索引

A

act() (openrl.drivers.onpolicy_driver.OnPolicyDriver 方法) (openrl.modules.common.ppo_net.PPONet 方法) (openrl.modules.common.PPONet 方法) (openrl.modules.ppo_module.PPOModule 方法) (openrl.modules.rl_module.RLModule 方法) (openrl.runners.common.ppo_agent.PPOAgent 方法) (openrl.runners.common.PPOAgent 方法) Action (openrl.envs.mpe.core 中的类) action_space (openrl.envs.vec_env.base_venv.BaseVecEnv 属性) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) actions() (openrl.envs.vec_env.wrappers.base_wrapper.VectorActionWrapper 方法) ACTLayer (openrl.modules.networks.utils.act 中的类) actor_rollout() (openrl.drivers.onpolicy_driver.OnPolicyDriver 方法) add2buffer() (openrl.drivers.onpolicy_driver.OnPolicyDriver 方法) add_attr() (openrl.envs.mpe.rendering.Geom 方法) add_geom() (openrl.envs.mpe.rendering.Viewer 方法) add_onetime() (openrl.envs.mpe.rendering.Viewer 方法) AddBias (openrl.modules.networks.utils.distributions 中的类) after_update() (openrl.buffers.normal_buffer.NormalReplayBuffer 方法) (openrl.buffers.NormalReplayBuffer 方法) (openrl.buffers.replay_data.ReplayData 方法) Agent (openrl.envs.mpe.core 中的类) agent_num (openrl.envs.mpe.multiagent_env.MultiAgentEnv property) (openrl.envs.vec_env.base_venv.BaseVecEnv property) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) (openrl.envs.wrappers.base_wrapper.BaseWrapper property) (openrl.envs.wrappers.BaseWrapper property) (openrl.envs.wrappers.multiagent_wrapper.Single2MultiAgentWrapper property) (openrl.envs.wrappers.Single2MultiAgentWrapper property)

AgentState (openrl.envs.mpe.core 中的类) all_batch() (openrl.buffers.utils.obs_data.ObsData 方法) all_batch_data() (openrl.buffers.replay_data.ReplayData 方法) append() (openrl.envs.vec_env.vec_info.base_vec_info.BaseVecInfo 方法) (openrl.envs.vec_env.vec_info.nlp_vec_info.NLPVecInfo 方法) (openrl.envs.vec_env.vec_info.simple_vec_info.SimpleVecInfo 方法) apply_action_force() (openrl.envs.mpe.core.World 方法) apply_environment_force() (openrl.envs.mpe.core.World 方法) assign_agent_colors() (openrl.envs.mpe.core.World 方法) assign_landmark_colors() (openrl.envs.mpe.core.World 方法) AsyncVectorEnv (openrl.envs.vec_env 中的类) (openrl.envs.vec_env.async_venv 中的类) Attr (openrl.envs.mpe.rendering 中的类) auto_register() (openrl.envs.vec_env.vec_info.VecInfoFactory 静态方法) (openrl.rewards.RewardFactory 静态方法) AutoReset (openrl.envs.wrappers 中的类) (openrl.envs.wrappers.extra_wrappers 中的类)

B

BaseAgent (openrl.runners.common.base_agent 中的类) BaseAlgorithm (openrl.algorithms.base_algorithm 中的类) BaseDriver (openrl.drivers.base_driver 中的类) BaseModule (openrl.modules.base_module 中的类) BaseNet (openrl.modules.common.base_net 中的类) BaseObservationWrapper (openrl.envs.wrappers 中的类) (openrl.envs.wrappers.base_wrapper 中的类) BasePolicyNetwork (openrl.modules.networks.base_policy_network 中的类) BaseReward (openrl.rewards.base_reward 中的类) BaseScenario (openrl.envs.mpe.scenario 中的类) BaseValueNetwork (openrl.modules.networks.base_value_network 中的类)

BaseVecEnv (openrl.envs.vec_env.base_venv 中的类) BaseVecInfo (openrl.envs.vec_env.vec_info.base_vec_info 中的类) BaseWrapper (openrl.envs.wrappers 中的类) (openrl.envs.wrappers.base_wrapper 中的类) batch_rewards() (openrl.envs.vec_env.RewardWrapper 方法) (openrl.envs.vec_env.wrappers.reward_wrapper.RewardWrapper 方法) (openrl.rewards.base_reward.BaseReward 方法) benchmark_data() (openrl.envs.mpe.scenarios.simple_spread.Scenario 方法) Bernoulli (openrl.modules.networks.utils.distributions 中的类) build_envs() (在 openrl.envs.common 模块中) (在 openrl.envs.common.build_envs 模块中)

