d3rlpy.online.explorers.LinearDecayEpsilonGreedy¶
-
class
d3rlpy.online.explorers.
LinearDecayEpsilonGreedy
(start_epsilon=1.0, end_epsilon=0.1, duration=1000000)[source]¶ \(\epsilon\)-greedy explorer with linear decay schedule.
- Parameters
Methods
-
sample
(algo, x, step)[source]¶ Returns \(\epsilon\)-greedy action.
- Parameters
algo (d3rlpy.online.explorers._ActionProtocol) – algorithm.
x (numpy.ndarray) – observation.
step (int) – current environment step.
- Returns
\(\epsilon\)-greedy action.
- Return type