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 CFittedIteration Class Reference #include <cbatchlearning.h> Inheritance diagram for CFittedIteration: List of all members. Public Member Functions   CFittedIteration (CEpisodeHistory *episodeHistory, CRewardHistory *rewardLogger, CBatchDataGenerator *dataGenerator) virtual  ~CFittedIteration () virtual void  doEvaluationTrial () virtual void  evaluatePolicy (int trials) virtual CBatchDataGenerator *  createTrainingsData () virtual void  setDataCollector (CDataCollector *dataCollector) virtual void  setInitialPolicyEvaluation (CPolicyEvaluation *initialPolicyEvaluation) virtual void  resetLearnData () void  setActorLearner (CPolicyEvaluation *actorLearner) virtual void  evaluatePolicy () Protected Member Functions virtual void  addResidualInput (CStep *step, CAction *action, double oldV, double newV, double nearestNeighborDistance, CAction *nextHistoryActon=NULL, double nextReward=0.0) virtual double  getWeighting (CStateCollection *state, CAction *action) virtual double  getValue (CStateCollection *state, CAction *action) virtual void  onParametersChanged ()   Interface for faster parameter handling (see description of the class). Protected Attributes CAgentController *  estimationPolicy CBatchDataGenerator *  dataGenerator CEpisodeHistory *  episodeHistory CRewardHistory *  rewardLogger CDataCollector *  dataCollector CPolicyEvaluation *  actorLearner CPolicyEvaluation *  initialPolicyEvaluation int  useResidualAlgorithm Constructor & Destructor Documentation CFittedIteration::CFittedIteration (  CEpisodeHistory *  episodeHistory, CRewardHistory *  rewardLogger, CBatchDataGenerator *  dataGenerator )  virtual CFittedIteration::~CFittedIteration (   )  [virtual] Member Function Documentation virtual void CFittedIteration::addResidualInput (  CStep *  step, CAction *  action, double  oldV, double  newV, double  nearestNeighborDistance, CAction *  nextHistoryActon = NULL, double  nextReward = 0.0 )  [protected, virtual]   Reimplemented in CFittedQIterationAnalyzer, and CFittedQIteration. virtual CBatchDataGenerator* CFittedIteration::createTrainingsData (   )  [virtual] virtual void CFittedIteration::doEvaluationTrial (   )  [virtual]   Reimplemented in CFittedQIteration. virtual void CFittedIteration::evaluatePolicy (   )  [virtual]   Reimplemented from CPolicyEvaluation. virtual void CFittedIteration::evaluatePolicy (  int  trials  )  [virtual]   Implements CPolicyEvaluation. virtual double CFittedIteration::getValue (  CStateCollection *  state, CAction *  action )  [protected, virtual]   Reimplemented in CFittedQIterationAnalyzer. virtual double CFittedIteration::getWeighting (  CStateCollection *  state, CAction *  action )  [protected, virtual]   Reimplemented in CFittedVIteration. virtual void CFittedIteration::onParametersChanged (   )  [protected, virtual]   Interface for faster parameter handling (see description of the class). Reimplemented from CParameterObject. virtual void CFittedIteration::resetLearnData (   )  [virtual]   Reimplemented from CPolicyEvaluation. void CFittedIteration::setActorLearner (  CPolicyEvaluation *  actorLearner  )  virtual void CFittedIteration::setDataCollector (  CDataCollector *  dataCollector  )  [virtual] virtual void CFittedIteration::setInitialPolicyEvaluation (  CPolicyEvaluation *  initialPolicyEvaluation  )  [virtual] Member Data Documentation CPolicyEvaluation* CFittedIteration::actorLearner [protected] CDataCollector* CFittedIteration::dataCollector [protected] CBatchDataGenerator* CFittedIteration::dataGenerator [protected] CEpisodeHistory* CFittedIteration::episodeHistory [protected] CAgentController* CFittedIteration::estimationPolicy [protected]   Reimplemented in CFittedVIteration. CPolicyEvaluation* CFittedIteration::initialPolicyEvaluation [protected] CRewardHistory* CFittedIteration::rewardLogger [protected] int CFittedIteration::useResidualAlgorithm [protected] The documentation for this class was generated from the following file: cbatchlearning.h