Title: Regret Analysis of Online LQR Control via Trajectory Prediction and Tracking
Time, Date, Location: 11:00, Friday, 3 February, 2022, Brian Anderson Building Seminar Room
Abstract: In this paper, we propose and analyse 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 future values to be previewed over a short window. Our novel method involves using the available cost matrices to predict the optimal trajectory along with a tracking controller to drive the system towards it which is less “pessimistic” than other existing methods. 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.