MCPcopy Create free account

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

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

⨍ Functions 342◇ Types & classes 72
↓ 21 callersMethodreset
(self)
contents/11_Dyna_Q/maze_env.py:80
↓ 21 callersMethodstep
(self, action)
contents/11_Dyna_Q/maze_env.py:92
↓ 15 callersMethodrender
(self)
contents/11_Dyna_Q/maze_env.py:125
↓ 9 callersMethodadd
(self, p, data)
contents/5.2_Prioritized_Replay_DQN/RL_brain.py:36
↓ 8 callersMethodreset
(self)
experiments/2D_car/car_env.py:62
↓ 8 callersMethodstep
(self, action)
experiments/2D_car/car_env.py:48
↓ 8 callersMethodupdate
(self)
contents/12_Proximal_Policy_Optimization/DPPO.py:67
↓ 7 callersMethodrender
(self)
experiments/2D_car/car_env.py:68
↓ 6 callersMethodsample
(self, n)
contents/5.2_Prioritized_Replay_DQN/RL_brain.py:109
↓ 5 callersMethodreset
(self)
experiments/Robot_arm/arm_env.py:62
↓ 5 callersMethodstep
(self, action)
experiments/Robot_arm/arm_env.py:44
↓ 4 callersMethodrender
(self)
experiments/Robot_arm/arm_env.py:81
↓ 4 callersMethodreset
(self)
contents/5_Deep_Q_Network/maze_env.py:82
↓ 4 callersMethodstep
(self, action)
contents/5_Deep_Q_Network/maze_env.py:94
↓ 4 callersMethodupdate
(self, tree_idx, p)
contents/5.2_Prioritized_Replay_DQN/RL_brain.py:45
↓ 3 callersMethodcheck_state_exist
(self, state)
contents/11_Dyna_Q/RL_brain.py:50
↓ 3 callersMethodsample
(self, n)
experiments/Solve_LunarLander/DuelingDQNPrioritizedReplay.py:112
↓ 3 callersMethodsample
(self, n)
experiments/Robot_arm/DDPG.py:191
↓ 2 callersMethod__init__
(self, action_space, learning_rate=0.01, reward_decay=0.9, e_greedy=0.9)
contents/3_Sarsa_maze/RL_brain.py:13
↓ 2 callersMethod_build_a
(self, s, scope, trainable)
contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG_update.py:98
↓ 2 callersMethod_build_a
(self, s, reuse=None, custom_getter=None)
contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG_update2.py:95
↓ 2 callersMethod_build_anet
(self, name, trainable)
experiments/Robot_arm/DPPO.py:92
↓ 2 callersMethod_build_anet
(self, name, trainable)
contents/12_Proximal_Policy_Optimization/simply_PPO.py:106
↓ 2 callersMethod_build_anet
(self, name, trainable)
contents/12_Proximal_Policy_Optimization/DPPO.py:84
↓ 2 callersMethod_build_anet
(self, name, trainable)
contents/12_Proximal_Policy_Optimization/discrete_DPPO.py:91
↓ 2 callersMethod_build_c
(self, s, a, scope, trainable)
contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG_update.py:104
↓ 2 callersMethod_build_c
(self, s, a, reuse=None, custom_getter=None)
contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG_update2.py:102
↓ 2 callersMethod_build_net
(self, s, scope, trainable)
experiments/Solve_BipedalWalker/DDPG.py:68
↓ 2 callersMethod_build_net
(self, s, a, scope, trainable)
experiments/Solve_BipedalWalker/DDPG.py:144
↓ 2 callersMethod_build_net
(self)
experiments/Solve_BipedalWalker/A3C.py:94
↓ 2 callersMethod_build_net
(self)
experiments/Solve_BipedalWalker/A3C_rnn.py:97
