ExcludeTransform¶
- class torchrl.envs.transforms.ExcludeTransform(*excluded_keys, inverse: bool = False)[source]¶
Excludes keys from the data.
- Parameters:
*excluded_keys (iterable of NestedKey) – The name of the keys to exclude. If the key is not present, it is simply ignored.
inverse (bool, optional) – if
True
, the exclusion will occur during theinv
call. Defaults toFalse
.
Examples
>>> import gymnasium >>> from torchrl.envs import GymWrapper >>> env = TransformedEnv( ... GymWrapper(gymnasium.make("Pendulum-v1")), ... ExcludeTransform("truncated") ... ) >>> env.rollout(3) TensorDict( fields={ action: Tensor(shape=torch.Size([3, 1]), device=cpu, dtype=torch.float32, is_shared=False), done: Tensor(shape=torch.Size([3, 1]), device=cpu, dtype=torch.bool, is_shared=False), next: TensorDict( fields={ done: Tensor(shape=torch.Size([3, 1]), device=cpu, dtype=torch.bool, is_shared=False), observation: Tensor(shape=torch.Size([3, 3]), device=cpu, dtype=torch.float32, is_shared=False), reward: Tensor(shape=torch.Size([3, 1]), device=cpu, dtype=torch.float32, is_shared=False)}, batch_size=torch.Size([3]), device=cpu, is_shared=False), observation: Tensor(shape=torch.Size([3, 3]), device=cpu, dtype=torch.float32, is_shared=False)}, batch_size=torch.Size([3]), device=cpu, is_shared=False)
- forward(tensordict: TensorDictBase) TensorDictBase ¶
Reads the input tensordict, and for the selected keys, applies the transform.
- transform_output_spec(output_spec: Composite) Composite [source]¶
Transforms the output spec such that the resulting spec matches transform mapping.
This method should generally be left untouched. Changes should be implemented using
transform_observation_spec()
,transform_reward_spec()
andtransformfull_done_spec()
. :param output_spec: spec before the transform :type output_spec: TensorSpec- Returns:
expected spec after the transform