180000 -15.3 -14.68 4451 0.07345 8.525000000000001e-05
2190000 -15.19 -14.68 4468 0.073225 8.512500000000001e-05
2200000 -15.08 -14.68 4483 0.07300000000000001 8.5e-05
2210000 -15.03 -14.68 4501 0.072775 8.4875e-05
2220000 -15.16 -14.68 4519 0.07255 8.475e-05
2230000 -15.11 -14.68 4535 0.072325 8.462500000000001e-05
2240000 -15.19 -14.68 4552 0.0721 8.450000000000001e-05
2250000 -15.41 -14.68 4569 0.071875 8.4375e-05
2260000 -15.45 -14.68 4586 0.07165 8.425e-05
2270000 -15.26 -14.68 4602 0.071425 8.4125e-05
2280000 -15.21 -14.68 4620 0.0712 8.400000000000001e-05
2290000 -15.29 -14.68 4636 0.070975 8.3875e-05
2300000 -15.33 -14.68 4653 0.07075000000000001 8.375e-05
2310000 -15.23 -14.68 4670 0.070525 8.3625e-05
2320000 -15.5 -14.68 4688 0.0703 8.35e-05
2330000 -15.73 -14.68 4706 0.070075 8.337500000000001e-05
2340000 -15.65 -14.68 4722 0.06985 8.325e-05
2350000 -15.51 -14.68 4739 0.06962499999999999 8.3125e-05
2360000 -15.63 -14.68 4756 0.0694 8.3e-05
2370000 -15.66 -14.68 4772 0.069175 8.2875e-05
2380000 -15.47 -14.68 4789 0.06895000000000001 8.275e-05
2390000 -15.31 -14.68 4806 0.06872500000000001 8.2625e-05
2400000 -15.44 -14.68 4823 0.0685 8.25e-05
2410000 -15.41 -14.68 4840 0.068275 8.237500000000001e-05
2420000 -15.15 -14.68 4856 0.06805 8.225000000000001e-05
2430000 -15.05 -14.68 4870 0.067825 8.2125e-05
2440000 -14.99 -14.68 4887 0.0676 8.2e-05
2450000 -14.81 -14.68 4903 0.067375 8.1875e-05
2460000 -14.75 -14.68 4921 0.06715 8.175000000000001e-05
2470000 -14.62 -14.62 4937 0.06692500000000001 8.1625e-05
2480000 -14.96 -14.59 4954 0.06670000000000001 8.15e-05
2490000 -14.72 -14.59 4969 0.066475 8.1375e-05
2500000 -14.6 -14.59 4984 0.06625 8.125e-05
2510000 -14.64 -14.56 5002 0.066025 8.112500000000001e-05
2520000 -14.53 -14.49 5019 0.0658 8.1e-05
2530000 -14.59 -14.49 5035 0.065575 8.0875e-05
2540000 -14.55 -14.49 5052 0.06534999999999999 8.075000000000001e-05
2550000 -14.69 -14.47 5067 0.065125 8.062500000000001e-05
2560000 -15.02 -14.47 5084 0.0649 8.05e-05
2570000 -14.72 -14.47 5100 0.06467500000000001 8.0375e-05
2580000 -14.55 -14.47 5116 0.06445000000000001 8.025e-05
2590000 -14.67 -14.47 5132 0.064225 8.012500000000001e-05
2600000 -14.59 -14.47 5148 0.064 8e-05
2610000 -14.61 -14.47 5164 0.063775 7.9875e-05
2620000 -14.41 -14.37 5181 0.06355 7.975e-05
2630000 -14.76 -14.37 5198 0.063325 7.9625e-05
2640000 -15.16 -14.37 5215 0.0631 7.950000000000001e-05
2650000 -15.06 -14.37 5230 0.062875 7.9375e-05
2660000 -15.02 -14.37 5247 0.06265000000000001 7.925e-05
2670000 -15.01 -14.37 5263 0.062425 7.912500000000001e-05
2680000 -14.89 -14.37 5279 0.062200000000000005 7.900000000000001e-05
2690000 -14.88 -14.37 5296 0.061975 7.8875e-05
2700000 -14.66 -14.37 5312 0.06175 7.875e-05
2710000 -14.63 -14.37 5328 0.061525 7.8625e-05
2720000 -14.58 -14.37 5343 0.0613 7.850000000000001e-05
2730000 -14.72 -14.37 5359 0.061075000000000004 7.837500000000001e-05
2740000 -14.64 -14.37 5375 0.06085 7.825e-05
2750000 -14.66 -14.37 5391 0.060625 7.8125e-05
2760000 -14.65 -14.37 5408 0.0604 7.8e-05
2770000 -14.73 -14.37 5424 0.060175 7.787500000000001e-05
2780000 -14.92 -14.37 5441 0.05995 7.775e-05
2790000 -14.83 -14.37 5456 0.059725 7.7625e-05
2800000 -14.89 -14.37 5471 0.0595 7.75e-05
2810000 -14.92 -14.37 5488 0.059275 7.7375e-05
2820000 -15.06 -14.37 5506 0.05905 7.725000000000001e-05
2830000 -15.11 -14.37 5523 0.058825 7.7125e-05
2840000 -15.05 -14.37 5539 0.0586 7.7e-05
2850000 -15.08 -14.37 5556 0.058374999999999996 7.6875e-05
2860000 -15.15 -14.37 5572 0.05815 7.675e-05
2870000 -15.03 -14.37 5588 0.057925 7.6625e-05
2880000 -15.05 -14.37 5606 0.0577 7.65e-05
2890000 -14.93 -14.37 5621 0.057475000000000005 7.6375e-05
2900000 -14.72 -14.37 5637 0.05725 7.625000000000001e-05
2910000 -14.87 -14.37 5653 0.057025 7.612500000000001e-05
2920000 -14.93 -14.37 5670 0.0568 7.6e-05
2930000 -14.93 -14.37 5686 0.056575 7.5875e-05
2940000 -14.82 -14.37 5703 0.056350000000000004 7.575e-05
2950000 -14.76 -14.37 5719 0.056125 7.562500000000001e-05
2960000 -14.94 -14.37 5735 0.0559 7.55e-05
2970000 -14.72 -14.37 5750 0.055675 7.5375e-05
2980000 -14.68 -14.37 5766 0.05545 7.525e-05
2990000 -14.53 -14.37 5780 0.055225 7.5125e-05
3000000 -14.46 -14.37 5797 0.055 7.500000000000001e-05
3010000 -14.44 -14.35 5813 0.054775000000000004 7.4875e-05
3020000 -14.39 -14.34 5828 0.05455 7.475e-05
3030000 -14.61 -14.24 5845 0.054325000000000005 7.462500000000001e-05
3040000 -14.46 -14.24 5860 0.0541 7.45e-05
3050000 -14.65 -14.24 5877 0.053875000000000006 7.4375e-05
3060000 -14.84 -14.24 5894 0.053649999999999996 7.425e-05
3070000 -14.89 -14.24 5910 0.053425 7.4125e-05
3080000 -14.86 -14.24 5926 0.0532 7.400000000000001e-05
3090000 -14.93 -14.24 5942 0.052975 7.3875e-05
3100000 -14.72 -14.24 5957 0.05275 7.375e-05
3110000 -14.69 -14.24 5973 0.052525 7.3625e-05
3120000 -14.63 -14.24 5988 0.0523 7.35e-05
3130000 -14.61 -14.24 6005 0.052075 7.337500000000001e-05
3140000 -14.68 -14.24 6022 0.05185 7.325e-05
3150000 -14.73 -14.24 6039 0.051625000000000004 7.3125e-05
3160000 -14.83 -14.24 6055 0.051399999999999994 7.3e-05
3170000 -15.02 -14.24 6072 0.051175 7.2875e-05
3180000 -15.05 -14.24 6088 0.050949999999999995 7.275e-05
3190000 -14.89 -14.24 6104 0.050725 7.2625e-05
3200000 -14.96 -14.24 6120 0.050499999999999996 7.25e-05
3210000 -14.92 -14.24 6136 0.050275 7.237500000000001e-05
3220000 -15.04 -14.24 6153 0.05005 7.225e-05
3230000 -14.89 -14.24 6169 0.049825 7.2125e-05
3240000 -14.69 -14.24 6184 0.0496 7.2e-05
3250000 -15.0 -14.24 6200 0.049375 7.1875e-05
3260000 -14.91 -14.24 6215 0.049150000000000006 7.175000000000001e-05
3270000 -14.83 -14.24 6231 0.048924999999999996 7.1625e-05
3280000 -14.47 -14.24 6245 0.04870000000000001 7.15e-05
3290000 -14.5 -14.24 6261 0.048475 7.1375e-05
