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 CVarioEta Class Reference Vario Eta Learning Rate Calculator. More... #include <cgradientfunction.h> Inheritance diagram for CVarioEta: List of all members. Public Member Functions   CVarioEta (unsigned int numParams, double eta, double beta=0.01, double epsilon=0.0001)   ~CVarioEta () virtual void  getWeightUpdates (CFeatureList *updates)   Multiply the update gradient list with the learning rates. Protected Attributes double *  eta_i double *  v_i unsigned int  numParams Detailed Description Vario Eta Learning Rate Calculator. Calculates the learning rate according to the weights standard deviation. Used by Coulum, more theoretical use to find out good fixed learning rates for a given function approximator. Parameters of CVarioEta: "VarioEtaLearningRate" : Base Learning Rate "VarioEtaBeta" : Update factor "VarioEtaEpsilon" : For a more detailed description of the parameters see [Coulom, 1] Constructor & Destructor Documentation CVarioEta::CVarioEta (  unsigned int  numParams, double  eta, double  beta = 0.01, double  epsilon = 0.0001 )  CVarioEta::~CVarioEta (   )  Member Function Documentation virtual void CVarioEta::getWeightUpdates (  CFeatureList *  updates  )  [virtual]   Multiply the update gradient list with the learning rates. Implements CAdaptiveEtaCalculator. Member Data Documentation double* CVarioEta::eta_i [protected] unsigned int CVarioEta::numParams [protected] double* CVarioEta::v_i [protected] The documentation for this class was generated from the following file: cgradientfunction.h