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 July 7, 2020 | Accepted Version
Report Open

The Power of Predictions in Online Control


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.

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.

Attached Files

Accepted Version - 2006.07569.pdf


Files (586.6 kB)
Name Size Download all
586.6 kB Preview Download

Additional details

August 19, 2023
August 19, 2023