Intelligent tutoring systems using reinforcement learning to teach autistic students

Abstract

Many Intelligent Tutoring Systems have been developed using different Artificial Intelligence techniques. In this paper we propose to use Reinforcement Learning for building an intelligent tutoring system to teach autistic students, who can't communicate well with others. In reinforcement learning, a policy is updated for taking appropriate action to teach the student. The main advantage of using reinforcement learning is that, it eliminates the need for encoding pedagogical rules. Various issues in using reinforcement learning for intelligent tutoring systems are discussed in this paper. © 2007 International Federation for Information Processing.