Class A3COptions<T>

Namespace

AiDotNet.Models.Options

Assembly

AiDotNet.dll

Configuration options for Asynchronous Advantage Actor-Critic (A3C) agents.

public class A3COptions<T> : ReinforcementLearningOptions<T>

Type Parameters

T

The numeric type used for calculations.

Inheritance

object

ReinforcementLearningOptions<T>

A3COptions<T>

Inherited Members

ReinforcementLearningOptions<T>.LearningRate

ReinforcementLearningOptions<T>.DiscountFactor

ReinforcementLearningOptions<T>.LossFunction

ReinforcementLearningOptions<T>.Seed

ReinforcementLearningOptions<T>.BatchSize

ReinforcementLearningOptions<T>.ReplayBufferSize

ReinforcementLearningOptions<T>.TargetUpdateFrequency

ReinforcementLearningOptions<T>.UsePrioritizedReplay

ReinforcementLearningOptions<T>.EpsilonStart

ReinforcementLearningOptions<T>.EpsilonEnd

ReinforcementLearningOptions<T>.EpsilonDecay

ReinforcementLearningOptions<T>.WarmupSteps

ReinforcementLearningOptions<T>.MaxGradientNorm

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

A3C runs multiple agents in parallel, each learning from different experiences. The parallel exploration provides diverse training data and stabilizes learning.

For Beginners: A3C is like having multiple students learn the same subject simultaneously, each with different experiences. They periodically share what they learned with a central "teacher" (global network), and everyone benefits from the combined knowledge.

Key features:

• Asynchronous: Multiple agents run in parallel
• Actor-Critic: Learns both policy and value function
• No Replay Buffer: Uses on-policy learning
• Diverse Exploration: Different agents explore different strategies

Famous for: DeepMind's breakthrough paper (2016), enables CPU-only training

Constructors

A3COptions()

public A3COptions()

Properties

ActionSize

public int ActionSize { get; init; }

Property Value

int

EntropyCoefficient

public T EntropyCoefficient { get; init; }

Property Value

T

IsContinuous

public bool IsContinuous { get; init; }

Property Value

bool

NumWorkers

public int NumWorkers { get; init; }

Property Value

int

Optimizer

The optimizer used for updating network parameters. If null, Adam optimizer will be used by default.

public IOptimizer<T, Vector<T>, Vector<T>>? Optimizer { get; init; }

Property Value

IOptimizer<T, Vector<T>, Vector<T>>

PolicyHiddenLayers

public List<int> PolicyHiddenLayers { get; init; }

Property Value

List<int>

PolicyLearningRate

public T PolicyLearningRate { get; init; }

Property Value

T

StateSize

public int StateSize { get; init; }

Property Value

int

TMax

public int TMax { get; init; }

Property Value

int

ValueHiddenLayers

public List<int> ValueHiddenLayers { get; init; }

Property Value

List<int>

ValueLearningRate

public T ValueLearningRate { get; init; }

Property Value

T

ValueLossCoefficient

public T ValueLossCoefficient { get; init; }

Property Value

T

ValueLossFunction

public ILossFunction<T> ValueLossFunction { get; init; }

Property Value

ILossFunction<T>