Regret Analysis of Online LQR Control via Trajectory Prediction and Tracking: Extended Version

TL;DR

This paper introduces a novel online LQR control method that predicts optimal trajectories using previewed cost matrices, achieving bounded regret and improved performance over existing methods.

Contribution

The paper presents a new online LQR control approach utilizing trajectory prediction and tracking, with regret bounds that decay exponentially with preview window length.

Findings

Regret of the method is upper bounded by a constant.

Regret decays exponentially with the preview window length.

The method outperforms existing online LQR approaches in simulations.

Abstract

In this paper, we propose and analyze a new method for online linear quadratic regulator (LQR) control with a priori unknown time-varying cost matrices. The cost matrices are revealed sequentially with the potential for future values to be previewed over a short window. Our novel method involves using the available cost matrices to predict the optimal trajectory, and a tracking controller to drive the system towards it. We adopted the notion of dynamic regret to measure the performance of this proposed online LQR control method, with our main result being that the (dynamic) regret of our method is upper bounded by a constant. Moreover, the regret upper bound decays exponentially with the preview window length, and is extendable to systems with disturbances. We show in simulations that our proposed method offers improved performance compared to other previously proposed online LQR methods.