索引 A | B | C | D | E | F | G | H | I | J | L | M | N | O | P | Q | R | S | T | U | V | W | Z | 模 A A2CAgent (openrl.runners.common 中的类) (openrl.runners.common.a2c_agent 中的类) A2CAlgorithm (openrl.algorithms.a2c 中的类) A2CNet (openrl.modules.common 中的类) (openrl.modules.common.a2c_net 中的类) act() (openrl.modules.bc_module.BCModule 方法) (openrl.modules.common.ddpg_net.DDPGNet 方法) (openrl.modules.common.DDPGNet 方法) (openrl.modules.common.dqn_net.DQNNet 方法) (openrl.modules.common.DQNNet 方法) (openrl.modules.common.ppo_net.PPONet 方法) (openrl.modules.common.PPONet 方法) (openrl.modules.common.sac_net.SACNet 方法) (openrl.modules.common.SACNet 方法) (openrl.modules.common.vdn_net.VDNNet 方法) (openrl.modules.common.VDNNet 方法) (openrl.modules.ddpg_module.DDPGModule 方法) (openrl.modules.dqn_module.DQNModule 方法) (openrl.modules.ppo_module.PPOModule 方法) (openrl.modules.rl_module.RLModule 方法) (openrl.modules.sac_module.SACModule 方法) (openrl.modules.vdn_module.VDNModule 方法) (openrl.runners.common.ddpg_agent.DDPGAgent 方法) (openrl.runners.common.DDPGAgent 方法) (openrl.runners.common.dqn_agent.DQNAgent 方法) (openrl.runners.common.DQNAgent 方法) (openrl.runners.common.ppo_agent.PPOAgent 方法) (openrl.runners.common.PPOAgent 方法) (openrl.runners.common.rl_agent.RLAgent 方法) (openrl.runners.common.sac_agent.SACAgent 方法) (openrl.runners.common.SACAgent 方法) (openrl.runners.common.vdn_agent.VDNAgent 方法) (openrl.runners.common.VDNAgent 方法) (openrl.selfplay.opponents.base_opponent.BaseOpponent 方法) (openrl.selfplay.opponents.jidi_opponent.JiDiOpponent 方法) (openrl.selfplay.opponents.network_opponent.NetworkOpponent 方法) (openrl.selfplay.opponents.random_opponent.RandomOpponent 方法) (openrl.utils.type_aliases.AgentActor 方法) Action (openrl.envs.mpe.core 中的类) action_space (openrl.envs.toy_envs.BitFlippingEnv 属性) (openrl.envs.toy_envs.IdentityEnv 属性) (openrl.envs.toy_envs.IdentityEnvcontinuous 属性) (openrl.envs.vec_env.base_venv.BaseVecEnv 属性) (openrl.envs.vec_env.BaseVecEnv 属性) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) (openrl.selfplay.opponents.opponent_env.BaseOpponentEnv property) (openrl.selfplay.wrappers.base_multiplayer_wrapper.BaseMultiPlayerWrapper property) actions() (openrl.envs.vec_env.wrappers.base_wrapper.VectorActionWrapper 方法) ACTLayer (openrl.modules.networks.utils.act 中的类) ActorNetwork (openrl.modules.networks.ddpg_network 中的类) add_attr() (openrl.envs.mpe.rendering.Geom 方法) add_battle_result() (openrl.selfplay.selfplay_api.selfplay_client.SelfPlayClient 方法) add_geom() (openrl.envs.mpe.rendering.Viewer 方法) add_onetime() (openrl.envs.mpe.rendering.Viewer 方法) add_opponent() (openrl.selfplay.selfplay_api.selfplay_client.SelfPlayClient 方法) AddBias (openrl.modules.networks.utils.distributions 中的类) AddStep (openrl.envs.wrappers.extra_wrappers 中的类) after_update() (openrl.buffers.normal_buffer.NormalReplayBuffer 方法) (openrl.buffers.NormalReplayBuffer 方法) (openrl.buffers.offpolicy_replay_data.OffPolicyReplayData 方法) (openrl.buffers.replay_data.ReplayData 方法) Agent (openrl.envs.mpe.core 中的类) agent (openrl.utils.callbacks.callbacks.BaseCallback 属性) agent_num (openrl.envs.mpe.multiagent_env.MultiAgentEnv property) (openrl.envs.vec_env.base_venv.BaseVecEnv property) (openrl.envs.vec_env.BaseVecEnv property) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) (openrl.envs.wrappers.base_wrapper.BaseWrapper property) (openrl.envs.wrappers.BaseWrapper property) (openrl.envs.wrappers.multiagent_wrapper.Single2MultiAgentWrapper property) (openrl.envs.wrappers.Single2MultiAgentWrapper property) (openrl.selfplay.opponents.opponent_env.BaseOpponentEnv property) AgentActor (openrl.utils.type_aliases 中的类) AgentState (openrl.envs.mpe.core 中的类) all_batch() (openrl.buffers.utils.obs_data.ObsData 方法) append() (openrl.envs.vec_env.vec_info.base_vec_info.BaseVecInfo 方法) (openrl.envs.vec_env.vec_info.nlp_vec_info.NLPVecInfo 方法) (openrl.envs.vec_env.vec_info.simple_vec_info.SimpleVecInfo 方法) (openrl.utils.custom_data_structure.ListDict 方法) apply_action_force() (openrl.envs.mpe.core.World 方法) apply_environment_force() (openrl.envs.mpe.core.World 方法) assign_agent_colors() (openrl.envs.mpe.core.World 方法) assign_landmark_colors() (openrl.envs.mpe.core.World 方法) AsyncVectorEnv (openrl.envs.vec_env 中的类) (openrl.envs.vec_env.async_venv 中的类) Attr (openrl.envs.mpe.rendering 中的类) auto_register() (openrl.envs.vec_env.vec_info.VecInfoFactory 静态方法) (openrl.rewards.RewardFactory 静态方法) AutoReset (openrl.envs.wrappers 中的类) (openrl.envs.wrappers.extra_wrappers 中的类) B BaseAgent (openrl.runners.common.base_agent 中的类) BaseAlgorithm (openrl.algorithms.base_algorithm 中的类) BaseCallback (openrl.utils.callbacks.callbacks 中的类) BaseConnectEnv (openrl.envs.connect_env.base_connect_env 中的类) BaseDriver (openrl.drivers.base_driver 中的类) BaseModule (openrl.modules.base_module 中的类) BaseMultiPlayerWrapper (openrl.selfplay.wrappers.base_multiplayer_wrapper 中的类) BaseNet (openrl.modules.common 中的类) (openrl.modules.common.base_net 中的类) BaseObservationWrapper (openrl.envs.wrappers 中的类) (openrl.envs.wrappers.base_wrapper 中的类) BaseOpponent (openrl.selfplay.opponents.base_opponent 中的类) BaseOpponentEnv (openrl.selfplay.opponents.opponent_env 中的类) BasePolicyNetwork (openrl.modules.networks.base_policy_network 中的类) BaseReward (openrl.rewards.base_reward 中的类) BaseRewardWrapper (openrl.envs.wrappers 中的类) (openrl.envs.wrappers.base_wrapper 中的类) BaseSampleStrategy (openrl.selfplay.sample_strategy.base_sample_strategy 中的类) BaseScenario (openrl.envs.mpe.scenario 中的类) BaseSelfplayCallback (openrl.selfplay.callbacks.base_callback 中的类) BaseValueNetwork (openrl.modules.networks.base_value_network 中的类) BaseValuePolicyNetwork (openrl.modules.networks.base_value_policy_network 中的类) BaseVecEnv (openrl.envs.vec_env 中的类) (openrl.envs.vec_env.base_venv 中的类) BaseVecInfo (openrl.envs.vec_env.vec_info.base_vec_info 中的类) BaseWrapper (openrl.envs.wrappers 中的类) (openrl.envs.wrappers.base_wrapper 中的类) batch_rewards() (openrl.envs.vec_env.RewardWrapper 方法) (openrl.envs.vec_env.wrappers.reward_wrapper.RewardWrapper 方法) (openrl.rewards.base_reward.BaseReward 方法) bc_update() (openrl.algorithms.behavior_cloning.BCAlgorithm 方法) BCAgent (openrl.runners.common 中的类) (openrl.runners.common.bc_agent 中的类) BCAlgorithm (openrl.algorithms.behavior_cloning 中的类) BCModule (openrl.modules.bc_module 中的类) BCNet (openrl.modules.common 中的类) (openrl.modules.common.bc_net 中的类) benchmark_data() (openrl.envs.mpe.scenarios.simple_spread.Scenario 方法) Bernoulli (openrl.modules.networks.utils.distributions 中的类) BitFlippingEnv (openrl.envs.toy_envs 中的类) (openrl.envs.toy_envs.bit_flipping_env 中的类) build_envs() (在 openrl.envs.common 模块中) (在 openrl.envs.common.build_envs 模块中) C cal_learner_number() (openrl.supports.opengpu.manager.RemoteGPUManager 方法) cal_value_loss() (openrl.algorithms.ddpg.DDPGAlgorithm 方法) (openrl.algorithms.ppo.PPOAlgorithm 方法) (openrl.algorithms.sac.SACAlgorithm 方法) (openrl.algorithms.vdn.VDNAlgorithm 方法) calc_flatten_size() (openrl.modules.networks.utils.cnn.CNNLayer 方法) calculate_distances() (openrl.envs.mpe.core.World 方法) call() (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.BaseVecEnv 方法) (openrl.envs.vec_env.sync_venv.SyncVectorEnv 方法) (openrl.envs.vec_env.SyncVectorEnv 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper 方法) call_fetch() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.BaseVecEnv 方法) call_send() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.BaseVecEnv 方法) CallbackFactory (openrl.utils.callbacks 中的类) (openrl.utils.callbacks.callbacks_factory 中的类) CallbackList (openrl.utils.callbacks.callbacks 中的类) Categorical (openrl.modules.networks.utils.distributions 中的类) CatSelfEmbedding (openrl.modules.networks.utils.attention 中的类) chat() (openrl.runners.common.Chat6BAgent 方法) (openrl.runners.common.chat_agent.Chat6BAgent 方法) (openrl.runners.common.chat_agent.ChatAgent 方法) (openrl.runners.common.ChatAgent 方法) Chat6BAgent (openrl.runners.common 中的类) (openrl.runners.common.chat_agent 中的类) ChatAgent (openrl.runners.common 中的类) (openrl.runners.common.chat_agent 中的类) check() (openrl.selfplay.opponents.opponent_template.OpponentTemplate 方法) (在 openrl.utils.util 模块中) check_gpus() (openrl.supports.opengpu.manager.RemoteGPUManager 方法) check_if_finish() (openrl.envs.connect_env.base_connect_env.BaseConnectEnv 方法) check_if_win() (在 openrl.envs.connect_env.utils 模块中) check_opponent_template() (在 openrl.selfplay.opponents.utils 模块中) check_v2() (在 openrl.utils.util 模块中) CheckpointCallback (openrl.utils.callbacks.checkpoint_callback 中的类) ClipRewardEnv (openrl.envs.wrappers.atari_wrappers 中的类) close() (openrl.envs.mpe.rendering.Viewer 方法) (openrl.envs.offline.offline_env.OfflineEnv 方法) (openrl.envs.toy_envs.bit_flipping_env.BitFlippingEnv 方法) (openrl.envs.toy_envs.BitFlippingEnv 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.BaseVecEnv 