SYMBOL INDEX (210 symbols across 22 files)

FILE: week01_intro/pong.py
  function make_pong (line 9) | def make_pong():
  class PreprocessAtari (line 14) | class PreprocessAtari(Wrapper):
    method __init__ (line 15) | def __init__(self, env, height=42, width=42,
    method reset (line 24) | def reset(self):
    method step (line 30) | def step(self, action):
    method update_buffer (line 38) | def update_buffer(self, img):
    method preproc_image (line 42) | def preproc_image(self, img):

FILE: week02_value_based/mdp.py
  class MDP (line 15) | class MDP:
    method __init__ (line 16) | def __init__(self, transition_probs, rewards, initial_state=None, seed...
    method get_all_states (line 59) | def get_all_states(self):
    method get_possible_actions (line 63) | def get_possible_actions(self, state):
    method is_terminal (line 67) | def is_terminal(self, state):
    method get_next_states (line 71) | def get_next_states(self, state, action):
    method get_transition_prob (line 76) | def get_transition_prob(self, state, action, next_state):
    method get_reward (line 80) | def get_reward(self, state, action, next_state):
    method reset (line 85) | def reset(self):
    method step (line 99) | def step(self, action):
    method render (line 108) | def render(self):
    method _check_param_consistency (line 111) | def _check_param_consistency(self, transition_probs, rewards):
  class FrozenLakeEnv (line 140) | class FrozenLakeEnv(MDP):
    method __init__ (line 185) | def __init__(self, desc=None, map_name="4x4", slip_chance=0.2, seed=No...
    method render (line 246) | def render(self):
  function plot_graph (line 252) | def plot_graph(mdp, s_node_size='1,5',
  function plot_graph_with_state_values (line 324) | def plot_graph_with_state_values(mdp, state_values):
  function get_optimal_action_for_plot (line 333) | def get_optimal_action_for_plot(mdp, state_values, state, get_action_val...
  function plot_graph_optimal_strategy_and_state_values (line 343) | def plot_graph_optimal_strategy_and_state_values(mdp, state_values, get_...

FILE: week04_[recap]_deep_learning/mnist.py
  function load_dataset (line 8) | def load_dataset():

FILE: week04_[recap]_deep_learning/notmnist.py
  function load_notmnist (line 10) | def load_notmnist(path='./notMNIST_small', letters='ABCDEFGHIJ',

FILE: week04_approx_rl/dqn/analysis.py
  function play_and_log_episode (line 7) | def play_and_log_episode(env, agent, t_max=10000):

FILE: week04_approx_rl/dqn/atari_wrappers.py
  class FireResetEnv (line 6) | class FireResetEnv(Wrapper):
    method __init__ (line 7) | def __init__(self, env):
    method reset (line 13) | def reset(self, **kwargs):
  class EpisodicLifeEnv (line 24) | class EpisodicLifeEnv(Wrapper):
    method __init__ (line 25) | def __init__(self, env):
    method step (line 33) | def step(self, action):
    method reset (line 47) | def reset(self, **kwargs):

FILE: week04_approx_rl/dqn/logger.py
  class Logger (line 5) | class Logger:
    method __init__ (line 6) | def __init__(self, use_tensorboard=True, log_dir='runs'):
    method log_loss (line 23) | def log_loss(self, loss, step):
    method log_grad_norm (line 29) | def log_grad_norm(self, grad_norm, step):
    method log_mean_reward (line 35) | def log_mean_reward(self, mean_reward, step):
    method log_initial_state_v (line 41) | def log_initial_state_v(self, initial_v, step):
    method plot (line 47) | def plot(self):
    method close (line 78) | def close(self):

FILE: week04_approx_rl/dqn/replay_buffer.py
  class ReplayBuffer (line 7) | class ReplayBuffer(object):
    method __init__ (line 8) | def __init__(self, size):
    method __len__ (line 20) | def __len__(self):
    method add (line 23) | def add(self, obs_t, action, reward, obs_tp1, done):
    method _encode_sample (line 32) | def _encode_sample(self, idxes):
    method sample (line 50) | def sample(self, batch_size):
  class LazyFramesVectorReplayBuffer (line 74) | class LazyFramesVectorReplayBuffer(ReplayBuffer):
    method _encode_sample (line 94) | def _encode_sample(self, idxes):

