Index

_

__init__() (torchrl.modules.mcts.EXP3Score method) (torchrl.modules.mcts.MCTSScore method) (torchrl.modules.mcts.MCTSScores method) (torchrl.modules.mcts.PUCTScore method) (torchrl.modules.mcts.UCB1TunedScore method) (torchrl.modules.mcts.UCBScore method) _get_server_weights() (torchrl.collectors.distributed.DistributedWeightUpdater method) (torchrl.collectors.distributed.RPCWeightUpdater method) (torchrl.collectors.llm.vLLMUpdater method) (torchrl.collectors.RayWeightUpdater method)

_maybe_map_weights() (torchrl.collectors.distributed.DistributedWeightUpdater method) (torchrl.collectors.distributed.RPCWeightUpdater method) (torchrl.collectors.llm.vLLMUpdater method) (torchrl.collectors.RayWeightUpdater method) _setup() (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.ThreadingAsyncEnvPool method) _skip_update() (torchrl.collectors.RayWeightUpdater method) _sync_weights_with_worker() (torchrl.collectors.distributed.DistributedWeightUpdater method) (torchrl.collectors.distributed.RPCWeightUpdater method) (torchrl.collectors.llm.vLLMUpdater method) (torchrl.collectors.RayWeightUpdater method)

A

A2CLoss (class in torchrl.objectives) action_key (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) action_keys (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) action_spec (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) action_spec_unbatched (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) ActionDiscretizer (class in torchrl.envs.transforms) ActionDiscretizer.SamplingStrategy (class in torchrl.envs.transforms) ActionDiscretizerConfig (class in torchrl.trainers.algorithms.configs.transforms) ActionMask (class in torchrl.envs.transforms) ActionMaskConfig (class in torchrl.trainers.algorithms.configs.transforms) Actor (class in torchrl.modules.tensordict_module) actor_loss() (torchrl.objectives.CrossQLoss method) (torchrl.objectives.TD3BCLoss method) ActorCriticOperator (class in torchrl.modules) ActorCriticWrapper (class in torchrl.modules) ActorValueOperator (class in torchrl.modules) AdadeltaConfig (class in torchrl.trainers.algorithms.configs.utils) AdagradConfig (class in torchrl.trainers.algorithms.configs.utils) AdamaxConfig (class in torchrl.trainers.algorithms.configs.utils) AdamConfig (class in torchrl.trainers.algorithms.configs.utils) AdamWConfig (class in torchrl.trainers.algorithms.configs.utils) add() (torchrl.data.datasets.AtariDQNExperienceReplay method) (torchrl.data.datasets.D4RLExperienceReplay method) (torchrl.data.datasets.GenDGRLExperienceReplay method) (torchrl.data.datasets.MinariExperienceReplay method) (torchrl.data.datasets.OpenMLExperienceReplay method) (torchrl.data.datasets.OpenXExperienceReplay method) (torchrl.data.datasets.RobosetExperienceReplay method) (torchrl.data.datasets.VD4RLExperienceReplay method) (torchrl.data.PrioritizedReplayBuffer method) (torchrl.data.RayReplayBuffer method) (torchrl.data.RemoteTensorDictReplayBuffer method) (torchrl.data.replay_buffers.ImmutableDatasetWriter method) (torchrl.data.replay_buffers.RoundRobinWriter method) (torchrl.data.replay_buffers.TensorDictMaxValueWriter method) (torchrl.data.replay_buffers.TensorDictRoundRobinWriter method) (torchrl.data.replay_buffers.Writer method) (torchrl.data.replay_buffers.WriterEnsemble method) (torchrl.data.ReplayBuffer method) (torchrl.data.ReplayBufferEnsemble method) (torchrl.data.TensorDictPrioritizedReplayBuffer method) (torchrl.data.TensorDictReplayBuffer method) add_chat_template (class in torchrl.data.llm) add_collectors() (torchrl.collectors.distributed.RayCollector method) add_module() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) add_random_module (class in torchrl.objectives) add_truncated_keys() (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.envs.transforms.TransformedEnv method) AdditiveGaussianModule (class in torchrl.modules) AddThinkingPrompt (class in torchrl.envs.llm.transforms) all_actions() (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) all_done_keys (torchrl.envs.transforms.StepCounter property) all_truncated_keys (torchrl.envs.transforms.StepCounter property) all_worker_ids() (torchrl.collectors.distributed.DistributedWeightUpdater method), [1] (torchrl.collectors.distributed.RPCWeightUpdater method), [1] (torchrl.collectors.llm.vLLMUpdater method), [1] (torchrl.collectors.llm.vLLMUpdaterV2 method) (torchrl.collectors.MultiProcessedWeightUpdater method) (torchrl.collectors.RayWeightUpdater method), [1] (torchrl.collectors.VanillaWeightUpdater method) (torchrl.collectors.WeightUpdaterBase method) alpha_loss() (torchrl.objectives.CrossQLoss method) (torchrl.objectives.DiscreteSACLoss method) (torchrl.objectives.SACLoss method)

any_done() (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) append() (torchrl.data.llm.History method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.transforms.Compose method) append_transform() (torchrl.data.datasets.AtariDQNExperienceReplay method) (torchrl.data.datasets.D4RLExperienceReplay method) (torchrl.data.datasets.GenDGRLExperienceReplay method) (torchrl.data.datasets.MinariExperienceReplay method) (torchrl.data.datasets.OpenMLExperienceReplay method) (torchrl.data.datasets.OpenXExperienceReplay method) (torchrl.data.datasets.RobosetExperienceReplay method) (torchrl.data.datasets.VD4RLExperienceReplay method) (torchrl.data.PrioritizedReplayBuffer method) (torchrl.data.RayReplayBuffer method) (torchrl.data.RemoteTensorDictReplayBuffer method) (torchrl.data.ReplayBuffer method) (torchrl.data.ReplayBufferEnsemble method) (torchrl.data.TensorDictPrioritizedReplayBuffer method) (torchrl.data.TensorDictReplayBuffer method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.envs.transforms.TransformedEnv method) apply() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) apply_chat_template() (torchrl.data.llm.History method) apply_weights() (torchrl.weight_update.DistributedWeightSyncScheme method) (torchrl.weight_update.llm.VLLMDoubleBufferSyncScheme method) (torchrl.weight_update.llm.VLLMDoubleBufferWeightReceiver method) (torchrl.weight_update.llm.VLLMWeightReceiver method) (torchrl.weight_update.llm.VLLMWeightSyncScheme method) (torchrl.weight_update.MultiProcessWeightSyncScheme method) (torchrl.weight_update.NoWeightSyncScheme method) (torchrl.weight_update.RayModuleTransformScheme method) (torchrl.weight_update.RayWeightSyncScheme method) (torchrl.weight_update.RPCWeightSyncScheme method) (torchrl.weight_update.SharedMemWeightSyncScheme method) (torchrl.weight_update.WeightStrategy method) (torchrl.weight_update.WeightSyncScheme method) as_nested_tensor (class in torchrl.envs.llm.transforms) as_padded_tensor (class in torchrl.envs.llm.transforms) as_remote() (torchrl.collectors.llm.LLMCollector class method) (torchrl.collectors.llm.RayLLMCollector class method) (torchrl.data.datasets.AtariDQNExperienceReplay class method) (torchrl.data.datasets.D4RLExperienceReplay class method) (torchrl.data.datasets.GenDGRLExperienceReplay class method) (torchrl.data.datasets.MinariExperienceReplay class method) (torchrl.data.datasets.OpenMLExperienceReplay class method) (torchrl.data.datasets.OpenXExperienceReplay class method) (torchrl.data.datasets.RobosetExperienceReplay class method) (torchrl.data.datasets.VD4RLExperienceReplay class method) (torchrl.data.PrioritizedReplayBuffer class method) (torchrl.data.RayReplayBuffer class method) (torchrl.data.RemoteTensorDictReplayBuffer class method) (torchrl.data.ReplayBuffer class method) (torchrl.data.ReplayBufferEnsemble class method) (torchrl.data.TensorDictPrioritizedReplayBuffer class method) (torchrl.data.TensorDictReplayBuffer class method) ASGDConfig (class in torchrl.trainers.algorithms.configs.utils) assert_is_in() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) async_reset_recv() (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.ThreadingAsyncEnvPool method) async_reset_send() (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.ThreadingAsyncEnvPool method) async_shutdown() (torchrl.collectors.AsyncCollector method) (torchrl.collectors.BaseCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.distributed.DistributedCollector method) (torchrl.collectors.distributed.DistributedDataCollector method) (torchrl.collectors.distributed.DistributedSyncCollector method) (torchrl.collectors.distributed.DistributedSyncDataCollector method) (torchrl.collectors.distributed.RayCollector method) (torchrl.collectors.distributed.RPCCollector method) (torchrl.collectors.distributed.RPCDataCollector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) async_step_recv() (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.ThreadingAsyncEnvPool method) async_step_send() (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.ThreadingAsyncEnvPool method) AsyncCollector (class in torchrl.collectors) AsyncCollectorConfig (class in torchrl.trainers.algorithms.configs.collectors) AsyncEnvPool (class in torchrl.envs) AsyncVLLM (class in torchrl.modules.llm) AtariDQNExperienceReplay (class in torchrl.data.datasets) attach() (torchrl.data.replay_buffers.CompressedListStorage method) (torchrl.data.replay_buffers.LazyMemmapStorage method) (torchrl.data.replay_buffers.LazyStackStorage method) (torchrl.data.replay_buffers.LazyTensorStorage method) (torchrl.data.replay_buffers.ListStorage method) (torchrl.data.replay_buffers.Storage method) (torchrl.data.replay_buffers.StorageEnsemble method) (torchrl.data.replay_buffers.TensorStorage method) auto_register_info_dict() (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.MLGymWrapper method) auto_specs_() (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) auto_unwrap_transformed_env (class in torchrl) AutoResetEnv (class in torchrl.envs.transforms) AutoResetTransform (class in torchrl.envs.transforms) AutoResetTransformConfig (class in torchrl.trainers.algorithms.configs.transforms)

B

base_env (torchrl.envs.llm.transforms.RayDataLoadingPrimer property) BaseCollector (class in torchrl.collectors) batch_dims (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) batch_locked (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.transforms.TransformedEnv property) batch_size (torchrl.data.datasets.AtariDQNExperienceReplay property) (torchrl.data.datasets.D4RLExperienceReplay property) (torchrl.data.datasets.GenDGRLExperienceReplay property) (torchrl.data.datasets.MinariExperienceReplay property) (torchrl.data.datasets.OpenMLExperienceReplay property) (torchrl.data.datasets.OpenXExperienceReplay property) (torchrl.data.datasets.RobosetExperienceReplay property) (torchrl.data.datasets.VD4RLExperienceReplay property) (torchrl.data.PrioritizedReplayBuffer property) (torchrl.data.RayReplayBuffer property) (torchrl.data.RemoteTensorDictReplayBuffer property) (torchrl.data.ReplayBuffer property) (torchrl.data.ReplayBufferEnsemble property) (torchrl.data.TensorDictPrioritizedReplayBuffer property) (torchrl.data.TensorDictReplayBuffer property) (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) (torchrl.envs.transforms.TransformedEnv property) BatchedEnvConfig (class in torchrl.trainers.algorithms.configs.envs) batching (torchrl.modules.llm.LLMWrapperBase property) (torchrl.modules.llm.RemoteTransformersWrapper property) (torchrl.modules.llm.TransformersWrapper property) (torchrl.modules.llm.vLLMWrapper property) BatchSizeTransform (class in torchrl.envs.transforms) BatchSizeTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) BatchSubSampler (class in torchrl.trainers) bfloat16() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method)

BinarizeReward (class in torchrl.envs.transforms) BinarizeRewardConfig (class in torchrl.trainers.algorithms.configs.transforms) Binary (class in torchrl.data) Bounded (class in torchrl.data) BraxEnv() (in module torchrl.envs) BraxEnvConfig (class in torchrl.trainers.algorithms.configs.envs_libs) BraxWrapper() (in module torchrl.envs) BrowserTransform (class in torchrl.envs.llm.transforms) buffers() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) build_td_for_shared_vecnorm() (torchrl.envs.transforms.VecNorm static method) BurnInTransform (class in torchrl.envs.transforms) BurnInTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) bytes() (torchrl.data.replay_buffers.CompressedListStorage method)

C

cardinality() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) cascade_execute() (torchrl.collectors.AsyncCollector method) (torchrl.collectors.BaseCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.distributed.DistributedCollector method) (torchrl.collectors.distributed.DistributedDataCollector method) (torchrl.collectors.distributed.DistributedSyncCollector method) (torchrl.collectors.distributed.DistributedSyncDataCollector method) (torchrl.collectors.distributed.RayCollector method) (torchrl.collectors.distributed.RPCCollector method) (torchrl.collectors.distributed.RPCDataCollector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) cat() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) Categorical (class in torchrl.data) CatFrames (class in torchrl.envs.transforms) CatFramesConfig (class in torchrl.trainers.algorithms.configs.transforms) CatTensors (class in torchrl.envs.transforms) CatTensorsConfig (class in torchrl.trainers.algorithms.configs.transforms) CenterCrop (class in torchrl.envs.transforms) CenterCropConfig (class in torchrl.trainers.algorithms.configs.transforms) ChatEnv (class in torchrl.envs.llm) ChatHistory (class in torchrl.modules.llm) check_connection() (torchrl.weight_update.llm.VLLMCollectiveTransport method) (torchrl.weight_update.llm.VLLMDoubleBufferTransport method) check_env_specs() (in module torchrl.envs) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) check_marl_grouping() (in module torchrl.envs) ChessEnv (class in torchrl.envs) children() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) CISPOLoss (class in torchrl.objectives.llm) CISPOLossOutput (class in torchrl.objectives.llm) cleanup() (torchrl.data.replay_buffers.LazyMemmapStorage method) (torchrl.envs.llm.transforms.PythonExecutorService method) cleanup_batching() (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.RemoteTransformersWrapper method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) clear_device_() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) ClearCudaCache (class in torchrl.trainers) ClipPPOLoss (class in torchrl.objectives) ClipTransform (class in torchrl.envs.transforms) ClipTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) clone() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.transforms.Transform method) (torchrl.envs.transforms.VecNormV2 method) close() (torchrl.data.llm.TopKRewardSelector method) (torchrl.data.RayReplayBuffer method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.transforms.Compose method) (torchrl.envs.transforms.Transform method) (torchrl.objectives.llm.MCAdvantage method) collective_rpc() (torchrl.modules.llm.AsyncVLLM method) Collector (class in torchrl.collectors) collector (torchrl.collectors.distributed.DistributedWeightUpdater property) (torchrl.collectors.distributed.RPCWeightUpdater property) (torchrl.collectors.llm.vLLMUpdater property) (torchrl.collectors.llm.vLLMUpdaterV2 property) (torchrl.collectors.MultiProcessedWeightUpdater property) (torchrl.collectors.RayWeightUpdater property) (torchrl.collectors.VanillaWeightUpdater property) (torchrl.collectors.WeightUpdaterBase property) (torchrl.data.llm.TopKRewardSelector property) (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.GSM8KPrepareQuestion property) (torchrl.envs.llm.GSM8KRewardParser property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.IfEvalScorer property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.llm.transforms.AddThinkingPrompt property) (torchrl.envs.llm.transforms.BrowserTransform property) (torchrl.envs.llm.transforms.DataLoadingPrimer property) (torchrl.envs.llm.transforms.ExecuteToolsInOrder property) (torchrl.envs.llm.transforms.KLComputation property) (torchrl.envs.llm.transforms.KLRewardTransform property) (torchrl.envs.llm.transforms.MCPToolTransform property) (torchrl.envs.llm.transforms.PolicyVersion property) (torchrl.envs.llm.transforms.PythonInterpreter property) (torchrl.envs.llm.transforms.RayDataLoadingPrimer property) (torchrl.envs.llm.transforms.RetrieveKL property) (torchrl.envs.llm.transforms.RetrieveLogProb property) (torchrl.envs.llm.transforms.SimpleToolTransform property) (torchrl.envs.llm.transforms.TemplateTransform property) (torchrl.envs.llm.transforms.Tokenizer property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) (torchrl.envs.transforms.Transform property) (torchrl.modules.llm.LLMWrapperBase property) (torchrl.modules.llm.RemoteTransformersWrapper property) (torchrl.modules.llm.TransformersWrapper property) (torchrl.modules.llm.vLLMWrapper property) (torchrl.objectives.llm.MCAdvantage property) CollectorConfig (class in torchrl.trainers.algorithms.configs.collectors) collectors (torchrl.collectors.distributed.DistributedWeightUpdater property) (torchrl.collectors.distributed.RPCWeightUpdater property) (torchrl.collectors.llm.vLLMUpdater property) (torchrl.collectors.llm.vLLMUpdaterV2 property) (torchrl.collectors.MultiProcessedWeightUpdater property) (torchrl.collectors.RayWeightUpdater property) (torchrl.collectors.VanillaWeightUpdater property) (torchrl.collectors.WeightUpdaterBase property) compile() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method)

