Abstraction-based branch and bound approach to Q-learning for hybrid optimal control

Legat, Benoît;Bouchat, Jean;Jungers, Raphaël
(2021) 3rd Annual Learning for Dynamics & Control Conference — Location: ETH Zurich (7.June.2021)

Files

201111029.pdf
  • Open Access
  • Adobe PDF
  • 202.87 KB
Download

Details

Authors
Abstract
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.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Legat, B., Bouchat, J., & Jungers, R. (2021). Abstraction-based branch and bound approach to Q-learning for hybrid optimal control. Published. 3rd Annual Learning for Dynamics & Control Conference, ETH Zurich. https://hdl.handle.net/2078.5/252416