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 CStateReward Class Reference Reward Function that only depends on the current state. More... #include <crewardfunction.h> Inheritance diagram for CStateReward: List of all members. Public Member Functions   CStateReward (CStateProperties *properties) virtual  ~CStateReward () virtual double  getReward (CStateCollection *oldState, CAction *action, CStateCollection *newState)   Virtual function for calculating the reward. virtual double  getStateReward (CState *modelState)=0 virtual void  getInputDerivation (CState *, ColumnVector *) Protected Attributes CStateProperties *  properties Detailed Description Reward Function that only depends on the current state. This class is the interface for all reward functions that only depend on the current (model) state. All subclasses have to implement the function getStateReward, which is called by the getReward function of the class with the newState object as argument. The class also offers the function getInputDerivation where the derivation of the reward function with respect to the model state can be calculated. This is needed by some algorithm (analytical pegasus), you will have to implement this function if you want to use these algorithms. Constructor & Destructor Documentation CStateReward::CStateReward (  CStateProperties *  properties  )  virtual CStateReward::~CStateReward (   )  [inline, virtual] Member Function Documentation virtual void CStateReward::getInputDerivation (  CState *  , ColumnVector *  )  [inline, virtual]   Reimplemented in CAcroBotRewardFunction, CAcroBotHeightRewardFunction, CAcroBotVelocityRewardFunction, CAcroBotExpRewardFunction, CCartPoleRewardFunction, CCartPoleHeightRewardFunction, CSubGoalBehaviour, and CPendulumRewardFunction. virtual double CStateReward::getReward (  CStateCollection *  oldState, CAction *  action, CStateCollection *  newState )  [virtual]   Virtual function for calculating the reward. Implements CRewardFunction. virtual double CStateReward::getStateReward (  CState *  modelState  )  [pure virtual]   Implemented in CAcroBotRewardFunction, CAcroBotHeightRewardFunction, CAcroBotVelocityRewardFunction, CAcroBotExpRewardFunction, CCartPoleRewardFunction, CCartPoleHeightRewardFunction, CSubGoalBehaviour, CMultiPoleContinuousReward, and CPendulumRewardFunction. Member Data Documentation CStateProperties* CStateReward::properties [protected]   Reimplemented from CStateObject. The documentation for this class was generated from the following file: crewardfunction.h