Skip to yearly menu bar Skip to main content


Poster

Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator

Sarah Dean · Horia Mania · Nikolai Matni · Benjamin Recht · Stephen Tu

Room 210 #81

Keywords: [ Learning Theory ] [ Online Learning ] [ Control Theory ]


Abstract:

We consider adaptive control of the Linear Quadratic Regulator (LQR), where an unknown linear system is controlled subject to quadratic costs. Leveraging recent developments in the estimation of linear systems and in robust controller synthesis, we present the first provably polynomial time algorithm that achieves sub-linear regret on this problem. We further study the interplay between regret minimization and parameter estimation by proving a lower bound on the expected regret in terms of the exploration schedule used by any algorithm. Finally, we conduct a numerical study comparing our robust adaptive algorithm to other methods from the adaptive LQR literature, and demonstrate the flexibility of our proposed method by extending it to a demand forecasting problem subject to state constraints.

Live content is unavailable. Log in and register to view live content