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 CRewardEpisode Class Reference Logs the reward during an Episode. More... #include <crewardmodel.h> Inheritance diagram for CRewardEpisode: List of all members. Public Member Functions   CRewardEpisode (CRewardFunction *rewardFunction) virtual  ~CRewardEpisode () virtual void  nextStep (CStateCollection *oldState, CAction *action, double reward, CStateCollection *newState)   Stores the current reward at the and of the rewards vector. virtual void  newEpisode ()   clears the reward vector int  getNumRewards () double  getReward (int index)   returns the requested reward from the rewards vector. double  getMeanReward () double  getLastStepsMeanReward (int Steps) virtual void  saveBIN (FILE *stream) virtual void  saveData (FILE *stream) virtual void  loadBIN (FILE *stream) virtual void  loadData (FILE *stream) Protected Attributes std::vector< double > *  rewards   array for the rewards Detailed Description Logs the reward during an Episode. Maintains a double array for logging the reward of each step. Can be used in combination with a normal episode to log the whole State-Action-Reward-State Tuples. Constructor & Destructor Documentation CRewardEpisode::CRewardEpisode (  CRewardFunction *  rewardFunction  )  virtual CRewardEpisode::~CRewardEpisode (   )  [virtual] Member Function Documentation double CRewardEpisode::getLastStepsMeanReward (  int  Steps  )  double CRewardEpisode::getMeanReward (   )  int CRewardEpisode::getNumRewards (   )  double CRewardEpisode::getReward (  int  index  )    returns the requested reward from the rewards vector. virtual void CRewardEpisode::loadBIN (  FILE *  stream  )  [virtual] virtual void CRewardEpisode::loadData (  FILE *  stream  )  [virtual] virtual void CRewardEpisode::newEpisode (   )  [virtual]   clears the reward vector Reimplemented from CSemiMDPListener. virtual void CRewardEpisode::nextStep (  CStateCollection *  oldState, CAction *  action, double  reward, CStateCollection *  newState )  [virtual]   Stores the current reward at the and of the rewards vector. Reimplemented from CSemiMDPRewardListener. virtual void CRewardEpisode::saveBIN (  FILE *  stream  )  [virtual] virtual void CRewardEpisode::saveData (  FILE *  stream  )  [virtual] Member Data Documentation std::vector<double>* CRewardEpisode::rewards [protected]   array for the rewards The documentation for this class was generated from the following file: crewardmodel.h