Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published June 6, 2022 | Submitted + Published
Book Section - Chapter Open

Robustness and Consistency in Linear Quadratic Control with Untrusted Predictions

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. We propose a novel λ-confident controller and prove that it maintains a competitive ratio upper bound of 1 + min {O(λ²ε)+ O(1-λ)²,O(1)+O(λ²)} where λ∈ [0,1] is a trust parameter set based on the confidence in the predictions, and ε is the prediction error. Further, motivated by online learning methods, we design a self-tuning policy that adaptively learns the trust parameter λ with a competitive ratio that depends on ε and the variation of system perturbations and predictions. We show that its competitive ratio is bounded from above by 1+O(ε) /(Θ)(1)+Θ(ε))+O(μVar) where μVar measures the variation of perturbations and predictions. It implies that by automatically adjusting the trust parameter online, the self-tuning scheme ensures a competitive ratio that does not scale up with the prediction error ε.

Additional Information

© 2022 Copyright held by the owner/author(s). 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.

Attached Files

Published - 3489048.3522658.pdf

Submitted - 2106.09659.pdf

Files

2106.09659.pdf
Files (4.5 MB)
Name Size Download all
md5:166b6d58c05f0534a8f6f106253c740a
3.5 MB Preview Download
md5:ce12cb73ac37fcb39ed6fd358fd37a37
1.0 MB Preview Download

Additional details

Created:
August 20, 2023
Modified:
October 24, 2023