SkewedER

class SkewedER(*args, **kwargs)

Bases: pandemonium.experience.buffers.ER

Skewed Experience Replay buffer.

Used in the UNREAL architecture for the auxiliary reward prediction task.

References

RL with unsupervised auxiliary tasks (Jaderberd et al., 2016)

Methods Summary

add(self, transition, weight)
sample(self, batch_size, contiguous)	Randomly draws a batch of transitions

Methods Documentation

add(self, transition: pandemonium.experience.experience.Transition, weight: float = None) → None

sample(self, batch_size: int = None, contiguous: bool = True) → List[pandemonium.experience.experience.Transition]

Randomly draws a batch of transitions

Parameters

• batch_size – Number of transitions to sample from the buffer.

• contiguous – Whether transitions should be contiguous or not. This is particularly useful when using \(n\)-step methods.