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper 方法) (openrl.envs.vec_env.wrappers.gen_data.GenDataWrapper 方法) (openrl.envs.vec_env.wrappers.gen_data.GenDataWrapper_v1 方法) (openrl.envs.wrappers.extra_wrappers.GIFWrapper 方法) (openrl.envs.wrappers.GIFWrapper 方法) (openrl.selfplay.wrappers.base_multiplayer_wrapper.BaseMultiPlayerWrapper 方法) (openrl.utils.logger.Logger 方法) close_extras() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.BaseVecEnv 方法) (openrl.envs.vec_env.sync_venv.SyncVectorEnv 方法) (openrl.envs.vec_env.SyncVectorEnv 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper 方法) closed (openrl.envs.vec_env.base_venv.BaseVecEnv 属性) (openrl.envs.vec_env.BaseVecEnv 属性) CNNBase (openrl.modules.networks.utils.cnn 中的类) CNNLayer (openrl.modules.networks.utils.cnn 中的类) Color (openrl.envs.mpe.rendering 中的类) combine() (openrl.modules.networks.utils.running_mean_std.RunningMeanStd 方法) compute_grad_pen() (openrl.modules.networks.gail_discriminator.Discriminator 方法) compute_returns() (openrl.buffers.normal_buffer.NormalReplayBuffer 方法) (openrl.buffers.NormalReplayBuffer 方法) (openrl.buffers.offpolicy_replay_data.OffPolicyReplayData 方法) (openrl.buffers.replay_data.ReplayData 方法) compute_reward() (openrl.envs.toy_envs.bit_flipping_env.BitFlippingEnv 方法) (openrl.envs.toy_envs.BitFlippingEnv 方法) concatenate() (在 openrl.envs.vec_env.utils.numpy_utils 模块中) Connect3Env (openrl.envs.connect_env.connect3_env 中的类) Connect4Env (openrl.envs.connect_env.connect4_env 中的类) construct_loss_list() (openrl.algorithms.behavior_cloning.BCAlgorithm 方法) (openrl.algorithms.mat.MATAlgorithm 方法) (openrl.algorithms.ppo.PPOAlgorithm 方法) construct_obs() (openrl.envs.mpe.multiagent_env.MultiAgentEnv 静态方法) contains() (openrl.envs.mpe.multi_discrete.MultiDiscrete 方法) continuous_autoregreesive_act() (在 openrl.modules.networks.utils.transformer_act 模块中) continuous_parallel_act() (在 openrl.modules.networks.utils.transformer_act 模块中) convert_distributed_model() (openrl.modules.base_module.BaseModule 方法) convert_if_needed() (openrl.envs.toy_envs.bit_flipping_env.BitFlippingEnv 方法) (openrl.envs.toy_envs.BitFlippingEnv 方法) convert_to_bit_vector() (openrl.envs.toy_envs.bit_flipping_env.BitFlippingEnv 方法) (openrl.envs.toy_envs.BitFlippingEnv 方法) convert_to_done_step_api() (在 openrl.envs.wrappers.extra_wrappers 模块中) ConvertCallback (openrl.utils.callbacks.callbacks 中的类) ConvertEmptyBoxWrapper (openrl.envs.wrappers.extra_wrappers 中的类) CONVLayer (openrl.modules.networks.utils.mlp 中的类) copy() (openrl.modules.networks.utils.running_mean_std.RunningMeanStd 方法) copy_files() (在 openrl.utils.file_tool 模块中) create_config_parser() (在 openrl.configs.config 模块中) create_empty_array() (在 openrl.envs.vec_env.utils.numpy_utils 模块中) create_shared_memory() (在 openrl.envs.vec_env.utils.share_memory 模块中) CriticNetwork (openrl.modules.networks.ddpg_network 中的类) CriticNetwork_v0 (openrl.modules.networks.ddpg_network 中的类) D data_abs_path() (在 openrl.supports.opendata.utils.opendata_utils 模块中) data_server_wrapper() (在 openrl.supports.opendata.utils.opendata_utils 模块中) ddpg_update() (openrl.algorithms.ddpg.DDPGAlgorithm 方法) DDPGAgent (openrl.runners.common 中的类) (openrl.runners.common.ddpg_agent 中的类) DDPGAlgorithm (openrl.algorithms.ddpg 中的类) DDPGModule (openrl.modules.ddpg_module 中的类) DDPGNet (openrl.modules.common 中的类) (openrl.modules.common.ddpg_net 中的类) deal_render() (openrl.envs.mpe.multiagent_env.MultiAgentEnv 方法) debiased_mean_var() (openrl.modules.networks.utils.popart.PopArt 方法) DecodeBlock (openrl.modules.networks.MAT_network 中的类) Decoder (openrl.modules.networks.MAT_network 中的类) DEFAULT (openrl.envs.vec_env.async_venv.AsyncState 属性) denormalize() (openrl.modules.networks.utils.popart.PopArt 方法) (openrl.modules.utils.valuenorm.ValueNorm 方法) DiagGaussian (openrl.modules.networks.utils.distributions 中的类) DictWrapper (openrl.envs.wrappers 中的类) (openrl.envs.wrappers.extra_wrappers 中的类) disable() (openrl.envs.mpe.rendering.Attr 方法) (openrl.envs.mpe.rendering.LineStyle 方法) (openrl.envs.mpe.rendering.Transform 方法) discrete_autoregreesive_act() (在 openrl.modules.networks.utils.transformer_act 模块中) discrete_parallel_act() (在 openrl.modules.networks.utils.transformer_act 模块中) Discriminator (openrl.modules.networks.gail_discriminator 中的类) dqn_update() (openrl.algorithms.dqn.DQNAlgorithm 方法) DQNAgent (openrl.runners.common 中的类) (openrl.runners.common.dqn_agent 中的类) DQNAlgorithm (openrl.algorithms.dqn 中的类) DQNModule (openrl.modules.dqn_module 中的类) DQNNet (openrl.modules.common 中的类) (openrl.modules.common.dqn_net 中的类) draw_circle() (openrl.envs.mpe.rendering.Viewer 方法) draw_line() (openrl.envs.mpe.rendering.Viewer 方法) draw_polygon() (openrl.envs.mpe.rendering.Viewer 方法) draw_polyline() (openrl.envs.mpe.rendering.Viewer 方法) dump() (openrl.envs.vec_env.wrappers.gen_data.TrajectoryData 方法) E Embedding (openrl.modules.networks.utils.attention 中的类) enable() (openrl.envs.mpe.rendering.Attr 方法) (openrl.envs.mpe.rendering.Color 方法) (openrl.envs.mpe.rendering.LineStyle 方法) (openrl.envs.mpe.rendering.LineWidth 方法) (openrl.envs.mpe.rendering.Transform 方法) EncodeBlock (openrl.modules.networks.MAT_network 中的类) Encoder (openrl.modules.networks.MAT_network 中的类) (openrl.modules.networks.utils.attention 中的类) EncoderLayer (openrl.modules.networks.utils.attention 中的类) entities (openrl.envs.mpe.core.World property) Entity (openrl.envs.mpe.core 中的类) EntityState (openrl.envs.mpe.core 中的类) entropy() (openrl.modules.networks.utils.distributions.FixedBernoulli 方法) (openrl.modules.networks.utils.distributions.FixedNormal 方法) env_is_wrapped() (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.BaseVecEnv 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper 方法) env_name (openrl.envs.offline.offline_env.OfflineEnv 属性) (openrl.envs.vec_env.async_venv.AsyncVectorEnv property) (openrl.envs.vec_env.AsyncVectorEnv property) (openrl.envs.vec_env.base_venv.BaseVecEnv property) (openrl.envs.vec_env.BaseVecEnv property) (openrl.envs.vec_env.sync_venv.SyncVectorEnv property) (openrl.envs.vec_env.SyncVectorEnv property) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) (openrl.envs.wrappers.base_wrapper.BaseWrapper property) (openrl.envs.wrappers.BaseWrapper property) EnvSpec (openrl.envs.mpe.multiagent_env 中的类) EpisodicLifeEnv (openrl.envs.wrappers.atari_wrappers 中的类) EPS_RewardInfo (openrl.envs.vec_env.vec_info.episode_rewards_info 中的类) eval_actions() (openrl.modules.networks.base_value_policy_network.BaseValuePolicyNetwork 方法) (openrl.modules.networks.MAT_network.MultiAgentTransformer 方法) (openrl.modules.networks.policy_network.PolicyNetwork 方法) (openrl.modules.networks.policy_value_network.PolicyValueNetwork 方法) (openrl.modules.networks.vdn_network.VDNNetwork 方法) eval_actions_target() (openrl.modules.networks.vdn_network.VDNNetwork 方法) eval_values() (openrl.modules.networks.vdn_network.VDNNetwork 方法) EvalCallback (openrl.utils.callbacks.eval_callback 中的类) evaluate() (openrl.modules.networks.sac_network.SACActorNetwork 方法) evaluate_actions() (openrl.modules.bc_module.BCModule 方法) (openrl.modules.ddpg_module.DDPGModule 方法) (openrl.modules.dqn_module.DQNModule 方法) (openrl.modules.networks.utils.act.ACTLayer 方法) (openrl.modules.ppo_module.PPOModule 方法) (openrl.modules.rl_module.RLModule 方法) (openrl.modules.sac_module.SACModule 方法) (openrl.modules.vdn_module.VDNModule 方法) evaluate_actor_loss() (openrl.modules.ddpg_module.DDPGModule 方法) (openrl.modules.sac_module.SACModule 方法) evaluate_critic_loss() (openrl.modules.ddpg_module.DDPGModule 方法) evaluate_policy() (在 openrl.utils.evaluation 模块中) EventCallback (openrl.utils.callbacks.callbacks 中的类) EveryNTimesteps (openrl.utils.callbacks.callbacks 中的类) exec_func() (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.BaseVecEnv 方法) (openrl.envs.vec_env.sync_venv.SyncVectorEnv 方法) (openrl.envs.vec_env.SyncVectorEnv 方法) exec_func_fetch() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.BaseVecEnv 方法) exec_func_send() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.BaseVecEnv 方法) ExpertDataset (openrl.datasets.expert_dataset 中的类) F feed_forward_critic_obs_generator() (openrl.buffers.normal_buffer.NormalReplayBuffer 方法) (openrl.buffers.NormalReplayBuffer 方法) (openrl.buffers.replay_data.ReplayData 方法) feed_forward_generator() (openrl.buffers.normal_buffer.NormalReplayBuffer 方法) (openrl.buffers.NormalReplayBuffer 方法) (openrl.buffers.offpolicy_replay_data.OffPolicyReplayData 方法) (openrl.buffers.replay_data.ReplayData 方法) feed_forward_generator_transformer() (openrl.buffers.replay_data.ReplayData 方法) FeedForward (openrl.modules.networks.utils.attention 中的类) FilledPolygon (openrl.envs.mpe.rendering 中的类) FireResetEnv (openrl.envs.wrappers.atari_wrappers 中的类) FixedBernoulli (openrl.modules.networks.utils.distributions 中的类) FixedCategorical (openrl.modules.networks.utils.distributions 中的类) FixedNormal (openrl.modules.networks.utils.distributions 中的类) Flatten (openrl.modules.networks.utils.cnn 中的类) (openrl.modules.networks.utils.mix 中的类) flatten() (openrl.buffers.utils.obs_data.ObsData 方法) (在 openrl.envs.wrappers.flatten 模块中) FlattenObservation (openrl.envs.wrappers 中的类) (openrl.envs.wrappers.extra_wrappers 中的类) format_obs() (openrl.envs.vec_env.sync_venv.SyncVectorEnv 方法) (openrl.envs.vec_env.SyncVectorEnv 方法) forward() (openrl.modules.networks.base_value_network.BaseValueNetwork 方法) (openrl.modules.networks.base_value_policy_network.BaseValuePolicyNetwork 方法) (openrl.modules.networks.ddpg_network.ActorNetwork 方法) (openrl.modules.networks.ddpg_network.CriticNetwork 方法) (openrl.modules.networks.ddpg_network.CriticNetwork_v0 方法) (openrl.modules.networks.MAT_network.DecodeBlock 方法) (openrl.modules.networks.MAT_network.Decoder 方法) (openrl.modules.networks.MAT_network.EncodeBlock 方法) (openrl.modules.networks.MAT_network.Encoder 方法) (openrl.modules.networks.MAT_network.SelfAttention 方法) (openrl.modules.networks.policy_network.PolicyNetwork 方法) (openrl.modules.networks.q_network.QNetwork 方法) (openrl.modules.networks.sac_network.SACActorNetwork 方法) (openrl.modules.networks.utils.act.ACTLayer 方法) (openrl.modules.networks.utils.attention.CatSelfEmbedding 方法) (openrl.modules.networks.utils.attention.Embedding 方法) (openrl.modules.networks.utils.attention.Encoder 方法) (openrl.modules.networks.utils.attention.EncoderLayer 方法) (openrl.modules.networks.utils.attention.FeedForward 方法) (openrl.modules.networks.utils.attention.MultiHeadAttention 方法) (openrl.modules.networks.utils.cnn.CNNBase 方法) (openrl.modules.networks.utils.cnn.CNNLayer 方法) (openrl.modules.networks.utils.cnn.Flatten 方法) (openrl.modules.networks.utils.distributions.AddBias 方法) (openrl.modules.networks.utils.distributions.Bernoulli 方法) (openrl.modules.networks.utils.distributions.Categorical 方法) (openrl.modules.networks.utils.distributions.DiagGaussian 方法) (openrl.modules.networks.utils.mix.Flatten 方法) (openrl.modules.networks.utils.mix.MIXBase 方法) (openrl.modules.networks.utils.mlp.CONVLayer 方法) (openrl.modules.networks.utils.mlp.MLPBase 方法) (openrl.modules.networks.utils.mlp.MLPLayer 方法) (openrl.modules.networks.utils.popart.PopArt 方法) (openrl.modules.networks.utils.rnn.RNNLayer 方法) (openrl.modules.networks.utils.vdn.VDNBase 方法) (openrl.modules.networks.value_network.ValueNetwork 方法) (openrl.modules.networks.vdn_network.VDNNetwork 方法) forward_original() (openrl.modules.networks.policy_network.PolicyNetwork 方法) FrameSkip (openrl.envs.wrappers.extra_wrappers 中的类) G GAILAgent (openrl.runners.common 中的类) (openrl.runners.common.gail_agent 中的类) GAILAlgorithm (openrl.algorithms.gail 中的类) GAILModule (openrl.modules.gail_module 中的类) GAILNet (openrl.modules.common 中的类) (openrl.modules.common.gail_net 中的类) GAILReward (openrl.rewards.gail_reward 中的类) GenDataWrapper (openrl.envs.vec_env.wrappers.gen_data 中的类) GenDataWrapper_v1 (openrl.envs.vec_env.wrappers.gen_data 中的类) Geom (openrl.envs.mpe.rendering 中的类) get_actions() (openrl.modules.bc_module.BCModule 方法) (openrl.modules.ddpg_module.DDPGModule 方法) (openrl.modules.dqn_module.DQNModule 方法) (openrl.modules.networks.base_value_policy_network.BaseValuePolicyNetwork 方法) (openrl.modules.networks.MAT_network.MultiAgentTransformer 方法) (openrl.modules.networks.policy_value_network.PolicyValueNetwork 方法) (openrl.modules.networks.vdn_network.VDNNetwork 方法) (openrl.modules.ppo_module.PPOModule 方法) (openrl.modules.rl_module.RLModule 方法) (openrl.modules.sac_module.SACModule 方法) (openrl.modules.vdn_module.VDNModule 方法) get_actor_para() (openrl.modules.networks.base_value_policy_network.BaseValuePolicyNetwork 方法) (openrl.modules.networks.MAT_network.MultiAgentTransformer 方法) get_array() (openrl.envs.mpe.rendering.Viewer 方法) get_attr() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.BaseVecEnv 方法) get_batch_data() (openrl.buffers.replay_data.ReplayData 方法) get_buffer_size() (openrl.buffers.offpolicy_buffer.OffPolicyReplayBuffer 方法) (openrl.buffers.OffPolicyReplayBuffer 方法) get_by_index() (openrl.utils.custom_data_structure.ListDict 方法) get_callback() (openrl.utils.callbacks.CallbackFactory 静态方法) (openrl.utils.callbacks.callbacks_factory.CallbackFactory 静态方法) get_callbacks() (openrl.utils.callbacks.CallbackFactory 静态方法) (openrl.utils.callbacks.callbacks_factory.CallbackFactory 静态方法) get_clones() (在 openrl.modules.networks.utils.util 模块中) get_critic_obs() (在 openrl.buffers.utils.util 模块中) get_critic_obs_space() (在 openrl.buffers.utils.util 模块中) get_critic_para() (openrl.modules.networks.base_value_policy_network.BaseValuePolicyNetwork 方法) (openrl.modules.networks.MAT_network.MultiAgentTransformer 方法) get_critic_value_normalizer() (openrl.modules.bc_module.BCModule 方法) (openrl.modules.ddpg_module.DDPGModule 方法) (openrl.modules.dqn_module.DQNModule 方法) (openrl.modules.ppo_module.PPOModule 方法) (openrl.modules.rl_module.RLModule 方法) (openrl.modules.sac_module.SACModule 方法) (openrl.modules.vdn_module.VDNModule 方法) get_data_generator() (openrl.algorithms.behavior_cloning.BCAlgorithm 方法) (openrl.algorithms.mat.MATAlgorithm 方法) (openrl.algorithms.ppo.PPOAlgorithm 方法) get_display() (在 openrl.envs.mpe.rendering 模块中) get_entity_collision_force() (openrl.envs.mpe.core.World 方法) get_env() (openrl.runners.common.base_agent.BaseAgent 方法) get_episode_lengths() (openrl.envs.wrappers.monitor.Monitor 方法) get_episode_rewards() (openrl.envs.wrappers.monitor.Monitor 方法) get_episode_times() (openrl.envs.wrappers.monitor.Monitor 方法) get_gpu() (openrl.supports.opengpu.manager.LocalGPUManager 方法) get_gpu_info() (openrl.supports.opengpu.manager.RemoteGPUManager 方法) get_grad_norm() (在 openrl.modules.utils.util 模块中) get_learner_gpu() (openrl.supports.opengpu.manager.LocalGPUManager 方法) get_learner_gpus() (openrl.supports.opengpu.manager.LocalGPUManager 方法) get_local_GPU_info() (在 openrl.supports.opengpu.gpu_info 模块中) get_model_configs() (openrl.modules.bc_module.BCModule 方法) (openrl.modules.gail_module.GAILModule 方法) (openrl.modules.ppo_module.PPOModule 方法) (openrl.modules.rl_module.RLModule 方法) get_obs() (在 openrl.buffers.utils.util 模块中) get_opponent() (openrl.selfplay.selfplay_api.selfplay_client.SelfPlayClient 方法) (openrl.selfplay.wrappers.opponent_pool_wrapper.OpponentPoolWrapper 方法) get_opponent_action() (openrl.selfplay.wrappers.base_multiplayer_wrapper.BaseMultiPlayerWrapper 方法) (openrl.selfplay.wrappers.human_opponent_wrapper.HumanOpponentWrapper 方法) (openrl.selfplay.wrappers.opponent_pool_wrapper.OpponentPoolWrapper 方法) (openrl.selfplay.wrappers.random_opponent_wrapper.RandomOpponentWrapper 方法) get_opponent_from_info() (在 openrl.selfplay.opponents.utils 模块中) get_opponent_from_path() (在 openrl.selfplay.opponents.utils 模块中) get_opponent_id() (在 openrl.selfplay.opponents.utils 模块中) get_opponent_info() (在 openrl.selfplay.opponents.utils 模块中) get_opponent_path() (openrl.selfplay.callbacks.selfplay_callback.SelfplayCallback 方法) get_policy_obs() (在 openrl.buffers.utils.util 模块中) get_policy_obs_space() (在 openrl.buffers.utils.util 模块中) get_policy_values() (openrl.modules.networks.policy_network.PolicyNetwork 方法) get_probs() (openrl.modules.networks.utils.act.ACTLayer 方法) get_q_values() (openrl.modules.sac_module.SACModule 方法) get_remote_GPU_info() (在 openrl.supports.opengpu.gpu_info 模块中) get_reward_class() (openrl.rewards.RewardFactory 静态方法) get_sample_strategy() (openrl.selfplay.sample_strategy.SampleStrategyFactory 静态方法) get_shape_from_act_space() (在 openrl.buffers.utils.util 模块中) get_shape_from_obs_space_v2() (在 openrl.buffers.utils.util 模块中) get_system_info() (在 openrl.utils.util 模块中) get_total_steps() (openrl.envs.wrappers.monitor.Monitor 方法) get_values() (openrl.modules.bc_module.BCModule 方法) (openrl.modules.ddpg_module.DDPGModule 方法) (openrl.modules.dqn_module.DQNModule 方法) (openrl.modules.networks.base_value_policy_network.BaseValuePolicyNetwork 方法) (openrl.modules.networks.MAT_network.MultiAgentTransformer 方法) (openrl.modules.networks.policy_value_network.PolicyValueNetwork 方法) (openrl.modules.networks.vdn_network.VDNNetwork 方法) (openrl.modules.ppo_module.PPOModule 方法) (openrl.modules.rl_module.RLModule 方法) (openrl.modules.sac_module.SACModule 方法) (openrl.modules.vdn_module.VDNModule 方法) get_vec_info_class() (openrl.envs.vec_env.vec_info.VecInfoFactory 静态方法) get_wall_collision_force() (openrl.envs.mpe.core.World 方法) get_worker_gpu() (openrl.supports.opengpu.manager.LocalGPUManager 方法) GIFWrapper (openrl.envs.wrappers 中的类) (openrl.envs.wrappers.extra_wrappers 中的类) gpu_id (openrl.supports.opengpu.gpu_info.GPUInfo 属性) GPUInfo (openrl.supports.opengpu.gpu_info 中的类) GridWorldEnv (openrl.envs.gridworld.gridworld_env 中的类) GridWorldEnvRandomGoal (openrl.envs.gridworld.gridworld_env 中的类) H has_auto_reset (openrl.envs.wrappers.AutoReset property) (openrl.envs.wrappers.base_wrapper.BaseWrapper property) (openrl.envs.wrappers.BaseWrapper property) (openrl.envs.wrappers.extra_wrappers.AutoReset property) (openrl.envs.wrappers.extra_wrappers.RecordReward property) huber_loss() (在 openrl.modules.utils.util 模块中) HumanOpponentWrapper (openrl.selfplay.wrappers.human_opponent_wrapper 中的类) I id (openrl.envs.mpe.multiagent_env.EnvSpec 属性) IdentityEnv (openrl.envs.toy_envs 中的类) (openrl.envs.toy_envs.identity_env 中的类) IdentityEnvcontinuous (openrl.envs.toy_envs 中的类) (openrl.envs.toy_envs.identity_env 中的类) info() (openrl.envs.mpe.scenario.BaseScenario 方法) (openrl.utils.logger.Logger 方法) init() (在 openrl.modules.networks.utils.util 模块中) init_() (在 openrl.modules.networks.MAT_network 模块中) init_buffer() (openrl.buffers.normal_buffer.NormalReplayBuffer 方法) (openrl.buffers.NormalReplayBuffer 方法) (openrl.buffers.offpolicy_replay_data.OffPolicyReplayData 方法) (openrl.buffers.replay_data.ReplayData 方法) init_callback() (openrl.utils.callbacks.callbacks.BaseCallback 方法) (openrl.utils.callbacks.callbacks.EventCallback 方法) init_empty_dict() (openrl.envs.vec_env.wrappers.gen_data.TrajectoryData 方法) init_rnn_states() (openrl.modules.bc_module.BCModule 静态方法) (openrl.modules.ddpg_module.DDPGModule 静态方法) (openrl.modules.dqn_module.DQNModule 静态方法) (openrl.modules.ppo_module.PPOModule 静态方法) (openrl.modules.sac_module.SACModule 静态方法) (openrl.modules.vdn_module.VDNModule 静态方法) insert() (openrl.buffers.normal_buffer.NormalReplayBuffer 方法) (openrl.buffers.NormalReplayBuffer 方法) (openrl.buffers.offpolicy_buffer.OffPolicyReplayBuffer 方法) (openrl.buffers.offpolicy_replay_data.OffPolicyReplayData 方法) (openrl.buffers.OffPolicyReplayBuffer 方法) (openrl.buffers.replay_data.ReplayData 方法) integrate_state() (openrl.envs.mpe.core.World 方法) is_collision() (openrl.envs.mpe.scenarios.simple_spread.Scenario 方法) is_wrapped() (在 openrl.envs.wrappers.util 模块中) iterate_action() (在 openrl.envs.vec_env.utils.numpy_utils 模块中) J JiDiOpponent (openrl.selfplay.opponents.jidi_opponent 中的类) L Landmark (openrl.envs.mpe.core 中的类) LastOpponent (openrl.selfplay.sample_strategy.last_opponent 中的类) Line (openrl.envs.mpe.rendering 中的类) LineStyle (openrl.envs.mpe.rendering 中的类) LineWidth (openrl.envs.mpe.rendering 中的类) link_files() (在 openrl.utils.file_tool 模块中) ListDict (openrl.utils.custom_data_structure 中的类) load() (openrl.runners.common.base_agent.BaseAgent 方法) (openrl.runners.common.Chat6BAgent 类方法) (openrl.runners.common.chat_agent.Chat6BAgent 类方法) (openrl.runners.common.chat_agent.ChatAgent 类方法) (openrl.runners.common.ChatAgent 类方法) (openrl.runners.common.rl_agent.RLAgent 方法) (openrl.selfplay.opponents.base_opponent.BaseOpponent 方法) (在 openrl.envs.mpe.scenarios 模块中) load_dataset() (在 openrl.supports.opendata.utils.opendata_utils 模块中) load_opponent_from_jidi_path() (在 openrl.selfplay.opponents.utils 模块中) load_opponent_from_path() (在 openrl.selfplay.opponents.utils 模块中) load_opponent_info() (openrl.selfplay.opponents.opponent_template.OpponentTemplate 方法) load_policy() (openrl.modules.common.ddpg_net.DDPGNet 方法) (openrl.modules.common.DDPGNet 方法) (openrl.modules.common.dqn_net.DQNNet 方法) (openrl.modules.common.DQNNet 方法) (openrl.modules.common.ppo_net.PPONet 方法) (openrl.modules.common.PPONet 方法) (openrl.modules.common.sac_net.SACNet 方法) (openrl.modules.common.SACNet 方法) (openrl.modules.common.vdn_net.VDNNet 方法) (openrl.modules.common.VDNNet 方法) (openrl.modules.rl_module.RLModule 方法) (openrl.runners.common.rl_agent.RLAgent 方法) load_script_files() (openrl.selfplay.opponents.opponent_template.OpponentTemplate 方法) LocalGPUManager (openrl.supports.opengpu.manager 中的类) log() (openrl.selfplay.opponents.base_opponent.BaseOpponent 方法) log_info() (openrl.supports.opengpu.manager.LocalGPUManager 方法) (openrl.utils.logger.Logger 方法) log_learner_info() (openrl.utils.logger.Logger 方法) log_probs() (openrl.modules.networks.utils.distributions.FixedBernoulli 方法) (openrl.modules.networks.utils.distributions.FixedCategorical 方法) (openrl.modules.networks.utils.distributions.FixedNormal 方法) logger (openrl.runners.common.base_agent.BaseAgent property) (openrl.utils.callbacks.callbacks.BaseCallback 属性) Logger (openrl.utils.logger 中的类) lr_decay() (openrl.modules.base_module.BaseModule 方法) (openrl.modules.bc_module.BCModule 方法) (openrl.modules.ddpg_module.DDPGModule 方法) (openrl.modules.dqn_module.DQNModule 方法) (openrl.modules.ppo_module.PPOModule 方法) (openrl.modules.sac_module.SACModule 方法) (openrl.modules.vdn_module.VDNModule 方法) M make() (在 openrl.envs.common 模块中) (在 openrl.envs.common.registration 模块中) (在 openrl.envs.connect_env 模块中) (在 openrl.envs.gridworld.gridworld_env 模块中) (在 openrl.envs.mpe.mpe_env 模块中) make_circle() (在 openrl.envs.mpe.rendering 模块中) make_connect_envs() (在 openrl.envs.connect_env 模块中) make_gridworld_envs() (在 openrl.envs.gridworld 模块中) make_gym_envs() (在 openrl.envs.gymnasium 模块中) make_mpe_envs() (在 openrl.envs.mpe 模块中) make_offline_envs() (在 openrl.envs.offline 模块中) make_old_gym_envs() (在 openrl.envs.gymnasium 模块中) make_polygon() (在 openrl.envs.mpe.rendering 模块中) make_polyline() (在 openrl.envs.mpe.rendering 模块中) make_single_agent_drone_env() (在 openrl.envs.gym_pybullet_drones 模块中) make_single_agent_drone_envs() (在 openrl.envs.gym_pybullet_drones 模块中) make_world() (openrl.envs.mpe.scenario.BaseScenario 方法) (openrl.envs.mpe.scenarios.simple_spread.Scenario 方法) mass (openrl.envs.mpe.core.Entity property) MATAgent (openrl.runners.common 中的类) (openrl.runners.common.mat_agent 中的类) MATAlgorithm (openrl.algorithms.mat 中的类) MATNet (openrl.modules.common 中的类) (openrl.modules.common.mat_net 中的类) MATWrapper (openrl.envs.wrappers.mat_wrapper 中的类) memory_free (openrl.supports.opengpu.gpu_info.GPUInfo 属性) memory_total (openrl.supports.opengpu.gpu_info.GPUInfo 属性) memory_used (openrl.supports.opengpu.gpu_info.GPUInfo 属性) metadata (openrl.envs.mpe.multiagent_env.MultiAgentEnv 属性) (openrl.envs.vec_env.base_venv.BaseVecEnv 属性) (openrl.envs.vec_env.BaseVecEnv 属性) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) MIXBase (openrl.modules.networks.utils.mix 中的类) MLPBase (openrl.modules.networks.utils.mlp 中的类) MLPLayer (openrl.modules.networks.utils.mlp 中的类) mode() (openrl.modules.networks.utils.distributions.FixedBernoulli 方法) (openrl.modules.networks.utils.distributions.FixedCategorical 方法) (openrl.modules.networks.utils.distributions.FixedNormal 方法) ModelConfig (openrl.modules.model_config 中的类) ModelTrainConfig (openrl.modules.model_config 中的类) Monitor (openrl.envs.wrappers.monitor 中的类) MoveActionMask2InfoWrapper (openrl.envs.wrappers 中的类) (openrl.envs.wrappers.extra_wrappers 中的类) mse_loss() (在 openrl.modules.utils.util 模块中) MultiAgentEnv (openrl.envs.mpe.multiagent_env 中的类) MultiAgentTransformer (openrl.modules.networks.MAT_network 中的类) MultiDiscrete (openrl.envs.mpe.multi_discrete 中的类) MultiHeadAttention (openrl.modules.networks.utils.attention 中的类) N naive_recurrent_generator() (openrl.buffers.normal_buffer.NormalReplayBuffer 方法) (openrl.buffers.NormalReplayBuffer 方法) (openrl.buffers.replay_data.ReplayData 方法) name (openrl.envs.mpe.core.World 属性) nest_expand_dim() (在 openrl.envs.wrappers.util 模块中) NetworkOpponent (openrl.selfplay.opponents.network_opponent 中的类) NLPVecInfo (openrl.envs.vec_env.vec_info.nlp_vec_info 中的类) NoopResetEnv (openrl.envs.wrappers.atari_wrappers 中的类) normalize() (openrl.modules.networks.utils.popart.PopArt 方法) (openrl.modules.utils.valuenorm.ValueNorm 方法) NormalReplayBuffer (openrl.buffers 中的类) (openrl.buffers.normal_buffer 中的类) np_random (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) (openrl.selfplay.wrappers.base_multiplayer_wrapper.BaseMultiPlayerWrapper property) O ObsData (openrl.buffers.utils.obs_data 中的类) observation() (openrl.envs.mpe.scenarios.simple_spread.Scenario 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VectorObservationWrapper 方法) (openrl.envs.wrappers.atari_wrappers.WarpFrame 方法) (openrl.envs.wrappers.base_wrapper.BaseObservationWrapper 方法) (openrl.envs.wrappers.BaseObservationWrapper 方法) (openrl.envs.wrappers.DictWrapper 方法) (openrl.envs.wrappers.extra_wrappers.AddStep 方法) (openrl.envs.wrappers.extra_wrappers.ConvertEmptyBoxWrapper 方法) (openrl.envs.wrappers.extra_wrappers.DictWrapper 方法) (openrl.envs.wrappers.extra_wrappers.FlattenObservation 方法) (openrl.envs.wrappers.FlattenObservation 方法) (openrl.envs.wrappers.image_wrappers.TransposeImage 方法) (openrl.envs.wrappers.mat_wrapper.MATWrapper 方法) observation_space (openrl.envs.toy_envs.BitFlippingEnv 属性) (openrl.envs.toy_envs.IdentityEnv 属性) (openrl.envs.toy_envs.IdentityEnvcontinuous 属性) (openrl.envs.vec_env.base_venv.BaseVecEnv 属性) (openrl.envs.vec_env.BaseVecEnv 属性) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) (openrl.envs.wrappers.mat_wrapper.MATWrapper