Compose (class in torchrl.envs.transforms) ComposeConfig (class in torchrl.trainers.algorithms.configs.transforms) Composite (class in torchrl.data) CompressedListStorage (class in torchrl.data.replay_buffers) CompressedListStorageCheckpointer (class in torchrl.data.replay_buffers) ConditionalPolicySwitch (class in torchrl.envs.transforms) ConditionalPolicySwitchConfig (class in torchrl.trainers.algorithms.configs.transforms) ConditionalSkip (class in torchrl.envs.transforms) ConditionalSkipConfig (class in torchrl.trainers.algorithms.configs.transforms) ConfigBase (class in torchrl.trainers.algorithms.configs.common) configure_parallel() (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) connect() (torchrl.weight_update.DistributedWeightSyncScheme method) (torchrl.weight_update.llm.VLLMDoubleBufferSyncScheme method) (torchrl.weight_update.llm.VLLMWeightSyncScheme method) (torchrl.weight_update.MultiProcessWeightSyncScheme method) (torchrl.weight_update.NoWeightSyncScheme method) (torchrl.weight_update.RayModuleTransformScheme method) (torchrl.weight_update.RayWeightSyncScheme method) (torchrl.weight_update.RPCWeightSyncScheme method) (torchrl.weight_update.SharedMemWeightSyncScheme method) (torchrl.weight_update.WeightSyncScheme method) connection_info_name (torchrl.weight_update.RayModuleTransformScheme property) (torchrl.weight_update.RayWeightSyncScheme property) ConsistentDropoutModule (class in torchrl.modules) container (torchrl.data.llm.TopKRewardSelector property) (torchrl.envs.llm.GSM8KPrepareQuestion property) (torchrl.envs.llm.GSM8KRewardParser property) (torchrl.envs.llm.IfEvalScorer property) (torchrl.envs.llm.transforms.AddThinkingPrompt property) (torchrl.envs.llm.transforms.BrowserTransform property) (torchrl.envs.llm.transforms.DataLoadingPrimer property) (torchrl.envs.llm.transforms.ExecuteToolsInOrder property) (torchrl.envs.llm.transforms.KLComputation property) (torchrl.envs.llm.transforms.KLRewardTransform property) (torchrl.envs.llm.transforms.MCPToolTransform property) (torchrl.envs.llm.transforms.PolicyVersion property) (torchrl.envs.llm.transforms.PythonInterpreter property) (torchrl.envs.llm.transforms.RayDataLoadingPrimer property) (torchrl.envs.llm.transforms.RetrieveKL property) (torchrl.envs.llm.transforms.RetrieveLogProb property) (torchrl.envs.llm.transforms.SimpleToolTransform property) (torchrl.envs.llm.transforms.TemplateTransform property) (torchrl.envs.llm.transforms.Tokenizer property) (torchrl.envs.transforms.Transform property) (torchrl.objectives.llm.MCAdvantage property) contains() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) ContentBase (class in torchrl.data.llm) context (torchrl.weight_update.DistributedWeightSyncScheme property) (torchrl.weight_update.llm.VLLMDoubleBufferSyncScheme property) (torchrl.weight_update.llm.VLLMWeightSyncScheme property) (torchrl.weight_update.MultiProcessWeightSyncScheme property) (torchrl.weight_update.NoWeightSyncScheme property) (torchrl.weight_update.RayModuleTransformScheme property) (torchrl.weight_update.RayWeightSyncScheme property) (torchrl.weight_update.RPCWeightSyncScheme property) (torchrl.weight_update.SharedMemWeightSyncScheme property) (torchrl.weight_update.WeightSyncScheme property) convert_to_functional() (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.SFTLoss method) (torchrl.objectives.LossModule method) ConvNet (class in torchrl.modules) ConvNetConfig (class in torchrl.trainers.algorithms.configs.modules) correct_for_frame_skip() (in module torchrl.trainers.helpers) CountFramesLog (class in torchrl.trainers) cpu() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.llm.TopKRewardSelector method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) CQLLoss (class in torchrl.objectives) create_load_balancer() (torchrl.modules.llm.AsyncVLLM method) create_receiver() (torchrl.weight_update.llm.VLLMDoubleBufferSyncScheme method) (torchrl.weight_update.llm.VLLMWeightSyncScheme method) create_sender() (torchrl.weight_update.llm.VLLMDoubleBufferSyncScheme method) (torchrl.weight_update.llm.VLLMWeightSyncScheme method) create_transport() (torchrl.weight_update.DistributedWeightSyncScheme method) (torchrl.weight_update.llm.VLLMDoubleBufferSyncScheme method) (torchrl.weight_update.llm.VLLMWeightSyncScheme method) (torchrl.weight_update.MultiProcessWeightSyncScheme method) (torchrl.weight_update.NoWeightSyncScheme method) (torchrl.weight_update.RayModuleTransformScheme method) (torchrl.weight_update.RayWeightSyncScheme method) (torchrl.weight_update.RPCWeightSyncScheme method) (torchrl.weight_update.SharedMemWeightSyncScheme method) (torchrl.weight_update.WeightSyncScheme method) Crop (class in torchrl.envs.transforms) CropConfig (class in torchrl.trainers.algorithms.configs.transforms) CrossQLoss (class in torchrl.objectives) CSVLogger() (in module torchrl.record.loggers.csv) CSVLoggerConfig (class in torchrl.trainers.algorithms.configs.logging) cuda() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.llm.TopKRewardSelector method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) custom_arange() (torchrl.envs.transforms.ActionDiscretizer method)

D

D4RLExperienceReplay (class in torchrl.data.datasets) DAPO (class in torchrl.objectives.llm) DAPOLossOutput (class in torchrl.objectives.llm) data_keys (torchrl.envs.llm.transforms.RayDataLoadingPrimer property) data_path (torchrl.data.datasets.AtariDQNExperienceReplay property) (torchrl.data.datasets.D4RLExperienceReplay property) (torchrl.data.datasets.GenDGRLExperienceReplay property) (torchrl.data.datasets.MinariExperienceReplay property) (torchrl.data.datasets.OpenMLExperienceReplay property) (torchrl.data.datasets.OpenXExperienceReplay property) (torchrl.data.datasets.RobosetExperienceReplay property) (torchrl.data.datasets.VD4RLExperienceReplay property) data_path_root (torchrl.data.datasets.AtariDQNExperienceReplay property) (torchrl.data.datasets.D4RLExperienceReplay property) (torchrl.data.datasets.GenDGRLExperienceReplay property) (torchrl.data.datasets.MinariExperienceReplay property) (torchrl.data.datasets.OpenMLExperienceReplay property) (torchrl.data.datasets.OpenXExperienceReplay property) (torchrl.data.datasets.RobosetExperienceReplay property) (torchrl.data.datasets.VD4RLExperienceReplay property) dataloader (torchrl.envs.llm.transforms.RayDataLoadingPrimer property) DataLoadingPrimer (class in torchrl.envs.llm.transforms) DatasetChatEnv (class in torchrl.envs.llm) DdpgCnnActor (class in torchrl.modules) DdpgCnnQNet (class in torchrl.modules) DDPGLoss (class in torchrl.objectives) DdpgMlpActor (class in torchrl.modules) DdpgMlpQNet (class in torchrl.modules) DecisionTransformer (class in torchrl.modules) DecisionTransformer.DTConfig (class in torchrl.modules) default_atari_dqn() (torchrl.modules.ConvNet class method) default_config() (torchrl.modules.DTActor class method) (torchrl.modules.OnlineDTActor class method) default_keys (torchrl.objectives.A2CLoss attribute) (torchrl.objectives.CQLLoss attribute) (torchrl.objectives.CrossQLoss attribute) (torchrl.objectives.DDPGLoss attribute) (torchrl.objectives.DiscreteCQLLoss attribute) (torchrl.objectives.DiscreteIQLLoss attribute) (torchrl.objectives.DiscreteSACLoss attribute) (torchrl.objectives.DistributionalDQNLoss attribute) (torchrl.objectives.DQNLoss attribute) (torchrl.objectives.DreamerActorLoss attribute) (torchrl.objectives.DreamerModelLoss attribute) (torchrl.objectives.DreamerValueLoss attribute) (torchrl.objectives.DTLoss attribute) (torchrl.objectives.GAILLoss attribute) (torchrl.objectives.IQLLoss attribute) (torchrl.objectives.llm.SFTLoss attribute) (torchrl.objectives.OnlineDTLoss attribute) (torchrl.objectives.PPOLoss attribute) (torchrl.objectives.REDQLoss attribute) (torchrl.objectives.ReinforceLoss attribute) (torchrl.objectives.SACLoss attribute) (torchrl.objectives.TD3BCLoss attribute) (torchrl.objectives.TD3Loss attribute) (torchrl.objectives.value.ValueEstimatorBase attribute) default_reward_aggregator() (torchrl.envs.llm.IfEvalScorer method) default_spec() (torchrl.data.llm.History class method) (torchrl.modules.llm.ChatHistory class method) (torchrl.modules.llm.LogProbs class method) (torchrl.modules.llm.Masks class method) (torchrl.modules.llm.Text class method) (torchrl.modules.llm.Tokens class method) delete() (torchrl.data.datasets.AtariDQNExperienceReplay method) (torchrl.data.datasets.D4RLExperienceReplay method) (torchrl.data.datasets.GenDGRLExperienceReplay method) (torchrl.data.datasets.MinariExperienceReplay method) (torchrl.data.datasets.OpenMLExperienceReplay method) (torchrl.data.datasets.OpenXExperienceReplay method) (torchrl.data.datasets.RobosetExperienceReplay method) (torchrl.data.datasets.VD4RLExperienceReplay method) Delta (class in torchrl.modules) device (torchrl.data.Binary attribute) (torchrl.data.Bounded property) (torchrl.data.Categorical attribute) (torchrl.data.Composite property) (torchrl.data.llm.ContentBase property) (torchrl.data.llm.History property) (torchrl.data.MultiCategorical attribute) (torchrl.data.MultiOneHot attribute) (torchrl.data.NonTensor property) (torchrl.data.OneHot attribute) (torchrl.data.Stacked property) (torchrl.data.StackedComposite property) (torchrl.data.TensorSpec property) (torchrl.data.Unbounded property) (torchrl.data.UnboundedContinuous property) (torchrl.data.UnboundedDiscrete property) (torchrl.envs.llm.IFEvalScoreData property) (torchrl.envs.llm.transforms.RayDataLoadingPrimer property) (torchrl.modules.llm.ChatHistory property) (torchrl.modules.llm.LogProbs property) (torchrl.modules.llm.Masks property) (torchrl.modules.llm.RemoteTransformersWrapper property) (torchrl.modules.llm.Text property) (torchrl.modules.llm.Tokens property) (torchrl.objectives.llm.CISPOLossOutput property) (torchrl.objectives.llm.DAPOLossOutput property) (torchrl.objectives.llm.GRPOLossOutput property) (torchrl.objectives.llm.LLMLossOutput property) (torchrl.objectives.llm.SFTLossOutput property) DeviceCastTransform (class in torchrl.envs.transforms) DeviceCastTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) dialog_turns_per_batch (torchrl.collectors.llm.LLMCollector property) (torchrl.collectors.llm.RayLLMCollector property) DiscreteActionProjection (class in torchrl.envs.transforms) DiscreteActionProjectionConfig (class in torchrl.trainers.algorithms.configs.transforms) DiscreteCQLLoss (class in torchrl.objectives) DiscreteIQLLoss (class in torchrl.objectives) DiscreteSACLoss (class in torchrl.objectives) dist_params_keys (torchrl.modules.llm.RemoteTransformersWrapper property) dist_sample_keys (torchrl.modules.llm.RemoteTransformersWrapper property) DistributedCollector (class in torchrl.collectors.distributed) DistributedDataCollector (class in torchrl.collectors.distributed) DistributedSyncCollector (class in torchrl.collectors.distributed) DistributedSyncDataCollector (class in torchrl.collectors.distributed) DistributedTransport (class in torchrl.weight_update) DistributedWeightSyncScheme (class in torchrl.weight_update) DistributedWeightUpdater (class in torchrl.collectors.distributed) DistributionalDQNLoss (class in torchrl.objectives) DistributionalDQNnet (class in torchrl.modules) DistributionalQValueActor (class in torchrl.modules) DistributionalQValueModule (class in torchrl.modules) DMControlEnv() (in module torchrl.envs) DMControlEnvConfig (class in torchrl.trainers.algorithms.configs.envs_libs) DMControlWrapper() (in module torchrl.envs) done_key (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) done_keys (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) done_keys_groups (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property)

done_spec (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) done_spec_unbatched (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) double() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) DoubleToFloat (class in torchrl.envs.transforms) DoubleToFloatConfig (class in torchrl.trainers.algorithms.configs.transforms) DQNLoss (class in torchrl.objectives) DreamerActor (class in torchrl.modules) DreamerActorLoss (class in torchrl.objectives) DreamerDecoder() (in module torchrl.envs.model_based.dreamer) DreamerEnv() (in module torchrl.envs.model_based.dreamer) DreamerModelLoss (class in torchrl.objectives) DreamerValueLoss (class in torchrl.objectives) DTActor (class in torchrl.modules) DTLoss (class in torchrl.objectives) DTypeCastTransform (class in torchrl.envs.transforms) DTypeCastTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) DuelingCnnDQNet (class in torchrl.modules) dump() (torchrl.data.datasets.AtariDQNExperienceReplay method) (torchrl.data.datasets.D4RLExperienceReplay method) (torchrl.data.datasets.GenDGRLExperienceReplay method) (torchrl.data.datasets.MinariExperienceReplay method) (torchrl.data.datasets.OpenMLExperienceReplay method) (torchrl.data.datasets.OpenXExperienceReplay method) (torchrl.data.datasets.RobosetExperienceReplay method) (torchrl.data.datasets.VD4RLExperienceReplay method) (torchrl.data.PrioritizedReplayBuffer method) (torchrl.data.RayReplayBuffer method) (torchrl.data.RemoteTensorDictReplayBuffer method) (torchrl.data.replay_buffers.CompressedListStorage method) (torchrl.data.replay_buffers.LazyMemmapStorage method) (torchrl.data.replay_buffers.LazyStackStorage method) (torchrl.data.replay_buffers.LazyTensorStorage method) (torchrl.data.replay_buffers.ListStorage method) (torchrl.data.replay_buffers.Storage method) (torchrl.data.replay_buffers.StorageEnsemble method) (torchrl.data.replay_buffers.TensorStorage method) (torchrl.data.ReplayBuffer method) (torchrl.data.ReplayBufferEnsemble method) (torchrl.data.TensorDictPrioritizedReplayBuffer method) (torchrl.data.TensorDictReplayBuffer method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) dumps() (torchrl.data.datasets.AtariDQNExperienceReplay method) (torchrl.data.datasets.D4RLExperienceReplay method) (torchrl.data.datasets.GenDGRLExperienceReplay method) (torchrl.data.datasets.MinariExperienceReplay method) (torchrl.data.datasets.OpenMLExperienceReplay method) (torchrl.data.datasets.OpenXExperienceReplay method) (torchrl.data.datasets.RobosetExperienceReplay method) (torchrl.data.datasets.VD4RLExperienceReplay method) (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.data.PrioritizedReplayBuffer method) (torchrl.data.RayReplayBuffer method) (torchrl.data.RemoteTensorDictReplayBuffer method) (torchrl.data.replay_buffers.CompressedListStorageCheckpointer method) (torchrl.data.ReplayBuffer method) (torchrl.data.ReplayBufferEnsemble method) (torchrl.data.TensorDictPrioritizedReplayBuffer method) (torchrl.data.TensorDictReplayBuffer method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method)

E

EGreedyModule (class in torchrl.modules) empty() (torchrl.data.Composite method) (torchrl.data.datasets.AtariDQNExperienceReplay method) (torchrl.data.datasets.D4RLExperienceReplay method) (torchrl.data.datasets.GenDGRLExperienceReplay method) (torchrl.data.datasets.MinariExperienceReplay method) (torchrl.data.datasets.OpenMLExperienceReplay method) (torchrl.data.datasets.OpenXExperienceReplay method) (torchrl.data.datasets.RobosetExperienceReplay method) (torchrl.data.datasets.VD4RLExperienceReplay method) (torchrl.data.PrioritizedReplayBuffer method) (torchrl.data.RayReplayBuffer method) (torchrl.data.RemoteTensorDictReplayBuffer method) (torchrl.data.ReplayBuffer method) (torchrl.data.ReplayBufferEnsemble method) (torchrl.data.StackedComposite method) (torchrl.data.TensorDictPrioritizedReplayBuffer method) (torchrl.data.TensorDictReplayBuffer method) empty_cache() (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.envs.transforms.TransformedEnv method) enable_profile() (torchrl.collectors.AsyncCollector method) (torchrl.collectors.BaseCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.distributed.DistributedCollector method) (torchrl.collectors.distributed.DistributedDataCollector method) (torchrl.collectors.distributed.DistributedSyncCollector method) (torchrl.collectors.distributed.DistributedSyncDataCollector method) (torchrl.collectors.distributed.RayCollector method) (torchrl.collectors.distributed.RPCCollector method) (torchrl.collectors.distributed.RPCDataCollector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) encode() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) endless_dataloader (torchrl.envs.llm.transforms.RayDataLoadingPrimer property) EndOfLifeTransform (class in torchrl.envs.transforms) EndOfLifeTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) entropy() (torchrl.modules.MaskedCategorical method) (torchrl.modules.OneHotCategorical method) enumerate() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) env_batch_sizes (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.ThreadingAsyncEnvPool property) EnvBase (class in torchrl.envs) EnvConfig (class in torchrl.trainers.algorithms.configs.envs) EnvCreator (class in torchrl.envs) EnvLibsConfig (class in torchrl.trainers.algorithms.configs.envs_libs) EnvMetaData (class in torchrl.envs) erase_memoize_cache() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) eval() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.envs.transforms.TransformedEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method)

ExcludeTransform (class in torchrl.envs.transforms) ExcludeTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) execute() (torchrl.envs.llm.transforms.PythonExecutorService method) ExecuteToolsInOrder (class in torchrl.envs.llm.transforms) EXP3Score (class in torchrl.modules.mcts) expand() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) (torchrl.modules.Delta method) exploration_type() (in module torchrl.envs) extend() (torchrl.data.datasets.AtariDQNExperienceReplay method) (torchrl.data.datasets.D4RLExperienceReplay method) (torchrl.data.datasets.GenDGRLExperienceReplay method) (torchrl.data.datasets.MinariExperienceReplay method) (torchrl.data.datasets.OpenMLExperienceReplay method) (torchrl.data.datasets.OpenXExperienceReplay method) (torchrl.data.datasets.RobosetExperienceReplay method) (torchrl.data.datasets.VD4RLExperienceReplay method) (torchrl.data.PrioritizedReplayBuffer method) (torchrl.data.RayReplayBuffer method) (torchrl.data.RemoteTensorDictReplayBuffer method) (torchrl.data.replay_buffers.ImmutableDatasetWriter method) (torchrl.data.replay_buffers.RoundRobinWriter method) (torchrl.data.replay_buffers.TensorDictMaxValueWriter method) (torchrl.data.replay_buffers.TensorDictRoundRobinWriter method) (torchrl.data.replay_buffers.Writer method) (torchrl.data.replay_buffers.WriterEnsemble method) (torchrl.data.ReplayBuffer method) (torchrl.data.ReplayBufferEnsemble method) (torchrl.data.TensorDictPrioritizedReplayBuffer method) (torchrl.data.TensorDictReplayBuffer method) extra_repr() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) extract_tags() (torchrl.envs.llm.GSM8KRewardParser static method) extract_weights() (torchrl.weight_update.WeightStrategy method)