3300000 -14.61 -14.24 6276 0.04825 7.125000000000001e-05
3310000 -14.78 -14.24 6294 0.048025 7.112500000000001e-05
3320000 -14.92 -14.24 6312 0.0478 7.1e-05
3330000 -15.08 -14.24 6328 0.047575 7.0875e-05
3340000 -15.21 -14.24 6344 0.04735 7.075000000000001e-05
3350000 -15.23 -14.24 6361 0.047125 7.0625e-05
3360000 -15.37 -14.24 6377 0.046900000000000004 7.05e-05
3370000 -15.03 -14.24 6392 0.046674999999999994 7.0375e-05
3380000 -14.86 -14.24 6409 0.04645 7.025e-05
3390000 -14.74 -14.24 6424 0.046224999999999995 7.0125e-05
3400000 -14.56 -14.24 6440 0.046 7.000000000000001e-05
3410000 -14.93 -14.24 6456 0.045774999999999996 6.9875e-05
3420000 -14.77 -14.24 6471 0.04555 6.975e-05
3430000 -14.92 -14.24 6487 0.045325 6.9625e-05
3440000 -14.73 -14.24 6503 0.0451 6.950000000000001e-05
3450000 -14.8 -14.24 6518 0.044875 6.937499999999999e-05
3460000 -14.91 -14.24 6535 0.04465 6.925e-05
3470000 -14.78 -14.24 6551 0.04442499999999999 6.9125e-05
3480000 -14.38 -14.24 6565 0.044199999999999996 6.9e-05
3490000 -14.43 -14.24 6581 0.04397499999999999 6.887500000000001e-05
3500000 -14.39 -14.24 6597 0.04375 6.875e-05
3510000 -14.38 -14.24 6612 0.043525 6.8625e-05
3520000 -14.57 -14.24 6628 0.0433 6.850000000000001e-05
3530000 -14.5 -14.24 6644 0.043075 6.837500000000001e-05
3540000 -14.81 -14.24 6661 0.04285 6.825e-05
3550000 -14.89 -14.24 6676 0.042625 6.8125e-05
3560000 -14.72 -14.24 6691 0.0424 6.8e-05
3570000 -14.55 -14.24 6706 0.042175000000000004 6.787500000000001e-05
3580000 -14.49 -14.24 6722 0.041949999999999994 6.775e-05
3590000 -14.5 -14.24 6736 0.041725000000000005 6.7625e-05
3600000 -14.67 -14.24 6753 0.041499999999999995 6.75e-05
3610000 -14.57 -14.24 6768 0.041275 6.7375e-05
3620000 -14.51 -14.24 6783 0.041049999999999996 6.725000000000001e-05
3630000 -14.72 -14.24 6799 0.040825 6.7125e-05
3640000 -14.74 -14.24 6815 0.0406 6.7e-05
3650000 -14.74 -14.24 6831 0.040375 6.687500000000001e-05
3660000 -14.63 -14.24 6846 0.04015 6.675e-05
3670000 -14.64 -14.24 6861 0.039925 6.6625e-05
3680000 -14.66 -14.24 6876 0.03969999999999999 6.65e-05
3690000 -14.61 -14.24 6892 0.039474999999999996 6.6375e-05
3700000 -14.67 -14.24 6908 0.03924999999999999 6.625e-05
3710000 -14.39 -14.24 6923 0.039025 6.6125e-05
3720000 -14.58 -14.24 6939 0.038799999999999994 6.6e-05
3730000 -14.83 -14.24 6956 0.038575 6.5875e-05
3740000 -14.81 -14.24 6971 0.038349999999999995 6.575e-05
3750000 -15.07 -14.24 6987 0.038125 6.562500000000001e-05
3760000 -14.9 -14.24 7003 0.0379 6.55e-05
3770000 -14.93 -14.24 7018 0.037675 6.5375e-05
3780000 -14.95 -14.24 7032 0.03745 6.525000000000001e-05
3790000 -14.53 -14.24 7046 0.037224999999999994 6.5125e-05
3800000 -14.34 -14.24 7062 0.037000000000000005 6.500000000000001e-05
3810000 -14.29 -14.24 7078 0.036775 6.4875e-05
3820000 -14.32 -14.24 7093 0.03655 6.475e-05
3830000 -14.3 -14.15 7108 0.036324999999999996 6.462500000000001e-05
3840000 -14.45 -14.15 7124 0.03610000000000001 6.45e-05
3850000 -14.79 -14.15 7140 0.03587499999999999 6.4375e-05
3860000 -14.63 -14.15 7154 0.03565 6.425e-05
3870000 -14.76 -14.15 7170 0.035425 6.4125e-05
3880000 -14.68 -14.15 7185 0.035199999999999995 6.400000000000001e-05
3890000 -14.75 -14.15 7201 0.03497499999999999 6.3875e-05
3900000 -14.69 -14.15 7216 0.03475 6.375e-05
3910000 -14.57 -14.15 7232 0.034525 6.3625e-05
3920000 -14.31 -14.15 7246 0.0343 6.35e-05
3930000 -14.47 -14.15 7261 0.034074999999999994 6.337500000000001e-05
3940000 -14.4 -14.15 7276 0.033850000000000005 6.325e-05
3950000 -14.49 -14.15 7292 0.03362499999999999 6.3125e-05
3960000 -14.29 -14.15 7307 0.0334 6.300000000000001e-05
3970000 -14.25 -14.08 7322 0.033174999999999996 6.2875e-05
3980000 -14.12 -14.08 7337 0.03294999999999999 6.275000000000001e-05
3990000 -13.93 -13.93 7351 0.03272499999999999 6.262499999999999e-05
4000000 -14.05 -13.78 7366 0.0325 6.25e-05
4010000 -14.17 -13.78 7380 0.032275 6.237500000000001e-05
4020000 -14.12 -13.78 7395 0.032049999999999995 6.225e-05
4030000 -14.21 -13.78 7410 0.031825000000000006 6.2125e-05
4040000 -14.37 -13.78 7427 0.0316 6.2e-05
4050000 -14.65 -13.78 7443 0.031375 6.1875e-05
4060000 -14.98 -13.78 7459 0.031149999999999997 6.175000000000001e-05
4070000 -15.05 -13.78 7475 0.030924999999999994 6.162500000000001e-05
4080000 -15.05 -13.78 7490 0.03069999999999999 6.15e-05
4090000 -15.05 -13.78 7506 0.030475000000000002 6.137500000000001e-05
4100000 -14.95 -13.78 7521 0.03025 6.125e-05
4110000 -15.09 -13.78 7538 0.030024999999999996 6.112500000000001e-05
4120000 -14.78 -13.78 7552 0.029799999999999993 6.1e-05
4130000 -14.59 -13.78 7566 0.029575000000000004 6.0875e-05
4140000 -14.47 -13.78 7581 0.02935 6.075e-05
4150000 -14.54 -13.78 7596 0.029124999999999998 6.0625e-05
4160000 -14.62 -13.78 7612 0.028899999999999995 6.05e-05
4170000 -14.72 -13.78 7627 0.028674999999999992 6.0375000000000004e-05
4180000 -14.65 -13.78 7642 0.02844999999999999 6.025e-05
4190000 -14.51 -13.78 7656 0.028225 6.0125000000000005e-05
4200000 -14.42 -13.78 7671 0.027999999999999997 6e-05
4210000 -14.65 -13.78 7686 0.027774999999999994 5.9875000000000005e-05
4220000 -14.51 -13.78 7700 0.02754999999999999 5.975e-05
4230000 -14.27 -13.78 7715 0.027325000000000002 5.9625000000000006e-05
4240000 -14.21 -13.78 7730 0.0271 5.95e-05
4250000 -14.59 -13.78 7747 0.026874999999999996 5.9375e-05
4260000 -14.42 -13.78 7761 0.026650000000000007 5.9250000000000004e-05
4270000 -14.59 -13.78 7777 0.02642499999999999 5.9125e-05
4280000 -14.58 -13.78 7791 0.0262 5.9000000000000004e-05
4290000 -14.71 -13.78 7807 0.025974999999999998 5.8875e-05
4300000 -14.8 -13.78 7822 0.025749999999999995 5.8750000000000005e-05
4310000 -14.63 -13.78 7837 0.025524999999999992 5.8625e-05
4320000 -14.52 -13.78 7852 0.025300000000000003 5.8500000000000006e-05
4330000 -14.73 -13.78 7868 0.025075 5.8375e-05
