Class DoubleQLearningAgent<T>

Namespace

AiDotNet.ReinforcementLearning.Agents.DoubleQLearning

Assembly

AiDotNet.dll

Double Q-Learning agent using two Q-tables to reduce overestimation bias.

public class DoubleQLearningAgent<T> : ReinforcementLearningAgentBase<T>, IRLAgent<T>, IFullModel<T, Vector<T>, Vector<T>>, IModel<Vector<T>, Vector<T>, ModelMetadata<T>>, IModelSerializer, ICheckpointableModel, IParameterizable<T, Vector<T>, Vector<T>>, IFeatureAware, IFeatureImportance<T>, ICloneable<IFullModel<T, Vector<T>, Vector<T>>>, IGradientComputable<T, Vector<T>, Vector<T>>, IJitCompilable<T>, IDisposable

Type Parameters

T

The numeric type used for calculations.

Inheritance

object

ReinforcementLearningAgentBase<T>

DoubleQLearningAgent<T>

Implements

IRLAgent<T>

IFullModel<T, Vector<T>, Vector<T>>

IModel<Vector<T>, Vector<T>, ModelMetadata<T>>

IModelSerializer

ICheckpointableModel

IParameterizable<T, Vector<T>, Vector<T>>

IFeatureAware

IFeatureImportance<T>

ICloneable<IFullModel<T, Vector<T>, Vector<T>>>

IGradientComputable<T, Vector<T>, Vector<T>>

IJitCompilable<T>

IDisposable

Inherited Members

ReinforcementLearningAgentBase<T>.NumOps

ReinforcementLearningAgentBase<T>.Random

ReinforcementLearningAgentBase<T>.LossFunction

ReinforcementLearningAgentBase<T>.LearningRate

ReinforcementLearningAgentBase<T>.DiscountFactor

ReinforcementLearningAgentBase<T>.TrainingSteps

ReinforcementLearningAgentBase<T>.Episodes

ReinforcementLearningAgentBase<T>.LossHistory

ReinforcementLearningAgentBase<T>.RewardHistory

ReinforcementLearningAgentBase<T>.Options

ReinforcementLearningAgentBase<T>.ResetEpisode()

ReinforcementLearningAgentBase<T>.Predict(Vector<T>)

ReinforcementLearningAgentBase<T>.DefaultLossFunction

ReinforcementLearningAgentBase<T>.Train(Vector<T>, Vector<T>)

ReinforcementLearningAgentBase<T>.FeatureNames

ReinforcementLearningAgentBase<T>.GetFeatureImportance()

ReinforcementLearningAgentBase<T>.GetActiveFeatureIndices()

ReinforcementLearningAgentBase<T>.IsFeatureUsed(int)

ReinforcementLearningAgentBase<T>.SetActiveFeatureIndices(IEnumerable<int>)

ReinforcementLearningAgentBase<T>.DeepCopy()

ReinforcementLearningAgentBase<T>.WithParameters(Vector<T>)

ReinforcementLearningAgentBase<T>.GetMetrics()

ReinforcementLearningAgentBase<T>.ComputeAverage(IEnumerable<T>)

ReinforcementLearningAgentBase<T>.Dispose()

ReinforcementLearningAgentBase<T>.SaveState(Stream)

ReinforcementLearningAgentBase<T>.LoadState(Stream)

ReinforcementLearningAgentBase<T>.SupportsJitCompilation

ReinforcementLearningAgentBase<T>.ExportComputationGraph(List<ComputationNode<T>>)

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Extension Methods

DistributedExtensions.AsDistributedForHighBandwidth<T, TInput, TOutput>(IFullModel<T, TInput, TOutput>, ICommunicationBackend<T>)

DistributedExtensions.AsDistributedForLowBandwidth<T, TInput, TOutput>(IFullModel<T, TInput, TOutput>, ICommunicationBackend<T>)

DistributedExtensions.AsDistributed<T, TInput, TOutput>(IFullModel<T, TInput, TOutput>, ICommunicationBackend<T>)

DistributedExtensions.AsDistributed<T, TInput, TOutput>(IFullModel<T, TInput, TOutput>, IShardingConfiguration<T>)

Remarks

Double Q-Learning maintains two Q-tables and uses one to select actions and the other to evaluate them, reducing maximization bias.

