Active Learning Strategy for Role-playing Game Modeled by Markov Decision Processes

Abstract

In previous research a role-playing game(RPG) is represented with Markov decision processes(MDP). But active learning method for RPG has not been studied yet. In this research we propose an active learning method which maximizes an expected total reward with respect to a Bayes criterion under the condition that the true parameter of MDP is unknown. We recognize the effectiveness of our proposed method by some simulations.