F

fake_tensordict() (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) fast_encoding() (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.MLGymWrapper method) fields() (torchrl.data.llm.ContentBase class method) (torchrl.data.llm.History class method) (torchrl.envs.llm.IFEvalScoreData class method) (torchrl.modules.llm.ChatHistory class method) (torchrl.modules.llm.LogProbs class method) (torchrl.modules.llm.Masks class method) (torchrl.modules.llm.Text class method) (torchrl.modules.llm.Tokens class method) (torchrl.objectives.llm.CISPOLossOutput class method) (torchrl.objectives.llm.DAPOLossOutput class method) (torchrl.objectives.llm.GRPOLossOutput class method) (torchrl.objectives.llm.LLMLossOutput class method) (torchrl.objectives.llm.SFTLossOutput class method) FiniteTensorDictCheck (class in torchrl.envs.transforms) FiniteTensorDictCheckConfig (class in torchrl.trainers.algorithms.configs.transforms) FlatStorageCheckpointer (class in torchrl.data.replay_buffers) flatten() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) FlattenObservation (class in torchrl.envs.transforms) FlattenObservationConfig (class in torchrl.trainers.algorithms.configs.transforms) float() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) forward() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.envs.transforms.ActionMask method) (torchrl.envs.transforms.AutoResetTransform method) (torchrl.envs.transforms.BatchSizeTransform method) (torchrl.envs.transforms.BurnInTransform method) (torchrl.envs.transforms.CatFrames method) (torchrl.envs.transforms.CatTensors method) (torchrl.envs.transforms.Compose method) (torchrl.envs.transforms.ConditionalPolicySwitch method) (torchrl.envs.transforms.ConditionalSkip method) (torchrl.envs.transforms.DeviceCastTransform method) (torchrl.envs.transforms.DTypeCastTransform method) (torchrl.envs.transforms.EndOfLifeTransform method) (torchrl.envs.transforms.ExcludeTransform method) (torchrl.envs.transforms.FiniteTensorDictCheck method) (torchrl.envs.transforms.FlattenObservation method) (torchrl.envs.transforms.FrameSkipTransform method) (torchrl.envs.transforms.InitTracker method) (torchrl.envs.transforms.ModuleTransform method) (torchrl.envs.transforms.PinMemoryTransform method) (torchrl.envs.transforms.RandomCropTensorDict method) (torchrl.envs.transforms.RemoveEmptySpecs method) (torchrl.envs.transforms.RenameTransform method) (torchrl.envs.transforms.Reward2GoTransform method) (torchrl.envs.transforms.RewardSum method) (torchrl.envs.transforms.SelectTransform method) (torchrl.envs.transforms.Stack method) (torchrl.envs.transforms.StepCounter method) (torchrl.envs.transforms.TargetReturn method) (torchrl.envs.transforms.TensorDictPrimer method) (torchrl.envs.transforms.TimeMaxPool method) (torchrl.envs.transforms.Timer method) (torchrl.envs.transforms.Tokenizer method) (torchrl.envs.transforms.TrajCounter method) (torchrl.envs.transforms.Transform method) (torchrl.envs.transforms.VC1Transform method) (torchrl.envs.transforms.VecGymEnvTransform method) (torchrl.envs.transforms.VecNorm method) (torchrl.envs.transforms.VIPRewardTransform method) (torchrl.modules.AdditiveGaussianModule method) (torchrl.modules.ConsistentDropoutModule method) (torchrl.modules.ConvNet method) (torchrl.modules.DdpgCnnActor method) (torchrl.modules.DdpgCnnQNet method) (torchrl.modules.DdpgMlpActor method) (torchrl.modules.DdpgMlpQNet method) (torchrl.modules.DecisionTransformer method) (torchrl.modules.DistributionalDQNnet method) (torchrl.modules.DistributionalQValueModule method) (torchrl.modules.DreamerActor method) (torchrl.modules.DTActor method) (torchrl.modules.DuelingCnnDQNet method) (torchrl.modules.EGreedyModule method) (torchrl.modules.GRUModule method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.modules.LSTMModule method) (torchrl.modules.MLP method) (torchrl.modules.models.utils.SquashDims method) (torchrl.modules.NormalParamExtractor method) (torchrl.modules.ObsDecoder method) (torchrl.modules.ObsEncoder method) (torchrl.modules.OnlineDTActor method) (torchrl.modules.OrnsteinUhlenbeckProcessModule method) (torchrl.modules.QValueModule method) (torchrl.modules.RSSMPosterior method) (torchrl.modules.RSSMPrior method) (torchrl.modules.RSSMRollout method) (torchrl.modules.tensordict_module.MultiStepActorWrapper method) (torchrl.modules.tensordict_module.TanhModule method) (torchrl.objectives.A2CLoss method) (torchrl.objectives.ClipPPOLoss method) (torchrl.objectives.CQLLoss method) (torchrl.objectives.CrossQLoss method) (torchrl.objectives.DDPGLoss method) (torchrl.objectives.DiscreteCQLLoss method) (torchrl.objectives.DiscreteIQLLoss method) (torchrl.objectives.DiscreteSACLoss method) (torchrl.objectives.DistributionalDQNLoss method) (torchrl.objectives.DQNLoss method) (torchrl.objectives.DreamerActorLoss method) (torchrl.objectives.DreamerModelLoss method) (torchrl.objectives.DreamerValueLoss method) (torchrl.objectives.DTLoss method) (torchrl.objectives.GAILLoss method) (torchrl.objectives.IQLLoss method) (torchrl.objectives.KLPENPPOLoss method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) (torchrl.objectives.LossModule method) (torchrl.objectives.OnlineDTLoss method) (torchrl.objectives.PPOLoss method) (torchrl.objectives.REDQLoss method) (torchrl.objectives.ReinforceLoss method) (torchrl.objectives.SACLoss method) (torchrl.objectives.TD3BCLoss method) (torchrl.objectives.TD3Loss method) (torchrl.objectives.value.GAE method) (torchrl.objectives.value.TD0Estimator method) (torchrl.objectives.value.TD1Estimator method) (torchrl.objectives.value.TDLambdaEstimator method) (torchrl.objectives.value.ValueEstimatorBase method) FrameSkipTransform (class in torchrl.envs.transforms) FrameSkipTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) freeze() (torchrl.envs.transforms.VecNorm method) (torchrl.envs.transforms.VecNormV2 method), [1] from_any() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) from_chats() (torchrl.data.llm.History class method) from_dataclass() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) from_dataloader() (torchrl.envs.llm.ChatEnv class method) (torchrl.envs.llm.DatasetChatEnv class method) (torchrl.envs.llm.GSM8KEnv class method) (torchrl.envs.llm.IFEvalEnv class method) (torchrl.envs.llm.LLMEnv class method) (torchrl.envs.llm.LLMEnv method) from_h5() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) from_modules() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method)

from_namedtuple() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) from_policy() (torchrl.collectors.distributed.DistributedWeightUpdater class method) (torchrl.collectors.distributed.RPCWeightUpdater class method) (torchrl.collectors.llm.vLLMUpdater class method) (torchrl.collectors.llm.vLLMUpdaterV2 class method) (torchrl.collectors.MultiProcessedWeightUpdater class method) (torchrl.collectors.RayWeightUpdater class method) (torchrl.collectors.VanillaWeightUpdater class method) (torchrl.collectors.WeightUpdaterBase class method) (torchrl.collectors.WeightUpdaterBase method) from_pretrained() (torchrl.modules.llm.AsyncVLLM class method) from_pytree() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) from_remote_init() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) from_stateful_net() (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.SFTLoss method) (torchrl.objectives.LossModule method) from_struct_array() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) from_tensordict() (torchrl.data.llm.ContentBase class method) (torchrl.data.llm.History class method) (torchrl.envs.llm.IFEvalScoreData class method) (torchrl.modules.llm.ChatHistory class method) (torchrl.modules.llm.LogProbs class method) (torchrl.modules.llm.Masks class method) (torchrl.modules.llm.Text class method) (torchrl.modules.llm.Tokens class method) (torchrl.objectives.llm.CISPOLossOutput class method) (torchrl.objectives.llm.DAPOLossOutput class method) (torchrl.objectives.llm.GRPOLossOutput class method) (torchrl.objectives.llm.LLMLossOutput class method) (torchrl.objectives.llm.SFTLossOutput class method) from_text() (torchrl.data.llm.History class method) from_tuple() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) fromkeys() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) frozen_copy() (torchrl.envs.transforms.VecNorm method) (torchrl.envs.transforms.VecNormV2 method), [1] full_action_spec (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) full_action_spec_unbatched (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) full_done_spec (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) full_done_spec_unbatched (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) full_observation_spec_unbatched (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) full_reward_spec (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) full_reward_spec_unbatched (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) full_state_spec (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) full_state_spec_unbatched (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) functional (torchrl.objectives.A2CLoss property) (torchrl.objectives.llm.CISPOLoss property) (torchrl.objectives.llm.DAPO property) (torchrl.objectives.llm.GRPOLoss property) (torchrl.objectives.llm.SFTLoss property) (torchrl.objectives.LossModule property) (torchrl.objectives.PPOLoss property) (torchrl.objectives.ReinforceLoss property)

G

GAE (class in torchrl.objectives.value) GAILLoss (class in torchrl.objectives) gen_params() (torchrl.envs.PendulumEnv static method) GenDGRLExperienceReplay (class in torchrl.data.datasets) generate (torchrl.modules.llm.RemoteTransformersWrapper property) generate() (torchrl.modules.llm.AsyncVLLM method) generate_exp_name() (in module torchrl.record.loggers) get() (torchrl.data.Composite method) (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.data.StackedComposite method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.envs.llm.transforms.ToolRegistry method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) (torchrl.services.RayService method) (torchrl.services.ServiceBase method) get_available_libraries() (in module torchrl.envs) get_batching_state() (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.RemoteTransformersWrapper method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) get_buffer() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) get_cache_usage() (torchrl.modules.llm.AsyncVLLM method) get_cached_weights() (torchrl.collectors.AsyncCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) get_class_that_defined_method() (torchrl.implement_for static method) get_critic_operator() (torchrl.modules.ActorCriticOperator method) get_dist() (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.RemoteTransformersWrapper method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) get_dist_with_prompt_mask() (torchrl.modules.llm.RemoteTransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) get_extra_state() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.envs.transforms.VecNorm method) (torchrl.envs.transforms.VecNormV2 method), [1] (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) get_input_from_hash() (torchrl.envs.transforms.Hash method) get_insert_index() (torchrl.data.replay_buffers.TensorDictMaxValueWriter method) get_legal_moves() (torchrl.envs.ChessEnv method) get_library_name() (torchrl.envs.llm.MLGymWrapper static method) get_logger() (in module torchrl.record.loggers) get_master_address() (torchrl.modules.llm.AsyncVLLM method) get_master_port() (torchrl.modules.llm.AsyncVLLM method) get_mode() (torchrl.modules.TanhNormal method) get_model() (torchrl.collectors.AsyncCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) get_model_metadata (class in torchrl.weight_update.llm) get_model_metadata() (torchrl.collectors.llm.vLLMUpdater class method) (torchrl.collectors.llm.vLLMUpdaterV2 class method) (torchrl.modules.llm.AsyncVLLM method) get_new_version() (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.RemoteTransformersWrapper method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method)

get_num_unfinished_requests() (torchrl.modules.llm.AsyncVLLM method) get_parameter() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) get_policy_head() (torchrl.modules.ActorCriticOperator method) (torchrl.modules.ActorCriticWrapper method) (torchrl.modules.ActorValueOperator method) get_policy_model() (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) get_policy_operator() (torchrl.modules.ActorCriticWrapper method) (torchrl.modules.ActorValueOperator method) get_policy_version() (torchrl.collectors.AsyncCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) get_random_actor_index() (torchrl.modules.llm.AsyncVLLM method) get_reward_operator() (torchrl.modules.WorldModelWrapper method) get_services (class in torchrl.services) get_stateful_net() (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.SFTLoss method) (torchrl.objectives.LossModule method) get_stats_random_rollout() (in module torchrl.trainers.helpers) get_submodule() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) get_tp_size() (torchrl.collectors.llm.vLLMUpdaterV2 method) (torchrl.modules.llm.AsyncVLLM method) get_transition_model_operator() (torchrl.modules.WorldModelWrapper method) get_value_head() (torchrl.modules.ActorCriticOperator method) (torchrl.modules.ActorCriticWrapper method) (torchrl.modules.ActorValueOperator method) get_value_operator() (torchrl.modules.ActorCriticOperator method) (torchrl.modules.ActorCriticWrapper method) (torchrl.modules.ActorValueOperator method) getattr_env() (torchrl.collectors.AsyncCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) getattr_policy() (torchrl.collectors.AsyncCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) getattr_rb() (torchrl.collectors.AsyncCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) GrayScale (class in torchrl.envs.transforms) GrayScaleConfig (class in torchrl.trainers.algorithms.configs.transforms) GRPOLoss (class in torchrl.objectives.llm) GRPOLossOutput (class in torchrl.objectives.llm) GRUModule (class in torchrl.modules) gSDENoise (class in torchrl.envs.transforms) GSM8KEnv (class in torchrl.envs.llm) GSM8KPrepareQuestion (class in torchrl.envs.llm) GSM8KRewardParser (class in torchrl.envs.llm) gym_backend() (in module torchrl.envs) GymEnv() (in module torchrl.envs) GymEnvConfig (class in torchrl.trainers.algorithms.configs.envs_libs) GymLikeEnv (class in torchrl.envs) GymWrapper() (in module torchrl.envs)

H

H5StorageCheckpointer (class in torchrl.data.replay_buffers) HabitatEnv() (in module torchrl.envs) HabitatEnvConfig (class in torchrl.trainers.algorithms.configs.envs_libs) half() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method)

Hash (class in torchrl.envs.transforms) HashConfig (class in torchrl.trainers.algorithms.configs.transforms) History (class in torchrl.data.llm)

I

IFEvalEnv (class in torchrl.envs.llm) IFEvalScoreData (class in torchrl.envs.llm) IfEvalScorer (class in torchrl.envs.llm) ImmutableDatasetWriter (class in torchrl.data.replay_buffers) implement_for (class in torchrl) implements_for_spec() (torchrl.data.Binary class method) (torchrl.data.Bounded class method) (torchrl.data.Categorical class method) (torchrl.data.Composite class method) (torchrl.data.MultiCategorical class method) (torchrl.data.MultiOneHot class method) (torchrl.data.NonTensor class method) (torchrl.data.OneHot class method) (torchrl.data.Stacked class method) (torchrl.data.StackedComposite class method) (torchrl.data.TensorSpec class method) (torchrl.data.Unbounded class method) (torchrl.data.UnboundedContinuous class method) (torchrl.data.UnboundedDiscrete class method) import_module() (torchrl.implement_for class method) in_keys (torchrl.envs.llm.transforms.RayDataLoadingPrimer property) (torchrl.modules.llm.RemoteTransformersWrapper property) in_keys_inv (torchrl.envs.llm.transforms.RayDataLoadingPrimer property) increment_version() (torchrl.collectors.AsyncCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.distributed.DistributedWeightUpdater method) (torchrl.collectors.distributed.RPCWeightUpdater method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.llm.vLLMUpdater method) (torchrl.collectors.llm.vLLMUpdaterV2 method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiProcessedWeightUpdater method) (torchrl.collectors.MultiSyncCollector method) (torchrl.collectors.RayWeightUpdater method) (torchrl.collectors.VanillaWeightUpdater method) (torchrl.collectors.WeightUpdaterBase method) (torchrl.envs.llm.transforms.PolicyVersion method) IndependentNormal (class in torchrl.modules) index() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) init() (torchrl.collectors.distributed.DistributedWeightUpdater method) (torchrl.collectors.distributed.RPCWeightUpdater method) (torchrl.collectors.llm.vLLMUpdater method), [1] (torchrl.collectors.llm.vLLMUpdaterV2 method) (torchrl.collectors.MultiProcessedWeightUpdater method) (torchrl.collectors.RayWeightUpdater method) (torchrl.collectors.VanillaWeightUpdater method) (torchrl.collectors.WeightUpdaterBase method) (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.transforms.Compose method) (torchrl.envs.transforms.Transform method) (torchrl.objectives.llm.MCAdvantage method) init_all_workers_group() (torchrl.weight_update.llm.VLLMCollectiveTransport method) (torchrl.weight_update.llm.VLLMWeightReceiver method) (torchrl.weight_update.llm.VLLMWeightSender method) init_key (torchrl.modules.tensordict_module.MultiStepActorWrapper property) init_on_receiver() (torchrl.weight_update.DistributedWeightSyncScheme method) (torchrl.weight_update.llm.VLLMDoubleBufferSyncScheme method) (torchrl.weight_update.llm.VLLMWeightSyncScheme method) (torchrl.weight_update.MultiProcessWeightSyncScheme method) (torchrl.weight_update.NoWeightSyncScheme method) (torchrl.weight_update.RayModuleTransformScheme method) (torchrl.weight_update.RayWeightSyncScheme method) (torchrl.weight_update.RPCWeightSyncScheme method) (torchrl.weight_update.SharedMemWeightSyncScheme method) (torchrl.weight_update.WeightSyncScheme method) init_on_sender() (torchrl.weight_update.DistributedWeightSyncScheme method) (torchrl.weight_update.llm.VLLMDoubleBufferSyncScheme method) (torchrl.weight_update.llm.VLLMWeightSyncScheme method) (torchrl.weight_update.MultiProcessWeightSyncScheme method) (torchrl.weight_update.NoWeightSyncScheme method) (torchrl.weight_update.RayModuleTransformScheme method) (torchrl.weight_update.RayWeightSyncScheme method) (torchrl.weight_update.RPCWeightSyncScheme method) (torchrl.weight_update.SharedMemWeightSyncScheme method) (torchrl.weight_update.WeightSyncScheme method) init_stats() (torchrl.envs.transforms.ObservationNorm method) init_updater() (torchrl.collectors.AsyncCollector method) (torchrl.collectors.BaseCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.distributed.DistributedCollector method) (torchrl.collectors.distributed.DistributedDataCollector method) (torchrl.collectors.distributed.DistributedSyncCollector method) (torchrl.collectors.distributed.DistributedSyncDataCollector method) (torchrl.collectors.distributed.RayCollector method) (torchrl.collectors.distributed.RPCCollector method) (torchrl.collectors.distributed.RPCDataCollector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) init_weight_update_group() (torchrl.modules.llm.AsyncVLLM method) initialized (torchrl.data.datasets.AtariDQNExperienceReplay property) (torchrl.data.datasets.D4RLExperienceReplay property) (torchrl.data.datasets.GenDGRLExperienceReplay property) (torchrl.data.datasets.MinariExperienceReplay property) (torchrl.data.datasets.OpenMLExperienceReplay property) (torchrl.data.datasets.OpenXExperienceReplay property) (torchrl.data.datasets.RobosetExperienceReplay property) (torchrl.data.datasets.VD4RLExperienceReplay property) (torchrl.data.PrioritizedReplayBuffer property) (torchrl.data.RayReplayBuffer property) (torchrl.data.RemoteTensorDictReplayBuffer property) (torchrl.data.ReplayBuffer property) (torchrl.data.ReplayBufferEnsemble property) (torchrl.data.TensorDictPrioritizedReplayBuffer property) (torchrl.data.TensorDictReplayBuffer property) InitTracker (class in torchrl.envs.transforms) InitTrackerConfig (class in torchrl.trainers.algorithms.configs.transforms) inplace (torchrl.modules.llm.RemoteTransformersWrapper property) input_spec (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) (torchrl.envs.transforms.TransformedEnv property)