property) (openrl.selfplay.opponents.opponent_env.BaseOpponentEnv property) (openrl.selfplay.wrappers.base_multiplayer_wrapper.BaseMultiPlayerWrapper property) offline_make() (在 openrl.envs.offline 模块中) OfflineEnv (openrl.envs.offline.offline_env 中的类) OffPolicyReplayBuffer (openrl.buffers 中的类) (openrl.buffers.offpolicy_buffer 中的类) OffPolicyReplayData (openrl.buffers.offpolicy_replay_data 中的类) on_episode_end() (openrl.selfplay.wrappers.base_multiplayer_wrapper.BaseMultiPlayerWrapper 方法) (openrl.selfplay.wrappers.opponent_pool_wrapper.OpponentPoolWrapper 方法) on_rollout_end() (openrl.utils.callbacks.callbacks.BaseCallback 方法) on_rollout_start() (openrl.utils.callbacks.callbacks.BaseCallback 方法) on_step() (openrl.utils.callbacks.callbacks.BaseCallback 方法) on_training_end() (openrl.utils.callbacks.callbacks.BaseCallback 方法) on_training_start() (openrl.utils.callbacks.callbacks.BaseCallback 方法) openrl.algorithms 模块 openrl.algorithms.a2c 模块 openrl.algorithms.base_algorithm 模块 openrl.algorithms.behavior_cloning 模块 openrl.algorithms.ddpg 模块 openrl.algorithms.dqn 模块 openrl.algorithms.gail 模块 openrl.algorithms.mat 模块 openrl.algorithms.ppo 模块 openrl.algorithms.sac 模块 openrl.algorithms.vdn 模块 openrl.arena.agents 模块 openrl.buffers 模块 openrl.buffers.normal_buffer 模块 openrl.buffers.offpolicy_buffer 模块 openrl.buffers.offpolicy_replay_data 模块 openrl.buffers.replay_data 模块 openrl.buffers.utils 模块 openrl.buffers.utils.obs_data 模块 openrl.buffers.utils.util 模块 openrl.cli 模块 openrl.cli.cli 模块 openrl.configs 模块 openrl.configs.config 模块 openrl.configs.utils 模块 openrl.datasets 模块 openrl.datasets.expert_dataset 模块 openrl.drivers 模块 openrl.drivers.base_driver 模块 openrl.envs 模块 openrl.envs.common 模块 openrl.envs.common.build_envs 模块 openrl.envs.common.registration 模块 openrl.envs.connect_env 模块 openrl.envs.connect_env.base_connect_env 模块 openrl.envs.connect_env.connect3_env 模块 openrl.envs.connect_env.connect4_env 模块 openrl.envs.connect_env.utils 模块 openrl.envs.gridworld 模块 openrl.envs.gridworld.gridworld_env 模块 openrl.envs.gym_pybullet_drones 模块 openrl.envs.gymnasium 模块 openrl.envs.mpe 模块 openrl.envs.mpe.core 模块 openrl.envs.mpe.mpe_env 模块 openrl.envs.mpe.multi_discrete 模块 openrl.envs.mpe.multiagent_env 模块 openrl.envs.mpe.rendering 模块 openrl.envs.mpe.scenario 模块 openrl.envs.mpe.scenarios 模块 openrl.envs.mpe.scenarios.simple_spread 模块 openrl.envs.offline 模块 openrl.envs.offline.offline_env 模块 openrl.envs.PettingZoo.registration 模块 openrl.envs.toy_envs 模块 openrl.envs.toy_envs.bit_flipping_env 模块 openrl.envs.toy_envs.identity_env 模块 openrl.envs.vec_env 模块 openrl.envs.vec_env.async_venv 模块 openrl.envs.vec_env.base_venv 模块 openrl.envs.vec_env.sync_venv 模块 openrl.envs.vec_env.utils 模块 openrl.envs.vec_env.utils.numpy_utils 模块 openrl.envs.vec_env.utils.share_memory 模块 openrl.envs.vec_env.utils.util 模块 openrl.envs.vec_env.vec_info 模块 openrl.envs.vec_env.vec_info.base_vec_info 模块 openrl.envs.vec_env.vec_info.episode_rewards_info 模块 openrl.envs.vec_env.vec_info.nlp_vec_info 模块 openrl.envs.vec_env.vec_info.simple_vec_info 模块 openrl.envs.vec_env.wrappers 模块 openrl.envs.vec_env.wrappers.base_wrapper 模块 openrl.envs.vec_env.wrappers.gen_data 模块 openrl.envs.vec_env.wrappers.reward_wrapper 模块 openrl.envs.vec_env.wrappers.vec_monitor_wrapper 模块 openrl.envs.vec_env.wrappers.zero_reward_wrapper 模块 openrl.envs.wrappers 模块 openrl.envs.wrappers.atari_wrappers 模块 openrl.envs.wrappers.base_wrapper 模块 openrl.envs.wrappers.extra_wrappers 模块 openrl.envs.wrappers.flatten 模块 openrl.envs.wrappers.image_wrappers 模块 openrl.envs.wrappers.mat_wrapper 模块 openrl.envs.wrappers.monitor 模块 openrl.envs.wrappers.multiagent_wrapper 模块 openrl.envs.wrappers.util 模块 openrl.modules 模块 openrl.modules.base_module 模块 openrl.modules.bc_module 模块 openrl.modules.common 模块 openrl.modules.common.a2c_net 模块 openrl.modules.common.base_net 模块 openrl.modules.common.bc_net 模块 openrl.modules.common.ddpg_net 模块 openrl.modules.common.dqn_net 模块 openrl.modules.common.gail_net 模块 openrl.modules.common.mat_net 模块 openrl.modules.common.ppo_net 模块 openrl.modules.common.sac_net 模块 openrl.modules.common.vdn_net 模块 openrl.modules.ddpg_module 模块 openrl.modules.dqn_module 模块 openrl.modules.gail_module 模块 openrl.modules.model_config 模块 openrl.modules.networks 模块 openrl.modules.networks.base_policy_network 模块 openrl.modules.networks.base_value_network 模块 openrl.modules.networks.base_value_policy_network 模块 openrl.modules.networks.ddpg_network 模块 openrl.modules.networks.gail_discriminator 模块 openrl.modules.networks.MAT_network 模块 openrl.modules.networks.policy_network 模块 openrl.modules.networks.policy_value_network 模块 openrl.modules.networks.q_network 模块 openrl.modules.networks.sac_network 模块 openrl.modules.networks.utils 模块 openrl.modules.networks.utils.act 模块 openrl.modules.networks.utils.attention 模块 openrl.modules.networks.utils.cnn 模块 openrl.modules.networks.utils.distributed_utils 模块 openrl.modules.networks.utils.distributions 模块 openrl.modules.networks.utils.mix 模块 openrl.modules.networks.utils.mlp 模块 openrl.modules.networks.utils.nlp 模块 openrl.modules.networks.utils.popart 模块 openrl.modules.networks.utils.rnn 模块 openrl.modules.networks.utils.running_mean_std 模块 openrl.modules.networks.utils.transformer_act 模块 openrl.modules.networks.utils.util 模块 openrl.modules.networks.utils.vdn 模块 openrl.modules.networks.value_network 模块 openrl.modules.networks.vdn_network 模块 openrl.modules.ppo_module 模块 openrl.modules.rl_module 模块 openrl.modules.sac_module 模块 openrl.modules.utils 模块 openrl.modules.utils.util 模块 openrl.modules.utils.valuenorm 模块 openrl.modules.vdn_module 模块 openrl.rewards 模块 openrl.rewards.base_reward 模块 openrl.rewards.gail_reward 模块 openrl.runners 模块 openrl.runners.common 模块 openrl.runners.common.a2c_agent 模块 openrl.runners.common.base_agent 模块 openrl.runners.common.bc_agent 模块 openrl.runners.common.chat_agent 模块 openrl.runners.common.ddpg_agent 模块 openrl.runners.common.dqn_agent 模块 openrl.runners.common.gail_agent 模块 openrl.runners.common.mat_agent 模块 openrl.runners.common.ppo_agent 模块 openrl.runners.common.rl_agent 模块 openrl.runners.common.sac_agent 模块 openrl.runners.common.vdn_agent 模块 openrl.selfplay 模块 openrl.selfplay.callbacks 模块 openrl.selfplay.callbacks.base_callback 模块 openrl.selfplay.callbacks.selfplay_callback 模块 openrl.selfplay.multiplayer_env 模块 openrl.selfplay.opponents 模块 openrl.selfplay.opponents.base_opponent 模块 openrl.selfplay.opponents.jidi_opponent 模块 openrl.selfplay.opponents.network_opponent 模块 openrl.selfplay.opponents.opponent_env 模块 openrl.selfplay.opponents.opponent_template 模块 openrl.selfplay.opponents.random_opponent 模块 openrl.selfplay.opponents.utils 模块 openrl.selfplay.sample_strategy 模块 openrl.selfplay.sample_strategy.base_sample_strategy 模块 openrl.selfplay.sample_strategy.last_opponent 模块 openrl.selfplay.sample_strategy.random_opponent 模块 openrl.selfplay.selfplay_api 模块 openrl.selfplay.selfplay_api.selfplay_client 模块 openrl.selfplay.wrappers 模块 openrl.selfplay.wrappers.base_multiplayer_wrapper 模块 openrl.selfplay.wrappers.human_opponent_wrapper 模块 openrl.selfplay.wrappers.opponent_pool_wrapper 模块 openrl.selfplay.wrappers.random_opponent_wrapper 模块 openrl.supports 模块 openrl.supports.opendata 模块 openrl.supports.opendata.utils 模块 openrl.supports.opendata.utils.opendata_utils 模块 openrl.supports.opengpu 模块 openrl.supports.opengpu.gpu_info 模块 openrl.supports.opengpu.manager 模块 openrl.utils 模块 openrl.utils.callbacks 模块 openrl.utils.callbacks.callbacks 模块 openrl.utils.callbacks.callbacks_factory 模块 openrl.utils.callbacks.checkpoint_callback 模块 openrl.utils.callbacks.eval_callback 模块 openrl.utils.callbacks.processbar_callback 模块 openrl.utils.callbacks.stop_callback 模块 openrl.utils.custom_data_structure 模块 openrl.utils.evaluation 模块 openrl.utils.file_tool 模块 openrl.utils.logger 模块 openrl.utils.type_aliases 模块 openrl.utils.util 模块 opponent_type (openrl.selfplay.opponents.base_opponent.BaseOpponent property) OpponentPoolWrapper (openrl.selfplay.wrappers.opponent_pool_wrapper 中的类) OpponentTemplate (openrl.selfplay.opponents.opponent_template 中的类) output_size (openrl.modules.networks.utils.cnn.CNNBase property) (openrl.modules.networks.utils.mix.MIXBase property) (openrl.modules.networks.utils.mlp.MLPBase property) P parallel_env_num (openrl.envs.vec_env.base_venv.BaseVecEnv 属性) (openrl.envs.vec_env.BaseVecEnv 属性) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) (openrl.selfplay.opponents.opponent_env.BaseOpponentEnv property) Point (openrl.envs.mpe.rendering 中的类) policy_agents (openrl.envs.mpe.core.World property) PolicyNetwork (openrl.modules.networks.policy_network 中的类) PolicyValueNetwork (openrl.modules.networks.policy_value_network 中的类) PolyLine (openrl.envs.mpe.rendering 中的类) PopArt (openrl.modules.networks.utils.popart 中的类) ppo_update() (openrl.algorithms.ppo.PPOAlgorithm 方法) PPOAgent (openrl.runners.common 