Functions — github.com/MorvanZhou/Reinforcement-learning-with-tensorflow

hub / github.com/MorvanZhou/Reinforcement-learning-with-tensorflow / functions

Functions342 in github.com/MorvanZhou/Reinforcement-learning-with-tensorflow

⨍ Functions 342◇ Types & classes 72

↓ 1 callersMethodstore_transition

(self, s, a, r, s_)

contents/5.3_Dueling_DQN/RL_brain.py:114

↓ 1 callersMethodstore_transition

(self, s, a, r, s_)

contents/Curiosity_Model/Random_Network_Distillation.py:103

↓ 1 callersMethodstore_transition

(self, s, a, r, s_)

contents/Curiosity_Model/Curiosity.py:102

↓ 1 callersMethodstore_transition

(self, s, a, r, s_)

contents/5.1_Double_DQN/RL_brain.py:98

↓ 1 callersMethodstore_transition

(self, s, a, r, s_)

contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG.py:184

↓ 1 callersMethodstore_transition

(self, s, a, r, s_)

contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG_update.py:92

↓ 1 callersMethodstore_transition

(self, s, a, r, s_)

contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG_update2.py:89

↓ 1 callersFunctiontrain

()

experiments/Robot_arm/DDPG.py:215

↓ 1 callersFunctiontrain

()

experiments/2D_car/DDPG.py:206

↓ 1 callersMethodupdate

(self, tree_idx, p)

experiments/Solve_BipedalWalker/DDPG.py:198

↓ 1 callersMethodupdate

(self, idx, error)

experiments/Solve_BipedalWalker/DDPG.py:297

↓ 1 callersMethodupdate

(self, tree_idx, p)

experiments/Solve_LunarLander/DuelingDQNPrioritizedReplay.py:44

↓ 1 callersMethodupdate

(self, idx, error)

experiments/Solve_LunarLander/DuelingDQNPrioritizedReplay.py:133

↓ 1 callersMethodupdate

(self, s, a, r)

contents/12_Proximal_Policy_Optimization/simply_PPO.py:82

↓ 1 callersMethodupdate_global

(self, feed_dict)

experiments/Solve_BipedalWalker/A3C.py:107

↓ 1 callersMethodupdate_global

(self, feed_dict)

experiments/Solve_BipedalWalker/A3C_rnn.py:118

↓ 1 callersMethodupdate_global

(self, feed_dict)

experiments/Solve_LunarLander/A3C.py:105

↓ 1 callersMethodupdate_global

(self, feed_dict)

experiments/Robot_arm/A3C.py:116

↓ 1 callersMethodupdate_global

(self, feed_dict)

contents/10_A3C/A3C_RNN.py:111

↓ 1 callersMethodupdate_global

(self, feed_dict)

contents/10_A3C/A3C_distributed_tf.py:89

↓ 1 callersMethodupdate_global

(self, feed_dict)

contents/10_A3C/A3C_discrete_action.py:93

↓ 1 callersMethodupdate_global

(self, feed_dict)

contents/10_A3C/A3C_continuous_action.py:102

↓ 1 callersMethodwork

(self)

experiments/Solve_BipedalWalker/A3C.py:125

↓ 1 callersMethodwork

(self)

experiments/Solve_LunarLander/A3C.py:125

↓ 1 callersMethodwork

(self)

experiments/Robot_arm/A3C.py:134

↓ 1 callersMethodwork

(self)

contents/10_A3C/A3C_RNN.py:129

↓ 1 callersMethodwork

(self)

contents/10_A3C/A3C_discrete_action.py:112

↓ 1 callersMethodwork

(self)

contents/10_A3C/A3C_continuous_action.py:119

Method__init__

(self, sess, action_dim, action_bound, learning_rate, t_replace_iter)

experiments/Solve_BipedalWalker/DDPG.py:50

Method__init__

(self, sess, state_dim, action_dim, learning_rate, gamma, t_replace_iter, a, a_)

experiments/Solve_BipedalWalker/DDPG.py:109

Method__init__

(self, capacity)

experiments/Solve_BipedalWalker/DDPG.py:180

Method__init__

(self, capacity)

experiments/Solve_BipedalWalker/DDPG.py:259

Method__init__

(self, scope, globalAC=None)

