pith. sign in

arxiv: 2006.11022 · v2 · pith:4E5NOEI5new · submitted 2020-06-19 · 📡 eess.SY · cs.LG· cs.RO· cs.SY

Learning Stabilizing Controllers for Unstable Linear Quadratic Regulators from a Single Trajectory

classification 📡 eess.SY cs.LGcs.ROcs.SY
keywords controllerstabilizinglinearquadraticsystemscontrollersdifferentexploration
0
0 comments X
read the original abstract

The principal task to control dynamical systems is to ensure their stability. When the system is unknown, robust approaches are promising since they aim to stabilize a large set of plausible systems simultaneously. We study linear controllers under quadratic costs model also known as linear quadratic regulators (LQR). We present two different semi-definite programs (SDP) which results in a controller that stabilizes all systems within an ellipsoid uncertainty set. We further show that the feasibility conditions of the proposed SDPs are \emph{equivalent}. Using the derived robust controller syntheses, we propose an efficient data dependent algorithm -- \textsc{eXploration} -- that with high probability quickly identifies a stabilizing controller. Our approach can be used to initialize existing algorithms that require a stabilizing controller as an input while adding constant to the regret. We further propose different heuristics which empirically reduce the number of steps taken by \textsc{eXploration} and reduce the suffered cost while searching for a stabilizing controller.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.