RewardScaling

class torchrl.envs.transforms.RewardScaling(loc: Union[float, torch.Tensor], scale: Union[float, torch.Tensor], in_keys: Sequence[NestedKey] | None = None, out_keys: Sequence[NestedKey] | None = None, standard_normal: bool = False)

Affine transform of the reward.

The reward is transformed according to:

$$reward=reward\ast scale+loc$$

Parameters:

• loc (number or torch.Tensor) – location of the affine transform

• scale (number or torch.Tensor) – scale of the affine transform

• standard_normal (bool, optional) –

  if True, the transform will be

  $$reward=(reward-loc)/scale$$

  as it is done for standardization. Default is False.

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