MCPcopy Create free account

hub / github.com/Lizhi-sjtu/DRL-code-pytorch / functions

Functions181 in github.com/Lizhi-sjtu/DRL-code-pytorch

⨍ Functions 181◇ Types & classes 52
↓ 17 callersMethodreset
(self)
4.PPO-discrete/normalization.py:51
↓ 15 callersMethodactor
(self, s)
9.PPO-discrete-RNN/ppo_discrete_rnn.py:54
↓ 15 callersMethodcritic
(self, s)
9.PPO-discrete-RNN/ppo_discrete_rnn.py:60
↓ 14 callersMethodmean
(self, s)
5.PPO-continuous/ppo_continuous.py:43
↓ 10 callersFunctionorthogonal_init
(layer, gain=1.0)
5.PPO-continuous/ppo_continuous.py:9
↓ 6 callersFunctiondrawing_LL
(plt, algorithm, number, color, label)
3.Rainbow_DQN/drawing_Rainbow_DQN.py:43
↓ 6 callersFunctionorthogonal_init
(layer, gain=1.0)
4.PPO-discrete/ppo_discrete.py:10
↓ 6 callersFunctionorthogonal_init
(layer, gain=np.sqrt(2))
9.PPO-discrete-RNN/ppo_discrete_rnn.py:11
↓ 6 callersMethodsample
(self, batch_size)
7.TD3/TD3.py:78
↓ 4 callersMethodupdate
(self, data_index, priority)
3.Rainbow_DQN/sum_tree.py:25
↓ 3 callersMethodget_dist
(self, s)
5.PPO-continuous/ppo_continuous.py:38
↓ 3 callersMethodreset
(self)
9.PPO-discrete-RNN/normalization.py:51
↓ 3 callersMethodreset
(self)
5.PPO-continuous/normalization.py:51
↓ 3 callersMethodreset_rnn_hidden
(self)
9.PPO-discrete-RNN/ppo_discrete_rnn.py:89
↓ 3 callersFunctionsmooth
(reward)
3.Rainbow_DQN/drawing_Rainbow_DQN.py:6
↓ 2 callersMethod__init__
(self, args)
3.Rainbow_DQN/network.py:29
↓ 2 callersMethod__init__
(self, state_dim, action_dim, max_action)
6.DDPG/DDPG.py:71
↓ 2 callersMethod__init__
(self, args)
5.PPO-continuous/ppo_continuous.py:80
↓ 2 callersMethod__init__
(self, state_dim, action_dim, max_action)
7.TD3/TD3.py:90
↓ 2 callersMethod__init__
(self, state_dim, action_dim, max_action)
8.SAC/SAC-continuous.py:102
↓ 2 callersMethod__init__
(self, state_dim, action_dim)
2.Actor-Critic/A2C.py:36
↓ 2 callersMethodchoose_action
(self, state, epsilon)
3.Rainbow_DQN/rainbow_dqn.py:37
↓ 2 callersMethodchoose_action
(self, s, evaluate=False)
9.PPO-discrete-RNN/ppo_discrete_rnn.py:93
↓ 2 callersMethodchoose_action
(self, s)
6.DDPG/DDPG.py:88
↓ 2 callersMethodchoose_action
(self, s)
7.TD3/TD3.py:110
↓ 2 callersMethodchoose_action
(self, s, deterministic)
1.REINFORCE/REINFORCE_baseline.py:48
↓ 2 callersMethodchoose_action
(self, s, deterministic)
1.REINFORCE/REINFORCE.py:33
↓ 2 callersMethodchoose_action
(self, s, deterministic=False)
8.SAC/SAC-continuous.py:127
↓ 2 callersMethodchoose_action
(self, s, deterministic)
2.Actor-Critic/A2C.py:50
↓ 2 callersMethodevaluate_policy
(self, )
3.Rainbow_DQN/Rainbow_DQN_main.py:107
↓ 2 callersMethodevaluate_policy
(self, )
9.PPO-discrete-RNN/PPO_discrete_rnn_main.py:101
↓ 2 callersMethodforward
(self, s)