C

cal_learner_number() (openrl.supports.opengpu.manager.RemoteGPUManager 方法) cal_value_loss() (openrl.algorithms.ppo.PPOAlgorithm 方法) calculate_distances() (openrl.envs.mpe.core.World 方法) call() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.sync_venv.SyncVectorEnv 方法) (openrl.envs.vec_env.SyncVectorEnv 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper 方法) call_fetch() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) call_send() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) Categorical (openrl.modules.networks.utils.distributions 中的类) CatSelfEmbedding (openrl.modules.networks.utils.attention 中的类) chat() (openrl.runners.common.chat_agent.ChatAgent 方法) (openrl.runners.common.ChatAgent 方法) ChatAgent (openrl.runners.common 中的类) (openrl.runners.common.chat_agent 中的类) check() (在 openrl.utils.util 模块中) check_gpus() (openrl.supports.opengpu.manager.RemoteGPUManager 方法) check_v2() (在 openrl.utils.util 模块中) close() (openrl.envs.mpe.rendering.SimpleImageViewer 方法) (openrl.envs.mpe.rendering.Viewer 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper 方法) (openrl.envs.wrappers.extra_wrappers.GIFWrapper 方法) (openrl.envs.wrappers.GIFWrapper 方法) (openrl.utils.logger.Logger 方法)

close_extras() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.sync_venv.SyncVectorEnv 方法) (openrl.envs.vec_env.SyncVectorEnv 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper 方法) closed (openrl.envs.vec_env.base_venv.BaseVecEnv 属性) CNNBase (openrl.modules.networks.utils.cnn 中的类) CNNLayer (openrl.modules.networks.utils.cnn 中的类) Color (openrl.envs.mpe.rendering 中的类) Compound (openrl.envs.mpe.rendering 中的类) compute_returns() (openrl.buffers.normal_buffer.NormalReplayBuffer 方法) (openrl.buffers.NormalReplayBuffer 方法) (openrl.buffers.replay_data.ReplayData 方法) (openrl.drivers.onpolicy_driver.OnPolicyDriver 方法) concatenate() (在 openrl.envs.vec_env.utils.numpy_utils 模块中) construct_obs() (openrl.envs.mpe.multiagent_env.MultiAgentEnv 静态方法) contains() (openrl.envs.mpe.multi_discrete.MultiDiscrete 方法) continuous_autoregreesive_act() (在 openrl.modules.networks.utils.transformer_act 模块中) continuous_parallel_act() (在 openrl.modules.networks.utils.transformer_act 模块中) convert_distributed_model() (openrl.modules.base_module.BaseModule 方法) CONVLayer (openrl.modules.networks.utils.mlp 中的类) create_config_parser() (在 openrl.configs.config 模块中) create_empty_array() (在 openrl.envs.vec_env.utils.numpy_utils 模块中) create_shared_memory() (在 openrl.envs.vec_env.utils.share_memory 模块中)

D

deal_render() (openrl.envs.mpe.multiagent_env.MultiAgentEnv 方法) debiased_mean_var() (openrl.modules.networks.utils.popart.PopArt 方法) DEFAULT (openrl.envs.vec_env.async_venv.AsyncState 属性) denormalize() (openrl.modules.networks.utils.popart.PopArt 方法) (openrl.modules.utils.valuenorm.ValueNorm 方法) DiagGaussian (openrl.modules.networks.utils.distributions 中的类) dict_insert() (openrl.buffers.replay_data.ReplayData 方法) DictWrapper (openrl.envs.wrappers 中的类) (openrl.envs.wrappers.extra_wrappers 中的类)

disable() (openrl.envs.mpe.rendering.Attr 方法) (openrl.envs.mpe.rendering.LineStyle 方法) (openrl.envs.mpe.rendering.Transform 方法) discrete_autoregreesive_act() (在 openrl.modules.networks.utils.transformer_act 模块中) discrete_parallel_act() (在 openrl.modules.networks.utils.transformer_act 模块中) draw_circle() (openrl.envs.mpe.rendering.Viewer 方法) draw_line() (openrl.envs.mpe.rendering.Viewer 方法) draw_polygon() (openrl.envs.mpe.rendering.Viewer 方法) draw_polyline() (openrl.envs.mpe.rendering.Viewer 方法)

E

Embedding (openrl.modules.networks.utils.attention 中的类) enable() (openrl.envs.mpe.rendering.Attr 方法) (openrl.envs.mpe.rendering.Color 方法) (openrl.envs.mpe.rendering.LineStyle 方法) (openrl.envs.mpe.rendering.LineWidth 方法) (openrl.envs.mpe.rendering.Transform 方法) Encoder (openrl.modules.networks.utils.attention 中的类) EncoderLayer (openrl.modules.networks.utils.attention 中的类) entities (openrl.envs.mpe.core.World property) Entity (openrl.envs.mpe.core 中的类) EntityState (openrl.envs.mpe.core 中的类) entropy() (openrl.modules.networks.utils.distributions.FixedBernoulli 方法) (openrl.modules.networks.utils.distributions.FixedNormal 方法)

env_name (openrl.envs.vec_env.async_venv.AsyncVectorEnv property) (openrl.envs.vec_env.AsyncVectorEnv property) (openrl.envs.vec_env.base_venv.BaseVecEnv property) (openrl.envs.vec_env.sync_venv.SyncVectorEnv property) (openrl.envs.vec_env.SyncVectorEnv property) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) (openrl.envs.wrappers.base_wrapper.BaseWrapper property) (openrl.envs.wrappers.BaseWrapper property) EnvSpec (openrl.envs.mpe.multiagent_env 中的类) eval_actions() (openrl.modules.networks.policy_network.PolicyNetwork 方法) evaluate_actions() (openrl.modules.networks.policy_value_network.PolicyValueNetwork 方法) (openrl.modules.networks.utils.act.ACTLayer 方法) (openrl.modules.ppo_module.PPOModule 方法) (openrl.modules.rl_module.RLModule 方法)

