Functions — github.com/AgentMaker/Paddle-RLBooks

hub / github.com/AgentMaker/Paddle-RLBooks / functions

Functions219 in github.com/AgentMaker/Paddle-RLBooks

⨍ Functions 219◇ Types & classes 33

↓ 1 callersMethodforward

(self, inputs)

policy_gradient/reinforce.py:28

↓ 1 callersMethodforward

(self, inputs)

policy_gradient/policy_gradient_basic.py:28

↓ 1 callersMethodforward

(self, inputs)

actor_critic/ac.py:29

↓ 1 callersMethodget_action

(self, state)

sac/model.py:38

↓ 1 callersFunctionget_loss

(obs, action, reward, next_obs, done)

dqn/categorical_dqn(C51)/train.py:48

↓ 1 callersFunctionmain

()

policy_gradient/policy_gradient_with_baseline_with_w.py:75

↓ 1 callersFunctionmain

()

policy_gradient/policy_gradient_with_baseline.py:65

↓ 1 callersFunctionmain

()

policy_gradient/reinforce.py:64

↓ 1 callersFunctionmain

()

policy_gradient/policy_gradient_basic.py:63

↓ 1 callersFunctionmain

()

dqn/dqn_noisy_networks/infer.py:22

↓ 1 callersFunctionmain

()

dqn/dqn_noisy_networks/test_env.py:4

↓ 1 callersFunctionmain

()

dqn/double_dqn/infer.py:22

↓ 1 callersFunctionmain

()

dqn/double_dqn/test_env.py:4

↓ 1 callersFunctionmain

()

dqn/nstep_dqn/infer.py:22

↓ 1 callersFunctionmain

()

dqn/nstep_dqn/test_env.py:4

↓ 1 callersFunctionmain

()

dqn/dueling_dqn/infer.py:22

↓ 1 callersFunctionmain

()

dqn/dueling_dqn/test_env.py:4

↓ 1 callersFunctionmain

()

dqn/categorical_dqn(C51)/infer.py:22

↓ 1 callersFunctionmain

()

dqn/categorical_dqn(C51)/test_env.py:4

↓ 1 callersFunctionmain

()

actor_critic/ac.py:81

↓ 1 callersFunctionpolicy_evaluation

(env, policy, gamma = 1.0)

policy_iteration/policy_iteration.py:32

↓ 1 callersFunctionpolicy_extraction

(env, v, gamma = 1.0)

value_iteration/value_iteration.py:32

↓ 1 callersFunctionpolicy_improvement

(env, v, gamma = 1.0)

policy_iteration/policy_iteration.py:46

↓ 1 callersFunctionpolicy_iteration

Policy-Iteration algorithm

policy_iteration/policy_iteration.py:58

↓ 1 callersFunctionpreprocess

(observation)

dqn/dqn_noisy_networks/infer.py:12

↓ 1 callersFunctionpreprocess

(observation)

dqn/double_dqn/infer.py:12

↓ 1 callersFunctionpreprocess

(observation)

dqn/nstep_dqn/infer.py:12

↓ 1 callersFunctionpreprocess

(observation)

dqn/dueling_dqn/infer.py:12

↓ 1 callersFunctionpreprocess

(observation)

dqn/categorical_dqn(C51)/infer.py:12

↓ 1 callersFunctionqlearning_td0

(env, actions=['UP', 'DOWN', 'RIGHT', 'LEFT'], num_states=4*12, num_

qlearning/qlearning_td0.py:10

↓ 1 callersFunctionqlearning_tdn

(env, n_step=4, actions=['UP', 'DOWN', 'RIGHT', 'LEFT'], num_states=4*12,

qlearning/qlearning_tdn.py:10

↓ 1 callersFunctionrun_episode

(env, policy, gamma = 1.0, render = False)

value_iteration/value_iteration.py:4

↓ 1 callersFunctionrun_episode

(env, policy, gamma = 1.0, render = False)

policy_iteration/policy_iteration.py:4

↓ 1 callersMethodsample

(self, batch_size)

ddpg/replay_memory.py:14

↓ 1 callersMethodsample

(self, batch_size)

td3/replay_memory.py:14

↓ 1 callersMethodsample

(self, batch_size)

dqn/dqn_noisy_networks/replay_memory.py:14

↓ 1 callersMethodsample

(self, batch_size)

dqn/double_dqn/replay_memory.py:14

↓ 1 callersMethodsample

(self, batch_size)

dqn/nstep_dqn/replay_memory.py:14

↓ 1 callersMethodsample

(self, batch_size)

dqn/dueling_dqn/replay_memory.py:14

↓ 1 callersMethodsample

(self, batch_size)

dqn/categorical_dqn(C51)/replay_memory.py:14

↓ 1 callersFunctionsarsa_mc

(env, actions=['UP', 'DOWN', 'RIGHT', 'LEFT'], num_states=4*12, num_

sarsa/sarsa_mc.py:10

↓ 1 callersFunctionsarsa_td0

(env, actions=['UP', 'DOWN', 'RIGHT', 'LEFT'], num_states=4*12, num_

sarsa/sarsa_td0.py:10

↓ 1 callersFunctionsarsa_tdn

(env, n_step=4, actions=['UP', 'DOWN', 'RIGHT', 'LEFT'], num_states=4*12,

sarsa/sarsa_tdn.py:10

↓ 1 callersMethodselect_action

(self, state)