5.PPO-continuous/ppo_continuous.py:30
↓ 2 callersMethodget_batch_index
(self, current_size, batch_size, beta)
3.Rainbow_DQN/sum_tree.py:54
↓ 2 callersFunctionget_data
(algorithm, env_index, number)
3.Rainbow_DQN/drawing_Rainbow_DQN.py:20
↓ 2 callersMethodget_value
(self, s)
9.PPO-discrete-RNN/ppo_discrete_rnn.py:106
↓ 2 callersMethodreset_buffer
(self)
9.PPO-discrete-RNN/replaybuffer.py:20
↓ 2 callersMethodreset_noise
(self)
3.Rainbow_DQN/network.py:83
↓ 2 callersMethodsample
(self, batch_size)
6.DDPG/DDPG.py:59
↓ 2 callersMethodsample
(self, batch_size)
8.SAC/SAC-continuous.py:90
↓ 2 callersMethodscale_noise
(self, size)
3.Rainbow_DQN/network.py:89
↓ 2 callersMethodtrain
(self, replay_buffer, total_steps)
9.PPO-discrete-RNN/ppo_discrete_rnn.py:112
↓ 2 callersMethodupdate
(self, x)
4.PPO-discrete/normalization.py:12
↓ 2 callersMethodupdate
(self, x)
9.PPO-discrete-RNN/normalization.py:12
↓ 2 callersMethodupdate
(self, x)
5.PPO-continuous/normalization.py:12
↓ 1 callersMethodQ1
(self, s, a)
7.TD3/TD3.py:49
↓ 1 callersMethod__init__
(self, args)
4.PPO-discrete/ppo_discrete.py:16
↓ 1 callersMethod__init__
(self, state_dim, hidden_width)
1.REINFORCE/REINFORCE_baseline.py:22
↓ 1 callersMethodchoose_action
(self, s)
4.PPO-discrete/ppo_discrete.py:89
↓ 1 callersMethodchoose_action
(self, s)
5.PPO-continuous/ppo_continuous.py:140
↓ 1 callersMethodevaluate
(self, s)
4.PPO-discrete/ppo_discrete.py:83
↓ 1 callersMethodevaluate
(self, s)
5.PPO-continuous/ppo_continuous.py:132
↓ 1 callersFunctionevaluate_policy
(args, env, agent, state_norm)
4.PPO-discrete/PPO_discrete_main.py:11
↓ 1 callersFunctionevaluate_policy
(env, agent)
6.DDPG/DDPG.py:132
↓ 1 callersFunctionevaluate_policy
(args, env, agent, state_norm)
5.PPO-continuous/PPO_continuous_main.py:11
↓ 1 callersFunctionevaluate_policy
(env, agent)
7.TD3/TD3.py:164
↓ 1 callersFunctionevaluate_policy
(env, agent)
1.REINFORCE/REINFORCE_baseline.py:93
↓ 1 callersFunctionevaluate_policy
(env, agent)
1.REINFORCE/REINFORCE.py:70
↓ 1 callersFunctionevaluate_policy
(env, agent)
8.SAC/SAC-continuous.py:183
↓ 1 callersFunctionevaluate_policy
(env, agent)
2.Actor-Critic/A2C.py:85
↓ 1 callersMethodforward
(self, s)
5.PPO-continuous/ppo_continuous.py:65
↓ 1 callersMethodget_adv
(self)
9.PPO-discrete-RNN/replaybuffer.py:49
↓ 1 callersMethodget_index
(self, v)
3.Rainbow_DQN/sum_tree.py:36
↓ 1 callersMethodget_n_steps_transition
(self)
3.Rainbow_DQN/replay_buffer.py:70
↓ 1 callersMethodget_n_steps_transition
(self)
3.Rainbow_DQN/replay_buffer.py:191
↓ 1 callersMethodget_training_data
(self)
9.PPO-discrete-RNN/replaybuffer.py:71
↓ 1 callersMethodlearn
(self, replay_buffer, total_steps)
3.Rainbow_DQN/rainbow_dqn.py:47
↓ 1 callersMethodlearn
(self, relay_buffer)
