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.
- Yasin Abbasi-Yadkori and Csaba Szepesvári. Regret bounds for the adaptive control of linear quadratic systems. In Proceedings of the 24th Annual Conference on Learning Theory, pages 1--26. JMLR Workshop and Conference Proceedings, 2011.Google Scholar
- Naman Agarwal, Brian Bullins, Elad Hazan, Sham Kakade, and Karan Singh. Online control with adversarial disturbances. In International Conference on Machine Learning, pages 111--119. PMLR, 2019.Google Scholar
- Brian DO Anderson and John B Moore. Optimal filtering. Courier Corporation, 2012.Google Scholar
- Spyros Angelopoulos, Christoph Dürr, Shendan Jin, Shahin Kamali, and Marc Renault. Online computation with untrusted advice. arXiv preprint arXiv:1905.05655, 2019.Google Scholar
- Antonios Antoniadis, Christian Coester, Marek Elias, Adam Polak, and Bertrand Simon. Online metric algorithms with untrusted predictions. In International Conference on Machine Learning, pages 345--355. PMLR, 2020.Google Scholar
- Antonios Antoniadis, Themis Gouleakis, Pieter Kleer, and Pavel Kolev. Secretary and online matching problems with machine learned advice. arXiv preprint arXiv:2006.01026, 2020.Google Scholar
- Etienne Bamas, Andreas Maggiori, and Ola Svensson. The primal-dual method for learning augmented algorithms. arXiv preprint arXiv:2010.11632, 2020.Google Scholar
- Alberto Bemporad and Manfred Morari. Robust model predictive control: A survey. In Robustness in identification and control, pages 207--226. Springer, 1999.Google Scholar
Cross Ref
- Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, and Wojciech Zaremba. Openai gym. arXiv preprint arXiv:1606.01540, 2016.Google Scholar
- Alon Cohen, Avinatan Hasidim, Tomer Koren, Nevena Lazic, Yishay Mansour, and Kunal Talwar. Online linear quadratic control. In International Conference on Machine Learning, pages 1029--1038. PMLR, 2018.Google Scholar
- Sarah Dean, Horia Mania, Nikolai Matni, Benjamin Recht, and Stephen Tu. On the sample complexity of the linear quadratic regulator. Foundations of Computational Mathematics, pages 1--47, 2019.Google Scholar
- John Doyle, Keith Glover, Pramod Khargonekar, and Bruce Francis. State-space solutions to standard $h_2$ and $h_infty$ control problems. In 1988 American Control Conference, pages 1691--1696. IEEE, 1988.Google Scholar
Cross Ref
- Geir E Dullerud and Fernando Paganini. A course in robust control theory: a convex approach, volume 36. Springer Science & Business Media, 2013.Google Scholar
- James Hannan. 4. approximation to rayes risk in repeated play. In Contributions to the Theory of Games (AM-39), Volume III, pages 97--140. Princeton University Press, 2016.Google Scholar
- Adam Kalai and Santosh Vempala. Efficient algorithms for online decision problems. Journal of Computer and System Sciences, 71(3):291--307, 2005.Google Scholar
Digital Library
- Islam SM Khalil. Robust and optimal control.Google Scholar
- Zachary J Lee, Tongxin Li, and Steven H Low. Acn-data: Analysis and applications of an open ev charging dataset. In Proceedings of the Tenth ACM International Conference on Future Energy Systems, pages 139--149, 2019.Google Scholar
Digital Library
- Tongxin Li, Yue Chen, Bo Sun, Adam Wierman, and Steven H Low. Information aggregation for constrained online control. Proceedings of the ACM on Measurement and Analysis of Computing Systems, 5(2):1--35, 2021.Google Scholar
Digital Library
- Yingying Li, Xin Chen, and Na Li. Online optimal control with linear dynamics and predictions: algorithms and regret analysis. In NeurIPS, pages 14858--14870, 2019.Google Scholar
- Thodoris Lykouris and Sergei Vassilvtiskii. Competitive caching with machine learned advice. In International Conference on Machine Learning, pages 3296--3305. PMLR, 2018.Google Scholar
- Brendan McMahan. Follow-the-regularized-leader and mirror descent: Equivalence theorems and l1 regularization. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pages 525--533. JMLR Workshop and Conference Proceedings, 2011.Google Scholar
- Manish Purohit, Zoya Svitkina, and Ravi Kumar. Improving online algorithms via ml predictions. In Advances in Neural Information Processing Systems, pages 9661--9670, 2018.Google Scholar
- Shai Shalev-Shwartz et al. Online learning and online convex optimization. Foundations and trends in Machine Learning, 4(2):107--194, 2011.Google Scholar
Digital Library
- Guanya Shi, Yiheng Lin, Soon-Jo Chung, Yisong Yue, and Adam Wierman. Online optimization with memory and competitive control. In Advances in Neural Information Processing Systems, volume 33, pages 20636--20647. Curran Associates, Inc., 2020.Google Scholar
- Max Simchowitz and Dylan Foster. Naive exploration is optimal for online lqr. In International Conference on Machine Learning, pages 8937--8948. PMLR, 2020.Google Scholar
- Jean-Jacques E Slotine, Weiping Li, et al. Applied nonlinear control, volume 199. Prentice hall Englewood Cliffs, NJ, 1991.Google Scholar
- Alexander Wei and Fred Zhang. Optimal robustness-consistency trade-offs for learning-augmented online algorithms. arXiv preprint arXiv:2010.11443, 2020.Google Scholar
- Chenkai Yu, Guanya Shi, Soon-Jo Chung, Yisong Yue, and Adam Wierman. Competitive control with delayed imperfect information. arXiv preprint arXiv:2010.11637, 2020.Google Scholar
- Chenkai Yu, Guanya Shi, Soon-Jo Chung, Yisong Yue, and Adam Wierman. The power of predictions in online control. Advances in Neural Information Processing Systems, 33, 2020.Google Scholar
- Runyu Zhang, Yingying Li, and Na Li. On the regret analysis of online lqr control with predictions. arXiv preprint arXiv:2102.01309, 2021.Google Scholar
- Kemin Zhou, John Comstock Doyle, Keith Glover, et al. Robust and optimal control, volume 40.Google Scholar
Index Terms
Robustness and Consistency in Linear Quadratic Control with Untrusted Predictions
Recommendations
Robustness and Consistency in Linear Quadratic Control with Untrusted Predictions
SIGMETRICS '22We 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 ...
Robustness and Consistency in Linear Quadratic Control with Untrusted Predictions
SIGMETRICS/PERFORMANCE '22: Abstract Proceedings of the 2022 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer SystemsWe 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 ...
Enhancing the robustness of the EPSAC predictive control using a Singular Value Decomposition approach
In this paper, we present a Robust Model Predictive Control (MPC) based on the Singular Value Decomposition (SVD) analysis to handle long prediction and control horizons where numerical instability might appear. The proposed method is developed ...






Comments