For Beginners: Q-Learning tends to overestimate Q-values because it uses max(Q) for both selecting and evaluating actions. Double Q-Learning fixes this by using two separate Q-tables and randomly switching which one is updated.

Key innovation:

• Two Q-tables: Q1 and Q2
• Decorrelation: Use Q1 to select action, Q2 to evaluate (or vice versa)
• Reduced Bias: Prevents overestimation from max operator

Famous for: Hado van Hasselt 2010, foundation for Double DQN

Constructors

DoubleQLearningAgent(DoubleQLearningOptions<T>)

public DoubleQLearningAgent(DoubleQLearningOptions<T> options)

Parameters

options DoubleQLearningOptions<T>

Properties

FeatureCount

Gets the number of input features (state dimensions).

public override int FeatureCount { get; }

Property Value

int

ParameterCount

Gets the number of parameters in the agent.

public override int ParameterCount { get; }

Property Value

int

Remarks

Deep RL agents return parameter counts from neural networks. Classical RL agents (tabular, linear) may have different implementations.

Methods

ApplyGradients(Vector<T>, T)

Applies gradients to update the agent.

public override void ApplyGradients(Vector<T> gradients, T learningRate)

Parameters

gradients Vector<T>

learningRate T

Clone()

Clones the agent.

public override IFullModel<T, Vector<T>, Vector<T>> Clone()

Returns

IFullModel<T, Vector<T>, Vector<T>>

ComputeGradients(Vector<T>, Vector<T>, ILossFunction<T>?)

Computes gradients for the agent.

public override Vector<T> ComputeGradients(Vector<T> input, Vector<T> target, ILossFunction<T>? lossFunction = null)

Parameters

input Vector<T>

target Vector<T>

lossFunction ILossFunction<T>

Returns

Vector<T>

Deserialize(byte[])

Deserializes the agent from bytes.

public override void Deserialize(byte[] data)

Parameters

data byte[]

GetModelMetadata()

Gets model metadata.

public override ModelMetadata<T> GetModelMetadata()

Returns

ModelMetadata<T>

GetParameters()

Gets the agent's parameters.

public override Vector<T> GetParameters()

Returns

Vector<T>

LoadModel(string)

Loads the agent's state from a file.

public override void LoadModel(string filepath)

Parameters

filepath string

Path to load the agent from.

SaveModel(string)

Saves the agent's state to a file.

public override void SaveModel(string filepath)

Parameters

filepath string

Path to save the agent.

SelectAction(Vector<T>, bool)

Selects an action given the current state observation.

public override Vector<T> SelectAction(Vector<T> state, bool training = true)

Parameters

state Vector<T>

The current state observation as a Vector.

training bool

Whether the agent is in training mode (affects exploration).

Returns

Vector<T>

Action as a Vector (can be discrete or continuous).

Serialize()

Serializes the agent to bytes.

public override byte[] Serialize()

Returns

byte[]

SetParameters(Vector<T>)

Sets the agent's parameters.

public override void SetParameters(Vector<T> parameters)

Parameters

parameters Vector<T>

StoreExperience(Vector<T>, Vector<T>, T, Vector<T>, bool)

Stores an experience tuple for later learning.

public override void StoreExperience(Vector<T> state, Vector<T> action, T reward, Vector<T> nextState, bool done)

Parameters

state Vector<T>

The state before action.

action Vector<T>

The action taken.

reward T

The reward received.

nextState Vector<T>

The state after action.

done bool

Whether the episode terminated.

Train()

Performs one training step, updating the agent's policy/value function.

public override T Train()

Returns

T

The training loss for monitoring.