Index

_

__getitem__() (xuance.common.segtree_tool.SegmentTree method) __init__() (xuance.common.segtree_tool.SegmentTree method) __setitem__() (xuance.common.segtree_tool.SegmentTree method) _capacity (xuance.common.segtree_tool.MinSegmentTree attribute) (xuance.common.segtree_tool.SegmentTree attribute) (xuance.common.segtree_tool.SumSegmentTree attribute) _neutral_element (xuance.common.segtree_tool.MinSegmentTree attribute) (xuance.common.segtree_tool.SegmentTree attribute) (xuance.common.segtree_tool.SumSegmentTree attribute)

_operation (xuance.common.segtree_tool.MinSegmentTree attribute) (xuance.common.segtree_tool.SegmentTree attribute) (xuance.common.segtree_tool.SumSegmentTree attribute) _registry (xuance.common.tuning_tools.AlgorithmHyperparametersRegistry attribute) _value (xuance.common.segtree_tool.MinSegmentTree attribute) (xuance.common.segtree_tool.SegmentTree attribute) (xuance.common.segtree_tool.SumSegmentTree attribute)

A

A2C_Agent (class in xuance.mindspore.agents.policy_gradient.a2c_agent) (class in xuance.tensorflow.agents.policy_gradient.a2c_agent) (class in xuance.torch.agents.policy_gradient.a2c_agent) A2C_Learner (class in xuance.mindspore.learners.policy_gradient.a2c_learner) (class in xuance.tensorflow.learners.policy_gradient.a2c_learner) (class in xuance.torch.learners.policy_gradient.a2c_learner) AC_CNN_Atari (class in xuance.mindspore.representations.cnn) (class in xuance.tensorflow.representations.cnn) (class in xuance.torch.representations.cnn) act() (xuance.mindspore.agents.multi_agent_rl.dcg_agents.DCG_Agents method) (xuance.mindspore.learners.multi_agent_rl.dcg_learner.DCG_Learner method) (xuance.tensorflow.agents.multi_agent_rl.dcg_agents.DCG_Agents method) (xuance.tensorflow.learners.multi_agent_rl.dcg_learner.DCG_Learner method) (xuance.torch.learners.multi_agent_rl.dcg_learner.DCG_Learner method) action_space (xuance.environment.utils.wrapper.XuanCeEnvWrapper property) activated_rsample() (xuance.mindspore.utils.distributions.ActivatedDiagGaussianDistribution method) (xuance.tensorflow.utils.distributions.ActivatedDiagGaussianDistribution method) (xuance.torch.utils.distributions.ActivatedDiagGaussianDistribution method) activated_rsample_and_logprob() (xuance.mindspore.utils.distributions.ActivatedDiagGaussianDistribution method) (xuance.tensorflow.utils.distributions.ActivatedDiagGaussianDistribution method) (xuance.torch.utils.distributions.ActivatedDiagGaussianDistribution method) ActivatedDiagGaussianDistribution (class in xuance.mindspore.utils.distributions) (class in xuance.tensorflow.utils.distributions) (class in xuance.torch.utils.distributions) Actor (class in xuance.mindspore.representations.world_model) (class in xuance.mindspore.representations.world_model_v2) (class in xuance.tensorflow.representations.world_model) (class in xuance.tensorflow.representations.world_model_v2) (class in xuance.torch.representations.world_model) (class in xuance.torch.representations.world_model_v2) actor_critic_forward() (xuance.mindspore.policies.dreamer.DreamerV2Policy method) (xuance.mindspore.policies.dreamer.DreamerV3Policy method) (xuance.tensorflow.policies.dreamer.DreamerV2Policy method) (xuance.tensorflow.policies.dreamer.DreamerV3Policy method) (xuance.torch.policies.dreamer.DreamerV2Policy method) (xuance.torch.policies.dreamer.DreamerV3Policy method) actor_forward_fn() (xuance.mindspore.learners.multi_agent_rl.coma_learner.COMA_Learner method) (xuance.tensorflow.learners.policy_gradient.ddpg_learner.DDPG_Learner method) (xuance.tensorflow.learners.policy_gradient.sac_learner.SAC_Learner method) (xuance.tensorflow.learners.policy_gradient.sacdis_learner.SACDIS_Learner method) (xuance.tensorflow.learners.policy_gradient.td3_learner.TD3_Learner method) actor_trainable_variables (xuance.tensorflow.policies.categorical.SACDISPolicy property) (xuance.tensorflow.policies.deterministic.DDPGPolicy property) (xuance.tensorflow.policies.deterministic.TD3Policy property) (xuance.tensorflow.policies.gaussian.SACPolicy property) actor_trainable_variables() (xuance.tensorflow.policies.deterministic_marl.Independent_DDPG_Policy method) (xuance.tensorflow.policies.gaussian_marl.Basic_ISAC_Policy method) ActorCriticPolicy (class in xuance.mindspore.policies.categorical) (class in xuance.mindspore.policies.gaussian) (class in xuance.tensorflow.policies.categorical) (class in xuance.tensorflow.policies.gaussian) (class in xuance.torch.policies.categorical) (class in xuance.torch.policies.gaussian) ActorNet (class in xuance.mindspore.policies.core) (class in xuance.tensorflow.policies.core) (class in xuance.torch.policies.core)

ActorPolicy (class in xuance.mindspore.policies.categorical) (class in xuance.mindspore.policies.gaussian) (class in xuance.tensorflow.policies.categorical) (class in xuance.tensorflow.policies.gaussian) (class in xuance.torch.policies.categorical) (class in xuance.torch.policies.gaussian) Agent (class in xuance.mindspore.agents.base.agent) (class in xuance.tensorflow.agents.base.agent) (class in xuance.torch.agents.base.agent) agent_mask (xuance.environment.utils.wrapper.XuanCeMultiAgentEnvWrapper property) agent_mask() (xuance.environment.multi_agent_env.drones.Drones_MultiAgentEnv method) (xuance.environment.multi_agent_env.mpe.MPE_Env method) (xuance.environment.multi_agent_env.starcraft2.StarCraft2_Env method) (xuance.environment.utils.base.RawMultiAgentEnv method) algo (xuance.common.tuning_tools.HyperParameterTuner attribute) AlgorithmHyperparametersRegistry (class in xuance.common.tuning_tools) alpha_forward_fn() (xuance.tensorflow.learners.policy_gradient.sac_learner.SAC_Learner method) (xuance.tensorflow.learners.policy_gradient.sacdis_learner.SACDIS_Learner method) AlphaLayer (class in xuance.tensorflow.learners.policy_gradient.sac_learner) (class in xuance.tensorflow.learners.policy_gradient.sacdis_learner) AlreadySteppingError arg_constraints (xuance.torch.utils.distributions.TruncatedStandardNormal attribute) as_dict() (xuance.torch.utils.operations.dotdict method) assign_from_flat_grads() (in module xuance.mindspore.utils.operations) (in module xuance.tensorflow.utils.operations) (in module xuance.torch.utils.operations) assign_from_flat_params() (in module xuance.mindspore.utils.operations) (in module xuance.tensorflow.utils.operations) (in module xuance.torch.utils.operations) Atarget() (xuance.mindspore.policies.deterministic.MPDQNPolicy method) (xuance.mindspore.policies.deterministic.PDQNPolicy method) (xuance.mindspore.policies.deterministic.SPDQNPolicy method) (xuance.mindspore.policies.deterministic_marl.Independent_DDPG_Policy method) (xuance.tensorflow.policies.deterministic.MPDQNPolicy method) (xuance.tensorflow.policies.deterministic.PDQNPolicy method) (xuance.tensorflow.policies.deterministic.SPDQNPolicy method) (xuance.tensorflow.policies.deterministic_marl.Independent_DDPG_Policy method) (xuance.torch.policies.deterministic.PDQNPolicy method) (xuance.torch.policies.deterministic_marl.Independent_DDPG_Policy method) Attention (class in xuance.mindspore.representations.vit) (class in xuance.tensorflow.representations.vit) (class in xuance.torch.representations.vit) attention_block() (xuance.mindspore.communications.attention_comm.TarMAC method) (xuance.tensorflow.communications.attention_comm.TarMAC method) (xuance.torch.communications.attention_comm.TarMAC method) auc (xuance.torch.utils.distributions.TruncatedStandardNormal property) auxiliary_forward_fn() (xuance.tensorflow.learners.policy_gradient.ppg_learner.PPG_Learner method) avail_actions (xuance.environment.utils.wrapper.XuanCeMultiAgentEnvWrapper property) avail_actions() (xuance.environment.multi_agent_env.drones.Drones_MultiAgentEnv method) (xuance.environment.multi_agent_env.mpe.MPE_Env method) (xuance.environment.multi_agent_env.starcraft2.StarCraft2_Env method) (xuance.environment.utils.base.RawEnvironment method) (xuance.environment.utils.base.RawMultiAgentEnv method)

B

BaseBuffer (class in xuance.common.memory_tools_marl) BaseCallback (class in xuance.common.callback) BaseComm (class in xuance.mindspore.communications.base_comm) (class in xuance.tensorflow.communications.base_comm) (class in xuance.torch.communications.base_comm) Basic_CNN (class in xuance.mindspore.representations.cnn) (class in xuance.tensorflow.representations.cnn) (class in xuance.torch.representations.cnn) Basic_Identical (class in xuance.mindspore.representations.mlp) (class in xuance.tensorflow.representations.mlp) (class in xuance.torch.representations.mlp) Basic_ISAC_Policy (class in xuance.mindspore.policies.categorical_marl) (class in xuance.mindspore.policies.gaussian_marl) (class in xuance.tensorflow.policies.categorical_marl) (class in xuance.tensorflow.policies.gaussian_marl) (class in xuance.torch.policies.categorical_marl) (class in xuance.torch.policies.gaussian_marl) Basic_MLP (class in xuance.mindspore.representations.mlp) (class in xuance.tensorflow.representations.mlp) (class in xuance.torch.representations.mlp) Basic_RNN (class in xuance.mindspore.representations.rnn) (class in xuance.tensorflow.representations.rnn) (class in xuance.torch.representations.rnn) Basic_ViT (class in xuance.mindspore.representations.vit) (class in xuance.tensorflow.representations.vit) (class in xuance.torch.representations.vit) BasicQhead (class in xuance.mindspore.policies.core) (class in xuance.tensorflow.policies.core) (class in xuance.torch.policies.core) BasicQnetwork (class in xuance.mindspore.policies.deterministic) (class in xuance.mindspore.policies.deterministic_marl) (class in xuance.tensorflow.policies.deterministic) (class in xuance.tensorflow.policies.deterministic_marl) (class in xuance.torch.policies.deterministic) (class in xuance.torch.policies.deterministic_marl) BasicRecurrent (class in xuance.mindspore.policies.core) (class in xuance.tensorflow.policies.core) (class in xuance.torch.policies.core) batch_actions() (xuance.tensorflow.agents.policy_gradient.ppg_agent.PPG_Agent method) benchmark() (xuance.engine.run_competition.RunnerCompetition method) (xuance.engine.run_football.RunnerFootball method) (xuance.engine.run_offlinerl.RunnerOfflineRL method)

BernoulliSafeMode (class in xuance.torch.utils.distributions) Buffer (class in xuance.common.memory_tools) build_actions_mean_input() (xuance.mindspore.learners.multi_agent_rl.mfac_learner.MFAC_Learner method) (xuance.mindspore.learners.multi_agent_rl.mfq_learner.MFQ_Learner method) (xuance.tensorflow.learners.multi_agent_rl.mfac_learner.MFAC_Learner method) (xuance.tensorflow.learners.multi_agent_rl.mfq_learner.MFQ_Learner method) (xuance.torch.learners.multi_agent_rl.mfac_learner.MFAC_Learner method) (xuance.torch.learners.multi_agent_rl.mfq_learner.MFQ_Learner method) build_gcn() (xuance.torch.communications.gnn_comm.DGNComm method) build_optimizer() (xuance.mindspore.learners.multi_agent_rl.coma_learner.COMA_Learner method) (xuance.mindspore.learners.multi_agent_rl.commnet_learner.CommNet_Learner method) (xuance.mindspore.learners.multi_agent_rl.iac_learner.IAC_Learner method) (xuance.tensorflow.learners.multi_agent_rl.coma_learner.COMA_Learner method) (xuance.tensorflow.learners.multi_agent_rl.commnet_learner.CommNet_Learner method) (xuance.tensorflow.learners.multi_agent_rl.iac_learner.IAC_Learner method) (xuance.tensorflow.learners.multi_agent_rl.iddpg_learner.IDDPG_Learner method) (xuance.tensorflow.learners.multi_agent_rl.iql_learner.IQL_Learner method) (xuance.tensorflow.learners.multi_agent_rl.isac_learner.ISAC_Learner method) (xuance.tensorflow.learners.multi_agent_rl.maddpg_learner.MADDPG_Learner method) (xuance.tensorflow.learners.multi_agent_rl.matd3_learner.MATD3_Learner method) (xuance.tensorflow.learners.multi_agent_rl.mfq_learner.MFQ_Learner method) (xuance.tensorflow.learners.multi_agent_rl.qmix_learner.QMIX_Learner method) (xuance.tensorflow.learners.multi_agent_rl.qtran_learner.QTRAN_Learner method) (xuance.tensorflow.learners.multi_agent_rl.vdn_learner.VDN_Learner method) (xuance.tensorflow.learners.multi_agent_rl.wqmix_learner.WQMIX_Learner method) (xuance.torch.learners.multi_agent_rl.coma_learner.COMA_Learner method) (xuance.torch.learners.multi_agent_rl.commnet_learner.CommNet_Learner method) (xuance.torch.learners.multi_agent_rl.iac_learner.IAC_Learner method) build_search_space() (in module xuance.common.tuning_tools) build_training_data() (xuance.mindspore.learners.learner.LearnerMAS method) (xuance.mindspore.learners.multi_agent_rl.coma_learner.COMA_Learner method) (xuance.mindspore.learners.multi_agent_rl.iac_learner.IAC_Learner method) (xuance.mindspore.learners.multi_agent_rl.ic3net_learner.IC3Net_Learner method) (xuance.tensorflow.learners.learner.LearnerMAS method) (xuance.tensorflow.learners.multi_agent_rl.iac_learner.IAC_Learner method) (xuance.tensorflow.learners.multi_agent_rl.ic3net_learner.IC3Net_Learner method) (xuance.torch.learners.learner.LearnerMAS method) (xuance.torch.learners.multi_agent_rl.iac_learner.IAC_Learner method) (xuance.torch.learners.multi_agent_rl.ic3net_learner.IC3Net_Learner method)

C

C51_Agent (class in xuance.mindspore.agents.qlearning_family.c51_agent) (class in xuance.tensorflow.agents.qlearning_family.c51_agent) (class in xuance.torch.agents.qlearning_family.c51_agent) C51_Learner (class in xuance.mindspore.learners.qlearning_family.c51_learner) (class in xuance.tensorflow.learners.qlearning_family.c51_learner) (class in xuance.torch.learners.qlearning_family.c51_learner) C51Qhead (class in xuance.mindspore.policies.core) (class in xuance.tensorflow.policies.core) (class in xuance.torch.policies.core) C51Qnetwork (class in xuance.mindspore.policies.deterministic) (class in xuance.tensorflow.policies.deterministic) (class in xuance.torch.policies.deterministic) call() (xuance.tensorflow.policies.categorical.ActorCriticPolicy method) (xuance.tensorflow.policies.categorical.ActorPolicy method) (xuance.tensorflow.policies.categorical.PPGActorCritic method) (xuance.tensorflow.policies.categorical.SACDISPolicy method) (xuance.tensorflow.policies.categorical_marl.COMA_Policy method) (xuance.tensorflow.policies.categorical_marl.MAAC_Policy method) (xuance.tensorflow.policies.categorical_marl.MAAC_Policy_Share method) (xuance.tensorflow.policies.categorical_marl.MeanFieldActorCriticPolicy method) (xuance.tensorflow.policies.coordination_graph.DCG_payoff method) (xuance.tensorflow.policies.coordination_graph.DCG_utility method) (xuance.tensorflow.policies.core.ActorNet method) (xuance.tensorflow.policies.core.BasicQhead method) (xuance.tensorflow.policies.core.BasicRecurrent method) (xuance.tensorflow.policies.core.C51Qhead method) (xuance.tensorflow.policies.core.CategoricalActorNet method) (xuance.tensorflow.policies.core.CriticNet method) (xuance.tensorflow.policies.core.DuelQhead method) (xuance.tensorflow.policies.core.GaussianActorNet method) (xuance.tensorflow.policies.core.GaussianActorNet_SAC method) (xuance.tensorflow.policies.core.QMIX_FF_mixer method) (xuance.tensorflow.policies.core.QMIX_mixer method) (xuance.tensorflow.policies.core.QRDQNhead method) (xuance.tensorflow.policies.core.QTRAN_alt method) (xuance.tensorflow.policies.core.QTRAN_base method) (xuance.tensorflow.policies.core.VDN_mixer method) (xuance.tensorflow.policies.deterministic.BasicQnetwork method) (xuance.tensorflow.policies.deterministic.C51Qnetwork method) (xuance.tensorflow.policies.deterministic.DDPGPolicy method) (xuance.tensorflow.policies.deterministic.DRQNPolicy method) (xuance.tensorflow.policies.deterministic.DuelQnetwork method) (xuance.tensorflow.policies.deterministic.NoisyQnetwork method) (xuance.tensorflow.policies.deterministic.QRDQN_Network method) (xuance.tensorflow.policies.deterministic.TD3Policy method) (xuance.tensorflow.policies.deterministic_marl.BasicQnetwork method) (xuance.tensorflow.policies.deterministic_marl.DCG_policy method) (xuance.tensorflow.policies.deterministic_marl.Independent_DDPG_Policy method) (xuance.tensorflow.policies.deterministic_marl.MFQnetwork method) (xuance.tensorflow.policies.deterministic_marl.Qtran_MixingQnetwork method) (xuance.tensorflow.policies.gaussian.ActorCriticPolicy method) (xuance.tensorflow.policies.gaussian.ActorPolicy method) (xuance.tensorflow.policies.gaussian.PPGActorCritic method) (xuance.tensorflow.policies.gaussian.SACPolicy method) (xuance.tensorflow.policies.gaussian_marl.Basic_ISAC_Policy method) (xuance.tensorflow.policies.gaussian_marl.MAAC_Policy method) (xuance.tensorflow.representations.cnn.Basic_CNN method) (xuance.tensorflow.representations.mlp.Basic_Identical method) (xuance.tensorflow.representations.mlp.Basic_MLP method) can_sample() (xuance.common.memory_tools.RecurrentOffPolicyBuffer method) CategoricalActorNet (class in xuance.mindspore.policies.core) (class in xuance.tensorflow.policies.core) (class in xuance.torch.policies.core) CategoricalActorNet_SAC (class in xuance.mindspore.policies.core) (class in xuance.tensorflow.policies.core) (class in xuance.torch.policies.core) CategoricalDistribution (class in xuance.mindspore.utils.distributions) (class in xuance.tensorflow.utils.distributions) (class in xuance.torch.utils.distributions) cdf() (xuance.torch.utils.distributions.TruncatedNormal method) (xuance.torch.utils.distributions.TruncatedStandardNormal method) clear() (xuance.common.memory_offline.OfflineBuffer_D4RL method) (xuance.common.memory_tools.Buffer method) (xuance.common.memory_tools.DummyOffPolicyBuffer method) (xuance.common.memory_tools.DummyOffPolicyBuffer_Atari method) (xuance.common.memory_tools.DummyOnPolicyBuffer method) (xuance.common.memory_tools.DummyOnPolicyBuffer_Atari method) (xuance.common.memory_tools.PerOffPolicyBuffer method) (xuance.common.memory_tools.RecurrentOffPolicyBuffer method) (xuance.common.memory_tools.SequentialReplayBuffer method) (xuance.common.memory_tools_marl.BaseBuffer method) (xuance.common.memory_tools_marl.IC3Net_OnPolicyBuffer_RNN method) (xuance.common.memory_tools_marl.MARL_OffPolicyBuffer method) (xuance.common.memory_tools_marl.MARL_OffPolicyBuffer_RNN method) (xuance.common.memory_tools_marl.MARL_OnPolicyBuffer method) (xuance.common.memory_tools_marl.MARL_OnPolicyBuffer_RNN method) (xuance.common.memory_tools_marl.MeanField_OffPolicyBuffer method) (xuance.common.memory_tools_marl.MeanField_OffPolicyBuffer_RNN method) (xuance.common.memory_tools_marl.MeanField_OnPolicyBuffer method) (xuance.common.memory_tools_marl.MeanField_OnPolicyBuffer_RNN method) clear_episodes() (xuance.common.memory_tools_marl.IC3Net_OnPolicyBuffer_RNN method) (xuance.common.memory_tools_marl.MARL_OffPolicyBuffer_RNN method) (xuance.common.memory_tools_marl.MARL_OnPolicyBuffer_RNN method) (xuance.common.memory_tools_marl.MeanField_OffPolicyBuffer_RNN method) (xuance.common.memory_tools_marl.MeanField_OnPolicyBuffer_RNN method) clear_mpi_env_vars() (in module xuance.environment.vector_envs.env_utils) clip_grads() (in module xuance.mindspore.utils.operations) close() (xuance.environment.multi_agent_env.drones.Drones_MultiAgentEnv method) (xuance.environment.multi_agent_env.football.GFootball_Env method) (xuance.environment.multi_agent_env.mpe.MPE_Env method) (xuance.environment.multi_agent_env.robotic_warehouse.RoboticWarehouseEnv method) (xuance.environment.multi_agent_env.starcraft2.StarCraft2_Env method) (xuance.environment.single_agent_env.metadrive.MetaDrive_Env method) (xuance.environment.single_agent_env.minigrid.MiniGridEnv method) (xuance.environment.single_agent_env.platform.PlatformEnv method) (xuance.environment.utils.base.RawEnvironment method) (xuance.environment.utils.base.RawMultiAgentEnv method) (xuance.environment.utils.wrapper.XuanCeEnvWrapper method) (xuance.environment.vector_envs.vector_env.VecEnv method) close_extras() (xuance.environment.vector_envs.dummy.dummy_vec_env.DummyVecEnv method) (xuance.environment.vector_envs.dummy.dummy_vec_maenv.DummyVecMultiAgentEnv method) (xuance.environment.vector_envs.subprocess.subproc_vec_env.SubprocVecEnv method) (xuance.environment.vector_envs.subprocess.subproc_vec_maenv.SubprocVecMultiAgentEnv method) (xuance.environment.vector_envs.vector_env.VecEnv method) CloudpickleWrapper (class in xuance.environment.vector_envs.env_utils) CNN (class in xuance.mindspore.utils.layers4dreamer) (class in xuance.tensorflow.utils.layers4dreamer) (class in xuance.torch.utils.layers4dreamer) cnn_block() (in module xuance.mindspore.utils.layers) (in module xuance.tensorflow.utils.layers) (in module xuance.torch.utils.layers) cnn_forward() (in module xuance.mindspore.utils.layers4dreamer) (in module xuance.tensorflow.utils.layers4dreamer) (in module xuance.torch.utils.layers4dreamer) cnn_keys (xuance.mindspore.utils.layers4dreamer.MultiDecoder property) (xuance.mindspore.utils.layers4dreamer.MultiEncoder property) (xuance.tensorflow.utils.layers4dreamer.MultiDecoder property) (xuance.tensorflow.utils.layers4dreamer.MultiEncoder property) (xuance.torch.utils.layers4dreamer.MultiDecoder property) (xuance.torch.utils.layers4dreamer.MultiEncoder property) CNNDecoder (class in xuance.mindspore.representations.world_model) (class in xuance.mindspore.representations.world_model_v2) (class in xuance.tensorflow.representations.world_model) (class in xuance.tensorflow.representations.world_model_v2) (class in xuance.torch.representations.world_model) (class in xuance.torch.representations.world_model_v2) CNNEncoder (class in xuance.mindspore.representations.world_model) (class in xuance.mindspore.representations.world_model_v2) (class in xuance.tensorflow.representations.world_model) (class in xuance.tensorflow.representations.world_model_v2) (class in xuance.torch.representations.world_model) (class in xuance.torch.representations.world_model_v2) collect_device_info() (in module xuance.mindspore.utils.device) (in module xuance.tensorflow.utils.device) (in module xuance.torch.utils.device) COMA_Agents (class in xuance.mindspore.agents.multi_agent_rl.coma_agents) (class in xuance.tensorflow.agents.multi_agent_rl.coma_agents) (class in xuance.torch.agents.multi_agent_rl.coma_agents) COMA_Learner (class in xuance.mindspore.learners.multi_agent_rl.coma_learner) (class in xuance.tensorflow.learners.multi_agent_rl.coma_learner) (class in xuance.torch.learners.multi_agent_rl.coma_learner) COMA_Policy (class in xuance.mindspore.policies.categorical_marl) (class in xuance.tensorflow.policies.categorical_marl) (class in xuance.torch.policies.categorical_marl) combine_actions() (in module xuance.environment.vector_envs.env_utils) comm (xuance.common.statistic_tools.RunningMeanStd attribute) CommNet (class in xuance.mindspore.communications.comm_net) (class in xuance.tensorflow.communications.comm_net) (class in xuance.torch.communications.comm_net) CommNet_Agents (class in xuance.mindspore.agents.multi_agent_rl.commnet_agents) (class in xuance.tensorflow.agents.multi_agent_rl.commnet_agents) (class in xuance.torch.agents.multi_agent_rl.commnet_agents) CommNet_Learner (class in xuance.mindspore.learners.multi_agent_rl.commnet_learner) (class in xuance.tensorflow.learners.multi_agent_rl.commnet_learner) (class in xuance.torch.learners.multi_agent_rl.commnet_learner)

