Towards Student Behaviour Simulation: A Decision Transformer Based Approach

Zhaoxing Li, Lei Shi, Yunzhan Zhou, Jindi Wang

Abstract: With the rapid development of Artificial Intelligence (AI), an increasing number of Machine Learning (ML) technologies have been widely applied in many aspects of life. In the field of education, Intelligence Tutoring Systems (ITS) have also made significant advancements using these technologies. Developing different teaching strategies automatically, according to mined student characteristics and learning styles, could significantly enhance students’ learning efficiency and performance. This requires the ITS to recommend different learning strategies and trajectories for different individual students. However, one of the greatest challenges is the scarcity of data sets providing interactions between students and ITS, for training such ITS. One promising solution to this challenge is to train “sim students”, which imitate real students’ behaviour while using the ITS. The simulated interactions between these sim students and the ITS can then be generated and used to train the ITS to provide personalised learning strategies and trajectories to real students. In this paper, we thus propose SimStu, built upon a Decision Transformer, to generate learning behavioural data to improve the performance of the trained ITS models. The experimental results suggest that our SimStu could model real students well in terms of action frequency distribution. Moreover, we evaluate SimStu in an emerging ITS technology, Knowledge Tracing. The results indicate that SimStu could improve the efficiency of ITS training.