d3rlpy.augmentation.vector.MultipleAmplitudeScaling

class d3rlpy.augmentation.vector.MultipleAmplitudeScaling(minimum=0.8, maximum=1.2)

Multiple Amplitude Scaling augmentation.

\[x' = x + z\]

where \(z \sim \text{Unif}(minimum, maximum)\) and \(z\) is a vector with different amplitude scale on each.

References

• Laskin et al., Reinforcement Learning with Augmented Data.

Parameters:

• minimum (float) – minimum amplitude scale.
• maximum (float) – maximum amplitude scale.

minimum

minimum amplitude scale.

Type:float

maximum

maximum amplitude scale.

Type:float

Methods

get_params()

Returns augmentation parameters.

Returns:augmentation parameters. Return type:dict

get_type()

Returns augmentation type.

Returns:multiple_amplitude_scaling. Return type:str

transform(x)

Returns scaled observation.

Parameters:x (torch.Tensor) – observation tensor. Returns:processed observation tensor. Return type:torch.Tensor