EgreedyOverOptions

class EgreedyOverOptions(epsilon: Union[pandemonium.utilities.schedules.ConstantSchedule, pandemonium.utilities.schedules.LinearSchedule], *args, **kwargs)

Bases: pandemonium.policies.discrete.Egreedy, pandemonium.policies.discrete.HierarchicalPolicy

\(\epsilon\)-greedy policy over options.

Picks the optimal option wrt to Q with probability 1 - \(\epsilon\).