2021 • Conference Paper
Abstraction-based branch and bound approach to Q-learning for hybrid optimal control
Authors:
Legat, Benoît ,
Bouchat, Jean,
Jungers, Raphaël M.
Published in:
Proceedings of Machine Learning Research
Volume: 144 • Pages: 263-274
In this paper, we design a theoretical framework allowing to apply model predictive control on hybrid systems. For this, we develop a theory of approximate dynamic programming by leveraging the concept of alternating simulation. We show how to combine these notions in a branch and bound algorithm that can further refine the Q-functions using Lagrangian duality. We illustrate the approach on a numerical example.