Safely Learning to Control the Constrained Linear Quadratic Regulator
2019 American Control Conference (ACC)(2019)
摘要
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.
更多查看译文
关键词
constrained linear quadratic regulator,unknown dynamics,data-driven control techniques,system identification,robust constraint-satisfying feedback controllers,safely learning,state input constraints,cost sub-optimality bounds,system level synthesis
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络