Safely Learning to Control the Constrained Linear Quadratic Regulator

Author name not available (Why is that?)

Publication date: 26 September 2018

Abstract: We study the constrained linear quadratic regulator with unknown dynamics, addressing the tension between safety and exploration in data-driven control techniques. We present a framework which allows for system identification through persistent excitation, while maintaining safety by guaranteeing the satisfaction of state and input constraints. This framework involves a novel method for synthesizing robust constraint-satisfying feedback controllers, leveraging newly developed tools from system level synthesis. We connect statistical results with cost sub-optimality bounds to give non-asymptotic guarantees on both estimation and controller performance.

Has companion code repository: https://github.com/monimoyb/RMPC_MixedUncertainty

This page was built for publication: Safely Learning to Control the Constrained Linear Quadratic Regulator

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6307339)