Class LinearSARSAOptions<T>

Namespace

AiDotNet.Models.Options

Assembly

AiDotNet.dll

Configuration options for Linear SARSA agents.

public class LinearSARSAOptions<T> : ReinforcementLearningOptions<T>

Type Parameters

T

The numeric type used for calculations.

Inheritance

object

ReinforcementLearningOptions<T>

LinearSARSAOptions<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

Linear SARSA uses linear function approximation for on-policy learning. Unlike Linear Q-Learning (off-policy), SARSA updates based on the action actually taken by the current policy, making it more conservative.

For Beginners: Linear SARSA is the on-policy version of Linear Q-Learning. It learns about the policy it's currently following, rather than the optimal policy. This makes it safer in risky environments where exploration could be dangerous.

Best for:

• Medium-sized continuous state spaces
• Risky environments (cliff walking, robotics)
• More conservative, safe learning
• Feature-based state representations

Not suitable for:

• Very small discrete states (use tabular SARSA)
• When fastest convergence is needed (use Q-learning)
• Highly non-linear problems (use neural networks)

Properties

ActionSize

Size of the action space (number of possible actions).

public int ActionSize { get; init; }

Property Value

int

FeatureSize

Number of features in the state representation.

public int FeatureSize { get; init; }

Property Value

int