OfflineTDPrediction

class OfflineTDPrediction(criterion=<function smooth_l1_loss>, **kwargs)

Bases: pandemonium.demons.offline_td.OfflineTD, pandemonium.demons.prediction.TDPrediction

Offline \(\TD\) for prediction tasks.

Methods Summary

delta(self, t)

Updates a value of a state using information in the trajectory.

Methods Documentation

delta(self, t: pandemonium.experience.experience.Trajectory) → Tuple[Union[torch.Tensor, NoneType], dict]

Updates a value of a state using information in the trajectory.