CommNet_Policy (class in xuance.mindspore.policies.categorical_marl) (class in xuance.tensorflow.policies.categorical_marl) (class in xuance.torch.policies.categorical_marl) compute_fisher_information() (xuance.mindspore.learners.policy_gradient.npg_learner.NPG_Learner method) (xuance.tensorflow.learners.policy_gradient.npg_learner.NPG_Learner method) (xuance.torch.learners.policy_gradient.npg_learner.NPG_Learner method) compute_lambda_values() (in module xuance.torch.utils.operations) (xuance.mindspore.policies.dreamer.DreamerV2Policy static method) (xuance.tensorflow.policies.dreamer.DreamerV2Policy static method) (xuance.torch.policies.dreamer.DreamerV2Policy static method) compute_mean_std() (in module xuance.common.offline_util) compute_stochastic_state() (in module xuance.torch.utils.operations) con_action() (xuance.mindspore.policies.deterministic.MPDQNPolicy method) (xuance.mindspore.policies.deterministic.PDQNPolicy method) (xuance.mindspore.policies.deterministic.SPDQNPolicy method) (xuance.tensorflow.policies.deterministic.MPDQNPolicy method) (xuance.tensorflow.policies.deterministic.PDQNPolicy method) (xuance.tensorflow.policies.deterministic.SPDQNPolicy method) (xuance.torch.policies.deterministic.PDQNPolicy method) config_path (xuance.common.tuning_tools.HyperParameterTuner attribute) construct() (xuance.mindspore.learners.multi_agent_rl.dcg_learner.DCG_Learner.PolicyNetWithLossCell method) (xuance.mindspore.learners.policy_gradient.mpdqn_learner.MPDQN_Learner.ConActorNetWithLossCell method) (xuance.mindspore.learners.policy_gradient.mpdqn_learner.MPDQN_Learner.QNetWithLossCell method) (xuance.mindspore.learners.policy_gradient.pdqn_learner.PDQN_Learner.ConActorNetWithLossCell method) (xuance.mindspore.learners.policy_gradient.pdqn_learner.PDQN_Learner.QNetWithLossCell method) (xuance.mindspore.learners.policy_gradient.spdqn_learner.SPDQN_Learner.ConActorNetWithLossCell method) (xuance.mindspore.learners.policy_gradient.spdqn_learner.SPDQN_Learner.QNetWithLossCell method) (xuance.mindspore.policies.categorical.ActorCriticPolicy method) (xuance.mindspore.policies.categorical.ActorPolicy method) (xuance.mindspore.policies.categorical.PPGActorCritic method) (xuance.mindspore.policies.categorical.SACDISPolicy method) (xuance.mindspore.policies.categorical_marl.COMA_Policy method) (xuance.mindspore.policies.categorical_marl.MAAC_Policy method) (xuance.mindspore.policies.categorical_marl.MAAC_Policy_Share method) (xuance.mindspore.policies.categorical_marl.MeanFieldActorCriticPolicy method) (xuance.mindspore.policies.coordination_graph.DCG_payoff method) (xuance.mindspore.policies.coordination_graph.DCG_utility method) (xuance.mindspore.policies.core.ActorNet method) (xuance.mindspore.policies.core.BasicQhead method) (xuance.mindspore.policies.core.BasicRecurrent method) (xuance.mindspore.policies.core.C51Qhead method) (xuance.mindspore.policies.core.CategoricalActorNet method) (xuance.mindspore.policies.core.CategoricalActorNet_SAC method) (xuance.mindspore.policies.core.CriticNet method) (xuance.mindspore.policies.core.DuelQhead method) (xuance.mindspore.policies.core.GaussianActorNet method) (xuance.mindspore.policies.core.GaussianActorNet_SAC method) (xuance.mindspore.policies.core.QMIX_FF_mixer method) (xuance.mindspore.policies.core.QMIX_mixer method) (xuance.mindspore.policies.core.QRDQNhead method) (xuance.mindspore.policies.core.QTRAN_alt method) (xuance.mindspore.policies.core.QTRAN_base method) (xuance.mindspore.policies.core.VDN_mixer method) (xuance.mindspore.policies.deterministic.BasicQnetwork method) (xuance.mindspore.policies.deterministic.C51Qnetwork method) (xuance.mindspore.policies.deterministic.DDPGPolicy method) (xuance.mindspore.policies.deterministic.DRQNPolicy method) (xuance.mindspore.policies.deterministic.DuelQnetwork method) (xuance.mindspore.policies.deterministic.MPDQNPolicy method) (xuance.mindspore.policies.deterministic.NoisyQnetwork method) (xuance.mindspore.policies.deterministic.PDQNPolicy method) (xuance.mindspore.policies.deterministic.QRDQN_Network method) (xuance.mindspore.policies.deterministic.SPDQNPolicy method) (xuance.mindspore.policies.deterministic.TD3Policy method) (xuance.mindspore.policies.deterministic_marl.BasicQnetwork method) (xuance.mindspore.policies.deterministic_marl.DCG_policy method) (xuance.mindspore.policies.deterministic_marl.Independent_DDPG_Policy method) (xuance.mindspore.policies.deterministic_marl.MFQnetwork method) (xuance.mindspore.policies.deterministic_marl.Qtran_MixingQnetwork method) (xuance.mindspore.policies.gaussian.ActorCriticPolicy method) (xuance.mindspore.policies.gaussian.ActorPolicy method) (xuance.mindspore.policies.gaussian.PPGActorCritic method) (xuance.mindspore.policies.gaussian.SACPolicy method) (xuance.mindspore.policies.gaussian_marl.Basic_ISAC_Policy method) (xuance.mindspore.policies.gaussian_marl.MAAC_Policy method) (xuance.mindspore.representations.cnn.AC_CNN_Atari method) (xuance.mindspore.representations.cnn.Basic_CNN method) (xuance.mindspore.representations.mlp.Basic_Identical method) (xuance.mindspore.representations.mlp.Basic_MLP method) (xuance.mindspore.representations.rnn.Basic_RNN method) Coordination_Graph (class in xuance.mindspore.policies.coordination_graph) (class in xuance.tensorflow.policies.coordination_graph) (class in xuance.torch.policies.coordination_graph) copy_obs_dict() (in module xuance.environment.vector_envs.env_utils) copy_target() (xuance.mindspore.agents.contrastive_unsupervised_rl.curl_agent.CURL_Policy method), [1] (xuance.mindspore.agents.contrastive_unsupervised_rl.spr_agent.SPR_Policy method), [1] (xuance.mindspore.policies.categorical_marl.COMA_Policy method) (xuance.mindspore.policies.deterministic.BasicQnetwork method) (xuance.mindspore.policies.deterministic.C51Qnetwork method) (xuance.mindspore.policies.deterministic.DRQNPolicy method) (xuance.mindspore.policies.deterministic.DuelQnetwork method) (xuance.mindspore.policies.deterministic.NoisyQnetwork method) (xuance.mindspore.policies.deterministic.QRDQN_Network method) (xuance.mindspore.policies.deterministic_marl.BasicQnetwork method) (xuance.mindspore.policies.deterministic_marl.DCG_policy method) (xuance.mindspore.policies.deterministic_marl.MFQnetwork method) (xuance.mindspore.policies.deterministic_marl.MixingQnetwork method) (xuance.mindspore.policies.deterministic_marl.Qtran_MixingQnetwork method) (xuance.mindspore.policies.deterministic_marl.Weighted_MixingQnetwork method) (xuance.tensorflow.agents.contrastive_unsupervised_rl.curl_agent.CURL_Policy method), [1] (xuance.tensorflow.agents.contrastive_unsupervised_rl.spr_agent.SPR_Policy method), [1] (xuance.tensorflow.policies.categorical_marl.COMA_Policy method) (xuance.tensorflow.policies.deterministic.BasicQnetwork method) (xuance.tensorflow.policies.deterministic.C51Qnetwork method) (xuance.tensorflow.policies.deterministic.DRQNPolicy method) (xuance.tensorflow.policies.deterministic.DuelQnetwork method) (xuance.tensorflow.policies.deterministic.NoisyQnetwork method) (xuance.tensorflow.policies.deterministic.QRDQN_Network method) (xuance.tensorflow.policies.deterministic_marl.BasicQnetwork method) (xuance.tensorflow.policies.deterministic_marl.DCG_policy method) (xuance.tensorflow.policies.deterministic_marl.MFQnetwork method) (xuance.tensorflow.policies.deterministic_marl.MixingQnetwork method) (xuance.tensorflow.policies.deterministic_marl.Qtran_MixingQnetwork method) (xuance.tensorflow.policies.deterministic_marl.Weighted_MixingQnetwork method) (xuance.torch.agents.contrastive_unsupervised_rl.curl_agent.CURL_Policy method), [1] (xuance.torch.agents.contrastive_unsupervised_rl.spr_agent.SPR_Policy method), [1] (xuance.torch.policies.categorical_marl.COMA_Policy method) (xuance.torch.policies.deterministic.BasicQnetwork method) (xuance.torch.policies.deterministic.C51Qnetwork method) (xuance.torch.policies.deterministic.DRQNPolicy method) (xuance.torch.policies.deterministic.DuelQnetwork method) (xuance.torch.policies.deterministic.NoisyQnetwork method) (xuance.torch.policies.deterministic.QRDQN_Network method) (xuance.torch.policies.deterministic_marl.BasicQnetwork method) (xuance.torch.policies.deterministic_marl.DCG_policy method) (xuance.torch.policies.deterministic_marl.MFQnetwork method) (xuance.torch.policies.deterministic_marl.MixingQnetwork method) (xuance.torch.policies.deterministic_marl.Qtran_MixingQnetwork method) (xuance.torch.policies.deterministic_marl.Weighted_MixingQnetwork method) create_adjacency_matrix() (xuance.torch.communications.gnn_comm.DGNComm method) create_directory() (in module xuance.common.common_tools) create_layer_with_args() (in module xuance.mindspore.utils.layers4dreamer) (in module xuance.tensorflow.utils.layers4dreamer) (in module xuance.torch.utils.layers4dreamer) create_layers() (in module xuance.mindspore.utils.layers4dreamer) (in module xuance.tensorflow.utils.layers4dreamer) (in module xuance.torch.utils.layers4dreamer) create_memory() (in module xuance.common.memory_tools) create_mlp() (xuance.mindspore.communications.comm_net.CommNet method) (xuance.tensorflow.communications.comm_net.CommNet method) (xuance.torch.communications.comm_net.CommNet method) critic_forward_fn() (xuance.mindspore.learners.multi_agent_rl.coma_learner.COMA_Learner method) (xuance.tensorflow.learners.policy_gradient.ddpg_learner.DDPG_Learner method) (xuance.tensorflow.learners.policy_gradient.ppg_learner.PPG_Learner method) (xuance.tensorflow.learners.policy_gradient.sac_learner.SAC_Learner method) (xuance.tensorflow.learners.policy_gradient.sacdis_learner.SACDIS_Learner method) (xuance.tensorflow.learners.policy_gradient.td3_learner.TD3_Learner method) critic_trainable_variables (xuance.tensorflow.policies.categorical.SACDISPolicy property) (xuance.tensorflow.policies.deterministic.DDPGPolicy property) (xuance.tensorflow.policies.deterministic.TD3Policy property) (xuance.tensorflow.policies.gaussian.SACPolicy property) critic_trainable_variables() (xuance.tensorflow.policies.deterministic_marl.Independent_DDPG_Policy method) (xuance.tensorflow.policies.deterministic_marl.MATD3_Policy method) (xuance.tensorflow.policies.gaussian_marl.Basic_ISAC_Policy method) CriticNet (class in xuance.mindspore.policies.core) (class in xuance.tensorflow.policies.core) (class in xuance.torch.policies.core) CURL_Agent (class in xuance.mindspore.agents.contrastive_unsupervised_rl.curl_agent), [1] (class in xuance.tensorflow.agents.contrastive_unsupervised_rl.curl_agent), [1] (class in xuance.torch.agents.contrastive_unsupervised_rl.curl_agent), [1] CURL_Learner (class in xuance.mindspore.learners.contrastive_unsupervised_rl.curl_learner) (class in xuance.tensorflow.learners.contrastive_unsupervised_rl.curl_learner) (class in xuance.torch.learners.contrastive_unsupervised_rl.curl_learner) CURL_Policy (class in xuance.mindspore.agents.contrastive_unsupervised_rl.curl_agent), [1] (class in xuance.tensorflow.agents.contrastive_unsupervised_rl.curl_agent), [1] (class in xuance.torch.agents.contrastive_unsupervised_rl.curl_agent), [1]

D

d4rl2buffer() (xuance.common.memory_offline.OfflineBuffer_D4RL method) DCG_Agents (class in xuance.mindspore.agents.multi_agent_rl.dcg_agents) (class in xuance.tensorflow.agents.multi_agent_rl.dcg_agents) (class in xuance.torch.agents.multi_agent_rl.dcg_agents) DCG_Learner (class in xuance.mindspore.learners.multi_agent_rl.dcg_learner) (class in xuance.tensorflow.learners.multi_agent_rl.dcg_learner) (class in xuance.torch.learners.multi_agent_rl.dcg_learner) DCG_Learner.PolicyNetWithLossCell (class in xuance.mindspore.learners.multi_agent_rl.dcg_learner) DCG_payoff (class in xuance.mindspore.policies.coordination_graph) (class in xuance.tensorflow.policies.coordination_graph) (class in xuance.torch.policies.coordination_graph) DCG_policy (class in xuance.mindspore.policies.deterministic_marl) (class in xuance.tensorflow.policies.deterministic_marl) (class in xuance.torch.policies.deterministic_marl) DCG_utility (class in xuance.mindspore.policies.coordination_graph) (class in xuance.tensorflow.policies.coordination_graph) (class in xuance.torch.policies.coordination_graph) DDPG_Agent (class in xuance.mindspore.agents.policy_gradient.ddpg_agent) (class in xuance.tensorflow.agents.policy_gradient.ddpg_agent) (class in xuance.torch.agents.policy_gradient.ddpg_agent) DDPG_Learner (class in xuance.mindspore.learners.policy_gradient.ddpg_learner) (class in xuance.tensorflow.learners.policy_gradient.ddpg_learner) (class in xuance.torch.learners.policy_gradient.ddpg_learner) DDPGPolicy (class in xuance.mindspore.policies.deterministic) (class in xuance.tensorflow.policies.deterministic) (class in xuance.torch.policies.deterministic) DDQN_Agent (class in xuance.mindspore.agents.qlearning_family.ddqn_agent) (class in xuance.tensorflow.agents.qlearning_family.ddqn_agent) (class in xuance.torch.agents.qlearning_family.ddqn_agent) DDQN_Learner (class in xuance.mindspore.learners.qlearning_family.ddqn_learner) (class in xuance.tensorflow.learners.qlearning_family.ddqn_learner) (class in xuance.torch.learners.qlearning_family.ddqn_learner) DeCNN (class in xuance.mindspore.utils.layers4dreamer) (class in xuance.tensorflow.utils.layers4dreamer) (class in xuance.torch.utils.layers4dreamer) default (xuance.common.tuning_tools.Hyperparameter attribute), [1] denormalize() (xuance.mindspore.utils.value_norm.ValueNorm method) (xuance.tensorflow.utils.value_norm.ValueNorm method) (xuance.torch.utils.value_norm.ValueNorm method) deterministic_sample() (xuance.mindspore.utils.distributions.CategoricalDistribution method) (xuance.mindspore.utils.distributions.DiagGaussianDistribution method) (xuance.mindspore.utils.distributions.Distribution method) (xuance.tensorflow.utils.distributions.CategoricalDistribution method) (xuance.tensorflow.utils.distributions.DiagGaussianDistribution method) (xuance.tensorflow.utils.distributions.Distribution method) (xuance.torch.utils.distributions.CategoricalDistribution method) (xuance.torch.utils.distributions.DiagGaussianDistribution method) (xuance.torch.utils.distributions.Distribution method) device (xuance.torch.policies.coordination_graph.DCG_utility attribute) DGNComm (class in xuance.mindspore.communications.gnn_comm) (class in xuance.tensorflow.communications.gnn_comm) (class in xuance.torch.communications.gnn_comm) DiagGaussianDistribution (class in xuance.mindspore.utils.distributions) (class in xuance.tensorflow.utils.distributions) (class in xuance.torch.utils.distributions) dict_to_obs() (in module xuance.environment.vector_envs.env_utils) discount_cumsum() (in module xuance.common.common_tools) Distribution (class in xuance.mindspore.utils.distributions) (class in xuance.tensorflow.utils.distributions) (class in xuance.torch.utils.distributions) distribution (xuance.common.tuning_tools.Hyperparameter attribute), [1] distribution() (xuance.mindspore.policies.core.CategoricalActorNet method) (xuance.mindspore.policies.core.CategoricalActorNet_SAC method) (xuance.mindspore.policies.core.GaussianActorNet method) (xuance.mindspore.policies.core.GaussianActorNet_SAC method) (xuance.tensorflow.policies.core.CategoricalActorNet method) (xuance.tensorflow.policies.core.GaussianActorNet method) (xuance.tensorflow.policies.core.GaussianActorNet_SAC method) dotdict (class in xuance.torch.utils.operations) DQN_Agent (class in xuance.mindspore.agents.qlearning_family.dqn_agent) (class in xuance.tensorflow.agents.qlearning_family.dqn_agent) (class in xuance.torch.agents.qlearning_family.dqn_agent)

DQN_Learner (class in xuance.mindspore.learners.qlearning_family.dqn_learner) (class in xuance.tensorflow.learners.qlearning_family.dqn_learner) (class in xuance.torch.learners.qlearning_family.dqn_learner) DreamerV2_Learner (class in xuance.mindspore.learners.model_based.dreamer_v2_learner) (class in xuance.tensorflow.learners.model_based.dreamer_v2_learner) (class in xuance.torch.learners.model_based.dreamer_v2_learner) DreamerV2Agent (class in xuance.mindspore.agents.model_based_rl.dreamer_v2_agent) (class in xuance.tensorflow.agents.model_based_rl.dreamer_v2_agent) (class in xuance.torch.agents.model_based_rl.dreamer_v2_agent) DreamerV2Policy (class in xuance.mindspore.policies.dreamer) (class in xuance.tensorflow.policies.dreamer) (class in xuance.torch.policies.dreamer) DreamerV2WorldModel (class in xuance.mindspore.representations.world_model_v2) (class in xuance.tensorflow.representations.world_model_v2) (class in xuance.torch.representations.world_model_v2) DreamerV3_Learner (class in xuance.mindspore.learners.model_based.dreamer_v3_learner) (class in xuance.tensorflow.learners.model_based.dreamer_v3_learner) (class in xuance.torch.learners.model_based.dreamer_v3_learner) DreamerV3Agent (class in xuance.mindspore.agents.model_based_rl.dreamer_v3_agent) (class in xuance.tensorflow.agents.model_based_rl.dreamer_v3_agent) (class in xuance.torch.agents.model_based_rl.dreamer_v3_agent) DreamerV3Policy (class in xuance.mindspore.policies.dreamer) (class in xuance.tensorflow.policies.dreamer) (class in xuance.torch.policies.dreamer) DreamerV3WorldModel (class in xuance.mindspore.representations.world_model) (class in xuance.tensorflow.representations.world_model) (class in xuance.torch.representations.world_model) Drones_MultiAgentEnv (class in xuance.environment.multi_agent_env.drones) DrQ_Agent (class in xuance.mindspore.agents.contrastive_unsupervised_rl.drq_agent), [1] (class in xuance.tensorflow.agents.contrastive_unsupervised_rl.drq_agent), [1] (class in xuance.torch.agents.contrastive_unsupervised_rl.drq_agent), [1] DrQ_Learner (class in xuance.mindspore.learners.contrastive_unsupervised_rl.drq_learner) (class in xuance.tensorflow.learners.contrastive_unsupervised_rl.drq_learner) (class in xuance.torch.learners.contrastive_unsupervised_rl.drq_learner) DRQN_Agent (class in xuance.mindspore.agents.qlearning_family.drqn_agent) (class in xuance.tensorflow.agents.qlearning_family.drqn_agent) (class in xuance.torch.agents.qlearning_family.drqn_agent) DRQN_Learner (class in xuance.mindspore.learners.qlearning_family.drqn_learner) (class in xuance.tensorflow.learners.qlearning_family.drqn_learner) (class in xuance.torch.learners.qlearning_family.drqn_learner) DRQNPolicy (class in xuance.mindspore.policies.deterministic) (class in xuance.tensorflow.policies.deterministic) (class in xuance.torch.policies.deterministic) DuelDQN_Agent (class in xuance.mindspore.agents.qlearning_family.dueldqn_agent) (class in xuance.tensorflow.agents.qlearning_family.dueldqn_agent) (class in xuance.torch.agents.qlearning_family.dueldqn_agent) DuelDQN_Learner (class in xuance.mindspore.learners.qlearning_family.dueldqn_learner) (class in xuance.tensorflow.learners.qlearning_family.dueldqn_learner) (class in xuance.torch.learners.qlearning_family.dueldqn_learner) DuelQhead (class in xuance.mindspore.policies.core) (class in xuance.tensorflow.policies.core) (class in xuance.torch.policies.core) DuelQnetwork (class in xuance.mindspore.policies.deterministic) (class in xuance.tensorflow.policies.deterministic) (class in xuance.torch.policies.deterministic) DummyOffPolicyBuffer (class in xuance.common.memory_tools) DummyOffPolicyBuffer_Atari (class in xuance.common.memory_tools) DummyOnPolicyBuffer (class in xuance.common.memory_tools) DummyOnPolicyBuffer_Atari (class in xuance.common.memory_tools) DummyVecEnv (class in xuance.environment.vector_envs.dummy.dummy_vec_env) DummyVecEnv_Atari (class in xuance.environment.vector_envs.dummy.dummy_vec_env) DummyVecEnv_Football (class in xuance.environment.vector_envs.dummy.dummy_vec_maenv) DummyVecEnv_StarCraft2 (class in xuance.environment.vector_envs.dummy.dummy_vec_maenv) DummyVecMultiAgentEnv (class in xuance.environment.vector_envs.dummy.dummy_vec_maenv) dynamic() (xuance.mindspore.representations.world_model.RSSM method) (xuance.mindspore.representations.world_model_v2.RSSM method) (xuance.tensorflow.representations.world_model.RSSM method) (xuance.tensorflow.representations.world_model_v2.RSSM method) (xuance.torch.representations.world_model.RSSM method) (xuance.torch.representations.world_model_v2.RSSM method)

E

encoder (xuance.mindspore.representations.world_model_v2.WorldModel attribute) (xuance.tensorflow.representations.world_model_v2.WorldModel attribute) (xuance.torch.representations.world_model_v2.WorldModel attribute) end_episode() (xuance.mindspore.agents.policy_gradient.pdqn_agent.PDQN_Agent method) (xuance.tensorflow.agents.policy_gradient.pdqn_agent.PDQN_Agent method) (xuance.torch.agents.policy_gradient.pdqn_agent.PDQN_Agent method) entropy() (xuance.mindspore.utils.distributions.CategoricalDistribution method) (xuance.mindspore.utils.distributions.DiagGaussianDistribution method) (xuance.mindspore.utils.distributions.Distribution method) (xuance.tensorflow.utils.distributions.CategoricalDistribution method) (xuance.tensorflow.utils.distributions.DiagGaussianDistribution method) (xuance.tensorflow.utils.distributions.Distribution method) (xuance.torch.utils.distributions.CategoricalDistribution method) (xuance.torch.utils.distributions.DiagGaussianDistribution method) (xuance.torch.utils.distributions.Distribution method) (xuance.torch.utils.distributions.TruncatedStandardNormal method) env_info (xuance.environment.utils.wrapper.XuanCeMultiAgentEnvWrapper property) EpisodeBuffer (class in xuance.common.memory_tools) epsilon (xuance.common.statistic_tools.RunningMeanStd attribute)

estimate_total_iterations() (xuance.mindspore.learners.learner.Learner method) (xuance.mindspore.learners.learner.LearnerMAS method) (xuance.mindspore.learners.policy_gradient.ppo_learner.PPO_Learner method) (xuance.tensorflow.learners.learner.Learner method) (xuance.tensorflow.learners.policy_gradient.ppo_learner.PPO_Learner method) (xuance.torch.learners.learner.Learner method) (xuance.torch.learners.learner.LearnerMAS method) (xuance.torch.learners.multi_agent_rl.iac_learner.IAC_Learner method) (xuance.torch.learners.policy_gradient.a2c_learner.A2C_Learner method) (xuance.torch.learners.policy_gradient.pg_learner.PG_Learner method) (xuance.torch.learners.policy_gradient.ppg_learner.PPG_Learner method) (xuance.torch.learners.policy_gradient.ppo_learner.PPO_Learner method) (xuance.torch.learners.policy_gradient.ppokl_learner.PPOKL_Learner method) eval_env_fn() (xuance.common.tuning_tools.HyperParameterTuner method) exploration() (xuance.mindspore.agents.core.off_policy.OffPolicyAgent method) (xuance.mindspore.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.tensorflow.agents.core.off_policy.OffPolicyAgent method) (xuance.tensorflow.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.torch.agents.core.off_policy.OffPolicyAgent method) (xuance.torch.agents.core.off_policy_marl.OffPolicyMARLAgents method)

F

FeedForward (class in xuance.mindspore.representations.vit) (class in xuance.tensorflow.representations.vit) (class in xuance.torch.representations.vit) find_prefixsum_idx() (xuance.common.segtree_tool.SumSegmentTree method) finish() (xuance.mindspore.agents.base.agent.Agent method) (xuance.mindspore.agents.base.agents_marl.MARLAgents method) (xuance.tensorflow.agents.base.agent.Agent method) (xuance.tensorflow.agents.base.agents_marl.MARLAgents method) (xuance.torch.agents.base.agent.Agent method) (xuance.torch.agents.base.agents_marl.MARLAgents method) finish_path() (xuance.common.memory_tools.Buffer method) (xuance.common.memory_tools.DummyOnPolicyBuffer method) (xuance.common.memory_tools_marl.BaseBuffer method) (xuance.common.memory_tools_marl.MARL_OffPolicyBuffer method) (xuance.common.memory_tools_marl.MARL_OffPolicyBuffer_RNN method) (xuance.common.memory_tools_marl.MARL_OnPolicyBuffer method) (xuance.common.memory_tools_marl.MARL_OnPolicyBuffer_RNN method) (xuance.common.memory_tools_marl.MeanField_OffPolicyBuffer_RNN method) flatten_dim (xuance.mindspore.utils.layers4dreamer.MLP property) (xuance.tensorflow.utils.layers4dreamer.MLP property) (xuance.torch.utils.layers4dreamer.MLP property) flatten_list() (in module xuance.environment.vector_envs.env_utils) flatten_obs() (in module xuance.environment.vector_envs.env_utils) (xuance.environment.single_agent_env.minigrid.MiniGridEnv method) football_raw_env (class in xuance.environment.multi_agent_env.football) forward() (xuance.mindspore.agents.contrastive_unsupervised_rl.curl_agent.CURL_Policy method), [1] (xuance.mindspore.agents.contrastive_unsupervised_rl.spr_agent.SPR_Policy method), [1] (xuance.mindspore.communications.attention_comm.TarMAC method) (xuance.mindspore.communications.base_comm.BaseComm method) (xuance.mindspore.communications.base_comm.NoneComm method) (xuance.mindspore.communications.comm_net.CommNet method) (xuance.mindspore.communications.gnn_comm.DGNComm method) (xuance.mindspore.communications.ic3net_comm.IC3NetComm method) (xuance.mindspore.policies.categorical_marl.CommNet_Policy method) (xuance.mindspore.policies.categorical_marl.IC3Net_Policy method) (xuance.mindspore.policies.categorical_marl.TarMAC_Policy method) (xuance.mindspore.representations.vit.Attention method) (xuance.mindspore.representations.vit.Basic_ViT method) (xuance.mindspore.representations.vit.FeedForward method) (xuance.mindspore.representations.vit.Transformer method) (xuance.mindspore.representations.vit.ViT method) (xuance.mindspore.representations.world_model.Actor method) (xuance.mindspore.representations.world_model.CNNDecoder method) (xuance.mindspore.representations.world_model.CNNEncoder method) (xuance.mindspore.representations.world_model.MLPDecoder method) (xuance.mindspore.representations.world_model.MLPEncoder method) (xuance.mindspore.representations.world_model.RecurrentModel method) (xuance.mindspore.representations.world_model_v2.Actor method) (xuance.mindspore.representations.world_model_v2.CNNDecoder method) (xuance.mindspore.representations.world_model_v2.CNNEncoder method) (xuance.mindspore.representations.world_model_v2.MLPDecoder method) (xuance.mindspore.representations.world_model_v2.MLPEncoder method) (xuance.mindspore.representations.world_model_v2.RecurrentModel method) (xuance.mindspore.utils.harmonizer.Harmonizer method) (xuance.mindspore.utils.layers4dreamer.CNN method) (xuance.mindspore.utils.layers4dreamer.DeCNN method) (xuance.mindspore.utils.layers4dreamer.LayerNorm method) (xuance.mindspore.utils.layers4dreamer.LayerNormChannelLast method) (xuance.mindspore.utils.layers4dreamer.LayerNormGRUCell method) (xuance.mindspore.utils.layers4dreamer.MLP method) (xuance.mindspore.utils.layers4dreamer.MultiDecoder method) (xuance.mindspore.utils.layers4dreamer.MultiEncoder method) (xuance.mindspore.utils.layers4dreamer.NatureCNN method) (xuance.tensorflow.agents.contrastive_unsupervised_rl.curl_agent.CURL_Policy method), [1] (xuance.tensorflow.agents.contrastive_unsupervised_rl.spr_agent.SPR_Policy method), [1] (xuance.tensorflow.communications.attention_comm.TarMAC method) (xuance.tensorflow.communications.base_comm.BaseComm method) (xuance.tensorflow.communications.base_comm.NoneComm method) (xuance.tensorflow.communications.comm_net.CommNet method) (xuance.tensorflow.communications.gnn_comm.DGNComm method) (xuance.tensorflow.communications.ic3net_comm.IC3NetComm method) (xuance.tensorflow.policies.categorical_marl.CommNet_Policy method) (xuance.tensorflow.policies.categorical_marl.IC3Net_Policy method) (xuance.tensorflow.policies.categorical_marl.TarMAC_Policy method) (xuance.tensorflow.representations.cnn.AC_CNN_Atari method) (xuance.tensorflow.representations.vit.Attention method) (xuance.tensorflow.representations.vit.Basic_ViT method) (xuance.tensorflow.representations.vit.FeedForward method) (xuance.tensorflow.representations.vit.Transformer method) (xuance.tensorflow.representations.vit.ViT method) (xuance.tensorflow.representations.world_model.Actor method) (xuance.tensorflow.representations.world_model.CNNDecoder method) (xuance.tensorflow.representations.world_model.CNNEncoder method) (xuance.tensorflow.representations.world_model.MLPDecoder method) (xuance.tensorflow.representations.world_model.MLPEncoder method) (xuance.tensorflow.representations.world_model.RecurrentModel method) (xuance.tensorflow.representations.world_model_v2.Actor method) (xuance.tensorflow.representations.world_model_v2.CNNDecoder method) (xuance.tensorflow.representations.world_model_v2.CNNEncoder method) (xuance.tensorflow.representations.world_model_v2.MLPDecoder method) (xuance.tensorflow.representations.world_model_v2.MLPEncoder method) (xuance.tensorflow.representations.world_model_v2.RecurrentModel method) (xuance.tensorflow.utils.harmonizer.Harmonizer method) (xuance.tensorflow.utils.layers4dreamer.CNN method) (xuance.tensorflow.utils.layers4dreamer.DeCNN method) (xuance.tensorflow.utils.layers4dreamer.LayerNorm method) (xuance.tensorflow.utils.layers4dreamer.LayerNormChannelLast method) (xuance.tensorflow.utils.layers4dreamer.LayerNormGRUCell method) (xuance.tensorflow.utils.layers4dreamer.MLP method) (xuance.tensorflow.utils.layers4dreamer.MultiDecoder method) (xuance.tensorflow.utils.layers4dreamer.MultiEncoder method) (xuance.tensorflow.utils.layers4dreamer.NatureCNN method) (xuance.torch.agents.contrastive_unsupervised_rl.curl_agent.CURL_Policy method), [1] (xuance.torch.agents.contrastive_unsupervised_rl.spr_agent.SPR_Policy method), [1] (xuance.torch.communications.attention_comm.TarMAC method) (xuance.torch.communications.base_comm.BaseComm method) (xuance.torch.communications.base_comm.NoneComm method) (xuance.torch.communications.comm_net.CommNet method) (xuance.torch.communications.gnn_comm.DGNComm method) (xuance.torch.communications.gnn_comm.GraphMultiHeadAttentionLayer method) (xuance.torch.communications.ic3net_comm.IC3NetComm method) (xuance.torch.policies.categorical.ActorCriticPolicy method) (xuance.torch.policies.categorical.ActorPolicy method) (xuance.torch.policies.categorical.PPGActorCritic method) (xuance.torch.policies.categorical.SACDISPolicy method) (xuance.torch.policies.categorical_marl.Basic_ISAC_Policy method) (xuance.torch.policies.categorical_marl.COMA_Policy method) (xuance.torch.policies.categorical_marl.CommNet_Policy method) (xuance.torch.policies.categorical_marl.IC3Net_Policy method) (xuance.torch.policies.categorical_marl.MAAC_Policy method) (xuance.torch.policies.categorical_marl.MAAC_Policy_Share method) (xuance.torch.policies.categorical_marl.MeanFieldActorCriticPolicy method) (xuance.torch.policies.categorical_marl.TarMAC_Policy method) (xuance.torch.policies.coordination_graph.DCG_payoff method) (xuance.torch.policies.coordination_graph.DCG_utility method) (xuance.torch.policies.core.ActorNet method) (xuance.torch.policies.core.BasicQhead method) (xuance.torch.policies.core.BasicRecurrent method) (xuance.torch.policies.core.C51Qhead method) (xuance.torch.policies.core.CategoricalActorNet method) (xuance.torch.policies.core.CategoricalActorNet_SAC method) (xuance.torch.policies.core.CriticNet method) (xuance.torch.policies.core.DuelQhead method) (xuance.torch.policies.core.GaussianActorNet method) (xuance.torch.policies.core.GaussianActorNet_SAC method) (xuance.torch.policies.core.QMIX_FF_mixer method) (xuance.torch.policies.core.QMIX_mixer method) (xuance.torch.policies.core.QRDQNhead method) (xuance.torch.policies.core.QTRAN_alt method) (xuance.torch.policies.core.QTRAN_base method) (xuance.torch.policies.core.VDN_mixer method) (xuance.torch.policies.deterministic.BasicQnetwork method) (xuance.torch.policies.deterministic.C51Qnetwork method) (xuance.torch.policies.deterministic.DDPGPolicy method) (xuance.torch.policies.deterministic.DRQNPolicy method) (xuance.torch.policies.deterministic.DuelQnetwork method) (xuance.torch.policies.deterministic.NoisyQnetwork method) (xuance.torch.policies.deterministic.QRDQN_Network method) (xuance.torch.policies.deterministic.TD3Policy method) (xuance.torch.policies.deterministic_marl.BasicQnetwork method) (xuance.torch.policies.deterministic_marl.Independent_DDPG_Policy method) (xuance.torch.policies.deterministic_marl.MFQnetwork method) (xuance.torch.policies.deterministic_marl.Qtran_MixingQnetwork method) (xuance.torch.policies.gaussian.ActorCriticPolicy method) (xuance.torch.policies.gaussian.ActorPolicy method) (xuance.torch.policies.gaussian.PPGActorCritic method) (xuance.torch.policies.gaussian.SACPolicy method) (xuance.torch.policies.gaussian_marl.Basic_ISAC_Policy method) (xuance.torch.policies.gaussian_marl.MAAC_Policy method) (xuance.torch.representations.cnn.AC_CNN_Atari method) (xuance.torch.representations.cnn.Basic_CNN method) (xuance.torch.representations.mlp.Basic_Identical method) (xuance.torch.representations.mlp.Basic_MLP method) (xuance.torch.representations.rnn.Basic_RNN method) (xuance.torch.representations.vit.Attention method) (xuance.torch.representations.vit.Basic_ViT method) (xuance.torch.representations.vit.FeedForward method) (xuance.torch.representations.vit.Transformer method) (xuance.torch.representations.vit.ViT method) (xuance.torch.representations.world_model.Actor method) (xuance.torch.representations.world_model.CNNDecoder method) (xuance.torch.representations.world_model.CNNEncoder method) (xuance.torch.representations.world_model.MLPDecoder method) (xuance.torch.representations.world_model.MLPEncoder method) (xuance.torch.representations.world_model.RecurrentModel method) (xuance.torch.representations.world_model_v2.Actor method) (xuance.torch.representations.world_model_v2.CNNDecoder method) (xuance.torch.representations.world_model_v2.CNNEncoder method) (xuance.torch.representations.world_model_v2.MLPDecoder method) (xuance.torch.representations.world_model_v2.MLPEncoder method) (xuance.torch.representations.world_model_v2.RecurrentModel method) (xuance.torch.utils.harmonizer.Harmonizer method) (xuance.torch.utils.layers.Moments method) (xuance.torch.utils.layers4dreamer.CNN method) (xuance.torch.utils.layers4dreamer.DeCNN method) (xuance.torch.utils.layers4dreamer.LayerNorm method) (xuance.torch.utils.layers4dreamer.LayerNormChannelLast method) (xuance.torch.utils.layers4dreamer.LayerNormGRUCell method) (xuance.torch.utils.layers4dreamer.MLP method) (xuance.torch.utils.layers4dreamer.MultiDecoder method) (xuance.torch.utils.layers4dreamer.MultiEncoder method) (xuance.torch.utils.layers4dreamer.NatureCNN method)

