OnlineTDControl¶
-
class
OnlineTDControl
(**kwargs)¶ Bases:
pandemonium.demons.control.TDControl
,pandemonium.demons.online_td.OnlineTD
Base class for online \(\TD\) methods for control tasks.
Methods Summary
delta
(self, t)Specifies the update rule for approximate value function (avf)
Methods Documentation
-
delta
(self, t: pandemonium.experience.experience.Transition) → Tuple[Union[torch.Tensor, NoneType], dict]¶ Specifies the update rule for approximate value function (avf)
Depending on whether the algorithm is online or offline, the demon will be learning from a single Transition vs a Trajectory of experiences.
-