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 CVPolicyLearner Class Reference #include <ctdpolicylearner.h> Inheritance diagram for CVPolicyLearner: List of all members. Public Member Functions   CVPolicyLearner (CStateReward *rewardFunction, CDynamicModel *dynModel, CDynamicModelInputDerivationCalculator *dynModeldInput, CGradientVFunction *vFunction, CVFunctionInputDerivationCalculator *vFunctionInputDerivation, CContinuousActionGradientPolicy *gradientPolicy, CCAGradientPolicyInputDerivationCalculator *policydInput, std::list< CStateModifier * > *stateModifiers, int nForwardView) virtual  ~CVPolicyLearner () virtual void  nextStep (CStateCollection *oldState, CAction *action, double reward, CStateCollection *nextState)   virtual function, to be implemented by subclass virtual void  newEpisode ()   tells the Listener that a new Episode has startet.   CVPolicyLearner (CStateReward *rewardFunction, CTransitionFunction *dynModel, CTransitionFunctionInputDerivationCalculator *dynModeldInput, CAbstractVFunction *vFunction, CVFunctionInputDerivationCalculator *vFunctionInputDerivation, CContinuousActionGradientPolicy *gradientPolicy, CCAGradientPolicyInputDerivationCalculator *policydInput, std::list< CStateModifier * > *stateModifiers, int nForwardView) virtual  ~CVPolicyLearner () virtual void  nextStep (CStateCollection *oldState, CAction *action, double reward, CStateCollection *nextState)   virtual function, to be implemented by subclass virtual void  newEpisode ()   tells the Listener that a new Episode has startet. void  calculateGradient (std::list< CStateCollectionImpl * > *states, std::list< ColumnVector * > *Drewards, std::list< CContinuousActionData * > *actionDatas, CFeatureList *policyGradient) Protected Types typedef std::list< CFeatureList * >  CStateGradient typedef std::list< CFeatureList * >  CStateGradient Protected Member Functions void  getDNextState (CStateGradient *stateGradient1, CStateGradient *stateGradient2, CStateCollection *currentState, CContinuousActionData *data) void  multMatrixFeatureList (Matrix *matrix, CFeatureList *features, int index, std::list< CFeatureList * > *newFeatures) void  getDNextState (CStateGradient *stateGradient1, CStateGradient *stateGradient2, CStateCollection *currentState, CContinuousActionData *data) void  multMatrixFeatureList (Matrix *matrix, CFeatureList *features, int index, std::list< CFeatureList * > *newFeatures) Protected Attributes CGradientVFunction *  vFunction   learned VFunction CVFunctionInputDerivationCalculator *  vFunctionInputDerivation CContinuousActionGradientPolicy *  gradientPolicy CCAGradientPolicyInputDerivationCalculator *  policydInput ColumnVector *  dReward ColumnVector *  dVFunction Matrix *  dPolicy Matrix *  dModelInput CContinuousActionData *  data std::list< CStateGradient * > *  stateGradients CStateGradient *  stateGradient1 CStateGradient *  stateGradient2 CStateGradient *  dModelGradient CStateReward *  rewardFunction CDynamicModel *  dynModel CDynamicModelInputDerivationCalculator *  dynModeldInput CStateCollectionImpl *  tempStateCol CFeatureList *  policyGradient int  nForwardView CAbstractVFunction *  vFunction CVFunctionInputDerivationCalculator *  vFunctionInputDerivation CContinuousActionGradientPolicy *  gradientPolicy CCAGradientPolicyInputDerivationCalculator *  policydInput ColumnVector *  dReward ColumnVector *  dVFunction Matrix *  dPolicy Matrix *  dModelInput CContinuousActionData *  data std::list< CStateGradient * > *  stateGradients CStateGradient *  stateGradient1 CStateGradient *  stateGradient2 CStateGradient *  dModelGradient CStateReward *  rewardFunction CTransitionFunction *  dynModel CTransitionFunctionInputDerivationCalculator *  dynModeldInput CStateCollectionImpl *  tempStateCol CFeatureList *  policyGradient std::list< CStateCollectionImpl * > *  pastStates std::list< ColumnVector * > *  pastDRewards std::list< CContinuousActionData * > *  pastActions std::list< CStateCollectionImpl * > *  statesResource std::list< ColumnVector * > *  rewardsResource std::list< CContinuousActionData * > *  actionsResource std::list< CStateModifier * > *  stateModifiers Member Typedef Documentation typedef std::list<CFeatureList *> CVPolicyLearner::CStateGradient [protected] typedef std::list<CFeatureList *> CVPolicyLearner::CStateGradient [protected] Constructor & Destructor Documentation CVPolicyLearner::CVPolicyLearner (  CStateReward *  rewardFunction, CDynamicModel *  dynModel, CDynamicModelInputDerivationCalculator *  dynModeldInput, CGradientVFunction *  vFunction, CVFunctionInputDerivationCalculator *  vFunctionInputDerivation, CContinuousActionGradientPolicy *  gradientPolicy, CCAGradientPolicyInputDerivationCalculator *  policydInput, std::list< CStateModifier * > *  stateModifiers, int  nForwardView )  virtual CVPolicyLearner::~CVPolicyLearner (   )  [virtual] CVPolicyLearner::CVPolicyLearner (  CStateReward *  rewardFunction, CTransitionFunction *  dynModel, CTransitionFunctionInputDerivationCalculator *  dynModeldInput, CAbstractVFunction *  