Finite Time Adaptive Stabilization of LQ Systems
This addresses a canonical problem in adaptive control for systems where unknown parameters can cause destabilization, offering a non-asymptotic solution that is more practical than existing approaches.
The paper tackles the problem of stabilizing linear systems with unknown dynamics in finite time, achieving high probability guarantees for stabilization using random linear feedbacks under minimal assumptions.
Stabilization of linear systems with unknown dynamics is a canonical problem in adaptive control. Since the lack of knowledge of system parameters can cause it to become destabilized, an adaptive stabilization procedure is needed prior to regulation. Therefore, the adaptive stabilization needs to be completed in finite time. In order to achieve this goal, asymptotic approaches are not very helpful. There are only a few existing non-asymptotic results and a full treatment of the problem is not currently available. In this work, leveraging the novel method of random linear feedbacks, we establish high probability guarantees for finite time stabilization. Our results hold for remarkably general settings because we carefully choose a minimal set of assumptions. These include stabilizability of the underlying system and restricting the degree of heaviness of the noise distribution. To derive our results, we also introduce a number of new concepts and technical tools to address regularity and instability of the closed-loop matrix.