SYMBOL INDEX (409 symbols across 51 files)

FILE: contents/10_A3C/A3C_RNN.py
  class ACNet (line 44) | class ACNet(object):
    method __init__ (line 45) | def __init__(self, scope, globalAC=None):
    method _build_net (line 89) | def _build_net(self, scope):
    method update_global (line 111) | def update_global(self, feed_dict):  # run by a local
    method pull_global (line 114) | def pull_global(self):  # run by a local
    method choose_action (line 117) | def choose_action(self, s, cell_state):  # run by a local
  class Worker (line 123) | class Worker(object):
    method __init__ (line 124) | def __init__(self, name, globalAC):
    method work (line 129) | def work(self):

FILE: contents/10_A3C/A3C_continuous_action.py
  class ACNet (line 44) | class ACNet(object):
    method __init__ (line 45) | def __init__(self, scope, globalAC=None):
    method _build_net (line 89) | def _build_net(self, scope):
    method update_global (line 102) | def update_global(self, feed_dict):  # run by a local
    method pull_global (line 105) | def pull_global(self):  # run by a local
    method choose_action (line 108) | def choose_action(self, s):  # run by a local
  class Worker (line 113) | class Worker(object):
    method __init__ (line 114) | def __init__(self, name, globalAC):
    method work (line 119) | def work(self):

FILE: contents/10_A3C/A3C_discrete_action.py
  class ACNet (line 42) | class ACNet(object):
    method __init__ (line 43) | def __init__(self, scope, globalAC=None):
    method _build_net (line 81) | def _build_net(self, scope):
    method update_global (line 93) | def update_global(self, feed_dict):  # run by a local
    method pull_global (line 96) | def pull_global(self):  # run by a local
    method choose_action (line 99) | def choose_action(self, s):  # run by a local
  class Worker (line 106) | class Worker(object):
    method __init__ (line 107) | def __init__(self, name, globalAC):
    method work (line 112) | def work(self):

FILE: contents/10_A3C/A3C_distributed_tf.py
  class ACNet (line 28) | class ACNet(object):
    method __init__ (line 31) | def __init__(self, scope, opt_a=None, opt_c=None, global_net=None):
    method _build_net (line 71) | def _build_net(self, scope):
    method choose_action (line 83) | def choose_action(self, s):  # run by a local
    method update_global (line 89) | def update_global(self, feed_dict):  # run by a local
    method pull_global (line 92) | def pull_global(self):  # run by a local
  function work (line 96) | def work(job_name, task_index, global_ep, lock, r_queue, global_running_r):

FILE: contents/11_Dyna_Q/RL_brain.py
  class QLearningTable (line 12) | class QLearningTable:
    method __init__ (line 13) | def __init__(self, actions, learning_rate=0.01, reward_decay=0.9, e_gr...
    method choose_action (line 22) | def choose_action(self, observation):
    method learn (line 40) | def learn(self, s, a, r, s_):
    method check_state_exist (line 50) | def check_state_exist(self, state):
  class EnvModel (line 62) | class EnvModel:
    method __init__ (line 65) | def __init__(self, actions):
    method store_transition (line 70) | def store_transition(self, s, a, r, s_):
    method sample_s_a (line 80) | def sample_s_a(self):
    method get_r_s_ (line 85) | def get_r_s_(self, s, a):

FILE: contents/11_Dyna_Q/maze_env.py
  class Maze (line 26) | class Maze(tk.Tk, object):
    method __init__ (line 27) | def __init__(self):
    method _build_maze (line 35) | def _build_maze(self):
    method reset (line 80) | def reset(self):
    method step (line 92) | def step(self, action):
    method render (line 125) | def render(self):

FILE: contents/11_Dyna_Q/run_this.py
  function update (line 19) | def update():

FILE: contents/12_Proximal_Policy_Optimization/DPPO.py
  class PPO (line 35) | class PPO(object):
    method __init__ (line 36) | def __init__(self):
    method update (line 67) | def update(self):
    method _build_anet (line 84) | def _build_anet(self, name, trainable):
    method choose_action (line 93) | def choose_action(self, s):
    method get_v (line 98) | def get_v(self, s):
  class Worker (line 103) | class Worker(object):
    method __init__ (line 104) | def __init__(self, wid):
    method work (line 109) | def work(self):