F

feed_forward_critic_obs_generator() (openrl.buffers.normal_buffer.NormalReplayBuffer 方法) (openrl.buffers.NormalReplayBuffer 方法) (openrl.buffers.replay_data.ReplayData 方法) feed_forward_generator() (openrl.buffers.normal_buffer.NormalReplayBuffer 方法) (openrl.buffers.NormalReplayBuffer 方法) (openrl.buffers.replay_data.ReplayData 方法) feed_forward_generator_transformer() (openrl.buffers.replay_data.ReplayData 方法) FeedForward (openrl.modules.networks.utils.attention 中的类) FilledPolygon (openrl.envs.mpe.rendering 中的类) FixedBernoulli (openrl.modules.networks.utils.distributions 中的类) FixedCategorical (openrl.modules.networks.utils.distributions 中的类) FixedNormal (openrl.modules.networks.utils.distributions 中的类) Flatten (openrl.modules.networks.utils.cnn 中的类) (openrl.modules.networks.utils.mix 中的类) flatten() (openrl.buffers.utils.obs_data.ObsData 方法) format_obs() (openrl.envs.vec_env.sync_venv.SyncVectorEnv 方法) (openrl.envs.vec_env.SyncVectorEnv 方法) forward() (openrl.modules.networks.base_value_network.BaseValueNetwork 方法) (openrl.modules.networks.policy_network.PolicyNetwork 方法) (openrl.modules.networks.utils.act.ACTLayer 方法) (openrl.modules.networks.utils.attention.CatSelfEmbedding 方法) (openrl.modules.networks.utils.attention.Embedding 方法) (openrl.modules.networks.utils.attention.Encoder 方法) (openrl.modules.networks.utils.attention.EncoderLayer 方法) (openrl.modules.networks.utils.attention.FeedForward 方法) (openrl.modules.networks.utils.attention.MultiHeadAttention 方法) (openrl.modules.networks.utils.cnn.CNNBase 方法) (openrl.modules.networks.utils.cnn.CNNLayer 方法) (openrl.modules.networks.utils.cnn.Flatten 方法) (openrl.modules.networks.utils.distributions.AddBias 方法) (openrl.modules.networks.utils.distributions.Bernoulli 方法) (openrl.modules.networks.utils.distributions.Categorical 方法) (openrl.modules.networks.utils.distributions.DiagGaussian 方法) (openrl.modules.networks.utils.mix.Flatten 方法) (openrl.modules.networks.utils.mix.MIXBase 方法) (openrl.modules.networks.utils.mlp.CONVLayer 方法) (openrl.modules.networks.utils.mlp.MLPBase 方法) (openrl.modules.networks.utils.mlp.MLPLayer 方法) (openrl.modules.networks.utils.popart.PopArt 方法) (openrl.modules.networks.utils.rnn.RNNLayer 方法) (openrl.modules.networks.value_network.ValueNetwork 方法)

forward_original() (openrl.modules.networks.policy_network.PolicyNetwork 方法)

G

Geom (openrl.envs.mpe.rendering 中的类) get_actions() (openrl.modules.networks.policy_value_network.PolicyValueNetwork 方法) (openrl.modules.ppo_module.PPOModule 方法) (openrl.modules.rl_module.RLModule 方法) get_array() (openrl.envs.mpe.rendering.Viewer 方法) get_attr() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) get_batch_data() (openrl.buffers.replay_data.ReplayData 方法) get_clones() (在 openrl.modules.networks.utils.util 模块中) get_critic_obs() (在 openrl.buffers.utils.util 模块中) get_critic_obs_space() (在 openrl.buffers.utils.util 模块中) get_critic_value_normalizer() (openrl.modules.ppo_module.PPOModule 方法) (openrl.modules.rl_module.RLModule 方法) get_display() (在 openrl.envs.mpe.rendering 模块中) get_entity_collision_force() (openrl.envs.mpe.core.World 方法) get_gard_norm() (在 openrl.modules.utils.util 模块中) get_gpu() (openrl.supports.opengpu.manager.LocalGPUManager 方法) get_gpu_info() (openrl.supports.opengpu.manager.RemoteGPUManager 方法) get_learner_gpu() (openrl.supports.opengpu.manager.LocalGPUManager 方法) get_learner_gpus() (openrl.supports.opengpu.manager.LocalGPUManager 方法)

get_local_GPU_info() (在 openrl.supports.opengpu.gpu_info 模块中) get_obs() (在 openrl.buffers.utils.util 模块中) get_policy_obs() (在 openrl.buffers.utils.util 模块中) get_policy_obs_space() (在 openrl.buffers.utils.util 模块中) get_policy_values() (openrl.modules.networks.policy_network.PolicyNetwork 方法) get_probs() (openrl.modules.networks.utils.act.ACTLayer 方法) get_remote_GPU_info() (在 openrl.supports.opengpu.gpu_info 模块中) get_reward_class() (openrl.rewards.RewardFactory 静态方法) get_shape_from_act_space() (在 openrl.buffers.utils.util 模块中) get_shape_from_obs_space_v2() (在 openrl.buffers.utils.util 模块中) get_system_info() (在 openrl.utils.util 模块中) get_values() (openrl.modules.networks.policy_value_network.PolicyValueNetwork 方法) (openrl.modules.ppo_module.PPOModule 方法) (openrl.modules.rl_module.RLModule 方法) get_vec_info_class() (openrl.envs.vec_env.vec_info.VecInfoFactory 静态方法) get_wall_collision_force() (openrl.envs.mpe.core.World 方法) get_worker_gpu() (openrl.supports.opengpu.manager.LocalGPUManager 方法) GIFWrapper (openrl.envs.wrappers 中的类) (openrl.envs.wrappers.extra_wrappers 中的类) gpu_id (openrl.supports.opengpu.gpu_info.GPUInfo 属性) GPUInfo (openrl.supports.opengpu.gpu_info 中的类)

