Online Control with Adversarial Disturbance for Continuous-Time Linear Systems

Abstract

We study online control for continuous-time linear systems with finite sampling rates, where the objective is to design an online procedure that learns under non-stochastic noise and performs comparably to a fixed optimal linear controller. We present a novel two-level online algorithm, by integrating a higher-level learning strategy and a lower-level feedback control strategy. This method offers a practical and robust solution for online control, which achieves sublinear regret. Our work provides one of the first nonasymptotic results for controlling continuous-time linear systems a with finite number of interactions with the system.

Cite

Text

Li et al. "Online Control with Adversarial Disturbance for Continuous-Time Linear Systems." ICML 2023 Workshops: Frontiers4LCD, 2023.

Markdown

[Li et al. "Online Control with Adversarial Disturbance for Continuous-Time Linear Systems." ICML 2023 Workshops: Frontiers4LCD, 2023.](https://mlanthology.org/icmlw/2023/li2023icmlw-online/)

BibTeX

@inproceedings{li2023icmlw-online,
  title     = {{Online Control with Adversarial Disturbance for Continuous-Time Linear Systems}},
  author    = {Li, Jingwei and Dong, Jing and Wang, Baoxiang and Zhang, Jingzhao},
  booktitle = {ICML 2023 Workshops: Frontiers4LCD},
  year      = {2023},
  url       = {https://mlanthology.org/icmlw/2023/li2023icmlw-online/}
}