FILE: contents/12_Proximal_Policy_Optimization/discrete_DPPO.py
  class PPONet (line 38) | class PPONet(object):
    method __init__ (line 39) | def __init__(self):
    method update (line 74) | def update(self):
    method _build_anet (line 91) | def _build_anet(self, name, trainable):
    method choose_action (line 98) | def choose_action(self, s):  # run by a local
    method get_v (line 104) | def get_v(self, s):
  class Worker (line 109) | class Worker(object):
    method __init__ (line 110) | def __init__(self, wid):
    method work (line 115) | def work(self):

FILE: contents/12_Proximal_Policy_Optimization/simply_PPO.py
  class PPO (line 35) | class PPO(object):
    method __init__ (line 37) | def __init__(self):
    method update (line 82) | def update(self, s, a, r):
    method _build_anet (line 106) | def _build_anet(self, name, trainable):
    method choose_action (line 115) | def choose_action(self, s):
    method get_v (line 120) | def get_v(self, s):

FILE: contents/1_command_line_reinforcement_learning/treasure_on_right.py
  function build_q_table (line 25) | def build_q_table(n_states, actions):
  function choose_action (line 34) | def choose_action(state, q_table):
  function get_env_feedback (line 44) | def get_env_feedback(S, A):
  function update_env (line 62) | def update_env(S, episode, step_counter):
  function rl (line 77) | def rl():

FILE: contents/2_Q_Learning_maze/RL_brain.py
  class QLearningTable (line 12) | class QLearningTable:
    method __init__ (line 13) | def __init__(self, actions, learning_rate=0.01, reward_decay=0.9, e_gr...
    method choose_action (line 20) | def choose_action(self, observation):
    method learn (line 33) | def learn(self, s, a, r, s_):
    method check_state_exist (line 42) | def check_state_exist(self, state):

FILE: contents/2_Q_Learning_maze/maze_env.py
  class Maze (line 29) | class Maze(tk.Tk, object):
    method __init__ (line 30) | def __init__(self):
    method _build_maze (line 38) | def _build_maze(self):
    method reset (line 83) | def reset(self):
    method step (line 95) | def step(self, action):
    method render (line 130) | def render(self):
  function update (line 135) | def update():

FILE: contents/2_Q_Learning_maze/run_this.py
  function update (line 19) | def update():

FILE: contents/3_Sarsa_maze/RL_brain.py
  class RL (line 12) | class RL(object):
    method __init__ (line 13) | def __init__(self, action_space, learning_rate=0.01, reward_decay=0.9,...
    method check_state_exist (line 21) | def check_state_exist(self, state):
    method choose_action (line 32) | def choose_action(self, observation):
    method learn (line 45) | def learn(self, *args):
  class QLearningTable (line 50) | class QLearningTable(RL):
    method __init__ (line 51) | def __init__(self, actions, learning_rate=0.01, reward_decay=0.9, e_gr...
    method learn (line 54) | def learn(self, s, a, r, s_):
  class SarsaTable (line 65) | class SarsaTable(RL):
    method __init__ (line 67) | def __init__(self, actions, learning_rate=0.01, reward_decay=0.9, e_gr...
    method learn (line 70) | def learn(self, s, a, r, s_, a_):

FILE: contents/3_Sarsa_maze/maze_env.py
  class Maze (line 30) | class Maze(tk.Tk, object):
    method __init__ (line 31) | def __init__(self):
    method _build_maze (line 39) | def _build_maze(self):
    method reset (line 84) | def reset(self):
    method step (line 96) | def step(self, action):
    method render (line 131) | def render(self):

FILE: contents/3_Sarsa_maze/run_this.py
  function update (line 14) | def update():

