I am using my research on optimal teaching, active learning, artificial curiosity and a general perspective on social learning to develop Intelligent Tutoring Systems different pedagogical problems. This engine adaptively personalizes sequences of learning activities to maximize skills acquired for each individual student, taking into account limited time and motivational resources. At a given point in time, the system tries to propose to the student the activity which makes him progress best, hence the name of the approach: the “Right Activity at the Right Time” (RiARiT).

The system is based on the combination of three approaches. First, it leverages recent models of intrinsically motivated learning by transposing them to active teaching, relying of empirical estimation of learning progress provided by specific activities to particular students. Second, it uses state-of-the-art Multi-Arm Bandit (MAB) techniques to efficiently manage the exploration/exploitation challenge of this optimization process. Third, it leverages expert knowledge to constrain and bootstrap initial exploration of the MAB, while requiring only coarse guidance information of the expert and allowing the system to deal with didactic gaps in its knowledge. We have already evaluated the algorithm in user studies at several schools of Bordeaux (approximately 150 students from CE1).

Relevant Publications:

Multi-Armed Bandits for Intelligent Tutoring Systems, Manuel Lopes, Benjamin Clement, Didier Roy, Pierre-Yves Oudeyer. arXiv:1310.3174 [cs.AI], 2013. (pdf)

The Strategic Student Approach for Life-Long Exploration and Learning, Manuel Lopes and Pierre-Yves Oudeyer. IEEE - International Conference on Development and Learning (ICDL), 2012. (pdf)

Algorithmic and Human Teaching of Sequential Decision Tasks, Maya Cakmak and Manuel Lopes. AAAI Conference on Artificial Intelligence (AAAI), Toronto, Canada, 2012. (pdf)