Abstraction-Based Branch and Bound Approach to Q-Learning for Hybrid Optimal Control

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.

Cite

Text

Legat et al. "Abstraction-Based Branch and Bound Approach to Q-Learning for Hybrid Optimal Control." Proceedings of the 3rd Conference on Learning for Dynamics and Control, 2021.

Markdown

[Legat et al. "Abstraction-Based Branch and Bound Approach to Q-Learning for Hybrid Optimal Control." Proceedings of the 3rd Conference on Learning for Dynamics and Control, 2021.](https://mlanthology.org/l4dc/2021/legat2021l4dc-abstractionbased/)

BibTeX

@inproceedings{legat2021l4dc-abstractionbased,
  title     = {{Abstraction-Based Branch and Bound Approach to Q-Learning for Hybrid Optimal Control}},
  author    = {Legat, Benoît and Jungers, Raphaël M. and Bouchat, Jean},
  booktitle = {Proceedings of the 3rd Conference on Learning for Dynamics and Control},
  year      = {2021},
  pages     = {263-274},
  volume    = {144},
  url       = {https://mlanthology.org/l4dc/2021/legat2021l4dc-abstractionbased/}
}