forward_fn() (xuance.mindspore.learners.multi_agent_rl.iac_learner.IAC_Learner method) (xuance.mindspore.learners.multi_agent_rl.ippo_learner.IPPO_Learner method) (xuance.mindspore.learners.multi_agent_rl.iql_learner.IQL_Learner method) (xuance.mindspore.learners.multi_agent_rl.mappo_learner.MAPPO_Learner method) (xuance.mindspore.learners.multi_agent_rl.mfac_learner.MFAC_Learner method) (xuance.mindspore.learners.multi_agent_rl.mfq_learner.MFQ_Learner method) (xuance.mindspore.learners.multi_agent_rl.qmix_learner.QMIX_Learner method) (xuance.mindspore.learners.multi_agent_rl.qtran_learner.QTRAN_Learner method) (xuance.mindspore.learners.multi_agent_rl.vdac_learner.VDAC_Learner method) (xuance.mindspore.learners.multi_agent_rl.vdn_learner.VDN_Learner method) (xuance.mindspore.learners.multi_agent_rl.wqmix_learner.WQMIX_Learner method) (xuance.mindspore.learners.policy_gradient.a2c_learner.A2C_Learner method) (xuance.mindspore.learners.policy_gradient.pg_learner.PG_Learner method) (xuance.mindspore.learners.policy_gradient.ppo_learner.PPO_Learner method) (xuance.mindspore.learners.policy_gradient.ppokl_learner.PPOKL_Learner method) (xuance.mindspore.learners.qlearning_family.c51_learner.C51_Learner method) (xuance.mindspore.learners.qlearning_family.ddqn_learner.DDQN_Learner method) (xuance.mindspore.learners.qlearning_family.dqn_learner.DQN_Learner method) (xuance.mindspore.learners.qlearning_family.drqn_learner.DRQN_Learner method) (xuance.mindspore.learners.qlearning_family.dueldqn_learner.DuelDQN_Learner method) (xuance.mindspore.learners.qlearning_family.perdqn_learner.PerDQN_Learner method) (xuance.mindspore.learners.qlearning_family.qrdqn_learner.QRDQN_Learner method) (xuance.tensorflow.learners.multi_agent_rl.coma_learner.COMA_Learner method) (xuance.tensorflow.learners.multi_agent_rl.iac_learner.IAC_Learner method) (xuance.tensorflow.learners.multi_agent_rl.iddpg_learner.IDDPG_Learner method) (xuance.tensorflow.learners.multi_agent_rl.ippo_learner.IPPO_Learner method) (xuance.tensorflow.learners.multi_agent_rl.iql_learner.IQL_Learner method) (xuance.tensorflow.learners.multi_agent_rl.isac_learner.ISAC_Learner method) (xuance.tensorflow.learners.multi_agent_rl.maddpg_learner.MADDPG_Learner method) (xuance.tensorflow.learners.multi_agent_rl.mappo_learner.MAPPO_Learner method) (xuance.tensorflow.learners.multi_agent_rl.masac_learner.MASAC_Learner method) (xuance.tensorflow.learners.multi_agent_rl.matd3_learner.MATD3_Learner method) (xuance.tensorflow.learners.multi_agent_rl.mfac_learner.MFAC_Learner method) (xuance.tensorflow.learners.multi_agent_rl.mfq_learner.MFQ_Learner method) (xuance.tensorflow.learners.multi_agent_rl.qmix_learner.QMIX_Learner method) (xuance.tensorflow.learners.multi_agent_rl.qtran_learner.QTRAN_Learner method) (xuance.tensorflow.learners.multi_agent_rl.vdac_learner.VDAC_Learner method) (xuance.tensorflow.learners.multi_agent_rl.vdn_learner.VDN_Learner method) (xuance.tensorflow.learners.multi_agent_rl.wqmix_learner.WQMIX_Learner method) (xuance.tensorflow.learners.policy_gradient.a2c_learner.A2C_Learner method) (xuance.tensorflow.learners.policy_gradient.pg_learner.PG_Learner method) (xuance.tensorflow.learners.policy_gradient.ppo_learner.PPO_Learner method) (xuance.tensorflow.learners.policy_gradient.ppokl_learner.PPOKL_Learner method) (xuance.tensorflow.learners.qlearning_family.c51_learner.C51_Learner method) (xuance.tensorflow.learners.qlearning_family.ddqn_learner.DDQN_Learner method) (xuance.tensorflow.learners.qlearning_family.dqn_learner.DQN_Learner method) (xuance.tensorflow.learners.qlearning_family.drqn_learner.DRQN_Learner method) (xuance.tensorflow.learners.qlearning_family.dueldqn_learner.DuelDQN_Learner method) (xuance.tensorflow.learners.qlearning_family.perdqn_learner.PerDQN_Learner method) (xuance.tensorflow.learners.qlearning_family.qrdqn_learner.QRDQN_Learner method) forward_fn_actor() (xuance.mindspore.learners.multi_agent_rl.iddpg_learner.IDDPG_Learner method) (xuance.mindspore.learners.multi_agent_rl.isac_learner.ISAC_Learner method) (xuance.mindspore.learners.multi_agent_rl.maddpg_learner.MADDPG_Learner method) (xuance.mindspore.learners.multi_agent_rl.masac_learner.MASAC_Learner method) (xuance.mindspore.learners.multi_agent_rl.matd3_learner.MATD3_Learner method) (xuance.mindspore.learners.policy_gradient.ddpg_learner.DDPG_Learner method) (xuance.mindspore.learners.policy_gradient.sac_learner.SAC_Learner method) (xuance.mindspore.learners.policy_gradient.sacdis_learner.SACDIS_Learner method) (xuance.mindspore.learners.policy_gradient.td3_learner.TD3_Learner method) forward_fn_alpha() (xuance.mindspore.learners.multi_agent_rl.isac_learner.ISAC_Learner method) (xuance.mindspore.learners.multi_agent_rl.masac_learner.MASAC_Learner method) (xuance.mindspore.learners.policy_gradient.sac_learner.SAC_Learner method) (xuance.mindspore.learners.policy_gradient.sacdis_learner.SACDIS_Learner method) forward_fn_auxiliary() (xuance.mindspore.learners.policy_gradient.ppg_learner.PPG_Learner method) forward_fn_critic() (xuance.mindspore.learners.multi_agent_rl.iddpg_learner.IDDPG_Learner method) (xuance.mindspore.learners.multi_agent_rl.isac_learner.ISAC_Learner method) (xuance.mindspore.learners.multi_agent_rl.maddpg_learner.MADDPG_Learner method) (xuance.mindspore.learners.multi_agent_rl.masac_learner.MASAC_Learner method) (xuance.mindspore.learners.multi_agent_rl.matd3_learner.MATD3_Learner method) (xuance.mindspore.learners.policy_gradient.ddpg_learner.DDPG_Learner method) (xuance.mindspore.learners.policy_gradient.ppg_learner.PPG_Learner method) (xuance.mindspore.learners.policy_gradient.sac_learner.SAC_Learner method) (xuance.mindspore.learners.policy_gradient.sacdis_learner.SACDIS_Learner method) (xuance.mindspore.learners.policy_gradient.td3_learner.TD3_Learner method) forward_fn_policy() (xuance.mindspore.learners.policy_gradient.ppg_learner.PPG_Learner method) FrameStackTransform (class in xuance.mindspore.learners.contrastive_unsupervised_rl.curl_learner) (class in xuance.mindspore.learners.contrastive_unsupervised_rl.drq_learner) (class in xuance.mindspore.learners.contrastive_unsupervised_rl.spr_learner) (class in xuance.tensorflow.learners.contrastive_unsupervised_rl.curl_learner) (class in xuance.tensorflow.learners.contrastive_unsupervised_rl.drq_learner) (class in xuance.tensorflow.learners.contrastive_unsupervised_rl.spr_learner) (class in xuance.torch.learners.contrastive_unsupervised_rl.curl_learner) (class in xuance.torch.learners.contrastive_unsupervised_rl.drq_learner) (class in xuance.torch.learners.contrastive_unsupervised_rl.spr_learner) full (xuance.common.memory_tools.Buffer property) (xuance.common.memory_tools.DummyOnPolicyBuffer property) (xuance.common.memory_tools.RecurrentOffPolicyBuffer property) (xuance.common.memory_tools_marl.BaseBuffer property) (xuance.common.memory_tools_marl.MARL_OnPolicyBuffer_RNN property)

G

GaussianActorNet (class in xuance.mindspore.policies.core) (class in xuance.tensorflow.policies.core) (class in xuance.torch.policies.core) GaussianActorNet_SAC (class in xuance.mindspore.policies.core) (class in xuance.tensorflow.policies.core) (class in xuance.torch.policies.core) gcn() (xuance.mindspore.communications.gnn_comm.DGNComm method) (xuance.tensorflow.communications.gnn_comm.DGNComm method) gcn_block() (xuance.torch.communications.gnn_comm.DGNComm method) get_actions() (xuance.mindspore.agents.base.agent.Agent method) (xuance.mindspore.agents.base.agents_marl.MARLAgents method) (xuance.mindspore.agents.base.agents_marl.RandomAgents method) (xuance.mindspore.agents.core.off_policy.OffPolicyAgent method) (xuance.mindspore.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.mindspore.agents.core.offline.OfflineAgent method) (xuance.mindspore.agents.core.on_policy.OnPolicyAgent method) (xuance.mindspore.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.mindspore.agents.model_based_rl.dreamer_v2_agent.DreamerV2Agent method) (xuance.mindspore.agents.model_based_rl.dreamer_v3_agent.DreamerV3Agent method) (xuance.mindspore.agents.multi_agent_rl.coma_agents.COMA_Agents method) (xuance.mindspore.agents.multi_agent_rl.commnet_agents.CommNet_Agents method) (xuance.mindspore.agents.multi_agent_rl.iac_agents.IAC_Agents method) (xuance.mindspore.agents.multi_agent_rl.ic3net_agents.IC3Net_Agents method) (xuance.mindspore.agents.multi_agent_rl.iddpg_agents.IDDPG_Agents method) (xuance.mindspore.agents.multi_agent_rl.isac_agents.ISAC_Agents method) (xuance.mindspore.agents.multi_agent_rl.mappo_agents.MAPPO_Agents method) (xuance.mindspore.agents.multi_agent_rl.mfac_agents.MFAC_Agents method) (xuance.mindspore.agents.multi_agent_rl.mfq_agents.MFQ_Agents method) (xuance.mindspore.agents.multi_agent_rl.qtran_agents.QTRAN_Agents method) (xuance.mindspore.agents.multi_agent_rl.vdac_agents.VDAC_Agents method) (xuance.mindspore.agents.offline_rl.td3bc_agent.TD3_BC_Agent method) (xuance.mindspore.agents.policy_gradient.ddpg_agent.DDPG_Agent method) (xuance.mindspore.agents.policy_gradient.pdqn_agent.PDQN_Agent method) (xuance.mindspore.agents.policy_gradient.ppg_agent.PPG_Agent method) (xuance.mindspore.agents.policy_gradient.sac_agent.SAC_Agent method) (xuance.mindspore.agents.qlearning_family.drqn_agent.DRQN_Agent method) (xuance.mindspore.agents.qlearning_family.noisydqn_agent.NoisyDQN_Agent method) (xuance.mindspore.representations.world_model.PlayerDV3 method) (xuance.mindspore.representations.world_model_v2.PlayerDV2 method) (xuance.tensorflow.agents.base.agent.Agent method) (xuance.tensorflow.agents.base.agents_marl.MARLAgents method) (xuance.tensorflow.agents.base.agents_marl.RandomAgents method) (xuance.tensorflow.agents.core.off_policy.OffPolicyAgent method) (xuance.tensorflow.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.tensorflow.agents.core.offline.OfflineAgent method) (xuance.tensorflow.agents.core.on_policy.OnPolicyAgent method) (xuance.tensorflow.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.tensorflow.agents.model_based_rl.dreamer_v2_agent.DreamerV2Agent method) (xuance.tensorflow.agents.model_based_rl.dreamer_v3_agent.DreamerV3Agent method) (xuance.tensorflow.agents.multi_agent_rl.coma_agents.COMA_Agents method) (xuance.tensorflow.agents.multi_agent_rl.commnet_agents.CommNet_Agents method) (xuance.tensorflow.agents.multi_agent_rl.iac_agents.IAC_Agents method) (xuance.tensorflow.agents.multi_agent_rl.ic3net_agents.IC3Net_Agents method) (xuance.tensorflow.agents.multi_agent_rl.iddpg_agents.IDDPG_Agents method) (xuance.tensorflow.agents.multi_agent_rl.isac_agents.ISAC_Agents method) (xuance.tensorflow.agents.multi_agent_rl.mappo_agents.MAPPO_Agents method) (xuance.tensorflow.agents.multi_agent_rl.mfac_agents.MFAC_Agents method) (xuance.tensorflow.agents.multi_agent_rl.mfq_agents.MFQ_Agents method) (xuance.tensorflow.agents.multi_agent_rl.qtran_agents.QTRAN_Agents method) (xuance.tensorflow.agents.multi_agent_rl.vdac_agents.VDAC_Agents method) (xuance.tensorflow.agents.offline_rl.td3bc_agent.TD3_BC_Agent method) (xuance.tensorflow.agents.policy_gradient.ddpg_agent.DDPG_Agent method) (xuance.tensorflow.agents.policy_gradient.pdqn_agent.PDQN_Agent method) (xuance.tensorflow.agents.policy_gradient.ppg_agent.PPG_Agent method) (xuance.tensorflow.agents.policy_gradient.sac_agent.SAC_Agent method) (xuance.tensorflow.agents.qlearning_family.drqn_agent.DRQN_Agent method) (xuance.tensorflow.agents.qlearning_family.noisydqn_agent.NoisyDQN_Agent method) (xuance.tensorflow.representations.world_model.PlayerDV3 method) (xuance.tensorflow.representations.world_model_v2.PlayerDV2 method) (xuance.torch.agents.base.agent.Agent method) (xuance.torch.agents.base.agents_marl.MARLAgents method) (xuance.torch.agents.base.agents_marl.RandomAgents method) (xuance.torch.agents.core.off_policy.OffPolicyAgent method) (xuance.torch.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.torch.agents.core.offline.OfflineAgent method) (xuance.torch.agents.core.on_policy.OnPolicyAgent method) (xuance.torch.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.torch.agents.model_based_rl.dreamer_v2_agent.DreamerV2Agent method) (xuance.torch.agents.model_based_rl.dreamer_v3_agent.DreamerV3Agent method) (xuance.torch.agents.multi_agent_rl.coma_agents.COMA_Agents method) (xuance.torch.agents.multi_agent_rl.commnet_agents.CommNet_Agents method) (xuance.torch.agents.multi_agent_rl.dcg_agents.DCG_Agents method) (xuance.torch.agents.multi_agent_rl.iac_agents.IAC_Agents method) (xuance.torch.agents.multi_agent_rl.ic3net_agents.IC3Net_Agents method) (xuance.torch.agents.multi_agent_rl.iddpg_agents.IDDPG_Agents method) (xuance.torch.agents.multi_agent_rl.isac_agents.ISAC_Agents method) (xuance.torch.agents.multi_agent_rl.mappo_agents.MAPPO_Agents method) (xuance.torch.agents.multi_agent_rl.mfac_agents.MFAC_Agents method) (xuance.torch.agents.multi_agent_rl.mfq_agents.MFQ_Agents method) (xuance.torch.agents.multi_agent_rl.qtran_agents.QTRAN_Agents method) (xuance.torch.agents.multi_agent_rl.vdac_agents.VDAC_Agents method) (xuance.torch.agents.offline_rl.td3bc_agent.TD3_BC_Agent method) (xuance.torch.agents.policy_gradient.ddpg_agent.DDPG_Agent method) (xuance.torch.agents.policy_gradient.pdqn_agent.PDQN_Agent method) (xuance.torch.agents.policy_gradient.ppg_agent.PPG_Agent method) (xuance.torch.agents.policy_gradient.sac_agent.SAC_Agent method) (xuance.torch.agents.qlearning_family.drqn_agent.DRQN_Agent method) (xuance.torch.agents.qlearning_family.noisydqn_agent.NoisyDQN_Agent method) (xuance.torch.representations.world_model.PlayerDV3 method) (xuance.torch.representations.world_model_v2.PlayerDV2 method)

get_agent_num() (xuance.engine.run_football.RunnerFootball method) (xuance.engine.run_sc2.RunnerSC2 method) get_arguments() (in module xuance.common.common_tools) get_aux_info() (xuance.mindspore.agents.core.on_policy.OnPolicyAgent method) (xuance.mindspore.agents.policy_gradient.ppg_agent.PPG_Agent method) (xuance.mindspore.agents.policy_gradient.ppo_agent.PPO_Agent method) (xuance.mindspore.agents.policy_gradient.ppokl_agent.PPOKL_Agent method) (xuance.tensorflow.agents.core.on_policy.OnPolicyAgent method) (xuance.tensorflow.agents.policy_gradient.ppg_agent.PPG_Agent method) (xuance.tensorflow.agents.policy_gradient.ppo_agent.PPO_Agent method) (xuance.tensorflow.agents.policy_gradient.ppokl_agent.PPOKL_Agent method) (xuance.torch.agents.core.on_policy.OnPolicyAgent method) (xuance.torch.agents.policy_gradient.ppg_agent.PPG_Agent method) (xuance.torch.agents.policy_gradient.ppo_agent.PPO_Agent method) (xuance.torch.agents.policy_gradient.ppokl_agent.PPOKL_Agent method) get_battles_info() (xuance.engine.run_football.RunnerFootball method) (xuance.engine.run_sc2.RunnerSC2 method) get_battles_result() (xuance.engine.run_football.RunnerFootball method) (xuance.engine.run_sc2.RunnerSC2 method) get_boltzmann_policy() (xuance.mindspore.policies.deterministic_marl.MFQnetwork method) (xuance.torch.policies.categorical_marl.MeanFieldActorCriticPolicy method) (xuance.torch.policies.deterministic_marl.MFQnetwork method) get_env_info() (xuance.environment.multi_agent_env.football.GFootball_Env method) (xuance.environment.multi_agent_env.starcraft2.StarCraft2_Env method) (xuance.environment.utils.base.RawMultiAgentEnv method) get_flat_grad() (in module xuance.mindspore.utils.operations) (in module xuance.torch.utils.operations) get_flat_params() (in module xuance.mindspore.utils.operations) (in module xuance.tensorflow.utils.operations) (in module xuance.torch.utils.operations) get_frame() (xuance.environment.multi_agent_env.football.football_raw_env method) get_grad_reducer() (xuance.mindspore.learners.learner.Learner method) get_graph_values() (xuance.mindspore.learners.multi_agent_rl.dcg_learner.DCG_Learner method) (xuance.tensorflow.learners.multi_agent_rl.dcg_learner.DCG_Learner method) (xuance.torch.learners.multi_agent_rl.dcg_learner.DCG_Learner method) get_groups_info() (xuance.environment.utils.base.RawMultiAgentEnv method) get_harmony() (xuance.mindspore.utils.harmonizer.Harmonizer method) (xuance.tensorflow.utils.harmonizer.Harmonizer method) (xuance.torch.utils.harmonizer.Harmonizer method) get_hidden_item() (xuance.mindspore.representations.rnn.Basic_RNN method) (xuance.torch.representations.rnn.Basic_RNN method) get_hidden_states() (xuance.mindspore.learners.multi_agent_rl.dcg_learner.DCG_Learner method) (xuance.tensorflow.learners.multi_agent_rl.dcg_learner.DCG_Learner method) (xuance.torch.policies.deterministic_marl.DCG_policy method) get_hyperparameters() (xuance.common.tuning_tools.AlgorithmHyperparametersRegistry class method) get_initial_states() (xuance.mindspore.representations.world_model.RSSM method) (xuance.tensorflow.representations.world_model.RSSM method) (xuance.torch.representations.world_model.RSSM method) get_joint_input() (xuance.mindspore.learners.learner.LearnerMAS method) (xuance.torch.learners.learner.LearnerMAS method) get_mean_actions() (xuance.mindspore.policies.categorical_marl.MeanFieldActorCriticPolicy method) (xuance.mindspore.policies.deterministic_marl.MFQnetwork method) (xuance.tensorflow.policies.categorical_marl.MeanFieldActorCriticPolicy method) (xuance.tensorflow.policies.deterministic_marl.MFQnetwork method) (xuance.torch.policies.categorical_marl.MeanFieldActorCriticPolicy method) (xuance.torch.policies.deterministic_marl.MFQnetwork method) get_more_info() (xuance.environment.multi_agent_env.football.GFootball_Env method) get_param() (xuance.mindspore.utils.distributions.CategoricalDistribution method) (xuance.mindspore.utils.distributions.DiagGaussianDistribution method) (xuance.mindspore.utils.distributions.Distribution method) (xuance.tensorflow.utils.distributions.CategoricalDistribution method) (xuance.tensorflow.utils.distributions.DiagGaussianDistribution method) (xuance.tensorflow.utils.distributions.Distribution method) (xuance.torch.utils.distributions.CategoricalDistribution method) (xuance.torch.utils.distributions.DiagGaussianDistribution method) (xuance.torch.utils.distributions.Distribution method) get_terminated_values() (xuance.mindspore.agents.core.on_policy.OnPolicyAgent method) (xuance.mindspore.agents.policy_gradient.pg_agent.PG_Agent method) (xuance.tensorflow.agents.core.on_policy.OnPolicyAgent method) (xuance.tensorflow.agents.policy_gradient.pg_agent.PG_Agent method) (xuance.torch.agents.core.on_policy.OnPolicyAgent method) (xuance.torch.agents.policy_gradient.pg_agent.PG_Agent method) get_time_string() (in module xuance.common.common_tools) get_values() (xuance.mindspore.policies.categorical_marl.COMA_Policy method) (xuance.mindspore.policies.categorical_marl.CommNet_Policy method) (xuance.mindspore.policies.categorical_marl.IC3Net_Policy method) (xuance.mindspore.policies.categorical_marl.MAAC_Policy method) (xuance.mindspore.policies.categorical_marl.MeanFieldActorCriticPolicy method) (xuance.mindspore.policies.gaussian_marl.MAAC_Policy method) (xuance.tensorflow.policies.categorical_marl.COMA_Policy method) (xuance.tensorflow.policies.categorical_marl.CommNet_Policy method) (xuance.tensorflow.policies.categorical_marl.IC3Net_Policy method) (xuance.tensorflow.policies.categorical_marl.MAAC_Policy method) (xuance.tensorflow.policies.categorical_marl.MeanFieldActorCriticPolicy method) (xuance.tensorflow.policies.gaussian_marl.MAAC_Policy method) (xuance.torch.policies.categorical_marl.COMA_Policy method) (xuance.torch.policies.categorical_marl.MAAC_Policy method) (xuance.torch.policies.categorical_marl.MAAC_Policy_Share method) (xuance.torch.policies.categorical_marl.MeanFieldActorCriticPolicy method) (xuance.torch.policies.gaussian_marl.MAAC_Policy method) get_values_target() (xuance.tensorflow.policies.categorical_marl.COMA_Policy method) GFootball_Env (class in xuance.environment.multi_agent_env.football) GraphMultiHeadAttentionLayer (class in xuance.torch.communications.gnn_comm) gru_block() (in module xuance.mindspore.utils.layers) (in module xuance.tensorflow.utils.layers) (in module xuance.torch.utils.layers) Gym_Env (class in xuance.environment.single_agent_env.gym)

H

hard_update() (xuance.mindspore.policies.dreamer.DreamerV2Policy method) (xuance.tensorflow.policies.dreamer.DreamerV2Policy method) (xuance.torch.policies.dreamer.DreamerV2Policy method) Harmonizer (class in xuance.mindspore.utils.harmonizer) (class in xuance.tensorflow.utils.harmonizer) (class in xuance.torch.utils.harmonizer)

has_rsample (xuance.torch.utils.distributions.TruncatedNormal attribute) (xuance.torch.utils.distributions.TruncatedStandardNormal attribute) Hyperparameter (class in xuance.common.tuning_tools) HyperParameterTuner (class in xuance.common.tuning_tools)

I

IAC_Agents (class in xuance.mindspore.agents.multi_agent_rl.iac_agents) (class in xuance.tensorflow.agents.multi_agent_rl.iac_agents) (class in xuance.torch.agents.multi_agent_rl.iac_agents) IAC_Learner (class in xuance.mindspore.learners.multi_agent_rl.iac_learner) (class in xuance.tensorflow.learners.multi_agent_rl.iac_learner) (class in xuance.torch.learners.multi_agent_rl.iac_learner) IC3Net_Agents (class in xuance.mindspore.agents.multi_agent_rl.ic3net_agents) (class in xuance.tensorflow.agents.multi_agent_rl.ic3net_agents) (class in xuance.torch.agents.multi_agent_rl.ic3net_agents) IC3Net_Learner (class in xuance.mindspore.learners.multi_agent_rl.ic3net_learner) (class in xuance.tensorflow.learners.multi_agent_rl.ic3net_learner) (class in xuance.torch.learners.multi_agent_rl.ic3net_learner) IC3Net_OnPolicyBuffer_RNN (class in xuance.common.memory_tools_marl) IC3Net_Policy (class in xuance.mindspore.policies.categorical_marl) (class in xuance.tensorflow.policies.categorical_marl) (class in xuance.torch.policies.categorical_marl) IC3NetComm (class in xuance.mindspore.communications.ic3net_comm) (class in xuance.tensorflow.communications.ic3net_comm) (class in xuance.torch.communications.ic3net_comm) icdf() (xuance.torch.utils.distributions.TruncatedNormal method) (xuance.torch.utils.distributions.TruncatedStandardNormal method) IDDPG_Agents (class in xuance.mindspore.agents.multi_agent_rl.iddpg_agents) (class in xuance.tensorflow.agents.multi_agent_rl.iddpg_agents) (class in xuance.torch.agents.multi_agent_rl.iddpg_agents) IDDPG_Learner (class in xuance.mindspore.learners.multi_agent_rl.iddpg_learner) (class in xuance.tensorflow.learners.multi_agent_rl.iddpg_learner) (class in xuance.torch.learners.multi_agent_rl.iddpg_learner) imagination() (xuance.mindspore.representations.world_model.RSSM method) (xuance.mindspore.representations.world_model_v2.RSSM method) (xuance.tensorflow.representations.world_model.RSSM method) (xuance.tensorflow.representations.world_model_v2.RSSM method) (xuance.torch.representations.world_model.RSSM method) (xuance.torch.representations.world_model_v2.RSSM method) Independent_DDPG_Policy (class in xuance.mindspore.policies.deterministic_marl) (class in xuance.tensorflow.policies.deterministic_marl) (class in xuance.torch.policies.deterministic_marl) Independent_TD3_Policy (class in xuance.torch.policies.deterministic_marl) init_distributed_mode() (in module xuance.torch.utils.operations) init_hidden() (xuance.mindspore.policies.deterministic.DRQNPolicy method) (xuance.mindspore.representations.rnn.Basic_RNN method) (xuance.tensorflow.policies.deterministic.DRQNPolicy method) (xuance.torch.policies.deterministic.DRQNPolicy method) (xuance.torch.representations.rnn.Basic_RNN method) init_hidden_item() (xuance.mindspore.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.mindspore.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.mindspore.agents.multi_agent_rl.iddpg_agents.IDDPG_Agents method) (xuance.mindspore.agents.multi_agent_rl.ippo_agents.IPPO_Agents method) (xuance.mindspore.agents.multi_agent_rl.masac_agents.MASAC_Agents method) (xuance.mindspore.policies.deterministic.DRQNPolicy method) (xuance.mindspore.representations.rnn.Basic_RNN method) (xuance.tensorflow.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.tensorflow.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.tensorflow.agents.multi_agent_rl.iddpg_agents.IDDPG_Agents method) (xuance.tensorflow.agents.multi_agent_rl.ippo_agents.IPPO_Agents method) (xuance.tensorflow.policies.deterministic.DRQNPolicy method) (xuance.torch.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.torch.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.torch.agents.multi_agent_rl.iddpg_agents.IDDPG_Agents method) (xuance.torch.agents.multi_agent_rl.masac_agents.MASAC_Agents method) (xuance.torch.policies.deterministic.DRQNPolicy method) (xuance.torch.representations.rnn.Basic_RNN method)

init_rnn_hidden() (xuance.mindspore.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.mindspore.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.mindspore.agents.multi_agent_rl.iddpg_agents.IDDPG_Agents method) (xuance.mindspore.agents.multi_agent_rl.ippo_agents.IPPO_Agents method) (xuance.mindspore.agents.multi_agent_rl.masac_agents.MASAC_Agents method) (xuance.tensorflow.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.tensorflow.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.tensorflow.agents.multi_agent_rl.iddpg_agents.IDDPG_Agents method) (xuance.tensorflow.agents.multi_agent_rl.ippo_agents.IPPO_Agents method) (xuance.torch.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.torch.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.torch.agents.multi_agent_rl.iddpg_agents.IDDPG_Agents method) (xuance.torch.agents.multi_agent_rl.masac_agents.MASAC_Agents method) init_states() (xuance.mindspore.representations.world_model.PlayerDV3 method) (xuance.mindspore.representations.world_model_v2.PlayerDV2 method) (xuance.tensorflow.representations.world_model.PlayerDV3 method) (xuance.tensorflow.representations.world_model_v2.PlayerDV2 method) (xuance.torch.representations.world_model.PlayerDV3 method) (xuance.torch.representations.world_model_v2.PlayerDV2 method) init_weights() (in module xuance.torch.utils.operations) IPPO_Agents (class in xuance.mindspore.agents.multi_agent_rl.ippo_agents) (class in xuance.tensorflow.agents.multi_agent_rl.ippo_agents) (class in xuance.torch.agents.multi_agent_rl.ippo_agents) IPPO_Learner (class in xuance.mindspore.learners.multi_agent_rl.ippo_learner) (class in xuance.tensorflow.learners.multi_agent_rl.ippo_learner) (class in xuance.torch.learners.multi_agent_rl.ippo_learner) IQL_Agents (class in xuance.mindspore.agents.multi_agent_rl.iql_agents) (class in xuance.tensorflow.agents.multi_agent_rl.iql_agents) (class in xuance.torch.agents.multi_agent_rl.iql_agents) IQL_Learner (class in xuance.mindspore.learners.multi_agent_rl.iql_learner) (class in xuance.tensorflow.learners.multi_agent_rl.iql_learner) (class in xuance.torch.learners.multi_agent_rl.iql_learner) ISAC_Agents (class in xuance.mindspore.agents.multi_agent_rl.isac_agents) (class in xuance.tensorflow.agents.multi_agent_rl.isac_agents) (class in xuance.torch.agents.multi_agent_rl.isac_agents) ISAC_Learner (class in xuance.mindspore.learners.multi_agent_rl.isac_learner) (class in xuance.tensorflow.learners.multi_agent_rl.isac_learner) (class in xuance.torch.learners.multi_agent_rl.isac_learner)

K

kl_divergence() (xuance.mindspore.utils.distributions.CategoricalDistribution method) (xuance.mindspore.utils.distributions.DiagGaussianDistribution method) (xuance.tensorflow.utils.distributions.CategoricalDistribution method) (xuance.tensorflow.utils.distributions.DiagGaussianDistribution method) (xuance.torch.utils.distributions.CategoricalDistribution method) (xuance.torch.utils.distributions.DiagGaussianDistribution method)

