mlpy.planners.explorers.discrete.EGreedyExplorer.choose_action¶

EGreedyExplorer.choose_action(actions, qvalues)[source]¶

Choose the next action.

With $\epsilon$ probability, a random action is chosen, otherwise the action resulting in the highest q-value is selected.

Parameters:

actions : list[Actions]

The available actions.

qvalues : list[float]

The q-value for each action.

Returns:

Action :

The action with maximum qvalue that can be taken from the given state.