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 CGPOMDPGradientCalculator Class Reference #include <cpolicygradient.h> Inheritance diagram for CGPOMDPGradientCalculator: List of all members. Public Member Functions   CGPOMDPGradientCalculator (CRewardFunction *reward, CStochasticPolicy *policy, CPolicyEvaluator *evaluator, CAgent *agent, CReinforcementBaseLineCalculator *baseLine, int TSteps, int nEpisodes, double beta) virtual  ~CGPOMDPGradientCalculator () virtual void  nextStep (CStateCollection *oldState, CAction *action, double reward, CStateCollection *newState)   virtual function, to be implemented by subclass virtual void  newEpisode ()   tells the Listener that a new Episode has startet. virtual void  getGradient (CFeatureList *gradient) virtual CFeatureList *  getGlobalGradient () virtual void  setGlobalGradient (CFeatureList *globalGradient) Protected Attributes CFeatureList *  localGradient CFeatureList *  localZTrace CFeatureList *  globalGradient CAgent *  agent CReinforcementBaseLineCalculator *  baseLine CStochasticPolicy *  stochPolicy Constructor & Destructor Documentation CGPOMDPGradientCalculator::CGPOMDPGradientCalculator (  CRewardFunction *  reward, CStochasticPolicy *  policy, CPolicyEvaluator *  evaluator, CAgent *  agent, CReinforcementBaseLineCalculator *  baseLine, int  TSteps, int  nEpisodes, double  beta )  virtual CGPOMDPGradientCalculator::~CGPOMDPGradientCalculator (   )  [virtual] Member Function Documentation virtual CFeatureList* CGPOMDPGradientCalculator::getGlobalGradient (   )  [virtual] virtual void CGPOMDPGradientCalculator::getGradient (  CFeatureList *  gradient  )  [virtual]   Implements CPolicyGradientCalculator. virtual void CGPOMDPGradientCalculator::newEpisode (   )  [virtual]   tells the Listener that a new Episode has startet. Reimplemented from CSemiMDPListener. virtual void CGPOMDPGradientCalculator::nextStep (  CStateCollection *  oldState, CAction *  action, double  reward, CStateCollection *  newState )  [virtual]   virtual function, to be implemented by subclass Reimplemented from CSemiMDPRewardListener. virtual void CGPOMDPGradientCalculator::setGlobalGradient (  CFeatureList *  globalGradient  )  [virtual] Member Data Documentation CAgent* CGPOMDPGradientCalculator::agent [protected] CReinforcementBaseLineCalculator* CGPOMDPGradientCalculator::baseLine [protected] CFeatureList* CGPOMDPGradientCalculator::globalGradient [protected] CFeatureList* CGPOMDPGradientCalculator::localGradient [protected] CFeatureList* CGPOMDPGradientCalculator::localZTrace [protected] CStochasticPolicy* CGPOMDPGradientCalculator::stochPolicy [protected] The documentation for this class was generated from the following file: cpolicygradient.h