H

has_auto_reset (openrl.envs.wrappers.AutoReset property) (openrl.envs.wrappers.base_wrapper.BaseWrapper property) (openrl.envs.wrappers.BaseWrapper property) (openrl.envs.wrappers.extra_wrappers.AutoReset property)

huber_loss() (在 openrl.modules.utils.util 模块中)

I

id (openrl.envs.mpe.multiagent_env.EnvSpec 属性) Image (openrl.envs.mpe.rendering 中的类) imshow() (openrl.envs.mpe.rendering.SimpleImageViewer 方法) info() (openrl.envs.mpe.scenario.BaseScenario 方法) (openrl.utils.logger.Logger 方法) init() (在 openrl.modules.networks.utils.util 模块中) init_buffer() (openrl.buffers.normal_buffer.NormalReplayBuffer 方法) (openrl.buffers.NormalReplayBuffer 方法) (openrl.buffers.replay_data.ReplayData 方法)

init_rnn_states() (openrl.modules.ppo_module.PPOModule 静态方法) insert() (openrl.buffers.normal_buffer.NormalReplayBuffer 方法) (openrl.buffers.NormalReplayBuffer 方法) (openrl.buffers.replay_data.ReplayData 方法) integrate_state() (openrl.envs.mpe.core.World 方法) is_collision() (openrl.envs.mpe.scenarios.simple_spread.Scenario 方法) iterate_action() (在 openrl.envs.vec_env.utils.numpy_utils 模块中)

L

Landmark (openrl.envs.mpe.core 中的类) learner_update() (openrl.drivers.onpolicy_driver.OnPolicyDriver 方法) Line (openrl.envs.mpe.rendering 中的类) LineStyle (openrl.envs.mpe.rendering 中的类) LineWidth (openrl.envs.mpe.rendering 中的类) load() (openrl.runners.common.base_agent.BaseAgent 方法) (openrl.runners.common.chat_agent.ChatAgent 类方法) (openrl.runners.common.ChatAgent 类方法) (openrl.runners.common.ppo_agent.PPOAgent 方法) (openrl.runners.common.PPOAgent 方法) (在 openrl.envs.mpe.scenarios 模块中) load_policy() (openrl.modules.common.ppo_net.PPONet 方法) (openrl.modules.common.PPONet 方法) (openrl.modules.rl_module.RLModule 方法) (openrl.runners.common.ppo_agent.PPOAgent 方法) (openrl.runners.common.PPOAgent 方法)

LocalGPUManager (openrl.supports.opengpu.manager 中的类) log_info() (openrl.supports.opengpu.manager.LocalGPUManager 方法) (openrl.utils.logger.Logger 方法) log_learner_info() (openrl.utils.logger.Logger 方法) log_probs() (openrl.modules.networks.utils.distributions.FixedBernoulli 方法) (openrl.modules.networks.utils.distributions.FixedCategorical 方法) (openrl.modules.networks.utils.distributions.FixedNormal 方法) Logger (openrl.utils.logger 中的类) lr_decay() (openrl.modules.base_module.BaseModule 方法) (openrl.modules.ppo_module.PPOModule 方法)

M

make() (在 openrl.envs.common 模块中) (在 openrl.envs.common.registration 模块中) (在 openrl.envs.mpe.mpe_env 模块中) make_capsule() (在 openrl.envs.mpe.rendering 模块中) make_circle() (在 openrl.envs.mpe.rendering 模块中) make_gym_envs() (在 openrl.envs.gymnasium 模块中) make_mpe_envs() (在 openrl.envs.mpe 模块中) make_polygon() (在 openrl.envs.mpe.rendering 模块中) make_polyline() (在 openrl.envs.mpe.rendering 模块中) make_world() (openrl.envs.mpe.scenario.BaseScenario 方法) (openrl.envs.mpe.scenarios.simple_spread.Scenario 方法) mass (openrl.envs.mpe.core.Entity property) memory_free (openrl.supports.opengpu.gpu_info.GPUInfo 属性) memory_total (openrl.supports.opengpu.gpu_info.GPUInfo 属性) memory_used (openrl.supports.opengpu.gpu_info.GPUInfo 属性)

metadata (openrl.envs.mpe.multiagent_env.MultiAgentEnv 属性) (openrl.envs.vec_env.base_venv.BaseVecEnv 属性) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) MIXBase (openrl.modules.networks.utils.mix 中的类) MLPBase (openrl.modules.networks.utils.mlp 中的类) MLPLayer (openrl.modules.networks.utils.mlp 中的类) mode() (openrl.modules.networks.utils.distributions.FixedBernoulli 方法) (openrl.modules.networks.utils.distributions.FixedCategorical 方法) (openrl.modules.networks.utils.distributions.FixedNormal 方法) ModelConfig (openrl.modules.model_config 中的类) ModelTrainConfig (openrl.modules.model_config 中的类) mse_loss() (在 openrl.modules.utils.util 模块中) MultiAgentEnv (openrl.envs.mpe.multiagent_env 中的类) MultiDiscrete (openrl.envs.mpe.multi_discrete 中的类) MultiHeadAttention (openrl.modules.networks.utils.attention 中的类)

