Catalano.MachineLearning.Exploration

Interface IExplorationPolicy

All Known Implementing Classes:

BoltzmannExploration, EpsilonGreedyExploration, RouletteWheelExploration, TabuSearchExploration

public interface IExplorationPolicy

The interface describes exploration policies, which are used in Reinforcement Learning to explore state space.

Method Summary

Modifier and Type	Method and Description
int	ChooseAction(double[] actionEstimates) The method chooses an action depending on the provided estimates.

Method Detail

ChooseAction

int ChooseAction(double[] actionEstimates)

The method chooses an action depending on the provided estimates. the estimates can be any sort of estimate, which values usefulness of the action (expected summary reward, discounted reward, etc).

Parameters:

actionEstimates - Action estimates.

Returns:

Returns selected action.