WoLFPolicy.hpp

Go to the documentation of this file.

#ifndef AI_TOOLBOX_MDP_WOLF_POLICY_HEADER_FILE
#define AI_TOOLBOX_MDP_WOLF_POLICY_HEADER_FILE
 
#include <vector>
 
#include <AIToolbox/MDP/Policies/QPolicyInterface.hpp>
#include <AIToolbox/MDP/Policies/PolicyWrapper.hpp>
 
namespace AIToolbox::MDP {
    class WoLFPolicy : public QPolicyInterface {
        public:
            WoLFPolicy(const QFunction & q, double deltaw = 0.0125, double deltal = 0.05, double scaling = 5000.0);
 
            void stepUpdateP(size_t s);
 
            virtual size_t sampleAction(const size_t & s) const override;
 
            virtual double getActionProbability(const size_t & s, const size_t & a) const override;
 
            virtual Matrix2D getPolicy() const override;
 
            void setDeltaW(double deltaW);
 
            double getDeltaW() const;
 
            void setDeltaL(double deltaL);
 
            double getDeltaL() const;
 
            void setScaling(double scaling);
 
            double getScaling() const;
 
        private:
            double deltaW_, deltaL_, scaling_;
 
            std::vector<unsigned> c_;
            PolicyWrapper::PolicyMatrix avgPolicyMatrix_, actualPolicyMatrix_;
            PolicyWrapper avgPolicy_, actualPolicy_;
    };
}
 
#endif