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

CContinuousTimeAndActionSigmoidVMGradientPolicy Class Reference

#include <ccontinuoustime.h>

Inheritance diagram for CContinuousTimeAndActionSigmoidVMGradientPolicy:

CContinuousActionGradientPolicy CContinuousActionController CGradientFunction CStateObject CAgentController CGradientUpdateFunction CActionObject CParameterObject CParameterObject CLearnDataObject CParameters CParameters CParameterObject CParameters List of all members.


Public Member Functions

  CContinuousTimeAndActionSigmoidVMGradientPolicy (CContinuousAction *action, CGradientVFunction *gradVFunction, CVFunctionInputDerivationCalculator *vfunction, CTransitionFunction * model, std::list< CStateModifier * > *modifiers)
virtual  ~CContinuousTimeAndActionSigmoidVMGradientPolicy ()
virtual int  getNumWeights ()
  Returns the number of weights.

virtual void  getWeights (double *parameters)
  Function for getting all weights.

virtual void  setWeights (double *parameters)
  Function for setting all weights.

virtual void  getGradient (CStateCollection *inputState, int outputDimension, CFeatureList *gradientFeatures)
virtual void  resetData ()
  Interface for resetting the weights.

virtual void  getNextContinuousAction (CStateCollection *state, CContinuousActionData *contAction)
void  setC (int index, double value)
double  getC (int index)
ColumnVector *  getC ()
virtual void  getNoise (CStateCollection *state, CContinuousActionData *action, CContinuousActionData *noise)


Protected Member Functions

virtual void  updateWeights (CFeatureList *dParams)
  Interface for updating the weights.

void  getActionValues (ColumnVector * actionValues, ColumnVector *noise)
virtual void  getGradientActionValues (ColumnVector *, ColumnVector *)


Protected Attributes

CGradientVFunction vFunction
CStateCollectionImpl derivationState
CFeatureList gradient1
CFeatureList gradient2
CVFunctionInputDerivationCalculator dVFunction
CTransitionFunction model
ColumnVector *  actionValues
ColumnVector *  derivationX
Matrix *  derivationU
ColumnVector *  c

Constructor & Destructor Documentation

CContinuousTimeAndActionSigmoidVMGradientPolicy::CContinuousTimeAndActionSigmoidVMGradientPolicy CContinuousAction action,
CGradientVFunction gradVFunction,
CVFunctionInputDerivationCalculator vfunction,
CTransitionFunction model,
std::list< CStateModifier * > *  modifiers
 
virtual CContinuousTimeAndActionSigmoidVMGradientPolicy::~CContinuousTimeAndActionSigmoidVMGradientPolicy  )  [virtual]
 

Member Function Documentation

void CContinuousTimeAndActionSigmoidVMGradientPolicy::getActionValues ColumnVector *  actionValues,
ColumnVector *  noise
[protected]
 
ColumnVector* CContinuousTimeAndActionSigmoidVMGradientPolicy::getC  )  [inline]
 
double CContinuousTimeAndActionSigmoidVMGradientPolicy::getC int  index  ) 
 
virtual void CContinuousTimeAndActionSigmoidVMGradientPolicy::getGradient CStateCollection inputState,
int  outputDimension,
CFeatureList gradientFeatures
[virtual]
 

Implements CContinuousActionGradientPolicy.

virtual void CContinuousTimeAndActionSigmoidVMGradientPolicy::getGradientActionValues ColumnVector *  ,
ColumnVector * 
[inline, protected, virtual]
 
virtual void CContinuousTimeAndActionSigmoidVMGradientPolicy::getNextContinuousAction CStateCollection state,
CContinuousActionData contAction
[virtual]
 

Implements CContinuousActionGradientPolicy.

virtual void CContinuousTimeAndActionSigmoidVMGradientPolicy::getNoise CStateCollection state,
CContinuousActionData action,
CContinuousActionData noise
[virtual]
 

Reimplemented from CContinuousActionController.

virtual int CContinuousTimeAndActionSigmoidVMGradientPolicy::getNumWeights  )  [virtual]
 

Returns the number of weights.

Implements CContinuousActionGradientPolicy.

virtual void CContinuousTimeAndActionSigmoidVMGradientPolicy::getWeights double *  parameters  )  [virtual]
 

Function for getting all weights.

The double array is assumed to be large enough. This isn't checked!

Implements CContinuousActionGradientPolicy.

virtual void CContinuousTimeAndActionSigmoidVMGradientPolicy::resetData  )  [virtual]
 

Interface for resetting the weights.

Implements CContinuousActionGradientPolicy.

void CContinuousTimeAndActionSigmoidVMGradientPolicy::setC int  index,
double  value
 
virtual void CContinuousTimeAndActionSigmoidVMGradientPolicy::setWeights double *  parameters  )  [virtual]
 

Function for setting all weights.

The double array is assumed to be large enough. This isn't checked!

Implements CContinuousActionGradientPolicy.

virtual void CContinuousTimeAndActionSigmoidVMGradientPolicy::updateWeights CFeatureList dParams  )  [protected, virtual]
 

Interface for updating the weights.

Implements CContinuousActionGradientPolicy.


Member Data Documentation

ColumnVector* CContinuousTimeAndActionSigmoidVMGradientPolicy::actionValues [protected]
 
ColumnVector* CContinuousTimeAndActionSigmoidVMGradientPolicy::c [protected]
 
CStateCollectionImpl* CContinuousTimeAndActionSigmoidVMGradientPolicy::derivationState [protected]
 
Matrix* CContinuousTimeAndActionSigmoidVMGradientPolicy::derivationU [protected]
 
ColumnVector* CContinuousTimeAndActionSigmoidVMGradientPolicy::derivationX [protected]
 
CVFunctionInputDerivationCalculator* CContinuousTimeAndActionSigmoidVMGradientPolicy::dVFunction [protected]
 
CFeatureList* CContinuousTimeAndActionSigmoidVMGradientPolicy::gradient1 [protected]
 
CFeatureList* CContinuousTimeAndActionSigmoidVMGradientPolicy::gradient2 [protected]
 
CTransitionFunction* CContinuousTimeAndActionSigmoidVMGradientPolicy::model [protected]
 
CGradientVFunction* CContinuousTimeAndActionSigmoidVMGradientPolicy::vFunction [protected]
 

The documentation for this class was generated from the following file: