Abstract : We present an approach to Intelligent Tutoring Systems which adaptively personalizes sequences of learning activities to maximize skills acquired by each 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. We introduce two algorithms that rely on the empirical estimation of the learning progress, one that uses information about the difficulty of each exercise RiARiT and another that does not use any knowledge about the problem ZPDES.
Type de document :
Communication dans un congrès
7th International Conference on Educational Data Mining, 2014, London, United Kingdom. 2014
https://hal.inria.fr/hal-01016428
Contributeur : Manuel Lopes
<>
Soumis le : lundi 30 juin 2014 - 11:31:51
Dernière modification le : lundi 17 décembre 2018 - 10:32:47
Document(s) archivé(s) le : mardi 30 septembre 2014 - 15:16:02
Benjamin Clement, Didier Roy, Pierre-Yves Oudeyer, Manuel Lopes. Online Optimization of Teaching Sequences with Multi-Armed Bandits. 7th International Conference on Educational Data Mining, 2014, London, United Kingdom. 2014. 〈hal-01016428〉