input_spec_unbatched (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) insert() (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.transforms.Compose method) insert_transform() (torchrl.data.datasets.AtariDQNExperienceReplay method) (torchrl.data.datasets.D4RLExperienceReplay method) (torchrl.data.datasets.GenDGRLExperienceReplay method) (torchrl.data.datasets.MinariExperienceReplay method) (torchrl.data.datasets.OpenMLExperienceReplay method) (torchrl.data.datasets.OpenXExperienceReplay method) (torchrl.data.datasets.RobosetExperienceReplay method) (torchrl.data.datasets.VD4RLExperienceReplay method) (torchrl.data.PrioritizedReplayBuffer method) (torchrl.data.RayReplayBuffer method) (torchrl.data.RemoteTensorDictReplayBuffer method) (torchrl.data.ReplayBuffer method) (torchrl.data.ReplayBufferEnsemble method) (torchrl.data.TensorDictPrioritizedReplayBuffer method) (torchrl.data.TensorDictReplayBuffer method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.transforms.AutoResetEnv method) (torchrl.envs.transforms.TransformedEnv method) inv() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.transforms.ActionDiscretizer method) (torchrl.envs.transforms.Transform method) (torchrl.objectives.llm.MCAdvantage method) ipu() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) IQLLoss (class in torchrl.objectives) is_empty() (torchrl.data.Composite method) (torchrl.data.StackedComposite method) is_in() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) is_initialized() (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) is_spec_locked (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) is_tdmodule_compatible() (torchrl.modules.llm.LLMWrapperBase static method) (torchrl.modules.llm.TransformersWrapper static method) (torchrl.modules.llm.vLLMWrapper static method) (torchrl.objectives.llm.CISPOLoss static method) (torchrl.objectives.llm.DAPO static method) (torchrl.objectives.llm.GRPOLoss static method) (torchrl.objectives.llm.SFTLoss static method) IsaacGymEnv() (in module torchrl.envs) IsaacGymEnvConfig (class in torchrl.trainers.algorithms.configs.envs_libs) IsaacGymWrapper() (in module torchrl.envs) IsaacLabWrapper() (in module torchrl.envs) items() (torchrl.data.Composite method) (torchrl.data.StackedComposite method) iterator() (torchrl.collectors.Collector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method)

J

JSONCallParser (class in torchrl.envs.llm.transforms) JumanjiEnv() (in module torchrl.envs)

JumanjiEnvConfig (class in torchrl.trainers.algorithms.configs.envs_libs) JumanjiWrapper() (in module torchrl.envs)

K

keys() (torchrl.data.Composite method) (torchrl.data.StackedComposite method) KLComputation (class in torchrl.envs.llm.transforms)

KLPENPPOLoss (class in torchrl.objectives) KLRewardTransform (class in torchrl.envs.llm.transforms) KLRewardTransformConfig (class in torchrl.trainers.algorithms.configs.transforms)

L

launch() (torchrl.modules.llm.AsyncVLLM class method) layout (torchrl.modules.llm.RemoteTransformersWrapper property) lazy_stack() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) LazyMemmapStorage (class in torchrl.data.replay_buffers) LazyMemmapStorageConfig (class in torchrl.trainers.algorithms.configs.data) LazyStackStorage (class in torchrl.data.replay_buffers) LazyStackStorageConfig (class in torchrl.trainers.algorithms.configs.data) LazyTensorStorage (class in torchrl.data.replay_buffers) LazyTensorStorageConfig (class in torchrl.trainers.algorithms.configs.data) LBFGSConfig (class in torchrl.trainers.algorithms.configs.utils) LineariseRewards (class in torchrl.envs.transforms) LineariseRewardsConfig (class in torchrl.trainers.algorithms.configs.transforms) LionConfig (class in torchrl.trainers.algorithms.configs.utils) list() (torchrl.services.RayService method) (torchrl.services.ServiceBase method) ListStorage (class in torchrl.data.replay_buffers) ListStorageCheckpointer (class in torchrl.data.replay_buffers) ListStorageConfig (class in torchrl.trainers.algorithms.configs.data) LLMCollector (class in torchrl.collectors.llm) LLMEnv (class in torchrl.envs.llm) LLMHashingEnv (class in torchrl.envs) (class in torchrl.envs.llm) LLMLossOutput (class in torchrl.objectives.llm) LLMWrapperBase (class in torchrl.modules.llm) load() (torchrl.data.datasets.AtariDQNExperienceReplay method) (torchrl.data.datasets.D4RLExperienceReplay method) (torchrl.data.datasets.GenDGRLExperienceReplay method) (torchrl.data.datasets.MinariExperienceReplay method) (torchrl.data.datasets.OpenMLExperienceReplay method) (torchrl.data.datasets.OpenXExperienceReplay method) (torchrl.data.datasets.RobosetExperienceReplay method) (torchrl.data.datasets.VD4RLExperienceReplay method) (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.data.PrioritizedReplayBuffer method) (torchrl.data.RayReplayBuffer method) (torchrl.data.RemoteTensorDictReplayBuffer method) (torchrl.data.replay_buffers.CompressedListStorage method) (torchrl.data.replay_buffers.LazyMemmapStorage method) (torchrl.data.replay_buffers.LazyStackStorage method) (torchrl.data.replay_buffers.LazyTensorStorage method) (torchrl.data.replay_buffers.ListStorage method) (torchrl.data.replay_buffers.Storage method) (torchrl.data.replay_buffers.StorageEnsemble method) (torchrl.data.replay_buffers.TensorStorage method) (torchrl.data.ReplayBuffer method) (torchrl.data.ReplayBufferEnsemble method) (torchrl.data.TensorDictPrioritizedReplayBuffer method) (torchrl.data.TensorDictReplayBuffer method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) load_() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) load_from_file() (torchrl.trainers.algorithms.PPOTrainer method) (torchrl.trainers.algorithms.SACTrainer method) (torchrl.trainers.Trainer method) load_memmap() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) load_state_dict() (torchrl.collectors.AsyncCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.distributed.RayCollector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.data.llm.TopKRewardSelector method) (torchrl.data.replay_buffers.CompressedListStorage method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.envs.transforms.TrajCounter method) (torchrl.envs.transforms.TransformedEnv method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.CrossQLoss method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) (torchrl.objectives.llm.SFTLossOutput method) (torchrl.objectives.SACLoss method) (torchrl.trainers.UTDRHook method)

loads() (torchrl.data.datasets.AtariDQNExperienceReplay method) (torchrl.data.datasets.D4RLExperienceReplay method) (torchrl.data.datasets.GenDGRLExperienceReplay method) (torchrl.data.datasets.MinariExperienceReplay method) (torchrl.data.datasets.OpenMLExperienceReplay method) (torchrl.data.datasets.OpenXExperienceReplay method) (torchrl.data.datasets.RobosetExperienceReplay method) (torchrl.data.datasets.VD4RLExperienceReplay method) (torchrl.data.PrioritizedReplayBuffer method) (torchrl.data.RayReplayBuffer method) (torchrl.data.RemoteTensorDictReplayBuffer method) (torchrl.data.replay_buffers.CompressedListStorageCheckpointer method) (torchrl.data.ReplayBuffer method) (torchrl.data.ReplayBufferEnsemble method) (torchrl.data.TensorDictPrioritizedReplayBuffer method) (torchrl.data.TensorDictReplayBuffer method) loc (torchrl.envs.transforms.VecNorm property) (torchrl.envs.transforms.VecNormV2 property) loc() (torchrl.envs.transforms.VecNormV2 method) local_policy() (torchrl.collectors.distributed.RayCollector method) lock_() (torchrl.data.Composite method) (torchrl.data.StackedComposite method) log_prob() (torchrl.modules.Delta method) (torchrl.modules.llm.RemoteTransformersWrapper method) (torchrl.modules.MaskedCategorical method) (torchrl.modules.OneHotCategorical method) (torchrl.modules.TruncatedNormal method) log_prob_keys (torchrl.modules.llm.RemoteTransformersWrapper property) log_probs_key (torchrl.modules.llm.RemoteTransformersWrapper property) Logger() (in module torchrl.record.loggers) LoggerConfig (class in torchrl.trainers.algorithms.configs.logging) LogProbs (class in torchrl.modules.llm) LogScalar (class in torchrl.trainers) LogValidationReward (class in torchrl.trainers) loss_critic() (torchrl.objectives.A2CLoss method) (torchrl.objectives.PPOLoss method) loss_value_diff() (torchrl.objectives.IQLLoss static method) LossConfig (class in torchrl.trainers.algorithms.configs.objectives) LossModule (class in torchrl.objectives) LSTMModule (class in torchrl.modules)

M

make_async_vllm_engine (class in torchrl.modules.llm) make_collector_offpolicy() (in module torchrl.trainers.helpers) make_collector_onpolicy() (in module torchrl.trainers.helpers) make_composite_from_td() (in module torchrl.envs) make_cudnn_based() (torchrl.modules.GRUModule method) (torchrl.modules.LSTMModule method) make_dqn_loss() (in module torchrl.trainers.helpers) make_gsm8k_env (class in torchrl.envs.llm) make_mlgym (class in torchrl.envs.llm) make_neg_dim() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) make_noload_model() (torchrl.envs.transforms.VC1Transform class method) make_parallel() (torchrl.envs.AsyncEnvPool class method) (torchrl.envs.ChessEnv class method) (torchrl.envs.EnvBase class method) (torchrl.envs.GymLikeEnv class method) (torchrl.envs.llm.ChatEnv class method) (torchrl.envs.llm.DatasetChatEnv class method) (torchrl.envs.llm.GSM8KEnv class method) (torchrl.envs.llm.IFEvalEnv class method) (torchrl.envs.llm.LLMEnv class method) (torchrl.envs.llm.LLMHashingEnv class method) (torchrl.envs.llm.MLGymWrapper class method) (torchrl.envs.LLMHashingEnv class method) (torchrl.envs.ParallelEnv class method) (torchrl.envs.PendulumEnv class method) (torchrl.envs.ProcessorAsyncEnvPool class method) (torchrl.envs.SerialEnv class method) (torchrl.envs.ThreadingAsyncEnvPool class method) (torchrl.envs.TicTacToeEnv class method) make_python_based() (torchrl.modules.GRUModule method) (torchrl.modules.LSTMModule method) make_rb_transform_and_sampler() (torchrl.envs.transforms.CatFrames method) make_replay_buffer() (in module torchrl.trainers.helpers) make_target_updater() (in module torchrl.trainers.helpers) make_tensordict() (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.LLMHashingEnv method) make_tensordict_primer() (torchrl.modules.ConsistentDropoutModule method) (torchrl.modules.GRUModule method), [1] (torchrl.modules.LSTMModule method), [1] make_trainer() (in module torchrl.trainers.helpers) make_value_estimator() (torchrl.objectives.A2CLoss method) (torchrl.objectives.CQLLoss method) (torchrl.objectives.CrossQLoss method) (torchrl.objectives.DDPGLoss method) (torchrl.objectives.DiscreteCQLLoss method) (torchrl.objectives.DiscreteSACLoss method) (torchrl.objectives.DistributionalDQNLoss method) (torchrl.objectives.DQNLoss method) (torchrl.objectives.DreamerActorLoss method) (torchrl.objectives.IQLLoss method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.SFTLoss method) (torchrl.objectives.LossModule method) (torchrl.objectives.PPOLoss method) (torchrl.objectives.REDQLoss method) (torchrl.objectives.ReinforceLoss method) (torchrl.objectives.SACLoss method) (torchrl.objectives.TD3BCLoss method) (torchrl.objectives.TD3Loss method) make_variant() (torchrl.envs.EnvCreator method) make_vllm_worker (class in torchrl.modules.llm) MarlGroupMapType() (in module torchrl.envs) MaskedCategorical (class in torchrl.modules) Masks (class in torchrl.modules.llm) masks_key (torchrl.modules.llm.RemoteTransformersWrapper property) maybe_dense_stack() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) maybe_init_target_entropy() (torchrl.objectives.CrossQLoss method) maybe_reset() (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) MCAdvantage (class in torchrl.objectives.llm) MCPToolTransform (class in torchrl.envs.llm.transforms) MCTSScore (class in torchrl.modules.mcts) MCTSScores (class in torchrl.modules.mcts) mean (torchrl.modules.Delta property) (torchrl.modules.TanhDelta property) (torchrl.modules.TanhNormal property) MeltingpotEnv() (in module torchrl.envs) MeltingpotEnvConfig (class in torchrl.trainers.algorithms.configs.envs_libs) MeltingpotWrapper() (in module torchrl.envs) memmap() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) memmap_() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) memmap_like() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) memmap_refresh_() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method)

memoize_encode() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) MinariExperienceReplay (class in torchrl.data.datasets) missing_tolerance (torchrl.envs.llm.transforms.RayDataLoadingPrimer property) MLFlowLogger() (in module torchrl.record.loggers.mlflow) MLGymWrapper (class in torchrl.envs.llm) MLP (class in torchrl.modules) MLPConfig (class in torchrl.trainers.algorithms.configs.modules) mode (torchrl.modules.Delta property) (torchrl.modules.IndependentNormal property) (torchrl.modules.OneHotCategorical property) (torchrl.modules.TanhDelta property) (torchrl.modules.TanhNormal property) (torchrl.modules.TruncatedNormal property) model (torchrl.weight_update.DistributedWeightSyncScheme property) (torchrl.weight_update.llm.VLLMDoubleBufferSyncScheme property) (torchrl.weight_update.llm.VLLMWeightSyncScheme property) (torchrl.weight_update.MultiProcessWeightSyncScheme property) (torchrl.weight_update.NoWeightSyncScheme property) (torchrl.weight_update.RayModuleTransformScheme property) (torchrl.weight_update.RayWeightSyncScheme property) (torchrl.weight_update.RPCWeightSyncScheme property) (torchrl.weight_update.SharedMemWeightSyncScheme property) (torchrl.weight_update.WeightSyncScheme property) model_id (torchrl.weight_update.DistributedWeightSyncScheme property) (torchrl.weight_update.llm.VLLMDoubleBufferSyncScheme property) (torchrl.weight_update.llm.VLLMWeightSyncScheme property) (torchrl.weight_update.MultiProcessWeightSyncScheme property) (torchrl.weight_update.NoWeightSyncScheme property) (torchrl.weight_update.RayModuleTransformScheme property) (torchrl.weight_update.RayWeightSyncScheme property) (torchrl.weight_update.RPCWeightSyncScheme property) (torchrl.weight_update.SharedMemWeightSyncScheme property) (torchrl.weight_update.WeightSyncScheme property) ModelBasedEnvBase() (in module torchrl.envs) ModelConfig (class in torchrl.trainers.algorithms.configs.modules) module_set() (torchrl.implement_for method) modules() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) ModuleTransform (class in torchrl.envs.transforms) MOGymEnv() (in module torchrl.envs) MOGymEnvConfig (class in torchrl.trainers.algorithms.configs.envs_libs) MOGymWrapper() (in module torchrl.envs) MPTransport (class in torchrl.weight_update) mtia() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) MultiAction (class in torchrl.envs.transforms) MultiActionConfig (class in torchrl.trainers.algorithms.configs.transforms) MultiAsyncCollector (class in torchrl.collectors) MultiAsyncCollectorConfig (class in torchrl.trainers.algorithms.configs.collectors) MultiCategorical (class in torchrl.data) MultiCollector (class in torchrl.collectors) MultiOneHot (class in torchrl.data) MultiProcessedWeightUpdater (class in torchrl.collectors) MultiProcessWeightSyncScheme (class in torchrl.weight_update) MultiStepActorWrapper (class in torchrl.modules.tensordict_module) MultiStepTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) MultiSyncCollector (class in torchrl.collectors) MultiSyncCollectorConfig (class in torchrl.trainers.algorithms.configs.collectors) MultiThreadedEnv() (in module torchrl.envs) MultiThreadedEnvConfig (class in torchrl.trainers.algorithms.configs.envs_libs) MultiThreadedEnvWrapper() (in module torchrl.envs)