4340000 -14.65 -13.78 7883 0.024849999999999997 5.8250000000000006e-05
4350000 -14.63 -13.78 7898 0.024624999999999994 5.8125e-05
4360000 -14.59 -13.78 7914 0.024400000000000005 5.800000000000001e-05
4370000 -14.79 -13.78 7930 0.024174999999999988 5.7875000000000004e-05
4380000 -14.99 -13.78 7946 0.02395 5.775e-05
4390000 -14.9 -13.78 7962 0.023724999999999996 5.7625e-05
4400000 -14.84 -13.78 7976 0.023499999999999993 5.75e-05
4410000 -14.91 -13.78 7991 0.02327499999999999 5.7375e-05
4420000 -15.08 -13.78 8007 0.02305 5.725e-05
4430000 -14.85 -13.78 8022 0.022824999999999998 5.7125e-05
4440000 -14.74 -13.78 8037 0.022599999999999995 5.7e-05
4450000 -14.64 -13.78 8052 0.022374999999999992 5.6875e-05
4460000 -14.6 -13.78 8067 0.022150000000000003 5.6750000000000004e-05
4470000 -14.6 -13.78 8081 0.021924999999999986 5.6625e-05
4480000 -14.38 -13.78 8096 0.021699999999999997 5.6500000000000005e-05
4490000 -14.23 -13.78 8110 0.021474999999999994 5.6375e-05
4500000 -14.18 -13.78 8125 0.02124999999999999 5.6250000000000005e-05
4510000 -14.09 -13.78 8139 0.021025000000000002 5.6125e-05
4520000 -14.14 -13.78 8154 0.0208 5.6e-05
4530000 -14.12 -13.78 8169 0.020574999999999996 5.5875e-05
4540000 -14.42 -13.78 8185 0.020349999999999993 5.575e-05
4550000 -14.35 -13.78 8199 0.020125000000000004 5.5625000000000004e-05
4560000 -14.19 -13.78 8214 0.0199 5.55e-05
4570000 -14.08 -13.78 8227 0.019674999999999998 5.5375000000000004e-05
4580000 -14.2 -13.78 8242 0.019449999999999995 5.525e-05
4590000 -13.77 -13.77 8256 0.019225000000000006 5.5125000000000005e-05
4600000 -13.73 -13.7 8271 0.01899999999999999 5.5e-05
4610000 -13.43 -13.42 8285 0.018775 5.4875000000000006e-05
4620000 -13.6 -13.42 8301 0.018549999999999997 5.475e-05
4630000 -13.64 -13.42 8315 0.018324999999999994 5.4625000000000006e-05
4640000 -14.02 -13.42 8331 0.01809999999999999 5.45e-05
4650000 -14.21 -13.42 8346 0.017875000000000002 5.437500000000001e-05
4660000 -14.25 -13.42 8360 0.01765 5.4250000000000004e-05
4670000 -14.29 -13.42 8374 0.017424999999999996 5.4125e-05
4680000 -14.59 -13.42 8390 0.017199999999999993 5.4e-05
4690000 -14.47 -13.42 8405 0.01697499999999999 5.3875e-05
4700000 -14.64 -13.42 8419 0.016749999999999987 5.375e-05
4710000 -14.6 -13.42 8435 0.016524999999999998 5.3625e-05
4720000 -14.49 -13.42 8449 0.016299999999999995 5.35e-05
4730000 -14.51 -13.42 8464 0.016074999999999992 5.3375e-05
4740000 -14.38 -13.42 8478 0.01584999999999999 5.325e-05
4750000 -13.97 -13.42 8493 0.015625 5.3125000000000004e-05
4760000 -14.16 -13.42 8509 0.015399999999999997 5.300000000000001e-05
4770000 -14.28 -13.42 8524 0.015174999999999994 5.2875000000000005e-05
4780000 -14.07 -13.42 8538 0.014950000000000005 5.275000000000001e-05
4790000 -14.26 -13.42 8554 0.014724999999999988 5.2625000000000005e-05
4800000 -14.29 -13.42 8568 0.014499999999999999 5.25e-05
4810000 -14.5 -13.42 8583 0.014274999999999996 5.2375e-05
4820000 -14.3 -13.42 8596 0.014049999999999993 5.225e-05
4830000 -13.96 -13.42 8610 0.01382499999999999 5.2125e-05
4840000 -14.0 -13.42 8625 0.013600000000000001 5.2000000000000004e-05
4850000 -14.05 -13.42 8639 0.013374999999999998 5.1875e-05
4860000 -13.87 -13.42 8654 0.013149999999999995 5.1750000000000004e-05
4870000 -14.06 -13.42 8669 0.012924999999999992 5.1625e-05
4880000 -13.9 -13.42 8683 0.012700000000000003 5.1500000000000005e-05
4890000 -14.12 -13.42 8698 0.012474999999999986 5.1375e-05
4900000 -14.33 -13.42 8714 0.012249999999999997 5.1250000000000006e-05
4910000 -14.35 -13.42 8729 0.012024999999999994 5.1125e-05
4920000 -14.31 -13.42 8742 0.011799999999999991 5.1000000000000006e-05
4930000 -14.63 -13.42 8758 0.011574999999999988 5.0875e-05
4940000 -14.76 -13.42 8774 0.011349999999999999 5.075e-05
4950000 -14.85 -13.42 8789 0.011124999999999996 5.0625e-05
4960000 -14.77 -13.42 8802 0.010899999999999993 5.05e-05
4970000 -14.72 -13.42 8817 0.01067499999999999 5.0375e-05
4980000 -14.7 -13.42 8831 0.010450000000000001 5.025e-05
4990000 -14.66 -13.42 8846 0.010224999999999984 5.0125e-05
5000000 -14.5 -13.42 8861 0.01 5e-05
5010000 -14.22 -13.42 8875 0.01 5e-05
5020000 -14.07 -13.42 8889 0.01 5e-05
5030000 -14.17 -13.42 8903 0.01 5e-05
5040000 -14.08 -13.42 8918 0.01 5e-05
5050000 -14.29 -13.42 8933 0.01 5e-05
5060000 -14.34 -13.42 8948 0.01 5e-05
5070000 -14.34 -13.42 8963 0.01 5e-05
5080000 -14.56 -13.42 8978 0.01 5e-05
5090000 -14.46 -13.42 8993 0.01 5e-05
5100000 -14.41 -13.42 9007 0.01 5e-05
5110000 -14.55 -13.42 9023 0.01 5e-05
5120000 -14.64 -13.42 9038 0.01 5e-05
5130000 -14.43 -13.42 9052 0.01 5e-05
5140000 -14.4 -13.42 9067 0.01 5e-05
5150000 -14.37 -13.42 9081 0.01 5e-05
5160000 -14.28 -13.42 9095 0.01 5e-05
5170000 -14.29 -13.42 9110 0.01 5e-05
5180000 -14.07 -13.42 9124 0.01 5e-05
5190000 -14.09 -13.42 9140 0.01 5e-05
5200000 -14.25 -13.42 9155 0.01 5e-05
5210000 -14.26 -13.42 9169 0.01 5e-05
5220000 -14.15 -13.42 9184 0.01 5e-05
5230000 -14.32 -13.42 9198 0.01 5e-05
5240000 -14.2 -13.42 9211 0.01 5e-05
5250000 -14.07 -13.42 9225 0.01 5e-05
5260000 -13.91 -13.42 9240 0.01 5e-05
5270000 -13.91 -13.42 9255 0.01 5e-05
5280000 -14.06 -13.42 9269 0.01 5e-05
5290000 -14.04 -13.42 9284 0.01 5e-05
5300000 -13.84 -13.42 9297 0.01 5e-05
5310000 -14.01 -13.42 9311 0.01 5e-05
5320000 -14.0 -13.42 9324 0.01 5e-05
5330000 -14.08 -13.42 9339 0.01 5e-05
5340000 -14.01 -13.42 9353 0.01 5e-05
5350000 -13.98 -13.42 9368 0.01 5e-05
5360000 -13.91 -13.42 9381 0.01 5e-05
5370000 -14.14 -13.42 9395 0.01 5e-05
5380000 -14.06 -13.42 9409 0.01 5e-05
5390000 -14.26 -13.42 9424 0.01 5e-05
5400000 -14.01 -13.42 9438 0.01 5e-05
5410000 -13.69 -13.42 9450 0.01 5e-05
5420000 -13.65 -13.42 9464 0.01 5e-05
5430000 -13.88 -13.42 9479 0.01 5e-05
5440000 -13.81 -13.42 9493 0.01 5e-05
5450000 -13.89 -13.42 9508 0.01 5e-05
