Résumé: Learning, planning, and representing knowledge at multiple levels of temporal abstraction are key, longstanding challenges in AI. The ways how to address these challenges within the mathematical framework of reinforcement learning and Markov decision processes (MDP) are discussed. A set options defined over an MDP constitutes a semi-MDP (SMDP), and the theory of SMDPs provides the foundation for the theory of options.

Langue: Anglais