Regret-Optimal Control for Finite-State Systems
IEEE Control Systems Letters · 2026 · 10 · 1627-1632
DOI: 10.1109/lcsys.2026.3708577 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Control Systems Letters, 2026. Verfasst von Yishay Polatov und 1 weiteren Autor:innen. Die Arbeit nennt 21 Literaturangaben. Gefördert von: Israel Science Foundation.
Abstract (Originalsprache)
We study the control of finite-state systems driven by exogenous disturbances, and design causal policies that track the performance of a lookahead benchmark controller. This objective is formalized through dynamic regret, so that favorable disturbance sequences are compared against a strong benchmark, while under adverse disturbance sequences the comparison accounts for the benchmark’s degraded performance. This benchmark-relative framework provides an alternative to classical MDP formulations, which assume i.i.d. disturbances, and to robust control approaches, which optimize against worst-case disturbances. Our main result is a nested dynamic-programming solution that computes both the optimal worst-case regret and a regret-optimal policy. In particular, we introduce the Regret-Bellman operator, whose fixed-point value function feeds into a finite-horizon dynamic program. Numerical examples show that regret-optimal policies interpolate nicely between MDP-based and robust controllers without requiring knowledge of the disturbance distribution, and can even outperform both under i.i.d. or structured disturbances.
Förderung
- Israel Science Foundation
Zitieren
APA
Polatov, Y., & Sabag, O. (2026). Regret-Optimal Control for Finite-State Systems. IEEE Control Systems Letters, 10, 1627-1632. https://doi.org/10.1109/lcsys.2026.3708577
Vancouver
Polatov Y, Sabag O. Regret-Optimal Control for Finite-State Systems. IEEE Control Systems Letters. 2026;10:1627-1632. doi:10.1109/lcsys.2026.3708577
BibTeX
@article{Polatov2026,
author = {Polatov, Yishay and Sabag, Oron},
title = {Regret-Optimal Control for Finite-State Systems},
journal = {IEEE Control Systems Letters},
year = {2026},
volume = {10},
pages = {1627--1632},
doi = {10.1109/lcsys.2026.3708577}
}
EUVIMED