5460000 -13.91 -13.42 9522 0.01 5e-05
5470000 -13.97 -13.42 9535 0.01 5e-05
5480000 -14.22 -13.42 9550 0.01 5e-05
5490000 -13.95 -13.42 9563 0.01 5e-05
5500000 -13.7 -13.42 9578 0.01 5e-05
5510000 -13.74 -13.42 9592 0.01 5e-05
5520000 -13.64 -13.42 9606 0.01 5e-05
5530000 -13.78 -13.42 9621 0.01 5e-05
5540000 -13.72 -13.42 9634 0.01 5e-05
5550000 -13.61 -13.42 9648 0.01 5e-05
5560000 -13.91 -13.42 9663 0.01 5e-05
5570000 -13.63 -13.42 9675 0.01 5e-05
5580000 -13.59 -13.42 9690 0.01 5e-05
5590000 -13.77 -13.42 9704 0.01 5e-05
5600000 -13.51 -13.42 9717 0.01 5e-05
5610000 -13.83 -13.42 9732 0.01 5e-05
5620000 -14.2 -13.42 9747 0.01 5e-05
5630000 -13.94 -13.42 9760 0.01 5e-05
5640000 -14.18 -13.42 9774 0.01 5e-05
5650000 -14.28 -13.42 9788 0.01 5e-05
5660000 -14.14 -13.42 9801 0.01 5e-05
5670000 -13.9 -13.42 9814 0.01 5e-05
5680000 -13.91 -13.42 9829 0.01 5e-05
5690000 -13.64 -13.42 9843 0.01 5e-05
5700000 -13.9 -13.42 9858 0.01 5e-05
5710000 -13.77 -13.42 9871 0.01 5e-05
5720000 -13.67 -13.42 9887 0.01 5e-05
5730000 -13.84 -13.42 9901 0.01 5e-05
5740000 -14.05 -13.42 9915 0.01 5e-05
5750000 -13.77 -13.42 9928 0.01 5e-05
5760000 -13.88 -13.42 9944 0.01 5e-05
5770000 -13.86 -13.42 9958 0.01 5e-05
5780000 -14.07 -13.42 9972 0.01 5e-05
5790000 -14.03 -13.42 9987 0.01 5e-05
5800000 -13.98 -13.42 10000 0.01 5e-05
5810000 -14.22 -13.42 10015 0.01 5e-05
5820000 -14.58 -13.42 10030 0.01 5e-05
5830000 -14.54 -13.42 10044 0.01 5e-05
5840000 -14.42 -13.42 10057 0.01 5e-05
5850000 -14.23 -13.42 10071 0.01 5e-05
5860000 -14.31 -13.42 10084 0.01 5e-05
5870000 -14.33 -13.42 10099 0.01 5e-05
5880000 -14.24 -13.42 10112 0.01 5e-05
5890000 -13.97 -13.42 10127 0.01 5e-05
5900000 -13.76 -13.42 10141 0.01 5e-05
5910000 -13.62 -13.42 10154 0.01 5e-05
5920000 -13.62 -13.42 10167 0.01 5e-05
5930000 -13.56 -13.4 10181 0.01 5e-05
5940000 -13.62 -13.4 10195 0.01 5e-05
5950000 -13.73 -13.4 10209 0.01 5e-05
5960000 -13.79 -13.4 10223 0.01 5e-05
5970000 -13.81 -13.4 10238 0.01 5e-05
5980000 -13.86 -13.4 10252 0.01 5e-05
5990000 -14.23 -13.4 10267 0.01 5e-05
6000000 -14.26 -13.4 10281 0.01 5e-05
6010000 -14.19 -13.4 10294 0.01 5e-05
6020000 -14.31 -13.4 10309 0.01 5e-05
6030000 -14.24 -13.4 10323 0.01 5e-05
6040000 -14.27 -13.4 10338 0.01 5e-05
6050000 -14.5 -13.4 10354 0.01 5e-05
6060000 -14.28 -13.4 10367 0.01 5e-05
6070000 -14.31 -13.4 10382 0.01 5e-05
6080000 -14.36 -13.4 10396 0.01 5e-05
6090000 -14.49 -13.4 10411 0.01 5e-05
6100000 -14.5 -13.4 10426 0.01 5e-05
6110000 -14.46 -13.4 10440 0.01 5e-05
6120000 -14.3 -13.4 10454 0.01 5e-05
6130000 -14.62 -13.4 10469 0.01 5e-05
6140000 -14.44 -13.4 10483 0.01 5e-05
6150000 -14.51 -13.4 10497 0.01 5e-05
6160000 -14.13 -13.4 10511 0.01 5e-05
6170000 -14.09 -13.4 10524 0.01 5e-05
6180000 -13.99 -13.4 10537 0.01 5e-05
6190000 -13.86 -13.4 10551 0.01 5e-05
6200000 -13.88 -13.4 10567 0.01 5e-05
6210000 -13.92 -13.4 10580 0.01 5e-05
6220000 -13.77 -13.4 10594 0.01 5e-05
6230000 -13.8 -13.4 10608 0.01 5e-05
6240000 -13.88 -13.4 10622 0.01 5e-05
6250000 -13.91 -13.4 10636 0.01 5e-05
6260000 -13.91 -13.4 10650 0.01 5e-05
6270000 -13.84 -13.4 10664 0.01 5e-05
6280000 -13.92 -13.4 10679 0.01 5e-05
6290000 -13.76 -13.4 10692 0.01 5e-05
6300000 -13.8 -13.4 10705 0.01 5e-05
6310000 -13.79 -13.4 10719 0.01 5e-05
6320000 -13.61 -13.4 10731 0.01 5e-05
6330000 -13.58 -13.4 10745 0.01 5e-05
6340000 -13.55 -13.4 10758 0.01 5e-05
6350000 -13.34 -13.34 10771 0.01 5e-05
6360000 -13.29 -13.17 10784 0.01 5e-05
6370000 -13.64 -13.17 10799 0.01 5e-05
6380000 -13.71 -13.17 10813 0.01 5e-05
6390000 -13.79 -13.17 10827 0.01 5e-05
6400000 -13.9 -13.17 10841 0.01 5e-05
6410000 -13.93 -13.17 10854 0.01 5e-05
6420000 -13.97 -13.17 10868 0.01 5e-05
6430000 -14.34 -13.17 10883 0.01 5e-05
6440000 -14.13 -13.17 10897 0.01 5e-05
6450000 -14.03 -13.17 10911 0.01 5e-05
6460000 -13.96 -13.17 10925 0.01 5e-05
6470000 -14.1 -13.17 10941 0.01 5e-05
6480000 -14.04 -13.17 10954 0.01 5e-05
6490000 -14.0 -13.17 10967 0.01 5e-05
6500000 -13.86 -13.17 10981 0.01 5e-05
6510000 -13.84 -13.17 10994 0.01 5e-05
6520000 -13.72 -13.17 11008 0.01 5e-05
6530000 -13.85 -13.17 11023 0.01 5e-05
6540000 -13.93 -13.17 11038 0.01 5e-05
6550000 -13.98 -13.17 11052 0.01 5e-05
6560000 -14.11 -13.17 11066 0.01 5e-05
6570000 -13.96 -13.17 11079 0.01 5e-05
6580000 -14.08 -13.17 11094 0.01 5e-05
6590000 -14.1 -13.17 11108 0.01 5e-05
6600000 -14.07 -13.17 11122 0.01 5e-05
6610000 -13.67 -13.17 11135 0.01 5e-05
6620000 -13.83 -13.17 11149 0.01 5e-05
6630000 -13.9 -13.17 11164 0.01 5e-05
6640000 -14.23 -13.17 11179 0.01 5e-05
6650000 -14.33 -13.17 11193 0.01 5e-05
6660000 -14.17 -13.17 11207 0.01 5e-05
6670000 -14.08 -13.17 11221 0.01 5e-05
6680000 -14.32 -13.17 11235 0.01 5e-05
6690000 -14.29 -13.17 11249 0.01 5e-05
6700000 -14.19 -13.17 11264 0.01 5e-05
6710000 -14.15 -13.17 11279 0.01 5e-05
6720000 -13.95 -13.17 11293 0.01 5e-05
6730000 -13.97 -13.17 11306 0.01 5e-05
6740000 -13.98 -13.17 11320 0.01 5e-05
6750000 -14.06 -13.17 11336 0.01 5e-05
6760000 -13.89 -13.17 11349 0.01 5e-05
6770000 -13.84 -13.17 11362 0.01 5e-05
6780000 -13.69 -13.17 11376 0.01 5e-05
6790000 -13.88 -13.17 11391 0.01 5e-05
6800000 -14.1 -13.17 11406 0.01 5e-05
6810000 -14.23 -13.17 11421 0.01 5e-05
6820000 -14.14 -13.17 11435 0.01 5e-05
6830000 -14.08 -13.17 11448 0.01 5e-05
6840000 -14.19 -13.17 11462 0.01 5e-05
6850000 -14.26 -13.17 11476 0.01 5e-05
6860000 -14.18 -13.17 11491 0.01 5e-05
6870000 -14.05 -13.17 11504 0.01 5e-05
6880000 -13.62 -13.17 11518 0.01 5e-05
6890000 -13.68 -13.17 11532 0.01 5e-05
6900000 -13.84 -13.17 11547 0.01 5e-05
6910000 -13.87 -13.17 11560 0.01 5e-05
6920000 -13.77 -13.17 11574 0.01 5e-05
6930000 -13.29 -13.17 11585 0.01 5e-05
6940000 -13.34 -13.14 11598 0.01 5e-05
6950000 -13.25 -13.14 11612 0.01 5e-05
