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 CAdaptiveParameterCalculator Class Reference Interface for all adaptive Parameter Calculators. More... #include <cparameters.h> Inheritance diagram for CAdaptiveParameterCalculator: List of all members. Public Member Functions   CAdaptiveParameterCalculator (CParameters *targetObject, string targetParameter, int functionKind) virtual  ~CAdaptiveParameterCalculator () virtual void  setParameterValue (double value)   Interface for all adaptive Parameter Calculators. virtual void  resetCalculator ()=0   Reset the targetValue. virtual void  onParametersChanged ()   Updates functionKind according to the parameter "APFunctionKind". Protected Attributes int  functionKind   The function kind is stored here. CParameters *  targetObject string  targetParameter Detailed Description Interface for all adaptive Parameter Calculators. For each parameter you can specify an adaptive parameter calculator (APC), which calculates the parameter value each time it is retrieved. Now, each time the parameter's value is requested by "getParameter" the calculated value of the adaptive parameter calculator is returned instead of the constant double value of the parameter map. This is useful for example for adapting the learning rate or the exploration of a policy. The parameter's value can depend on any other value like the number of steps or episodes or even the current average reward. Adaptive Parameter Calculators also have same parameters too, all parameters of the Adaptive Parameter Classes begin with the prefix "AP". When an adaptive parameter calculator is set to a parameter, the parameters name is used as prefix for the parameters of the adaptive parameter calculator. So the parameter "APFunctionKind" gets to the parameter "VLearningRateAPFunctionKind" if you specify a APC for the parameter "VLearningRate". The interface CAdaptiveParameterCalculator already includes the parameter "APFunctionKind", the functionkind property is used to determine which function shall be used to transform the targetvalue in the parametervalue. The targetvalue can be the number of learning steps, number of episodes, the current value of a V-Function or the average reward. See the subclasses for more details. There are 6 different functionkinds implemented. Linear Function (LINEAR, 1) Square Function (SQUARE, 2) Logarithm Function (LOG, 3) Fraction (FRACT, 4) Squared Fraction (FRACTSQUARE, 5) Logarithm Fraction (FRACTLOG, 6) All these functions are used in a slightly different way for the 2 main subclasses, CAdaptiveParameterBoundedValuesCalculator and CAdaptiveParameterUnBoundedValuesCalculator. For more details see these classes. Parameters of CAdaptiveParameterCalculator: "APFunctionKind": Defining the function to transform target value into the parameter value. See also: CAdaptiveParameterUnBoundedValuesCalculator CAdaptiveParameterBoundedValuesCalculator Constructor & Destructor Documentation CAdaptiveParameterCalculator::CAdaptiveParameterCalculator (  CParameters *  targetObject, string  targetParameter, int  functionKind )  virtual CAdaptiveParameterCalculator::~CAdaptiveParameterCalculator (   )  [virtual] Member Function Documentation virtual void CAdaptiveParameterCalculator::onParametersChanged (   )  [virtual]   Updates functionKind according to the parameter "APFunctionKind". Reimplemented from CParameterObject. Reimplemented in CAdaptiveParameterFromNStepsCalculator, CAdaptiveParameterFromNEpisodesCalculator, CAdaptiveParameterFromAverageRewardCalculator, CAdaptiveParameterBoundedValuesCalculator, CAdaptiveParameterUnBoundedValuesCalculator, and CAdaptiveParameterFromValueCalculator. virtual void CAdaptiveParameterCalculator::resetCalculator (   )  [pure virtual]   Reset the targetValue. This function is used for resetting for example the steps or number of episodes when learning is restarted. (used for parameter evaluation) Implemented in CAdaptiveParameterFromNStepsCalculator, CAdaptiveParameterFromNEpisodesCalculator, CAdaptiveParameterFromAverageRewardCalculator, and CAdaptiveParameterFromValueCalculator. virtual void CAdaptiveParameterCalculator::setParameterValue (  double  value  )  [virtual]   Interface for all adaptive Parameter Calculators. Reimplemented in CAdaptiveParameterBoundedValuesCalculator, and CAdaptiveParameterUnBoundedValuesCalculator. Member Data Documentation int CAdaptiveParameterCalculator::functionKind [protected]   The function kind is stored here. The parameter "APFunctionKind" isn't used for performance reasons, functionKind is updated each time the "APFunctionKind" parameter changes (in the function onParameterChanged()) CParameters* CAdaptiveParameterCalculator::targetObject [protected] string CAdaptiveParameterCalculator::targetParameter [protected] The documentation for this class was generated from the following file: cparameters.h