↓ 2 callersMethod_build_net
(self, n_a)
experiments/Solve_LunarLander/A3C.py:85
↓ 2 callersMethod_build_net
(self, s, scope, trainable)
experiments/Robot_arm/DDPG.py:79
↓ 2 callersMethod_build_net
(self, s, a, scope, trainable)
experiments/Robot_arm/DDPG.py:151
↓ 2 callersMethod_build_net
(self)
experiments/Robot_arm/A3C.py:103
↓ 2 callersMethod_build_net
(self, s, scope, trainable)
experiments/2D_car/DDPG.py:77
↓ 2 callersMethod_build_net
(self, s, a, scope, trainable)
experiments/2D_car/DDPG.py:145
↓ 2 callersMethod_build_net
(self, scope)
contents/10_A3C/A3C_RNN.py:89
↓ 2 callersMethod_build_net
(self, scope)
contents/10_A3C/A3C_distributed_tf.py:71
↓ 2 callersMethod_build_net
(self, scope)
contents/10_A3C/A3C_discrete_action.py:81
↓ 2 callersMethod_build_net
(self, scope)
contents/10_A3C/A3C_continuous_action.py:89
↓ 2 callersMethod_build_net
(self, s, scope, trainable)
contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG.py:69
↓ 2 callersMethod_build_net
(self, s, a, scope, trainable)
contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG.py:150
↓ 2 callersMethod_get_priority
(self, error)
experiments/Solve_BipedalWalker/DDPG.py:301
↓ 2 callersMethod_get_priority
(self, error)
experiments/Solve_LunarLander/DuelingDQNPrioritizedReplay.py:137
↓ 2 callersMethod_get_state
(self)
experiments/Robot_arm/arm_env.py:92
↓ 2 callersMethod_get_state
(self)
experiments/2D_car/car_env.py:83
↓ 2 callersMethod_update_sensor
(self)
experiments/2D_car/car_env.py:87
↓ 2 callersMethodcheck_state_exist
(self, state)
contents/2_Q_Learning_maze/RL_brain.py:42
↓ 2 callersMethodcheck_state_exist
(self, state)
contents/3_Sarsa_maze/RL_brain.py:21
↓ 2 callersMethodchoose_action
(self, s, cell_state)
experiments/Solve_LunarLander/A3C.py:111
↓ 2 callersMethodchoose_action
(self, s)
experiments/Robot_arm/DDPG.py:104
↓ 2 callersMethodchoose_action
(self, s)
experiments/Robot_arm/DPPO.py:101
↓ 2 callersMethodchoose_action
(self, s)
experiments/2D_car/DDPG.py:99
↓ 2 callersMethodchoose_action
(self, observation)
contents/7_Policy_gradient_softmax/RL_brain.py:86
↓ 2 callersMethodchoose_action
(self, observation)
contents/4_Sarsa_lambda_maze/RL_brain.py:32
↓ 2 callersMethodchoose_action
(self, s)
contents/12_Proximal_Policy_Optimization/DPPO.py:93
↓ 2 callersMethodchoose_action
(self, s)
contents/12_Proximal_Policy_Optimization/discrete_DPPO.py:98
↓ 2 callersMethodchoose_action
(self, observation)
contents/6_OpenAI_gym/RL_brain.py:123
↓ 2 callersMethodchoose_action
(self, observation)
contents/3_Sarsa_maze/RL_brain.py:32
↓ 2 callersMethodlearn
(self, s)
experiments/Solve_BipedalWalker/DDPG.py:83
↓ 2 callersMethodlearn
(self, s)
experiments/Robot_arm/DDPG.py:98
↓ 2 callersMethodlearn
(self, s)
experiments/2D_car/DDPG.py:93
↓ 2 callersMethodlearn
(self)
contents/7_Policy_gradient_softmax/RL_brain.py:96
↓ 2 callersMethodlearn
(self, s, a, r, s_)
contents/11_Dyna_Q/RL_brain.py:40
↓ 2 callersMethodlearn
(self)
contents/6_OpenAI_gym/RL_brain.py:135