6960000 -13.38 -13.14 11625 0.01 5e-05
6970000 -13.24 -13.14 11638 0.01 5e-05
6980000 -13.24 -13.14 11653 0.01 5e-05
6990000 -13.19 -13.14 11667 0.01 5e-05
7000000 -13.41 -13.14 11680 0.01 5e-05
7010000 -13.72 -13.14 11694 0.01 5e-05
7020000 -13.77 -13.14 11708 0.01 5e-05
7030000 -13.82 -13.14 11720 0.01 5e-05
7040000 -13.85 -13.14 11734 0.01 5e-05
7050000 -13.8 -13.14 11748 0.01 5e-05
7060000 -13.97 -13.14 11763 0.01 5e-05
7070000 -14.11 -13.14 11777 0.01 5e-05
7080000 -14.26 -13.14 11792 0.01 5e-05
7090000 -14.15 -13.14 11805 0.01 5e-05
7100000 -14.18 -13.14 11818 0.01 5e-05
7110000 -14.19 -13.14 11833 0.01 5e-05
7120000 -14.19 -13.14 11847 0.01 5e-05
7130000 -14.05 -13.14 11861 0.01 5e-05
7140000 -13.91 -13.14 11875 0.01 5e-05
7150000 -13.8 -13.14 11888 0.01 5e-05
7160000 -13.82 -13.14 11901 0.01 5e-05
7170000 -13.74 -13.14 11916 0.01 5e-05
7180000 -13.92 -13.14 11930 0.01 5e-05
7190000 -14.0 -13.14 11944 0.01 5e-05
7200000 -14.08 -13.14 11959 0.01 5e-05
7210000 -13.94 -13.14 11971 0.01 5e-05
7220000 -13.7 -13.14 11985 0.01 5e-05
7230000 -13.76 -13.14 11998 0.01 5e-05
7240000 -13.7 -13.14 12011 0.01 5e-05
7250000 -13.63 -13.14 12025 0.01 5e-05
7260000 -13.43 -13.14 12036 0.01 5e-05
7270000 -13.25 -13.14 12050 0.01 5e-05
7280000 -13.37 -13.03 12064 0.01 5e-05
7290000 -13.46 -13.03 12077 0.01 5e-05
7300000 -13.61 -13.03 12091 0.01 5e-05
7310000 -13.94 -13.03 12106 0.01 5e-05
7320000 -13.9 -13.03 12119 0.01 5e-05
7330000 -14.12 -13.03 12133 0.01 5e-05
7340000 -14.07 -13.03 12146 0.01 5e-05
7350000 -14.17 -13.03 12159 0.01 5e-05
7360000 -14.06 -13.03 12173 0.01 5e-05
7370000 -14.18 -13.03 12187 0.01 5e-05
7380000 -13.82 -13.03 12200 0.01 5e-05
7390000 -13.73 -13.03 12214 0.01 5e-05
7400000 -13.65 -13.03 12226 0.01 5e-05
7410000 -13.4 -13.03 12240 0.01 5e-05
7420000 -13.64 -13.03 12254 0.01 5e-05
7430000 -13.51 -13.03 12267 0.01 5e-05
7440000 -13.4 -13.03 12281 0.01 5e-05
7450000 -13.7 -13.03 12295 0.01 5e-05
7460000 -13.73 -13.03 12310 0.01 5e-05
7470000 -14.02 -13.03 12324 0.01 5e-05
7480000 -14.04 -13.03 12337 0.01 5e-05
7490000 -13.95 -13.03 12350 0.01 5e-05
7500000 -13.9 -13.03 12363 0.01 5e-05
7510000 -13.61 -13.03 12376 0.01 5e-05
7520000 -13.44 -13.03 12389 0.01 5e-05
7530000 -13.19 -13.03 12402 0.01 5e-05
7540000 -13.25 -13.03 12416 0.01 5e-05
7550000 -13.21 -13.03 12430 0.01 5e-05
7560000 -13.53 -13.03 12444 0.01 5e-05
7570000 -13.32 -13.03 12456 0.01 5e-05
7580000 -13.11 -13.03 12469 0.01 5e-05
7590000 -13.45 -13.03 12482 0.01 5e-05
7600000 -13.65 -13.03 12495 0.01 5e-05
7610000 -13.84 -13.03 12511 0.01 5e-05
7620000 -13.7 -13.03 12525 0.01 5e-05
7630000 -13.48 -13.03 12537 0.01 5e-05
7640000 -13.46 -13.03 12551 0.01 5e-05
7650000 -13.77 -13.03 12565 0.01 5e-05
7660000 -13.89 -13.03 12579 0.01 5e-05
7670000 -13.96 -13.03 12592 0.01 5e-05
7680000 -13.77 -13.03 12606 0.01 5e-05
7690000 -13.6 -13.03 12619 0.01 5e-05
7700000 -13.71 -13.03 12632 0.01 5e-05
7710000 -13.64 -13.03 12645 0.01 5e-05
7720000 -13.71 -13.03 12660 0.01 5e-05
7730000 -13.92 -13.03 12675 0.01 5e-05
7740000 -13.74 -13.03 12687 0.01 5e-05
7750000 -13.78 -13.03 12701 0.01 5e-05
7760000 -13.91 -13.03 12715 0.01 5e-05
7770000 -14.12 -13.03 12730 0.01 5e-05
7780000 -14.22 -13.03 12743 0.01 5e-05
7790000 -14.11 -13.03 12757 0.01 5e-05
7800000 -13.92 -13.03 12770 0.01 5e-05
7810000 -13.74 -13.03 12782 0.01 5e-05
7820000 -13.87 -13.03 12797 0.01 5e-05
7830000 -13.75 -13.03 12810 0.01 5e-05
7840000 -13.57 -13.03 12823 0.01 5e-05
7850000 -13.6 -13.03 12837 0.01 5e-05
7860000 -13.85 -13.03 12851 0.01 5e-05
7870000 -13.66 -13.03 12865 0.01 5e-05
7880000 -13.65 -13.03 12877 0.01 5e-05
7890000 -13.69 -13.03 12891 0.01 5e-05
7900000 -13.93 -13.03 12907 0.01 5e-05
7910000 -14.26 -13.03 12921 0.01 5e-05
7920000 -14.28 -13.03 12934 0.01 5e-05
7930000 -14.31 -13.03 12948 0.01 5e-05
7940000 -14.37 -13.03 12962 0.01 5e-05
7950000 -14.22 -13.03 12976 0.01 5e-05
7960000 -14.31 -13.03 12989 0.01 5e-05
7970000 -14.32 -13.03 13004 0.01 5e-05
7980000 -14.05 -13.03 13018 0.01 5e-05
7990000 -14.13 -13.03 13032 0.01 5e-05
8000000 -13.9 -13.03 13045 0.01 5e-05
8010000 -13.91 -13.03 13058 0.01 5e-05
8020000 -14.03 -13.03 13071 0.01 5e-05
8030000 -13.97 -13.03 13086 0.01 5e-05
8040000 -13.82 -13.03 13099 0.01 5e-05
8050000 -13.91 -13.03 13114 0.01 5e-05
8060000 -14.03 -13.03 13129 0.01 5e-05
8070000 -14.39 -13.03 13144 0.01 5e-05
8080000 -14.25 -13.03 13157 0.01 5e-05
8090000 -14.21 -13.03 13170 0.01 5e-05
8100000 -14.25 -13.03 13183 0.01 5e-05
8110000 -14.2 -13.03 13196 0.01 5e-05
8120000 -14.37 -13.03 13211 0.01 5e-05
8130000 -14.07 -13.03 13224 0.01 5e-05
8140000 -13.94 -13.03 13238 0.01 5e-05
8150000 -13.92 -13.03 13251 0.01 5e-05
8160000 -13.98 -13.03 13265 0.01 5e-05
8170000 -13.96 -13.03 13279 0.01 5e-05
8180000 -13.72 -13.03 13291 0.01 5e-05
8190000 -13.69 -13.03 13304 0.01 5e-05
8200000 -13.81 -13.03 13319 0.01 5e-05
8210000 -13.86 -13.03 13331 0.01 5e-05
8220000 -13.62 -13.03 13344 0.01 5e-05
8230000 -13.61 -13.03 13358 0.01 5e-05
8240000 -13.45 -13.03 13371 0.01 5e-05
8250000 -13.5 -13.03 13384 0.01 5e-05
8260000 -13.73 -13.03 13399 0.01 5e-05
8270000 -13.52 -13.03 13412 0.01 5e-05
8280000 -13.34 -13.03 13425 0.01 5e-05
8290000 -13.34 -13.03 13437 0.01 5e-05
8300000 -13.27 -13.03 13450 0.01 5e-05
8310000 -13.48 -13.03 13464 0.01 5e-05
8320000 -13.73 -13.03 13478 0.01 5e-05
8330000 -13.79 -13.03 13491 0.01 5e-05
8340000 -13.65 -13.03 13506 0.01 5e-05
8350000 -14.21 -13.03 13522 0.01 5e-05
8360000 -14.13 -13.03 13535 0.01 5e-05
8370000 -14.28 -13.03 13548 0.01 5e-05
8380000 -14.07 -13.03 13562 0.01 5e-05
8390000 -14.1 -13.03 13577 0.01 5e-05
8400000 -14.14 -13.03 13591 0.01 5e-05
8410000 -14.29 -13.03 13605 0.01 5e-05
8420000 -14.09 -13.03 13619 0.01 5e-05
8430000 -14.08 -13.03 13633 0.01 5e-05
