Online Learning for Supervisory Switching Control
IEEE Control Systems Letters · 2026 · 10 · 1015-1020
DOI: 10.1109/lcsys.2026.3704454 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Control Systems Letters, 2026. Verfasst von Haoyuan Sun und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 23 Literaturangaben. Gefördert von: Office of Naval Research, Air Force Office of Scientific Research (AFOSR) Multidisciplinary University Research Initiative.
Abstract (Originalsprache)
We study supervisory switching control for partially-observed linear dynamical systems. The objective is to identify and deploy a suitable controller for the unknown system by periodically selecting among a collection of N candidate controllers, some of which may destabilize the underlying system. While classical estimator-based supervisory control guarantees asymptotic stability, it lacks quantitative finite-time performance bounds. Conversely, current non-asymptotic methods in both online learning and system identification require restrictive assumptions that are incompatible in a control setting, such as system stability, which preclude testing potentially unstable controllers. To bridge this gap, we propose a novel, non-asymptotic analysis of supervisory control that adapts multi-armed bandit algorithms to a control-theoretic setting. The proposed data-driven algorithm evaluates candidate controllers via scoring criteria that leverage system observability to isolate the effects of state history, enabling both detection of destabilizing controllers and accurate system identification. We present two algorithmic variants with dimension-free, finite-time guarantees, where each identifies the matching controller in $\text {O}(\text {N}~\log ^{{2}}~\text {N})$ steps, while simultaneously achieving finite $\text {L}_{{2}}$ -gain with respect to system disturbances.
Förderung
- Office of Naval Research
- Air Force Office of Scientific Research (AFOSR) Multidisciplinary University Research Initiative
Zitieren
APA
Sun, H., & Jadbabaie, A. (2026). Online Learning for Supervisory Switching Control. IEEE Control Systems Letters, 10, 1015-1020. https://doi.org/10.1109/lcsys.2026.3704454
Vancouver
Sun H, Jadbabaie A. Online Learning for Supervisory Switching Control. IEEE Control Systems Letters. 2026;10:1015-1020. doi:10.1109/lcsys.2026.3704454
BibTeX
@article{Sun2026,
author = {Sun, Haoyuan and Jadbabaie, Ali},
title = {Online Learning for Supervisory Switching Control},
journal = {IEEE Control Systems Letters},
year = {2026},
volume = {10},
pages = {1015--1020},
doi = {10.1109/lcsys.2026.3704454}
}
EUVIMED