RewardScaling¶
- class torchrl.envs.transforms.RewardScaling(loc: Union[float, Tensor], scale: Union[float, Tensor], in_keys: Optional[Sequence[NestedKey]] = None, out_keys: Optional[Sequence[NestedKey]] = None, standard_normal: bool = False)[source]¶
Affine transform of the reward.
The reward is transformed according to:
\[reward = reward * scale + loc\]- 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 [source]¶
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