↓ 2 callersMethodlearn
(self, s, a, td)
contents/8_Actor_Critic_Advantage/AC_continue_Pendulum.py:73
↓ 2 callersMethodlearn
(self, s, a, td)
contents/8_Actor_Critic_Advantage/AC_CartPole.py:72
↓ 2 callersMethodlearn
(self, s)
contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG.py:82
↓ 2 callersMethodplot_cost
(self)
contents/6_OpenAI_gym/RL_brain.py:200
↓ 2 callersMethodrender
(self)
contents/2_Q_Learning_maze/maze_env.py:130
↓ 2 callersMethodreset
(self)
contents/2_Q_Learning_maze/maze_env.py:83
↓ 2 callersMethodset_fps
(self, fps=30)
experiments/Robot_arm/arm_env.py:89
↓ 2 callersMethodset_fps
(self, fps=30)
experiments/2D_car/car_env.py:80
↓ 2 callersMethodstep
(self, action)
contents/2_Q_Learning_maze/maze_env.py:95
↓ 2 callersMethodstore_transition
(self, s, a, r)
contents/7_Policy_gradient_softmax/RL_brain.py:91
↓ 2 callersMethodstore_transition
(self, s, a, r, s_)
contents/6_OpenAI_gym/RL_brain.py:111
↓ 2 callersFunctiontrain
(RL)
contents/5.2_Prioritized_Replay_DQN/run_MountainCar.py:38
↓ 2 callersFunctiontrain
(RL)
contents/5.3_Dueling_DQN/run_Pendulum.py:39
↓ 2 callersFunctiontrain
(RL)
contents/5.1_Double_DQN/run_Pendulum.py:41
↓ 2 callersFunctionupdate_env
(S, episode, step_counter)
contents/1_command_line_reinforcement_learning/treasure_on_right.py:62
↓ 1 callersMethod__init__
(self, mode='easy')
experiments/Robot_arm/arm_env.py:33
↓ 1 callersMethod__init__
(self, discrete_action=False)
experiments/2D_car/car_env.py:30
↓ 1 callersMethod__init__
(self, action_space, learning_rate=0.01, reward_decay=0.9, e_greedy=0.9)
contents/4_Sarsa_lambda_maze/RL_brain.py:13
↓ 1 callersMethod_build_dqn
(self, s, a, ri, re, s_)
contents/Curiosity_Model/Random_Network_Distillation.py:83
↓ 1 callersMethod_build_dqn
(self, s, a, r, s_)
contents/Curiosity_Model/Curiosity.py:82
↓ 1 callersMethod_build_dynamics_net
(self, s, a, s_)
contents/Curiosity_Model/Curiosity.py:67
↓ 1 callersMethod_build_maze
(self)
contents/4_Sarsa_lambda_maze/maze_env.py:39
↓ 1 callersMethod_build_maze
(self)
contents/5_Deep_Q_Network/maze_env.py:37
↓ 1 callersMethod_build_maze
(self)
contents/2_Q_Learning_maze/maze_env.py:38
↓ 1 callersMethod_build_maze
(self)
contents/11_Dyna_Q/maze_env.py:35
↓ 1 callersMethod_build_maze
(self)
contents/3_Sarsa_maze/maze_env.py:39
↓ 1 callersMethod_build_net
(self)
experiments/Solve_LunarLander/DuelingDQNPrioritizedReplay.py:186
↓ 1 callersMethod_build_net
(self)
contents/7_Policy_gradient_softmax/RL_brain.py:50
↓ 1 callersMethod_build_net
(self)
contents/5.2_Prioritized_Replay_DQN/RL_brain.py:184
↓ 1 callersMethod_build_net
(self)
contents/5_Deep_Q_Network/RL_brain.py:69
↓ 1 callersMethod_build_net
(self)
contents/5_Deep_Q_Network/DQN_modified.py:69
↓ 1 callersMethod_build_net
(self)
contents/5.3_Dueling_DQN/RL_brain.py:63
↓ 1 callersMethod_build_net
(self)
contents/5.1_Double_DQN/RL_brain.py:63
↓ 1 callersMethod_build_net
(self)
contents/6_OpenAI_gym/RL_brain.py:66
next →1–100 of 342, ranked by callers