N

NAdamConfig (class in torchrl.trainers.algorithms.configs.utils) named_buffers() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) named_children() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) named_modules() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method)

named_parameters() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) (torchrl.objectives.LossModule method) names (torchrl.data.Composite property) (torchrl.data.StackedComposite property) ndim (torchrl.data.Binary property) (torchrl.data.Bounded property) (torchrl.data.Categorical property) (torchrl.data.Composite property) (torchrl.data.MultiCategorical property) (torchrl.data.MultiOneHot property) (torchrl.data.NonTensor property) (torchrl.data.OneHot property) (torchrl.data.Stacked property) (torchrl.data.StackedComposite property) (torchrl.data.TensorSpec property) (torchrl.data.Unbounded property) (torchrl.data.UnboundedContinuous property) (torchrl.data.UnboundedDiscrete property) ndimension() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) NestedStorageCheckpointer (class in torchrl.data.replay_buffers) NetworkConfig (class in torchrl.trainers.algorithms.configs.modules) next() (torchrl.collectors.llm.RayLLMCollector method) (torchrl.data.datasets.AtariDQNExperienceReplay method) (torchrl.data.datasets.D4RLExperienceReplay method) (torchrl.data.datasets.GenDGRLExperienceReplay method) (torchrl.data.datasets.MinariExperienceReplay method) (torchrl.data.datasets.OpenMLExperienceReplay method) (torchrl.data.datasets.OpenXExperienceReplay method) (torchrl.data.datasets.RobosetExperienceReplay method) (torchrl.data.datasets.VD4RLExperienceReplay method) (torchrl.data.PrioritizedReplayBuffer method) (torchrl.data.RayReplayBuffer method) (torchrl.data.RemoteTensorDictReplayBuffer method) (torchrl.data.ReplayBuffer method) (torchrl.data.ReplayBufferEnsemble method) (torchrl.data.TensorDictPrioritizedReplayBuffer method) (torchrl.data.TensorDictReplayBuffer method) NonTensor (class in torchrl.data) NoopResetEnv (class in torchrl.envs.transforms) NoopResetEnvConfig (class in torchrl.trainers.algorithms.configs.transforms) NormalParamExtractor (class in torchrl.modules) NoWeightSyncScheme (class in torchrl.weight_update) num_samples (torchrl.modules.llm.RemoteTransformersWrapper property)

O

ObsDecoder (class in torchrl.modules) ObsEncoder (class in torchrl.modules) observation_keys (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) observation_spec (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) observation_spec_unbatched (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) ObservationNorm (class in torchrl.envs.transforms) ObservationNormConfig (class in torchrl.trainers.algorithms.configs.transforms) ObservationTransform (class in torchrl.envs.transforms) one() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method)

OneHot (class in torchrl.data) OneHotCategorical (class in torchrl.modules) ones() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) ones_update() (torchrl.data.Composite method) (torchrl.data.StackedComposite method) OnlineDTActor (class in torchrl.modules) OnlineDTLoss (class in torchrl.objectives) OpenMLEnv() (in module torchrl.envs) OpenMLEnvConfig (class in torchrl.trainers.algorithms.configs.envs_libs) OpenMLExperienceReplay (class in torchrl.data.datasets) OpenSpielEnv() (in module torchrl.envs) OpenSpielEnvConfig (class in torchrl.trainers.algorithms.configs.envs_libs) OpenSpielWrapper() (in module torchrl.envs) OpenXExperienceReplay (class in torchrl.data.datasets) OptimizerHook (class in torchrl.trainers) OrnsteinUhlenbeckProcessModule (class in torchrl.modules) out_keys (torchrl.envs.llm.transforms.RayDataLoadingPrimer property) (torchrl.modules.llm.RemoteTransformersWrapper property) out_keys_inv (torchrl.envs.llm.transforms.RayDataLoadingPrimer property) output_spec (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) (torchrl.envs.transforms.TransformedEnv property) output_spec_unbatched (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) output_type (torchrl.objectives.llm.CISPOLoss attribute) (torchrl.objectives.llm.DAPO attribute) (torchrl.objectives.llm.GRPOLoss attribute)

P

pad_output (torchrl.modules.llm.RemoteTransformersWrapper property) padding_value (torchrl.modules.MaskedCategorical property) parallel_env_constructor() (in module torchrl.trainers.helpers) ParallelEnv (class in torchrl.envs) parameters() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) (torchrl.objectives.LossModule method) parent (torchrl.data.llm.TopKRewardSelector property) (torchrl.envs.llm.GSM8KPrepareQuestion property) (torchrl.envs.llm.GSM8KRewardParser property) (torchrl.envs.llm.IfEvalScorer property) (torchrl.envs.llm.transforms.AddThinkingPrompt property) (torchrl.envs.llm.transforms.BrowserTransform property) (torchrl.envs.llm.transforms.DataLoadingPrimer property) (torchrl.envs.llm.transforms.ExecuteToolsInOrder property) (torchrl.envs.llm.transforms.KLComputation property) (torchrl.envs.llm.transforms.KLRewardTransform property) (torchrl.envs.llm.transforms.MCPToolTransform property) (torchrl.envs.llm.transforms.PolicyVersion property) (torchrl.envs.llm.transforms.PythonInterpreter property) (torchrl.envs.llm.transforms.RayDataLoadingPrimer property) (torchrl.envs.llm.transforms.RetrieveKL property) (torchrl.envs.llm.transforms.RetrieveLogProb property) (torchrl.envs.llm.transforms.SimpleToolTransform property) (torchrl.envs.llm.transforms.TemplateTransform property) (torchrl.envs.llm.transforms.Tokenizer property) (torchrl.envs.transforms.Transform property) (torchrl.objectives.llm.MCAdvantage property) pause() (torchrl.collectors.AsyncCollector method) (torchrl.collectors.BaseCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.distributed.DistributedCollector method) (torchrl.collectors.distributed.DistributedDataCollector method) (torchrl.collectors.distributed.DistributedSyncCollector method) (torchrl.collectors.distributed.DistributedSyncDataCollector method) (torchrl.collectors.distributed.RayCollector method) (torchrl.collectors.distributed.RPCCollector method) (torchrl.collectors.distributed.RPCDataCollector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) PendulumEnv (class in torchrl.envs) PermuteTransform (class in torchrl.envs.transforms) PermuteTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) PettingZooEnv() (in module torchrl.envs) PettingZooEnvConfig (class in torchrl.trainers.algorithms.configs.envs_libs) PettingZooWrapper() (in module torchrl.envs) PinMemoryTransform (class in torchrl.envs.transforms) PinMemoryTransformConfig (class in torchrl.trainers.algorithms.configs.transforms)

PixelRenderTransform() (in module torchrl.record) policy_version (torchrl.collectors.AsyncCollector property) (torchrl.collectors.Collector property) (torchrl.collectors.llm.LLMCollector property) (torchrl.collectors.llm.RayLLMCollector property) (torchrl.collectors.MultiAsyncCollector property) (torchrl.collectors.MultiCollector property) (torchrl.collectors.MultiSyncCollector property) PolicyVersion (class in torchrl.envs.llm.transforms) poll_and_apply() (torchrl.weight_update.llm.VLLMDoubleBufferWeightReceiver method) (torchrl.weight_update.llm.VLLMWeightReceiver method) pop() (torchrl.data.Composite method) (torchrl.data.StackedComposite method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.transforms.Compose method) post_hooks (torchrl.collectors.distributed.DistributedWeightUpdater property) (torchrl.collectors.distributed.RPCWeightUpdater property) (torchrl.collectors.llm.vLLMUpdater property) (torchrl.collectors.llm.vLLMUpdaterV2 property) (torchrl.collectors.MultiProcessedWeightUpdater property) (torchrl.collectors.RayWeightUpdater property) (torchrl.collectors.VanillaWeightUpdater property) (torchrl.collectors.WeightUpdaterBase property) PPOLoss (class in torchrl.objectives) PPOLossConfig (class in torchrl.trainers.algorithms.configs.objectives) PPOTrainer (class in torchrl.trainers.algorithms) PPOTrainerConfig (class in torchrl.trainers.algorithms.configs.trainers) prepare_weights() (torchrl.weight_update.DistributedWeightSyncScheme method) (torchrl.weight_update.llm.VLLMDoubleBufferSyncScheme method) (torchrl.weight_update.llm.VLLMWeightSyncScheme method) (torchrl.weight_update.MultiProcessWeightSyncScheme method) (torchrl.weight_update.NoWeightSyncScheme method) (torchrl.weight_update.RayModuleTransformScheme method) (torchrl.weight_update.RayWeightSyncScheme method) (torchrl.weight_update.RPCWeightSyncScheme method) (torchrl.weight_update.SharedMemWeightSyncScheme method) (torchrl.weight_update.WeightSyncScheme method) preprocess() (torchrl.data.datasets.AtariDQNExperienceReplay method) (torchrl.data.datasets.D4RLExperienceReplay method) (torchrl.data.datasets.GenDGRLExperienceReplay method) (torchrl.data.datasets.MinariExperienceReplay method) (torchrl.data.datasets.OpenMLExperienceReplay method) (torchrl.data.datasets.OpenXExperienceReplay method) (torchrl.data.datasets.RobosetExperienceReplay method) (torchrl.data.datasets.VD4RLExperienceReplay method) primers (torchrl.envs.llm.transforms.RayDataLoadingPrimer property) PrioritizedReplayBuffer (class in torchrl.data) PrioritizedSampler (class in torchrl.data.replay_buffers) PrioritizedSamplerConfig (class in torchrl.trainers.algorithms.configs.data) PrioritizedSliceSampler (class in torchrl.data.replay_buffers) ProbabilisticActor (class in torchrl.modules.tensordict_module) ProcessorAsyncEnvPool (class in torchrl.envs) ProcgenWrapper() (in module torchrl.envs) profile_config (torchrl.collectors.AsyncCollector property) (torchrl.collectors.BaseCollector property) (torchrl.collectors.Collector property) (torchrl.collectors.distributed.DistributedCollector property) (torchrl.collectors.distributed.DistributedDataCollector property) (torchrl.collectors.distributed.DistributedSyncCollector property) (torchrl.collectors.distributed.DistributedSyncDataCollector property) (torchrl.collectors.distributed.RayCollector property) (torchrl.collectors.distributed.RPCCollector property) (torchrl.collectors.distributed.RPCDataCollector property) (torchrl.collectors.llm.LLMCollector property) (torchrl.collectors.llm.RayLLMCollector property) (torchrl.collectors.MultiAsyncCollector property) (torchrl.collectors.MultiCollector property) (torchrl.collectors.MultiSyncCollector property) project() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) PUCTScore (class in torchrl.modules.mcts) push_weights() (torchrl.collectors.distributed.DistributedWeightUpdater method) (torchrl.collectors.distributed.RPCWeightUpdater method) (torchrl.collectors.llm.vLLMUpdater method) (torchrl.collectors.llm.vLLMUpdaterV2 method) (torchrl.collectors.MultiProcessedWeightUpdater method) (torchrl.collectors.RayWeightUpdater method) (torchrl.collectors.VanillaWeightUpdater method) (torchrl.collectors.WeightUpdaterBase method), [1] push_weights_from_transformers() (torchrl.collectors.llm.vLLMUpdaterV2 method) push_weights_from_transformers_optimized() (torchrl.collectors.llm.vLLMUpdaterV2 method) PythonExecutorService (class in torchrl.envs.llm.transforms) PythonInterpreter (class in torchrl.envs.llm.transforms)

Q

qvalue_loss() (torchrl.objectives.CrossQLoss method) (torchrl.objectives.TD3BCLoss method)

QValueActor (class in torchrl.modules) QValueModule (class in torchrl.modules)

R

R3MTransform (class in torchrl.envs.transforms) R3MTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) RAdamConfig (class in torchrl.trainers.algorithms.configs.utils) rand() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) rand_action() (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.envs.transforms.TransformedEnv method) rand_step() (in module torchrl.envs) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method), [1] (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) rand_update() (torchrl.data.Composite method) (torchrl.data.StackedComposite method) random() (torchrl.modules.tensordict_module.SafeModule method) (torchrl.modules.tensordict_module.SafeProbabilisticModule method) random_sample() (torchrl.modules.tensordict_module.SafeModule method) (torchrl.modules.tensordict_module.SafeProbabilisticModule method) RandomCropTensorDict (class in torchrl.envs.transforms) RandomCropTensorDictConfig (class in torchrl.trainers.algorithms.configs.transforms) RandomPolicy (class in torchrl.modules.tensordict_module) RandomSampler (class in torchrl.data.replay_buffers) RandomSamplerConfig (class in torchrl.trainers.algorithms.configs.data) RayCollector (class in torchrl.collectors.distributed) RayDataLoadingPrimer (class in torchrl.envs.llm.transforms) RayLLMCollector (class in torchrl.collectors.llm) RayModuleTransformScheme (class in torchrl.weight_update) RayReplayBuffer (class in torchrl.data) RayService (class in torchrl.services) RayTransport (class in torchrl.weight_update) RayWeightSyncScheme (class in torchrl.weight_update) RayWeightUpdater (class in torchrl.collectors) read_action() (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.MLGymWrapper method) read_done() (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.MLGymWrapper method) read_obs() (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.MLGymWrapper method) read_reward() (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.MLGymWrapper method) receive() (torchrl.weight_update.DistributedWeightSyncScheme method) (torchrl.weight_update.llm.VLLMDoubleBufferSyncScheme method) (torchrl.weight_update.llm.VLLMWeightSyncScheme method) (torchrl.weight_update.MultiProcessWeightSyncScheme method) (torchrl.weight_update.NoWeightSyncScheme method) (torchrl.weight_update.RayModuleTransformScheme method) (torchrl.weight_update.RayWeightSyncScheme method) (torchrl.weight_update.RPCWeightSyncScheme method) (torchrl.weight_update.SharedMemWeightSyncScheme method) (torchrl.weight_update.WeightSyncScheme method) receive_initial_weights() (torchrl.weight_update.DistributedTransport method) receive_weights() (torchrl.collectors.AsyncCollector method) (torchrl.collectors.BaseCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.distributed.DistributedCollector method) (torchrl.collectors.distributed.DistributedDataCollector method) (torchrl.collectors.distributed.DistributedSyncCollector method) (torchrl.collectors.distributed.DistributedSyncDataCollector method) (torchrl.collectors.distributed.RayCollector method) (torchrl.collectors.distributed.RPCCollector method) (torchrl.collectors.distributed.RPCDataCollector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) (torchrl.weight_update.DistributedTransport method) (torchrl.weight_update.llm.VLLMCollectiveTransport method) (torchrl.weight_update.llm.VLLMDoubleBufferTransport method) (torchrl.weight_update.MPTransport method) (torchrl.weight_update.RayTransport method) (torchrl.weight_update.RPCTransport method) (torchrl.weight_update.SharedMemTransport method) (torchrl.weight_update.TransportBackend method) receiver_transport (torchrl.weight_update.DistributedWeightSyncScheme property) (torchrl.weight_update.llm.VLLMDoubleBufferSyncScheme property) (torchrl.weight_update.llm.VLLMWeightSyncScheme property) (torchrl.weight_update.MultiProcessWeightSyncScheme property) (torchrl.weight_update.NoWeightSyncScheme property) (torchrl.weight_update.RayModuleTransformScheme property) (torchrl.weight_update.RayWeightSyncScheme property) (torchrl.weight_update.RPCWeightSyncScheme property) (torchrl.weight_update.SharedMemWeightSyncScheme property) (torchrl.weight_update.WeightSyncScheme property) REDQLoss (class in torchrl.objectives) refine_names() (torchrl.data.Composite method) (torchrl.data.StackedComposite method) register() (torchrl.envs.llm.transforms.ToolRegistry method) (torchrl.services.RayService method) (torchrl.services.ServiceBase method) (torchrl.trainers.BatchSubSampler method) (torchrl.trainers.ClearCudaCache method) (torchrl.trainers.CountFramesLog method) (torchrl.trainers.LogScalar method) (torchrl.trainers.LogValidationReward method) (torchrl.trainers.OptimizerHook method) (torchrl.trainers.ReplayBufferTrainer method) (torchrl.trainers.RewardNormalizer method) (torchrl.trainers.SelectKeys method) (torchrl.trainers.TargetNetUpdaterHook method) (torchrl.trainers.TrainerHookBase method) (torchrl.trainers.UpdateWeights method) (torchrl.trainers.UTDRHook method) register_backward_hook() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) register_buffer() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) register_collector() (torchrl.collectors.distributed.DistributedWeightUpdater method) (torchrl.collectors.distributed.RPCWeightUpdater method) (torchrl.collectors.llm.vLLMUpdater method) (torchrl.collectors.llm.vLLMUpdaterV2 method) (torchrl.collectors.MultiProcessedWeightUpdater method) (torchrl.collectors.RayWeightUpdater method) (torchrl.collectors.VanillaWeightUpdater method) (torchrl.collectors.WeightUpdaterBase method), [1] (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) register_forward_hook() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) register_forward_pre_hook() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) register_full_backward_hook() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) register_full_backward_pre_hook() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) register_gym() (torchrl.envs.AsyncEnvPool class method) (torchrl.envs.ChessEnv class method) (torchrl.envs.EnvBase class method) (torchrl.envs.GymLikeEnv class method) (torchrl.envs.llm.ChatEnv class method) (torchrl.envs.llm.DatasetChatEnv class method) (torchrl.envs.llm.GSM8KEnv class method) (torchrl.envs.llm.IFEvalEnv class method) (torchrl.envs.llm.LLMEnv class method) (torchrl.envs.llm.LLMHashingEnv class method) (torchrl.envs.llm.MLGymWrapper class method) (torchrl.envs.LLMHashingEnv class method) (torchrl.envs.ParallelEnv class method) (torchrl.envs.PendulumEnv class method) (torchrl.envs.ProcessorAsyncEnvPool class method) (torchrl.envs.SerialEnv class method) (torchrl.envs.ThreadingAsyncEnvPool class method) (torchrl.envs.TicTacToeEnv class method) register_gym_spec_conversion() (in module torchrl.envs) register_keys() (torchrl.envs.transforms.EndOfLifeTransform method) register_load_hook() (torchrl.data.datasets.AtariDQNExperienceReplay method) (torchrl.data.datasets.D4RLExperienceReplay method) (torchrl.data.datasets.GenDGRLExperienceReplay method) (torchrl.data.datasets.MinariExperienceReplay method) (torchrl.data.datasets.OpenMLExperienceReplay method) (torchrl.data.datasets.OpenXExperienceReplay method) (torchrl.data.datasets.RobosetExperienceReplay method) (torchrl.data.datasets.VD4RLExperienceReplay method) (torchrl.data.PrioritizedReplayBuffer method) (torchrl.data.RayReplayBuffer method) (torchrl.data.RemoteTensorDictReplayBuffer method) (torchrl.data.replay_buffers.CompressedListStorage method) (torchrl.data.replay_buffers.CompressedListStorageCheckpointer method) (torchrl.data.replay_buffers.FlatStorageCheckpointer method) (torchrl.data.replay_buffers.H5StorageCheckpointer method) (torchrl.data.replay_buffers.LazyMemmapStorage method) (torchrl.data.replay_buffers.LazyStackStorage method) (torchrl.data.replay_buffers.LazyTensorStorage method) (torchrl.data.replay_buffers.ListStorage method) (torchrl.data.replay_buffers.ListStorageCheckpointer method) (torchrl.data.replay_buffers.NestedStorageCheckpointer method) (torchrl.data.replay_buffers.Storage method) (torchrl.data.replay_buffers.StorageCheckpointerBase method) (torchrl.data.replay_buffers.StorageEnsemble method) (torchrl.data.replay_buffers.StorageEnsembleCheckpointer method) (torchrl.data.replay_buffers.TensorStorage method) (torchrl.data.replay_buffers.TensorStorageCheckpointer method) (torchrl.data.ReplayBuffer method) (torchrl.data.ReplayBufferEnsemble method) (torchrl.data.TensorDictPrioritizedReplayBuffer method) (torchrl.data.TensorDictReplayBuffer method) register_load_state_dict_post_hook() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) register_load_state_dict_pre_hook() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method)

