Machine learning and control engineering: The model-free case

Michel Fliess (1, 2) , Cédric Join (3, 2)

1 LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau]
2 AL.I.E.N. - ALgèbre pour Identification & Estimation Numériques
3 CRAN - Centre de Recherche en Automatique de Nancy

This paper states that Model-Free Control (MFC), which must not be confused with Model-Free Reinforcement Learning, is a new tool for Machine Learning (ML). MFC is easy to implement and should be substituted in control engineering to ML via Artificial Neural Networks and/or Reinforcement Learning. A laboratory experiment, which was already investigated via today's ML techniques, is reported in order to confirm this viewpoint.

Mots clés: half-quadrotor; artificial neural networks; unsupervised learning; supervised learning; model-free control; intelligent proportional controllers; machine learning; reinforcement learning; Model-free control

Domaines: Intelligence artificielle [cs.AI]; Apprentissage [cs.LG]; Automatique; Automatique / Robotique; Systèmes et contrôle [cs.SY]; Optimisation et contrôle [math.OC]

Michel Fliess, Cédric Join. Machine learning and control engineering: The model-free case. Future Technologies Conference, FTC 2020, Nov 2020, Vancouver, Canada. pp. 258-278, ⟨10.1007/978-3-030-63128-4_20⟩. ⟨hal-02851119v2⟩