8440000 -14.2 -13.03 13647 0.01 5e-05
8450000 -14.2 -13.03 13661 0.01 5e-05
8460000 -14.28 -13.03 13676 0.01 5e-05
8470000 -14.18 -13.03 13690 0.01 5e-05
8480000 -14.04 -13.03 13703 0.01 5e-05
8490000 -13.84 -13.03 13716 0.01 5e-05
8500000 -13.87 -13.03 13730 0.01 5e-05
8510000 -13.88 -13.03 13744 0.01 5e-05
8520000 -13.79 -13.03 13758 0.01 5e-05
8530000 -13.67 -13.03 13771 0.01 5e-05
8540000 -13.71 -13.03 13784 0.01 5e-05
8550000 -13.48 -13.03 13796 0.01 5e-05
8560000 -13.51 -13.03 13810 0.01 5e-05
8570000 -13.62 -13.03 13824 0.01 5e-05
8580000 -13.47 -13.03 13837 0.01 5e-05
8590000 -13.33 -13.03 13850 0.01 5e-05
8600000 -13.27 -13.03 13862 0.01 5e-05
8610000 -13.1 -13.03 13876 0.01 5e-05
8620000 -13.31 -13.01 13890 0.01 5e-05
8630000 -13.43 -13.01 13903 0.01 5e-05
8640000 -13.35 -13.01 13917 0.01 5e-05
8650000 -13.31 -13.01 13931 0.01 5e-05
8660000 -13.38 -13.01 13945 0.01 5e-05
8670000 -13.46 -13.01 13958 0.01 5e-05
8680000 -13.74 -13.01 13973 0.01 5e-05
8690000 -13.86 -13.01 13987 0.01 5e-05
8700000 -13.86 -13.01 14002 0.01 5e-05
8710000 -13.73 -13.01 14015 0.01 5e-05
8720000 -13.51 -13.01 14028 0.01 5e-05
8730000 -13.86 -13.01 14043 0.01 5e-05
8740000 -13.76 -13.01 14056 0.01 5e-05
8750000 -13.69 -13.01 14070 0.01 5e-05
8760000 -13.78 -13.01 14084 0.01 5e-05
8770000 -13.79 -13.01 14098 0.01 5e-05
8780000 -13.79 -13.01 14111 0.01 5e-05
8790000 -13.99 -13.01 14125 0.01 5e-05
8800000 -13.83 -13.01 14140 0.01 5e-05
8810000 -13.82 -13.01 14153 0.01 5e-05
8820000 -13.54 -13.01 14165 0.01 5e-05
8830000 -13.46 -13.01 14178 0.01 5e-05
8840000 -13.24 -13.01 14191 0.01 5e-05
8850000 -13.3 -13.01 14206 0.01 5e-05
8860000 -13.25 -13.01 14219 0.01 5e-05
8870000 -13.21 -13.01 14234 0.01 5e-05
8880000 -13.07 -13.01 14246 0.01 5e-05
8890000 -13.26 -12.94 14260 0.01 5e-05
8900000 -13.53 -12.94 14274 0.01 5e-05
8910000 -13.72 -12.94 14288 0.01 5e-05
8920000 -13.47 -12.94 14302 0.01 5e-05
8930000 -13.2 -12.94 14315 0.01 5e-05
8940000 -13.47 -12.94 14330 0.01 5e-05
8950000 -13.74 -12.94 14344 0.01 5e-05
8960000 -13.84 -12.94 14357 0.01 5e-05
8970000 -13.54 -12.94 14370 0.01 5e-05
8980000 -13.63 -12.94 14384 0.01 5e-05
8990000 -13.65 -12.94 14396 0.01 5e-05
9000000 -13.7 -12.94 14411 0.01 5e-05
9010000 -13.64 -12.94 14424 0.01 5e-05
9020000 -13.46 -12.94 14437 0.01 5e-05
9030000 -13.3 -12.94 14451 0.01 5e-05
9040000 -13.37 -12.94 14464 0.01 5e-05
9050000 -13.26 -12.94 14478 0.01 5e-05
9060000 -13.46 -12.94 14492 0.01 5e-05
9070000 -13.66 -12.94 14506 0.01 5e-05
9080000 -13.38 -12.94 14519 0.01 5e-05
9090000 -13.36 -12.94 14531 0.01 5e-05
9100000 -13.1 -12.94 14543 0.01 5e-05
9110000 -13.38 -12.94 14558 0.01 5e-05
9120000 -13.53 -12.94 14572 0.01 5e-05
9130000 -13.64 -12.94 14586 0.01 5e-05
9140000 -13.65 -12.94 14600 0.01 5e-05
9150000 -13.46 -12.94 14613 0.01 5e-05
9160000 -13.46 -12.94 14626 0.01 5e-05
9170000 -13.8 -12.94 14640 0.01 5e-05
9180000 -14.0 -12.94 14654 0.01 5e-05
9190000 -13.9 -12.94 14667 0.01 5e-05
9200000 -13.65 -12.94 14680 0.01 5e-05
9210000 -13.59 -12.94 14694 0.01 5e-05
9220000 -13.54 -12.94 14708 0.01 5e-05
9230000 -13.87 -12.94 14721 0.01 5e-05
9240000 -13.93 -12.94 14735 0.01 5e-05
9250000 -13.54 -12.94 14747 0.01 5e-05
9260000 -13.34 -12.94 14760 0.01 5e-05
9270000 -13.36 -12.94 14773 0.01 5e-05
9280000 -13.41 -12.94 14787 0.01 5e-05
9290000 -13.52 -12.94 14801 0.01 5e-05
9300000 -13.43 -12.94 14814 0.01 5e-05
9310000 -13.41 -12.94 14827 0.01 5e-05
9320000 -13.48 -12.94 14841 0.01 5e-05
9330000 -13.58 -12.94 14854 0.01 5e-05
9340000 -13.8 -12.94 14869 0.01 5e-05
9350000 -13.8 -12.94 14884 0.01 5e-05
9360000 -13.71 -12.94 14896 0.01 5e-05
9370000 -13.67 -12.94 14909 0.01 5e-05
9380000 -13.48 -12.94 14923 0.01 5e-05
9390000 -13.64 -12.94 14937 0.01 5e-05
9400000 -13.72 -12.94 14950 0.01 5e-05
9410000 -13.64 -12.94 14964 0.01 5e-05
9420000 -13.54 -12.94 14979 0.01 5e-05
9430000 -13.53 -12.94 14992 0.01 5e-05
9440000 -13.47 -12.94 15005 0.01 5e-05
9450000 -13.25 -12.94 15018 0.01 5e-05
9460000 -13.1 -12.94 15029 0.01 5e-05
9470000 -12.92 -12.92 15043 0.01 5e-05
9480000 -13.02 -12.9 15056 0.01 5e-05
9490000 -13.04 -12.88 15070 0.01 5e-05
9500000 -12.96 -12.88 15083 0.01 5e-05
9510000 -13.1 -12.86 15097 0.01 5e-05
9520000 -13.05 -12.86 15110 0.01 5e-05
9530000 -13.44 -12.86 15124 0.01 5e-05
9540000 -13.25 -12.86 15135 0.01 5e-05
9550000 -13.34 -12.86 15150 0.01 5e-05
9560000 -13.28 -12.86 15162 0.01 5e-05
9570000 -13.24 -12.86 15175 0.01 5e-05
9580000 -13.04 -12.86 15188 0.01 5e-05
9590000 -13.1 -12.86 15201 0.01 5e-05
9600000 -12.92 -12.86 15214 0.01 5e-05
9610000 -13.34 -12.86 15229 0.01 5e-05
9620000 -13.28 -12.86 15243 0.01 5e-05
9630000 -13.33 -12.86 15256 0.01 5e-05
9640000 -13.29 -12.86 15269 0.01 5e-05
9650000 -13.38 -12.86 15283 0.01 5e-05
9660000 -13.64 -12.86 15296 0.01 5e-05
9670000 -13.45 -12.86 15309 0.01 5e-05
9680000 -13.57 -12.86 15322 0.01 5e-05
9690000 -13.34 -12.86 15336 0.01 5e-05
9700000 -13.38 -12.86 15350 0.01 5e-05
9710000 -13.5 -12.86 15364 0.01 5e-05
9720000 -13.53 -12.86 15378 0.01 5e-05
9730000 -13.68 -12.86 15393 0.01 5e-05
9740000 -13.93 -12.86 15406 0.01 5e-05
9750000 -13.77 -12.86 15419 0.01 5e-05
9760000 -13.87 -12.86 15432 0.01 5e-05
9770000 -14.04 -12.86 15446 0.01 5e-05
9780000 -13.73 -12.86 15458 0.01 5e-05
9790000 -13.9 -12.86 15472 0.01 5e-05
9800000 -13.66 -12.86 15485 0.01 5e-05
9810000 -13.37 -12.86 15499 0.01 5e-05
9820000 -13.26 -12.86 15511 0.01 5e-05
9830000 -13.37 -12.86 15525 0.01 5e-05
9840000 -13.03 -12.86 15538 0.01 5e-05
9850000 -13.24 -12.86 15552 0.01 5e-05
9860000 -13.3 -12.86 15565 0.01 5e-05
9870000 -13.22 -12.86 15578 0.01 5e-05
9880000 -13.35 -12.86 15592 0.01 5e-05
9890000 -13.51 -12.86 15605 0.01 5e-05
9900000 -13.77 -12.86 15619 0.01 5e-05
9910000 -13.8 -12.86 15632 0.01 5e-05
