Modeling the Student with Reinforcement Learning

We describe a methodology for enabling an intelligent teaching system to m ake high level strategy decisions on the basis of low level student modeling information. Thi s framework is less costly to construct, and superior to hand coding teaching strategies as it is more responsive t o the learner’s needs. In order to accomplish this, reinforcement learning is used to learn to associate superio r teaching actions with certain states of the student’s knowledge. Reinforcement learning (RL) has been sho w to be flexible in handling noisy data, and does not need expert domain knowledge. A drawback of RL is th at t often needs a significant number of trials for learning. We propose an off-line learning method ol gy using sample data, simulated students, and small amounts of expert knowledge to bypass this probl em.