FILE: contents/4_Sarsa_lambda_maze/RL_brain.py
  class RL (line 12) | class RL(object):
    method __init__ (line 13) | def __init__(self, action_space, learning_rate=0.01, reward_decay=0.9,...
    method check_state_exist (line 21) | def check_state_exist(self, state):
    method choose_action (line 32) | def choose_action(self, observation):
    method learn (line 45) | def learn(self, *args):
  class SarsaLambdaTable (line 50) | class SarsaLambdaTable(RL):
    method __init__ (line 51) | def __init__(self, actions, learning_rate=0.01, reward_decay=0.9, e_gr...
    method check_state_exist (line 58) | def check_state_exist(self, state):
    method learn (line 71) | def learn(self, s, a, r, s_, a_):

FILE: contents/4_Sarsa_lambda_maze/maze_env.py
  class Maze (line 30) | class Maze(tk.Tk, object):
    method __init__ (line 31) | def __init__(self):
    method _build_maze (line 39) | def _build_maze(self):
    method reset (line 84) | def reset(self):
    method step (line 96) | def step(self, action):
    method render (line 131) | def render(self):

FILE: contents/4_Sarsa_lambda_maze/run_this.py
  function update (line 14) | def update():

FILE: contents/5.1_Double_DQN/RL_brain.py
  class DoubleDQN (line 18) | class DoubleDQN:
    method __init__ (line 19) | def __init__(
    method _build_net (line 63) | def _build_net(self):
    method store_transition (line 98) | def store_transition(self, s, a, r, s_):
    method choose_action (line 106) | def choose_action(self, observation):
    method learn (line 121) | def learn(self):

FILE: contents/5.1_Double_DQN/run_Pendulum.py
  function train (line 41) | def train(RL):

FILE: contents/5.2_Prioritized_Replay_DQN/RL_brain.py
  class SumTree (line 18) | class SumTree(object):
    method __init__ (line 27) | def __init__(self, capacity):
    method add (line 36) | def add(self, p, data):
    method update (line 45) | def update(self, tree_idx, p):
    method get_leaf (line 53) | def get_leaf(self, v):
    method total_p (line 85) | def total_p(self):
  class Memory (line 89) | class Memory(object):  # stored as ( s, a, r, s_ ) in SumTree
    method __init__ (line 100) | def __init__(self, capacity):
    method store (line 103) | def store(self, transition):
    method sample (line 109) | def sample(self, n):
    method batch_update (line 124) | def batch_update(self, tree_idx, abs_errors):
  class DQNPrioritizedReplay (line 132) | class DQNPrioritizedReplay:
    method __init__ (line 133) | def __init__(
    method _build_net (line 184) | def _build_net(self):
    method store_transition (line 224) | def store_transition(self, s, a, r, s_):
    method choose_action (line 236) | def choose_action(self, observation):
    method learn (line 245) | def learn(self):

FILE: contents/5.2_Prioritized_Replay_DQN/run_MountainCar.py
  function train (line 38) | def train(RL):

FILE: contents/5.3_Dueling_DQN/RL_brain.py
  class DuelingDQN (line 18) | class DuelingDQN:
    method __init__ (line 19) | def __init__(
    method _build_net (line 63) | def _build_net(self):
    method store_transition (line 114) | def store_transition(self, s, a, r, s_):
    method choose_action (line 122) | def choose_action(self, observation):
    method learn (line 131) | def learn(self):

FILE: contents/5.3_Dueling_DQN/run_Pendulum.py
  function train (line 39) | def train(RL):

FILE: contents/5_Deep_Q_Network/DQN_modified.py
  class DeepQNetwork (line 20) | class DeepQNetwork:
    method __init__ (line 21) | def __init__(
    method _build_net (line 69) | def _build_net(self):
    method store_transition (line 103) | def store_transition(self, s, a, r, s_):
    method choose_action (line 112) | def choose_action(self, observation):
    method learn (line 124) | def learn(self):
    method plot_cost (line 152) | def plot_cost(self):

FILE: contents/5_Deep_Q_Network/RL_brain.py
  class DeepQNetwork (line 22) | class DeepQNetwork:
    method __init__ (line 23) | def __init__(
    method _build_net (line 69) | def _build_net(self):
    method store_transition (line 114) | def store_transition(self, s, a, r, s_):
    method choose_action (line 126) | def choose_action(self, observation):
    method learn (line 138) | def learn(self):
    method plot_cost (line 203) | def plot_cost(self):