N

naive_recurrent_generator() (openrl.buffers.normal_buffer.NormalReplayBuffer 方法) (openrl.buffers.NormalReplayBuffer 方法) (openrl.buffers.replay_data.ReplayData 方法) name (openrl.envs.mpe.core.World 属性) nest_expand_dim() (在 openrl.envs.wrappers.util 模块中)

NLPVecInfo (openrl.envs.vec_env.vec_info.nlp_vec_info 中的类) normalize() (openrl.modules.networks.utils.popart.PopArt 方法) (openrl.modules.utils.valuenorm.ValueNorm 方法) NormalReplayBuffer (openrl.buffers 中的类) (openrl.buffers.normal_buffer 中的类) np_random (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property)

O

ObsData (openrl.buffers.utils.obs_data 中的类) observation() (openrl.envs.mpe.scenarios.simple_spread.Scenario 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VectorObservationWrapper 方法) (openrl.envs.wrappers.DictWrapper 方法) (openrl.envs.wrappers.extra_wrappers.DictWrapper 方法) observation_space (openrl.envs.vec_env.base_venv.BaseVecEnv 属性) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) OnPolicyDriver (openrl.drivers.onpolicy_driver 中的类) openrl.algorithms 模块 openrl.algorithms.base_algorithm 模块 openrl.algorithms.ppo 模块 openrl.buffers 模块 openrl.buffers.normal_buffer 模块 openrl.buffers.replay_data 模块 openrl.buffers.utils 模块 openrl.buffers.utils.obs_data 模块 openrl.buffers.utils.util 模块 openrl.cli 模块 openrl.cli.cli 模块 openrl.cli.train 模块 openrl.configs 模块 openrl.configs.config 模块 openrl.drivers 模块 openrl.drivers.base_driver 模块 openrl.drivers.onpolicy_driver 模块 openrl.drivers.rl_driver 模块 openrl.envs 模块 openrl.envs.common 模块 openrl.envs.common.build_envs 模块 openrl.envs.common.registration 模块 openrl.envs.gymnasium 模块 openrl.envs.mpe 模块 openrl.envs.mpe.core 模块 openrl.envs.mpe.mpe_env 模块 openrl.envs.mpe.multi_discrete 模块 openrl.envs.mpe.multiagent_env 模块 openrl.envs.mpe.rendering 模块 openrl.envs.mpe.scenario 模块 openrl.envs.mpe.scenarios 模块 openrl.envs.mpe.scenarios.simple_spread 模块 openrl.envs.vec_env 模块 openrl.envs.vec_env.async_venv 模块 openrl.envs.vec_env.base_venv 模块 openrl.envs.vec_env.sync_venv 模块 openrl.envs.vec_env.utils 模块 openrl.envs.vec_env.utils.numpy_utils 模块 openrl.envs.vec_env.utils.share_memory 模块 openrl.envs.vec_env.utils.util 模块 openrl.envs.vec_env.vec_info 模块 openrl.envs.vec_env.vec_info.base_vec_info 模块 openrl.envs.vec_env.vec_info.nlp_vec_info 模块 openrl.envs.vec_env.vec_info.simple_vec_info 模块 openrl.envs.vec_env.wrappers 模块 openrl.envs.vec_env.wrappers.base_wrapper 模块 openrl.envs.vec_env.wrappers.reward_wrapper 模块 openrl.envs.vec_env.wrappers.vec_monitor_wrapper 模块

openrl.envs.wrappers 模块 openrl.envs.wrappers.base_wrapper 模块 openrl.envs.wrappers.extra_wrappers 模块 openrl.envs.wrappers.multiagent_wrapper 模块 openrl.envs.wrappers.util 模块 openrl.modules 模块 openrl.modules.base_module 模块 openrl.modules.common 模块 openrl.modules.common.base_net 模块 openrl.modules.common.ppo_net 模块 openrl.modules.model_config 模块 openrl.modules.networks 模块 openrl.modules.networks.base_policy_network 模块 openrl.modules.networks.base_value_network 模块 openrl.modules.networks.policy_network 模块 openrl.modules.networks.policy_value_network 模块 openrl.modules.networks.utils 模块 openrl.modules.networks.utils.act 模块 openrl.modules.networks.utils.attention 模块 openrl.modules.networks.utils.cnn 模块 openrl.modules.networks.utils.distributed_utils 模块 openrl.modules.networks.utils.distributions 模块 openrl.modules.networks.utils.mix 模块 openrl.modules.networks.utils.mlp 模块 openrl.modules.networks.utils.nlp 模块 openrl.modules.networks.utils.popart 模块 openrl.modules.networks.utils.rnn 模块 openrl.modules.networks.utils.transformer_act 模块 openrl.modules.networks.utils.util 模块 openrl.modules.networks.value_network 模块 openrl.modules.ppo_module 模块 openrl.modules.rl_module 模块 openrl.modules.utils 模块 openrl.modules.utils.util 模块 openrl.modules.utils.valuenorm 模块 openrl.rewards 模块 openrl.rewards.base_reward 模块 openrl.runners 模块 openrl.runners.common 模块 openrl.runners.common.base_agent 模块 openrl.runners.common.chat_agent 模块 openrl.runners.common.ppo_agent 模块 openrl.supports 模块 openrl.supports.opendata 模块 openrl.supports.opendata.utils 模块 openrl.supports.opengpu 模块 openrl.supports.opengpu.gpu_info 模块 openrl.supports.opengpu.manager 模块 openrl.utils 模块 openrl.utils.logger 模块 openrl.utils.util 模块 output_size (openrl.modules.networks.utils.cnn.CNNBase property) (openrl.modules.networks.utils.mix.MIXBase property) (openrl.modules.networks.utils.mlp.MLPBase property)