中的类) (openrl.runners.common.ppo_agent 中的类) PPOAlgorithm (openrl.algorithms.ppo 中的类) PPOModule (openrl.modules.ppo_module 中的类) PPONet (openrl.modules.common 中的类) (openrl.modules.common.ppo_net 中的类) predict_reward() (openrl.modules.networks.gail_discriminator.Discriminator 方法) prep_rollout() (openrl.algorithms.base_algorithm.BaseAlgorithm 方法) prep_training() (openrl.algorithms.base_algorithm.BaseAlgorithm 方法) prepare_action_masks() (在 openrl.envs.vec_env.utils.util 模块中) prepare_actor_loss() (openrl.algorithms.ddpg.DDPGAlgorithm 方法) (openrl.algorithms.sac.SACAlgorithm 方法) prepare_alpha_loss() (openrl.algorithms.sac.SACAlgorithm 方法) prepare_critic_loss() (openrl.algorithms.ddpg.DDPGAlgorithm 方法) (openrl.algorithms.sac.SACAlgorithm 方法) prepare_input() (openrl.buffers.utils.obs_data.ObsData 静态方法) prepare_loss() (openrl.algorithms.a2c.A2CAlgorithm 方法) (openrl.algorithms.behavior_cloning.BCAlgorithm 方法) (openrl.algorithms.dqn.DQNAlgorithm 方法) (openrl.algorithms.ppo.PPOAlgorithm 方法) (openrl.algorithms.vdn.VDNAlgorithm 方法) preserve_decimal() (在 openrl.supports.opengpu.gpu_info 模块中) print_system_info() (在 openrl.cli.cli 模块中) print_version() (在 openrl.cli.cli 模块中) process_action() (openrl.selfplay.opponents.opponent_env.BaseOpponentEnv 方法) process_obs() (openrl.selfplay.opponents.opponent_env.BaseOpponentEnv 方法) ProcessYamlAction (openrl.configs.utils 中的类) product_name (openrl.supports.opengpu.gpu_info.GPUInfo 属性) ProgressBarCallback (openrl.utils.callbacks.processbar_callback 中的类) Q QNetwork (openrl.modules.networks.q_network 中的类) R random_action() (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.BaseVecEnv 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper 方法) RandomOpponent (openrl.selfplay.opponents.random_opponent 中的类) (openrl.selfplay.sample_strategy.random_opponent 中的类) RandomOpponentWrapper (openrl.selfplay.wrappers.random_opponent_wrapper 中的类) read_from_shared_memory() (在 openrl.envs.vec_env.utils.share_memory 模块中) real_id (openrl.supports.opengpu.gpu_info.GPUInfo 属性) RecordReward (openrl.envs.wrappers.extra_wrappers 中的类) recurrent_generator() (openrl.buffers.normal_buffer.NormalReplayBuffer 方法) (openrl.buffers.NormalReplayBuffer 方法) (openrl.buffers.replay_data.ReplayData 方法) recurrent_generator_v3() (openrl.buffers.replay_data.ReplayData 方法) red() (在 openrl.cli.cli 模块中) reduce_tensor() (在 openrl.modules.networks.utils.distributed_utils 模块中) register() (openrl.envs.vec_env.vec_info.VecInfoFactory 静态方法) (openrl.rewards.RewardFactory 静态方法) (openrl.utils.callbacks.CallbackFactory 静态方法) (openrl.utils.callbacks.callbacks_factory.CallbackFactory 静态方法) (在 openrl.envs.PettingZoo.registration 模块中) register_sample_strategy() (openrl.selfplay.sample_strategy.SampleStrategyFactory 静态方法) RemoteGPUManager (openrl.supports.opengpu.manager 中的类) RemoveTruncated (openrl.envs.wrappers 中的类) (openrl.envs.wrappers.extra_wrappers 中的类) render() (openrl.envs.gridworld.gridworld_env.GridWorldEnv 方法) (openrl.envs.mpe.multiagent_env.MultiAgentEnv 方法) (openrl.envs.mpe.rendering.Geom 方法) (openrl.envs.mpe.rendering.Viewer 方法) (openrl.envs.toy_envs.bit_flipping_env.BitFlippingEnv 方法) (openrl.envs.toy_envs.BitFlippingEnv 方法) (openrl.envs.toy_envs.identity_env.IdentityEnv 方法) (openrl.envs.toy_envs.identity_env.IdentityEnvcontinuous 方法) (openrl.envs.toy_envs.IdentityEnv 方法) (openrl.envs.toy_envs.IdentityEnvcontinuous 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.BaseVecEnv 方法) render1() (openrl.envs.mpe.rendering.FilledPolygon 方法) (openrl.envs.mpe.rendering.Geom 方法) (openrl.envs.mpe.rendering.Line 方法) (openrl.envs.mpe.rendering.Point 方法) (openrl.envs.mpe.rendering.PolyLine 方法) render_mode (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) replace_data_server() (在 openrl.supports.opendata.utils.opendata_utils 模块中) ReplayData (openrl.buffers.replay_data 中的类) reset() (openrl.envs.connect_env.base_connect_env.BaseConnectEnv 方法) (openrl.envs.gridworld.gridworld_env.GridWorldEnv 方法) (openrl.envs.gridworld.gridworld_env.GridWorldEnvRandomGoal 方法) (openrl.envs.mpe.multiagent_env.MultiAgentEnv 方法) (openrl.envs.offline.offline_env.OfflineEnv 方法) (openrl.envs.toy_envs.bit_flipping_env.BitFlippingEnv 方法) (openrl.envs.toy_envs.BitFlippingEnv 方法) (openrl.envs.toy_envs.identity_env.IdentityEnv 方法) (openrl.envs.toy_envs.identity_env.IdentityEnvcontinuous 方法) (openrl.envs.toy_envs.IdentityEnv 方法) (openrl.envs.toy_envs.IdentityEnvcontinuous 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.BaseVecEnv 方法) (openrl.envs.vec_env.vec_info.base_vec_info.BaseVecInfo 方法) (openrl.envs.vec_env.vec_info.nlp_vec_info.NLPVecInfo 方法) (openrl.envs.vec_env.vec_info.simple_vec_info.SimpleVecInfo 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VectorObservationWrapper 方法) (openrl.envs.vec_env.wrappers.gen_data.GenDataWrapper 方法) (openrl.envs.vec_env.wrappers.gen_data.GenDataWrapper_v1 方法) (openrl.envs.vec_env.wrappers.gen_data.TrajectoryData 方法) (openrl.envs.wrappers.atari_wrappers.EpisodicLifeEnv 方法) (openrl.envs.wrappers.atari_wrappers.FireResetEnv 方法) (openrl.envs.wrappers.atari_wrappers.NoopResetEnv 方法) (openrl.envs.wrappers.base_wrapper.BaseObservationWrapper 方法) (openrl.envs.wrappers.BaseObservationWrapper 方法) (openrl.envs.wrappers.extra_wrappers.AddStep 方法) (openrl.envs.wrappers.extra_wrappers.GIFWrapper 方法) (openrl.envs.wrappers.extra_wrappers.MoveActionMask2InfoWrapper 方法) (openrl.envs.wrappers.GIFWrapper 方法) (openrl.envs.wrappers.monitor.Monitor 方法) (openrl.envs.wrappers.MoveActionMask2InfoWrapper 方法) (openrl.envs.wrappers.multiagent_wrapper.Single2MultiAgentWrapper 方法) (openrl.envs.wrappers.Single2MultiAgentWrapper 方法) (openrl.modules.common.ddpg_net.DDPGNet 方法) (openrl.modules.common.DDPGNet 方法) (openrl.modules.common.dqn_net.DQNNet 方法) (openrl.modules.common.DQNNet 方法) (openrl.modules.common.ppo_net.PPONet 方法) (openrl.modules.common.PPONet 方法) (openrl.modules.common.sac_net.SACNet 方法) (openrl.modules.common.SACNet 方法) (openrl.modules.common.vdn_net.VDNNet 方法) (openrl.modules.common.VDNNet 方法) (openrl.runners.common.rl_agent.RLAgent 方法) (openrl.selfplay.opponents.base_opponent.BaseOpponent 方法) (openrl.selfplay.opponents.network_opponent.NetworkOpponent 方法) (openrl.selfplay.opponents.opponent_env.BaseOpponentEnv 方法) (openrl.selfplay.wrappers.base_multiplayer_wrapper.BaseMultiPlayerWrapper 方法) (openrl.selfplay.wrappers.opponent_pool_wrapper.OpponentPoolWrapper 方法) reset_fetch() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) reset_parameters() (openrl.modules.networks.utils.popart.PopArt 方法) (openrl.modules.utils.valuenorm.ValueNorm 方法) reset_rnn_states() (在 openrl.modules.common.ppo_net 模块中) reset_send() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) reset_world() (openrl.envs.mpe.scenario.BaseScenario 方法) (openrl.envs.mpe.scenarios.simple_spread.Scenario 方法) restore() (openrl.modules.base_module.BaseModule 方法) (openrl.modules.rl_module.RLModule 方法) reward() (openrl.envs.mpe.scenarios.simple_spread.Scenario 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VectorRewardWrapper 方法) (openrl.envs.vec_env.wrappers.zero_reward_wrapper.ZeroRewardWrapper 方法) (openrl.envs.wrappers.atari_wrappers.ClipRewardEnv 方法) (openrl.envs.wrappers.base_wrapper.BaseRewardWrapper 方法) (openrl.envs.wrappers.BaseRewardWrapper 方法) (openrl.envs.wrappers.extra_wrappers.ZeroRewardWrapper 方法) reward_range (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) RewardFactory (openrl.rewards 中的类) RewardPredictor (openrl.rewards.gail_reward 中的类) RewardWrapper (openrl.envs.vec_env 中的类) (openrl.envs.vec_env.wrappers.reward_wrapper 中的类) RLAgent (openrl.runners.common.rl_agent 中的类) RLModule (openrl.modules.rl_module 中的类) rnn_forward() (openrl.modules.networks.utils.rnn.RNNLayer 方法) RNNLayer (openrl.modules.networks.utils.rnn 中的类) run() (openrl.drivers.base_driver.BaseDriver 方法) running_mean_var() (openrl.modules.utils.valuenorm.ValueNorm 方法) RunningMeanStd (openrl.modules.networks.utils.running_mean_std 中的类) S sac_update() (openrl.algorithms.sac.SACAlgorithm 方法) SACActorNetwork (openrl.modules.networks.sac_network 中的类) SACAgent (openrl.runners.common 中的类) (openrl.runners.common.sac_agent 中的类) SACAlgorithm (openrl.algorithms.sac 中的类) SACModule (openrl.modules.sac_module 中的类) SACNet (openrl.modules.common 中的类) (openrl.modules.common.sac_net 中的类) sample() (openrl.envs.mpe.multi_discrete.MultiDiscrete 方法) (openrl.modules.networks.utils.distributions.FixedCategorical 方法) sample_opponent() (openrl.selfplay.sample_strategy.base_sample_strategy.BaseSampleStrategy 方法) (openrl.selfplay.sample_strategy.last_opponent.LastOpponent 方法) (openrl.selfplay.sample_strategy.random_opponent.RandomOpponent 方法) sample_random_action() (openrl.selfplay.opponents.random_opponent.RandomOpponent 方法) SampleStrategyFactory (openrl.selfplay.sample_strategy 