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 CPEGASUSAnalyticalPolicyGradientCalculator Class Reference #include <cpegasus.h> Inheritance diagram for CPEGASUSAnalyticalPolicyGradientCalculator: List of all members. Public Member Functions   CPEGASUSAnalyticalPolicyGradientCalculator (CAgent *agent, CContinuousActionGradientPolicy *policy, CCAGradientPolicyInputDerivationCalculator *policyInputDerivation, CTransitionFunctionEnvironment *dynModel, CTransitionFunctionInputDerivationCalculator *dynModeldInput, CStateReward *reward, int numStartStates, int horizon, double gamma)   ~CPEGASUSAnalyticalPolicyGradientCalculator () virtual void  getPEGASUSGradient (CFeatureList *gradientFeatures, CStateList *startStates) virtual void  nextStep (CStateCollection *oldState, CAction *action, CStateCollection *newState)   sends the Listener the S-A-S tuple from a new step virtual void  newEpisode ()   tells the Listener that a new Episode has startet. Protected Member Functions void  multMatrixFeatureList (Matrix *matrix, CFeatureList *features, int index, std::list< CFeatureList * > *newFeatures) Protected Attributes ColumnVector *  dReward Matrix *  dPolicy Matrix *  dModelInput std::list< CFeatureList * > *  stateGradient1 std::list< CFeatureList * > *  stateGradient2 std::list< CFeatureList * > *  dModelGradient CFeatureList *  episodeGradient CStateReward *  rewardFunction CTransitionFunctionInputDerivationCalculator *  dynModeldInput CCAGradientPolicyInputDerivationCalculator *  policydInput int  steps CAgent *  agent Constructor & Destructor Documentation CPEGASUSAnalyticalPolicyGradientCalculator::CPEGASUSAnalyticalPolicyGradientCalculator (  CAgent *  agent, CContinuousActionGradientPolicy *  policy, CCAGradientPolicyInputDerivationCalculator *  policyInputDerivation, CTransitionFunctionEnvironment *  dynModel, CTransitionFunctionInputDerivationCalculator *  dynModeldInput, CStateReward *  reward, int  numStartStates, int  horizon, double  gamma )  CPEGASUSAnalyticalPolicyGradientCalculator::~CPEGASUSAnalyticalPolicyGradientCalculator (   )  Member Function Documentation virtual void CPEGASUSAnalyticalPolicyGradientCalculator::getPEGASUSGradient (  CFeatureList *  gradientFeatures, CStateList *  startStates )  [virtual]   Implements CPEGASUSPolicyGradientCalculator. void CPEGASUSAnalyticalPolicyGradientCalculator::multMatrixFeatureList (  Matrix *  matrix, CFeatureList *  features, int  index, std::list< CFeatureList * > *  newFeatures )  [protected] virtual void CPEGASUSAnalyticalPolicyGradientCalculator::newEpisode (   )  [virtual]   tells the Listener that a new Episode has startet. Reimplemented from CSemiMDPListener. virtual void CPEGASUSAnalyticalPolicyGradientCalculator::nextStep (  CStateCollection *  oldState, CAction *  action, CStateCollection *  newState )  [virtual]   sends the Listener the S-A-S tuple from a new step Reimplemented from CSemiMDPListener. Member Data Documentation CAgent* CPEGASUSAnalyticalPolicyGradientCalculator::agent [protected] std::list<CFeatureList *>* CPEGASUSAnalyticalPolicyGradientCalculator::dModelGradient [protected] Matrix* CPEGASUSAnalyticalPolicyGradientCalculator::dModelInput [protected] Matrix* CPEGASUSAnalyticalPolicyGradientCalculator::dPolicy [protected] ColumnVector* CPEGASUSAnalyticalPolicyGradientCalculator::dReward [protected] CTransitionFunctionInputDerivationCalculator* CPEGASUSAnalyticalPolicyGradientCalculator::dynModeldInput [protected] CFeatureList* CPEGASUSAnalyticalPolicyGradientCalculator::episodeGradient [protected] CCAGradientPolicyInputDerivationCalculator* CPEGASUSAnalyticalPolicyGradientCalculator::policydInput [protected] CStateReward* CPEGASUSAnalyticalPolicyGradientCalculator::rewardFunction [protected] std::list<CFeatureList *>* CPEGASUSAnalyticalPolicyGradientCalculator::stateGradient1 [protected] std::list<CFeatureList *>* CPEGASUSAnalyticalPolicyGradientCalculator::stateGradient2 [protected] int CPEGASUSAnalyticalPolicyGradientCalculator::steps [protected] The documentation for this class was generated from the following file: cpegasus.h