Safely Learning to Control the Constrained Linear Quadratic Regulator
Optimization and Control
2019-07-09 v2 Machine Learning
Machine Learning
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.
Keywords
Cite
@article{arxiv.1809.10121,
title = {Safely Learning to Control the Constrained Linear Quadratic Regulator},
author = {Sarah Dean and Stephen Tu and Nikolai Matni and Benjamin Recht},
journal= {arXiv preprint arXiv:1809.10121},
year = {2019}
}