================================================
FILE: hw3/logz.py
================================================
import json
"""
Some simple logging functionality, inspired by rllab's logging.
Assumes that each diagnostic gets logged each iteration
Call logz.configure_output_dir() to start logging to a
tab-separated-values file (some_folder_name/log.txt)
To load the learning curves, you can do, for example
A = np.genfromtxt('/tmp/expt_1468984536/log.txt',delimiter='\t',dtype=None, names=True)
A['EpRewMean']
"""
import os.path as osp, shutil, time, atexit, os, subprocess
import pickle
import tensorflow as tf
color2num = dict(
gray=30,
red=31,
green=32,
yellow=33,
blue=34,
magenta=35,
cyan=36,
white=37,
crimson=38
)
def colorize(string, color, bold=False, highlight=False):
attr = []
num = color2num[color]
if highlight: num += 10
attr.append(str(num))
if bold: attr.append('1')
return '\x1b[%sm%s\x1b[0m' % (';'.join(attr), string)
class G:
output_dir = None
output_file = None
first_row = True
log_headers = []
log_current_row = {}
def configure_output_dir(d=None):
"""
Set output directory to d, or to /tmp/somerandomnumber if d is None
"""
G.output_dir = d or "/tmp/experiments/%i"%int(time.time())
assert not osp.exists(G.output_dir), "Log dir %s already exists! Delete it first or use a different dir"%G.output_dir
os.makedirs(G.output_dir)
G.output_file = open(osp.join(G.output_dir, "log.txt"), 'w')
atexit.register(G.output_file.close)
print(colorize("Logging data to %s"%G.output_file.name, 'green', bold=True))
def log_tabular(key, val):
"""
Log a value of some diagnostic
Call this once for each diagnostic quantity, each iteration
"""
if G.first_row:
G.log_headers.append(key)
else:
assert key in G.log_headers, "Trying to introduce a new key %s that you didn't include in the first iteration"%key
assert key not in G.log_current_row, "You already set %s this iteration. Maybe you forgot to call dump_tabular()"%key
G.log_current_row[key] = val
def save_params(params):
with open(osp.join(G.output_dir, "params.json"), 'w') as out:
out.write(json.dumps(params, separators=(',\n','\t:\t'), sort_keys=True))
def pickle_tf_vars():
"""
Saves tensorflow variables
Requires them to be initialized first, also a default session must exist
"""
_dict = {v.name : v.eval() for v in tf.global_variables()}
with open(osp.join(G.output_dir, "vars.pkl"), 'wb') as f:
pickle.dump(_dict, f)
def dump_tabular():
"""
Write all of the diagnostics from the current iteration
"""
vals = []
key_lens = [len(key) for key in G.log_headers]
max_key_len = max(15,max(key_lens))
keystr = '%'+'%d'%max_key_len
fmt = "| " + keystr + "s | %15s |"
n_slashes = 22 + max_key_len
print("-"*n_slashes)
for key in G.log_headers:
val = G.log_current_row.get(key, "")
if hasattr(val, "__float__"): valstr = "%8.3g"%val
else: valstr = val
print(fmt%(key, valstr))
vals.append(val)
print("-"*n_slashes)
if G.output_file is not None:
if G.first_row:
G.output_file.write("\t".join(G.log_headers))
G.output_file.write("\n")
G.output_file.write("\t".join(map(str,vals)))
G.output_file.write("\n")
G.output_file.flush()
G.log_current_row.clear()
G.first_row=False
================================================
FILE: hw3/plot.py
================================================
import seaborn as sns
import pandas as pd
import matplotlib.pyplot as plt
import json
import os
"""
Using the plotter:
Call it from the command line, and supply it with logdirs to experiments.
Suppose you ran an experiment with name 'test', and you ran 'test' for 10
random seeds. The runner code stored it in the directory structure
data
L test_EnvName_DateTime
L 0
L log.txt
L params.json
L 1
L log.txt
L params.json
.
.
.
L 9
L log.txt
L params.json
To plot learning curves from the experiment, averaged over all random
seeds, call
python plot.py data/test_EnvName_DateTime --value AverageReturn
and voila. To see a different statistics, change what you put in for
the keyword --value. You can also enter /multiple/ values, and it will
make all of them in order.
Suppose you ran two experiments: 'test1' and 'test2'. In 'test2' you tried
a different set of hyperparameters from 'test1', and now you would like
to compare them -- see their learning curves side-by-side. Just call
python plot.py data/test1 data/test2
and it will plot them both! They will be given titles in the legend according
to their exp_name parameters. If you want to use custom legend titles, use
the --legend flag and then provide a title for each logdir.
"""
def plot_data(data, value="MeanReward"):
if isinstance(data, list):
data = pd.concat(data, ignore_index=True)
sns.set(style="darkgrid", font_scale=1.5)
sns.tsplot(data=data, time="Timestep", value=value, unit="Unit", condition="Condition")
sns.tsplot(data=data, time="Timestep", value="BestMeanReward", unit="Unit", condition="Condition")
plt.legend(loc='best').draggable()
plt.show()
def get_datasets(fpath, condition=None):
unit = 0
datasets = []
for root, dir, files in os.walk(fpath):
if 'log.txt' in files:
# param_path = open(os.path.join(root,'params.json'))
# params = json.load(param_path)
exp_name = fpath
log_path = os.path.join(root,'log.txt')
experiment_data = pd.read_table(log_path)
experiment_data.insert(
len(experiment_data.columns),
'Unit',
unit
)
experiment_data.insert(
len(experiment_data.columns),
'Condition',
condition or exp_name
)
datasets.append(experiment_data)
unit += 1
return datasets
def main():
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('logdir', nargs='*')
parser.add_argument('--legend', nargs='*')
parser.add_argument('--value', default='MeanReward', nargs='*')
args = parser.parse_args()
use_legend = False
if args.legend is not None:
assert len(args.legend) == len(args.logdir), \
"Must give a legend title for each set of experiments."
