A Caltech Library Service

The Power of Predictions in Online Control

Yu, Chenkai and Shi, Guanya and Chung, Soon-Jo and Yue, Yisong and Wierman, Adam (2020) The Power of Predictions in Online Control. . (Unpublished)

[img] PDF - Accepted Version
See Usage Policy.


Use this Persistent URL to link to this item:


We study the impact of predictions in online Linear Quadratic Regulator control with both stochastic and adversarial disturbances in the dynamics. In both settings, we characterize the optimal policy and derive tight bounds on the minimum cost and dynamic regret. Perhaps surprisingly, our analysis shows that the conventional greedy MPC approach is a near-optimal policy in both stochastic and adversarial settings. Specifically, for length-T problems, MPC requires only O(logT) predictions to reach O(1) dynamic regret, which matches (up to lower-order terms) our lower bound on the required prediction horizon for constant regret.

Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription Paper ItemConference Paper
Yu, Chenkai0000-0001-8683-7773
Shi, Guanya0000-0002-9075-3705
Chung, Soon-Jo0000-0002-6657-3907
Yue, Yisong0000-0001-9127-1989
Wierman, Adam0000-0002-5923-0199
Additional Information:This project was supported in part by funding from Raytheon, DARPA PAI, AitF-1637598 and CNS-1518941, with additional support for Guanya Shi provided by the Simoudis Discovery Prize. We see no ethical concerns related to the results in this paper.
Funding AgencyGrant Number
Raytheon CompanyUNSPECIFIED
Defense Advanced Research Projects Agency (DARPA)UNSPECIFIED
Simoudis Discovery PrizeUNSPECIFIED
Record Number:CaltechAUTHORS:20200707-094715120
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:104236
Deposited By: Tony Diaz
Deposited On:07 Jul 2020 17:16
Last Modified:22 Dec 2022 18:53

Repository Staff Only: item control page