FILE: contents/5_Deep_Q_Network/maze_env.py
  class Maze (line 27) | class Maze(tk.Tk, object):
    method __init__ (line 28) | def __init__(self):
    method _build_maze (line 37) | def _build_maze(self):
    method reset (line 82) | def reset(self):
    method step (line 94) | def step(self, action):
    method render (line 127) | def render(self):

FILE: contents/5_Deep_Q_Network/run_this.py
  function run_maze (line 5) | def run_maze():

FILE: contents/6_OpenAI_gym/RL_brain.py
  class DeepQNetwork (line 19) | class DeepQNetwork:
    method __init__ (line 20) | def __init__(
    method _build_net (line 66) | def _build_net(self):
    method store_transition (line 111) | def store_transition(self, s, a, r, s_):
    method choose_action (line 123) | def choose_action(self, observation):
    method learn (line 135) | def learn(self):
    method plot_cost (line 200) | def plot_cost(self):

FILE: contents/7_Policy_gradient_softmax/RL_brain.py
  class PolicyGradient (line 22) | class PolicyGradient:
    method __init__ (line 23) | def __init__(
    method _build_net (line 50) | def _build_net(self):
    method choose_action (line 86) | def choose_action(self, observation):
    method store_transition (line 91) | def store_transition(self, s, a, r):
    method learn (line 96) | def learn(self):
    method _discount_and_norm_rewards (line 110) | def _discount_and_norm_rewards(self):

FILE: contents/8_Actor_Critic_Advantage/AC_CartPole.py
  class Actor (line 38) | class Actor(object):
    method __init__ (line 39) | def __init__(self, sess, n_features, n_actions, lr=0.001):
    method learn (line 72) | def learn(self, s, a, td):
    method choose_action (line 78) | def choose_action(self, s):
  class Critic (line 84) | class Critic(object):
    method __init__ (line 85) | def __init__(self, sess, n_features, lr=0.01):
    method learn (line 119) | def learn(self, s, r, s_):

FILE: contents/8_Actor_Critic_Advantage/AC_continue_Pendulum.py
  class Actor (line 23) | class Actor(object):
    method __init__ (line 24) | def __init__(self, sess, n_features, action_bound, lr=0.0001):
    method learn (line 73) | def learn(self, s, a, td):
    method choose_action (line 79) | def choose_action(self, s):
  class Critic (line 84) | class Critic(object):
    method __init__ (line 85) | def __init__(self, sess, n_features, lr=0.01):
    method learn (line 117) | def learn(self, s, r, s_):

FILE: contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG.py
  class Actor (line 43) | class Actor(object):
    method __init__ (line 44) | def __init__(self, sess, action_dim, action_bound, learning_rate, repl...
    method _build_net (line 69) | def _build_net(self, s, scope, trainable):
    method learn (line 82) | def learn(self, s):   # batch update
    method choose_action (line 92) | def choose_action(self, s):
    method add_grad_to_graph (line 96) | def add_grad_to_graph(self, a_grads):
  class Critic (line 111) | class Critic(object):
    method __init__ (line 112) | def __init__(self, sess, state_dim, action_dim, learning_rate, gamma, ...
    method _build_net (line 150) | def _build_net(self, s, a, scope, trainable):
    method learn (line 166) | def learn(self, s, a, r, s_):
  class Memory (line 178) | class Memory(object):
    method __init__ (line 179) | def __init__(self, capacity, dims):
    method store_transition (line 184) | def store_transition(self, s, a, r, s_):
    method sample (line 190) | def sample(self, n):

FILE: contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG_update.py
  class DDPG (line 35) | class DDPG(object):
    method __init__ (line 36) | def __init__(self, a_dim, s_dim, a_bound,):
    method choose_action (line 75) | def choose_action(self, s):
    method learn (line 78) | def learn(self):
    method store_transition (line 92) | def store_transition(self, s, a, r, s_):
    method _build_a (line 98) | def _build_a(self, s, scope, trainable):
    method _build_c (line 104) | def _build_c(self, s, a, scope, trainable):

