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

CPEGASUSNumericPolicyGradientCalculator Class Reference

#include <cpegasus.h>

Inheritance diagram for CPEGASUSNumericPolicyGradientCalculator:

CPEGASUSPolicyGradientCalculator CPolicyGradientCalculator CGradientCalculator CParameterObject CParameters List of all members.


Public Member Functions

  CPEGASUSNumericPolicyGradientCalculator (CAgent *agent, CContinuousActionGradientPolicy *policy, CTransitionFunctionEnvironment *dynModel, CRewardFunction *reward, double stepSize, int startStates, int horizon, double gamma)
  ~CPEGASUSNumericPolicyGradientCalculator ()
virtual void  getPEGASUSGradient (CFeatureList *gradientFeatures, CStateList *startStates)


Protected Attributes

CFeatureList gradientFeatures
double *  weights
CRewardFunction rewardFunction
CAgent agent

Constructor & Destructor Documentation

CPEGASUSNumericPolicyGradientCalculator::CPEGASUSNumericPolicyGradientCalculator CAgent agent,
CContinuousActionGradientPolicy policy,
CTransitionFunctionEnvironment dynModel,
CRewardFunction reward,
double  stepSize,
int  startStates,
int  horizon,
double  gamma
 
CPEGASUSNumericPolicyGradientCalculator::~CPEGASUSNumericPolicyGradientCalculator  ) 
 

Member Function Documentation

virtual void CPEGASUSNumericPolicyGradientCalculator::getPEGASUSGradient CFeatureList gradientFeatures,
CStateList startStates
[virtual]
 

Implements CPEGASUSPolicyGradientCalculator.


Member Data Documentation

CAgent* CPEGASUSNumericPolicyGradientCalculator::agent [protected]
 
CFeatureList* CPEGASUSNumericPolicyGradientCalculator::gradientFeatures [protected]
 
CRewardFunction* CPEGASUSNumericPolicyGradientCalculator::rewardFunction [protected]
 
double* CPEGASUSNumericPolicyGradientCalculator::weights [protected]
 

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