register_model() (torchrl.weight_update.llm.VLLMDoubleBufferWeightSender method) (torchrl.weight_update.llm.VLLMWeightSender method) register_module() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) register_parameter() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) register_post_hook() (torchrl.collectors.distributed.DistributedWeightUpdater method) (torchrl.collectors.distributed.RPCWeightUpdater method) (torchrl.collectors.llm.vLLMUpdater method) (torchrl.collectors.llm.vLLMUpdaterV2 method) (torchrl.collectors.MultiProcessedWeightUpdater method) (torchrl.collectors.RayWeightUpdater method) (torchrl.collectors.VanillaWeightUpdater method) (torchrl.collectors.WeightUpdaterBase method) register_save_hook() (torchrl.data.datasets.AtariDQNExperienceReplay method) (torchrl.data.datasets.D4RLExperienceReplay method) (torchrl.data.datasets.GenDGRLExperienceReplay method) (torchrl.data.datasets.MinariExperienceReplay method) (torchrl.data.datasets.OpenMLExperienceReplay method) (torchrl.data.datasets.OpenXExperienceReplay method) (torchrl.data.datasets.RobosetExperienceReplay method) (torchrl.data.datasets.VD4RLExperienceReplay method) (torchrl.data.PrioritizedReplayBuffer method) (torchrl.data.RayReplayBuffer method) (torchrl.data.RemoteTensorDictReplayBuffer method) (torchrl.data.replay_buffers.CompressedListStorage method) (torchrl.data.replay_buffers.CompressedListStorageCheckpointer method) (torchrl.data.replay_buffers.FlatStorageCheckpointer method) (torchrl.data.replay_buffers.H5StorageCheckpointer method) (torchrl.data.replay_buffers.LazyMemmapStorage method) (torchrl.data.replay_buffers.LazyStackStorage method) (torchrl.data.replay_buffers.LazyTensorStorage method) (torchrl.data.replay_buffers.ListStorage method) (torchrl.data.replay_buffers.ListStorageCheckpointer method) (torchrl.data.replay_buffers.NestedStorageCheckpointer method) (torchrl.data.replay_buffers.Storage method) (torchrl.data.replay_buffers.StorageCheckpointerBase method) (torchrl.data.replay_buffers.StorageEnsemble method) (torchrl.data.replay_buffers.StorageEnsembleCheckpointer method) (torchrl.data.replay_buffers.TensorStorage method) (torchrl.data.replay_buffers.TensorStorageCheckpointer method) (torchrl.data.ReplayBuffer method) (torchrl.data.ReplayBufferEnsemble method) (torchrl.data.TensorDictPrioritizedReplayBuffer method) (torchrl.data.TensorDictReplayBuffer method) register_scheme_receiver() (torchrl.collectors.AsyncCollector method) (torchrl.collectors.BaseCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.distributed.DistributedCollector method) (torchrl.collectors.distributed.DistributedDataCollector method) (torchrl.collectors.distributed.DistributedSyncCollector method) (torchrl.collectors.distributed.DistributedSyncDataCollector method) (torchrl.collectors.distributed.RayCollector method) (torchrl.collectors.distributed.RPCCollector method) (torchrl.collectors.distributed.RPCDataCollector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) register_state_dict_post_hook() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) register_state_dict_pre_hook() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) register_weights() (torchrl.weight_update.SharedMemTransport method) register_with_options() (torchrl.services.RayService method) ReinforceLoss (class in torchrl.objectives) remote_collectors (torchrl.collectors.distributed.RayCollector property) RemoteTensorDictReplayBuffer (class in torchrl.data) RemoteTransformersWrapper (class in torchrl.modules.llm) RemoveEmptySpecs (class in torchrl.envs.transforms) RemoveEmptySpecsConfig (class in torchrl.trainers.algorithms.configs.transforms) RenameTransform (class in torchrl.envs.transforms) RenameTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) ReparamGradientStrategy (class in torchrl.modules) repeat_interleave_causal() (torchrl.modules.llm.TransformersWrapper method) repeats (torchrl.envs.llm.transforms.RayDataLoadingPrimer property) ReplayBuffer (class in torchrl.data) ReplayBufferConfig (class in torchrl.trainers.algorithms.configs.data) ReplayBufferEnsemble (class in torchrl.data) ReplayBufferTrainer (class in torchrl.trainers) reproducible_hash() (torchrl.envs.transforms.Hash class method) requires_grad_() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) reset() (in module torchrl.envs) (torchrl.collectors.AsyncCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method), [1] (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method), [1] (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.implement_for class method) (torchrl.services.RayService method) (torchrl.services.ServiceBase method) reset_dataloader() (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) reset_keys (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) reset_out_keys() (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.SFTLoss method) reset_parameters_recursive() (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.SFTLoss method) (torchrl.objectives.LossModule method) reset_parent() (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.transforms.Transform method) reshape() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) Resize (class in torchrl.envs.transforms) ResizeConfig (class in torchrl.trainers.algorithms.configs.transforms) RetrieveKL (class in torchrl.envs.llm.transforms) RetrieveLogProb (class in torchrl.envs.llm.transforms) Reward2GoTransform (class in torchrl.envs.transforms) Reward2GoTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) reward_key (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) reward_keys (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) reward_spec (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) reward_spec_unbatched (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) RewardClipping (class in torchrl.envs.transforms) RewardClippingConfig (class in torchrl.trainers.algorithms.configs.transforms) RewardNormalizer (class in torchrl.trainers) RewardScaling (class in torchrl.envs.transforms) RewardScalingConfig (class in torchrl.trainers.algorithms.configs.transforms) RewardSum (class in torchrl.envs.transforms) RewardSumConfig (class in torchrl.trainers.algorithms.configs.transforms) RMSpropConfig (class in torchrl.trainers.algorithms.configs.utils) RoboHiveEnv() (in module torchrl.envs) RoboHiveEnvConfig (class in torchrl.trainers.algorithms.configs.envs_libs) RobosetExperienceReplay (class in torchrl.data.datasets) rollout (torchrl.collectors.llm.LLMCollector property) (torchrl.collectors.llm.RayLLMCollector property) rollout() (in module torchrl.envs) (torchrl.collectors.Collector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method), [1] (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) RoundRobinWriter (class in torchrl.data.replay_buffers) RoundRobinWriterConfig (class in torchrl.trainers.algorithms.configs.data) RPCCollector (class in torchrl.collectors.distributed) RPCDataCollector (class in torchrl.collectors.distributed) RPCTransport (class in torchrl.weight_update) RPCWeightSyncScheme (class in torchrl.weight_update) RPCWeightUpdater (class in torchrl.collectors.distributed) RpropConfig (class in torchrl.trainers.algorithms.configs.utils) rsample() (torchrl.modules.Delta method) (torchrl.modules.OneHotCategorical method) RSSMPosterior (class in torchrl.modules) RSSMPrior (class in torchrl.modules) RSSMRollout (class in torchrl.modules)

S

SACLoss (class in torchrl.objectives) SACTrainer (class in torchrl.trainers.algorithms) SafeModule (class in torchrl.modules.tensordict_module) SafeProbabilisticModule (class in torchrl.modules.tensordict_module) SafeProbabilisticTensorDictSequential (class in torchrl.modules.tensordict_module) SafeSequential (class in torchrl.modules.tensordict_module) sample() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.datasets.AtariDQNExperienceReplay method) (torchrl.data.datasets.D4RLExperienceReplay method) (torchrl.data.datasets.GenDGRLExperienceReplay method) (torchrl.data.datasets.MinariExperienceReplay method) (torchrl.data.datasets.OpenMLExperienceReplay method) (torchrl.data.datasets.OpenXExperienceReplay method) (torchrl.data.datasets.RobosetExperienceReplay method) (torchrl.data.datasets.VD4RLExperienceReplay method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.PrioritizedReplayBuffer method) (torchrl.data.RayReplayBuffer method) (torchrl.data.RemoteTensorDictReplayBuffer method) (torchrl.data.ReplayBuffer method) (torchrl.data.ReplayBufferEnsemble method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorDictPrioritizedReplayBuffer method) (torchrl.data.TensorDictReplayBuffer method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) (torchrl.modules.Delta method) (torchrl.modules.MaskedCategorical method) (torchrl.modules.OneHotCategorical method) Sampler (class in torchrl.data.replay_buffers) sampler (torchrl.data.datasets.AtariDQNExperienceReplay property) (torchrl.data.datasets.D4RLExperienceReplay property) (torchrl.data.datasets.GenDGRLExperienceReplay property) (torchrl.data.datasets.MinariExperienceReplay property) (torchrl.data.datasets.OpenMLExperienceReplay property) (torchrl.data.datasets.OpenXExperienceReplay property) (torchrl.data.datasets.RobosetExperienceReplay property) (torchrl.data.datasets.VD4RLExperienceReplay property) (torchrl.data.PrioritizedReplayBuffer property) (torchrl.data.RayReplayBuffer property) (torchrl.data.RemoteTensorDictReplayBuffer property) (torchrl.data.ReplayBuffer property) (torchrl.data.ReplayBufferEnsemble property) (torchrl.data.TensorDictPrioritizedReplayBuffer property) (torchrl.data.TensorDictReplayBuffer property) SamplerEnsemble (class in torchrl.data.replay_buffers) SamplerWithoutReplacement (class in torchrl.data.replay_buffers) SamplerWithoutReplacementConfig (class in torchrl.trainers.algorithms.configs.data) save() (torchrl.data.datasets.AtariDQNExperienceReplay method) (torchrl.data.datasets.D4RLExperienceReplay method) (torchrl.data.datasets.GenDGRLExperienceReplay method) (torchrl.data.datasets.MinariExperienceReplay method) (torchrl.data.datasets.OpenMLExperienceReplay method) (torchrl.data.datasets.OpenXExperienceReplay method) (torchrl.data.datasets.RobosetExperienceReplay method) (torchrl.data.datasets.VD4RLExperienceReplay method) (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.data.PrioritizedReplayBuffer method) (torchrl.data.RayReplayBuffer method) (torchrl.data.RemoteTensorDictReplayBuffer method) (torchrl.data.replay_buffers.CompressedListStorage method) (torchrl.data.replay_buffers.LazyMemmapStorage method) (torchrl.data.replay_buffers.LazyStackStorage method) (torchrl.data.replay_buffers.LazyTensorStorage method) (torchrl.data.replay_buffers.ListStorage method) (torchrl.data.replay_buffers.Storage method) (torchrl.data.replay_buffers.StorageEnsemble method) (torchrl.data.replay_buffers.TensorStorage method) (torchrl.data.ReplayBuffer method) (torchrl.data.ReplayBufferEnsemble method) (torchrl.data.TensorDictPrioritizedReplayBuffer method) (torchrl.data.TensorDictReplayBuffer method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) scale (torchrl.envs.transforms.VecNorm property) (torchrl.envs.transforms.VecNormV2 property) scale() (torchrl.envs.transforms.VecNormV2 method) select_out_keys() (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.SFTLoss method) SelectKeys (class in torchrl.trainers) SelectTransform (class in torchrl.envs.transforms) SelectTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) send() (torchrl.weight_update.DistributedWeightSyncScheme method) (torchrl.weight_update.llm.VLLMDoubleBufferSyncScheme method) (torchrl.weight_update.llm.VLLMWeightSyncScheme method) (torchrl.weight_update.MultiProcessWeightSyncScheme method) (torchrl.weight_update.NoWeightSyncScheme method) (torchrl.weight_update.RayModuleTransformScheme method) (torchrl.weight_update.RayWeightSyncScheme method) (torchrl.weight_update.RPCWeightSyncScheme method) (torchrl.weight_update.SharedMemWeightSyncScheme method) (torchrl.weight_update.WeightSyncScheme method) send_ack() (torchrl.weight_update.SharedMemTransport method) send_initial_weights() (torchrl.weight_update.DistributedTransport method) send_weights() (torchrl.weight_update.DistributedTransport method) (torchrl.weight_update.llm.VLLMCollectiveTransport method) (torchrl.weight_update.llm.VLLMDoubleBufferTransport method) (torchrl.weight_update.RayTransport method) (torchrl.weight_update.RPCTransport method) (torchrl.weight_update.SharedMemTransport method) (torchrl.weight_update.TransportBackend method) send_weights_async() (torchrl.weight_update.DistributedTransport method) (torchrl.weight_update.MPTransport method) (torchrl.weight_update.RayTransport method) (torchrl.weight_update.RPCTransport method) sender_transports (torchrl.weight_update.DistributedWeightSyncScheme property) (torchrl.weight_update.llm.VLLMDoubleBufferSyncScheme property) (torchrl.weight_update.llm.VLLMWeightSyncScheme property) (torchrl.weight_update.MultiProcessWeightSyncScheme property) (torchrl.weight_update.NoWeightSyncScheme property) (torchrl.weight_update.RayModuleTransformScheme property) (torchrl.weight_update.RayWeightSyncScheme property) (torchrl.weight_update.RPCWeightSyncScheme property) (torchrl.weight_update.SharedMemWeightSyncScheme property) (torchrl.weight_update.WeightSyncScheme property) separates() (torchrl.data.Composite method) (torchrl.data.StackedComposite method) SerialEnv (class in torchrl.envs) ServiceBase (class in torchrl.services) set() (torchrl.data.Composite method) (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.data.StackedComposite method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) set_auto_unwrap_transformed_env (class in torchrl) set_container() (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.transforms.Transform method) set_exploration_modules_spec_from_env (class in torchrl.modules) set_exploration_type() (in module torchrl.envs) set_extra_state() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.envs.transforms.VecNorm method) (torchrl.envs.transforms.VecNormV2 method), [1] (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) set_gym_backend() (in module torchrl.envs) set_info_dict_reader() (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.MLGymWrapper method) set_keys() (torchrl.objectives.CrossQLoss method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.SFTLoss method) (torchrl.objectives.LossModule method) (torchrl.objectives.value.ValueEstimatorBase method) set_missing_tolerance() (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.transforms.TransformedEnv method) set_model() (torchrl.weight_update.RayTransport method) set_provisional_n() (torchrl.data.Binary method) (torchrl.data.Categorical method) (torchrl.data.MultiCategorical method) set_recurrent_mode() (torchrl.modules.GRUModule method) (torchrl.modules.LSTMModule method) set_sampler() (torchrl.data.datasets.AtariDQNExperienceReplay method) (torchrl.data.datasets.D4RLExperienceReplay method) (torchrl.data.datasets.GenDGRLExperienceReplay method) (torchrl.data.datasets.MinariExperienceReplay method) (torchrl.data.datasets.OpenMLExperienceReplay method) (torchrl.data.datasets.OpenXExperienceReplay method) (torchrl.data.datasets.RobosetExperienceReplay method) (torchrl.data.datasets.VD4RLExperienceReplay method) (torchrl.data.PrioritizedReplayBuffer method) (torchrl.data.RayReplayBuffer method) (torchrl.data.RemoteTensorDictReplayBuffer method) (torchrl.data.ReplayBuffer method) (torchrl.data.ReplayBufferEnsemble method) (torchrl.data.TensorDictPrioritizedReplayBuffer method) (torchrl.data.TensorDictReplayBuffer method) set_seed() (in module torchrl.envs) (torchrl.collectors.AsyncCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.distributed.RayCollector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method), [1] (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.envs.transforms.TransformedEnv method) set_spec_lock_() (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) set_storage() (torchrl.data.datasets.AtariDQNExperienceReplay method) (torchrl.data.datasets.D4RLExperienceReplay method) (torchrl.data.datasets.GenDGRLExperienceReplay method) (torchrl.data.datasets.MinariExperienceReplay method) (torchrl.data.datasets.OpenMLExperienceReplay method) (torchrl.data.datasets.OpenXExperienceReplay method) (torchrl.data.datasets.RobosetExperienceReplay method) (torchrl.data.datasets.VD4RLExperienceReplay method) (torchrl.data.PrioritizedReplayBuffer method) (torchrl.data.RayReplayBuffer method) (torchrl.data.RemoteTensorDictReplayBuffer method) (torchrl.data.ReplayBuffer method) (torchrl.data.ReplayBufferEnsemble method) (torchrl.data.TensorDictPrioritizedReplayBuffer method) (torchrl.data.TensorDictReplayBuffer method) set_submodule() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) set_tokenizer() (torchrl.modules.llm.vLLMWrapper method) set_writer() (torchrl.data.datasets.AtariDQNExperienceReplay method) (torchrl.data.datasets.D4RLExperienceReplay method) (torchrl.data.datasets.GenDGRLExperienceReplay method) (torchrl.data.datasets.MinariExperienceReplay method) (torchrl.data.datasets.OpenMLExperienceReplay method) (torchrl.data.datasets.OpenXExperienceReplay method) (torchrl.data.datasets.RobosetExperienceReplay method) (torchrl.data.datasets.VD4RLExperienceReplay method) (torchrl.data.PrioritizedReplayBuffer method) (torchrl.data.RayReplayBuffer method) (torchrl.data.RemoteTensorDictReplayBuffer method) (torchrl.data.ReplayBuffer method) (torchrl.data.ReplayBufferEnsemble method) (torchrl.data.TensorDictPrioritizedReplayBuffer method) (torchrl.data.TensorDictReplayBuffer method) setup_connection_and_weights_on_receiver() (torchrl.weight_update.DistributedTransport method) (torchrl.weight_update.MPTransport method) (torchrl.weight_update.RayTransport method) (torchrl.weight_update.RPCTransport method) (torchrl.weight_update.SharedMemTransport method) (torchrl.weight_update.TransportBackend method) setup_connection_and_weights_on_sender() (torchrl.weight_update.DistributedTransport method) (torchrl.weight_update.MPTransport method) (torchrl.weight_update.RayTransport method) (torchrl.weight_update.RPCTransport method) (torchrl.weight_update.SharedMemTransport method) (torchrl.weight_update.TransportBackend method) SFTLoss (class in torchrl.objectives.llm) SFTLossOutput (class in torchrl.objectives.llm) SGDConfig (class in torchrl.trainers.algorithms.configs.utils) shape (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property)

share_memory() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) shared_transport (torchrl.weight_update.DistributedWeightSyncScheme property) (torchrl.weight_update.llm.VLLMDoubleBufferSyncScheme property) (torchrl.weight_update.llm.VLLMWeightSyncScheme property) (torchrl.weight_update.MultiProcessWeightSyncScheme property) (torchrl.weight_update.NoWeightSyncScheme property) (torchrl.weight_update.RayModuleTransformScheme property) (torchrl.weight_update.RayWeightSyncScheme property) (torchrl.weight_update.RPCWeightSyncScheme property) (torchrl.weight_update.SharedMemWeightSyncScheme property) (torchrl.weight_update.WeightSyncScheme property) SharedMemTransport (class in torchrl.weight_update) SharedMemWeightSyncScheme (class in torchrl.weight_update) shutdown() (torchrl.collectors.AsyncCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.distributed.RayCollector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.modules.llm.AsyncVLLM method) (torchrl.services.RayService method) (torchrl.weight_update.DistributedWeightSyncScheme method) (torchrl.weight_update.llm.VLLMDoubleBufferSyncScheme method) (torchrl.weight_update.llm.VLLMWeightSyncScheme method) (torchrl.weight_update.MultiProcessWeightSyncScheme method) (torchrl.weight_update.NoWeightSyncScheme method) (torchrl.weight_update.RayModuleTransformScheme method) (torchrl.weight_update.RayWeightSyncScheme method) (torchrl.weight_update.RPCWeightSyncScheme method) (torchrl.weight_update.SharedMemWeightSyncScheme method) (torchrl.weight_update.WeightSyncScheme method) SignTransform (class in torchrl.envs.transforms) SignTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) SimpleToolTransform (class in torchrl.envs.llm.transforms) SliceSampler (class in torchrl.data.replay_buffers) SliceSamplerConfig (class in torchrl.trainers.algorithms.configs.data) SliceSamplerWithoutReplacement (class in torchrl.data.replay_buffers) SliceSamplerWithoutReplacementConfig (class in torchrl.trainers.algorithms.configs.data) SMACv2Env() (in module torchrl.envs) SMACv2EnvConfig (class in torchrl.trainers.algorithms.configs.envs_libs) SMACv2Wrapper() (in module torchrl.envs) SparseAdamConfig (class in torchrl.trainers.algorithms.configs.utils) specs (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) split_trajectories() (in module torchrl.collectors.utils) SquashDims (class in torchrl.modules.models.utils) squeeze() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) SqueezeTransform (class in torchrl.envs.transforms) SqueezeTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) Stack (class in torchrl.envs.transforms) stack() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) stack_method (torchrl.envs.llm.transforms.RayDataLoadingPrimer property) StackConfig (class in torchrl.trainers.algorithms.configs.transforms) Stacked (class in torchrl.data) StackedComposite (class in torchrl.data) standard_normal (torchrl.envs.transforms.VecNorm property) (torchrl.envs.transforms.VecNormV2 property) standard_normal() (torchrl.envs.transforms.VecNormV2 method) start() (torchrl.collectors.AsyncCollector method) (torchrl.collectors.BaseCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.distributed.DistributedCollector method) (torchrl.collectors.distributed.DistributedDataCollector method) (torchrl.collectors.distributed.DistributedSyncCollector method) (torchrl.collectors.distributed.DistributedSyncDataCollector method) (torchrl.collectors.distributed.RayCollector method) (torchrl.collectors.distributed.RPCCollector method) (torchrl.collectors.distributed.RPCDataCollector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) state_dict() (torchrl.collectors.AsyncCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.distributed.RayCollector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.data.llm.TopKRewardSelector method) (torchrl.data.replay_buffers.CompressedListStorage method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.envs.transforms.Hash method) (torchrl.envs.transforms.TrajCounter method) (torchrl.envs.transforms.TransformedEnv method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.CrossQLoss method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) (torchrl.objectives.llm.SFTLossOutput method) (torchrl.objectives.SACLoss method) (torchrl.trainers.UTDRHook method) state_keys (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) state_spec (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) state_spec_unbatched (torchrl.envs.AsyncEnvPool property) (torchrl.envs.ChessEnv property) (torchrl.envs.EnvBase property) (torchrl.envs.GymLikeEnv property) (torchrl.envs.llm.ChatEnv property) (torchrl.envs.llm.DatasetChatEnv property) (torchrl.envs.llm.GSM8KEnv property) (torchrl.envs.llm.IFEvalEnv property) (torchrl.envs.llm.LLMEnv property) (torchrl.envs.llm.LLMHashingEnv property) (torchrl.envs.llm.MLGymWrapper property) (torchrl.envs.LLMHashingEnv property) (torchrl.envs.ParallelEnv property) (torchrl.envs.PendulumEnv property) (torchrl.envs.ProcessorAsyncEnvPool property) (torchrl.envs.SerialEnv property) (torchrl.envs.ThreadingAsyncEnvPool property) (torchrl.envs.TicTacToeEnv property) stateless_init_process_group (class in torchrl.modules.llm) stateless_init_process_group_async (class in torchrl.modules.llm) step() (in module torchrl.envs) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method), [1] (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method), [1] (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.AdditiveGaussianModule method) (torchrl.modules.EGreedyModule method) (torchrl.modules.OrnsteinUhlenbeckProcessModule method) step_and_maybe_reset() (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) step_mdp() (in module torchrl.envs) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) StepCounter (class in torchrl.envs.transforms) StepCounterConfig (class in torchrl.trainers.algorithms.configs.transforms) stop_remote_collectors() (torchrl.collectors.distributed.RayCollector method) Storage (class in torchrl.data.replay_buffers) storage (torchrl.data.datasets.AtariDQNExperienceReplay property) (torchrl.data.datasets.D4RLExperienceReplay property) (torchrl.data.datasets.GenDGRLExperienceReplay property) (torchrl.data.datasets.MinariExperienceReplay property) (torchrl.data.datasets.OpenMLExperienceReplay property) (torchrl.data.datasets.OpenXExperienceReplay property) (torchrl.data.datasets.RobosetExperienceReplay property) (torchrl.data.datasets.VD4RLExperienceReplay property) (torchrl.data.PrioritizedReplayBuffer property) (torchrl.data.RayReplayBuffer property) (torchrl.data.RemoteTensorDictReplayBuffer property) (torchrl.data.ReplayBuffer property) (torchrl.data.ReplayBufferEnsemble property) (torchrl.data.TensorDictPrioritizedReplayBuffer property) (torchrl.data.TensorDictReplayBuffer property) StorageCheckpointerBase (class in torchrl.data.replay_buffers) StorageEnsemble (class in torchrl.data.replay_buffers) StorageEnsembleCheckpointer (class in torchrl.data.replay_buffers) StorageEnsembleConfig (class in torchrl.trainers.algorithms.configs.data) StorageEnsembleWriterConfig (class in torchrl.trainers.algorithms.configs.data) submitit_delayed_launcher (class in torchrl.collectors.distributed) support (torchrl.modules.TanhNormal property) sync_async_collector() (in module torchrl.trainers.helpers) sync_sync_collector() (in module torchrl.trainers.helpers)

T

TanhDelta (class in torchrl.modules) TanhModule (class in torchrl.modules.tensordict_module) TanhNormal (class in torchrl.modules) TanhNormalModelConfig (class in torchrl.trainers.algorithms.configs.modules) target_entropy_buffer (torchrl.objectives.CrossQLoss property) TargetNetUpdaterHook (class in torchrl.trainers) TargetReturn (class in torchrl.envs.transforms) TargetReturnConfig (class in torchrl.trainers.algorithms.configs.transforms) TD0Estimator (class in torchrl.objectives.value) TD1Estimator (class in torchrl.objectives.value) TD3BCLoss (class in torchrl.objectives) TD3Loss (class in torchrl.objectives) TDLambdaEstimator (class in torchrl.objectives.value) TemplateTransform (class in torchrl.envs.llm.transforms) tensor_keys (torchrl.objectives.llm.CISPOLoss property) (torchrl.objectives.llm.DAPO property) (torchrl.objectives.llm.GRPOLoss property) TensorboardLogger() (in module torchrl.record.loggers.tensorboard) TensorboardLoggerConfig (class in torchrl.trainers.algorithms.configs.logging) TensorDictMaxValueWriter (class in torchrl.data.replay_buffers) TensorDictModuleConfig (class in torchrl.trainers.algorithms.configs.modules) TensorDictPrimer (class in torchrl.envs.transforms) TensorDictPrimerConfig (class in torchrl.trainers.algorithms.configs.transforms) TensorDictPrioritizedReplayBuffer (class in torchrl.data) TensorDictRecorder() (in module torchrl.record) TensorDictReplayBuffer (class in torchrl.data) TensorDictReplayBufferConfig (class in torchrl.trainers.algorithms.configs.data) TensorDictRoundRobinWriter (class in torchrl.data.replay_buffers) TensorSpec (class in torchrl.data) TensorStorage (class in torchrl.data.replay_buffers) TensorStorageCheckpointer (class in torchrl.data.replay_buffers) TensorStorageConfig (class in torchrl.trainers.algorithms.configs.data) terminated_or_truncated() (in module torchrl.envs) Text (class in torchrl.modules.llm) text_key (torchrl.modules.llm.RemoteTransformersWrapper property) ThreadingAsyncEnvPool (class in torchrl.envs) TicTacToeEnv (class in torchrl.envs) TimeMaxPool (class in torchrl.envs.transforms) TimeMaxPoolConfig (class in torchrl.trainers.algorithms.configs.transforms) Timer (class in torchrl.envs.transforms) TimerConfig (class in torchrl.trainers.algorithms.configs.transforms) to() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.llm.TopKRewardSelector method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.envs.transforms.Compose method) (torchrl.envs.transforms.R3MTransform method) (torchrl.envs.transforms.TensorDictPrimer method) (torchrl.envs.transforms.Transform method) (torchrl.envs.transforms.TransformedEnv method) (torchrl.envs.transforms.VC1Transform method) (torchrl.envs.transforms.VIPTransform method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.modules.tensordict_module.SafeModule method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) to_bytestream() (torchrl.data.replay_buffers.CompressedListStorage method) to_categorical() (torchrl.data.Binary method) (torchrl.data.Categorical method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.OneHot method) to_categorical_spec() (torchrl.data.Binary method) (torchrl.data.Categorical method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.OneHot method) to_empty() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) to_history() (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) to_numpy() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) to_observation_norm() (torchrl.envs.transforms.VecNorm method) (torchrl.envs.transforms.VecNormV2 method) to_one_hot() (torchrl.data.Binary method) (torchrl.data.Categorical method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.OneHot method) to_one_hot_spec() (torchrl.data.Binary method) (torchrl.data.Categorical method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.OneHot method) to_tensordict() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) to_text() (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.Tokens method) to_tokens() (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.Text method) Tokenizer (class in torchrl.envs.llm.transforms) (class in torchrl.envs.transforms) TokenizerConfig (class in torchrl.trainers.algorithms.configs.transforms) Tokens (class in torchrl.modules.llm) tokens_key (torchrl.modules.llm.RemoteTransformersWrapper property) ToolCall (class in torchrl.envs.llm.transforms) ToolRegistry (class in torchrl.envs.llm.transforms) ToolService (class in torchrl.envs.llm.transforms) TopKRewardSelector (class in torchrl.data.llm) total_dialog_turns (torchrl.collectors.llm.RayLLMCollector property) ToTensorImage (class in torchrl.envs.transforms) ToTensorImageConfig (class in torchrl.trainers.algorithms.configs.transforms) TrackioLogger() (in module torchrl.record.loggers.trackio) train() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.envs.transforms.TransformedEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) Trainer (class in torchrl.trainers) TrainerConfig (class in torchrl.trainers.algorithms.configs.trainers) TrainerHookBase (class in torchrl.trainers) TrajCounter (class in torchrl.envs.transforms) TrajCounterConfig (class in torchrl.trainers.algorithms.configs.transforms) Transform (class in torchrl.envs.transforms) transform (torchrl.data.datasets.AtariDQNExperienceReplay property) (torchrl.data.datasets.D4RLExperienceReplay property) (torchrl.data.datasets.GenDGRLExperienceReplay property) (torchrl.data.datasets.MinariExperienceReplay property) (torchrl.data.datasets.OpenMLExperienceReplay property) (torchrl.data.datasets.OpenXExperienceReplay property) (torchrl.data.datasets.RobosetExperienceReplay property) (torchrl.data.datasets.VD4RLExperienceReplay property) (torchrl.data.PrioritizedReplayBuffer property) (torchrl.data.RayReplayBuffer property) (torchrl.data.RemoteTensorDictReplayBuffer property) (torchrl.data.ReplayBuffer property) (torchrl.data.ReplayBufferEnsemble property) (torchrl.data.TensorDictPrioritizedReplayBuffer property) (torchrl.data.TensorDictReplayBuffer property) transform_action_spec() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.transforms.Compose method) (torchrl.envs.transforms.DeviceCastTransform method) (torchrl.envs.transforms.ModuleTransform method) (torchrl.envs.transforms.ObservationNorm method) (torchrl.envs.transforms.Transform method) (torchrl.envs.transforms.UnaryTransform method) (torchrl.envs.transforms.UnsqueezeTransform method) (torchrl.objectives.llm.MCAdvantage method) transform_done_spec() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.transforms.DeviceCastTransform method) (torchrl.envs.transforms.ModuleTransform method) (torchrl.envs.transforms.Stack method) (torchrl.envs.transforms.Tokenizer method) (torchrl.envs.transforms.Transform method) (torchrl.envs.transforms.UnaryTransform method) (torchrl.objectives.llm.MCAdvantage method)