vFunction, CVFunctionInputDerivationCalculator *  vFunctionInputDerivation, CContinuousActionGradientPolicy *  gradientPolicy, CCAGradientPolicyInputDerivationCalculator *  policydInput, std::list< CStateModifier * > *  stateModifiers, int  nForwardView )  virtual CVPolicyLearner::~CVPolicyLearner (   )  [virtual] Member Function Documentation void CVPolicyLearner::calculateGradient (  std::list< CStateCollectionImpl * > *  states, std::list< ColumnVector * > *  Drewards, std::list< CContinuousActionData * > *  actionDatas, CFeatureList *  policyGradient )  void CVPolicyLearner::getDNextState (  CStateGradient *  stateGradient1, CStateGradient *  stateGradient2, CStateCollection *  currentState, CContinuousActionData *  data )  [protected] void CVPolicyLearner::getDNextState (  CStateGradient *  stateGradient1, CStateGradient *  stateGradient2, CStateCollection *  currentState, CContinuousActionData *  data )  [protected] void CVPolicyLearner::multMatrixFeatureList (  Matrix *  matrix, CFeatureList *  features, int  index, std::list< CFeatureList * > *  newFeatures )  [protected] void CVPolicyLearner::multMatrixFeatureList (  Matrix *  matrix, CFeatureList *  features, int  index, std::list< CFeatureList * > *  newFeatures )  [protected] virtual void CVPolicyLearner::newEpisode (   )  [virtual]   tells the Listener that a new Episode has startet. Reimplemented from CSemiMDPListener. virtual void CVPolicyLearner::newEpisode (   )  [virtual]   tells the Listener that a new Episode has startet. Reimplemented from CSemiMDPListener. virtual void CVPolicyLearner::nextStep (  CStateCollection *  oldState, CAction *  action, double  reward, CStateCollection *  nextState )  [virtual]   virtual function, to be implemented by subclass Reimplemented from CSemiMDPRewardListener. virtual void CVPolicyLearner::nextStep (  CStateCollection *  oldState, CAction *  action, double  reward, CStateCollection *  nextState )  [virtual]   virtual function, to be implemented by subclass Reimplemented from CSemiMDPRewardListener. Member Data Documentation std::list<CContinuousActionData *>* CVPolicyLearner::actionsResource [protected] CContinuousActionData* CVPolicyLearner::data [protected] CContinuousActionData* CVPolicyLearner::data [protected] CStateGradient* CVPolicyLearner::dModelGradient [protected] CStateGradient* CVPolicyLearner::dModelGradient [protected] Matrix* CVPolicyLearner::dModelInput [protected] Matrix* CVPolicyLearner::dModelInput [protected] Matrix* CVPolicyLearner::dPolicy [protected] Matrix* CVPolicyLearner::dPolicy [protected] ColumnVector* CVPolicyLearner::dReward [protected] ColumnVector* CVPolicyLearner::dReward [protected] ColumnVector* CVPolicyLearner::dVFunction [protected] ColumnVector* CVPolicyLearner::dVFunction [protected] CTransitionFunction* CVPolicyLearner::dynModel [protected] CDynamicModel* CVPolicyLearner::dynModel [protected] CTransitionFunctionInputDerivationCalculator* CVPolicyLearner::dynModeldInput [protected] CDynamicModelInputDerivationCalculator* CVPolicyLearner::dynModeldInput [protected] CContinuousActionGradientPolicy* CVPolicyLearner::gradientPolicy [protected] CContinuousActionGradientPolicy* CVPolicyLearner::gradientPolicy [protected] int CVPolicyLearner::nForwardView [protected] std::list<CContinuousActionData *>* CVPolicyLearner::pastActions [protected] std::list<ColumnVector *>* CVPolicyLearner::pastDRewards [protected] std::list<CStateCollectionImpl *>* CVPolicyLearner::pastStates [protected] CCAGradientPolicyInputDerivationCalculator* CVPolicyLearner::policydInput [protected] CCAGradientPolicyInputDerivationCalculator* CVPolicyLearner::policydInput [protected] CFeatureList* CVPolicyLearner::policyGradient [protected] CFeatureList* CVPolicyLearner::policyGradient [protected] CStateReward* CVPolicyLearner::rewardFunction [protected] CStateReward* CVPolicyLearner::rewardFunction [protected] std::list<ColumnVector *>* CVPolicyLearner::rewardsResource [protected] CStateGradient* CVPolicyLearner::stateGradient1 [protected] CStateGradient* CVPolicyLearner::stateGradient1 [protected] CStateGradient* CVPolicyLearner::stateGradient2 [protected] CStateGradient* CVPolicyLearner::stateGradient2 [protected] std::list<CStateGradient *>* CVPolicyLearner::stateGradients [protected] std::list<CStateGradient *>* CVPolicyLearner::stateGradients [protected] std::list<CStateModifier *>* CVPolicyLearner::stateModifiers [protected] std::list<CStateCollectionImpl *>* CVPolicyLearner::statesResource [protected] CStateCollectionImpl* CVPolicyLearner::tempStateCol [protected] CStateCollectionImpl* CVPolicyLearner::tempStateCol [protected] CAbstractVFunction* CVPolicyLearner::vFunction [protected] CGradientVFunction* CVPolicyLearner::vFunction [protected]   learned VFunction CVFunctionInputDerivationCalculator* CVPolicyLearner::vFunctionInputDerivation [protected] CVFunctionInputDerivationCalculator* CVPolicyLearner::vFunctionInputDerivation [protected] The documentation for this class was generated from the following files: ctdpolicylearner.h cvaluepolicygradientlearner.h