use_legend = True
data = []
if use_legend:
for logdir, legend_title in zip(args.logdir, args.legend):
data += get_datasets(logdir, legend_title)
else:
for logdir in args.logdir:
data += get_datasets(logdir)
if isinstance(args.value, list):
values = args.value
else:
values = [args.value]
for value in values:
plot_data(data, value=value)
if __name__ == "__main__":
main()
================================================
FILE: hw3/run_dqn_atari.py
================================================
import argparse
import gym
from gym import wrappers
import os.path as osp
import random
import numpy as np
import tensorflow as tf
import logz
import os
import time
import tensorflow.contrib.layers as layers
import dqn
from dqn_utils import *
from atari_wrappers import *
def atari_model(img_in, num_actions, scope, reuse=False):
# as described in https://storage.googleapis.com/deepmind-data/assets/papers/DeepMindNature14236Paper.pdf
with tf.variable_scope(scope, reuse=reuse):
out = img_in
with tf.variable_scope("convnet"):
# original architecture
out = layers.convolution2d(out, num_outputs=32, kernel_size=8, stride=4, activation_fn=tf.nn.relu)
out = layers.convolution2d(out, num_outputs=64, kernel_size=4, stride=2, activation_fn=tf.nn.relu)
out = layers.convolution2d(out, num_outputs=64, kernel_size=3, stride=1, activation_fn=tf.nn.relu)
out = layers.flatten(out)
with tf.variable_scope("action_value"):
out = layers.fully_connected(out, num_outputs=512, activation_fn=tf.nn.relu)
out = layers.fully_connected(out, num_outputs=num_actions, activation_fn=None)
return out
def atari_learn(env,
session,
num_timesteps):
# This is just a rough estimate
num_iterations = float(num_timesteps) / 4.0
lr_multiplier = 1.0
lr_schedule = PiecewiseSchedule([
(0, 1e-4 * lr_multiplier),
(num_iterations / 10, 1e-4 * lr_multiplier),
(num_iterations / 2, 5e-5 * lr_multiplier),
],
outside_value=5e-5 * lr_multiplier)
optimizer = dqn.OptimizerSpec(
constructor=tf.train.AdamOptimizer,
kwargs=dict(epsilon=1e-4),
lr_schedule=lr_schedule
)
def stopping_criterion(env, t):
# notice that here t is the number of steps of the wrapped env,
# which is different from the number of steps in the underlying env
return get_wrapper_by_name(env, "Monitor").get_total_steps() >= num_timesteps
exploration_schedule = PiecewiseSchedule(
[
(0, 1.0),
(1e6, 0.1),
(num_iterations / 2, 0.01),
], outside_value=0.01
)
dqn.learn(
env,
q_func=atari_model,
optimizer_spec=optimizer,
session=session,
exploration=exploration_schedule,
stopping_criterion=stopping_criterion,
replay_buffer_size=1000000,
batch_size=32,
gamma=0.99,
learning_starts=50000,
learning_freq=4,
frame_history_len=4,
target_update_freq=10000,
grad_norm_clipping=10
)
env.close()
def get_available_gpus():
from tensorflow.python.client import device_lib
local_device_protos = device_lib.list_local_devices()
return [x.physical_device_desc for x in local_device_protos if x.device_type == 'GPU']
def set_global_seeds(i):
try:
import tensorflow as tf
except ImportError:
pass
else:
tf.set_random_seed(i)
np.random.seed(i)
random.seed(i)
def get_session():
tf.reset_default_graph()
tf_config = tf.ConfigProto(
inter_op_parallelism_threads=1,
intra_op_parallelism_threads=1)
session = tf.Session(config=tf_config)
print("AVAILABLE GPUS: ", get_available_gpus())
return session
def get_env(task, seed):
env_id = task.env_id
env = gym.make(env_id)
set_global_seeds(seed)
env.seed(seed)
expt_dir = '/tmp/hw3_vid_dir2/'
env = wrappers.Monitor(env, osp.join(expt_dir, "gym"), force=True)
env = wrap_deepmind(env)
return env
def main():
# Get Atari games.
benchmark = gym.benchmark_spec('Atari40M')
# Change the index to select a different game.
task = benchmark.tasks[3]
PROJECT_ROOT = os.path.dirname(os.path.realpath(__file__))
logz.configure_output_dir(os.path.join(PROJECT_ROOT, "log/"+"_RAM_"+time.strftime("%d-%m-%Y_%H-%M-%S")))
# Run training
seed = 0 # Use a seed of zero (you may want to randomize the seed!)
env = get_env(task, seed)
session = get_session()
atari_learn(env, session, num_timesteps=task.max_timesteps)
if __name__ == "__main__":
main()
================================================
FILE: hw3/run_dqn_ram.py
================================================
import argparse
import gym
from gym import wrappers
import os.path as osp
import random
import numpy as np
import tensorflow as tf
import tensorflow.contrib.layers as layers
import logz
import os
import time
import dqn
from dqn_utils import *
from atari_wrappers import *
def atari_model(ram_in, num_actions, scope, reuse=False):
with tf.variable_scope(scope, reuse=reuse):
out = ram_in
#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]))
with tf.variable_scope("action_value"):
out = layers.fully_connected(out, num_outputs=256, activation_fn=tf.nn.relu)
out = layers.fully_connected(out, num_outputs=128, activation_fn=tf.nn.relu)
out = layers.fully_connected(out, num_outputs=64, activation_fn=tf.nn.relu)
out = layers.fully_connected(out, num_outputs=num_actions, activation_fn=None)
return out
def atari_learn(env,
session,
num_timesteps):
# This is just a rough estimate
num_iterations = float(num_timesteps) / 4.0
lr_multiplier = 1.0
lr_schedule = PiecewiseSchedule([
(0, 1e-4 * lr_multiplier),
(num_iterations / 10, 1e-4 * lr_multiplier),
(num_iterations / 2, 5e-5 * lr_multiplier),
],
outside_value=5e-5 * lr_multiplier)
optimizer = dqn.OptimizerSpec(
constructor=tf.train.AdamOptimizer,
kwargs=dict(epsilon=1e-4),
lr_schedule=lr_schedule
)
def stopping_criterion(env, t):
# notice that here t is the number of steps of the wrapped env,
# which is different from the number of steps in the underlying env
return get_wrapper_by_name(env, "Monitor").get_total_steps() >= num_timesteps
exploration_schedule = PiecewiseSchedule(
[
(0, 0.2),
(1e6, 0.1),
(num_iterations / 2, 0.01),
], outside_value=0.01
)
dqn.learn(
env,
q_func=atari_model,
optimizer_spec=optimizer,
session=session,
exploration=exploration_schedule,
stopping_criterion=stopping_criterion,
replay_buffer_size=1000000,
batch_size=32,
gamma=0.99,
learning_starts=50000,
learning_freq=4,
frame_history_len=1,
target_update_freq=10000,#10000
grad_norm_clipping=10
)
env.close()
def get_available_gpus():
from tensorflow.python.client import device_lib
local_device_protos = device_lib.list_local_devices()
return [x.physical_device_desc for x in local_device_protos if x.device_type == 'GPU']
def set_global_seeds(i):
try:
import tensorflow as tf
except ImportError:
pass
else:
tf.set_random_seed(i)
np.random.seed(i)
random.seed(i)
def get_session():
tf.reset_default_graph()
tf_config = tf.ConfigProto(
inter_op_parallelism_threads=1,
intra_op_parallelism_threads=1)
session = tf.Session(config=tf_config)
print("AVAILABLE GPUS: ", get_available_gpus())
return session
def get_env(seed):
env = gym.make('Pong-ram-v0')
set_global_seeds(seed)
env.seed(seed)
expt_dir = '/tmp/hw3_vid_dir/'
env = wrappers.Monitor(env, osp.join(expt_dir, "gym"), force=True)
env = wrap_deepmind_ram(env)
return env
def main():
PROJECT_ROOT = os.path.dirname(os.path.realpath(__file__))
logz.configure_output_dir(os.path.join(PROJECT_ROOT, "log/"+"_RAM_"+time.strftime("%d-%m-%Y_%H-%M-%S")))
# Run training
seed = 0 # Use a seed of zero (you may want to randomize the seed!)
env = get_env(seed)
session = get_session()
atari_learn(env, session, num_timesteps=int(4e7))
if __name__ == "__main__":
main()
================================================
FILE: hw4/.idea/hw4.iml
================================================
================================================
FILE: hw4/.idea/misc.xml
================================================
================================================
FILE: hw4/.idea/modules.xml
================================================
================================================
FILE: hw4/.idea/workspace.xml
================================================
num_simulated_paths
plot_comparison
path_cost