C# Class Accord.MachineLearning.BoltzmannExploration

Boltzmann distribution exploration policy.

The class implements exploration policy base on Boltzmann distribution. Acording to the policy, action a at state s is selected with the next probability:

exp( Q( s, a ) / t ) p( s, a ) = ----------------------------- SUM( exp( Q( s, b ) / t ) ) b

where Q(s, a) is action's a estimation (usefulness) at state s and t is Temperature.

Inheritance: IExplorationPolicy
Afficher le fichier Open project: accord-net/framework

Méthodes publiques

Méthode Description
BoltzmannExploration ( double temperature ) : System

Initializes a new instance of the BoltzmannExploration class.
ChooseAction ( double actionEstimates ) : int

Choose an action.

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).

Method Details

BoltzmannExploration() public méthode

Initializes a new instance of the BoltzmannExploration class.
public BoltzmannExploration ( double temperature ) : System
temperature double Temperature parameter of Boltzmann distribution.
Résultat System

ChooseAction() public méthode

Choose an action.
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).
public ChooseAction ( double actionEstimates ) : int
actionEstimates double Action estimates.
Résultat int