Interface IExplorationPolicy

Exploration policy interface.

Namespace: Mars.Components.Services.Explorations

Assembly: Mars.Components.dll

Syntax

public interface IExplorationPolicy

Remarks

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

Methods

ChooseAction(Double[])

Choose an action.

Declaration

int ChooseAction(double[] actionEstimates)

Parameters

Type	Name	Description
System.Double[]	actionEstimates	Action estimates.

Returns

Type	Description
System.Int32	Returns selected action.

Remarks

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).

Extension Methods

Serializer.Save<T>(T, out Byte[], SerializerCompression)

Serializer.Save<T>(T, Stream, SerializerCompression)

Serializer.Save<T>(T, BinaryFormatter, Stream, SerializerCompression)

Serializer.Save<T>(T, String, SerializerCompression)

Serializer.Save<T>(T, String)

Matrix.Concatenate<T>(T, T[])

Matrix.Replace<T>(T, Object, Object)

DomainDataImporter.Import(Object, InputConfiguration)

ObjectSerialize.Serialize(Object)

Matrix.IsEqual(Object, Object, Decimal, Decimal)