Reinforcement Learning Toolbox 2.0
last updated:
General
Documentation
Manual
Tutorial
Class Reference
Master Thesis
Examples
Related Papers
Downloads
Links
News
mailto:webmaster
Main Page     Class Hierarchy   Compound List   File List   Compound Members   File Members

CTDGradientLearner Class Reference

#include <ctdlearner.h>

Inheritance diagram for CTDGradientLearner:

CTDLearner CSemiMDPRewardListener CErrorSender CSemiMDPListener CParameterObject CParameters CTDResidualLearner CAdvantageLearner List of all members.


Public Member Functions

  CTDGradientLearner (CRewardFunction *rewardFunction, CGradientQFunction *qfunction, CAgentController *agent, CResidualFunction *residual, CResidualGradientFunction *residualGradient)
  ~CTDGradientLearner ()


Protected Member Functions

virtual double  getResidual (double oldQ, double reward, int duration, double newQ)
  returns the temporal difference error residual

virtual void  addETraces (CStateCollection *oldState, CStateCollection *newState, CAction *action)
  adds the current state to the etraces



Protected Attributes

CResidualFunction residual
CResidualGradientFunction residualGradient
CGradientQFunction gradientQFunction
CGradientQETraces gradientQETraces
CFeatureList oldGradient
CFeatureList newGradient
CFeatureList residualGradientFeatures

Constructor & Destructor Documentation

CTDGradientLearner::CTDGradientLearner CRewardFunction rewardFunction,
CGradientQFunction qfunction,
CAgentController agent,
CResidualFunction residual,
CResidualGradientFunction residualGradient
 
CTDGradientLearner::~CTDGradientLearner  ) 
 

Member Function Documentation

virtual void CTDGradientLearner::addETraces CStateCollection oldState,
CStateCollection newState,
CAction action
[protected, virtual]
 

adds the current state to the etraces

Reimplemented from CTDLearner.

virtual double CTDGradientLearner::getResidual double  oldQ,
double  reward,
int  duration,
double  newQ
[protected, virtual]
 

returns the temporal difference error residual

Reimplemented from CTDLearner.


Member Data Documentation

CGradientQETraces* CTDGradientLearner::gradientQETraces [protected]
 
CGradientQFunction* CTDGradientLearner::gradientQFunction [protected]
 
CFeatureList* CTDGradientLearner::newGradient [protected]
 
CFeatureList* CTDGradientLearner::oldGradient [protected]
 
CResidualFunction* CTDGradientLearner::residual [protected]
 
CResidualGradientFunction* CTDGradientLearner::residualGradient [protected]
 
CFeatureList* CTDGradientLearner::residualGradientFeatures [protected]
 

The documentation for this class was generated from the following file: