SARSAL.hpp

Go to the documentation of this file.

#ifndef AI_TOOLBOX_MDP_SARSAL_HEADER_FILE
#define AI_TOOLBOX_MDP_SARSAL_HEADER_FILE
 
#include <stddef.h>
 
#include <AIToolbox/MDP/Types.hpp>
#include <AIToolbox/MDP/TypeTraits.hpp>
#include <AIToolbox/MDP/Utils.hpp>
 
namespace AIToolbox::MDP {
    class SARSAL {
        public:
            using Trace = std::tuple<size_t, size_t, double>;
            using Traces = std::vector<Trace>;
            SARSAL(size_t S, size_t A, double discount = 1.0, double alpha = 0.1, double lambda = 0.9, double tolerance = 0.001);
 
            template <IsGenerativeModel M>
            SARSAL(const M& model, double alpha = 0.1, double lambda = 0.9, double tolerance = 0.001);
 
            void stepUpdateQ(size_t s, size_t a, size_t s1, size_t a1, double rew);
 
            void setLearningRate(double a);
 
            double getLearningRate() const;
 
            void setDiscount(double d);
 
            double getDiscount() const;
 
            void setLambda(double l);
 
            double getLambda() const;
 
            void setTolerance(double t);
 
            double getTolerance() const;
 
            void clearTraces();
 
            const Traces & getTraces() const;
 
            void setTraces(const Traces & t);
 
            size_t getS() const;
 
            size_t getA() const;
 
            const QFunction & getQFunction() const;
 
            void setQFunction(const QFunction & qfun);
 
        private:
            size_t S, A;
            double alpha_;
            double discount_;
            double lambda_, tolerance_;
            // This is used to avoid multiplying the discount and lambda all the time.
            double gammaL_;
 
            QFunction q_;
            Traces traces_;
    };
 
    template <IsGenerativeModel M>
    SARSAL::SARSAL(const M& model, const double alpha, const double lambda, const double tolerance) :
            SARSAL(model.getS(), model.getA(), model.getDiscount(), alpha, lambda, tolerance) {}
}
#endif