reference/generated/torchrl.envs.transforms.BinarizeReward

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

BinarizeReward

class torchrl.envs.transforms.BinarizeReward(in_keys: Sequence[NestedKey] | None = None, out_keys: Sequence[NestedKey] | None = None)

Maps the reward to a binary value (0 or 1) if the reward is null or non-null, respectively.

Parameters:

• in_keys (List[NestedKey]) – input keys

• out_keys (List[NestedKey], optional) – output keys. Defaults to value of in_keys.

• dtype (torch.dtype, optional) – the dtype of the binerized reward. Defaults to torch.int8.

transform_reward_spec(reward_spec: TensorSpec) → TensorSpec

Transforms the reward spec such that the resulting spec matches transform mapping.

Parameters:

reward_spec (TensorSpec) – spec before the transform

Returns:

expected spec after the transform