L

LayerNorm (class in xuance.mindspore.utils.layers4dreamer) (class in xuance.tensorflow.utils.layers4dreamer) (class in xuance.torch.utils.layers4dreamer) LayerNormChannelLast (class in xuance.mindspore.utils.layers4dreamer) (class in xuance.tensorflow.utils.layers4dreamer) (class in xuance.torch.utils.layers4dreamer) LayerNormGRUCell (class in xuance.mindspore.utils.layers4dreamer) (class in xuance.tensorflow.utils.layers4dreamer) (class in xuance.torch.utils.layers4dreamer) LazyFrames (class in xuance.environment.single_agent_env.gym) learn() (xuance.tensorflow.learners.multi_agent_rl.coma_learner.COMA_Learner method) (xuance.tensorflow.learners.multi_agent_rl.iac_learner.IAC_Learner method) (xuance.tensorflow.learners.multi_agent_rl.iddpg_learner.IDDPG_Learner method) (xuance.tensorflow.learners.multi_agent_rl.ippo_learner.IPPO_Learner method) (xuance.tensorflow.learners.multi_agent_rl.iql_learner.IQL_Learner method) (xuance.tensorflow.learners.multi_agent_rl.isac_learner.ISAC_Learner method) (xuance.tensorflow.learners.multi_agent_rl.maddpg_learner.MADDPG_Learner method) (xuance.tensorflow.learners.multi_agent_rl.mappo_learner.MAPPO_Learner method) (xuance.tensorflow.learners.multi_agent_rl.matd3_learner.MATD3_Learner method) (xuance.tensorflow.learners.multi_agent_rl.mfac_learner.MFAC_Learner method) (xuance.tensorflow.learners.multi_agent_rl.mfq_learner.MFQ_Learner method) (xuance.tensorflow.learners.multi_agent_rl.qmix_learner.QMIX_Learner method) (xuance.tensorflow.learners.multi_agent_rl.qtran_learner.QTRAN_Learner method) (xuance.tensorflow.learners.multi_agent_rl.vdac_learner.VDAC_Learner method) (xuance.tensorflow.learners.multi_agent_rl.vdn_learner.VDN_Learner method) (xuance.tensorflow.learners.multi_agent_rl.wqmix_learner.WQMIX_Learner method) (xuance.tensorflow.learners.policy_gradient.a2c_learner.A2C_Learner method) (xuance.tensorflow.learners.policy_gradient.pg_learner.PG_Learner method) (xuance.tensorflow.learners.policy_gradient.ppo_learner.PPO_Learner method) (xuance.tensorflow.learners.policy_gradient.ppokl_learner.PPOKL_Learner method) (xuance.tensorflow.learners.qlearning_family.c51_learner.C51_Learner method) (xuance.tensorflow.learners.qlearning_family.ddqn_learner.DDQN_Learner method) (xuance.tensorflow.learners.qlearning_family.dqn_learner.DQN_Learner method) (xuance.tensorflow.learners.qlearning_family.drqn_learner.DRQN_Learner method) (xuance.tensorflow.learners.qlearning_family.dueldqn_learner.DuelDQN_Learner method) (xuance.tensorflow.learners.qlearning_family.perdqn_learner.PerDQN_Learner method) (xuance.tensorflow.learners.qlearning_family.qrdqn_learner.QRDQN_Learner method) learn_actor() (xuance.tensorflow.learners.policy_gradient.ddpg_learner.DDPG_Learner method) (xuance.tensorflow.learners.policy_gradient.sac_learner.SAC_Learner method) (xuance.tensorflow.learners.policy_gradient.sacdis_learner.SACDIS_Learner method) (xuance.tensorflow.learners.policy_gradient.td3_learner.TD3_Learner method) learn_alpha() (xuance.tensorflow.learners.policy_gradient.sac_learner.SAC_Learner method) (xuance.tensorflow.learners.policy_gradient.sacdis_learner.SACDIS_Learner method) learn_auxiliary() (xuance.tensorflow.learners.policy_gradient.ppg_learner.PPG_Learner method) learn_critic() (xuance.tensorflow.learners.policy_gradient.ddpg_learner.DDPG_Learner method) (xuance.tensorflow.learners.policy_gradient.ppg_learner.PPG_Learner method) (xuance.tensorflow.learners.policy_gradient.sac_learner.SAC_Learner method) (xuance.tensorflow.learners.policy_gradient.sacdis_learner.SACDIS_Learner method) (xuance.tensorflow.learners.policy_gradient.td3_learner.TD3_Learner method) learn_policy() (xuance.tensorflow.learners.policy_gradient.ppg_learner.PPG_Learner method) Learner (class in xuance.mindspore.learners.learner) (class in xuance.tensorflow.learners.learner) (class in xuance.torch.learners.learner) learner (xuance.torch.agents.base.agent.Agent attribute) LearnerMAS (class in xuance.mindspore.learners.learner) (class in xuance.tensorflow.learners.learner) (class in xuance.torch.learners.learner)

list_algorithms() (xuance.common.tuning_tools.AlgorithmHyperparametersRegistry class method) list_hyperparameters() (xuance.common.tuning_tools.HyperParameterTuner method) load_d4rl_dataset() (in module xuance.common.offline_util) load_dataset() (xuance.mindspore.agents.offline_rl.td3bc_agent.TD3_BC_Agent method) (xuance.tensorflow.agents.offline_rl.td3bc_agent.TD3_BC_Agent method) (xuance.torch.agents.offline_rl.td3bc_agent.TD3_BC_Agent method) load_model() (xuance.mindspore.agents.base.agent.Agent method) (xuance.mindspore.agents.base.agents_marl.MARLAgents method) (xuance.mindspore.agents.base.agents_marl.RandomAgents method) (xuance.mindspore.learners.learner.Learner method) (xuance.mindspore.learners.learner.LearnerMAS method) (xuance.tensorflow.agents.base.agent.Agent method) (xuance.tensorflow.agents.base.agents_marl.MARLAgents method) (xuance.tensorflow.agents.base.agents_marl.RandomAgents method) (xuance.tensorflow.learners.learner.Learner method) (xuance.tensorflow.learners.learner.LearnerMAS method) (xuance.torch.agents.base.agent.Agent method) (xuance.torch.agents.base.agents_marl.MARLAgents method) (xuance.torch.agents.base.agents_marl.RandomAgents method) (xuance.torch.learners.learner.Learner method) (xuance.torch.learners.learner.LearnerMAS method) load_snapshot() (xuance.torch.learners.learner.Learner method) load_yaml() (in module xuance.common.common_tools) log (xuance.common.tuning_tools.Hyperparameter attribute), [1] log_infos() (xuance.mindspore.agents.base.agent.Agent method) (xuance.mindspore.agents.base.agents_marl.MARLAgents method) (xuance.tensorflow.agents.base.agent.Agent method) (xuance.tensorflow.agents.base.agents_marl.MARLAgents method) (xuance.torch.agents.base.agent.Agent method) (xuance.torch.agents.base.agents_marl.MARLAgents method) log_prob() (xuance.mindspore.utils.distributions.CategoricalDistribution method) (xuance.mindspore.utils.distributions.DiagGaussianDistribution method) (xuance.mindspore.utils.distributions.Distribution method) (xuance.tensorflow.utils.distributions.CategoricalDistribution method) (xuance.tensorflow.utils.distributions.DiagGaussianDistribution method) (xuance.tensorflow.utils.distributions.Distribution method) (xuance.torch.utils.distributions.CategoricalDistribution method) (xuance.torch.utils.distributions.DiagGaussianDistribution method) (xuance.torch.utils.distributions.Distribution method) (xuance.torch.utils.distributions.MSEDistribution method) (xuance.torch.utils.distributions.SymLogDistribution method) (xuance.torch.utils.distributions.TruncatedNormal method) (xuance.torch.utils.distributions.TruncatedStandardNormal method) (xuance.torch.utils.distributions.TwoHotEncodingDistribution method) log_videos() (xuance.mindspore.agents.base.agent.Agent method) (xuance.mindspore.agents.base.agents_marl.MARLAgents method) (xuance.tensorflow.agents.base.agent.Agent method) (xuance.tensorflow.agents.base.agents_marl.MARLAgents method) (xuance.torch.agents.base.agent.Agent method) (xuance.torch.agents.base.agents_marl.MARLAgents method) lstm_block() (in module xuance.mindspore.utils.layers) (in module xuance.tensorflow.utils.layers) (in module xuance.torch.utils.layers)

M

MAAC_Policy (class in xuance.mindspore.policies.categorical_marl) (class in xuance.mindspore.policies.gaussian_marl) (class in xuance.tensorflow.policies.categorical_marl) (class in xuance.tensorflow.policies.gaussian_marl) (class in xuance.torch.policies.categorical_marl) (class in xuance.torch.policies.gaussian_marl) MAAC_Policy_Share (class in xuance.mindspore.policies.categorical_marl) (class in xuance.tensorflow.policies.categorical_marl) (class in xuance.torch.policies.categorical_marl) MADDPG_Agents (class in xuance.mindspore.agents.multi_agent_rl.maddpg_agents) (class in xuance.tensorflow.agents.multi_agent_rl.maddpg_agents) (class in xuance.torch.agents.multi_agent_rl.maddpg_agents) MADDPG_Learner (class in xuance.mindspore.learners.multi_agent_rl.maddpg_learner) (class in xuance.tensorflow.learners.multi_agent_rl.maddpg_learner) (class in xuance.torch.learners.multi_agent_rl.maddpg_learner) MADDPG_Policy (class in xuance.mindspore.policies.deterministic_marl) (class in xuance.tensorflow.policies.deterministic_marl) (class in xuance.torch.policies.deterministic_marl) make_envs() (in module xuance.environment) MAPPO_Agents (class in xuance.mindspore.agents.multi_agent_rl.mappo_agents) (class in xuance.tensorflow.agents.multi_agent_rl.mappo_agents) (class in xuance.torch.agents.multi_agent_rl.mappo_agents) MAPPO_Learner (class in xuance.mindspore.learners.multi_agent_rl.mappo_learner) (class in xuance.tensorflow.learners.multi_agent_rl.mappo_learner) (class in xuance.torch.learners.multi_agent_rl.mappo_learner) MARL_OffPolicyBuffer (class in xuance.common.memory_tools_marl) MARL_OffPolicyBuffer_RNN (class in xuance.common.memory_tools_marl) MARL_OnPolicyBuffer (class in xuance.common.memory_tools_marl) MARL_OnPolicyBuffer_RNN (class in xuance.common.memory_tools_marl) MARLAgents (class in xuance.mindspore.agents.base.agents_marl) (class in xuance.tensorflow.agents.base.agents_marl) (class in xuance.torch.agents.base.agents_marl) MASAC_Agents (class in xuance.mindspore.agents.multi_agent_rl.masac_agents) (class in xuance.tensorflow.agents.multi_agent_rl.masac_agents) (class in xuance.torch.agents.multi_agent_rl.masac_agents) MASAC_Learner (class in xuance.mindspore.learners.multi_agent_rl.masac_learner) (class in xuance.tensorflow.learners.multi_agent_rl.masac_learner) (class in xuance.torch.learners.multi_agent_rl.masac_learner) MASAC_Policy (class in xuance.mindspore.policies.categorical_marl) (class in xuance.mindspore.policies.gaussian_marl) (class in xuance.tensorflow.policies.categorical_marl) (class in xuance.tensorflow.policies.gaussian_marl) (class in xuance.torch.policies.categorical_marl) (class in xuance.torch.policies.gaussian_marl) MASACDIS_Learner (class in xuance.mindspore.learners.multi_agent_rl.masacdis_learner) (class in xuance.tensorflow.learners.multi_agent_rl.masacdis_learner) (class in xuance.torch.learners.multi_agent_rl.masacdis_learner) MATD3_Agents (class in xuance.mindspore.agents.multi_agent_rl.matd3_agents) (class in xuance.tensorflow.agents.multi_agent_rl.matd3_agents) (class in xuance.torch.agents.multi_agent_rl.matd3_agents) MATD3_Learner (class in xuance.mindspore.learners.multi_agent_rl.matd3_learner) (class in xuance.tensorflow.learners.multi_agent_rl.matd3_learner) (class in xuance.torch.learners.multi_agent_rl.matd3_learner) MATD3_Policy (class in xuance.mindspore.policies.deterministic_marl) (class in xuance.tensorflow.policies.deterministic_marl) (class in xuance.torch.policies.deterministic_marl) max_episode_steps (xuance.environment.utils.wrapper.XuanCeEnvWrapper property) mean (xuance.torch.utils.distributions.MSEDistribution property) (xuance.torch.utils.distributions.SymLogDistribution property) (xuance.torch.utils.distributions.TruncatedStandardNormal property) (xuance.torch.utils.distributions.TwoHotEncodingDistribution property) MeanField_OffPolicyBuffer (class in xuance.common.memory_tools_marl) MeanField_OffPolicyBuffer_RNN (class in xuance.common.memory_tools_marl) MeanField_OnPolicyBuffer (class in xuance.common.memory_tools_marl) MeanField_OnPolicyBuffer_RNN (class in xuance.common.memory_tools_marl) MeanFieldActorCriticPolicy (class in xuance.mindspore.policies.categorical_marl) (class in xuance.tensorflow.policies.categorical_marl) (class in xuance.torch.policies.categorical_marl) memory (xuance.torch.agents.base.agent.Agent attribute) (xuance.torch.agents.core.off_policy.OffPolicyAgent attribute) merge_distributions() (in module xuance.mindspore.utils.distributions) (in module xuance.tensorflow.utils.distributions) (in module xuance.torch.utils.distributions) message_encode() (xuance.mindspore.communications.comm_net.CommNet method) (xuance.tensorflow.communications.comm_net.CommNet method) (xuance.torch.communications.comm_net.CommNet method) metadata (xuance.environment.utils.wrapper.XuanCeEnvWrapper property) MetaDrive_Env (class in xuance.environment.single_agent_env.metadrive) MFAC_Agents (class in xuance.mindspore.agents.multi_agent_rl.mfac_agents) (class in xuance.tensorflow.agents.multi_agent_rl.mfac_agents) (class in xuance.torch.agents.multi_agent_rl.mfac_agents) MFAC_Learner (class in xuance.mindspore.learners.multi_agent_rl.mfac_learner) (class in xuance.tensorflow.learners.multi_agent_rl.mfac_learner) (class in xuance.torch.learners.multi_agent_rl.mfac_learner) MFQ_Agents (class in xuance.mindspore.agents.multi_agent_rl.mfq_agents) (class in xuance.tensorflow.agents.multi_agent_rl.mfq_agents) (class in xuance.torch.agents.multi_agent_rl.mfq_agents) MFQ_Learner (class in xuance.mindspore.learners.multi_agent_rl.mfq_learner) (class in xuance.tensorflow.learners.multi_agent_rl.mfq_learner) (class in xuance.torch.learners.multi_agent_rl.mfq_learner) MFQnetwork (class in xuance.mindspore.policies.deterministic_marl) (class in xuance.tensorflow.policies.deterministic_marl) (class in xuance.torch.policies.deterministic_marl) min() (xuance.common.segtree_tool.MinSegmentTree method) miniblock() (in module xuance.mindspore.utils.layers4dreamer) (in module xuance.tensorflow.utils.layers4dreamer) (in module xuance.torch.utils.layers4dreamer) MiniGridEnv (class in xuance.environment.single_agent_env.minigrid) MinSegmentTree (class in xuance.common.segtree_tool) MixingQnetwork (class in xuance.mindspore.policies.deterministic_marl) (class in xuance.tensorflow.policies.deterministic_marl) (class in xuance.torch.policies.deterministic_marl) MLP (class in xuance.mindspore.utils.layers4dreamer) (class in xuance.tensorflow.utils.layers4dreamer) (class in xuance.torch.utils.layers4dreamer) mlp_block() (in module xuance.mindspore.utils.layers) (in module xuance.tensorflow.utils.layers) (in module xuance.torch.utils.layers) mlp_keys (xuance.mindspore.utils.layers4dreamer.MultiDecoder property) (xuance.mindspore.utils.layers4dreamer.MultiEncoder property) (xuance.tensorflow.utils.layers4dreamer.MultiDecoder property) (xuance.tensorflow.utils.layers4dreamer.MultiEncoder property) (xuance.torch.utils.layers4dreamer.MultiDecoder property) (xuance.torch.utils.layers4dreamer.MultiEncoder property) MLPDecoder (class in xuance.mindspore.representations.world_model) (class in xuance.mindspore.representations.world_model_v2) (class in xuance.tensorflow.representations.world_model) (class in xuance.tensorflow.representations.world_model_v2) (class in xuance.torch.representations.world_model) (class in xuance.torch.representations.world_model_v2) MLPEncoder (class in xuance.mindspore.representations.world_model) (class in xuance.mindspore.representations.world_model_v2) (class in xuance.tensorflow.representations.world_model) (class in xuance.tensorflow.representations.world_model_v2) (class in xuance.torch.representations.world_model) (class in xuance.torch.representations.world_model_v2) mode (xuance.torch.utils.distributions.BernoulliSafeMode property) (xuance.torch.utils.distributions.MSEDistribution property) (xuance.torch.utils.distributions.SymLogDistribution property) (xuance.torch.utils.distributions.TwoHotEncodingDistribution property) model (xuance.mindspore.utils.layers4dreamer.CNN property) (xuance.mindspore.utils.layers4dreamer.DeCNN property) (xuance.mindspore.utils.layers4dreamer.MLP property) (xuance.tensorflow.utils.layers4dreamer.CNN property) (xuance.tensorflow.utils.layers4dreamer.DeCNN property) (xuance.tensorflow.utils.layers4dreamer.MLP property) (xuance.torch.utils.layers4dreamer.CNN property) (xuance.torch.utils.layers4dreamer.DeCNN property) (xuance.torch.utils.layers4dreamer.MLP property) model_forward() (xuance.mindspore.policies.dreamer.DreamerV2Policy method) (xuance.mindspore.policies.dreamer.DreamerV3Policy method) (xuance.tensorflow.policies.dreamer.DreamerV2Policy method) (xuance.tensorflow.policies.dreamer.DreamerV3Policy method) (xuance.torch.policies.dreamer.DreamerV2Policy method) (xuance.torch.policies.dreamer.DreamerV3Policy method) module xuance.common.callback xuance.common.common_tools xuance.common.memory_offline xuance.common.memory_tools xuance.common.memory_tools_marl xuance.common.offline_util xuance.common.segtree_tool xuance.common.statistic_tools xuance.common.tuning_tools xuance.engine.run_basic xuance.engine.run_competition xuance.engine.run_drl xuance.engine.run_football xuance.engine.run_marl xuance.engine.run_offlinerl xuance.engine.run_sc2 xuance.environment xuance.environment.multi_agent_env.drones xuance.environment.multi_agent_env.football xuance.environment.multi_agent_env.mpe xuance.environment.multi_agent_env.robotic_warehouse xuance.environment.multi_agent_env.starcraft2 xuance.environment.single_agent_env.gym xuance.environment.single_agent_env.metadrive xuance.environment.single_agent_env.minigrid xuance.environment.single_agent_env.platform xuance.environment.utils.base xuance.environment.utils.wrapper xuance.environment.vector_envs.dummy.dummy_vec_env xuance.environment.vector_envs.dummy.dummy_vec_maenv xuance.environment.vector_envs.env_utils xuance.environment.vector_envs.subprocess.subproc_vec_env xuance.environment.vector_envs.subprocess.subproc_vec_maenv xuance.environment.vector_envs.vector_env xuance.mindspore.agents.base.agent xuance.mindspore.agents.base.agents_marl xuance.mindspore.agents.contrastive_unsupervised_rl.curl_agent, [1] xuance.mindspore.agents.contrastive_unsupervised_rl.drq_agent, [1] xuance.mindspore.agents.contrastive_unsupervised_rl.spr_agent, [1] xuance.mindspore.agents.core.off_policy xuance.mindspore.agents.core.off_policy_marl xuance.mindspore.agents.core.offline xuance.mindspore.agents.core.on_policy xuance.mindspore.agents.core.on_policy_marl xuance.mindspore.agents.model_based_rl.dreamer_v2_agent xuance.mindspore.agents.model_based_rl.dreamer_v3_agent xuance.mindspore.agents.multi_agent_rl.coma_agents xuance.mindspore.agents.multi_agent_rl.commnet_agents xuance.mindspore.agents.multi_agent_rl.dcg_agents xuance.mindspore.agents.multi_agent_rl.iac_agents xuance.mindspore.agents.multi_agent_rl.ic3net_agents xuance.mindspore.agents.multi_agent_rl.iddpg_agents xuance.mindspore.agents.multi_agent_rl.ippo_agents xuance.mindspore.agents.multi_agent_rl.iql_agents xuance.mindspore.agents.multi_agent_rl.isac_agents xuance.mindspore.agents.multi_agent_rl.maddpg_agents xuance.mindspore.agents.multi_agent_rl.mappo_agents xuance.mindspore.agents.multi_agent_rl.masac_agents xuance.mindspore.agents.multi_agent_rl.matd3_agents xuance.mindspore.agents.multi_agent_rl.mfac_agents xuance.mindspore.agents.multi_agent_rl.mfq_agents xuance.mindspore.agents.multi_agent_rl.qmix_agents xuance.mindspore.agents.multi_agent_rl.qtran_agents xuance.mindspore.agents.multi_agent_rl.tarmac_agents xuance.mindspore.agents.multi_agent_rl.vdac_agents xuance.mindspore.agents.multi_agent_rl.vdn_agents xuance.mindspore.agents.multi_agent_rl.wqmix_agents xuance.mindspore.agents.offline_rl.td3bc_agent xuance.mindspore.agents.policy_gradient.a2c_agent xuance.mindspore.agents.policy_gradient.ddpg_agent xuance.mindspore.agents.policy_gradient.mpdqn_agent xuance.mindspore.agents.policy_gradient.npg_agent xuance.mindspore.agents.policy_gradient.pdqn_agent xuance.mindspore.agents.policy_gradient.pg_agent xuance.mindspore.agents.policy_gradient.ppg_agent xuance.mindspore.agents.policy_gradient.ppo_agent xuance.mindspore.agents.policy_gradient.ppokl_agent xuance.mindspore.agents.policy_gradient.sac_agent xuance.mindspore.agents.policy_gradient.spdqn_agent xuance.mindspore.agents.policy_gradient.td3_agent xuance.mindspore.agents.qlearning_family.c51_agent xuance.mindspore.agents.qlearning_family.ddqn_agent xuance.mindspore.agents.qlearning_family.dqn_agent xuance.mindspore.agents.qlearning_family.drqn_agent xuance.mindspore.agents.qlearning_family.dueldqn_agent xuance.mindspore.agents.qlearning_family.noisydqn_agent xuance.mindspore.agents.qlearning_family.perdqn_agent xuance.mindspore.agents.qlearning_family.qrdqn_agent xuance.mindspore.communications.attention_comm xuance.mindspore.communications.base_comm xuance.mindspore.communications.comm_net xuance.mindspore.communications.emergent_comm xuance.mindspore.communications.gnn_comm xuance.mindspore.communications.ic3net_comm xuance.mindspore.learners.contrastive_unsupervised_rl.curl_learner xuance.mindspore.learners.contrastive_unsupervised_rl.drq_learner xuance.mindspore.learners.contrastive_unsupervised_rl.spr_learner xuance.mindspore.learners.learner xuance.mindspore.learners.model_based.dreamer_v2_learner xuance.mindspore.learners.model_based.dreamer_v3_learner xuance.mindspore.learners.multi_agent_rl.coma_learner xuance.mindspore.learners.multi_agent_rl.commnet_learner xuance.mindspore.learners.multi_agent_rl.dcg_learner xuance.mindspore.learners.multi_agent_rl.iac_learner xuance.mindspore.learners.multi_agent_rl.ic3net_learner xuance.mindspore.learners.multi_agent_rl.iddpg_learner xuance.mindspore.learners.multi_agent_rl.ippo_learner xuance.mindspore.learners.multi_agent_rl.iql_learner xuance.mindspore.learners.multi_agent_rl.isac_learner xuance.mindspore.learners.multi_agent_rl.isacdis_learner xuance.mindspore.learners.multi_agent_rl.maddpg_learner xuance.mindspore.learners.multi_agent_rl.mappo_learner xuance.mindspore.learners.multi_agent_rl.masac_learner xuance.mindspore.learners.multi_agent_rl.masacdis_learner xuance.mindspore.learners.multi_agent_rl.matd3_learner xuance.mindspore.learners.multi_agent_rl.mfac_learner xuance.mindspore.learners.multi_agent_rl.mfq_learner xuance.mindspore.learners.multi_agent_rl.qmix_learner xuance.mindspore.learners.multi_agent_rl.qtran_learner xuance.mindspore.learners.multi_agent_rl.tarmac_learner xuance.mindspore.learners.multi_agent_rl.vdac_learner xuance.mindspore.learners.multi_agent_rl.vdn_learner xuance.mindspore.learners.multi_agent_rl.wqmix_learner xuance.mindspore.learners.offline.td3bc_learner xuance.mindspore.learners.policy_gradient.a2c_learner xuance.mindspore.learners.policy_gradient.ddpg_learner xuance.mindspore.learners.policy_gradient.mpdqn_learner xuance.mindspore.learners.policy_gradient.npg_learner xuance.mindspore.learners.policy_gradient.pdqn_learner xuance.mindspore.learners.policy_gradient.pg_learner xuance.mindspore.learners.policy_gradient.ppg_learner xuance.mindspore.learners.policy_gradient.ppo_learner xuance.mindspore.learners.policy_gradient.ppokl_learner xuance.mindspore.learners.policy_gradient.sac_learner xuance.mindspore.learners.policy_gradient.sacdis_learner xuance.mindspore.learners.policy_gradient.spdqn_learner xuance.mindspore.learners.policy_gradient.td3_learner xuance.mindspore.learners.qlearning_family.c51_learner xuance.mindspore.learners.qlearning_family.ddqn_learner xuance.mindspore.learners.qlearning_family.dqn_learner xuance.mindspore.learners.qlearning_family.drqn_learner xuance.mindspore.learners.qlearning_family.dueldqn_learner xuance.mindspore.learners.qlearning_family.perdqn_learner xuance.mindspore.learners.qlearning_family.qrdqn_learner xuance.mindspore.policies.categorical xuance.mindspore.policies.categorical_marl xuance.mindspore.policies.coordination_graph xuance.mindspore.policies.core xuance.mindspore.policies.deterministic xuance.mindspore.policies.deterministic_marl xuance.mindspore.policies.dreamer xuance.mindspore.policies.gaussian xuance.mindspore.policies.gaussian_marl xuance.mindspore.representations.cnn xuance.mindspore.representations.mlp xuance.mindspore.representations.rnn xuance.mindspore.representations.vit xuance.mindspore.representations.world_model xuance.mindspore.representations.world_model_v2 xuance.mindspore.utils.device xuance.mindspore.utils.distributions xuance.mindspore.utils.harmonizer xuance.mindspore.utils.layers xuance.mindspore.utils.layers4dreamer xuance.mindspore.utils.operations xuance.mindspore.utils.value_norm xuance.tensorflow.agents.base.agent xuance.tensorflow.agents.base.agents_marl xuance.tensorflow.agents.contrastive_unsupervised_rl.curl_agent, [1] xuance.tensorflow.agents.contrastive_unsupervised_rl.drq_agent, [1] xuance.tensorflow.agents.contrastive_unsupervised_rl.spr_agent, [1] xuance.tensorflow.agents.core.off_policy xuance.tensorflow.agents.core.off_policy_marl xuance.tensorflow.agents.core.offline xuance.tensorflow.agents.core.on_policy xuance.tensorflow.agents.core.on_policy_marl xuance.tensorflow.agents.model_based_rl.dreamer_v2_agent xuance.tensorflow.agents.model_based_rl.dreamer_v3_agent xuance.tensorflow.agents.multi_agent_rl.coma_agents xuance.tensorflow.agents.multi_agent_rl.commnet_agents xuance.tensorflow.agents.multi_agent_rl.dcg_agents xuance.tensorflow.agents.multi_agent_rl.iac_agents xuance.tensorflow.agents.multi_agent_rl.ic3net_agents xuance.tensorflow.agents.multi_agent_rl.iddpg_agents xuance.tensorflow.agents.multi_agent_rl.ippo_agents xuance.tensorflow.agents.multi_agent_rl.iql_agents xuance.tensorflow.agents.multi_agent_rl.isac_agents xuance.tensorflow.agents.multi_agent_rl.maddpg_agents xuance.tensorflow.agents.multi_agent_rl.mappo_agents xuance.tensorflow.agents.multi_agent_rl.masac_agents xuance.tensorflow.agents.multi_agent_rl.matd3_agents xuance.tensorflow.agents.multi_agent_rl.mfac_agents xuance.tensorflow.agents.multi_agent_rl.mfq_agents xuance.tensorflow.agents.multi_agent_rl.qmix_agents xuance.tensorflow.agents.multi_agent_rl.qtran_agents xuance.tensorflow.agents.multi_agent_rl.tarmac_agents xuance.tensorflow.agents.multi_agent_rl.vdac_agents xuance.tensorflow.agents.multi_agent_rl.vdn_agents xuance.tensorflow.agents.multi_agent_rl.wqmix_agents xuance.tensorflow.agents.offline_rl.td3bc_agent xuance.tensorflow.agents.policy_gradient.a2c_agent xuance.tensorflow.agents.policy_gradient.ddpg_agent xuance.tensorflow.agents.policy_gradient.mpdqn_agent xuance.tensorflow.agents.policy_gradient.npg_agent xuance.tensorflow.agents.policy_gradient.pdqn_agent xuance.tensorflow.agents.policy_gradient.pg_agent xuance.tensorflow.agents.policy_gradient.ppg_agent xuance.tensorflow.agents.policy_gradient.ppo_agent xuance.tensorflow.agents.policy_gradient.ppokl_agent xuance.tensorflow.agents.policy_gradient.sac_agent xuance.tensorflow.agents.policy_gradient.spdqn_agent xuance.tensorflow.agents.policy_gradient.td3_agent xuance.tensorflow.agents.qlearning_family.c51_agent xuance.tensorflow.agents.qlearning_family.ddqn_agent xuance.tensorflow.agents.qlearning_family.dqn_agent xuance.tensorflow.agents.qlearning_family.drqn_agent xuance.tensorflow.agents.qlearning_family.dueldqn_agent xuance.tensorflow.agents.qlearning_family.noisydqn_agent xuance.tensorflow.agents.qlearning_family.perdqn_agent xuance.tensorflow.agents.qlearning_family.qrdqn_agent xuance.tensorflow.communications.attention_comm xuance.tensorflow.communications.base_comm xuance.tensorflow.communications.comm_net xuance.tensorflow.communications.emergent_comm xuance.tensorflow.communications.gnn_comm xuance.tensorflow.communications.ic3net_comm xuance.tensorflow.learners.contrastive_unsupervised_rl.curl_learner xuance.tensorflow.learners.contrastive_unsupervised_rl.drq_learner xuance.tensorflow.learners.contrastive_unsupervised_rl.spr_learner xuance.tensorflow.learners.learner xuance.tensorflow.learners.model_based.dreamer_v2_learner xuance.tensorflow.learners.model_based.dreamer_v3_learner xuance.tensorflow.learners.multi_agent_rl.coma_learner xuance.tensorflow.learners.multi_agent_rl.commnet_learner xuance.tensorflow.learners.multi_agent_rl.dcg_learner xuance.tensorflow.learners.multi_agent_rl.iac_learner xuance.tensorflow.learners.multi_agent_rl.ic3net_learner xuance.tensorflow.learners.multi_agent_rl.iddpg_learner xuance.tensorflow.learners.multi_agent_rl.ippo_learner xuance.tensorflow.learners.multi_agent_rl.iql_learner xuance.tensorflow.learners.multi_agent_rl.isac_learner xuance.tensorflow.learners.multi_agent_rl.isacdis_learner xuance.tensorflow.learners.multi_agent_rl.maddpg_learner xuance.tensorflow.learners.multi_agent_rl.mappo_learner xuance.tensorflow.learners.multi_agent_rl.masac_learner xuance.tensorflow.learners.multi_agent_rl.masacdis_learner xuance.tensorflow.learners.multi_agent_rl.matd3_learner xuance.tensorflow.learners.multi_agent_rl.mfac_learner xuance.tensorflow.learners.multi_agent_rl.mfq_learner xuance.tensorflow.learners.multi_agent_rl.qmix_learner xuance.tensorflow.learners.multi_agent_rl.qtran_learner xuance.tensorflow.learners.multi_agent_rl.tarmac_learner xuance.tensorflow.learners.multi_agent_rl.vdac_learner xuance.tensorflow.learners.multi_agent_rl.vdn_learner xuance.tensorflow.learners.multi_agent_rl.wqmix_learner xuance.tensorflow.learners.offline.td3bc_learner xuance.tensorflow.learners.policy_gradient.a2c_learner xuance.tensorflow.learners.policy_gradient.ddpg_learner xuance.tensorflow.learners.policy_gradient.mpdqn_learner xuance.tensorflow.learners.policy_gradient.npg_learner xuance.tensorflow.learners.policy_gradient.pdqn_learner xuance.tensorflow.learners.policy_gradient.pg_learner xuance.tensorflow.learners.policy_gradient.ppg_learner xuance.tensorflow.learners.policy_gradient.ppo_learner xuance.tensorflow.learners.policy_gradient.ppokl_learner xuance.tensorflow.learners.policy_gradient.sac_learner xuance.tensorflow.learners.policy_gradient.sacdis_learner xuance.tensorflow.learners.policy_gradient.spdqn_learner xuance.tensorflow.learners.policy_gradient.td3_learner xuance.tensorflow.learners.qlearning_family.c51_learner xuance.tensorflow.learners.qlearning_family.ddqn_learner xuance.tensorflow.learners.qlearning_family.dqn_learner xuance.tensorflow.learners.qlearning_family.drqn_learner xuance.tensorflow.learners.qlearning_family.dueldqn_learner xuance.tensorflow.learners.qlearning_family.perdqn_learner xuance.tensorflow.learners.qlearning_family.qrdqn_learner xuance.tensorflow.policies.categorical xuance.tensorflow.policies.categorical_marl xuance.tensorflow.policies.coordination_graph xuance.tensorflow.policies.core xuance.tensorflow.policies.deterministic xuance.tensorflow.policies.deterministic_marl xuance.tensorflow.policies.dreamer xuance.tensorflow.policies.gaussian xuance.tensorflow.policies.gaussian_marl xuance.tensorflow.representations.cnn xuance.tensorflow.representations.mlp xuance.tensorflow.representations.rnn xuance.tensorflow.representations.vit xuance.tensorflow.representations.world_model xuance.tensorflow.representations.world_model_v2 xuance.tensorflow.utils.device xuance.tensorflow.utils.distributions xuance.tensorflow.utils.harmonizer xuance.tensorflow.utils.layers xuance.tensorflow.utils.layers4dreamer xuance.tensorflow.utils.operations xuance.tensorflow.utils.value_norm xuance.torch.agents.base.agent xuance.torch.agents.base.agents_marl xuance.torch.agents.contrastive_unsupervised_rl.curl_agent, [1] xuance.torch.agents.contrastive_unsupervised_rl.drq_agent, [1] xuance.torch.agents.contrastive_unsupervised_rl.spr_agent, [1] xuance.torch.agents.core.off_policy xuance.torch.agents.core.off_policy_marl xuance.torch.agents.core.offline xuance.torch.agents.core.on_policy xuance.torch.agents.core.on_policy_marl xuance.torch.agents.model_based_rl.dreamer_v2_agent xuance.torch.agents.model_based_rl.dreamer_v3_agent xuance.torch.agents.multi_agent_rl.coma_agents xuance.torch.agents.multi_agent_rl.commnet_agents xuance.torch.agents.multi_agent_rl.dcg_agents xuance.torch.agents.multi_agent_rl.iac_agents xuance.torch.agents.multi_agent_rl.ic3net_agents xuance.torch.agents.multi_agent_rl.iddpg_agents xuance.torch.agents.multi_agent_rl.ippo_agents xuance.torch.agents.multi_agent_rl.iql_agents xuance.torch.agents.multi_agent_rl.isac_agents xuance.torch.agents.multi_agent_rl.maddpg_agents xuance.torch.agents.multi_agent_rl.mappo_agents xuance.torch.agents.multi_agent_rl.masac_agents xuance.torch.agents.multi_agent_rl.matd3_agents xuance.torch.agents.multi_agent_rl.mfac_agents xuance.torch.agents.multi_agent_rl.mfq_agents xuance.torch.agents.multi_agent_rl.qmix_agents xuance.torch.agents.multi_agent_rl.qtran_agents xuance.torch.agents.multi_agent_rl.tarmac_agents xuance.torch.agents.multi_agent_rl.vdac_agents xuance.torch.agents.multi_agent_rl.vdn_agents xuance.torch.agents.multi_agent_rl.wqmix_agents xuance.torch.agents.offline_rl.td3bc_agent xuance.torch.agents.policy_gradient.a2c_agent xuance.torch.agents.policy_gradient.ddpg_agent xuance.torch.agents.policy_gradient.mpdqn_agent xuance.torch.agents.policy_gradient.npg_agent xuance.torch.agents.policy_gradient.pdqn_agent xuance.torch.agents.policy_gradient.pg_agent xuance.torch.agents.policy_gradient.ppg_agent xuance.torch.agents.policy_gradient.ppo_agent xuance.torch.agents.policy_gradient.ppokl_agent xuance.torch.agents.policy_gradient.sac_agent xuance.torch.agents.policy_gradient.spdqn_agent xuance.torch.agents.policy_gradient.td3_agent xuance.torch.agents.qlearning_family.c51_agent xuance.torch.agents.qlearning_family.ddqn_agent xuance.torch.agents.qlearning_family.dqn_agent xuance.torch.agents.qlearning_family.drqn_agent xuance.torch.agents.qlearning_family.dueldqn_agent xuance.torch.agents.qlearning_family.noisydqn_agent xuance.torch.agents.qlearning_family.perdqn_agent xuance.torch.agents.qlearning_family.qrdqn_agent xuance.torch.communications.attention_comm xuance.torch.communications.base_comm xuance.torch.communications.comm_net xuance.torch.communications.emergent_comm xuance.torch.communications.gnn_comm xuance.torch.communications.ic3net_comm xuance.torch.learners.contrastive_unsupervised_rl.curl_learner xuance.torch.learners.contrastive_unsupervised_rl.drq_learner xuance.torch.learners.contrastive_unsupervised_rl.spr_learner xuance.torch.learners.learner xuance.torch.learners.model_based.dreamer_v2_learner xuance.torch.learners.model_based.dreamer_v3_learner xuance.torch.learners.multi_agent_rl.coma_learner xuance.torch.learners.multi_agent_rl.commnet_learner xuance.torch.learners.multi_agent_rl.dcg_learner xuance.torch.learners.multi_agent_rl.iac_learner xuance.torch.learners.multi_agent_rl.ic3net_learner xuance.torch.learners.multi_agent_rl.iddpg_learner xuance.torch.learners.multi_agent_rl.ippo_learner xuance.torch.learners.multi_agent_rl.iql_learner xuance.torch.learners.multi_agent_rl.isac_learner xuance.torch.learners.multi_agent_rl.isacdis_learner xuance.torch.learners.multi_agent_rl.maddpg_learner xuance.torch.learners.multi_agent_rl.mappo_learner xuance.torch.learners.multi_agent_rl.masac_learner xuance.torch.learners.multi_agent_rl.masacdis_learner xuance.torch.learners.multi_agent_rl.matd3_learner xuance.torch.learners.multi_agent_rl.mfac_learner xuance.torch.learners.multi_agent_rl.mfq_learner xuance.torch.learners.multi_agent_rl.qmix_learner xuance.torch.learners.multi_agent_rl.qtran_learner xuance.torch.learners.multi_agent_rl.tarmac_learner xuance.torch.learners.multi_agent_rl.vdac_learner xuance.torch.learners.multi_agent_rl.vdn_learner xuance.torch.learners.multi_agent_rl.wqmix_learner xuance.torch.learners.offline.td3bc_learner xuance.torch.learners.policy_gradient.a2c_learner xuance.torch.learners.policy_gradient.ddpg_learner xuance.torch.learners.policy_gradient.mpdqn_learner xuance.torch.learners.policy_gradient.npg_learner xuance.torch.learners.policy_gradient.pdqn_learner xuance.torch.learners.policy_gradient.pg_learner xuance.torch.learners.policy_gradient.ppg_learner xuance.torch.learners.policy_gradient.ppo_learner xuance.torch.learners.policy_gradient.ppokl_learner xuance.torch.learners.policy_gradient.sac_learner xuance.torch.learners.policy_gradient.sacdis_learner xuance.torch.learners.policy_gradient.spdqn_learner xuance.torch.learners.policy_gradient.td3_learner xuance.torch.learners.qlearning_family.c51_learner xuance.torch.learners.qlearning_family.ddqn_learner xuance.torch.learners.qlearning_family.dqn_learner xuance.torch.learners.qlearning_family.drqn_learner xuance.torch.learners.qlearning_family.dueldqn_learner xuance.torch.learners.qlearning_family.perdqn_learner xuance.torch.learners.qlearning_family.qrdqn_learner xuance.torch.policies.categorical xuance.torch.policies.categorical_marl xuance.torch.policies.coordination_graph xuance.torch.policies.core xuance.torch.policies.deterministic xuance.torch.policies.deterministic_marl xuance.torch.policies.dreamer xuance.torch.policies.gaussian xuance.torch.policies.gaussian_marl xuance.torch.representations.cnn xuance.torch.representations.mlp xuance.torch.representations.rnn xuance.torch.representations.vit xuance.torch.representations.world_model xuance.torch.representations.world_model_v2 xuance.torch.utils.device xuance.torch.utils.distributions xuance.torch.utils.harmonizer xuance.torch.utils.layers xuance.torch.utils.layers4dreamer xuance.torch.utils.operations xuance.torch.utils.value_norm

