CooperativeExperience.hpp

Go to the documentation of this file.

#ifndef AI_TOOLBOX_FACTORED_MDP_COOPERATIVE_EXPERIENCE_HEADER_FILE
#define AI_TOOLBOX_FACTORED_MDP_COOPERATIVE_EXPERIENCE_HEADER_FILE
 
#include <AIToolbox/Factored/MDP/Types.hpp>
#include <AIToolbox/Factored/Utils/BayesianNetwork.hpp>
 
namespace AIToolbox::Factored::MDP {
    class CooperativeExperience {
        public:
            using RewardMatrix = std::vector<Vector>;
            using VisitsTable = std::vector<Table2D>;
 
            // Used to avoid recomputation when doing sync in RL.
            using Indeces = std::vector<size_t>;
 
            CooperativeExperience(const DDNGraph & graph);
 
            const Indeces & record(const State & s, const Action & a, const State & s1, const Rewards & rew);
 
            void reset();
 
            unsigned long getTimesteps() const;
 
            const VisitsTable & getVisitsTable() const;
 
            const RewardMatrix & getRewardMatrix() const;
 
            const RewardMatrix & getM2Matrix() const;
 
            const State & getS() const;
 
            const Action & getA() const;
 
            const DDNGraph & getGraph() const;
 
        private:
            const DDNGraph & graph_;
 
            VisitsTable visits_;
            RewardMatrix rewards_;
            RewardMatrix M2s_;
            Indeces indeces_;
 
            unsigned long timesteps_;
    };
}
 
#endif