experiments/Solve_BipedalWalker/A3C.py:45

Method__init__

(self, name, globalAC)

experiments/Solve_BipedalWalker/A3C.py:120

Method__init__

(self, scope, globalAC=None)

experiments/Solve_BipedalWalker/A3C_rnn.py:45

Method__init__

(self, name, globalAC)

experiments/Solve_BipedalWalker/A3C_rnn.py:132

Method__init__

(self, scope, globalAC=None)

experiments/Solve_LunarLander/A3C.py:45

Method__init__

(self, name, globalAC)

experiments/Solve_LunarLander/A3C.py:120

Method__init__

(self, capacity)

experiments/Solve_LunarLander/DuelingDQNPrioritizedReplay.py:26

Method__init__

(self, capacity)

experiments/Solve_LunarLander/DuelingDQNPrioritizedReplay.py:105

Method__init__

( self, n_actions, n_features, learning_rate=0.005,

experiments/Solve_LunarLander/DuelingDQNPrioritizedReplay.py:144

Method__init__

(self, sess, action_dim, action_bound, learning_rate, t_replace_iter)

experiments/Robot_arm/DDPG.py:60

Method__init__

(self, sess, state_dim, action_dim, learning_rate, gamma, t_replace_iter, a, a_)

experiments/Robot_arm/DDPG.py:118

Method__init__

(self, capacity, dims)

experiments/Robot_arm/DDPG.py:180

Method__init__

(self, width, height, arm_info, point_info, point_l, mouse_in)

experiments/Robot_arm/arm_env.py:125

Method__init__

(self, scope, globalAC=None)

experiments/Robot_arm/A3C.py:54

Method__init__

(self, name, globalAC)

experiments/Robot_arm/A3C.py:129

Method__init__

(self)

experiments/Robot_arm/DPPO.py:44

Method__init__

(self, wid)

experiments/Robot_arm/DPPO.py:112

Method__init__

(self, width, height, car_info, sensor_info, obstacle_coords)

experiments/2D_car/car_env.py:157

Method__init__

(self, sess, action_dim, action_bound, learning_rate, t_replace_iter)

experiments/2D_car/DDPG.py:59

Method__init__

(self, sess, state_dim, action_dim, learning_rate, gamma, t_replace_iter, a, a_)

experiments/2D_car/DDPG.py:113

Method__init__

(self, capacity, dims)

experiments/2D_car/DDPG.py:171

Method__init__

( self, n_actions, n_features, learning_rate=0.01,

contents/7_Policy_gradient_softmax/RL_brain.py:23

Method__init__

(self, capacity)

contents/5.2_Prioritized_Replay_DQN/RL_brain.py:27

Method__init__

(self, capacity)

contents/5.2_Prioritized_Replay_DQN/RL_brain.py:100

Method__init__

( self, n_actions, n_features, learning_rate=0.005,

contents/5.2_Prioritized_Replay_DQN/RL_brain.py:133

Method__init__

(self, actions, learning_rate=0.01, reward_decay=0.9, e_greedy=0.9, trace_decay=0.9)

contents/4_Sarsa_lambda_maze/RL_brain.py:51

Method__init__

(self)

contents/4_Sarsa_lambda_maze/maze_env.py:31

Method__init__

( self, n_actions, n_features, learning_rate=0.01,

contents/5_Deep_Q_Network/RL_brain.py:23

Method__init__

( self, n_actions, n_features, learning_rate=0.01,

contents/5_Deep_Q_Network/DQN_modified.py:21

Method__init__

(self)

contents/5_Deep_Q_Network/maze_env.py:28

Method__init__

(self, actions, learning_rate=0.01, reward_decay=0.9, e_greedy=0.9)

contents/2_Q_Learning_maze/RL_brain.py:13

Method__init__

(self)

contents/2_Q_Learning_maze/maze_env.py:30

Method__init__

(self)

contents/12_Proximal_Policy_Optimization/simply_PPO.py:37

Method__init__

(self)

contents/12_Proximal_Policy_Optimization/DPPO.py:36

Method__init__

(self, wid)

contents/12_Proximal_Policy_Optimization/DPPO.py:104

Method__init__

(self)