Moments (class in xuance.torch.utils.layers) MountainCar (class in xuance.environment.single_agent_env.gym) MPDQN_Agent (class in xuance.mindspore.agents.policy_gradient.mpdqn_agent) (class in xuance.tensorflow.agents.policy_gradient.mpdqn_agent) (class in xuance.torch.agents.policy_gradient.mpdqn_agent) MPDQN_Learner (class in xuance.mindspore.learners.policy_gradient.mpdqn_learner) (class in xuance.tensorflow.learners.policy_gradient.mpdqn_learner) (class in xuance.torch.learners.policy_gradient.mpdqn_learner) MPDQN_Learner.ConActorNetWithLossCell (class in xuance.mindspore.learners.policy_gradient.mpdqn_learner) MPDQN_Learner.QNetWithLossCell (class in xuance.mindspore.learners.policy_gradient.mpdqn_learner) MPDQNPolicy (class in xuance.mindspore.policies.deterministic) (class in xuance.tensorflow.policies.deterministic) (class in xuance.torch.policies.deterministic) MPE_Env (class in xuance.environment.multi_agent_env.mpe) mpi_mean() (in module xuance.common.statistic_tools) mpi_moments() (in module xuance.common.statistic_tools) MSEDistribution (class in xuance.torch.utils.distributions) MultiAgentBaseCallback (class in xuance.common.callback) MultiDecoder (class in xuance.mindspore.utils.layers4dreamer) (class in xuance.tensorflow.utils.layers4dreamer) (class in xuance.torch.utils.layers4dreamer) MultiEncoder (class in xuance.mindspore.utils.layers4dreamer) (class in xuance.tensorflow.utils.layers4dreamer) (class in xuance.torch.utils.layers4dreamer) MultiHoverAviary (class in xuance.environment.multi_agent_env.drones) MultiObjectiveTuner (class in xuance.common.tuning_tools) MyLinearLR (class in xuance.tensorflow.utils.operations)

N

name (xuance.common.tuning_tools.Hyperparameter attribute), [1] NatureCNN (class in xuance.mindspore.utils.layers4dreamer) (class in xuance.tensorflow.utils.layers4dreamer) (class in xuance.torch.utils.layers4dreamer) noisy_parameters() (xuance.mindspore.policies.deterministic.NoisyQnetwork method) NoisyDQN_Agent (class in xuance.mindspore.agents.qlearning_family.noisydqn_agent) (class in xuance.tensorflow.agents.qlearning_family.noisydqn_agent) (class in xuance.torch.agents.qlearning_family.noisydqn_agent) NoisyQnetwork (class in xuance.mindspore.policies.deterministic) (class in xuance.tensorflow.policies.deterministic) (class in xuance.torch.policies.deterministic) NoneComm (class in xuance.mindspore.communications.base_comm) (class in xuance.tensorflow.communications.base_comm) (class in xuance.torch.communications.base_comm)

normalize() (xuance.mindspore.utils.value_norm.ValueNorm method) (xuance.tensorflow.utils.value_norm.ValueNorm method) (xuance.torch.utils.value_norm.ValueNorm method) normalize_states() (in module xuance.common.offline_util) NotSteppingError NPG_Agent (class in xuance.mindspore.agents.policy_gradient.npg_agent) (class in xuance.tensorflow.agents.policy_gradient.npg_agent) (class in xuance.torch.agents.policy_gradient.npg_agent) NPG_Learner (class in xuance.mindspore.learners.policy_gradient.npg_learner) (class in xuance.tensorflow.learners.policy_gradient.npg_learner) (class in xuance.torch.learners.policy_gradient.npg_learner)

O

objective() (xuance.common.tuning_tools.HyperParameterTuner method) (xuance.common.tuning_tools.MultiObjectiveTuner method) obs_encode() (xuance.mindspore.communications.comm_net.CommNet method) (xuance.mindspore.communications.gnn_comm.DGNComm method) (xuance.tensorflow.communications.comm_net.CommNet method) (xuance.tensorflow.communications.gnn_comm.DGNComm method) (xuance.torch.communications.comm_net.CommNet method) obs_n_space_info() (in module xuance.environment.vector_envs.env_utils) obs_shape (xuance.mindspore.agents.model_based_rl.dreamer_v2_agent.DreamerV2Agent attribute) (xuance.mindspore.agents.model_based_rl.dreamer_v3_agent.DreamerV3Agent attribute) (xuance.tensorflow.agents.model_based_rl.dreamer_v2_agent.DreamerV2Agent attribute) (xuance.tensorflow.agents.model_based_rl.dreamer_v3_agent.DreamerV3Agent attribute) (xuance.torch.agents.model_based_rl.dreamer_v2_agent.DreamerV2Agent attribute) (xuance.torch.agents.model_based_rl.dreamer_v3_agent.DreamerV3Agent attribute) obs_space (xuance.mindspore.representations.world_model.DreamerV3WorldModel attribute) (xuance.mindspore.representations.world_model_v2.DreamerV2WorldModel attribute) (xuance.tensorflow.representations.world_model.DreamerV3WorldModel attribute) (xuance.tensorflow.representations.world_model_v2.DreamerV2WorldModel attribute) (xuance.torch.representations.world_model.DreamerV3WorldModel attribute) (xuance.torch.representations.world_model_v2.DreamerV2WorldModel attribute) obs_space_info() (in module xuance.environment.vector_envs.env_utils) observation_space (xuance.environment.utils.wrapper.XuanCeEnvWrapper property) OfflineAgent (class in xuance.mindspore.agents.core.offline) (class in xuance.tensorflow.agents.core.offline) (class in xuance.torch.agents.core.offline) OfflineBuffer_D4RL (class in xuance.common.memory_offline) OffPolicyAgent (class in xuance.mindspore.agents.core.off_policy) (class in xuance.tensorflow.agents.core.off_policy) (class in xuance.torch.agents.core.off_policy)

OffPolicyMARLAgents (class in xuance.mindspore.agents.core.off_policy_marl) (class in xuance.tensorflow.agents.core.off_policy_marl) (class in xuance.torch.agents.core.off_policy_marl) on_test_end() (xuance.common.callback.BaseCallback method) on_test_step() (xuance.common.callback.BaseCallback method) on_train_episode_info() (xuance.common.callback.BaseCallback method) on_train_epochs_end() (xuance.common.callback.BaseCallback method) on_train_step() (xuance.common.callback.BaseCallback method) on_train_step_end() (xuance.common.callback.BaseCallback method) on_update_agent_wise() (xuance.common.callback.MultiAgentBaseCallback method) on_update_end() (xuance.common.callback.BaseCallback method) on_update_start() (xuance.common.callback.BaseCallback method) OnPolicyAgent (class in xuance.mindspore.agents.core.on_policy) (class in xuance.tensorflow.agents.core.on_policy) (class in xuance.torch.agents.core.on_policy) OnPolicyMARLAgents (class in xuance.mindspore.agents.core.on_policy_marl) (class in xuance.tensorflow.agents.core.on_policy_marl) (class in xuance.torch.agents.core.on_policy_marl) output_dim (xuance.mindspore.utils.layers4dreamer.CNN property) (xuance.mindspore.utils.layers4dreamer.DeCNN property) (xuance.mindspore.utils.layers4dreamer.MLP property) (xuance.mindspore.utils.layers4dreamer.NatureCNN property) (xuance.tensorflow.utils.layers4dreamer.CNN property) (xuance.tensorflow.utils.layers4dreamer.DeCNN property) (xuance.tensorflow.utils.layers4dreamer.MLP property) (xuance.tensorflow.utils.layers4dreamer.NatureCNN property) (xuance.torch.utils.layers4dreamer.CNN property) (xuance.torch.utils.layers4dreamer.DeCNN property) (xuance.torch.utils.layers4dreamer.MLP property) (xuance.torch.utils.layers4dreamer.NatureCNN property)

P

pad_action() (xuance.mindspore.agents.policy_gradient.pdqn_agent.PDQN_Agent method) (xuance.tensorflow.agents.policy_gradient.pdqn_agent.PDQN_Agent method) (xuance.torch.agents.policy_gradient.pdqn_agent.PDQN_Agent method) pad_observation() (xuance.mindspore.agents.multi_agent_rl.commnet_agents.CommNet_Agents static method) (xuance.tensorflow.agents.multi_agent_rl.commnet_agents.CommNet_Agents static method) (xuance.torch.agents.multi_agent_rl.commnet_agents.CommNet_Agents static method) pair() (in module xuance.mindspore.representations.vit) (in module xuance.tensorflow.representations.vit) (in module xuance.torch.representations.vit) parameters_actor (xuance.mindspore.policies.categorical_marl.COMA_Policy property) (xuance.mindspore.policies.deterministic_marl.Independent_DDPG_Policy property) (xuance.mindspore.policies.gaussian_marl.Basic_ISAC_Policy property) (xuance.tensorflow.policies.categorical_marl.COMA_Policy property) (xuance.torch.policies.categorical_marl.Basic_ISAC_Policy property) (xuance.torch.policies.categorical_marl.COMA_Policy property) (xuance.torch.policies.deterministic_marl.Independent_DDPG_Policy property) (xuance.torch.policies.gaussian_marl.Basic_ISAC_Policy property) parameters_critic (xuance.mindspore.policies.categorical_marl.COMA_Policy property) (xuance.mindspore.policies.deterministic_marl.Independent_DDPG_Policy property) (xuance.mindspore.policies.deterministic_marl.MATD3_Policy property) (xuance.mindspore.policies.gaussian_marl.Basic_ISAC_Policy property) (xuance.tensorflow.policies.categorical_marl.COMA_Policy property) (xuance.torch.policies.categorical_marl.Basic_ISAC_Policy property) (xuance.torch.policies.categorical_marl.COMA_Policy property) (xuance.torch.policies.deterministic_marl.Independent_DDPG_Policy property) (xuance.torch.policies.deterministic_marl.Independent_TD3_Policy property) (xuance.torch.policies.deterministic_marl.MATD3_Policy property) (xuance.torch.policies.gaussian_marl.Basic_ISAC_Policy property) parameters_model (xuance.mindspore.policies.categorical_marl.CommNet_Policy property) (xuance.mindspore.policies.categorical_marl.MAAC_Policy property) (xuance.mindspore.policies.categorical_marl.MeanFieldActorCriticPolicy property) (xuance.mindspore.policies.deterministic_marl.BasicQnetwork property) (xuance.mindspore.policies.deterministic_marl.MFQnetwork property) (xuance.mindspore.policies.deterministic_marl.Qtran_MixingQnetwork property) (xuance.mindspore.policies.gaussian_marl.MAAC_Policy property) (xuance.tensorflow.policies.categorical_marl.CommNet_Policy property) (xuance.tensorflow.policies.deterministic_marl.MixingQnetwork property) (xuance.tensorflow.policies.deterministic_marl.Qtran_MixingQnetwork property) (xuance.torch.policies.categorical_marl.CommNet_Policy property) (xuance.torch.policies.categorical_marl.MAAC_Policy property) (xuance.torch.policies.categorical_marl.MAAC_Policy_Share property) (xuance.torch.policies.categorical_marl.MeanFieldActorCriticPolicy property) (xuance.torch.policies.deterministic_marl.BasicQnetwork property) (xuance.torch.policies.deterministic_marl.DCG_policy property) (xuance.torch.policies.deterministic_marl.MFQnetwork property) (xuance.torch.policies.deterministic_marl.MixingQnetwork property) (xuance.torch.policies.deterministic_marl.Qtran_MixingQnetwork property) (xuance.torch.policies.deterministic_marl.Weighted_MixingQnetwork property) (xuance.torch.policies.gaussian_marl.MAAC_Policy property) parameters_model() (xuance.tensorflow.policies.categorical_marl.MeanFieldActorCriticPolicy method) (xuance.tensorflow.policies.deterministic_marl.BasicQnetwork method) (xuance.tensorflow.policies.deterministic_marl.MFQnetwork method) PDQN_Agent (class in xuance.mindspore.agents.policy_gradient.pdqn_agent) (class in xuance.tensorflow.agents.policy_gradient.pdqn_agent) (class in xuance.torch.agents.policy_gradient.pdqn_agent) PDQN_Learner (class in xuance.mindspore.learners.policy_gradient.pdqn_learner) (class in xuance.tensorflow.learners.policy_gradient.pdqn_learner) (class in xuance.torch.learners.policy_gradient.pdqn_learner)

PDQN_Learner.ConActorNetWithLossCell (class in xuance.mindspore.learners.policy_gradient.pdqn_learner) PDQN_Learner.QNetWithLossCell (class in xuance.mindspore.learners.policy_gradient.pdqn_learner) PDQNPolicy (class in xuance.mindspore.policies.deterministic) (class in xuance.tensorflow.policies.deterministic) (class in xuance.torch.policies.deterministic) per_layer_ortho_init_weights() (in module xuance.mindspore.utils.layers4dreamer) (in module xuance.tensorflow.utils.layers4dreamer) (in module xuance.torch.utils.layers4dreamer) PerDQN_Agent (class in xuance.mindspore.agents.qlearning_family.perdqn_agent) (class in xuance.tensorflow.agents.qlearning_family.perdqn_agent) (class in xuance.torch.agents.qlearning_family.perdqn_agent) PerDQN_Learner (class in xuance.mindspore.learners.qlearning_family.perdqn_learner) (class in xuance.tensorflow.learners.qlearning_family.perdqn_learner) (class in xuance.torch.learners.qlearning_family.perdqn_learner) PerOffPolicyBuffer (class in xuance.common.memory_tools) PG_Agent (class in xuance.mindspore.agents.policy_gradient.pg_agent) (class in xuance.tensorflow.agents.policy_gradient.pg_agent) (class in xuance.torch.agents.policy_gradient.pg_agent) PG_Learner (class in xuance.mindspore.learners.policy_gradient.pg_learner) (class in xuance.tensorflow.learners.policy_gradient.pg_learner) (class in xuance.torch.learners.policy_gradient.pg_learner) PlatformEnv (class in xuance.environment.single_agent_env.platform) PlayerDV2 (class in xuance.mindspore.representations.world_model_v2) (class in xuance.tensorflow.representations.world_model_v2) (class in xuance.torch.representations.world_model_v2) PlayerDV3 (class in xuance.mindspore.representations.world_model) (class in xuance.tensorflow.representations.world_model) (class in xuance.torch.representations.world_model) policy (xuance.torch.agents.base.agent.Agent attribute) policy_forward_fn() (xuance.tensorflow.learners.policy_gradient.ppg_learner.PPG_Learner method) pooling_block() (in module xuance.mindspore.utils.layers) (in module xuance.tensorflow.utils.layers) (in module xuance.torch.utils.layers) PPG_Agent (class in xuance.mindspore.agents.policy_gradient.ppg_agent) (class in xuance.tensorflow.agents.policy_gradient.ppg_agent) (class in xuance.torch.agents.policy_gradient.ppg_agent) PPG_Learner (class in xuance.mindspore.learners.policy_gradient.ppg_learner) (class in xuance.tensorflow.learners.policy_gradient.ppg_learner) (class in xuance.torch.learners.policy_gradient.ppg_learner) PPGActorCritic (class in xuance.mindspore.policies.categorical) (class in xuance.mindspore.policies.gaussian) (class in xuance.tensorflow.policies.categorical) (class in xuance.tensorflow.policies.gaussian) (class in xuance.torch.policies.categorical) (class in xuance.torch.policies.gaussian) PPO_Agent (class in xuance.mindspore.agents.policy_gradient.ppo_agent) (class in xuance.tensorflow.agents.policy_gradient.ppo_agent) (class in xuance.torch.agents.policy_gradient.ppo_agent) PPO_Learner (class in xuance.mindspore.learners.policy_gradient.ppo_learner) (class in xuance.tensorflow.learners.policy_gradient.ppo_learner) (class in xuance.torch.learners.policy_gradient.ppo_learner) PPOKL_Agent (class in xuance.mindspore.agents.policy_gradient.ppokl_agent) (class in xuance.tensorflow.agents.policy_gradient.ppokl_agent) (class in xuance.torch.agents.policy_gradient.ppokl_agent) PPOKL_Learner (class in xuance.mindspore.learners.policy_gradient.ppokl_learner) (class in xuance.tensorflow.learners.policy_gradient.ppokl_learner) (class in xuance.torch.learners.policy_gradient.ppokl_learner) put() (xuance.common.memory_tools.EpisodeBuffer method)

Q

q_centralized() (xuance.mindspore.policies.deterministic_marl.Weighted_MixingQnetwork method) (xuance.tensorflow.policies.deterministic_marl.Weighted_MixingQnetwork method) (xuance.torch.policies.deterministic_marl.Weighted_MixingQnetwork method) q_dcg() (xuance.mindspore.learners.multi_agent_rl.dcg_learner.DCG_Learner method) (xuance.tensorflow.learners.multi_agent_rl.dcg_learner.DCG_Learner method) (xuance.torch.learners.multi_agent_rl.dcg_learner.DCG_Learner method) q_feedforward() (xuance.mindspore.policies.deterministic_marl.Weighted_MixingQnetwork method) (xuance.tensorflow.policies.deterministic_marl.Weighted_MixingQnetwork method) (xuance.torch.policies.deterministic_marl.Weighted_MixingQnetwork method) Q_tot() (xuance.mindspore.policies.deterministic_marl.MixingQnetwork method) (xuance.mindspore.policies.deterministic_marl.Qtran_MixingQnetwork method) (xuance.tensorflow.policies.deterministic_marl.MixingQnetwork method) (xuance.tensorflow.policies.deterministic_marl.Qtran_MixingQnetwork method) (xuance.torch.policies.deterministic_marl.MixingQnetwork method) (xuance.torch.policies.deterministic_marl.Qtran_MixingQnetwork method) Q_tran() (xuance.mindspore.policies.deterministic_marl.Qtran_MixingQnetwork method) (xuance.tensorflow.policies.deterministic_marl.Qtran_MixingQnetwork method) (xuance.torch.policies.deterministic_marl.Qtran_MixingQnetwork method) Q_tran_target() (xuance.mindspore.policies.deterministic_marl.Qtran_MixingQnetwork method) (xuance.tensorflow.policies.deterministic_marl.Qtran_MixingQnetwork method) (xuance.torch.policies.deterministic_marl.Qtran_MixingQnetwork method) Qaction() (xuance.mindspore.policies.categorical.SACDISPolicy method) (xuance.mindspore.policies.deterministic.DDPGPolicy method) (xuance.mindspore.policies.deterministic.TD3Policy method) (xuance.mindspore.policies.gaussian.SACPolicy method) (xuance.tensorflow.policies.categorical.SACDISPolicy method) (xuance.tensorflow.policies.deterministic.DDPGPolicy method) (xuance.tensorflow.policies.deterministic.TD3Policy method) (xuance.torch.policies.categorical.SACDISPolicy method) (xuance.torch.policies.categorical_marl.Basic_ISAC_Policy method) (xuance.torch.policies.categorical_marl.MASAC_Policy method) (xuance.torch.policies.deterministic.DDPGPolicy method) (xuance.torch.policies.deterministic.TD3Policy method) (xuance.torch.policies.gaussian.SACPolicy method) Qeval() (xuance.mindspore.policies.deterministic.MPDQNPolicy method) (xuance.mindspore.policies.deterministic.PDQNPolicy method) (xuance.mindspore.policies.deterministic.SPDQNPolicy method) (xuance.tensorflow.policies.deterministic.MPDQNPolicy method) (xuance.tensorflow.policies.deterministic.PDQNPolicy method) (xuance.tensorflow.policies.deterministic.SPDQNPolicy method) (xuance.torch.policies.deterministic.MPDQNPolicy method) (xuance.torch.policies.deterministic.PDQNPolicy method) (xuance.torch.policies.deterministic.SPDQNPolicy method) QMIX_Agents (class in xuance.mindspore.agents.multi_agent_rl.qmix_agents) (class in xuance.tensorflow.agents.multi_agent_rl.qmix_agents) (class in xuance.torch.agents.multi_agent_rl.qmix_agents) QMIX_FF_mixer (class in xuance.mindspore.policies.core) (class in xuance.tensorflow.policies.core) (class in xuance.torch.policies.core) QMIX_Learner (class in xuance.mindspore.learners.multi_agent_rl.qmix_learner) (class in xuance.tensorflow.learners.multi_agent_rl.qmix_learner) (class in xuance.torch.learners.multi_agent_rl.qmix_learner) QMIX_mixer (class in xuance.mindspore.policies.core) (class in xuance.tensorflow.policies.core) (class in xuance.torch.policies.core) Qpolicy() (xuance.mindspore.policies.categorical.SACDISPolicy method) (xuance.mindspore.policies.deterministic.DDPGPolicy method) (xuance.mindspore.policies.deterministic.MPDQNPolicy method) (xuance.mindspore.policies.deterministic.PDQNPolicy method) (xuance.mindspore.policies.deterministic.SPDQNPolicy method) (xuance.mindspore.policies.deterministic.TD3Policy method) (xuance.mindspore.policies.deterministic_marl.Independent_DDPG_Policy method) (xuance.mindspore.policies.deterministic_marl.MADDPG_Policy method) (xuance.mindspore.policies.deterministic_marl.MATD3_Policy method) (xuance.mindspore.policies.gaussian.SACPolicy method) (xuance.mindspore.policies.gaussian_marl.Basic_ISAC_Policy method) (xuance.mindspore.policies.gaussian_marl.MASAC_Policy method) (xuance.tensorflow.policies.categorical.SACDISPolicy method) (xuance.tensorflow.policies.deterministic.DDPGPolicy method) (xuance.tensorflow.policies.deterministic.MPDQNPolicy method) (xuance.tensorflow.policies.deterministic.PDQNPolicy method) (xuance.tensorflow.policies.deterministic.SPDQNPolicy method) (xuance.tensorflow.policies.deterministic.TD3Policy method) (xuance.tensorflow.policies.deterministic_marl.Independent_DDPG_Policy method) (xuance.tensorflow.policies.deterministic_marl.MADDPG_Policy method) (xuance.tensorflow.policies.deterministic_marl.MATD3_Policy method) (xuance.tensorflow.policies.gaussian.SACPolicy method) (xuance.tensorflow.policies.gaussian_marl.Basic_ISAC_Policy method) (xuance.tensorflow.policies.gaussian_marl.MASAC_Policy method) (xuance.torch.policies.categorical.SACDISPolicy method) (xuance.torch.policies.categorical_marl.Basic_ISAC_Policy method) (xuance.torch.policies.categorical_marl.MASAC_Policy method) (xuance.torch.policies.deterministic.DDPGPolicy method) (xuance.torch.policies.deterministic.MPDQNPolicy method) (xuance.torch.policies.deterministic.PDQNPolicy method) (xuance.torch.policies.deterministic.SPDQNPolicy method) (xuance.torch.policies.deterministic.TD3Policy method) (xuance.torch.policies.deterministic_marl.Independent_DDPG_Policy method) (xuance.torch.policies.deterministic_marl.Independent_TD3_Policy method) (xuance.torch.policies.deterministic_marl.MADDPG_Policy method) (xuance.torch.policies.deterministic_marl.MATD3_Policy method) (xuance.torch.policies.gaussian.SACPolicy method) (xuance.torch.policies.gaussian_marl.Basic_ISAC_Policy method) (xuance.torch.policies.gaussian_marl.MASAC_Policy method)

