d3rlpy.algos.ConstantEpsilonGreedy

class d3rlpy.algos.ConstantEpsilonGreedy(epsilon)

\(\epsilon\)-greedy explorer with constant \(\epsilon\).

Parameters:

epsilon (float) – the constant \(\epsilon\).

Methods

sample(algo, x, step)

Parameters:

• algo (QLearningAlgoProtocol) –

• x (Union[ndarray[Any, dtype[Any]], Sequence[ndarray[Any, dtype[Any]]]]) –

• step (int) –

Return type:

ndarray[Any, dtype[Any]]