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

CNumericPolicyGradientCalculator Class Reference

#include <cpolicygradient.h>

Inheritance diagram for CNumericPolicyGradientCalculator:

CPolicyGradientCalculator CGradientCalculator CParameterObject CParameters List of all members.


Public Member Functions

  CNumericPolicyGradientCalculator (CAgent *agent, CContinuousActionGradientPolicy *policy, CTransitionFunctionEnvironment *dynModel, CRewardFunction *reward, double stepSize, CPolicyEvaluator *evaluator)
  ~CNumericPolicyGradientCalculator ()
virtual void  getGradient (CFeatureList *gradientFeatures)


Protected Attributes

CFeatureList gradientFeatures
double *  weights
CRewardFunction rewardFunction
CAgent agent
CTransitionFunctionEnvironment dynModel
CContinuousActionGradientPolicy gradientPolicy

Constructor & Destructor Documentation

CNumericPolicyGradientCalculator::CNumericPolicyGradientCalculator CAgent agent,
CContinuousActionGradientPolicy policy,
CTransitionFunctionEnvironment dynModel,
CRewardFunction reward,
double  stepSize,
CPolicyEvaluator evaluator
 
CNumericPolicyGradientCalculator::~CNumericPolicyGradientCalculator  ) 
 

Member Function Documentation

virtual void CNumericPolicyGradientCalculator::getGradient CFeatureList gradientFeatures  )  [virtual]
 

Implements CPolicyGradientCalculator.


Member Data Documentation

CAgent* CNumericPolicyGradientCalculator::agent [protected]
 
CTransitionFunctionEnvironment* CNumericPolicyGradientCalculator::dynModel [protected]
 
CFeatureList* CNumericPolicyGradientCalculator::gradientFeatures [protected]
 
CContinuousActionGradientPolicy* CNumericPolicyGradientCalculator::gradientPolicy [protected]
 
CRewardFunction* CNumericPolicyGradientCalculator::rewardFunction [protected]
 
double* CNumericPolicyGradientCalculator::weights [protected]
 

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