transform_env_batch_size() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.transforms.BatchSizeTransform method) (torchrl.envs.transforms.Compose method) (torchrl.envs.transforms.Transform method) (torchrl.objectives.llm.MCAdvantage method) transform_env_device() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.transforms.Compose method) (torchrl.envs.transforms.DeviceCastTransform method) (torchrl.envs.transforms.Transform method) (torchrl.objectives.llm.MCAdvantage method) transform_input_spec() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.transforms.ActionDiscretizer method) (torchrl.envs.transforms.BatchSizeTransform method) (torchrl.envs.transforms.Compose method) (torchrl.envs.transforms.DeviceCastTransform method) (torchrl.envs.transforms.DiscreteActionProjection method) (torchrl.envs.transforms.DTypeCastTransform method) (torchrl.envs.transforms.MultiAction method) (torchrl.envs.transforms.PermuteTransform method) (torchrl.envs.transforms.RemoveEmptySpecs method) (torchrl.envs.transforms.RenameTransform method) (torchrl.envs.transforms.RewardSum method) (torchrl.envs.transforms.Stack method) (torchrl.envs.transforms.StepCounter method) (torchrl.envs.transforms.TargetReturn method) (torchrl.envs.transforms.TensorDictPrimer method) (torchrl.envs.transforms.Tokenizer method) (torchrl.envs.transforms.Transform method) (torchrl.envs.transforms.UnaryTransform method) (torchrl.envs.transforms.VIPRewardTransform method) (torchrl.objectives.llm.MCAdvantage method) transform_observation_spec() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.transforms.CatFrames method) (torchrl.envs.transforms.CatTensors method) (torchrl.envs.transforms.CenterCrop method) (torchrl.envs.transforms.ClipTransform method) (torchrl.envs.transforms.Compose method) (torchrl.envs.transforms.Crop method) (torchrl.envs.transforms.DeviceCastTransform method) (torchrl.envs.transforms.DTypeCastTransform method) (torchrl.envs.transforms.EndOfLifeTransform method) (torchrl.envs.transforms.FlattenObservation method) (torchrl.envs.transforms.GrayScale method) (torchrl.envs.transforms.InitTracker method) (torchrl.envs.transforms.ModuleTransform method) (torchrl.envs.transforms.ObservationNorm method) (torchrl.envs.transforms.PermuteTransform method) (torchrl.envs.transforms.Resize method) (torchrl.envs.transforms.RewardSum method) (torchrl.envs.transforms.SignTransform method) (torchrl.envs.transforms.Stack method) (torchrl.envs.transforms.StepCounter method) (torchrl.envs.transforms.TargetReturn method) (torchrl.envs.transforms.TensorDictPrimer method) (torchrl.envs.transforms.TimeMaxPool method) (torchrl.envs.transforms.Timer method) (torchrl.envs.transforms.Tokenizer method) (torchrl.envs.transforms.ToTensorImage method) (torchrl.envs.transforms.TrajCounter method) (torchrl.envs.transforms.Transform method) (torchrl.envs.transforms.UnaryTransform method) (torchrl.envs.transforms.UnsqueezeTransform method) (torchrl.envs.transforms.VC1Transform method) (torchrl.envs.transforms.VecGymEnvTransform method) (torchrl.envs.transforms.VecNorm method) (torchrl.envs.transforms.VecNormV2 method), [1] (torchrl.objectives.llm.MCAdvantage method) transform_output_spec() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.transforms.BatchSizeTransform method) (torchrl.envs.transforms.Compose method) (torchrl.envs.transforms.DeviceCastTransform method) (torchrl.envs.transforms.DTypeCastTransform method) (torchrl.envs.transforms.ExcludeTransform method) (torchrl.envs.transforms.MultiAction method) (torchrl.envs.transforms.RemoveEmptySpecs method) (torchrl.envs.transforms.RenameTransform method) (torchrl.envs.transforms.SelectTransform method) (torchrl.envs.transforms.StepCounter method) (torchrl.envs.transforms.Tokenizer method) (torchrl.envs.transforms.Transform method) (torchrl.envs.transforms.UnaryTransform method) (torchrl.envs.transforms.VecNormV2 method), [1] (torchrl.objectives.llm.MCAdvantage method) transform_reward_spec() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.transforms.BinarizeReward method) (torchrl.envs.transforms.ClipTransform method) (torchrl.envs.transforms.Compose method) (torchrl.envs.transforms.DeviceCastTransform method) (torchrl.envs.transforms.LineariseRewards method) (torchrl.envs.transforms.ModuleTransform method) (torchrl.envs.transforms.RewardClipping method) (torchrl.envs.transforms.RewardScaling method) (torchrl.envs.transforms.RewardSum method) (torchrl.envs.transforms.SignTransform method) (torchrl.envs.transforms.Stack method) (torchrl.envs.transforms.Tokenizer method) (torchrl.envs.transforms.Transform method) (torchrl.envs.transforms.UnaryTransform method) (torchrl.envs.transforms.UnsqueezeTransform method) (torchrl.envs.transforms.VecNormV2 method), [1] (torchrl.objectives.llm.MCAdvantage method) transform_state_spec() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.transforms.Compose method) (torchrl.envs.transforms.DeviceCastTransform method) (torchrl.envs.transforms.ModuleTransform method) (torchrl.envs.transforms.ObservationNorm method) (torchrl.envs.transforms.Transform method) (torchrl.envs.transforms.UnaryTransform method) (torchrl.envs.transforms.UnsqueezeTransform method) (torchrl.objectives.llm.MCAdvantage method) TransformConfig (class in torchrl.trainers.algorithms.configs.transforms) transformed_env_constructor() (in module torchrl.trainers.helpers) TransformedEnv (class in torchrl.envs.transforms) TransformedEnvConfig (class in torchrl.trainers.algorithms.configs.envs) TransformersWrapper (class in torchrl.modules.llm) TransportBackend (class in torchrl.weight_update) TruncatedNormal (class in torchrl.modules) type() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method) type_check() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method)

U

UCB1TunedScore (class in torchrl.modules.mcts) UCBScore (class in torchrl.modules.mcts) UnaryTransform (class in torchrl.envs.transforms) UnaryTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) unbind() (torchrl.data.llm.ContentBase method) (torchrl.data.llm.History method) (torchrl.envs.llm.IFEvalScoreData method) (torchrl.modules.llm.ChatHistory method) (torchrl.modules.llm.LogProbs method) (torchrl.modules.llm.Masks method) (torchrl.modules.llm.Text method) (torchrl.modules.llm.Tokens method) (torchrl.objectives.llm.CISPOLossOutput method) (torchrl.objectives.llm.DAPOLossOutput method) (torchrl.objectives.llm.GRPOLossOutput method) (torchrl.objectives.llm.LLMLossOutput method) (torchrl.objectives.llm.SFTLossOutput method) Unbounded (class in torchrl.data) UnboundedContinuous (class in torchrl.data) UnboundedDiscrete (class in torchrl.data) unflatten() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) unfreeze() (torchrl.envs.transforms.VecNorm method) (torchrl.envs.transforms.VecNormV2 method), [1] unique_weights (torchrl.weight_update.SharedMemTransport property) UnityMLAgentsEnv() (in module torchrl.envs) UnityMLAgentsEnvConfig (class in torchrl.trainers.algorithms.configs.envs_libs) UnityMLAgentsWrapper() (in module torchrl.envs) unlock_() (torchrl.data.Composite method) (torchrl.data.StackedComposite method) unsqueeze() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method)

UnsqueezeTransform (class in torchrl.envs.transforms) UnsqueezeTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) update_kwargs() (torchrl.envs.ParallelEnv method) (torchrl.envs.SerialEnv method) update_mask() (torchrl.data.Binary method) (torchrl.data.Categorical method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.OneHot method) update_policy_weights_() (torchrl.collectors.AsyncCollector method) (torchrl.collectors.BaseCollector method) (torchrl.collectors.Collector method) (torchrl.collectors.distributed.DistributedCollector method) (torchrl.collectors.distributed.DistributedDataCollector method) (torchrl.collectors.distributed.DistributedSyncCollector method) (torchrl.collectors.distributed.DistributedSyncDataCollector method) (torchrl.collectors.distributed.RayCollector method) (torchrl.collectors.distributed.RPCCollector method) (torchrl.collectors.distributed.RPCDataCollector method) (torchrl.collectors.llm.LLMCollector method) (torchrl.collectors.llm.RayLLMCollector method) (torchrl.collectors.MultiAsyncCollector method) (torchrl.collectors.MultiCollector method) (torchrl.collectors.MultiSyncCollector method) update_priority() (torchrl.data.replay_buffers.PrioritizedSampler method) (torchrl.data.replay_buffers.PrioritizedSliceSampler method) update_weights() (torchrl.collectors.distributed.DistributedWeightUpdater method) (torchrl.collectors.distributed.RPCWeightUpdater method) (torchrl.modules.llm.AsyncVLLM method) (torchrl.weight_update.llm.VLLMDoubleBufferWeightSender method) (torchrl.weight_update.llm.VLLMWeightSender method) UpdateWeights (class in torchrl.trainers) UTDRHook (class in torchrl.trainers)

V

value_estimate() (torchrl.objectives.value.GAE method) (torchrl.objectives.value.TD0Estimator method) (torchrl.objectives.value.TD1Estimator method) (torchrl.objectives.value.TDLambdaEstimator method) (torchrl.objectives.value.ValueEstimatorBase method) value_estimator (torchrl.objectives.llm.CISPOLoss property) (torchrl.objectives.llm.DAPO property) (torchrl.objectives.llm.GRPOLoss property) (torchrl.objectives.llm.SFTLoss property) (torchrl.objectives.LossModule property) ValueEstimatorBase (class in torchrl.objectives.value) ValueEstimators (class in torchrl.objectives) ValueModelConfig (class in torchrl.trainers.algorithms.configs.modules) ValueOperator (class in torchrl.modules) values() (torchrl.data.Composite method) (torchrl.data.StackedComposite method) VanillaWeightUpdater (class in torchrl.collectors) VC1Transform (class in torchrl.envs.transforms) VC1TransformConfig (class in torchrl.trainers.algorithms.configs.transforms) VD4RLExperienceReplay (class in torchrl.data.datasets) VecGymEnvTransform (class in torchrl.envs.transforms) VecGymEnvTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) VecNorm (class in torchrl.envs.transforms) VecNormConfig (class in torchrl.trainers.algorithms.configs.transforms) VecNormV2 (class in torchrl.envs.transforms) VecNormV2Config (class in torchrl.trainers.algorithms.configs.transforms) version (torchrl.envs.llm.transforms.PolicyVersion property) VideoRecorder() (in module torchrl.record) view() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method)

VIPRewardTransform (class in torchrl.envs.transforms) VIPRewardTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) VIPTransform (class in torchrl.envs.transforms) VIPTransformConfig (class in torchrl.trainers.algorithms.configs.transforms) VLLMCollectiveTransport (class in torchrl.weight_update.llm) VLLMDoubleBufferSyncScheme (class in torchrl.weight_update.llm) VLLMDoubleBufferTransport (class in torchrl.weight_update.llm) VLLMDoubleBufferWeightReceiver (class in torchrl.weight_update.llm) VLLMDoubleBufferWeightSender (class in torchrl.weight_update.llm) vLLMUpdater (class in torchrl.collectors.llm) vLLMUpdaterV2 (class in torchrl.collectors.llm) VLLMWeightReceiver (class in torchrl.weight_update.llm) VLLMWeightSender (class in torchrl.weight_update.llm) VLLMWeightSyncScheme (class in torchrl.weight_update.llm) vLLMWrapper (class in torchrl.modules.llm) vmap_randomness (torchrl.objectives.llm.CISPOLoss property) (torchrl.objectives.llm.DAPO property) (torchrl.objectives.llm.GRPOLoss property) (torchrl.objectives.llm.SFTLoss property) (torchrl.objectives.LossModule property) VmasEnv() (in module torchrl.envs) VmasEnvConfig (class in torchrl.trainers.algorithms.configs.envs_libs) VmasWrapper() (in module torchrl.envs)

W

wait_ack() (torchrl.weight_update.DistributedTransport method) (torchrl.weight_update.RayTransport method) (torchrl.weight_update.RPCTransport method) WandbLogger() (in module torchrl.record.loggers.wandb) WandbLoggerConfig (class in torchrl.trainers.algorithms.configs.logging) weight_updater (torchrl.collectors.llm.RayLLMCollector property) weights (torchrl.weight_update.DistributedWeightSyncScheme property) (torchrl.weight_update.llm.VLLMDoubleBufferSyncScheme property) (torchrl.weight_update.llm.VLLMWeightSyncScheme property) (torchrl.weight_update.MultiProcessWeightSyncScheme property) (torchrl.weight_update.NoWeightSyncScheme property) (torchrl.weight_update.RayModuleTransformScheme property) (torchrl.weight_update.RayWeightSyncScheme property) (torchrl.weight_update.RPCWeightSyncScheme property) (torchrl.weight_update.SharedMemWeightSyncScheme property) (torchrl.weight_update.WeightSyncScheme property) WeightStrategy (class in torchrl.weight_update) WeightSyncScheme (class in torchrl.weight_update) WeightUpdaterBase (class in torchrl.collectors) worker_idx (torchrl.collectors.AsyncCollector property) (torchrl.collectors.BaseCollector property) (torchrl.collectors.Collector property) (torchrl.collectors.distributed.DistributedCollector property) (torchrl.collectors.distributed.DistributedDataCollector property) (torchrl.collectors.distributed.DistributedSyncCollector property) (torchrl.collectors.distributed.DistributedSyncDataCollector property) (torchrl.collectors.distributed.RayCollector property) (torchrl.collectors.distributed.RPCCollector property) (torchrl.collectors.distributed.RPCDataCollector property) (torchrl.collectors.llm.LLMCollector property) (torchrl.collectors.llm.RayLLMCollector property) (torchrl.collectors.MultiAsyncCollector property) (torchrl.collectors.MultiCollector property) (torchrl.collectors.MultiSyncCollector property) (torchrl.weight_update.DistributedWeightSyncScheme property) (torchrl.weight_update.llm.VLLMDoubleBufferSyncScheme property) (torchrl.weight_update.llm.VLLMWeightSyncScheme property) (torchrl.weight_update.MultiProcessWeightSyncScheme property) (torchrl.weight_update.NoWeightSyncScheme property) (torchrl.weight_update.RayModuleTransformScheme property) (torchrl.weight_update.RayWeightSyncScheme property) (torchrl.weight_update.RPCWeightSyncScheme property) (torchrl.weight_update.SharedMemWeightSyncScheme property) (torchrl.weight_update.WeightSyncScheme property)

WorldModelWrapper (class in torchrl.modules) write_count (torchrl.data.datasets.AtariDQNExperienceReplay property) (torchrl.data.datasets.D4RLExperienceReplay property) (torchrl.data.datasets.GenDGRLExperienceReplay property) (torchrl.data.datasets.MinariExperienceReplay property) (torchrl.data.datasets.OpenMLExperienceReplay property) (torchrl.data.datasets.OpenXExperienceReplay property) (torchrl.data.datasets.RobosetExperienceReplay property) (torchrl.data.datasets.VD4RLExperienceReplay property) (torchrl.data.PrioritizedReplayBuffer property) (torchrl.data.RayReplayBuffer property) (torchrl.data.RemoteTensorDictReplayBuffer property) (torchrl.data.ReplayBuffer property) (torchrl.data.ReplayBufferEnsemble property) (torchrl.data.TensorDictPrioritizedReplayBuffer property) (torchrl.data.TensorDictReplayBuffer property) Writer (class in torchrl.data.replay_buffers) writer (torchrl.data.datasets.AtariDQNExperienceReplay property) (torchrl.data.datasets.D4RLExperienceReplay property) (torchrl.data.datasets.GenDGRLExperienceReplay property) (torchrl.data.datasets.MinariExperienceReplay property) (torchrl.data.datasets.OpenMLExperienceReplay property) (torchrl.data.datasets.OpenXExperienceReplay property) (torchrl.data.datasets.RobosetExperienceReplay property) (torchrl.data.datasets.VD4RLExperienceReplay property) (torchrl.data.PrioritizedReplayBuffer property) (torchrl.data.RayReplayBuffer property) (torchrl.data.RemoteTensorDictReplayBuffer property) (torchrl.data.ReplayBuffer property) (torchrl.data.ReplayBufferEnsemble property) (torchrl.data.TensorDictPrioritizedReplayBuffer property) (torchrl.data.TensorDictReplayBuffer property) WriterEnsemble (class in torchrl.data.replay_buffers)

X

XMLBlockParser (class in torchrl.envs.llm.transforms) xpu() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method)

Z

zero() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) zero_grad() (torchrl.data.llm.TopKRewardSelector method) (torchrl.envs.AsyncEnvPool method) (torchrl.envs.ChessEnv method) (torchrl.envs.EnvBase method) (torchrl.envs.GymLikeEnv method) (torchrl.envs.llm.ChatEnv method) (torchrl.envs.llm.DatasetChatEnv method) (torchrl.envs.llm.GSM8KEnv method) (torchrl.envs.llm.GSM8KPrepareQuestion method) (torchrl.envs.llm.GSM8KRewardParser method) (torchrl.envs.llm.IFEvalEnv method) (torchrl.envs.llm.IfEvalScorer method) (torchrl.envs.llm.LLMEnv method) (torchrl.envs.llm.LLMHashingEnv method) (torchrl.envs.llm.MLGymWrapper method) (torchrl.envs.llm.transforms.AddThinkingPrompt method) (torchrl.envs.llm.transforms.BrowserTransform method) (torchrl.envs.llm.transforms.DataLoadingPrimer method) (torchrl.envs.llm.transforms.ExecuteToolsInOrder method) (torchrl.envs.llm.transforms.KLComputation method) (torchrl.envs.llm.transforms.KLRewardTransform method) (torchrl.envs.llm.transforms.MCPToolTransform method) (torchrl.envs.llm.transforms.PolicyVersion method) (torchrl.envs.llm.transforms.PythonInterpreter method) (torchrl.envs.llm.transforms.RayDataLoadingPrimer method) (torchrl.envs.llm.transforms.RetrieveKL method) (torchrl.envs.llm.transforms.RetrieveLogProb method) (torchrl.envs.llm.transforms.SimpleToolTransform method) (torchrl.envs.llm.transforms.TemplateTransform method) (torchrl.envs.llm.transforms.Tokenizer method) (torchrl.envs.LLMHashingEnv method) (torchrl.envs.ParallelEnv method) (torchrl.envs.PendulumEnv method) (torchrl.envs.ProcessorAsyncEnvPool method) (torchrl.envs.SerialEnv method) (torchrl.envs.ThreadingAsyncEnvPool method) (torchrl.envs.TicTacToeEnv method) (torchrl.modules.llm.LLMWrapperBase method) (torchrl.modules.llm.TransformersWrapper method) (torchrl.modules.llm.vLLMWrapper method) (torchrl.objectives.llm.CISPOLoss method) (torchrl.objectives.llm.DAPO method) (torchrl.objectives.llm.GRPOLoss method) (torchrl.objectives.llm.MCAdvantage method) (torchrl.objectives.llm.SFTLoss method)

zeros() (torchrl.data.Binary method) (torchrl.data.Bounded method) (torchrl.data.Categorical method) (torchrl.data.Composite method) (torchrl.data.MultiCategorical method) (torchrl.data.MultiOneHot method) (torchrl.data.NonTensor method) (torchrl.data.OneHot method) (torchrl.data.Stacked method) (torchrl.data.StackedComposite method) (torchrl.data.TensorSpec method) (torchrl.data.Unbounded method) (torchrl.data.UnboundedContinuous method) (torchrl.data.UnboundedDiscrete method) zeros_update() (torchrl.data.Composite method) (torchrl.data.StackedComposite method)