Efficiently learning teaching strategies that remain effective for different learner categories while becoming efficient over time

We propose a machine learning framework for an adaptive and self-improving tutoring system that performs efficient and effective teaching strategies, and learns these strategies efficiently while interacting on-line with students belonging to specific learning categories. Categories that may be learned via a conceptual clustering algorithm serves as background knowledge for the reinforcement learning tutor agent to learn efficient teaching strategies (i.e., a sequence of teaching activities) whose number decreases asymptotically over time without sacrificing effectiveness.