QRDQN_Agent (class in xuance.mindspore.agents.qlearning_family.qrdqn_agent) (class in xuance.tensorflow.agents.qlearning_family.qrdqn_agent) (class in xuance.torch.agents.qlearning_family.qrdqn_agent) QRDQN_Learner (class in xuance.mindspore.learners.qlearning_family.qrdqn_learner) (class in xuance.tensorflow.learners.qlearning_family.qrdqn_learner) (class in xuance.torch.learners.qlearning_family.qrdqn_learner) QRDQN_Network (class in xuance.mindspore.policies.deterministic) (class in xuance.tensorflow.policies.deterministic) (class in xuance.torch.policies.deterministic) QRDQNhead (class in xuance.mindspore.policies.core) (class in xuance.tensorflow.policies.core) (class in xuance.torch.policies.core) Qtarget() (xuance.mindspore.policies.categorical.SACDISPolicy method) (xuance.mindspore.policies.deterministic.DDPGPolicy method) (xuance.mindspore.policies.deterministic.MPDQNPolicy method) (xuance.mindspore.policies.deterministic.PDQNPolicy method) (xuance.mindspore.policies.deterministic.SPDQNPolicy method) (xuance.mindspore.policies.deterministic.TD3Policy method) (xuance.mindspore.policies.deterministic_marl.BasicQnetwork method) (xuance.mindspore.policies.deterministic_marl.Independent_DDPG_Policy method) (xuance.mindspore.policies.deterministic_marl.MADDPG_Policy method) (xuance.mindspore.policies.deterministic_marl.MATD3_Policy method) (xuance.mindspore.policies.deterministic_marl.MFQnetwork method) (xuance.mindspore.policies.deterministic_marl.Qtran_MixingQnetwork method) (xuance.mindspore.policies.gaussian.SACPolicy method) (xuance.mindspore.policies.gaussian_marl.Basic_ISAC_Policy method) (xuance.mindspore.policies.gaussian_marl.MASAC_Policy method) (xuance.tensorflow.policies.categorical.SACDISPolicy method) (xuance.tensorflow.policies.deterministic.DDPGPolicy method) (xuance.tensorflow.policies.deterministic.MPDQNPolicy method) (xuance.tensorflow.policies.deterministic.PDQNPolicy method) (xuance.tensorflow.policies.deterministic.SPDQNPolicy method) (xuance.tensorflow.policies.deterministic.TD3Policy method) (xuance.tensorflow.policies.deterministic_marl.BasicQnetwork method) (xuance.tensorflow.policies.deterministic_marl.Independent_DDPG_Policy method) (xuance.tensorflow.policies.deterministic_marl.MADDPG_Policy method) (xuance.tensorflow.policies.deterministic_marl.MATD3_Policy method) (xuance.tensorflow.policies.deterministic_marl.MFQnetwork method) (xuance.tensorflow.policies.deterministic_marl.Qtran_MixingQnetwork method) (xuance.tensorflow.policies.gaussian.SACPolicy method) (xuance.tensorflow.policies.gaussian_marl.Basic_ISAC_Policy method) (xuance.tensorflow.policies.gaussian_marl.MASAC_Policy method) (xuance.torch.policies.categorical.SACDISPolicy method) (xuance.torch.policies.categorical_marl.Basic_ISAC_Policy method) (xuance.torch.policies.categorical_marl.MASAC_Policy method) (xuance.torch.policies.deterministic.DDPGPolicy method) (xuance.torch.policies.deterministic.MPDQNPolicy method) (xuance.torch.policies.deterministic.PDQNPolicy method) (xuance.torch.policies.deterministic.SPDQNPolicy method) (xuance.torch.policies.deterministic.TD3Policy method) (xuance.torch.policies.deterministic_marl.BasicQnetwork method) (xuance.torch.policies.deterministic_marl.Independent_DDPG_Policy method) (xuance.torch.policies.deterministic_marl.Independent_TD3_Policy method) (xuance.torch.policies.deterministic_marl.MADDPG_Policy method) (xuance.torch.policies.deterministic_marl.MATD3_Policy method) (xuance.torch.policies.deterministic_marl.MFQnetwork method) (xuance.torch.policies.deterministic_marl.Qtran_MixingQnetwork method) (xuance.torch.policies.gaussian.SACPolicy method) (xuance.torch.policies.gaussian_marl.Basic_ISAC_Policy method) (xuance.torch.policies.gaussian_marl.MASAC_Policy method) Qtarget_tot() (xuance.mindspore.policies.deterministic_marl.MixingQnetwork method) (xuance.tensorflow.policies.deterministic_marl.MixingQnetwork method) (xuance.torch.policies.deterministic_marl.MixingQnetwork method) QTRAN_Agents (class in xuance.mindspore.agents.multi_agent_rl.qtran_agents) (class in xuance.tensorflow.agents.multi_agent_rl.qtran_agents) (class in xuance.torch.agents.multi_agent_rl.qtran_agents) QTRAN_alt (class in xuance.mindspore.policies.core) (class in xuance.tensorflow.policies.core) (class in xuance.torch.policies.core) QTRAN_base (class in xuance.mindspore.policies.core) (class in xuance.tensorflow.policies.core) (class in xuance.torch.policies.core) QTRAN_Learner (class in xuance.mindspore.learners.multi_agent_rl.qtran_learner) (class in xuance.tensorflow.learners.multi_agent_rl.qtran_learner) (class in xuance.torch.learners.multi_agent_rl.qtran_learner) Qtran_MixingQnetwork (class in xuance.mindspore.policies.deterministic_marl) (class in xuance.tensorflow.policies.deterministic_marl) (class in xuance.torch.policies.deterministic_marl)

R

RandomAgents (class in xuance.mindspore.agents.base.agents_marl) (class in xuance.tensorflow.agents.base.agents_marl) (class in xuance.torch.agents.base.agents_marl) RawEnvironment (class in xuance.environment.utils.base) RawMultiAgentEnv (class in xuance.environment.utils.base) RecurrentModel (class in xuance.mindspore.representations.world_model) (class in xuance.mindspore.representations.world_model_v2) (class in xuance.tensorflow.representations.world_model) (class in xuance.tensorflow.representations.world_model_v2) (class in xuance.torch.representations.world_model) (class in xuance.torch.representations.world_model_v2) RecurrentOffPolicyBuffer (class in xuance.common.memory_tools) recursive_dict_update() (in module xuance.common.common_tools) reduce() (xuance.common.segtree_tool.SegmentTree method), [1] register_algorithm() (xuance.common.tuning_tools.AlgorithmHyperparametersRegistry class method) render() (xuance.environment.multi_agent_env.drones.Drones_MultiAgentEnv method) (xuance.environment.multi_agent_env.football.GFootball_Env method) (xuance.environment.multi_agent_env.mpe.MPE_Env method) (xuance.environment.multi_agent_env.robotic_warehouse.RoboticWarehouseEnv method) (xuance.environment.multi_agent_env.starcraft2.StarCraft2_Env method) (xuance.environment.single_agent_env.gym.Gym_Env method) (xuance.environment.single_agent_env.metadrive.MetaDrive_Env method) (xuance.environment.single_agent_env.minigrid.MiniGridEnv method) (xuance.environment.single_agent_env.platform.PlatformEnv method) (xuance.environment.utils.base.RawEnvironment method) (xuance.environment.utils.base.RawMultiAgentEnv method) (xuance.environment.utils.wrapper.XuanCeEnvWrapper method) (xuance.environment.vector_envs.dummy.dummy_vec_env.DummyVecEnv method) (xuance.environment.vector_envs.dummy.dummy_vec_maenv.DummyVecMultiAgentEnv method) (xuance.environment.vector_envs.subprocess.subproc_vec_env.SubprocVecEnv method) (xuance.environment.vector_envs.subprocess.subproc_vec_maenv.SubprocVecMultiAgentEnv method) (xuance.environment.vector_envs.vector_env.VecEnv method) render_mode (xuance.environment.utils.wrapper.XuanCeEnvWrapper property) reset() (xuance.environment.multi_agent_env.drones.Drones_MultiAgentEnv method) (xuance.environment.multi_agent_env.football.football_raw_env method) (xuance.environment.multi_agent_env.football.GFootball_Env method) (xuance.environment.multi_agent_env.mpe.MPE_Env method) (xuance.environment.multi_agent_env.robotic_warehouse.RoboticWarehouseEnv method) (xuance.environment.multi_agent_env.starcraft2.StarCraft2_Env method) (xuance.environment.single_agent_env.gym.Gym_Env method) (xuance.environment.single_agent_env.gym.MountainCar method) (xuance.environment.single_agent_env.metadrive.MetaDrive_Env method) (xuance.environment.single_agent_env.minigrid.MiniGridEnv method) (xuance.environment.single_agent_env.platform.PlatformEnv method) (xuance.environment.utils.base.RawEnvironment method) (xuance.environment.utils.base.RawMultiAgentEnv method) (xuance.environment.utils.wrapper.XuanCeAtariEnvWrapper method) (xuance.environment.utils.wrapper.XuanCeEnvWrapper method) (xuance.environment.utils.wrapper.XuanCeMultiAgentEnvWrapper method) (xuance.environment.vector_envs.dummy.dummy_vec_env.DummyVecEnv method) (xuance.environment.vector_envs.dummy.dummy_vec_maenv.DummyVecMultiAgentEnv method) (xuance.environment.vector_envs.subprocess.subproc_vec_env.SubprocVecEnv method) (xuance.environment.vector_envs.subprocess.subproc_vec_maenv.SubprocVecMultiAgentEnv method) (xuance.environment.vector_envs.vector_env.VecEnv method)

reset_parameters() (xuance.mindspore.utils.value_norm.ValueNorm method) (xuance.tensorflow.utils.value_norm.ValueNorm method) (xuance.torch.communications.gnn_comm.GraphMultiHeadAttentionLayer method) (xuance.torch.utils.value_norm.ValueNorm method) return_range() (in module xuance.common.offline_util) RoboticWarehouseEnv (class in xuance.environment.multi_agent_env.robotic_warehouse) rprint() (xuance.engine.run_basic.RunnerBase method) (xuance.engine.run_competition.RunnerCompetition method) rsample() (xuance.torch.utils.distributions.DiagGaussianDistribution method) (xuance.torch.utils.distributions.TruncatedStandardNormal method) RSSM (class in xuance.mindspore.representations.world_model) (class in xuance.mindspore.representations.world_model_v2) (class in xuance.tensorflow.representations.world_model) (class in xuance.tensorflow.representations.world_model_v2) (class in xuance.torch.representations.world_model) (class in xuance.torch.representations.world_model_v2) run() (xuance.engine.run_basic.RunnerBase method) (xuance.engine.run_competition.RunnerCompetition method) (xuance.engine.run_football.RunnerFootball method) (xuance.engine.run_offlinerl.RunnerOfflineRL method) run_episodes() (xuance.engine.run_competition.RunnerCompetition method) (xuance.mindspore.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.mindspore.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.mindspore.agents.multi_agent_rl.coma_agents.COMA_Agents method) (xuance.mindspore.agents.multi_agent_rl.commnet_agents.CommNet_Agents method) (xuance.mindspore.agents.multi_agent_rl.ic3net_agents.IC3Net_Agents method) (xuance.mindspore.agents.multi_agent_rl.mfac_agents.MFAC_Agents method) (xuance.mindspore.agents.multi_agent_rl.mfq_agents.MFQ_Agents method) (xuance.tensorflow.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.tensorflow.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.tensorflow.agents.multi_agent_rl.coma_agents.COMA_Agents method) (xuance.tensorflow.agents.multi_agent_rl.commnet_agents.CommNet_Agents method) (xuance.tensorflow.agents.multi_agent_rl.ic3net_agents.IC3Net_Agents method) (xuance.tensorflow.agents.multi_agent_rl.mfac_agents.MFAC_Agents method) (xuance.tensorflow.agents.multi_agent_rl.mfq_agents.MFQ_Agents method) (xuance.torch.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.torch.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.torch.agents.multi_agent_rl.coma_agents.COMA_Agents method) (xuance.torch.agents.multi_agent_rl.commnet_agents.CommNet_Agents method) (xuance.torch.agents.multi_agent_rl.ic3net_agents.IC3Net_Agents method) (xuance.torch.agents.multi_agent_rl.mfac_agents.MFAC_Agents method) (xuance.torch.agents.multi_agent_rl.mfq_agents.MFQ_Agents method) RunnerBase (class in xuance.engine.run_basic) RunnerCompetition (class in xuance.engine.run_competition) RunnerDRL (class in xuance.engine.run_drl) RunnerFootball (class in xuance.engine.run_football) RunnerMARL (class in xuance.engine.run_marl) RunnerOfflineRL (class in xuance.engine.run_offlinerl) RunnerSC2 (class in xuance.engine.run_sc2) running_mean_var() (xuance.mindspore.utils.value_norm.ValueNorm method) (xuance.tensorflow.utils.value_norm.ValueNorm method) (xuance.torch.utils.value_norm.ValueNorm method) running_steps (xuance.common.tuning_tools.HyperParameterTuner attribute) RunningMeanStd (class in xuance.common.statistic_tools)

S

SAC_Agent (class in xuance.mindspore.agents.policy_gradient.sac_agent) (class in xuance.tensorflow.agents.policy_gradient.sac_agent) (class in xuance.torch.agents.policy_gradient.sac_agent) SAC_Learner (class in xuance.mindspore.learners.policy_gradient.sac_learner) (class in xuance.tensorflow.learners.policy_gradient.sac_learner) (class in xuance.torch.learners.policy_gradient.sac_learner) SACDIS_Learner (class in xuance.mindspore.learners.policy_gradient.sacdis_learner) (class in xuance.tensorflow.learners.policy_gradient.sacdis_learner) (class in xuance.torch.learners.policy_gradient.sacdis_learner) SACDISPolicy (class in xuance.mindspore.policies.categorical) (class in xuance.tensorflow.policies.categorical) (class in xuance.torch.policies.categorical) SACPolicy (class in xuance.mindspore.policies.gaussian) (class in xuance.tensorflow.policies.gaussian) (class in xuance.torch.policies.gaussian) sample() (xuance.common.memory_offline.OfflineBuffer_D4RL method) (xuance.common.memory_tools.Buffer method) (xuance.common.memory_tools.DummyOffPolicyBuffer method) (xuance.common.memory_tools.DummyOnPolicyBuffer method) (xuance.common.memory_tools.EpisodeBuffer method) (xuance.common.memory_tools.PerOffPolicyBuffer method) (xuance.common.memory_tools.RecurrentOffPolicyBuffer method) (xuance.common.memory_tools.SequentialReplayBuffer method) (xuance.common.memory_tools_marl.BaseBuffer method) (xuance.common.memory_tools_marl.MARL_OffPolicyBuffer method) (xuance.common.memory_tools_marl.MARL_OffPolicyBuffer_RNN method) (xuance.common.memory_tools_marl.MARL_OnPolicyBuffer method) (xuance.common.memory_tools_marl.MARL_OnPolicyBuffer_RNN method) sample_batch() (in module xuance.common.memory_tools) save_model() (xuance.mindspore.agents.base.agent.Agent method) (xuance.mindspore.agents.base.agents_marl.MARLAgents method) (xuance.mindspore.learners.learner.Learner method) (xuance.mindspore.learners.learner.LearnerMAS method) (xuance.tensorflow.agents.base.agent.Agent method) (xuance.tensorflow.agents.base.agents_marl.MARLAgents method) (xuance.tensorflow.learners.learner.Learner method) (xuance.tensorflow.learners.learner.LearnerMAS method) (xuance.torch.agents.base.agent.Agent method) (xuance.torch.agents.base.agents_marl.MARLAgents method) (xuance.torch.learners.learner.Learner method) (xuance.torch.learners.learner.LearnerMAS method) save_snapshot() (xuance.torch.learners.learner.Learner method) SegmentTree (class in xuance.common.segtree_tool) select_hyperparameter() (xuance.common.tuning_tools.HyperParameterTuner method) SequentialReplayBuffer (class in xuance.common.memory_tools) set_coordination_graph() (xuance.mindspore.policies.coordination_graph.Coordination_Graph method) (xuance.tensorflow.policies.coordination_graph.Coordination_Graph method) (xuance.torch.policies.coordination_graph.Coordination_Graph method) set_device() (in module xuance.mindspore.utils.device) (in module xuance.tensorflow.utils.device) (in module xuance.torch.utils.device) set_hyperparameters() (in module xuance.common.tuning_tools) set_param() (xuance.mindspore.utils.distributions.CategoricalDistribution method) (xuance.mindspore.utils.distributions.DiagGaussianDistribution method) (xuance.mindspore.utils.distributions.Distribution method) (xuance.tensorflow.utils.distributions.CategoricalDistribution method) (xuance.tensorflow.utils.distributions.DiagGaussianDistribution method) (xuance.tensorflow.utils.distributions.Distribution method) (xuance.torch.utils.distributions.CategoricalDistribution method) (xuance.torch.utils.distributions.DiagGaussianDistribution method) (xuance.torch.utils.distributions.Distribution method) set_seed() (in module xuance.mindspore.utils.operations) (in module xuance.tensorflow.utils.operations) (in module xuance.torch.utils.operations) shape (xuance.common.statistic_tools.RunningMeanStd attribute) soft_update() (xuance.mindspore.policies.categorical.SACDISPolicy method) (xuance.mindspore.policies.deterministic.DDPGPolicy method) (xuance.mindspore.policies.deterministic.MPDQNPolicy method) (xuance.mindspore.policies.deterministic.PDQNPolicy method) (xuance.mindspore.policies.deterministic.SPDQNPolicy method) (xuance.mindspore.policies.deterministic.TD3Policy method) (xuance.mindspore.policies.deterministic_marl.Independent_DDPG_Policy method) (xuance.mindspore.policies.deterministic_marl.MATD3_Policy method) (xuance.mindspore.policies.dreamer.DreamerV3Policy method) (xuance.mindspore.policies.gaussian.SACPolicy method) (xuance.mindspore.policies.gaussian_marl.Basic_ISAC_Policy method) (xuance.tensorflow.policies.categorical.SACDISPolicy method) (xuance.tensorflow.policies.deterministic.DDPGPolicy method) (xuance.tensorflow.policies.deterministic.MPDQNPolicy method) (xuance.tensorflow.policies.deterministic.PDQNPolicy method) (xuance.tensorflow.policies.deterministic.SPDQNPolicy method) (xuance.tensorflow.policies.deterministic.TD3Policy method) (xuance.tensorflow.policies.deterministic_marl.Independent_DDPG_Policy method) (xuance.tensorflow.policies.deterministic_marl.MATD3_Policy method) (xuance.tensorflow.policies.dreamer.DreamerV3Policy method) (xuance.tensorflow.policies.gaussian.SACPolicy method) (xuance.tensorflow.policies.gaussian_marl.Basic_ISAC_Policy method) (xuance.torch.policies.categorical.SACDISPolicy method) (xuance.torch.policies.categorical_marl.Basic_ISAC_Policy method) (xuance.torch.policies.deterministic.DDPGPolicy method) (xuance.torch.policies.deterministic.PDQNPolicy method) (xuance.torch.policies.deterministic.TD3Policy method) (xuance.torch.policies.deterministic_marl.Independent_DDPG_Policy method) (xuance.torch.policies.deterministic_marl.Independent_TD3_Policy method) (xuance.torch.policies.deterministic_marl.MATD3_Policy method) (xuance.torch.policies.dreamer.DreamerV3Policy method) (xuance.torch.policies.gaussian.SACPolicy method) (xuance.torch.policies.gaussian_marl.Basic_ISAC_Policy method) space_reshape() (xuance.environment.multi_agent_env.drones.Drones_MultiAgentEnv method) SPDQN_Agent (class in xuance.mindspore.agents.policy_gradient.spdqn_agent) (class in xuance.tensorflow.agents.policy_gradient.spdqn_agent) (class in xuance.torch.agents.policy_gradient.spdqn_agent) SPDQN_Learner (class in xuance.mindspore.learners.policy_gradient.spdqn_learner) (class in xuance.tensorflow.learners.policy_gradient.spdqn_learner) (class in xuance.torch.learners.policy_gradient.spdqn_learner) SPDQN_Learner.ConActorNetWithLossCell (class in xuance.mindspore.learners.policy_gradient.spdqn_learner) SPDQN_Learner.QNetWithLossCell (class in xuance.mindspore.learners.policy_gradient.spdqn_learner) SPDQNPolicy (class in xuance.mindspore.policies.deterministic) (class in xuance.tensorflow.policies.deterministic) (class in xuance.torch.policies.deterministic) split_distributions() (in module xuance.mindspore.utils.distributions) (in module xuance.tensorflow.utils.distributions) (in module xuance.torch.utils.distributions)

SPR_Agent (class in xuance.mindspore.agents.contrastive_unsupervised_rl.spr_agent), [1] (class in xuance.tensorflow.agents.contrastive_unsupervised_rl.spr_agent), [1] (class in xuance.torch.agents.contrastive_unsupervised_rl.spr_agent), [1] SPR_Learner (class in xuance.mindspore.learners.contrastive_unsupervised_rl.spr_learner) (class in xuance.tensorflow.learners.contrastive_unsupervised_rl.spr_learner) (class in xuance.torch.learners.contrastive_unsupervised_rl.spr_learner) SPR_Policy (class in xuance.mindspore.agents.contrastive_unsupervised_rl.spr_agent), [1] (class in xuance.tensorflow.agents.contrastive_unsupervised_rl.spr_agent), [1] (class in xuance.torch.agents.contrastive_unsupervised_rl.spr_agent), [1] StarCraft2_Env (class in xuance.environment.multi_agent_env.starcraft2) state (xuance.environment.utils.wrapper.XuanCeMultiAgentEnvWrapper property) state() (xuance.environment.multi_agent_env.drones.Drones_MultiAgentEnv method) (xuance.environment.multi_agent_env.football.football_raw_env method) (xuance.environment.multi_agent_env.football.GFootball_Env method) (xuance.environment.multi_agent_env.mpe.MPE_Env method) (xuance.environment.multi_agent_env.robotic_warehouse.RoboticWarehouseEnv method) (xuance.environment.multi_agent_env.starcraft2.StarCraft2_Env method) (xuance.environment.utils.base.RawMultiAgentEnv method) state_space (xuance.environment.utils.wrapper.XuanCeMultiAgentEnvWrapper property) std (xuance.common.statistic_tools.RunningMeanStd property) step() (xuance.environment.multi_agent_env.drones.Drones_MultiAgentEnv method) (xuance.environment.multi_agent_env.football.football_raw_env method) (xuance.environment.multi_agent_env.football.GFootball_Env method) (xuance.environment.multi_agent_env.mpe.MPE_Env method) (xuance.environment.multi_agent_env.robotic_warehouse.RoboticWarehouseEnv method) (xuance.environment.multi_agent_env.starcraft2.StarCraft2_Env method) (xuance.environment.single_agent_env.gym.Gym_Env method) (xuance.environment.single_agent_env.gym.MountainCar method) (xuance.environment.single_agent_env.metadrive.MetaDrive_Env method) (xuance.environment.single_agent_env.minigrid.MiniGridEnv method) (xuance.environment.single_agent_env.platform.PlatformEnv method) (xuance.environment.utils.base.RawEnvironment method) (xuance.environment.utils.base.RawMultiAgentEnv method) (xuance.environment.utils.wrapper.XuanCeAtariEnvWrapper method) (xuance.environment.utils.wrapper.XuanCeEnvWrapper method) (xuance.environment.utils.wrapper.XuanCeMultiAgentEnvWrapper method) (xuance.environment.vector_envs.vector_env.VecEnv method) step_async() (xuance.environment.vector_envs.dummy.dummy_vec_env.DummyVecEnv method) (xuance.environment.vector_envs.dummy.dummy_vec_maenv.DummyVecMultiAgentEnv method) (xuance.environment.vector_envs.subprocess.subproc_vec_env.SubprocVecEnv method) (xuance.environment.vector_envs.subprocess.subproc_vec_maenv.SubprocVecMultiAgentEnv method) (xuance.environment.vector_envs.vector_env.VecEnv method) step_wait() (xuance.environment.vector_envs.dummy.dummy_vec_env.DummyVecEnv method) (xuance.environment.vector_envs.dummy.dummy_vec_maenv.DummyVecEnv_Football method) (xuance.environment.vector_envs.dummy.dummy_vec_maenv.DummyVecEnv_StarCraft2 method) (xuance.environment.vector_envs.dummy.dummy_vec_maenv.DummyVecMultiAgentEnv method) (xuance.environment.vector_envs.subprocess.subproc_vec_env.SubprocVecEnv method) (xuance.environment.vector_envs.subprocess.subproc_vec_maenv.SubprocVecEnv_Football method) (xuance.environment.vector_envs.subprocess.subproc_vec_maenv.SubprocVecEnv_StarCraft2 method) (xuance.environment.vector_envs.subprocess.subproc_vec_maenv.SubprocVecMultiAgentEnv method) (xuance.environment.vector_envs.vector_env.VecEnv method) stochastic_sample() (xuance.mindspore.utils.distributions.CategoricalDistribution method) (xuance.mindspore.utils.distributions.DiagGaussianDistribution method) (xuance.mindspore.utils.distributions.Distribution method) (xuance.tensorflow.utils.distributions.CategoricalDistribution method) (xuance.tensorflow.utils.distributions.DiagGaussianDistribution method) (xuance.tensorflow.utils.distributions.Distribution method) (xuance.torch.utils.distributions.CategoricalDistribution method) (xuance.torch.utils.distributions.DiagGaussianDistribution method) (xuance.torch.utils.distributions.Distribution method) store() (xuance.common.memory_offline.OfflineBuffer_D4RL method) (xuance.common.memory_tools.Buffer method) (xuance.common.memory_tools.DummyOffPolicyBuffer method) (xuance.common.memory_tools.DummyOnPolicyBuffer method) (xuance.common.memory_tools.PerOffPolicyBuffer method) (xuance.common.memory_tools.RecurrentOffPolicyBuffer method) (xuance.common.memory_tools.SequentialReplayBuffer method) (xuance.common.memory_tools_marl.BaseBuffer method) (xuance.common.memory_tools_marl.MARL_OffPolicyBuffer method) (xuance.common.memory_tools_marl.MARL_OffPolicyBuffer_RNN method) (xuance.common.memory_tools_marl.MARL_OnPolicyBuffer method) (xuance.common.memory_tools_marl.MARL_OnPolicyBuffer_RNN method) store_element() (in module xuance.common.memory_tools) store_episodes() (xuance.common.memory_tools_marl.MARL_OffPolicyBuffer_RNN method) (xuance.common.memory_tools_marl.MARL_OnPolicyBuffer_RNN method) store_experience() (xuance.mindspore.agents.base.agents_marl.MARLAgents method) (xuance.mindspore.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.mindspore.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.mindspore.agents.multi_agent_rl.coma_agents.COMA_Agents method) (xuance.mindspore.agents.multi_agent_rl.iac_agents.IAC_Agents method) (xuance.mindspore.agents.multi_agent_rl.ic3net_agents.IC3Net_Agents method) (xuance.mindspore.agents.multi_agent_rl.mfac_agents.MFAC_Agents method) (xuance.mindspore.agents.multi_agent_rl.mfq_agents.MFQ_Agents method) (xuance.mindspore.agents.multi_agent_rl.vdac_agents.VDAC_Agents method) (xuance.tensorflow.agents.base.agents_marl.MARLAgents method) (xuance.tensorflow.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.tensorflow.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.tensorflow.agents.multi_agent_rl.coma_agents.COMA_Agents method) (xuance.tensorflow.agents.multi_agent_rl.iac_agents.IAC_Agents method) (xuance.tensorflow.agents.multi_agent_rl.ic3net_agents.IC3Net_Agents method) (xuance.tensorflow.agents.multi_agent_rl.mfac_agents.MFAC_Agents method) (xuance.tensorflow.agents.multi_agent_rl.mfq_agents.MFQ_Agents method) (xuance.tensorflow.agents.multi_agent_rl.vdac_agents.VDAC_Agents method) (xuance.torch.agents.base.agents_marl.MARLAgents method) (xuance.torch.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.torch.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.torch.agents.multi_agent_rl.coma_agents.COMA_Agents method) (xuance.torch.agents.multi_agent_rl.iac_agents.IAC_Agents method) (xuance.torch.agents.multi_agent_rl.ic3net_agents.IC3Net_Agents method) (xuance.torch.agents.multi_agent_rl.mfac_agents.MFAC_Agents method) (xuance.torch.agents.multi_agent_rl.mfq_agents.MFQ_Agents method) (xuance.torch.agents.multi_agent_rl.vdac_agents.VDAC_Agents method) SubprocVecEnv (class in xuance.environment.vector_envs.subprocess.subproc_vec_env) SubprocVecEnv_Atari (class in xuance.environment.vector_envs.subprocess.subproc_vec_env) SubprocVecEnv_Football (class in xuance.environment.vector_envs.subprocess.subproc_vec_maenv) SubprocVecEnv_StarCraft2 (class in xuance.environment.vector_envs.subprocess.subproc_vec_maenv) SubprocVecMultiAgentEnv (class in xuance.environment.vector_envs.subprocess.subproc_vec_maenv) sum() (xuance.common.segtree_tool.SumSegmentTree method) SumSegmentTree (class in xuance.common.segtree_tool) support() (xuance.torch.utils.distributions.TruncatedStandardNormal method) sym_exp() (in module xuance.torch.utils.operations) sym_log() (in module xuance.torch.utils.operations) SymLogDistribution (class in xuance.torch.utils.distributions)

