Class ExplorationScheduleConfig<T>

Namespace

AiDotNet.Configuration

Assembly

AiDotNet.dll

Configuration for exploration schedule (epsilon decay for epsilon-greedy).

public class ExplorationScheduleConfig<T>

Type Parameters

T

The numeric type.

Inheritance

object

ExplorationScheduleConfig<T>

Inherited Members

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

For Beginners: The agent needs to explore early in training (try random actions) but exploit more later (use learned policy). This schedule controls that transition.

Constructors

ExplorationScheduleConfig()

Creates a new instance with default values.

public ExplorationScheduleConfig()

Properties

DecaySteps

Number of steps over which to decay from initial to final epsilon.

public int DecaySteps { get; set; }

Property Value

int

DecayType

Type of decay schedule.

public ExplorationDecayType DecayType { get; set; }

Property Value

ExplorationDecayType

FinalEpsilon

Final exploration rate (0.01 = mostly learned policy).

public T FinalEpsilon { get; set; }

Property Value

T

InitialEpsilon

Initial exploration rate (1.0 = fully random).

public T InitialEpsilon { get; set; }

Property Value

T