Index

_

__call__() (tianshou.data.advantage_estimation.ddpg_return method) (tianshou.data.advantage_estimation.nstep_q_return method) (tianshou.data.advantage_estimation.nstep_return method)

A

act() (tianshou.core.policy.deterministic.Deterministic method) (tianshou.core.policy.distributional.Distributional method) (tianshou.core.policy.dqn.DQN method) act_test() (tianshou.core.policy.deterministic.Deterministic method) (tianshou.core.policy.distributional.Distributional method) (tianshou.core.policy.dqn.DQN method)

ActionValue (class in tianshou.core.value_function.action_value) add() (tianshou.data.data_buffer.batch_set.BatchSet method) (tianshou.data.data_buffer.vanilla.VanillaReplayBuffer method)

B

BatchSet (class in tianshou.data.data_buffer.batch_set)

C

clear() (tianshou.data.data_buffer.batch_set.BatchSet method) (tianshou.data.data_buffer.vanilla.VanillaReplayBuffer method)

collect() (tianshou.data.data_collector.DataCollector method)

D

DataCollector (class in tianshou.data.data_collector) ddpg_return (class in tianshou.data.advantage_estimation) denoise_action() (tianshou.data.data_collector.DataCollector method) Deterministic (class in tianshou.core.policy.deterministic)

Distributional (class in tianshou.core.policy.distributional) DPG() (in module tianshou.core.opt) DQN (class in tianshou.core.policy.dqn) (class in tianshou.core.value_function.action_value)

E

eval_action() (tianshou.core.policy.deterministic.Deterministic method) eval_action_old() (tianshou.core.policy.deterministic.Deterministic method) eval_value() (tianshou.core.value_function.action_value.ActionValue method) (tianshou.core.value_function.action_value.DQN method) (tianshou.core.value_function.state_value.StateValue method)

eval_value_all_actions() (tianshou.core.value_function.action_value.DQN method) eval_value_all_actions_old() (tianshou.core.value_function.action_value.DQN method) eval_value_old() (tianshou.core.value_function.action_value.ActionValue method) (tianshou.core.value_function.action_value.DQN method) (tianshou.core.value_function.state_value.StateValue method)

F

full_return() (in module tianshou.data.advantage_estimation)

G

GaussianWhiteNoiseProcess (class in tianshou.core.random)

get_soft_update_op() (in module tianshou.core.utils)

N

next_batch() (tianshou.data.data_collector.DataCollector method)

nstep_q_return (class in tianshou.data.advantage_estimation) nstep_return (class in tianshou.data.advantage_estimation)

O

OrnsteinUhlenbeckProcess (class in tianshou.core.random)

P

ppo_clip() (in module tianshou.core.losses)

Q

q_net (tianshou.core.policy.dqn.DQN attribute)

R

REINFORCE() (in module tianshou.core.losses) remove() (tianshou.data.data_buffer.vanilla.VanillaReplayBuffer method) reset() (tianshou.core.policy.deterministic.Deterministic method) (tianshou.core.policy.distributional.Distributional method) (tianshou.core.policy.dqn.DQN method)

reset_states() (tianshou.core.random.OrnsteinUhlenbeckProcess method)

S

sample() (tianshou.core.random.GaussianWhiteNoiseProcess method) (tianshou.core.random.OrnsteinUhlenbeckProcess method) (tianshou.data.data_buffer.batch_set.BatchSet method) (tianshou.data.data_buffer.vanilla.VanillaReplayBuffer method) set_epsilon_test() (tianshou.core.policy.dqn.DQN method) set_epsilon_train() (tianshou.core.policy.dqn.DQN method) StateValue (class in tianshou.core.value_function.state_value)

statistics() (tianshou.data.data_buffer.batch_set.BatchSet method) sync_weights() (tianshou.core.policy.deterministic.Deterministic method) (tianshou.core.policy.distributional.Distributional method) (tianshou.core.policy.dqn.DQN method) (tianshou.core.value_function.action_value.ActionValue method) (tianshou.core.value_function.action_value.DQN method) (tianshou.core.value_function.state_value.StateValue method)

T

test_policy_in_env() (in module tianshou.data.tester) tianshou.core.losses (module) tianshou.core.opt (module) tianshou.core.policy (module) tianshou.core.policy.base (module) tianshou.core.policy.deterministic (module) tianshou.core.policy.distributional (module) tianshou.core.policy.dqn (module) tianshou.core.random (module) tianshou.core.utils (module) tianshou.core.value_function (module) tianshou.core.value_function.action_value (module) tianshou.core.value_function.base (module)

tianshou.core.value_function.state_value (module) tianshou.data.advantage_estimation (module) tianshou.data.data_buffer (module) tianshou.data.data_buffer.base (module) tianshou.data.data_buffer.batch_set (module) tianshou.data.data_buffer.replay_buffer_base (module) tianshou.data.data_buffer.vanilla (module) tianshou.data.data_collector (module) tianshou.data.tester (module) trainable_variables (tianshou.core.policy.deterministic.Deterministic attribute) (tianshou.core.policy.distributional.Distributional attribute) (tianshou.core.value_function.action_value.ActionValue attribute) (tianshou.core.value_function.action_value.DQN attribute) (tianshou.core.value_function.state_value.StateValue attribute)

V

value_mse() (in module tianshou.core.losses) value_tensor (tianshou.core.value_function.action_value.ActionValue attribute) (tianshou.core.value_function.action_value.DQN attribute) (tianshou.core.value_function.state_value.StateValue attribute)

value_tensor_all_actions (tianshou.core.value_function.action_value.DQN attribute) VanillaReplayBuffer (class in tianshou.data.data_buffer.vanilla)