T

target() (xuance.mindspore.agents.contrastive_unsupervised_rl.curl_agent.CURL_Policy method), [1] (xuance.mindspore.agents.contrastive_unsupervised_rl.spr_agent.SPR_Policy method), [1] (xuance.mindspore.policies.deterministic.BasicQnetwork method) (xuance.mindspore.policies.deterministic.C51Qnetwork method) (xuance.mindspore.policies.deterministic.DRQNPolicy method) (xuance.mindspore.policies.deterministic.DuelQnetwork method) (xuance.mindspore.policies.deterministic.NoisyQnetwork method) (xuance.mindspore.policies.deterministic.QRDQN_Network method) (xuance.tensorflow.agents.contrastive_unsupervised_rl.curl_agent.CURL_Policy method), [1] (xuance.tensorflow.agents.contrastive_unsupervised_rl.spr_agent.SPR_Policy method), [1] (xuance.tensorflow.policies.deterministic.BasicQnetwork method) (xuance.tensorflow.policies.deterministic.C51Qnetwork method) (xuance.tensorflow.policies.deterministic.DRQNPolicy method) (xuance.tensorflow.policies.deterministic.DuelQnetwork method) (xuance.tensorflow.policies.deterministic.NoisyQnetwork method) (xuance.tensorflow.policies.deterministic.QRDQN_Network method) (xuance.torch.agents.contrastive_unsupervised_rl.curl_agent.CURL_Policy method), [1] (xuance.torch.agents.contrastive_unsupervised_rl.spr_agent.SPR_Policy method), [1] (xuance.torch.policies.deterministic.BasicQnetwork method) (xuance.torch.policies.deterministic.C51Qnetwork method) (xuance.torch.policies.deterministic.DRQNPolicy method) (xuance.torch.policies.deterministic.DuelQnetwork method) (xuance.torch.policies.deterministic.NoisyQnetwork method) (xuance.torch.policies.deterministic.QRDQN_Network method) target_q_centralized() (xuance.mindspore.policies.deterministic_marl.Weighted_MixingQnetwork method) (xuance.tensorflow.policies.deterministic_marl.Weighted_MixingQnetwork method) (xuance.torch.policies.deterministic_marl.Weighted_MixingQnetwork method) target_q_feedforward() (xuance.mindspore.policies.deterministic_marl.Weighted_MixingQnetwork method) (xuance.tensorflow.policies.deterministic_marl.Weighted_MixingQnetwork method) (xuance.torch.policies.deterministic_marl.Weighted_MixingQnetwork method) TarMAC (class in xuance.mindspore.communications.attention_comm) (class in xuance.tensorflow.communications.attention_comm) (class in xuance.torch.communications.attention_comm) TarMAC_Agents (class in xuance.mindspore.agents.multi_agent_rl.tarmac_agents) (class in xuance.tensorflow.agents.multi_agent_rl.tarmac_agents) (class in xuance.torch.agents.multi_agent_rl.tarmac_agents) TarMAC_Learner (class in xuance.mindspore.learners.multi_agent_rl.tarmac_learner) (class in xuance.tensorflow.learners.multi_agent_rl.tarmac_learner) (class in xuance.torch.learners.multi_agent_rl.tarmac_learner) TarMAC_Policy (class in xuance.mindspore.policies.categorical_marl) (class in xuance.tensorflow.policies.categorical_marl) (class in xuance.torch.policies.categorical_marl) TD3_Agent (class in xuance.mindspore.agents.policy_gradient.td3_agent) (class in xuance.tensorflow.agents.policy_gradient.td3_agent) (class in xuance.torch.agents.policy_gradient.td3_agent) TD3_BC_Agent (class in xuance.mindspore.agents.offline_rl.td3bc_agent) (class in xuance.tensorflow.agents.offline_rl.td3bc_agent) (class in xuance.torch.agents.offline_rl.td3bc_agent) TD3_BC_Learner (class in xuance.mindspore.learners.offline.td3bc_learner) (class in xuance.tensorflow.learners.offline.td3bc_learner) (class in xuance.torch.learners.offline.td3bc_learner) TD3_Learner (class in xuance.mindspore.learners.policy_gradient.td3_learner) (class in xuance.tensorflow.learners.policy_gradient.td3_learner) (class in xuance.torch.learners.policy_gradient.td3_learner) TD3Policy (class in xuance.mindspore.policies.deterministic) (class in xuance.tensorflow.policies.deterministic) (class in xuance.torch.policies.deterministic) test() (xuance.engine.run_competition.RunnerCompetition method) (xuance.mindspore.agents.base.agent.Agent method) (xuance.mindspore.agents.base.agents_marl.MARLAgents method) (xuance.mindspore.agents.core.off_policy.OffPolicyAgent method) (xuance.mindspore.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.mindspore.agents.core.offline.OfflineAgent method) (xuance.mindspore.agents.core.on_policy.OnPolicyAgent method) (xuance.mindspore.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.mindspore.agents.model_based_rl.dreamer_v2_agent.DreamerV2Agent method) (xuance.mindspore.agents.model_based_rl.dreamer_v3_agent.DreamerV3Agent method) (xuance.mindspore.agents.offline_rl.td3bc_agent.TD3_BC_Agent method) (xuance.mindspore.agents.policy_gradient.pdqn_agent.PDQN_Agent method) (xuance.mindspore.agents.qlearning_family.drqn_agent.DRQN_Agent method) (xuance.mindspore.agents.qlearning_family.noisydqn_agent.NoisyDQN_Agent method) (xuance.tensorflow.agents.base.agent.Agent method) (xuance.tensorflow.agents.base.agents_marl.MARLAgents method) (xuance.tensorflow.agents.core.off_policy.OffPolicyAgent method) (xuance.tensorflow.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.tensorflow.agents.core.offline.OfflineAgent method) (xuance.tensorflow.agents.core.on_policy.OnPolicyAgent method) (xuance.tensorflow.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.tensorflow.agents.model_based_rl.dreamer_v2_agent.DreamerV2Agent method) (xuance.tensorflow.agents.model_based_rl.dreamer_v3_agent.DreamerV3Agent method) (xuance.tensorflow.agents.offline_rl.td3bc_agent.TD3_BC_Agent method) (xuance.tensorflow.agents.policy_gradient.pdqn_agent.PDQN_Agent method) (xuance.tensorflow.agents.qlearning_family.drqn_agent.DRQN_Agent method) (xuance.tensorflow.agents.qlearning_family.noisydqn_agent.NoisyDQN_Agent method) (xuance.torch.agents.base.agent.Agent method) (xuance.torch.agents.base.agents_marl.MARLAgents method) (xuance.torch.agents.core.off_policy.OffPolicyAgent method) (xuance.torch.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.torch.agents.core.offline.OfflineAgent method) (xuance.torch.agents.core.on_policy.OnPolicyAgent method) (xuance.torch.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.torch.agents.model_based_rl.dreamer_v2_agent.DreamerV2Agent method) (xuance.torch.agents.model_based_rl.dreamer_v3_agent.DreamerV3Agent method) (xuance.torch.agents.offline_rl.td3bc_agent.TD3_BC_Agent method) (xuance.torch.agents.policy_gradient.pdqn_agent.PDQN_Agent method) (xuance.torch.agents.qlearning_family.drqn_agent.DRQN_Agent method) (xuance.torch.agents.qlearning_family.noisydqn_agent.NoisyDQN_Agent method) test_episodes (xuance.common.tuning_tools.HyperParameterTuner attribute) test_episodes() (xuance.engine.run_football.RunnerFootball method) (xuance.engine.run_sc2.RunnerSC2 method) tile_images() (in module xuance.environment.vector_envs.env_utils) time_estimate() (xuance.engine.run_sc2.RunnerSC2 method) train() (xuance.engine.run_competition.RunnerCompetition method) (xuance.mindspore.agents.base.agent.Agent method) (xuance.mindspore.agents.base.agents_marl.MARLAgents method) (xuance.mindspore.agents.core.off_policy.OffPolicyAgent method) (xuance.mindspore.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.mindspore.agents.core.offline.OfflineAgent method) (xuance.mindspore.agents.core.on_policy.OnPolicyAgent method) (xuance.mindspore.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.mindspore.agents.model_based_rl.dreamer_v2_agent.DreamerV2Agent method) (xuance.mindspore.agents.model_based_rl.dreamer_v3_agent.DreamerV3Agent method) (xuance.mindspore.agents.multi_agent_rl.coma_agents.COMA_Agents method) (xuance.mindspore.agents.multi_agent_rl.dcg_agents.DCG_Agents method) (xuance.mindspore.agents.multi_agent_rl.mfac_agents.MFAC_Agents method) (xuance.mindspore.agents.multi_agent_rl.mfq_agents.MFQ_Agents method) (xuance.mindspore.agents.policy_gradient.pdqn_agent.PDQN_Agent method) (xuance.mindspore.agents.policy_gradient.ppg_agent.PPG_Agent method) (xuance.mindspore.agents.policy_gradient.ppo_agent.PPO_Agent method) (xuance.mindspore.agents.policy_gradient.ppokl_agent.PPOKL_Agent method) (xuance.mindspore.agents.policy_gradient.spdqn_agent.SPDQN_Agent method) (xuance.mindspore.agents.qlearning_family.drqn_agent.DRQN_Agent method) (xuance.mindspore.agents.qlearning_family.noisydqn_agent.NoisyDQN_Agent method) (xuance.mindspore.agents.qlearning_family.perdqn_agent.PerDQN_Agent method) (xuance.tensorflow.agents.base.agent.Agent method) (xuance.tensorflow.agents.base.agents_marl.MARLAgents method) (xuance.tensorflow.agents.core.off_policy.OffPolicyAgent method) (xuance.tensorflow.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.tensorflow.agents.core.offline.OfflineAgent method) (xuance.tensorflow.agents.core.on_policy.OnPolicyAgent method) (xuance.tensorflow.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.tensorflow.agents.model_based_rl.dreamer_v2_agent.DreamerV2Agent method) (xuance.tensorflow.agents.model_based_rl.dreamer_v3_agent.DreamerV3Agent method) (xuance.tensorflow.agents.multi_agent_rl.coma_agents.COMA_Agents method) (xuance.tensorflow.agents.multi_agent_rl.dcg_agents.DCG_Agents method) (xuance.tensorflow.agents.multi_agent_rl.mfac_agents.MFAC_Agents method) (xuance.tensorflow.agents.multi_agent_rl.mfq_agents.MFQ_Agents method) (xuance.tensorflow.agents.policy_gradient.pdqn_agent.PDQN_Agent method) (xuance.tensorflow.agents.policy_gradient.ppg_agent.PPG_Agent method) (xuance.tensorflow.agents.policy_gradient.ppo_agent.PPO_Agent method) (xuance.tensorflow.agents.policy_gradient.ppokl_agent.PPOKL_Agent method) (xuance.tensorflow.agents.policy_gradient.spdqn_agent.SPDQN_Agent method) (xuance.tensorflow.agents.qlearning_family.drqn_agent.DRQN_Agent method) (xuance.tensorflow.agents.qlearning_family.noisydqn_agent.NoisyDQN_Agent method) (xuance.tensorflow.agents.qlearning_family.perdqn_agent.PerDQN_Agent method) (xuance.torch.agents.base.agent.Agent method) (xuance.torch.agents.base.agents_marl.MARLAgents method) (xuance.torch.agents.core.off_policy.OffPolicyAgent method) (xuance.torch.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.torch.agents.core.offline.OfflineAgent method) (xuance.torch.agents.core.on_policy.OnPolicyAgent method) (xuance.torch.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.torch.agents.model_based_rl.dreamer_v2_agent.DreamerV2Agent method) (xuance.torch.agents.model_based_rl.dreamer_v3_agent.DreamerV3Agent method) (xuance.torch.agents.multi_agent_rl.coma_agents.COMA_Agents method) (xuance.torch.agents.multi_agent_rl.mfac_agents.MFAC_Agents method) (xuance.torch.agents.multi_agent_rl.mfq_agents.MFQ_Agents method) (xuance.torch.agents.policy_gradient.pdqn_agent.PDQN_Agent method) (xuance.torch.agents.policy_gradient.ppg_agent.PPG_Agent method) (xuance.torch.agents.policy_gradient.ppo_agent.PPO_Agent method) (xuance.torch.agents.policy_gradient.ppokl_agent.PPOKL_Agent method) (xuance.torch.agents.policy_gradient.spdqn_agent.SPDQN_Agent method) (xuance.torch.agents.qlearning_family.drqn_agent.DRQN_Agent method) (xuance.torch.agents.qlearning_family.noisydqn_agent.NoisyDQN_Agent method) (xuance.torch.agents.qlearning_family.perdqn_agent.PerDQN_Agent method)

train_epochs() (xuance.mindspore.agents.base.agents_marl.MARLAgents method) (xuance.mindspore.agents.core.off_policy.OffPolicyAgent method) (xuance.mindspore.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.mindspore.agents.core.offline.OfflineAgent method) (xuance.mindspore.agents.core.on_policy.OnPolicyAgent method) (xuance.mindspore.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.mindspore.agents.model_based_rl.dreamer_v2_agent.DreamerV2Agent method) (xuance.mindspore.agents.model_based_rl.dreamer_v3_agent.DreamerV3Agent method) (xuance.mindspore.agents.multi_agent_rl.coma_agents.COMA_Agents method) (xuance.mindspore.agents.policy_gradient.pdqn_agent.PDQN_Agent method) (xuance.mindspore.agents.qlearning_family.noisydqn_agent.NoisyDQN_Agent method) (xuance.mindspore.agents.qlearning_family.perdqn_agent.PerDQN_Agent method) (xuance.tensorflow.agents.base.agents_marl.MARLAgents method) (xuance.tensorflow.agents.core.off_policy.OffPolicyAgent method) (xuance.tensorflow.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.tensorflow.agents.core.offline.OfflineAgent method) (xuance.tensorflow.agents.core.on_policy.OnPolicyAgent method) (xuance.tensorflow.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.tensorflow.agents.model_based_rl.dreamer_v2_agent.DreamerV2Agent method) (xuance.tensorflow.agents.model_based_rl.dreamer_v3_agent.DreamerV3Agent method) (xuance.tensorflow.agents.multi_agent_rl.coma_agents.COMA_Agents method) (xuance.tensorflow.agents.policy_gradient.pdqn_agent.PDQN_Agent method) (xuance.tensorflow.agents.qlearning_family.noisydqn_agent.NoisyDQN_Agent method) (xuance.tensorflow.agents.qlearning_family.perdqn_agent.PerDQN_Agent method) (xuance.torch.agents.base.agents_marl.MARLAgents method) (xuance.torch.agents.core.off_policy.OffPolicyAgent method) (xuance.torch.agents.core.off_policy_marl.OffPolicyMARLAgents method) (xuance.torch.agents.core.offline.OfflineAgent method) (xuance.torch.agents.core.on_policy.OnPolicyAgent method) (xuance.torch.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.torch.agents.model_based_rl.dreamer_v2_agent.DreamerV2Agent method) (xuance.torch.agents.model_based_rl.dreamer_v3_agent.DreamerV3Agent method) (xuance.torch.agents.multi_agent_rl.coma_agents.COMA_Agents method) (xuance.torch.agents.policy_gradient.pdqn_agent.PDQN_Agent method) (xuance.torch.agents.qlearning_family.noisydqn_agent.NoisyDQN_Agent method) (xuance.torch.agents.qlearning_family.perdqn_agent.PerDQN_Agent method) trainable_param() (xuance.mindspore.policies.categorical_marl.MAAC_Policy_Share method) (xuance.tensorflow.policies.categorical_marl.MAAC_Policy_Share method) trainable_params() (xuance.mindspore.policies.deterministic.BasicQnetwork method) (xuance.mindspore.policies.deterministic.DuelQnetwork method) (xuance.mindspore.policies.deterministic.NoisyQnetwork method) (xuance.mindspore.policies.deterministic.QRDQN_Network method) (xuance.mindspore.policies.deterministic_marl.MixingQnetwork method) (xuance.mindspore.policies.deterministic_marl.Weighted_MixingQnetwork method) trainable_variables (xuance.tensorflow.policies.deterministic.BasicQnetwork property) (xuance.tensorflow.policies.deterministic.C51Qnetwork property) (xuance.tensorflow.policies.deterministic.DRQNPolicy property) (xuance.tensorflow.policies.deterministic.DuelQnetwork property) (xuance.tensorflow.policies.deterministic.NoisyQnetwork property) (xuance.tensorflow.policies.deterministic.QRDQN_Network property) Transformer (class in xuance.mindspore.representations.vit) (class in xuance.tensorflow.representations.vit) (class in xuance.torch.representations.vit) TruncatedNormal (class in xuance.torch.utils.distributions) TruncatedStandardNormal (class in xuance.torch.utils.distributions) tune() (xuance.common.tuning_tools.HyperParameterTuner method) (xuance.common.tuning_tools.MultiObjectiveTuner method) two_hot_decoder() (in module xuance.torch.utils.operations) two_hot_encoder() (in module xuance.torch.utils.operations) TwoHotEncodingDistribution (class in xuance.torch.utils.distributions) type (xuance.common.tuning_tools.Hyperparameter attribute), [1]

U

uniform_init_weights() (in module xuance.torch.utils.operations) unwrapped (xuance.environment.utils.wrapper.XuanCeEnvWrapper property) update() (xuance.common.statistic_tools.RunningMeanStd method) (xuance.mindspore.learners.contrastive_unsupervised_rl.curl_learner.CURL_Learner method) (xuance.mindspore.learners.contrastive_unsupervised_rl.drq_learner.DrQ_Learner method) (xuance.mindspore.learners.contrastive_unsupervised_rl.spr_learner.SPR_Learner method) (xuance.mindspore.learners.learner.Learner method) (xuance.mindspore.learners.learner.LearnerMAS method) (xuance.mindspore.learners.model_based.dreamer_v2_learner.DreamerV2_Learner method) (xuance.mindspore.learners.model_based.dreamer_v3_learner.DreamerV3_Learner method) (xuance.mindspore.learners.multi_agent_rl.coma_learner.COMA_Learner method) (xuance.mindspore.learners.multi_agent_rl.dcg_learner.DCG_Learner method) (xuance.mindspore.learners.multi_agent_rl.iac_learner.IAC_Learner method) (xuance.mindspore.learners.multi_agent_rl.iddpg_learner.IDDPG_Learner method) (xuance.mindspore.learners.multi_agent_rl.ippo_learner.IPPO_Learner method) (xuance.mindspore.learners.multi_agent_rl.iql_learner.IQL_Learner method) (xuance.mindspore.learners.multi_agent_rl.isac_learner.ISAC_Learner method) (xuance.mindspore.learners.multi_agent_rl.maddpg_learner.MADDPG_Learner method) (xuance.mindspore.learners.multi_agent_rl.mappo_learner.MAPPO_Learner method) (xuance.mindspore.learners.multi_agent_rl.masac_learner.MASAC_Learner method) (xuance.mindspore.learners.multi_agent_rl.masacdis_learner.MASACDIS_Learner method) (xuance.mindspore.learners.multi_agent_rl.matd3_learner.MATD3_Learner method) (xuance.mindspore.learners.multi_agent_rl.mfac_learner.MFAC_Learner method) (xuance.mindspore.learners.multi_agent_rl.mfq_learner.MFQ_Learner method) (xuance.mindspore.learners.multi_agent_rl.qmix_learner.QMIX_Learner method) (xuance.mindspore.learners.multi_agent_rl.qtran_learner.QTRAN_Learner method) (xuance.mindspore.learners.multi_agent_rl.vdac_learner.VDAC_Learner method) (xuance.mindspore.learners.multi_agent_rl.vdn_learner.VDN_Learner method) (xuance.mindspore.learners.multi_agent_rl.wqmix_learner.WQMIX_Learner method) (xuance.mindspore.learners.offline.td3bc_learner.TD3_BC_Learner method) (xuance.mindspore.learners.policy_gradient.a2c_learner.A2C_Learner method) (xuance.mindspore.learners.policy_gradient.ddpg_learner.DDPG_Learner method) (xuance.mindspore.learners.policy_gradient.mpdqn_learner.MPDQN_Learner method) (xuance.mindspore.learners.policy_gradient.npg_learner.NPG_Learner method) (xuance.mindspore.learners.policy_gradient.pdqn_learner.PDQN_Learner method) (xuance.mindspore.learners.policy_gradient.pg_learner.PG_Learner method) (xuance.mindspore.learners.policy_gradient.ppg_learner.PPG_Learner method) (xuance.mindspore.learners.policy_gradient.ppo_learner.PPO_Learner method) (xuance.mindspore.learners.policy_gradient.ppokl_learner.PPOKL_Learner method) (xuance.mindspore.learners.policy_gradient.sac_learner.SAC_Learner method) (xuance.mindspore.learners.policy_gradient.sacdis_learner.SACDIS_Learner method) (xuance.mindspore.learners.policy_gradient.spdqn_learner.SPDQN_Learner method) (xuance.mindspore.learners.policy_gradient.td3_learner.TD3_Learner method) (xuance.mindspore.learners.qlearning_family.c51_learner.C51_Learner method) (xuance.mindspore.learners.qlearning_family.ddqn_learner.DDQN_Learner method) (xuance.mindspore.learners.qlearning_family.dqn_learner.DQN_Learner method) (xuance.mindspore.learners.qlearning_family.drqn_learner.DRQN_Learner method) (xuance.mindspore.learners.qlearning_family.dueldqn_learner.DuelDQN_Learner method) (xuance.mindspore.learners.qlearning_family.perdqn_learner.PerDQN_Learner method) (xuance.mindspore.learners.qlearning_family.qrdqn_learner.QRDQN_Learner method) (xuance.mindspore.utils.value_norm.ValueNorm method) (xuance.tensorflow.learners.contrastive_unsupervised_rl.curl_learner.CURL_Learner method) (xuance.tensorflow.learners.contrastive_unsupervised_rl.drq_learner.DrQ_Learner method) (xuance.tensorflow.learners.contrastive_unsupervised_rl.spr_learner.SPR_Learner method) (xuance.tensorflow.learners.learner.Learner method) (xuance.tensorflow.learners.learner.LearnerMAS method) (xuance.tensorflow.learners.model_based.dreamer_v2_learner.DreamerV2_Learner method) (xuance.tensorflow.learners.model_based.dreamer_v3_learner.DreamerV3_Learner method) (xuance.tensorflow.learners.multi_agent_rl.coma_learner.COMA_Learner method) (xuance.tensorflow.learners.multi_agent_rl.dcg_learner.DCG_Learner method) (xuance.tensorflow.learners.multi_agent_rl.iac_learner.IAC_Learner method) (xuance.tensorflow.learners.multi_agent_rl.iddpg_learner.IDDPG_Learner method) (xuance.tensorflow.learners.multi_agent_rl.ippo_learner.IPPO_Learner method) (xuance.tensorflow.learners.multi_agent_rl.iql_learner.IQL_Learner method) (xuance.tensorflow.learners.multi_agent_rl.isac_learner.ISAC_Learner method) (xuance.tensorflow.learners.multi_agent_rl.maddpg_learner.MADDPG_Learner method) (xuance.tensorflow.learners.multi_agent_rl.mappo_learner.MAPPO_Learner method) (xuance.tensorflow.learners.multi_agent_rl.masac_learner.MASAC_Learner method) (xuance.tensorflow.learners.multi_agent_rl.masacdis_learner.MASACDIS_Learner method) (xuance.tensorflow.learners.multi_agent_rl.matd3_learner.MATD3_Learner method) (xuance.tensorflow.learners.multi_agent_rl.mfac_learner.MFAC_Learner method) (xuance.tensorflow.learners.multi_agent_rl.mfq_learner.MFQ_Learner method) (xuance.tensorflow.learners.multi_agent_rl.qmix_learner.QMIX_Learner method) (xuance.tensorflow.learners.multi_agent_rl.qtran_learner.QTRAN_Learner method) (xuance.tensorflow.learners.multi_agent_rl.vdac_learner.VDAC_Learner method) (xuance.tensorflow.learners.multi_agent_rl.vdn_learner.VDN_Learner method) (xuance.tensorflow.learners.multi_agent_rl.wqmix_learner.WQMIX_Learner method) (xuance.tensorflow.learners.offline.td3bc_learner.TD3_BC_Learner method) (xuance.tensorflow.learners.policy_gradient.a2c_learner.A2C_Learner method) (xuance.tensorflow.learners.policy_gradient.ddpg_learner.DDPG_Learner method) (xuance.tensorflow.learners.policy_gradient.mpdqn_learner.MPDQN_Learner method) (xuance.tensorflow.learners.policy_gradient.npg_learner.NPG_Learner method) (xuance.tensorflow.learners.policy_gradient.pdqn_learner.PDQN_Learner method) (xuance.tensorflow.learners.policy_gradient.pg_learner.PG_Learner method) (xuance.tensorflow.learners.policy_gradient.ppg_learner.PPG_Learner method) (xuance.tensorflow.learners.policy_gradient.ppo_learner.PPO_Learner method) (xuance.tensorflow.learners.policy_gradient.ppokl_learner.PPOKL_Learner method) (xuance.tensorflow.learners.policy_gradient.sac_learner.SAC_Learner method) (xuance.tensorflow.learners.policy_gradient.sacdis_learner.SACDIS_Learner method) (xuance.tensorflow.learners.policy_gradient.spdqn_learner.SPDQN_Learner method) (xuance.tensorflow.learners.policy_gradient.td3_learner.TD3_Learner method) (xuance.tensorflow.learners.qlearning_family.c51_learner.C51_Learner method) (xuance.tensorflow.learners.qlearning_family.ddqn_learner.DDQN_Learner method) (xuance.tensorflow.learners.qlearning_family.dqn_learner.DQN_Learner method) (xuance.tensorflow.learners.qlearning_family.drqn_learner.DRQN_Learner method) (xuance.tensorflow.learners.qlearning_family.dueldqn_learner.DuelDQN_Learner method) (xuance.tensorflow.learners.qlearning_family.perdqn_learner.PerDQN_Learner method) (xuance.tensorflow.learners.qlearning_family.qrdqn_learner.QRDQN_Learner method) (xuance.tensorflow.utils.value_norm.ValueNorm method) (xuance.torch.learners.contrastive_unsupervised_rl.curl_learner.CURL_Learner method) (xuance.torch.learners.contrastive_unsupervised_rl.drq_learner.DrQ_Learner method) (xuance.torch.learners.contrastive_unsupervised_rl.spr_learner.SPR_Learner method) (xuance.torch.learners.learner.Learner method) (xuance.torch.learners.learner.LearnerMAS method) (xuance.torch.learners.model_based.dreamer_v2_learner.DreamerV2_Learner method) (xuance.torch.learners.model_based.dreamer_v3_learner.DreamerV3_Learner method) (xuance.torch.learners.multi_agent_rl.coma_learner.COMA_Learner method) (xuance.torch.learners.multi_agent_rl.dcg_learner.DCG_Learner method) (xuance.torch.learners.multi_agent_rl.iac_learner.IAC_Learner method) (xuance.torch.learners.multi_agent_rl.iddpg_learner.IDDPG_Learner method) (xuance.torch.learners.multi_agent_rl.ippo_learner.IPPO_Learner method) (xuance.torch.learners.multi_agent_rl.iql_learner.IQL_Learner method) (xuance.torch.learners.multi_agent_rl.isac_learner.ISAC_Learner method) (xuance.torch.learners.multi_agent_rl.maddpg_learner.MADDPG_Learner method) (xuance.torch.learners.multi_agent_rl.mappo_learner.MAPPO_Learner method) (xuance.torch.learners.multi_agent_rl.masac_learner.MASAC_Learner method) (xuance.torch.learners.multi_agent_rl.masacdis_learner.MASACDIS_Learner method) (xuance.torch.learners.multi_agent_rl.matd3_learner.MATD3_Learner method) (xuance.torch.learners.multi_agent_rl.mfac_learner.MFAC_Learner method) (xuance.torch.learners.multi_agent_rl.mfq_learner.MFQ_Learner method) (xuance.torch.learners.multi_agent_rl.qmix_learner.QMIX_Learner method) (xuance.torch.learners.multi_agent_rl.qtran_learner.QTRAN_Learner method) (xuance.torch.learners.multi_agent_rl.vdac_learner.VDAC_Learner method) (xuance.torch.learners.multi_agent_rl.vdn_learner.VDN_Learner method) (xuance.torch.learners.multi_agent_rl.wqmix_learner.WQMIX_Learner method) (xuance.torch.learners.offline.td3bc_learner.TD3_BC_Learner method) (xuance.torch.learners.policy_gradient.a2c_learner.A2C_Learner method) (xuance.torch.learners.policy_gradient.ddpg_learner.DDPG_Learner method) (xuance.torch.learners.policy_gradient.mpdqn_learner.MPDQN_Learner method) (xuance.torch.learners.policy_gradient.npg_learner.NPG_Learner method) (xuance.torch.learners.policy_gradient.pdqn_learner.PDQN_Learner method) (xuance.torch.learners.policy_gradient.pg_learner.PG_Learner method) (xuance.torch.learners.policy_gradient.ppg_learner.PPG_Learner method) (xuance.torch.learners.policy_gradient.ppo_learner.PPO_Learner method) (xuance.torch.learners.policy_gradient.ppokl_learner.PPOKL_Learner method) (xuance.torch.learners.policy_gradient.sac_learner.SAC_Learner method) (xuance.torch.learners.policy_gradient.sacdis_learner.SACDIS_Learner method) (xuance.torch.learners.policy_gradient.spdqn_learner.SPDQN_Learner method) (xuance.torch.learners.policy_gradient.td3_learner.TD3_Learner method) (xuance.torch.learners.qlearning_family.c51_learner.C51_Learner method) (xuance.torch.learners.qlearning_family.ddqn_learner.DDQN_Learner method) (xuance.torch.learners.qlearning_family.dqn_learner.DQN_Learner method) (xuance.torch.learners.qlearning_family.drqn_learner.DRQN_Learner method) (xuance.torch.learners.qlearning_family.dueldqn_learner.DuelDQN_Learner method) (xuance.torch.learners.qlearning_family.perdqn_learner.PerDQN_Learner method) (xuance.torch.learners.qlearning_family.qrdqn_learner.QRDQN_Learner method) (xuance.torch.utils.value_norm.ValueNorm method)

update_auxiliary() (xuance.mindspore.learners.policy_gradient.ppg_learner.PPG_Learner method) (xuance.tensorflow.learners.policy_gradient.ppg_learner.PPG_Learner method) (xuance.torch.learners.policy_gradient.ppg_learner.PPG_Learner method) update_critic() (xuance.mindspore.learners.policy_gradient.ppg_learner.PPG_Learner method) (xuance.tensorflow.learners.policy_gradient.ppg_learner.PPG_Learner method) (xuance.torch.learners.policy_gradient.ppg_learner.PPG_Learner method) update_from_moments() (xuance.common.statistic_tools.RunningMeanStd method) update_linear_decay() (in module xuance.mindspore.utils.operations) (in module xuance.tensorflow.utils.operations) (in module xuance.torch.utils.operations) update_noise() (xuance.mindspore.policies.deterministic.NoisyQnetwork method) (xuance.tensorflow.policies.deterministic.NoisyQnetwork method) (xuance.torch.policies.deterministic.NoisyQnetwork method) update_policy() (xuance.mindspore.learners.policy_gradient.ppg_learner.PPG_Learner method) (xuance.tensorflow.learners.policy_gradient.ppg_learner.PPG_Learner method) (xuance.torch.learners.policy_gradient.ppg_learner.PPG_Learner method) update_priorities() (xuance.common.memory_tools.PerOffPolicyBuffer method) update_rnn() (xuance.mindspore.learners.learner.LearnerMAS method) (xuance.mindspore.learners.multi_agent_rl.commnet_learner.CommNet_Learner method) (xuance.mindspore.learners.multi_agent_rl.ic3net_learner.IC3Net_Learner method) (xuance.mindspore.learners.multi_agent_rl.masacdis_learner.MASACDIS_Learner method) (xuance.tensorflow.learners.learner.LearnerMAS method) (xuance.tensorflow.learners.multi_agent_rl.commnet_learner.CommNet_Learner method) (xuance.tensorflow.learners.multi_agent_rl.ic3net_learner.IC3Net_Learner method) (xuance.tensorflow.learners.multi_agent_rl.masacdis_learner.MASACDIS_Learner method) (xuance.torch.learners.learner.LearnerMAS method) (xuance.torch.learners.multi_agent_rl.coma_learner.COMA_Learner method) (xuance.torch.learners.multi_agent_rl.commnet_learner.CommNet_Learner method) (xuance.torch.learners.multi_agent_rl.dcg_learner.DCG_Learner method) (xuance.torch.learners.multi_agent_rl.iac_learner.IAC_Learner method) (xuance.torch.learners.multi_agent_rl.ic3net_learner.IC3Net_Learner method) (xuance.torch.learners.multi_agent_rl.iddpg_learner.IDDPG_Learner method) (xuance.torch.learners.multi_agent_rl.ippo_learner.IPPO_Learner method) (xuance.torch.learners.multi_agent_rl.iql_learner.IQL_Learner method) (xuance.torch.learners.multi_agent_rl.isac_learner.ISAC_Learner method) (xuance.torch.learners.multi_agent_rl.maddpg_learner.MADDPG_Learner method) (xuance.torch.learners.multi_agent_rl.mappo_learner.MAPPO_Learner method) (xuance.torch.learners.multi_agent_rl.masac_learner.MASAC_Learner method) (xuance.torch.learners.multi_agent_rl.masacdis_learner.MASACDIS_Learner method) (xuance.torch.learners.multi_agent_rl.matd3_learner.MATD3_Learner method) (xuance.torch.learners.multi_agent_rl.mfac_learner.MFAC_Learner method) (xuance.torch.learners.multi_agent_rl.mfq_learner.MFQ_Learner method) (xuance.torch.learners.multi_agent_rl.qmix_learner.QMIX_Learner method) (xuance.torch.learners.multi_agent_rl.qtran_learner.QTRAN_Learner method) (xuance.torch.learners.multi_agent_rl.vdac_learner.VDAC_Learner method) (xuance.torch.learners.multi_agent_rl.vdn_learner.VDN_Learner method) (xuance.torch.learners.multi_agent_rl.wqmix_learner.WQMIX_Learner method) use_mpi (xuance.common.statistic_tools.RunningMeanStd attribute)

