Improving student's modeling framework in a tutorial-like system based on Pursuit learning automata and reinforcement learning

Abstract

Intelligent Tutorial Systems are educational software packages that occupy Artificial Intelligence (AI) techniques and methods to represent the knowledge, as well as to conduct the learning interaction. Tutorial-like systems simulates a Socratic model of learning for teaching uncertain course material by simulating the learning process for both Teacher and a School of Students. The Student is the center of attention in any Tutorial system. The proposed method in this paper improves the student's behavior model in a tutorial-Like system. In the proposed method, student model is determined by high level learning automata called Level Determinant Agent (LDA-LAQ), which attempts to characterize and improve the learning model of the students. LDA-LAQ actually use learning automata as a learning mechanism to show how the student is slow, normal or fast in the term of learning. This paper shows the new student how learning model increases speed accuracy using Pursuit learning automata and Reinforcement Learning.