P

parallel_env_num (openrl.envs.vec_env.base_venv.BaseVecEnv 属性) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) Point (openrl.envs.mpe.rendering 中的类) policy_agents (openrl.envs.mpe.core.World property) PolicyNetwork (openrl.modules.networks.policy_network 中的类) PolicyValueNetwork (openrl.modules.networks.policy_value_network 中的类) PolyLine (openrl.envs.mpe.rendering 中的类) PopArt (openrl.modules.networks.utils.popart 中的类) ppo_update() (openrl.algorithms.ppo.PPOAlgorithm 方法) PPOAgent (openrl.runners.common 中的类) (openrl.runners.common.ppo_agent 中的类)

PPOAlgorithm (openrl.algorithms.ppo 中的类) PPOModule (openrl.modules.ppo_module 中的类) PPONet (openrl.modules.common 中的类) (openrl.modules.common.ppo_net 中的类) prep_rollout() (openrl.algorithms.base_algorithm.BaseAlgorithm 方法) prep_training() (openrl.algorithms.base_algorithm.BaseAlgorithm 方法) prepare_input() (openrl.buffers.utils.obs_data.ObsData 静态方法) prepare_loss() (openrl.algorithms.ppo.PPOAlgorithm 方法) preserve_decimal() (在 openrl.supports.opengpu.gpu_info 模块中) print_system_info() (在 openrl.cli.cli 模块中) print_version() (在 openrl.cli.cli 模块中) product_name (openrl.supports.opengpu.gpu_info.GPUInfo 属性)

R

random_action() (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper 方法) read_from_shared_memory() (在 openrl.envs.vec_env.utils.share_memory 模块中) real_id (openrl.supports.opengpu.gpu_info.GPUInfo 属性) recurrent_generator() (openrl.buffers.normal_buffer.NormalReplayBuffer 方法) (openrl.buffers.NormalReplayBuffer 方法) (openrl.buffers.replay_data.ReplayData 方法) recurrent_generator_v2() (openrl.buffers.replay_data.ReplayData 方法) recurrent_generator_v3() (openrl.buffers.replay_data.ReplayData 方法) red() (在 openrl.cli.cli 模块中) reduce_tensor() (在 openrl.modules.networks.utils.distributed_utils 模块中) register() (openrl.envs.vec_env.vec_info.VecInfoFactory 静态方法) (openrl.rewards.RewardFactory 静态方法) RemoteGPUManager (openrl.supports.opengpu.manager 中的类) RemoveTruncated (openrl.envs.wrappers 中的类) (openrl.envs.wrappers.extra_wrappers 中的类) render() (openrl.envs.mpe.multiagent_env.MultiAgentEnv 方法) (openrl.envs.mpe.rendering.Geom 方法) (openrl.envs.mpe.rendering.Viewer 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) render1() (openrl.envs.mpe.rendering.Compound 方法) (openrl.envs.mpe.rendering.FilledPolygon 方法) (openrl.envs.mpe.rendering.Geom 方法) (openrl.envs.mpe.rendering.Image 方法) (openrl.envs.mpe.rendering.Line 方法) (openrl.envs.mpe.rendering.Point 方法) (openrl.envs.mpe.rendering.PolyLine 方法) render_mode (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) ReplayData (openrl.buffers.replay_data 中的类) reset() (openrl.envs.mpe.multiagent_env.MultiAgentEnv 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.vec_info.base_vec_info.BaseVecInfo 方法) (openrl.envs.vec_env.vec_info.nlp_vec_info.NLPVecInfo 方法) (openrl.envs.vec_env.vec_info.simple_vec_info.SimpleVecInfo 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VectorObservationWrapper 方法) (openrl.envs.wrappers.extra_wrappers.GIFWrapper 方法) (openrl.envs.wrappers.GIFWrapper 方法) (openrl.envs.wrappers.multiagent_wrapper.Single2MultiAgentWrapper 方法) (openrl.envs.wrappers.Single2MultiAgentWrapper 方法) (openrl.modules.common.ppo_net.PPONet 方法) (openrl.modules.common.PPONet 方法)

reset_and_buffer_init() (openrl.drivers.onpolicy_driver.OnPolicyDriver 方法) reset_fetch() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) reset_parameters() (openrl.modules.networks.utils.popart.PopArt 方法) (openrl.modules.utils.valuenorm.ValueNorm 方法) reset_send() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) reset_world() (openrl.envs.mpe.scenario.BaseScenario 方法) (openrl.envs.mpe.scenarios.simple_spread.Scenario 方法) restore() (openrl.modules.base_module.BaseModule 方法) (openrl.modules.rl_module.RLModule 方法) reward() (openrl.envs.mpe.scenarios.simple_spread.Scenario 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VectorRewardWrapper 方法) reward_range (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) RewardFactory (openrl.rewards 中的类) RewardWrapper (openrl.envs.vec_env 中的类) (openrl.envs.vec_env.wrappers.reward_wrapper 中的类) RLDriver (openrl.drivers.rl_driver 中的类) RLModule (openrl.modules.rl_module 中的类) rnn_forward() (openrl.modules.networks.utils.rnn.RNNLayer 方法) RNNLayer (openrl.modules.networks.utils.rnn 中的类) run() (openrl.drivers.base_driver.BaseDriver 方法) (openrl.drivers.onpolicy_driver.OnPolicyDriver 方法) running_mean_var() (openrl.modules.utils.valuenorm.ValueNorm 方法)