FILE: contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG_update2.py
  class DDPG (line 41) | class DDPG(object):
    method __init__ (line 42) | def __init__(self, a_dim, s_dim, a_bound,):
    method choose_action (line 75) | def choose_action(self, s):
    method learn (line 78) | def learn(self):
    method store_transition (line 89) | def store_transition(self, s, a, r, s_):
    method _build_a (line 95) | def _build_a(self, s, reuse=None, custom_getter=None):
    method _build_c (line 102) | def _build_c(self, s, a, reuse=None, custom_getter=None):

FILE: contents/Curiosity_Model/Curiosity.py
  class CuriosityNet (line 9) | class CuriosityNet:
    method __init__ (line 10) | def __init__(
    method _build_nets (line 53) | def _build_nets(self):
    method _build_dynamics_net (line 67) | def _build_dynamics_net(self, s, a, s_):
    method _build_dqn (line 82) | def _build_dqn(self, s, a, r, s_):
    method store_transition (line 102) | def store_transition(self, s, a, r, s_):
    method choose_action (line 109) | def choose_action(self, observation):
    method learn (line 121) | def learn(self):

FILE: contents/Curiosity_Model/Random_Network_Distillation.py
  class CuriosityNet (line 9) | class CuriosityNet:
    method __init__ (line 10) | def __init__(
    method _build_nets (line 54) | def _build_nets(self):
    method _build_predictor (line 71) | def _build_predictor(self, s_, rand_encode_s_):
    method _build_dqn (line 83) | def _build_dqn(self, s, a, ri, re, s_):
    method store_transition (line 103) | def store_transition(self, s, a, r, s_):
    method choose_action (line 110) | def choose_action(self, observation):
    method learn (line 122) | def learn(self):

FILE: experiments/2D_car/DDPG.py
  class Actor (line 58) | class Actor(object):
    method __init__ (line 59) | def __init__(self, sess, action_dim, action_bound, learning_rate, t_re...
    method _build_net (line 77) | def _build_net(self, s, scope, trainable):
    method learn (line 93) | def learn(self, s):   # batch update
    method choose_action (line 99) | def choose_action(self, s):
    method add_grad_to_graph (line 103) | def add_grad_to_graph(self, a_grads):
  class Critic (line 112) | class Critic(object):
    method __init__ (line 113) | def __init__(self, sess, state_dim, action_dim, learning_rate, gamma, ...
    method _build_net (line 145) | def _build_net(self, s, a, scope, trainable):
    method learn (line 163) | def learn(self, s, a, r, s_):
  class Memory (line 170) | class Memory(object):
    method __init__ (line 171) | def __init__(self, capacity, dims):
    method store_transition (line 176) | def store_transition(self, s, a, r, s_):
    method sample (line 182) | def sample(self, n):
  function train (line 206) | def train():
  function eval (line 252) | def eval():

FILE: experiments/2D_car/car_env.py
  class CarEnv (line 19) | class CarEnv(object):
    method __init__ (line 30) | def __init__(self, discrete_action=False):
    method step (line 48) | def step(self, action):
    method reset (line 62) | def reset(self):
    method render (line 68) | def render(self):
    method sample_action (line 73) | def sample_action(self):
    method set_fps (line 80) | def set_fps(self, fps=30):
    method _get_state (line 83) | def _get_state(self):
    method _update_sensor (line 87) | def _update_sensor(self):
  class Viewer (line 150) | class Viewer(pyglet.window.Window):
    method __init__ (line 157) | def __init__(self, width, height, car_info, sensor_info, obstacle_coor...
    method render (line 182) | def render(self):
    method on_draw (line 190) | def on_draw(self):
    method _update (line 195) | def _update(self):

FILE: experiments/2D_car/collision.py
  function intersection (line 3) | def intersection():
  function point2segment (line 31) | def point2segment():

FILE: experiments/Robot_arm/A3C.py
  class ACNet (line 53) | class ACNet(object):
    method __init__ (line 54) | def __init__(self, scope, globalAC=None):
    method _build_net (line 103) | def _build_net(self):
    method update_global (line 116) | def update_global(self, feed_dict):  # run by a local
    method pull_global (line 120) | def pull_global(self):  # run by a local
    method choose_action (line 123) | def choose_action(self, s):  # run by a local
  class Worker (line 128) | class Worker(object):
    method __init__ (line 129) | def __init__(self, name, globalAC):
    method work (line 134) | def work(self):