6.DDPG/DDPG.py:93
↓ 1 callersMethodlearn
(self, relay_buffer)
7.TD3/TD3.py:115
↓ 1 callersMethodlearn
(self, )
1.REINFORCE/REINFORCE_baseline.py:63
↓ 1 callersMethodlearn
(self, )
1.REINFORCE/REINFORCE.py:48
↓ 1 callersMethodlearn
(self, relay_buffer)
8.SAC/SAC-continuous.py:132
↓ 1 callersMethodlearn
(self, s, a, r, s_, dw)
2.Actor-Critic/A2C.py:60
↓ 1 callersMethodlr_decay
(self, total_steps)
3.Rainbow_DQN/rainbow_dqn.py:85
↓ 1 callersMethodlr_decay
(self, total_steps)
4.PPO-discrete/ppo_discrete.py:150
↓ 1 callersMethodlr_decay
(self, total_steps)
9.PPO-discrete-RNN/ppo_discrete_rnn.py:150
↓ 1 callersMethodlr_decay
(self, total_steps)
5.PPO-continuous/ppo_continuous.py:208
↓ 1 callersFunctionmain
(args, env_name, number, seed)
4.PPO-discrete/PPO_discrete_main.py:32
↓ 1 callersFunctionmain
(args, env_name, number, seed)
5.PPO-continuous/PPO_continuous_main.py:36
↓ 1 callersMethodnumpy_to_tensor
(self)
4.PPO-discrete/replaybuffer.py:26
↓ 1 callersMethodnumpy_to_tensor
(self)
5.PPO-continuous/replaybuffer.py:26
↓ 1 callersMethodreset_parameters
(self)
3.Rainbow_DQN/network.py:75
↓ 1 callersFunctionreward_adapter
(r, env_index)
6.DDPG/DDPG.py:149
↓ 1 callersFunctionreward_adapter
(r, env_index)
7.TD3/TD3.py:181
↓ 1 callersFunctionreward_adapter
(r, env_index)
8.SAC/SAC-continuous.py:200
↓ 1 callersMethodrun
(self, )
3.Rainbow_DQN/Rainbow_DQN_main.py:71
↓ 1 callersMethodrun
(self, )
9.PPO-discrete-RNN/PPO_discrete_rnn_main.py:50
↓ 1 callersMethodrun_episode
(self, )
9.PPO-discrete-RNN/PPO_discrete_rnn_main.py:67
↓ 1 callersMethodsample
(self, total_steps)
3.Rainbow_DQN/replay_buffer.py:29
↓ 1 callersMethodstore
(self, s, a, a_logprob, r, s_, dw, done)
4.PPO-discrete/replaybuffer.py:16
↓ 1 callersMethodstore
(self, s, a, r, s_, dw)
6.DDPG/DDPG.py:50
↓ 1 callersMethodstore
(self, s, a, a_logprob, r, s_, dw, done)
5.PPO-continuous/replaybuffer.py:16
↓ 1 callersMethodstore
(self, s, a, r, s_, dw)
7.TD3/TD3.py:69
↓ 1 callersMethodstore
(self, s, a, r)
1.REINFORCE/REINFORCE_baseline.py:58
↓ 1 callersMethodstore
(self, s, a, r)
1.REINFORCE/REINFORCE.py:43
↓ 1 callersMethodstore
(self, s, a, r, s_, dw)
8.SAC/SAC-continuous.py:81
↓ 1 callersMethodstore_last_value
(self, episode_step, v)
9.PPO-discrete-RNN/replaybuffer.py:42
↓ 1 callersMethodstore_transition
(self, state, action, reward, next_state, terminal, done)
3.Rainbow_DQN/replay_buffer.py:20
↓ 1 callersMethodstore_transition
(self, episode_step, s, v, a, a_logprob, r, dw)
9.PPO-discrete-RNN/replaybuffer.py:32
↓ 1 callersMethodupdate
(self, replay_buffer, total_steps)
4.PPO-discrete/ppo_discrete.py:97
↓ 1 callersMethodupdate
(self, replay_buffer, total_steps)
5.PPO-continuous/ppo_continuous.py:155
next →1–100 of 181, ranked by callers