SYMBOL INDEX (100 symbols across 13 files)

FILE: A3C_sparse.py
  class A3C (line 23) | class A3C:
    method __init__ (line 26) | def __init__(self):
    method _build_actor (line 39) | def _build_actor(self):
    method _build_critic (line 51) | def _build_critic(self):
    method _build_model (line 63) | def _build_model(self):
    method _build_optimizer (line 73) | def _build_optimizer(self):
    method train (line 104) | def train(self, episode, n_thread, update_iter):
    method load (line 126) | def load(self):
    method save (line 133) | def save(self):
  class Agent (line 140) | class Agent(threading.Thread):
    method __init__ (line 143) | def __init__(self, index, actor, critic, optimizer, gamma, episode, up...
    method run (line 156) | def run(self):
    method discount_reward (line 203) | def discount_reward(self, rewards, next_state, done):
    method train_episode (line 228) | def train_episode(self, states, actions, rewards, next_observation, do...
  function save_history (line 247) | def save_history(history, name):
  function play (line 256) | def play(model):

FILE: AC_continue.py
  class AC (line 14) | class AC(DRL):
    method __init__ (line 18) | def __init__(self):
    method _build_actor (line 33) | def _build_actor(self):
    method _build_critic (line 52) | def _build_critic(self):
    method _actor_loss (line 64) | def _actor_loss(self, y_true, y_pred):
    method discount_reward (line 90) | def discount_reward(self, next_states, reward):
    method choice_action (line 103) | def choice_action(self, x):
    method train (line 120) | def train(self, episode):
    method play (line 184) | def play(self):

FILE: AC_sparse.py
  class AC (line 14) | class AC(DRL):
    method __init__ (line 17) | def __init__(self):
    method load (line 25) | def load(self):
    method _build_actor (line 30) | def _build_actor(self):
    method _build_critic (line 42) | def _build_critic(self):
    method _actor_loss (line 54) | def _actor_loss(self, y_true, y_pred):
    method discount_reward (line 73) | def discount_reward(self, next_states, reward, done):
    method train (line 89) | def train(self, episode):

FILE: DDPG.py
  class DDPG (line 18) | class DDPG(DRL):
    method __init__ (line 21) | def __init__(self):
    method load (line 61) | def load(self):
    method _build_actor (line 66) | def _build_actor(self):
    method _build_critic (line 80) | def _build_critic(self):
    method actor_optimizer (line 96) | def actor_optimizer(self):
    method critic_gradient (line 114) | def critic_gradient(self):
    method OU (line 128) | def OU(self, x, mu=0, theta=0.15, sigma=0.2):
    method get_action (line 143) | def get_action(self, X):
    method remember (line 157) | def remember(self, state, action, reward, next_state, done):
    method update_epsilon (line 170) | def update_epsilon(self):
    method process_batch (line 176) | def process_batch(self, batch):
    method update_model (line 207) | def update_model(self, X1, X2, y):
    method update_target_model (line 231) | def update_target_model(self):
    method train (line 249) | def train(self, episode, batch):
    method play (line 300) | def play(self):

FILE: DQN.py
  class DQN (line 15) | class DQN(DRL):
    method __init__ (line 18) | def __init__(self):
    method load (line 34) | def load(self):
    method build_model (line 38) | def build_model(self):
    method egreedy_action (line 52) | def egreedy_action(self, state):
    method remember (line 66) | def remember(self, state, action, reward, next_state, done):
    method update_epsilon (line 78) | def update_epsilon(self):
    method process_batch (line 84) | def process_batch(self, batch):
    method train (line 111) | def train(self, episode, batch):

FILE: DRL.py
  class DRL (line 9) | class DRL:
    method __init__ (line 10) | def __init__(self):
    method play (line 19) | def play(self, m='pg'):
    method plot (line 52) | def plot(self, history):
    method save_history (line 69) | def save_history(self, history, name):

FILE: DoubleDQN.py
  class DDQN (line 9) | class DDQN(DQN):
    method __init__ (line 12) | def __init__(self):
    method load (line 19) | def load(self):
    method update_target_model (line 23) | def update_target_model(self):
    method process_batch (line 28) | def process_batch(self, batch):
    method train (line 55) | def train(self, episode, batch):

FILE: DuelingDQN.py
  class DuelingDQN (line 13) | class DuelingDQN(NDQN):
    method __init__ (line 16) | def __init__(self):
    method load (line 19) | def load(self):
    method build_model (line 23) | def build_model(self):
    method train (line 43) | def train(self, episode, batch):

FILE: NatureDQN.py
  class NDQN (line 9) | class NDQN(DQN):
    method __init__ (line 12) | def __init__(self):
    method load (line 19) | def load(self):
    method update_target_model (line 23) | def update_target_model(self):
    method process_batch (line 28) | def process_batch(self, batch):
    method train (line 54) | def train(self, episode, batch):

FILE: PPO_TF.py
  class PPO (line 8) | class PPO:
    method __init__ (line 9) | def __init__(self, ep, batch, t='ppo2'):
    method _build_critic (line 33) | def _build_critic(self):
    method _build_actor (line 42) | def _build_actor(self, name, trainable):
    method build_model (line 57) | def build_model(self):
    method choose_action (line 107) | def choose_action(self, state):
    method get_value (line 121) | def get_value(self, state):
    method discount_reward (line 134) | def discount_reward(self, states, rewards, next_observation):
    method update (line 161) | def update(self, states, action, dr):
    method train (line 204) | def train(self):
    method save_history (line 249) | def save_history(self, history, name):

FILE: PolicyNetwork.py
  class PolicyNetwork (line 14) | class PolicyNetwork(DRL):
    method __init__ (line 17) | def __init__(self):
    method load (line 23) | def load(self):
    method _build_model (line 27) | def _build_model(self):
    method loss (line 39) | def loss(self, y_true, y_pred):
    method discount_reward (line 57) | def discount_reward(self, rewards):
    method train (line 75) | def train(self, episode, batch):

FILE: game/CartPole.py
  function try_gym (line 6) | def try_gym():

FILE: game/Pendulum.py
  function try_gym (line 5) | def try_gym():