S

sample() (openrl.envs.mpe.multi_discrete.MultiDiscrete 方法) (openrl.modules.networks.utils.distributions.FixedCategorical 方法) save() (openrl.modules.base_module.BaseModule 方法) (openrl.modules.rl_module.RLModule 方法) (openrl.runners.common.base_agent.BaseAgent 方法) (openrl.runners.common.chat_agent.ChatAgent 方法) (openrl.runners.common.ChatAgent 方法) (openrl.runners.common.ppo_agent.PPOAgent 方法) (openrl.runners.common.PPOAgent 方法) ScaledDotProductAttention() (在 openrl.modules.networks.utils.attention 模块中) Scenario (openrl.envs.mpe.scenarios.simple_spread 中的类) scripted_agents (openrl.envs.mpe.core.World property) seed() (openrl.envs.mpe.multiagent_env.MultiAgentEnv 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.sync_venv.SyncVectorEnv 方法) (openrl.envs.vec_env.SyncVectorEnv 方法) set_attr() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.sync_venv.SyncVectorEnv 方法) (openrl.envs.vec_env.SyncVectorEnv 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper 方法) set_bounds() (openrl.envs.mpe.rendering.Viewer 方法) set_color() (openrl.envs.mpe.rendering.Geom 方法) set_env() (openrl.runners.common.ppo_agent.PPOAgent 方法) (openrl.runners.common.PPOAgent 方法) set_linewidth() (openrl.envs.mpe.rendering.PolyLine 方法) set_rotation() (openrl.envs.mpe.rendering.Transform 方法) set_scale() (openrl.envs.mpe.rendering.Transform 方法) set_seed() (在 openrl.utils.util 模块中) set_translation() (openrl.envs.mpe.rendering.Transform 方法) shape (openrl.envs.mpe.multi_discrete.MultiDiscrete property) SimpleImageViewer (openrl.envs.mpe.rendering 中的类) SimpleVecInfo (openrl.envs.vec_env.vec_info.simple_vec_info 中的类)

Single2MultiAgentWrapper (openrl.envs.wrappers 中的类) (openrl.envs.wrappers.multiagent_wrapper 中的类) spec (openrl.envs.mpe.multiagent_env.MultiAgentEnv 属性) split_obs() (在 openrl.modules.networks.utils.attention 模块中) statistics() (openrl.envs.vec_env.vec_info.base_vec_info.BaseVecInfo 方法) (openrl.envs.vec_env.vec_info.nlp_vec_info.NLPVecInfo 方法) (openrl.envs.vec_env.vec_info.simple_vec_info.SimpleVecInfo 方法) (openrl.envs.vec_env.VecMonitorWrapper 方法) (openrl.envs.vec_env.wrappers.vec_monitor_wrapper.VecMonitorWrapper 方法) step() (openrl.envs.mpe.core.World 方法) (openrl.envs.mpe.multiagent_env.MultiAgentEnv 方法) (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) (openrl.envs.vec_env.RewardWrapper 方法) (openrl.envs.vec_env.VecMonitorWrapper 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VectorActionWrapper 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VectorObservationWrapper 方法) (openrl.envs.vec_env.wrappers.base_wrapper.VectorRewardWrapper 方法) (openrl.envs.vec_env.wrappers.reward_wrapper.RewardWrapper 方法) (openrl.envs.vec_env.wrappers.vec_monitor_wrapper.VecMonitorWrapper 方法) (openrl.envs.wrappers.base_wrapper.BaseWrapper 方法) (openrl.envs.wrappers.BaseWrapper 方法) (openrl.envs.wrappers.extra_wrappers.GIFWrapper 方法) (openrl.envs.wrappers.GIFWrapper 方法) (openrl.envs.wrappers.multiagent_wrapper.Single2MultiAgentWrapper 方法) (openrl.envs.wrappers.Single2MultiAgentWrapper 方法) step_batch() (openrl.buffers.utils.obs_data.ObsData 方法) step_fetch() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) step_flatten() (openrl.buffers.utils.obs_data.ObsData 方法) step_reward() (openrl.rewards.base_reward.BaseReward 方法) step_send() (openrl.envs.vec_env.async_venv.AsyncVectorEnv 方法) (openrl.envs.vec_env.AsyncVectorEnv 方法) SyncVectorEnv (openrl.envs.vec_env 中的类) (openrl.envs.vec_env.sync_venv 中的类)

T

tile_images() (在 openrl.envs.vec_env.utils.util 模块中) to_single_np() (openrl.algorithms.ppo.PPOAlgorithm 方法) train() (openrl.algorithms.base_algorithm.BaseAlgorithm 方法) (openrl.algorithms.ppo.PPOAlgorithm 方法) (openrl.runners.common.ppo_agent.PPOAgent 方法) (openrl.runners.common.PPOAgent 方法)

train_agent() (在 openrl.cli.train 模块中) Transform (openrl.envs.mpe.rendering 中的类)

