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 CContinuousDynamicProgramming Class Reference #include <cbatchlearning.h> Inheritance diagram for CContinuousDynamicProgramming: List of all members. Public Member Functions   CContinuousDynamicProgramming (CActionSet *allActions, CSamplingBasedTransitionModel *transModel) virtual  ~CContinuousDynamicProgramming () virtual void  evaluatePolicy (int numEvaluations) virtual double  getValueFromDistribution (CActionSet *availableActions, double *actionValues, CActionDistribution *distribution) virtual double  getValue (CState *state, CActionSet *availableActions)=0 virtual void  updateOutputs (int index, CActionSet *availableActions, double *actionValues)=0 virtual void  learn ()=0 virtual void  resetLearnData () virtual void  resetDynamicProgramming ()=0 Protected Attributes CSamplingBasedTransitionModel *  transModel CActionSet *  availableActions double *  actionValues double *  actionProbabilities int  numIteration Constructor & Destructor Documentation CContinuousDynamicProgramming::CContinuousDynamicProgramming (  CActionSet *  allActions, CSamplingBasedTransitionModel *  transModel )  virtual CContinuousDynamicProgramming::~CContinuousDynamicProgramming (   )  [virtual] Member Function Documentation virtual void CContinuousDynamicProgramming::evaluatePolicy (  int  numEvaluations  )  [virtual]   Implements CPolicyEvaluation. virtual double CContinuousDynamicProgramming::getValue (  CState *  state, CActionSet *  availableActions )  [pure virtual]   Implemented in CContinuousDynamicVProgramming, CContinuousDynamicQProgramming, and CContinuousMCQEvaluation. virtual double CContinuousDynamicProgramming::getValueFromDistribution (  CActionSet *  availableActions, double *  actionValues, CActionDistribution *  distribution )  [virtual] virtual void CContinuousDynamicProgramming::learn (   )  [pure virtual]   Implemented in CContinuousDynamicVProgramming, and CContinuousDynamicQProgramming. virtual void CContinuousDynamicProgramming::resetDynamicProgramming (   )  [pure virtual]   Implemented in CContinuousDynamicVProgramming, and CContinuousDynamicQProgramming. virtual void CContinuousDynamicProgramming::resetLearnData (   )  [virtual]   Reimplemented from CPolicyEvaluation. virtual void CContinuousDynamicProgramming::updateOutputs (  int  index, CActionSet *  availableActions, double *  actionValues )  [pure virtual]   Implemented in CContinuousDynamicVProgramming, and CContinuousDynamicQProgramming. Member Data Documentation double* CContinuousDynamicProgramming::actionProbabilities [protected] double* CContinuousDynamicProgramming::actionValues [protected] CActionSet* CContinuousDynamicProgramming::availableActions [protected] int CContinuousDynamicProgramming::numIteration [protected] CSamplingBasedTransitionModel* CContinuousDynamicProgramming::transModel [protected] The documentation for this class was generated from the following file: cbatchlearning.h