sac/model.py:28

↓ 1 callersMethodselect_action

(self, state)

ddpg/model.py:21

↓ 1 callersMethodselect_action

(self, state)

td3/model.py:21

↓ 1 callersMethodselect_action

(self, inputs)

policy_gradient/policy_gradient_with_baseline_with_w.py:36

↓ 1 callersMethodselect_action

(self, inputs)

policy_gradient/policy_gradient_with_baseline.py:34

↓ 1 callersMethodselect_action

(self, inputs)

policy_gradient/reinforce.py:34

↓ 1 callersMethodselect_action

(self, inputs)

policy_gradient/policy_gradient_basic.py:34

↓ 1 callersMethodselect_action

(self, inputs)

actor_critic/ac.py:36

↓ 1 callersFunctionshowScore

displays score in center of screen

dqn/dqn_noisy_networks/flappy_bird/wrapped_flappy_bird.py:173

↓ 1 callersFunctionshowScore

displays score in center of screen

dqn/double_dqn/flappy_bird/wrapped_flappy_bird.py:173

↓ 1 callersFunctionshowScore

displays score in center of screen

dqn/nstep_dqn/flappy_bird/wrapped_flappy_bird.py:173

↓ 1 callersFunctionshowScore

displays score in center of screen

dqn/dueling_dqn/flappy_bird/wrapped_flappy_bird.py:173

↓ 1 callersFunctionshowScore

displays score in center of screen

dqn/categorical_dqn(C51)/flappy_bird/wrapped_flappy_bird.py:173

↓ 1 callersFunctiontest_episode

(env, policy)

value_iteration/value_iteration.py:19

↓ 1 callersFunctiontest_episode

(env, policy)

policy_iteration/policy_iteration.py:19

↓ 1 callersFunctiontrain

()

sac/train.py:45

↓ 1 callersFunctiontrain

()

ddpg/train.py:42

↓ 1 callersFunctiontrain

()

td3/train.py:50

↓ 1 callersFunctiontrain

()

qlearning/qlearning_tdn.py:55

↓ 1 callersFunctiontrain

()

qlearning/qlearning_td0.py:47

↓ 1 callersFunctiontrain

()

dqn/dqn_noisy_networks/train.py:66

↓ 1 callersFunctiontrain

()

dqn/double_dqn/train.py:66

↓ 1 callersFunctiontrain

()

dqn/nstep_dqn/train.py:68

↓ 1 callersFunctiontrain

()

dqn/dueling_dqn/train.py:66

↓ 1 callersFunctiontrain

()

dqn/categorical_dqn(C51)/train.py:134

↓ 1 callersFunctiontrain

()

sarsa/sarsa_mc.py:55

↓ 1 callersFunctiontrain

()

sarsa/sarsa_td0.py:49

↓ 1 callersFunctiontrain

()

sarsa/sarsa_tdn.py:57

↓ 1 callersFunctionvalue_iteration

(env, gamma = 1.0)

value_iteration/value_iteration.py:43

Method__init__

(self, max_size)

sac/replay_memory.py:8

Method__init__

(self, state_dim, action_dim, max_action, log_min_std=-20, log_max_std=2)

ddpg/replay_memory.py:8

Method__init__

(self, state_dim, action_dim)

ddpg/model.py:26

Method__init__

(self, max_size)

td3/replay_memory.py:8

Method__init__

(self, state_dim, action_dim)

td3/model.py:26

Method__init__

(self)

policy_gradient/policy_gradient_with_baseline_with_w.py:20

Method__init__

(self)

policy_gradient/policy_gradient_with_baseline.py:20

Method__init__

(self)

policy_gradient/reinforce.py:20

Method__init__

(self)

policy_gradient/policy_gradient_basic.py:20

Method__init__

(self)

qlearning/cliffwalk/cliffwalk.py:16

Method__init__

(self, max_size)

dqn/dqn_noisy_networks/replay_memory.py:8

Method__init__

(self, in_features, out_features, sigma_zero=0.4, bias=True)

dqn/dqn_noisy_networks/model.py:8

Method__init__

(self, max_size)

dqn/double_dqn/replay_memory.py:8

Method__init__

(self, num_inputs, num_actions)

dqn/double_dqn/model.py:5

Method__init__

(self, max_size)

dqn/nstep_dqn/replay_memory.py:8

Method__init__

(self, num_inputs, num_actions)

dqn/nstep_dqn/model.py:5

Method__init__

(self, max_size)

dqn/dueling_dqn/replay_memory.py:8

Method__init__

(self, num_inputs, num_actions)

dqn/dueling_dqn/model.py:5

Method__init__

(self, max_size)

dqn/categorical_dqn(C51)/replay_memory.py:8

Method__init__

(self, num_inputs, num_actions, atoms=51)

dqn/categorical_dqn(C51)/model.py:5

Method__init__

(self)

actor_critic/ac.py:20

Method__init__

(self)

sarsa/cliffwalk/cliffwalk.py:16

Method__len__

(self)

sac/replay_memory.py:33

Method__len__

(self)

ddpg/replay_memory.py:33

Method__len__

(self)

td3/replay_memory.py:33

Method__len__

(self)

dqn/dqn_noisy_networks/replay_memory.py:33

← previous next →101–200 of 219, ranked by callers