Proposal model for e-learning based on Case Based Reasoning and Reinforcement Learning

Abstract

This paper presents a proposal model for implementing personalized e-learning. The proposal model considers the level of skills or knowledge that a student has on a particular subject; this is determined through a pretest; this aspect is very important to avoid problems as anxiety or boredom according flow theory. In addition, in an e-learning system to determine the optimal sequence of learning resources for a student, we will work in a complementary manner with two machine-learning techniques: Case Based Reasoning and Reinforcement Learning (Q-Learning). The Case Based Reasoning, will allow based on previous success cases, determine the sequence of learning resources most appropriate for the student; and if there are not very similar cases, a learning sequence will be chosen from the proposed ones by Reinforcement Learning (Q-Learning).