FILE: experiments/Robot_arm/DDPG.py
  class Actor (line 59) | class Actor(object):
    method __init__ (line 60) | def __init__(self, sess, action_dim, action_bound, learning_rate, t_re...
    method _build_net (line 79) | def _build_net(self, s, scope, trainable):
    method learn (line 98) | def learn(self, s):   # batch update
    method choose_action (line 104) | def choose_action(self, s):
    method add_grad_to_graph (line 108) | def add_grad_to_graph(self, a_grads):
  class Critic (line 117) | class Critic(object):
    method __init__ (line 118) | def __init__(self, sess, state_dim, action_dim, learning_rate, gamma, ...
    method _build_net (line 151) | def _build_net(self, s, a, scope, trainable):
    method learn (line 172) | def learn(self, s, a, r, s_):
  class Memory (line 179) | class Memory(object):
    method __init__ (line 180) | def __init__(self, capacity, dims):
    method store_transition (line 185) | def store_transition(self, s, a, r, s_):
    method sample (line 191) | def sample(self, n):
  function train (line 215) | def train():
  function eval (line 264) | def eval():

FILE: experiments/Robot_arm/DPPO.py
  class PPO (line 43) | class PPO(object):
    method __init__ (line 44) | def __init__(self):
    method update (line 76) | def update(self):
    method _build_anet (line 92) | def _build_anet(self, name, trainable):
    method choose_action (line 101) | def choose_action(self, s):
    method get_v (line 106) | def get_v(self, s):
  class Worker (line 111) | class Worker(object):
    method __init__ (line 112) | def __init__(self, wid):
    method work (line 117) | def work(self):

FILE: experiments/Robot_arm/arm_env.py
  class ArmEnv (line 19) | class ArmEnv(object):
    method __init__ (line 33) | def __init__(self, mode='easy'):
    method step (line 44) | def step(self, action):
    method reset (line 62) | def reset(self):
    method render (line 81) | def render(self):
    method sample_action (line 86) | def sample_action(self):
    method set_fps (line 89) | def set_fps(self, fps=30):
    method _get_state (line 92) | def _get_state(self):
    method _r_func (line 102) | def _r_func(self, distance):
  class Viewer (line 118) | class Viewer(pyglet.window.Window):
    method __init__ (line 125) | def __init__(self, width, height, arm_info, point_info, point_l, mouse...
    method render (line 144) | def render(self):
    method on_draw (line 152) | def on_draw(self):
    method _update_arm (line 157) | def _update_arm(self):
    method on_key_press (line 190) | def on_key_press(self, symbol, modifiers):
    method on_mouse_motion (line 208) | def on_mouse_motion(self, x, y, dx, dy):
    method on_mouse_enter (line 211) | def on_mouse_enter(self, x, y):
    method on_mouse_leave (line 214) | def on_mouse_leave(self, x, y):

FILE: experiments/Solve_BipedalWalker/A3C.py
  class ACNet (line 44) | class ACNet(object):
    method __init__ (line 45) | def __init__(self, scope, globalAC=None):
    method _build_net (line 94) | def _build_net(self):
    method update_global (line 107) | def update_global(self, feed_dict):  # run by a local
    method pull_global (line 111) | def pull_global(self):  # run by a local
    method choose_action (line 114) | def choose_action(self, s):  # run by a local
  class Worker (line 119) | class Worker(object):
    method __init__ (line 120) | def __init__(self, name, globalAC):
    method work (line 125) | def work(self):

FILE: experiments/Solve_BipedalWalker/A3C_rnn.py
  class ACNet (line 44) | class ACNet(object):
    method __init__ (line 45) | def __init__(self, scope, globalAC=None):
    method _build_net (line 97) | def _build_net(self):
    method update_global (line 118) | def update_global(self, feed_dict):  # run by a local
    method pull_global (line 122) | def pull_global(self):  # run by a local
    method choose_action (line 125) | def choose_action(self, s, cell_state):  # run by a local
  class Worker (line 131) | class Worker(object):
    method __init__ (line 132) | def __init__(self, name, globalAC):
    method work (line 137) | def work(self):

