Robustness and Consistency in Linear Quadratic Control with Untrusted Predictions

Robustness and Consistency in Linear Quadratic Control with Untrusted Predictions

We study the problem of learning-augmented predictive linear quadratic control. Our goal is to design a controller that balances consistency, which measures the competitive ratio when predictions are accurate, and robustness, which bounds the competitive ratio when predictions are inaccurate.

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings of the ACM on measurement and analysis of computing systems 2022-03, Vol.6 (1), p.1-35, Article 18
Hauptverfasser: Li, Tongxin, Yang, Ruixiao, Qu, Guannan, Shi, Guanya, Yu, Chenkai, Wierman, Adam, Low, Steven
Format: Artikel
Sprache:eng
Schlagworte:
Design and analysis of algorithms
Machine learning theory
Online algorithms
Online learning algorithms
Regret bounds
Theory and algorithms for application domains
Theory of computation
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We study the problem of learning-augmented predictive linear quadratic control. Our goal is to design a controller that balances consistency, which measures the competitive ratio when predictions are accurate, and robustness, which bounds the competitive ratio when predictions are inaccurate.
ISSN:2476-1249
2476-1249
DOI:10.1145/3508038