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 CVFunctionFromGradientFunction Class Reference Class for learning with Torch-Gradient machines. More... #include <ctorchvfunction.h> Inheritance diagram for CVFunctionFromGradientFunction: List of all members. Public Member Functions   CVFunctionFromGradientFunction (CGradientFunction *gradientFunction, CStateProperties *properties)   Creates a new value function learning with a torch gradient machine. virtual  ~CVFunctionFromGradientFunction () virtual void  setValue (CState *state, double value)   Calls update value with "value" - currentValue as parameter. virtual void  resetData ()   Resets the parameters of the gradient machine. virtual double  getValue (CState *state)   Converts the state into an input sequence, tansfers the sequence to the machine and returns its output. virtual void  getGradient (CStateCollection *originalState, CFeatureList *modifiedState) virtual int  getNumWeights ()   Returns the number of weights. virtual CAbstractVETraces *  getStandardETraces ()   Returns a standard VETraces object. void  getInputDerivation (CStateCollection *originalState, ColumnVector *targetVector) virtual void  getWeights (double *parameters)   Function for getting all weights. virtual void  setWeights (double *parameters)   Function for setting all weights. Protected Member Functions virtual void  updateWeights (CFeatureList *gradientFeatures)   Interface for updating the weights. void  getInputSequence (CState *state, ColumnVector *sequence) Protected Attributes CGradientFunction *  gradientFunction   Pointer to the gradient Machine. ColumnVector *  input ColumnVector *  outputError Matrix *  inputDerivation Detailed Description Class for learning with Torch-Gradient machines. Extends the ability from CTorchVFunction, to learn with a torch gradient machine. The parameters of the machine are updated by adding the current gradient of the parameters multplied with the difference given by updateValue. Constructor & Destructor Documentation CVFunctionFromGradientFunction::CVFunctionFromGradientFunction (  CGradientFunction *  gradientFunction, CStateProperties *  properties )    Creates a new value function learning with a torch gradient machine. virtual CVFunctionFromGradientFunction::~CVFunctionFromGradientFunction (   )  [virtual] Member Function Documentation virtual void CVFunctionFromGradientFunction::getGradient (  CStateCollection *  originalState, CFeatureList *  modifiedState )  [virtual]   Implements CGradientVFunction. void CVFunctionFromGradientFunction::getInputDerivation (  CStateCollection *  originalState, ColumnVector *  targetVector )  [virtual]   Implements CVFunctionInputDerivationCalculator. void CVFunctionFromGradientFunction::getInputSequence (  CState *  state, ColumnVector *  sequence )  [protected] virtual int CVFunctionFromGradientFunction::getNumWeights (   )  [virtual]   Returns the number of weights. Implements CGradientUpdateFunction. virtual CAbstractVETraces* CVFunctionFromGradientFunction::getStandardETraces (   )  [virtual]   Returns a standard VETraces object. The function has to return a new instantiated CAbstractVETraces object, which is used to compose the CQETtraces object. The function returns CStateVETraces as standard. Reimplemented from CGradientVFunction. virtual double CVFunctionFromGradientFunction::getValue (  CState *  state  )  [virtual]   Converts the state into an input sequence, tansfers the sequence to the machine and returns its output. Implements CAbstractVFunction. virtual void CVFunctionFromGradientFunction::getWeights (  double *  parameters  )  [virtual]   Function for getting all weights. The double array is assumed to be large enough. This isn't checked! Implements CGradientUpdateFunction. virtual void CVFunctionFromGradientFunction::resetData (   )  [virtual]   Resets the parameters of the gradient machine. Implements CGradientVFunction. virtual void CVFunctionFromGradientFunction::setValue (  CState *  state, double  value )  [virtual]   Calls update value with "value" - currentValue as parameter. For learning only updateValue should be used. Reimplemented from CAbstractVFunction. virtual void CVFunctionFromGradientFunction::setWeights (  double *  parameters  )  [virtual]   Function for setting all weights. The double array is assumed to be large enough. This isn't checked! Implements CGradientUpdateFunction. virtual void CVFunctionFromGradientFunction::updateWeights (  CFeatureList *  gradientFeatures  )  [protected, virtual]   Interface for updating the weights. Implements CGradientUpdateFunction. Member Data Documentation CGradientFunction* CVFunctionFromGradientFunction::gradientFunction [protected]   Pointer to the gradient Machine. ColumnVector* CVFunctionFromGradientFunction::input [protected] Matrix* CVFunctionFromGradientFunction::inputDerivation [protected] ColumnVector* CVFunctionFromGradientFunction::outputError [protected] The documentation for this class was generated from the following file: ctorchvfunction.h