V

value_tot() (xuance.mindspore.policies.categorical_marl.MAAC_Policy method) (xuance.mindspore.policies.categorical_marl.MAAC_Policy_Share method) (xuance.mindspore.policies.gaussian_marl.MAAC_Policy method) (xuance.tensorflow.policies.categorical_marl.MAAC_Policy method) (xuance.tensorflow.policies.categorical_marl.MAAC_Policy_Share method) (xuance.tensorflow.policies.gaussian_marl.MAAC_Policy method) (xuance.torch.policies.categorical_marl.MAAC_Policy method) (xuance.torch.policies.gaussian_marl.MAAC_Policy method) ValueNorm (class in xuance.mindspore.utils.value_norm) (class in xuance.tensorflow.utils.value_norm) (class in xuance.torch.utils.value_norm) values_next() (xuance.mindspore.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.mindspore.agents.multi_agent_rl.coma_agents.COMA_Agents method) (xuance.mindspore.agents.multi_agent_rl.iac_agents.IAC_Agents method) (xuance.mindspore.agents.multi_agent_rl.mappo_agents.MAPPO_Agents method) (xuance.mindspore.agents.multi_agent_rl.mfac_agents.MFAC_Agents method) (xuance.mindspore.agents.multi_agent_rl.vdac_agents.VDAC_Agents method) (xuance.tensorflow.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.tensorflow.agents.multi_agent_rl.coma_agents.COMA_Agents method) (xuance.tensorflow.agents.multi_agent_rl.iac_agents.IAC_Agents method) (xuance.tensorflow.agents.multi_agent_rl.mappo_agents.MAPPO_Agents method) (xuance.tensorflow.agents.multi_agent_rl.mfac_agents.MFAC_Agents method) (xuance.tensorflow.agents.multi_agent_rl.vdac_agents.VDAC_Agents method) (xuance.torch.agents.core.on_policy_marl.OnPolicyMARLAgents method) (xuance.torch.agents.multi_agent_rl.coma_agents.COMA_Agents method) (xuance.torch.agents.multi_agent_rl.iac_agents.IAC_Agents method) (xuance.torch.agents.multi_agent_rl.mappo_agents.MAPPO_Agents method) (xuance.torch.agents.multi_agent_rl.mfac_agents.MFAC_Agents method) (xuance.torch.agents.multi_agent_rl.vdac_agents.VDAC_Agents method)

variance (xuance.torch.utils.distributions.TruncatedStandardNormal property) VDAC_Agents (class in xuance.mindspore.agents.multi_agent_rl.vdac_agents) (class in xuance.tensorflow.agents.multi_agent_rl.vdac_agents) (class in xuance.torch.agents.multi_agent_rl.vdac_agents) VDAC_Learner (class in xuance.mindspore.learners.multi_agent_rl.vdac_learner) (class in xuance.tensorflow.learners.multi_agent_rl.vdac_learner) (class in xuance.torch.learners.multi_agent_rl.vdac_learner) VDN_Agents (class in xuance.mindspore.agents.multi_agent_rl.vdn_agents) (class in xuance.tensorflow.agents.multi_agent_rl.vdn_agents) (class in xuance.torch.agents.multi_agent_rl.vdn_agents) VDN_Learner (class in xuance.mindspore.learners.multi_agent_rl.vdn_learner) (class in xuance.tensorflow.learners.multi_agent_rl.vdn_learner) (class in xuance.torch.learners.multi_agent_rl.vdn_learner) VDN_mixer (class in xuance.mindspore.policies.core) (class in xuance.tensorflow.policies.core) (class in xuance.torch.policies.core) VecEnv (class in xuance.environment.vector_envs.vector_env) ViT (class in xuance.mindspore.representations.vit) (class in xuance.tensorflow.representations.vit) (class in xuance.torch.representations.vit)

W

Weighted_MixingQnetwork (class in xuance.mindspore.policies.deterministic_marl) (class in xuance.tensorflow.policies.deterministic_marl) (class in xuance.torch.policies.deterministic_marl) worker() (in module xuance.environment.vector_envs.subprocess.subproc_vec_env) (in module xuance.environment.vector_envs.subprocess.subproc_vec_maenv) WorldModel (class in xuance.mindspore.representations.world_model) (class in xuance.mindspore.representations.world_model_v2) (class in xuance.tensorflow.representations.world_model) (class in xuance.tensorflow.representations.world_model_v2) (class in xuance.torch.representations.world_model) (class in xuance.torch.representations.world_model_v2)

WQMIX_Agents (class in xuance.mindspore.agents.multi_agent_rl.wqmix_agents) (class in xuance.tensorflow.agents.multi_agent_rl.wqmix_agents) (class in xuance.torch.agents.multi_agent_rl.wqmix_agents) WQMIX_Learner (class in xuance.mindspore.learners.multi_agent_rl.wqmix_learner) (class in xuance.tensorflow.learners.multi_agent_rl.wqmix_learner) (class in xuance.torch.learners.multi_agent_rl.wqmix_learner)

X

xuance.common.callback module xuance.common.common_tools module xuance.common.memory_offline module xuance.common.memory_tools module xuance.common.memory_tools_marl module xuance.common.offline_util module xuance.common.segtree_tool module xuance.common.statistic_tools module xuance.common.tuning_tools module xuance.engine.run_basic module xuance.engine.run_competition module xuance.engine.run_drl module xuance.engine.run_football module xuance.engine.run_marl module xuance.engine.run_offlinerl module xuance.engine.run_sc2 module xuance.environment module xuance.environment.multi_agent_env.drones module xuance.environment.multi_agent_env.football module xuance.environment.multi_agent_env.mpe module xuance.environment.multi_agent_env.robotic_warehouse module xuance.environment.multi_agent_env.starcraft2 module xuance.environment.single_agent_env.gym module xuance.environment.single_agent_env.metadrive module xuance.environment.single_agent_env.minigrid module xuance.environment.single_agent_env.platform module xuance.environment.utils.base module xuance.environment.utils.wrapper module xuance.environment.vector_envs.dummy.dummy_vec_env module xuance.environment.vector_envs.dummy.dummy_vec_maenv module xuance.environment.vector_envs.env_utils module xuance.environment.vector_envs.subprocess.subproc_vec_env module xuance.environment.vector_envs.subprocess.subproc_vec_maenv module xuance.environment.vector_envs.vector_env module xuance.mindspore.agents.base.agent module xuance.mindspore.agents.base.agents_marl module xuance.mindspore.agents.contrastive_unsupervised_rl.curl_agent module, [1] xuance.mindspore.agents.contrastive_unsupervised_rl.drq_agent module, [1] xuance.mindspore.agents.contrastive_unsupervised_rl.spr_agent module, [1] xuance.mindspore.agents.core.off_policy module xuance.mindspore.agents.core.off_policy_marl module xuance.mindspore.agents.core.offline module xuance.mindspore.agents.core.on_policy module xuance.mindspore.agents.core.on_policy_marl module xuance.mindspore.agents.model_based_rl.dreamer_v2_agent module xuance.mindspore.agents.model_based_rl.dreamer_v3_agent module xuance.mindspore.agents.multi_agent_rl.coma_agents module xuance.mindspore.agents.multi_agent_rl.commnet_agents module xuance.mindspore.agents.multi_agent_rl.dcg_agents module xuance.mindspore.agents.multi_agent_rl.iac_agents module xuance.mindspore.agents.multi_agent_rl.ic3net_agents module xuance.mindspore.agents.multi_agent_rl.iddpg_agents module xuance.mindspore.agents.multi_agent_rl.ippo_agents module xuance.mindspore.agents.multi_agent_rl.iql_agents module xuance.mindspore.agents.multi_agent_rl.isac_agents module xuance.mindspore.agents.multi_agent_rl.maddpg_agents module xuance.mindspore.agents.multi_agent_rl.mappo_agents module xuance.mindspore.agents.multi_agent_rl.masac_agents module xuance.mindspore.agents.multi_agent_rl.matd3_agents module xuance.mindspore.agents.multi_agent_rl.mfac_agents module xuance.mindspore.agents.multi_agent_rl.mfq_agents module xuance.mindspore.agents.multi_agent_rl.qmix_agents module xuance.mindspore.agents.multi_agent_rl.qtran_agents module xuance.mindspore.agents.multi_agent_rl.tarmac_agents module xuance.mindspore.agents.multi_agent_rl.vdac_agents module xuance.mindspore.agents.multi_agent_rl.vdn_agents module xuance.mindspore.agents.multi_agent_rl.wqmix_agents module xuance.mindspore.agents.offline_rl.td3bc_agent module xuance.mindspore.agents.policy_gradient.a2c_agent module xuance.mindspore.agents.policy_gradient.ddpg_agent module xuance.mindspore.agents.policy_gradient.mpdqn_agent module xuance.mindspore.agents.policy_gradient.npg_agent module xuance.mindspore.agents.policy_gradient.pdqn_agent module xuance.mindspore.agents.policy_gradient.pg_agent module xuance.mindspore.agents.policy_gradient.ppg_agent module xuance.mindspore.agents.policy_gradient.ppo_agent module xuance.mindspore.agents.policy_gradient.ppokl_agent module xuance.mindspore.agents.policy_gradient.sac_agent module xuance.mindspore.agents.policy_gradient.spdqn_agent module xuance.mindspore.agents.policy_gradient.td3_agent module xuance.mindspore.agents.qlearning_family.c51_agent module xuance.mindspore.agents.qlearning_family.ddqn_agent module xuance.mindspore.agents.qlearning_family.dqn_agent module xuance.mindspore.agents.qlearning_family.drqn_agent module xuance.mindspore.agents.qlearning_family.dueldqn_agent module xuance.mindspore.agents.qlearning_family.noisydqn_agent module xuance.mindspore.agents.qlearning_family.perdqn_agent module xuance.mindspore.agents.qlearning_family.qrdqn_agent module xuance.mindspore.communications.attention_comm module xuance.mindspore.communications.base_comm module xuance.mindspore.communications.comm_net module xuance.mindspore.communications.emergent_comm module xuance.mindspore.communications.gnn_comm module xuance.mindspore.communications.ic3net_comm module xuance.mindspore.learners.contrastive_unsupervised_rl.curl_learner module xuance.mindspore.learners.contrastive_unsupervised_rl.drq_learner module xuance.mindspore.learners.contrastive_unsupervised_rl.spr_learner module xuance.mindspore.learners.learner module xuance.mindspore.learners.model_based.dreamer_v2_learner module xuance.mindspore.learners.model_based.dreamer_v3_learner module xuance.mindspore.learners.multi_agent_rl.coma_learner module xuance.mindspore.learners.multi_agent_rl.commnet_learner module xuance.mindspore.learners.multi_agent_rl.dcg_learner module xuance.mindspore.learners.multi_agent_rl.iac_learner module xuance.mindspore.learners.multi_agent_rl.ic3net_learner module xuance.mindspore.learners.multi_agent_rl.iddpg_learner module xuance.mindspore.learners.multi_agent_rl.ippo_learner module xuance.mindspore.learners.multi_agent_rl.iql_learner module xuance.mindspore.learners.multi_agent_rl.isac_learner module xuance.mindspore.learners.multi_agent_rl.isacdis_learner module xuance.mindspore.learners.multi_agent_rl.maddpg_learner module xuance.mindspore.learners.multi_agent_rl.mappo_learner module xuance.mindspore.learners.multi_agent_rl.masac_learner module xuance.mindspore.learners.multi_agent_rl.masacdis_learner module xuance.mindspore.learners.multi_agent_rl.matd3_learner module xuance.mindspore.learners.multi_agent_rl.mfac_learner module xuance.mindspore.learners.multi_agent_rl.mfq_learner module xuance.mindspore.learners.multi_agent_rl.qmix_learner module xuance.mindspore.learners.multi_agent_rl.qtran_learner module xuance.mindspore.learners.multi_agent_rl.tarmac_learner module xuance.mindspore.learners.multi_agent_rl.vdac_learner module xuance.mindspore.learners.multi_agent_rl.vdn_learner module xuance.mindspore.learners.multi_agent_rl.wqmix_learner module xuance.mindspore.learners.offline.td3bc_learner module xuance.mindspore.learners.policy_gradient.a2c_learner module xuance.mindspore.learners.policy_gradient.ddpg_learner module xuance.mindspore.learners.policy_gradient.mpdqn_learner module xuance.mindspore.learners.policy_gradient.npg_learner module xuance.mindspore.learners.policy_gradient.pdqn_learner module xuance.mindspore.learners.policy_gradient.pg_learner module xuance.mindspore.learners.policy_gradient.ppg_learner module xuance.mindspore.learners.policy_gradient.ppo_learner module xuance.mindspore.learners.policy_gradient.ppokl_learner module xuance.mindspore.learners.policy_gradient.sac_learner module xuance.mindspore.learners.policy_gradient.sacdis_learner module xuance.mindspore.learners.policy_gradient.spdqn_learner module xuance.mindspore.learners.policy_gradient.td3_learner module xuance.mindspore.learners.qlearning_family.c51_learner module xuance.mindspore.learners.qlearning_family.ddqn_learner module xuance.mindspore.learners.qlearning_family.dqn_learner module xuance.mindspore.learners.qlearning_family.drqn_learner module xuance.mindspore.learners.qlearning_family.dueldqn_learner module xuance.mindspore.learners.qlearning_family.perdqn_learner module xuance.mindspore.learners.qlearning_family.qrdqn_learner module xuance.mindspore.policies.categorical module xuance.mindspore.policies.categorical_marl module xuance.mindspore.policies.coordination_graph module xuance.mindspore.policies.core module xuance.mindspore.policies.deterministic module xuance.mindspore.policies.deterministic_marl module xuance.mindspore.policies.dreamer module xuance.mindspore.policies.gaussian module xuance.mindspore.policies.gaussian_marl module xuance.mindspore.representations.cnn module xuance.mindspore.representations.mlp module xuance.mindspore.representations.rnn module xuance.mindspore.representations.vit module xuance.mindspore.representations.world_model module xuance.mindspore.representations.world_model_v2 module xuance.mindspore.utils.device module xuance.mindspore.utils.distributions module xuance.mindspore.utils.harmonizer module xuance.mindspore.utils.layers module xuance.mindspore.utils.layers4dreamer module xuance.mindspore.utils.operations module xuance.mindspore.utils.value_norm module xuance.tensorflow.agents.base.agent module xuance.tensorflow.agents.base.agents_marl module xuance.tensorflow.agents.contrastive_unsupervised_rl.curl_agent module, [1] xuance.tensorflow.agents.contrastive_unsupervised_rl.drq_agent module, [1] xuance.tensorflow.agents.contrastive_unsupervised_rl.spr_agent module, [1] xuance.tensorflow.agents.core.off_policy module xuance.tensorflow.agents.core.off_policy_marl module xuance.tensorflow.agents.core.offline module xuance.tensorflow.agents.core.on_policy module xuance.tensorflow.agents.core.on_policy_marl module xuance.tensorflow.agents.model_based_rl.dreamer_v2_agent module xuance.tensorflow.agents.model_based_rl.dreamer_v3_agent module xuance.tensorflow.agents.multi_agent_rl.coma_agents module xuance.tensorflow.agents.multi_agent_rl.commnet_agents module xuance.tensorflow.agents.multi_agent_rl.dcg_agents module xuance.tensorflow.agents.multi_agent_rl.iac_agents module xuance.tensorflow.agents.multi_agent_rl.ic3net_agents module xuance.tensorflow.agents.multi_agent_rl.iddpg_agents module xuance.tensorflow.agents.multi_agent_rl.ippo_agents module xuance.tensorflow.agents.multi_agent_rl.iql_agents module xuance.tensorflow.agents.multi_agent_rl.isac_agents module xuance.tensorflow.agents.multi_agent_rl.maddpg_agents module xuance.tensorflow.agents.multi_agent_rl.mappo_agents module xuance.tensorflow.agents.multi_agent_rl.masac_agents module xuance.tensorflow.agents.multi_agent_rl.matd3_agents module xuance.tensorflow.agents.multi_agent_rl.mfac_agents module xuance.tensorflow.agents.multi_agent_rl.mfq_agents module xuance.tensorflow.agents.multi_agent_rl.qmix_agents module xuance.tensorflow.agents.multi_agent_rl.qtran_agents module xuance.tensorflow.agents.multi_agent_rl.tarmac_agents module xuance.tensorflow.agents.multi_agent_rl.vdac_agents module xuance.tensorflow.agents.multi_agent_rl.vdn_agents module xuance.tensorflow.agents.multi_agent_rl.wqmix_agents module xuance.tensorflow.agents.offline_rl.td3bc_agent module xuance.tensorflow.agents.policy_gradient.a2c_agent module xuance.tensorflow.agents.policy_gradient.ddpg_agent module xuance.tensorflow.agents.policy_gradient.mpdqn_agent module xuance.tensorflow.agents.policy_gradient.npg_agent module xuance.tensorflow.agents.policy_gradient.pdqn_agent module xuance.tensorflow.agents.policy_gradient.pg_agent module xuance.tensorflow.agents.policy_gradient.ppg_agent module xuance.tensorflow.agents.policy_gradient.ppo_agent module xuance.tensorflow.agents.policy_gradient.ppokl_agent module xuance.tensorflow.agents.policy_gradient.sac_agent module xuance.tensorflow.agents.policy_gradient.spdqn_agent module xuance.tensorflow.agents.policy_gradient.td3_agent module xuance.tensorflow.agents.qlearning_family.c51_agent module xuance.tensorflow.agents.qlearning_family.ddqn_agent module xuance.tensorflow.agents.qlearning_family.dqn_agent module xuance.tensorflow.agents.qlearning_family.drqn_agent module

xuance.tensorflow.agents.qlearning_family.dueldqn_agent module xuance.tensorflow.agents.qlearning_family.noisydqn_agent module xuance.tensorflow.agents.qlearning_family.perdqn_agent module xuance.tensorflow.agents.qlearning_family.qrdqn_agent module xuance.tensorflow.communications.attention_comm module xuance.tensorflow.communications.base_comm module xuance.tensorflow.communications.comm_net module xuance.tensorflow.communications.emergent_comm module xuance.tensorflow.communications.gnn_comm module xuance.tensorflow.communications.ic3net_comm module xuance.tensorflow.learners.contrastive_unsupervised_rl.curl_learner module xuance.tensorflow.learners.contrastive_unsupervised_rl.drq_learner module xuance.tensorflow.learners.contrastive_unsupervised_rl.spr_learner module xuance.tensorflow.learners.learner module xuance.tensorflow.learners.model_based.dreamer_v2_learner module xuance.tensorflow.learners.model_based.dreamer_v3_learner module xuance.tensorflow.learners.multi_agent_rl.coma_learner module xuance.tensorflow.learners.multi_agent_rl.commnet_learner module xuance.tensorflow.learners.multi_agent_rl.dcg_learner module xuance.tensorflow.learners.multi_agent_rl.iac_learner module xuance.tensorflow.learners.multi_agent_rl.ic3net_learner module xuance.tensorflow.learners.multi_agent_rl.iddpg_learner module xuance.tensorflow.learners.multi_agent_rl.ippo_learner module xuance.tensorflow.learners.multi_agent_rl.iql_learner module xuance.tensorflow.learners.multi_agent_rl.isac_learner module xuance.tensorflow.learners.multi_agent_rl.isacdis_learner module xuance.tensorflow.learners.multi_agent_rl.maddpg_learner module xuance.tensorflow.learners.multi_agent_rl.mappo_learner module xuance.tensorflow.learners.multi_agent_rl.masac_learner module xuance.tensorflow.learners.multi_agent_rl.masacdis_learner module xuance.tensorflow.learners.multi_agent_rl.matd3_learner module xuance.tensorflow.learners.multi_agent_rl.mfac_learner module xuance.tensorflow.learners.multi_agent_rl.mfq_learner module xuance.tensorflow.learners.multi_agent_rl.qmix_learner module xuance.tensorflow.learners.multi_agent_rl.qtran_learner module xuance.tensorflow.learners.multi_agent_rl.tarmac_learner module xuance.tensorflow.learners.multi_agent_rl.vdac_learner module xuance.tensorflow.learners.multi_agent_rl.vdn_learner module xuance.tensorflow.learners.multi_agent_rl.wqmix_learner module xuance.tensorflow.learners.offline.td3bc_learner module xuance.tensorflow.learners.policy_gradient.a2c_learner module xuance.tensorflow.learners.policy_gradient.ddpg_learner module xuance.tensorflow.learners.policy_gradient.mpdqn_learner module xuance.tensorflow.learners.policy_gradient.npg_learner module xuance.tensorflow.learners.policy_gradient.pdqn_learner module xuance.tensorflow.learners.policy_gradient.pg_learner module xuance.tensorflow.learners.policy_gradient.ppg_learner module xuance.tensorflow.learners.policy_gradient.ppo_learner module xuance.tensorflow.learners.policy_gradient.ppokl_learner module xuance.tensorflow.learners.policy_gradient.sac_learner module xuance.tensorflow.learners.policy_gradient.sacdis_learner module xuance.tensorflow.learners.policy_gradient.spdqn_learner module xuance.tensorflow.learners.policy_gradient.td3_learner module xuance.tensorflow.learners.qlearning_family.c51_learner module xuance.tensorflow.learners.qlearning_family.ddqn_learner module xuance.tensorflow.learners.qlearning_family.dqn_learner module xuance.tensorflow.learners.qlearning_family.drqn_learner module xuance.tensorflow.learners.qlearning_family.dueldqn_learner module xuance.tensorflow.learners.qlearning_family.perdqn_learner module xuance.tensorflow.learners.qlearning_family.qrdqn_learner module xuance.tensorflow.policies.categorical module xuance.tensorflow.policies.categorical_marl module xuance.tensorflow.policies.coordination_graph module xuance.tensorflow.policies.core module xuance.tensorflow.policies.deterministic module xuance.tensorflow.policies.deterministic_marl module xuance.tensorflow.policies.dreamer module xuance.tensorflow.policies.gaussian module xuance.tensorflow.policies.gaussian_marl module xuance.tensorflow.representations.cnn module xuance.tensorflow.representations.mlp module xuance.tensorflow.representations.rnn module xuance.tensorflow.representations.vit module xuance.tensorflow.representations.world_model module xuance.tensorflow.representations.world_model_v2 module xuance.tensorflow.utils.device module xuance.tensorflow.utils.distributions module xuance.tensorflow.utils.harmonizer module xuance.tensorflow.utils.layers module xuance.tensorflow.utils.layers4dreamer module xuance.tensorflow.utils.operations module xuance.tensorflow.utils.value_norm module xuance.torch.agents.base.agent module xuance.torch.agents.base.agents_marl module xuance.torch.agents.contrastive_unsupervised_rl.curl_agent module, [1] xuance.torch.agents.contrastive_unsupervised_rl.drq_agent module, [1] xuance.torch.agents.contrastive_unsupervised_rl.spr_agent module, [1] xuance.torch.agents.core.off_policy module xuance.torch.agents.core.off_policy_marl module xuance.torch.agents.core.offline module xuance.torch.agents.core.on_policy module xuance.torch.agents.core.on_policy_marl module xuance.torch.agents.model_based_rl.dreamer_v2_agent module xuance.torch.agents.model_based_rl.dreamer_v3_agent module xuance.torch.agents.multi_agent_rl.coma_agents module xuance.torch.agents.multi_agent_rl.commnet_agents module xuance.torch.agents.multi_agent_rl.dcg_agents module xuance.torch.agents.multi_agent_rl.iac_agents module xuance.torch.agents.multi_agent_rl.ic3net_agents module xuance.torch.agents.multi_agent_rl.iddpg_agents module xuance.torch.agents.multi_agent_rl.ippo_agents module xuance.torch.agents.multi_agent_rl.iql_agents module xuance.torch.agents.multi_agent_rl.isac_agents module xuance.torch.agents.multi_agent_rl.maddpg_agents module xuance.torch.agents.multi_agent_rl.mappo_agents module xuance.torch.agents.multi_agent_rl.masac_agents module xuance.torch.agents.multi_agent_rl.matd3_agents module xuance.torch.agents.multi_agent_rl.mfac_agents module xuance.torch.agents.multi_agent_rl.mfq_agents module xuance.torch.agents.multi_agent_rl.qmix_agents module xuance.torch.agents.multi_agent_rl.qtran_agents module xuance.torch.agents.multi_agent_rl.tarmac_agents module xuance.torch.agents.multi_agent_rl.vdac_agents module xuance.torch.agents.multi_agent_rl.vdn_agents module xuance.torch.agents.multi_agent_rl.wqmix_agents module xuance.torch.agents.offline_rl.td3bc_agent module xuance.torch.agents.policy_gradient.a2c_agent module xuance.torch.agents.policy_gradient.ddpg_agent module xuance.torch.agents.policy_gradient.mpdqn_agent module xuance.torch.agents.policy_gradient.npg_agent module xuance.torch.agents.policy_gradient.pdqn_agent module xuance.torch.agents.policy_gradient.pg_agent module xuance.torch.agents.policy_gradient.ppg_agent module xuance.torch.agents.policy_gradient.ppo_agent module xuance.torch.agents.policy_gradient.ppokl_agent module xuance.torch.agents.policy_gradient.sac_agent module xuance.torch.agents.policy_gradient.spdqn_agent module xuance.torch.agents.policy_gradient.td3_agent module xuance.torch.agents.qlearning_family.c51_agent module xuance.torch.agents.qlearning_family.ddqn_agent module xuance.torch.agents.qlearning_family.dqn_agent module xuance.torch.agents.qlearning_family.drqn_agent module xuance.torch.agents.qlearning_family.dueldqn_agent module xuance.torch.agents.qlearning_family.noisydqn_agent module xuance.torch.agents.qlearning_family.perdqn_agent module xuance.torch.agents.qlearning_family.qrdqn_agent module xuance.torch.communications.attention_comm module xuance.torch.communications.base_comm module xuance.torch.communications.comm_net module xuance.torch.communications.emergent_comm module xuance.torch.communications.gnn_comm module xuance.torch.communications.ic3net_comm module xuance.torch.learners.contrastive_unsupervised_rl.curl_learner module xuance.torch.learners.contrastive_unsupervised_rl.drq_learner module xuance.torch.learners.contrastive_unsupervised_rl.spr_learner module xuance.torch.learners.learner module xuance.torch.learners.model_based.dreamer_v2_learner module xuance.torch.learners.model_based.dreamer_v3_learner module xuance.torch.learners.multi_agent_rl.coma_learner module xuance.torch.learners.multi_agent_rl.commnet_learner module xuance.torch.learners.multi_agent_rl.dcg_learner module xuance.torch.learners.multi_agent_rl.iac_learner module xuance.torch.learners.multi_agent_rl.ic3net_learner module xuance.torch.learners.multi_agent_rl.iddpg_learner module xuance.torch.learners.multi_agent_rl.ippo_learner module xuance.torch.learners.multi_agent_rl.iql_learner module xuance.torch.learners.multi_agent_rl.isac_learner module xuance.torch.learners.multi_agent_rl.isacdis_learner module xuance.torch.learners.multi_agent_rl.maddpg_learner module xuance.torch.learners.multi_agent_rl.mappo_learner module xuance.torch.learners.multi_agent_rl.masac_learner module xuance.torch.learners.multi_agent_rl.masacdis_learner module xuance.torch.learners.multi_agent_rl.matd3_learner module xuance.torch.learners.multi_agent_rl.mfac_learner module xuance.torch.learners.multi_agent_rl.mfq_learner module xuance.torch.learners.multi_agent_rl.qmix_learner module xuance.torch.learners.multi_agent_rl.qtran_learner module xuance.torch.learners.multi_agent_rl.tarmac_learner module xuance.torch.learners.multi_agent_rl.vdac_learner module xuance.torch.learners.multi_agent_rl.vdn_learner module xuance.torch.learners.multi_agent_rl.wqmix_learner module xuance.torch.learners.offline.td3bc_learner module xuance.torch.learners.policy_gradient.a2c_learner module xuance.torch.learners.policy_gradient.ddpg_learner module xuance.torch.learners.policy_gradient.mpdqn_learner module xuance.torch.learners.policy_gradient.npg_learner module xuance.torch.learners.policy_gradient.pdqn_learner module xuance.torch.learners.policy_gradient.pg_learner module xuance.torch.learners.policy_gradient.ppg_learner module xuance.torch.learners.policy_gradient.ppo_learner module xuance.torch.learners.policy_gradient.ppokl_learner module xuance.torch.learners.policy_gradient.sac_learner module xuance.torch.learners.policy_gradient.sacdis_learner module xuance.torch.learners.policy_gradient.spdqn_learner module xuance.torch.learners.policy_gradient.td3_learner module xuance.torch.learners.qlearning_family.c51_learner module xuance.torch.learners.qlearning_family.ddqn_learner module xuance.torch.learners.qlearning_family.dqn_learner module xuance.torch.learners.qlearning_family.drqn_learner module xuance.torch.learners.qlearning_family.dueldqn_learner module xuance.torch.learners.qlearning_family.perdqn_learner module xuance.torch.learners.qlearning_family.qrdqn_learner module xuance.torch.policies.categorical module xuance.torch.policies.categorical_marl module xuance.torch.policies.coordination_graph module xuance.torch.policies.core module xuance.torch.policies.deterministic module xuance.torch.policies.deterministic_marl module xuance.torch.policies.dreamer module xuance.torch.policies.gaussian module xuance.torch.policies.gaussian_marl module xuance.torch.representations.cnn module xuance.torch.representations.mlp module xuance.torch.representations.rnn module xuance.torch.representations.vit module xuance.torch.representations.world_model module xuance.torch.representations.world_model_v2 module xuance.torch.utils.device module xuance.torch.utils.distributions module xuance.torch.utils.harmonizer module xuance.torch.utils.layers module xuance.torch.utils.layers4dreamer module xuance.torch.utils.operations module xuance.torch.utils.value_norm module XuanCeAtariEnvWrapper (class in xuance.environment.utils.wrapper) XuanCeEnvWrapper (class in xuance.environment.utils.wrapper) XuanCeMultiAgentEnvWrapper (class in xuance.environment.utils.wrapper)