中的类) save() (openrl.modules.base_module.BaseModule 方法) (openrl.modules.rl_module.RLModule 方法) (openrl.runners.common.base_agent.BaseAgent 方法) (openrl.runners.common.chat_agent.ChatAgent 方法) (openrl.runners.common.ChatAgent 方法) (openrl.runners.common.rl_agent.RLAgent 方法) (openrl.selfplay.opponents.opponent_template.OpponentTemplate 方法) save_opponent() (openrl.selfplay.callbacks.selfplay_callback.SelfplayCallback 方法) ScaledDotProductAttention() (在 openrl.modules.networks.utils.attention 模块中) Scenario (openrl.envs.mpe.scenarios.simple_spread 中的类) scripted_agents (openrl.envs.mpe.core.World property) seed() (openrl.envs.mpe.multiagent_env.MultiAgentEnv 方法) (openrl.envs.offline.offline_env.OfflineEnv 方法) (openrl.envs.toy_envs.bit_flipping_env.BitFlippingEnv 方法) (openrl.envs.toy_envs.BitFlippingEnv 方法) (openrl.envs.toy_envs.identity_env.IdentityEnv 方法) (openrl.envs.toy_envs.identity_env.IdentityEnvcontinuous 方法) (openrl.envs.toy_envs.IdentityEnv 方法) (openrl.envs.toy_envs.IdentityEnvcontinuous 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.BaseVecEnv 方法) (openrl.envs.vec_env.sync_venv.SyncVectorEnv 方法) (openrl.envs.vec_env.SyncVectorEnv 方法) self_player (openrl.selfplay.wrappers.base_multiplayer_wrapper.BaseMultiPlayerWrapper 属性) SelfAttention (openrl.modules.networks.MAT_network 中的类) SelfplayCallback (openrl.selfplay.callbacks.selfplay_callback 中的类) SelfPlayClient (openrl.selfplay.selfplay_api.selfplay_client 中的类) set_attr() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.BaseVecEnv 方法) (openrl.envs.vec_env.sync_venv.SyncVectorEnv 方法) (openrl.envs.vec_env.SyncVectorEnv 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper 方法) set_bounds() (openrl.envs.mpe.rendering.Viewer 方法) set_color() (openrl.envs.mpe.rendering.Geom 方法) set_discriminator() (openrl.rewards.gail_reward.GAILReward 方法) set_env() (openrl.runners.common.rl_agent.RLAgent 方法) (openrl.selfplay.opponents.base_opponent.BaseOpponent 方法) set_linewidth() (openrl.envs.mpe.rendering.PolyLine 方法) set_parent() (openrl.utils.callbacks.callbacks.BaseCallback 方法) (openrl.utils.callbacks.callbacks.CallbackList 方法) set_render_mode() (openrl.envs.wrappers.base_wrapper.BaseWrapper 方法) (openrl.envs.wrappers.BaseWrapper 方法) set_rotation() (openrl.envs.mpe.rendering.Transform 方法) set_sample_strategy() (openrl.selfplay.selfplay_api.selfplay_client.SelfPlayClient 方法) set_scale() (openrl.envs.mpe.rendering.Transform 方法) set_seed() (在 openrl.utils.util 模块中) set_translation() (openrl.envs.mpe.rendering.Transform 方法) shape (openrl.envs.mpe.multi_discrete.MultiDiscrete property) SimpleVecInfo (openrl.envs.vec_env.vec_info.simple_vec_info 中的类) Single2MultiAgentWrapper (openrl.envs.wrappers 中的类) (openrl.envs.wrappers.multiagent_wrapper 中的类) single_random_action() (在 openrl.envs.vec_env.utils.numpy_utils 模块中) spec (openrl.envs.mpe.multiagent_env.MultiAgentEnv 属性) (openrl.envs.toy_envs.bit_flipping_env.BitFlippingEnv 属性) (openrl.envs.toy_envs.BitFlippingEnv 属性) (openrl.envs.toy_envs.identity_env.IdentityEnv 属性) (openrl.envs.toy_envs.identity_env.IdentityEnvcontinuous 属性) (openrl.envs.toy_envs.IdentityEnv 属性) (openrl.envs.toy_envs.IdentityEnvcontinuous 属性) split_obs() (在 openrl.modules.networks.utils.attention 模块中) statistics() (openrl.envs.vec_env.vec_info.base_vec_info.BaseVecInfo 方法) (openrl.envs.vec_env.vec_info.episode_rewards_info.EPS_RewardInfo 方法) (openrl.envs.vec_env.vec_info.nlp_vec_info.NLPVecInfo 方法) (openrl.envs.vec_env.vec_info.simple_vec_info.SimpleVecInfo 方法) (openrl.envs.vec_env.VecMonitorWrapper 方法) (openrl.envs.vec_env.wrappers.vec_monitor_wrapper.VecMonitorWrapper 方法) step() (openrl.envs.connect_env.base_connect_env.BaseConnectEnv 方法) (openrl.envs.gridworld.gridworld_env.GridWorldEnv 方法) (openrl.envs.mpe.core.World 方法) (openrl.envs.mpe.multiagent_env.MultiAgentEnv 方法) (openrl.envs.offline.offline_env.OfflineEnv 方法) (openrl.envs.toy_envs.bit_flipping_env.BitFlippingEnv 方法) (openrl.envs.toy_envs.BitFlippingEnv 方法) (openrl.envs.toy_envs.identity_env.IdentityEnv 方法) (openrl.envs.toy_envs.identity_env.IdentityEnvcontinuous 方法) (openrl.envs.toy_envs.IdentityEnv 方法) (openrl.envs.toy_envs.IdentityEnvcontinuous 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.BaseVecEnv 方法) (openrl.envs.vec_env.RewardWrapper 方法) (openrl.envs.vec_env.VecMonitorWrapper 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VectorActionWrapper 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VectorObservationWrapper 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VectorRewardWrapper 方法) (openrl.envs.vec_env.wrappers.gen_data.GenDataWrapper 方法) (openrl.envs.vec_env.wrappers.gen_data.GenDataWrapper_v1 方法) (openrl.envs.vec_env.wrappers.gen_data.TrajectoryData 方法) (openrl.envs.vec_env.wrappers.reward_wrapper.RewardWrapper 方法) (openrl.envs.vec_env.wrappers.vec_monitor_wrapper.VecMonitorWrapper 方法) (openrl.envs.wrappers.atari_wrappers.EpisodicLifeEnv 方法) (openrl.envs.wrappers.base_wrapper.BaseObservationWrapper 方法) (openrl.envs.wrappers.base_wrapper.BaseRewardWrapper 方法) (openrl.envs.wrappers.base_wrapper.BaseWrapper 方法) (openrl.envs.wrappers.BaseObservationWrapper 方法) (openrl.envs.wrappers.BaseRewardWrapper 方法) (openrl.envs.wrappers.BaseWrapper 方法) (openrl.envs.wrappers.extra_wrappers.AddStep 方法) (openrl.envs.wrappers.extra_wrappers.FrameSkip 方法) (openrl.envs.wrappers.extra_wrappers.GIFWrapper 方法) (openrl.envs.wrappers.extra_wrappers.MoveActionMask2InfoWrapper 方法) (openrl.envs.wrappers.extra_wrappers.RemoveTruncated 方法) (openrl.envs.wrappers.GIFWrapper 方法) (openrl.envs.wrappers.monitor.Monitor 方法) (openrl.envs.wrappers.MoveActionMask2InfoWrapper 方法) (openrl.envs.wrappers.multiagent_wrapper.Single2MultiAgentWrapper 方法) (openrl.envs.wrappers.RemoveTruncated 方法) (openrl.envs.wrappers.Single2MultiAgentWrapper 方法) (openrl.selfplay.wrappers.base_multiplayer_wrapper.BaseMultiPlayerWrapper 方法) step_api_compatibility() (在 openrl.envs.wrappers.extra_wrappers 模块中) step_batch() (openrl.buffers.utils.obs_data.ObsData 方法) step_fetch() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) step_flatten() (openrl.buffers.utils.obs_data.ObsData 方法) step_reward() (openrl.rewards.base_reward.BaseReward 方法) (openrl.rewards.gail_reward.GAILReward 方法) step_send() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) StopTrainingOnMaxEpisodes (openrl.utils.callbacks.stop_callback 中的类) StopTrainingOnNoModelImprovement (openrl.utils.callbacks.stop_callback 中的类) StopTrainingOnRewardThreshold (openrl.utils.callbacks.stop_callback 中的类) SyncVectorEnv (openrl.envs.vec_env 中的类) (openrl.envs.vec_env.sync_venv 中的类) T tile_images() (在 openrl.envs.vec_env.utils.util 模块中) to_single_np() (openrl.algorithms.behavior_cloning.BCAlgorithm 方法) (openrl.algorithms.ddpg.DDPGAlgorithm 方法) (openrl.algorithms.dqn.DQNAlgorithm 方法) (openrl.algorithms.ppo.PPOAlgorithm 方法) (openrl.algorithms.sac.SACAlgorithm 方法) (openrl.algorithms.vdn.VDNAlgorithm 方法) train() (openrl.algorithms.a2c.A2CAlgorithm 方法) (openrl.algorithms.base_algorithm.BaseAlgorithm 方法) (openrl.algorithms.behavior_cloning.BCAlgorithm 方法) (openrl.algorithms.ddpg.DDPGAlgorithm 方法) (openrl.algorithms.dqn.DQNAlgorithm 方法) (openrl.algorithms.ppo.PPOAlgorithm 方法) (openrl.algorithms.sac.SACAlgorithm 方法) (openrl.algorithms.vdn.VDNAlgorithm 方法) (openrl.runners.common.a2c_agent.A2CAgent 方法) (openrl.runners.common.A2CAgent 方法) (openrl.runners.common.bc_agent.BCAgent 方法) (openrl.runners.common.BCAgent 方法) (openrl.runners.common.ddpg_agent.DDPGAgent 方法) (openrl.runners.common.DDPGAgent 方法) (openrl.runners.common.dqn_agent.DQNAgent 方法) (openrl.runners.common.DQNAgent 方法) (openrl.runners.common.gail_agent.GAILAgent 方法) (openrl.runners.common.GAILAgent 方法) (openrl.runners.common.mat_agent.MATAgent 方法) (openrl.runners.common.MATAgent 方法) (openrl.runners.common.ppo_agent.PPOAgent 方法) (openrl.runners.common.PPOAgent 方法) (openrl.runners.common.rl_agent.RLAgent 方法) (openrl.runners.common.sac_agent.SACAgent 方法) (openrl.runners.common.SACAgent 方法) (openrl.runners.common.vdn_agent.VDNAgent 方法) (openrl.runners.common.VDNAgent 方法) train_bc() (openrl.algorithms.behavior_cloning.BCAlgorithm 方法) train_gail() (openrl.algorithms.gail.GAILAlgorithm 方法) train_ppo() (openrl.algorithms.ppo.PPOAlgorithm 方法) TrajectoryData (openrl.envs.vec_env.wrappers.gen_data 中的类) Transform (openrl.envs.mpe.rendering 中的类) TransposeImage (openrl.envs.wrappers.image_wrappers 中的类) U unwrap_wrapper() (在 openrl.envs.wrappers.util 模块中) unwrapped (openrl.envs.vec_env.base_venv.BaseVecEnv property) (openrl.envs.vec_env.BaseVecEnv property) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) update() (openrl.modules.networks.gail_discriminator.Discriminator 方法) (openrl.modules.networks.utils.popart.PopArt 方法) (openrl.modules.networks.utils.running_mean_std.RunningMeanStd 方法) (openrl.modules.utils.valuenorm.ValueNorm 方法) update_agent_state() (openrl.envs.mpe.core.World 