Les systèmes de classeurs : Un état de l'art

Learning Classifier Systems (LCSs) are rule-based systems that automatically build their ruleset. initially LCSs were dedicated to the modelling of the emergence of cognitive abilities thanks to adaptive mechanisms, particularly evolutionary processes. After a renewal of the field more focused on learning, LCSs have been reconsidered as sequential decision problem solving systems endowed with a generalization property. Finally, much more recently, LCSs have proved very efficient at solving classification tasks, which boosted the field. In this context, the aim of this contribution is to present the state-of-the-art of LCSs, insisting on recent developments, and focusing more on the sequential decision domain than on automatic classification.