U

unwrapped (openrl.envs.vec_env.base_venv.BaseVecEnv property) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) update() (openrl.modules.networks.utils.popart.PopArt 方法) (openrl.modules.utils.valuenorm.ValueNorm 方法) update_agent_state() (openrl.envs.mpe.core.World 方法)

update_linear_schedule() (在 openrl.modules.utils.util 模块中) use_monitor (openrl.envs.vec_env.VecMonitorWrapper property) (openrl.envs.vec_env.wrappers.base_wrapper.VecEnvWrapper property) (openrl.envs.vec_env.wrappers.vec_monitor_wrapper.VecMonitorWrapper property) (openrl.envs.wrappers.base_wrapper.BaseWrapper property) (openrl.envs.wrappers.BaseWrapper property)

V

ValueNetwork (openrl.modules.networks.value_network 中的类) ValueNorm (openrl.modules.utils.valuenorm 中的类) VecEnvWrapper (openrl.envs.vec_env.wrappers.base_wrapper 中的类) VecInfoFactory (openrl.envs.vec_env.vec_info 中的类) VecMonitorWrapper (openrl.envs.vec_env 中的类) (openrl.envs.vec_env.wrappers.vec_monitor_wrapper 中的类)

vector_render() (openrl.envs.vec_env.base_venv.BaseVecEnv 方法) VectorActionWrapper (openrl.envs.vec_env.wrappers.base_wrapper 中的类) VectorObservationWrapper (openrl.envs.vec_env.wrappers.base_wrapper 中的类) VectorRewardWrapper (openrl.envs.vec_env.wrappers.base_wrapper 中的类) Viewer (openrl.envs.mpe.rendering 中的类)

W

WAITING_CALL (openrl.envs.vec_env.async_venv.AsyncState 属性) WAITING_RESET (openrl.envs.vec_env.async_venv.AsyncState 属性) WAITING_STEP (openrl.envs.vec_env.async_venv.AsyncState 属性)

Wall (openrl.envs.mpe.core 中的类) window_closed_by_user() (openrl.envs.mpe.rendering.Viewer 方法) World (openrl.envs.mpe.core 中的类) write_to_shared_memory() (在 openrl.envs.vec_env.utils.share_memory 模块中)

模

模块 openrl.algorithms openrl.algorithms.base_algorithm openrl.algorithms.ppo openrl.buffers openrl.buffers.normal_buffer openrl.buffers.replay_data openrl.buffers.utils openrl.buffers.utils.obs_data openrl.buffers.utils.util openrl.cli openrl.cli.cli openrl.cli.train openrl.configs openrl.configs.config openrl.drivers openrl.drivers.base_driver openrl.drivers.onpolicy_driver openrl.drivers.rl_driver openrl.envs openrl.envs.common openrl.envs.common.build_envs openrl.envs.common.registration openrl.envs.gymnasium openrl.envs.mpe openrl.envs.mpe.core openrl.envs.mpe.mpe_env openrl.envs.mpe.multi_discrete openrl.envs.mpe.multiagent_env openrl.envs.mpe.rendering openrl.envs.mpe.scenario openrl.envs.mpe.scenarios openrl.envs.mpe.scenarios.simple_spread openrl.envs.vec_env openrl.envs.vec_env.async_venv openrl.envs.vec_env.base_venv openrl.envs.vec_env.sync_venv openrl.envs.vec_env.utils openrl.envs.vec_env.utils.numpy_utils openrl.envs.vec_env.utils.share_memory openrl.envs.vec_env.utils.util openrl.envs.vec_env.vec_info openrl.envs.vec_env.vec_info.base_vec_info openrl.envs.vec_env.vec_info.nlp_vec_info openrl.envs.vec_env.vec_info.simple_vec_info openrl.envs.vec_env.wrappers openrl.envs.vec_env.wrappers.base_wrapper openrl.envs.vec_env.wrappers.reward_wrapper openrl.envs.vec_env.wrappers.vec_monitor_wrapper openrl.envs.wrappers openrl.envs.wrappers.base_wrapper openrl.envs.wrappers.extra_wrappers openrl.envs.wrappers.multiagent_wrapper openrl.envs.wrappers.util openrl.modules openrl.modules.base_module openrl.modules.common openrl.modules.common.base_net openrl.modules.common.ppo_net openrl.modules.model_config openrl.modules.networks openrl.modules.networks.base_policy_network openrl.modules.networks.base_value_network openrl.modules.networks.policy_network openrl.modules.networks.policy_value_network openrl.modules.networks.utils openrl.modules.networks.utils.act openrl.modules.networks.utils.attention openrl.modules.networks.utils.cnn openrl.modules.networks.utils.distributed_utils openrl.modules.networks.utils.distributions openrl.modules.networks.utils.mix openrl.modules.networks.utils.mlp openrl.modules.networks.utils.nlp openrl.modules.networks.utils.popart openrl.modules.networks.utils.rnn openrl.modules.networks.utils.transformer_act openrl.modules.networks.utils.util openrl.modules.networks.value_network openrl.modules.ppo_module openrl.modules.rl_module openrl.modules.utils openrl.modules.utils.util openrl.modules.utils.valuenorm openrl.rewards openrl.rewards.base_reward openrl.runners openrl.runners.common openrl.runners.common.base_agent openrl.runners.common.chat_agent openrl.runners.common.ppo_agent openrl.supports openrl.supports.opendata openrl.supports.opendata.utils openrl.supports.opengpu openrl.supports.opengpu.gpu_info openrl.supports.opengpu.manager openrl.utils openrl.utils.logger openrl.utils.util