FILE: week04_approx_rl/dqn/utils.py
  function is_enough_ram (line 4) | def is_enough_ram(min_available_gb=0.1):
  function linear_decay (line 9) | def linear_decay(

FILE: week04_approx_rl/test_td_loss/compute_td_loss.py
  class ComputeTdLossProtocol (line 6) | class ComputeTdLossProtocol(Protocol):
    method __call__ (line 11) | def __call__(
  class MockAgent (line 25) | class MockAgent(nn.Module):
    method __init__ (line 31) | def __init__(self, output_q_values: torch.Tensor):
    method forward (line 37) | def forward(self, state):
  function test_is_done_is_used (line 42) | def test_is_done_is_used(compute_td_loss: ComputeTdLossProtocol):
  function test_compute_td_loss_vanilla (line 81) | def test_compute_td_loss_vanilla(compute_td_loss: ComputeTdLossProtocol):
  function test_compute_td_loss_double (line 145) | def test_compute_td_loss_double(compute_td_loss: ComputeTdLossProtocol):

FILE: week05_explore/q_learning_agent.py
  class QLearningAgent (line 7) | class QLearningAgent:
    method __init__ (line 8) | def __init__(self, alpha, epsilon, discount, get_legal_actions):
    method get_qvalue (line 35) | def get_qvalue(self, state, action):
    method set_qvalue (line 39) | def set_qvalue(self, state, action, value):
    method get_value (line 43) | def get_value(self, state):
    method update (line 58) | def update(self, state, action, reward, next_state, done):
    method get_best_action (line 73) | def get_best_action(self, state):
    method get_action (line 87) | def get_action(self, state):

FILE: week05_explore/replay_buffer.py
  class ReplayBuffer (line 7) | class ReplayBuffer(object):
    method __init__ (line 8) | def __init__(self, size):
    method __len__ (line 20) | def __len__(self):
    method add (line 23) | def add(self, obs_t, action, reward, obs_tp1, done):
    method _encode_sample (line 32) | def _encode_sample(self, idxes):
    method sample (line 50) | def sample(self, batch_size):