contents/12_Proximal_Policy_Optimization/discrete_DPPO.py:39

Method__init__

(self, wid)

contents/12_Proximal_Policy_Optimization/discrete_DPPO.py:110

Method__init__

(self, actions, learning_rate=0.01, reward_decay=0.9, e_greedy=0.9)

contents/11_Dyna_Q/RL_brain.py:13

Method__init__

(self, actions)

contents/11_Dyna_Q/RL_brain.py:65

Method__init__

(self)

contents/11_Dyna_Q/maze_env.py:27

Method__init__

(self, scope, globalAC=None)

contents/10_A3C/A3C_RNN.py:45

Method__init__

(self, name, globalAC)

contents/10_A3C/A3C_RNN.py:124

Method__init__

(self, scope, opt_a=None, opt_c=None, global_net=None)

contents/10_A3C/A3C_distributed_tf.py:31

Method__init__

(self, scope, globalAC=None)

contents/10_A3C/A3C_discrete_action.py:43

Method__init__

(self, name, globalAC)

contents/10_A3C/A3C_discrete_action.py:107

Method__init__

(self, scope, globalAC=None)

contents/10_A3C/A3C_continuous_action.py:45

Method__init__

(self, name, globalAC)

contents/10_A3C/A3C_continuous_action.py:114

Method__init__

( self, n_actions, n_features, learning_rate=0.001,

contents/5.3_Dueling_DQN/RL_brain.py:19

Method__init__

( self, n_a, n_s, lr=0.01, gamma=0.95,

contents/Curiosity_Model/Random_Network_Distillation.py:10

Method__init__

( self, n_a, n_s, lr=0.01, gamma=0.98,

contents/Curiosity_Model/Curiosity.py:10

Method__init__

( self, n_actions, n_features, learning_rate=0.005,

contents/5.1_Double_DQN/RL_brain.py:19

Method__init__

( self, n_actions, n_features, learning_rate=0.01,

contents/6_OpenAI_gym/RL_brain.py:20

Method__init__

(self, sess, n_features, action_bound, lr=0.0001)

contents/8_Actor_Critic_Advantage/AC_continue_Pendulum.py:24

Method__init__

(self, sess, n_features, lr=0.01)

contents/8_Actor_Critic_Advantage/AC_continue_Pendulum.py:85

Method__init__

(self, sess, n_features, n_actions, lr=0.001)

contents/8_Actor_Critic_Advantage/AC_CartPole.py:39

Method__init__

(self, sess, n_features, lr=0.01)

contents/8_Actor_Critic_Advantage/AC_CartPole.py:85

Method__init__

(self, sess, action_dim, action_bound, learning_rate, replacement)

contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG.py:44

Method__init__

(self, sess, state_dim, action_dim, learning_rate, gamma, replacement, a, a_)

contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG.py:112

Method__init__

(self, capacity, dims)

contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG.py:179

Method__init__

(self, a_dim, s_dim, a_bound,)

contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG_update.py:36

Method__init__

(self, a_dim, s_dim, a_bound,)

contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG_update2.py:42

Method__init__

(self, actions, learning_rate=0.01, reward_decay=0.9, e_greedy=0.9)

contents/3_Sarsa_maze/RL_brain.py:51

Method__init__

(self, actions, learning_rate=0.01, reward_decay=0.9, e_greedy=0.9)

contents/3_Sarsa_maze/RL_brain.py:67

Method__init__

(self)

contents/3_Sarsa_maze/maze_env.py:31

Methodbuild_layers

(s, c_names, w_initializer, b_initializer)

experiments/Solve_LunarLander/DuelingDQNPrioritizedReplay.py:187

Methodbuild_layers

(s, c_names, n_l1, w_initializer, b_initializer, trainable)

contents/5.2_Prioritized_Replay_DQN/RL_brain.py:185

Methodbuild_layers

(s, c_names, n_l1, w_initializer, b_initializer)

contents/5.3_Dueling_DQN/RL_brain.py:64

Methodbuild_layers

(s, c_names, n_l1, w_initializer, b_initializer)

contents/5.1_Double_DQN/RL_brain.py:64

← previous next →201–300 of 342, ranked by callers