[This is preliminary documentation and is subject to change.]
This class implements a Q-learning with backpropagation neural network in the Clarion Library
Namespace: Clarion.FrameworkAssembly: ClarionLibrary (in ClarionLibrary.dll) Version: 6.1.1.0 (6.1.1.0)
Syntax
C# |
---|
public class QBPNetwork : ReinforcementTrainableBPNetwork, IUsesQLearning, IHandlesNewInput |
Remarks
The following parameters are OPTIONAL:
- An EligibilityChecker, a delegate that is used to determine if the SimplifiedQBPNetwork should be used on the current input
- An ExtractionChecker a delegate that is used to determine if a rule should be extracted given the current input
- A PositiveMatchDeterminer delegate that determines whether to update the positive match statistics
- A parameters class for the QBPNetwork
Copyright 2011. Nicholas Wilson
Inheritance Hierarchy
System..::..Object
Clarion.Framework.Core..::..ClarionComponent
Clarion.Framework.Templates..::..ImplicitComponent
Clarion.Framework.Templates..::..NeuralNetwork
Clarion.Framework..::..BPNetwork
Clarion.Framework.Templates..::..ReinforcementTrainableBPNetwork
Clarion.Framework..::..QBPNetwork
Clarion.Framework.Core..::..ClarionComponent
Clarion.Framework.Templates..::..ImplicitComponent
Clarion.Framework.Templates..::..NeuralNetwork
Clarion.Framework..::..BPNetwork
Clarion.Framework.Templates..::..ReinforcementTrainableBPNetwork
Clarion.Framework..::..QBPNetwork