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