方法) update_child_locals() (openrl.utils.callbacks.callbacks.BaseCallback 方法) (openrl.utils.callbacks.callbacks.CallbackList 方法) (openrl.utils.callbacks.callbacks.EventCallback 方法) (openrl.utils.callbacks.eval_callback.EvalCallback 方法) update_from_moments() (openrl.modules.networks.utils.running_mean_std.RunningMeanStd 方法) update_linear_schedule() (在 openrl.modules.utils.util 模块中) update_locals() (openrl.utils.callbacks.callbacks.BaseCallback 方法) use_monitor (openrl.envs.vec_env.VecMonitorWrapper property) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) (openrl.envs.vec_env.wrappers.vec_monitor_wrapper.VecMonitorWrapper property) (openrl.envs.wrappers.base_wrapper.BaseWrapper property) (openrl.envs.wrappers.BaseWrapper property) V ValueNetwork (openrl.modules.networks.value_network 中的类) ValueNorm (openrl.modules.utils.valuenorm 中的类) vdn_update() (openrl.algorithms.vdn.VDNAlgorithm 方法) VDNAgent (openrl.runners.common 中的类) (openrl.runners.common.vdn_agent 中的类) VDNAlgorithm (openrl.algorithms.vdn 中的类) VDNBase (openrl.modules.networks.utils.vdn 中的类) VDNModule (openrl.modules.vdn_module 中的类) VDNNet (openrl.modules.common 中的类) (openrl.modules.common.vdn_net 中的类) VDNNetwork (openrl.modules.networks.vdn_network 中的类) VecEnvWrapper (openrl.envs.vec_env.wrappers.base_wrapper 中的类) VecInfoFactory (openrl.envs.vec_env.vec_info 中的类) VecMonitorWrapper (openrl.envs.vec_env 中的类) (openrl.envs.vec_env.wrappers.vec_monitor_wrapper 中的类) vector_render() (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.BaseVecEnv 方法) VectorActionWrapper (openrl.envs.vec_env.wrappers.base_wrapper 中的类) VectorObservationWrapper (openrl.envs.vec_env.wrappers.base_wrapper 中的类) VectorRewardWrapper (openrl.envs.vec_env.wrappers.base_wrapper 中的类) Viewer (openrl.envs.mpe.rendering 中的类) W WAITING_CALL (openrl.envs.vec_env.async_venv.AsyncState 属性) WAITING_RESET (openrl.envs.vec_env.async_venv.AsyncState 属性) WAITING_STEP (openrl.envs.vec_env.async_venv.AsyncState 属性) Wall (openrl.envs.mpe.core 中的类) WarpFrame (openrl.envs.wrappers.atari_wrappers 中的类) window_closed_by_user() (openrl.envs.mpe.rendering.Viewer 方法) World (openrl.envs.mpe.core 中的类) write_to_shared_memory() (在 openrl.envs.vec_env.utils.share_memory 模块中) Z zero_std() (openrl.modules.networks.MAT_network.Decoder 方法) (openrl.modules.networks.MAT_network.MultiAgentTransformer 方法) ZeroRewardWrapper (openrl.envs.vec_env.wrappers.zero_reward_wrapper 中的类) (openrl.envs.wrappers.extra_wrappers 中的类) 模 模块 openrl.algorithms openrl.algorithms.a2c openrl.algorithms.base_algorithm openrl.algorithms.behavior_cloning openrl.algorithms.ddpg openrl.algorithms.dqn openrl.algorithms.gail openrl.algorithms.mat openrl.algorithms.ppo openrl.algorithms.sac openrl.algorithms.vdn openrl.arena.agents openrl.buffers openrl.buffers.normal_buffer openrl.buffers.offpolicy_buffer openrl.buffers.offpolicy_replay_data openrl.buffers.replay_data openrl.buffers.utils openrl.buffers.utils.obs_data openrl.buffers.utils.util openrl.cli openrl.cli.cli openrl.configs openrl.configs.config openrl.configs.utils openrl.datasets openrl.datasets.expert_dataset openrl.drivers openrl.drivers.base_driver openrl.envs openrl.envs.common openrl.envs.common.build_envs openrl.envs.common.registration openrl.envs.connect_env openrl.envs.connect_env.base_connect_env openrl.envs.connect_env.connect3_env openrl.envs.connect_env.connect4_env openrl.envs.connect_env.utils openrl.envs.gridworld openrl.envs.gridworld.gridworld_env openrl.envs.gym_pybullet_drones openrl.envs.gymnasium openrl.envs.mpe openrl.envs.mpe.core openrl.envs.mpe.mpe_env openrl.envs.mpe.multi_discrete openrl.envs.mpe.multiagent_env openrl.envs.mpe.rendering openrl.envs.mpe.scenario openrl.envs.mpe.scenarios openrl.envs.mpe.scenarios.simple_spread openrl.envs.offline openrl.envs.offline.offline_env openrl.envs.PettingZoo.registration openrl.envs.toy_envs openrl.envs.toy_envs.bit_flipping_env openrl.envs.toy_envs.identity_env openrl.envs.vec_env openrl.envs.vec_env.async_venv openrl.envs.vec_env.base_venv openrl.envs.vec_env.sync_venv openrl.envs.vec_env.utils openrl.envs.vec_env.utils.numpy_utils openrl.envs.vec_env.utils.share_memory openrl.envs.vec_env.utils.util openrl.envs.vec_env.vec_info openrl.envs.vec_env.vec_info.base_vec_info openrl.envs.vec_env.vec_info.episode_rewards_info openrl.envs.vec_env.vec_info.nlp_vec_info openrl.envs.vec_env.vec_info.simple_vec_info openrl.envs.vec_env.wrappers openrl.envs.vec_env.wrappers.base_wrapper openrl.envs.vec_env.wrappers.gen_data openrl.envs.vec_env.wrappers.reward_wrapper openrl.envs.vec_env.wrappers.vec_monitor_wrapper openrl.envs.vec_env.wrappers.zero_reward_wrapper openrl.envs.wrappers openrl.envs.wrappers.atari_wrappers openrl.envs.wrappers.base_wrapper openrl.envs.wrappers.extra_wrappers openrl.envs.wrappers.flatten openrl.envs.wrappers.image_wrappers openrl.envs.wrappers.mat_wrapper openrl.envs.wrappers.monitor openrl.envs.wrappers.multiagent_wrapper openrl.envs.wrappers.util openrl.modules openrl.modules.base_module openrl.modules.bc_module openrl.modules.common openrl.modules.common.a2c_net openrl.modules.common.base_net openrl.modules.common.bc_net openrl.modules.common.ddpg_net openrl.modules.common.dqn_net openrl.modules.common.gail_net openrl.modules.common.mat_net openrl.modules.common.ppo_net openrl.modules.common.sac_net openrl.modules.common.vdn_net openrl.modules.ddpg_module openrl.modules.dqn_module openrl.modules.gail_module openrl.modules.model_config openrl.modules.networks openrl.modules.networks.base_policy_network openrl.modules.networks.base_value_network openrl.modules.networks.base_value_policy_network openrl.modules.networks.ddpg_network openrl.modules.networks.gail_discriminator openrl.modules.networks.MAT_network openrl.modules.networks.policy_network openrl.modules.networks.policy_value_network openrl.modules.networks.q_network openrl.modules.networks.sac_network openrl.modules.networks.utils openrl.modules.networks.utils.act openrl.modules.networks.utils.attention openrl.modules.networks.utils.cnn openrl.modules.networks.utils.distributed_utils openrl.modules.networks.utils.distributions openrl.modules.networks.utils.mix openrl.modules.networks.utils.mlp openrl.modules.networks.utils.nlp openrl.modules.networks.utils.popart openrl.modules.networks.utils.rnn openrl.modules.networks.utils.running_mean_std openrl.modules.networks.utils.transformer_act openrl.modules.networks.utils.util openrl.modules.networks.utils.vdn openrl.modules.networks.value_network openrl.modules.networks.vdn_network openrl.modules.ppo_module openrl.modules.rl_module openrl.modules.sac_module openrl.modules.utils openrl.modules.utils.util openrl.modules.utils.valuenorm openrl.modules.vdn_module openrl.rewards openrl.rewards.base_reward openrl.rewards.gail_reward openrl.runners openrl.runners.common openrl.runners.common.a2c_agent openrl.runners.common.base_agent openrl.runners.common.bc_agent openrl.runners.common.chat_agent openrl.runners.common.ddpg_agent openrl.runners.common.dqn_agent openrl.runners.common.gail_agent openrl.runners.common.mat_agent openrl.runners.common.ppo_agent openrl.runners.common.rl_agent openrl.runners.common.sac_agent openrl.runners.common.vdn_agent openrl.selfplay openrl.selfplay.callbacks openrl.selfplay.callbacks.base_callback openrl.selfplay.callbacks.selfplay_callback openrl.selfplay.multiplayer_env openrl.selfplay.opponents openrl.selfplay.opponents.base_opponent openrl.selfplay.opponents.jidi_opponent openrl.selfplay.opponents.network_opponent openrl.selfplay.opponents.opponent_env openrl.selfplay.opponents.opponent_template openrl.selfplay.opponents.random_opponent openrl.selfplay.opponents.utils openrl.selfplay.sample_strategy openrl.selfplay.sample_strategy.base_sample_strategy openrl.selfplay.sample_strategy.last_opponent openrl.selfplay.sample_strategy.random_opponent openrl.selfplay.selfplay_api openrl.selfplay.selfplay_api.selfplay_client openrl.selfplay.wrappers openrl.selfplay.wrappers.base_multiplayer_wrapper openrl.selfplay.wrappers.human_opponent_wrapper openrl.selfplay.wrappers.opponent_pool_wrapper openrl.selfplay.wrappers.random_opponent_wrapper openrl.supports openrl.supports.opendata openrl.supports.opendata.utils openrl.supports.opendata.utils.opendata_utils openrl.supports.opengpu openrl.supports.opengpu.gpu_info openrl.supports.opengpu.manager openrl.utils openrl.utils.callbacks openrl.utils.callbacks.callbacks openrl.utils.callbacks.callbacks_factory openrl.utils.callbacks.checkpoint_callback openrl.utils.callbacks.eval_callback openrl.utils.callbacks.processbar_callback openrl.utils.callbacks.stop_callback openrl.utils.custom_data_structure openrl.utils.evaluation openrl.utils.file_tool openrl.utils.logger openrl.utils.type_aliases openrl.utils.util