FILE: week06_policy_based/atari_wrappers.py
  class EpisodicLife (line 18) | class EpisodicLife(Wrapper):
    method __init__ (line 21) | def __init__(self, env):
    method step (line 26) | def step(self, action):
    method reset (line 36) | def reset(self, **kwargs):
  class FireReset (line 47) | class FireReset(Wrapper):
    method __init__ (line 54) | def __init__(self, env):
    method step (line 68) | def step(self, action):
    method reset (line 71) | def reset(self, **kwargs):
  class StartWithRandomActions (line 82) | class StartWithRandomActions(Wrapper):
    method __init__ (line 86) | def __init__(self, env, max_random_actions=30):
    method step (line 91) | def step(self, action):
    method reset (line 96) | def reset(self, **kwargs):
  class ImagePreprocessing (line 108) | class ImagePreprocessing(ObservationWrapper):
    method __init__ (line 111) | def __init__(self, env, height=84, width=84, grayscale=True):
    method observation (line 133) | def observation(self, observation):
  class MaxBetweenFrames (line 141) | class MaxBetweenFrames(ObservationWrapper):
    method __init__ (line 144) | def __init__(self, env):
    method observation (line 150) | def observation(self, observation):
    method reset (line 155) | def reset(self, **kwargs):
  class QueueFrames (line 160) | class QueueFrames(ObservationWrapper):
    method __init__ (line 163) | def __init__(self, env, nframes, concat=False):
    method observation (line 176) | def observation(self, observation):
    method reset (line 184) | def reset(self, **kwargs):
  class SkipFrames (line 191) | class SkipFrames(Wrapper):
    method __init__ (line 194) | def __init__(self, env, nskip=4):
    method step (line 200) | def step(self, action):
    method reset (line 209) | def reset(self, **kwargs):
  class ClipReward (line 213) | class ClipReward(RewardWrapper):
    method reward (line 216) | def reward(self, reward):
  class SwapImageAxes (line 220) | class SwapImageAxes(ObservationWrapper):
    method __init__ (line 225) | def __init__(self, env):
    method observation (line 235) | def observation(self, observation):
  class SummariesBase (line 239) | class SummariesBase(Wrapper):
    method __init__ (line 242) | def __init__(self, env, prefix=None, running_mean_size=100, step_var=N...
    method should_write_summaries (line 256) | def should_write_summaries(self):
    method add_summaries (line 260) | def add_summaries(self):
    method step (line 282) | def step(self, action):
    method reset (line 310) | def reset(self, **kwargs):
  class TensorboardSummaries (line 317) | class TensorboardSummaries(SummariesBase):
    method __init__ (line 320) | def __init__(self, env, prefix=None, running_mean_size=100, step_var=N...
    method add_summary (line 324) | def add_summary(self, name, value):
  class NumpySummaries (line 331) | class NumpySummaries(SummariesBase):
    method get_values (line 336) | def get_values(cls, name):
    method clear (line 340) | def clear(cls):
    method __init__ (line 343) | def __init__(self, env, prefix=None, running_mean_size=100, step_var=N...
    method add_summary (line 346) | def add_summary(self, name, value):
  function get_summaries_class (line 350) | def get_summaries_class(summaries):
  class _thunk (line 364) | class _thunk:
    method __init__ (line 365) | def __init__(self, i, env_id, **kwargs):
    method __call__ (line 370) | def __call__(self):
  function nature_dqn_env (line 379) | def nature_dqn_env(env_id, nenvs=None, seed=None, summaries="Numpy", cli...

FILE: week06_policy_based/env_batch.py
  class SpaceBatch (line 9) | class SpaceBatch(Space):
    method __init__ (line 10) | def __init__(self, spaces):
    method sample (line 37) | def sample(self):
    method __getattr__ (line 40) | def __getattr__(self, attr):
  class EnvBatch (line 44) | class EnvBatch(Env):
    method __init__ (line 45) | def __init__(self, make_env, nenvs=None):
    method _get_make_env_functions (line 53) | def _get_make_env_functions(self, make_env, nenvs):
    method nenvs (line 66) | def nenvs(self):
    method envs (line 70) | def envs(self):
    method _check_actions (line 73) | def _check_actions(self, actions):
    method step (line 80) | def step(self, actions):
    method reset (line 100) | def reset(self, **kwargs):
  class SingleEnvBatch (line 109) | class SingleEnvBatch(Wrapper, EnvBatch):
    method __init__ (line 110) | def __init__(self, env):
    method nenvs (line 116) | def nenvs(self):
    method envs (line 120) | def envs(self):
    method step (line 123) | def step(self, actions):
    method reset (line 136) | def reset(self, **kwargs):
  function worker (line 141) | def worker(parent_connection, worker_connection, make_env_function, send...
  class ParallelEnvBatch (line 165) | class ParallelEnvBatch(EnvBatch):
    method __init__ (line 170) | def __init__(self, make_env, nenvs=None, seeds=None):
    method nenvs (line 207) | def nenvs(self):
    method step (line 210) | def step(self, actions):
    method reset (line 224) | def reset(self, **kwargs):
    method close (line 233) | def close(self):
    method render (line 242) | def render(self):

FILE: week06_policy_based/runners.py
  class EnvRunner (line 6) | class EnvRunner:
    method __init__ (line 9) | def __init__(self, env, policy, nsteps, transforms=None, step_var=None):
    method nenvs (line 18) | def nenvs(self):
    method reset (line 22) | def reset(self, **kwargs):
    method add_summary (line 27) | def add_summary(self, name, val):
    method get_next (line 32) | def get_next(self):

