CaltechAUTHORS
  A Caltech Library Service

Robustness and Consistency in Linear Quadratic Control with Untrusted Predictions

Li, Tongxin and Yang, Ruixiao and Qu, Guannan and Shi, Guanya and Yu, Chenkai and Wierman, Adam and Low, Steven (2022) Robustness and Consistency in Linear Quadratic Control with Untrusted Predictions. Proceedings of the ACM on Measurement and Analysis of Computing System, 6 (1). Art. No. 18. ISSN 2476-1249. doi:10.1145/3508038. https://resolver.caltech.edu/CaltechAUTHORS:20210716-225846876

[img] PDF - Published Version
See Usage Policy.

3MB
[img] PDF (24 Feb 2022) - Submitted Version
Creative Commons Attribution.

3MB

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20210716-225846876

Abstract

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.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1145/3508038DOIArticle
https://arxiv.org/abs/2106.09659arXivDiscussion Paper
https://resolver.caltech.edu/CaltechAUTHORS:20220802-839213000Related ItemConference Abstract Paper
ORCID:
AuthorORCID
Li, Tongxin0000-0002-9806-8964
Qu, Guannan0000-0002-5466-3550
Shi, Guanya0000-0002-9075-3705
Yu, Chenkai0000-0001-8683-7773
Wierman, Adam0000-0002-5923-0199
Low, Steven0000-0001-6476-3048
Alternate Title:Robustness and Consistency in Linear Quadratic Control with Predictions
Additional Information:© 2022 held by the owner/author(s). Received October 2021; revised December 2021; accepted January 2022. This work is supported by the National Science Foundation, under grants ECCS1931662, CCF 1637598, ECCS 1619352, CPS 1739355, AitF-1637598, CNS-1518941, PIMCO and Amazon Web Services. Tongxin Li and Ruixiao Yang contributed equally to the paper.
Funders:
Funding AgencyGrant Number
NSFECCS-1931662
NSFCCF-1637598
NSFECCS-1619352
NSFECCS-1739355
NSFCCF-1637598
NSFCNS-1518941
PIMCOUNSPECIFIED
Amazon Web ServicesUNSPECIFIED
Subject Keywords:online control; model predictive control; online learning; competitive analysis
Issue or Number:1
Classification Code:CCS Concepts: Theory of computation→Online learning algorithms; Regret bounds
DOI:10.1145/3508038
Record Number:CaltechAUTHORS:20210716-225846876
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20210716-225846876
Official Citation:Tongxin Li, Ruixiao Yang, Guannan Qu, Guanya Shi, Chenkai Yu, Adam Wierman, and Steven Low. 2022. Robustness and Consistency in Linear Quadratic Control with Untrusted Predictions. Proc. ACM Meas. Anal. Comput. Syst. 6, 1, Article 18 (March 2022), 35 pages. https://doi.org/10.1145/3508038
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:109906
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:16 Jul 2021 23:23
Last Modified:02 Aug 2022 23:25

Repository Staff Only: item control page