All modules for which code is available
- tensordict.nn.utils
- torchrl._utils
- torchrl.collectors.collectors
- torchrl.collectors.distributed.generic
- torchrl.collectors.distributed.ray
- torchrl.collectors.distributed.rpc
- torchrl.collectors.distributed.sync
- torchrl.collectors.distributed.utils
- torchrl.collectors.utils
- torchrl.data.datasets.atari_dqn
- torchrl.data.datasets.common
- torchrl.data.datasets.d4rl
- torchrl.data.datasets.gen_dgrl
- torchrl.data.datasets.minari_data
- torchrl.data.datasets.openml
- torchrl.data.datasets.openx
- torchrl.data.datasets.roboset
- torchrl.data.datasets.vd4rl
- torchrl.data.map.hash
- torchrl.data.map.query
- torchrl.data.map.tdstorage
- torchrl.data.map.tree
- torchrl.data.postprocs.postprocs
- torchrl.data.replay_buffers.checkpointers
- torchrl.data.replay_buffers.replay_buffers
- torchrl.data.replay_buffers.samplers
- torchrl.data.replay_buffers.storages
- torchrl.data.replay_buffers.utils
- torchrl.data.replay_buffers.writers
- torchrl.data.rlhf.dataset
- torchrl.data.rlhf.prompt
- torchrl.data.rlhf.reward
- torchrl.data.rlhf.utils
- torchrl.data.tensor_specs
- torchrl.data.utils
- torchrl.envs.batched_envs
- torchrl.envs.common
- torchrl.envs.custom.pendulum
- torchrl.envs.custom.tictactoeenv
- torchrl.envs.env_creator
- torchrl.envs.gym_like
- torchrl.envs.libs.brax
- torchrl.envs.libs.dm_control
- torchrl.envs.libs.envpool
- torchrl.envs.libs.gym
- torchrl.envs.libs.habitat
- torchrl.envs.libs.isaacgym
- torchrl.envs.libs.jumanji
- torchrl.envs.libs.meltingpot
- torchrl.envs.libs.openml
- torchrl.envs.libs.openspiel
- torchrl.envs.libs.pettingzoo
- torchrl.envs.libs.robohive
- torchrl.envs.libs.smacv2
- torchrl.envs.libs.unity_mlagents
- torchrl.envs.libs.vmas
- torchrl.envs.model_based.common
- torchrl.envs.model_based.dreamer
- torchrl.envs.transforms.gym_transforms
- torchrl.envs.transforms.r3m
- torchrl.envs.transforms.rb_transforms
- torchrl.envs.transforms.rlhf
- torchrl.envs.transforms.transforms
- torchrl.envs.transforms.vc1
- torchrl.envs.transforms.vip
- torchrl.envs.utils
- torchrl.modules.distributions.continuous
- torchrl.modules.distributions.discrete
- torchrl.modules.models.batchrenorm
- torchrl.modules.models.decision_transformer
- torchrl.modules.models.exploration
- torchrl.modules.models.model_based
- torchrl.modules.models.models
- torchrl.modules.models.multiagent
- torchrl.modules.models.utils
- torchrl.modules.planners.cem
- torchrl.modules.planners.common
- torchrl.modules.planners.mppi
- torchrl.modules.tensordict_module.actors
- torchrl.modules.tensordict_module.common
- torchrl.modules.tensordict_module.exploration
- torchrl.modules.tensordict_module.probabilistic
- torchrl.modules.tensordict_module.rnn
- torchrl.modules.tensordict_module.sequence
- torchrl.modules.tensordict_module.world_models
- torchrl.modules.utils.mappings
- torchrl.modules.utils.utils
- torchrl.objectives.a2c
- torchrl.objectives.common
- torchrl.objectives.cql
- torchrl.objectives.crossq
- torchrl.objectives.ddpg
- torchrl.objectives.decision_transformer
- torchrl.objectives.dqn
- torchrl.objectives.dreamer
- torchrl.objectives.gail
- torchrl.objectives.iql
- torchrl.objectives.multiagent.qmixer
- torchrl.objectives.ppo
- torchrl.objectives.redq
- torchrl.objectives.reinforce
- torchrl.objectives.sac
- torchrl.objectives.td3
- torchrl.objectives.td3_bc
- torchrl.objectives.utils
- torchrl.objectives.value.advantages
- torchrl.objectives.value.functional
- torchrl.record.loggers.common
- torchrl.record.loggers.csv
- torchrl.record.loggers.mlflow
- torchrl.record.loggers.tensorboard
- torchrl.record.loggers.utils
- torchrl.record.loggers.wandb
- torchrl.record.recorder
- torchrl.trainers.helpers.collectors
- torchrl.trainers.helpers.envs
- torchrl.trainers.helpers.losses
- torchrl.trainers.helpers.replay_buffer
- torchrl.trainers.helpers.trainers
- torchrl.trainers.trainers