FILE: week07_seq2seq/basic_model_tf.py
  class BasicTranslationModel (line 14) | class BasicTranslationModel:
    method __init__ (line 15) | def __init__(self, name, inp_voc, out_voc,
    method encode (line 41) | def encode(self, inp, **flags):
    method decode (line 58) | def decode(self, prev_state, prev_tokens, **flags):
    method symbolic_score (line 76) | def symbolic_score(self, inp, out, eps=1e-30, **flags):
    method symbolic_translate (line 113) | def symbolic_translate(
  function initialize_uninitialized (line 178) | def initialize_uninitialized(sess=None):
  function infer_length (line 198) | def infer_length(seq, eos_ix, time_major=False, dtype=tf.int32):
  function infer_mask (line 212) | def infer_mask(seq, eos_ix, time_major=False, dtype=tf.float32):
  function select_values_over_last_axis (line 227) | def select_values_over_last_axis(values, indices):

FILE: week07_seq2seq/basic_model_torch.py
  class BasicTranslationModel (line 10) | class BasicTranslationModel(nn.Module):
    method __init__ (line 11) | def __init__(self, inp_voc, out_voc,
    method encode (line 24) | def encode(self, inp, **flags):
    method decode (line 41) | def decode(self, prev_state, prev_tokens, **flags):
    method forward (line 56) | def forward(self, inp, out, eps=1e-30, **flags):
    method translate (line 84) | def translate(self, inp, greedy=False, max_len=None, eps=1e-30, **flags):
  function infer_mask (line 132) | def infer_mask(
  function infer_length (line 157) | def infer_length(
  function to_one_hot (line 174) | def to_one_hot(y, n_dims=None):

FILE: week07_seq2seq/voc.py
  class Vocab (line 4) | class Vocab:
    method __init__ (line 5) | def __init__(self, tokens, bos="__BOS__", eos="__EOS__", sep=''):
    method __len__ (line 19) | def __len__(self):
    method from_lines (line 23) | def from_lines(lines, bos="__BOS__", eos="__EOS__", sep=''):
    method tokenize (line 31) | def tokenize(self, string):
    method to_matrix (line 37) | def to_matrix(self, lines, max_len=None):
    method to_lines (line 56) | def to_lines(self, matrix, crop=True):

FILE: week08_pomdp/atari_util.py
  class PreprocessAtari (line 7) | class PreprocessAtari(Wrapper):
    method __init__ (line 8) | def __init__(self, env, height=42, width=42, color=False,
    method reset (line 28) | def reset(self, **kwargs):
    method step (line 35) | def step(self, action):
    method update_buffer (line 44) | def update_buffer(self, img):
    method preproc_image (line 55) | def preproc_image(self, img):

FILE: week08_pomdp/env_pool.py
  class EnvPool (line 11) | class EnvPool(object):
    method __init__ (line 12) | def __init__(self, agent, make_env, n_parallel_games=1):
    method interact (line 37) | def interact(self, n_steps=100, verbose=False):

FILE: week09_policy_II/mujoco_wrappers.py
  class RunningMeanVar (line 7) | class RunningMeanVar:
    method __init__ (line 17) | def __init__(self, eps=1e-4, shape=()):
    method update (line 22) | def update(self, batch):
    method update_from_moments (line 32) | def update_from_moments(self, batch_mean, batch_var, batch_count):
  function update_mean_var_count_from_moments (line 38) | def update_mean_var_count_from_moments(mean, var, count,
  class Normalize (line 54) | class Normalize(gym.Wrapper):
    method __init__ (line 61) | def __init__(self, env, obs=True, ret=True,
    method observation (line 73) | def observation(self, obs):
    method step (line 85) | def step(self, action):
    method reset (line 96) | def reset(self, **kwargs):

FILE: week09_policy_II/td3_and_sac/logger.py
  class TensorboardSummaries (line 8) | class TensorboardSummaries(gym.Wrapper):
    method __init__ (line 11) | def __init__(self, env, prefix=None, running_mean_size=100, step_var=N...
    method should_write_summaries (line 26) | def should_write_summaries(self):
    method add_summaries (line 30) | def add_summaries(self):
    method step (line 59) | def step(self, action):
    method reset (line 87) | def reset(self, **kwargs):