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 CFeatureRewardFunction Class Reference Class for calculating the reward given a feature not a state. More... #include <crewardfunction.h> Inheritance diagram for CFeatureRewardFunction: List of all members. Public Member Functions   CFeatureRewardFunction (CStateProperties *discretizer)   Creates the reward function with the specified discetizer for the states. virtual  ~CFeatureRewardFunction () virtual double  getReward (CStateCollection *oldState, CAction *action, CStateCollection *newState)   Calls getReward(CState *oldState, CAction *action, CState *newState). virtual double  getReward (int oldState, CAction *action, int newState)=0   The function to be implemented by the subclasses, has to return a reward based on discrete integer states. virtual double  getReward (CState *oldState, CAction *action, CState *newState)   Calls getReward(int oldState, CAction *action, int newState) with the features from the state as argument. virtual double  getReward (CFeatureList *oldState, CAction *action, CFeatureList *newState)   Deprecated. Protected Attributes CStateProperties *  discretizer Detailed Description Class for calculating the reward given a feature not a state. Used to calculate the reward for features (integer values). Also implements the CRewardFunction interface, so it can be used as normal reward function. When the getReward function is called with state collection objects as parameters, the state from the specified discritizer is chosen. This state has to be a feature or discrete state, and it gets decomposed into his features Constructor & Destructor Documentation CFeatureRewardFunction::CFeatureRewardFunction (  CStateProperties *  discretizer  )    Creates the reward function with the specified discetizer for the states. virtual CFeatureRewardFunction::~CFeatureRewardFunction (   )  [virtual] Member Function Documentation virtual double CFeatureRewardFunction::getReward (  CFeatureList *  oldState, CAction *  action, CFeatureList *  newState )  [virtual]   Deprecated. virtual double CFeatureRewardFunction::getReward (  CState *  oldState, CAction *  action, CState *  newState )  [virtual]   Calls getReward(int oldState, CAction *action, int newState) with the features from the state as argument. The state has to be a feature state, this state gets decomposed into his features, the reward for the features is calculated and summed up wheighted with the feature factors. Reimplemented in CFeatureStateRewardModel. virtual double CFeatureRewardFunction::getReward (  int  oldState, CAction *  action, int  newState )  [pure virtual]   The function to be implemented by the subclasses, has to return a reward based on discrete integer states. Implemented in CFeatureRewardFunctionFromValueFunction, CFeatureStateRewardFunction, CFeatureRewardModel, and CFeatureStateRewardModel. virtual double CFeatureRewardFunction::getReward (  CStateCollection *  oldState, CAction *  action, CStateCollection *  newState )  [virtual]   Calls getReward(CState *oldState, CAction *action, CState *newState). Implements CRewardFunction. Member Data Documentation CStateProperties* CFeatureRewardFunction::discretizer [protected] The documentation for this class was generated from the following file: crewardfunction.h