FILE: experiments/Solve_BipedalWalker/DDPG.py
  class Actor (line 49) | class Actor(object):
    method __init__ (line 50) | def __init__(self, sess, action_dim, action_bound, learning_rate, t_re...
    method _build_net (line 68) | def _build_net(self, s, scope, trainable):
    method learn (line 83) | def learn(self, s):  # batch update
    method choose_action (line 89) | def choose_action(self, s):
    method add_grad_to_graph (line 93) | def add_grad_to_graph(self, a_grads):
  class Critic (line 108) | class Critic(object):
    method __init__ (line 109) | def __init__(self, sess, state_dim, action_dim, learning_rate, gamma, ...
    method _build_net (line 144) | def _build_net(self, s, a, scope, trainable):
    method learn (line 163) | def learn(self, s, a, r, s_, ISW):
  class SumTree (line 171) | class SumTree(object):
    method __init__ (line 180) | def __init__(self, capacity):
    method add_new_priority (line 189) | def add_new_priority(self, p, data):
    method update (line 198) | def update(self, tree_idx, p):
    method _propagate_change (line 204) | def _propagate_change(self, tree_idx, change):
    method get_leaf (line 211) | def get_leaf(self, lower_bound):
    method _retrieve (line 216) | def _retrieve(self, lower_bound, parent_idx=0):
    method root_priority (line 244) | def root_priority(self):
  class Memory (line 248) | class Memory(object):  # stored as ( s, a, r, s_ ) in SumTree
    method __init__ (line 259) | def __init__(self, capacity):
    method store (line 262) | def store(self, error, transition):
    method prio_sample (line 266) | def prio_sample(self, n):
    method random_sample (line 293) | def random_sample(self, n):
    method update (line 297) | def update(self, idx, error):
    method _get_priority (line 301) | def _get_priority(self, error):

FILE: experiments/Solve_LunarLander/A3C.py
  class ACNet (line 44) | class ACNet(object):
    method __init__ (line 45) | def __init__(self, scope, globalAC=None):
    method _build_net (line 85) | def _build_net(self, n_a):
    method update_global (line 105) | def update_global(self, feed_dict):  # run by a local
    method pull_global (line 108) | def pull_global(self):  # run by a local
    method choose_action (line 111) | def choose_action(self, s, cell_state):  # run by a local
  class Worker (line 119) | class Worker(object):
    method __init__ (line 120) | def __init__(self, name, globalAC):
    method work (line 125) | def work(self):

FILE: experiments/Solve_LunarLander/DuelingDQNPrioritizedReplay.py
  class SumTree (line 17) | class SumTree(object):
    method __init__ (line 26) | def __init__(self, capacity):
    method add_new_priority (line 35) | def add_new_priority(self, p, data):
    method update (line 44) | def update(self, tree_idx, p):
    method _propagate_change (line 50) | def _propagate_change(self, tree_idx, change):
    method get_leaf (line 57) | def get_leaf(self, lower_bound):
    method _retrieve (line 62) | def _retrieve(self, lower_bound, parent_idx=0):
    method root_priority (line 90) | def root_priority(self):
  class Memory (line 94) | class Memory(object):  # stored as ( s, a, r, s_ ) in SumTree
    method __init__ (line 105) | def __init__(self, capacity):
    method store (line 108) | def store(self, error, transition):
    method sample (line 112) | def sample(self, n):
    method update (line 133) | def update(self, idx, error):
    method _get_priority (line 137) | def _get_priority(self, error):
  class DuelingDQNPrioritizedReplay (line 143) | class DuelingDQNPrioritizedReplay:
    method __init__ (line 144) | def __init__(
    method _build_net (line 186) | def _build_net(self):
    method store_transition (line 241) | def store_transition(self, s, a, r, s_):
    method choose_action (line 246) | def choose_action(self, observation):
    method _replace_target_params (line 255) | def _replace_target_params(self):
    method learn (line 260) | def learn(self):