Online Actuator Selection and Controller Design for Linear Quadratic Regulation with Unknown System Model

TL;DR

This paper introduces online algorithms for actuator selection and controller design in linear quadratic regulation with unknown models, achieving sublinear regret bounds in both episodic and non-episodic settings.

Contribution

It presents a novel combined approach using multiarmed bandits and certainty equivalence for simultaneous actuator selection and control in unknown LQR systems.

Findings

Achieves -regret in episodic setting

Achieves T^{2/3}-regret in non-episodic setting

Demonstrates scalability with number of actuators

Abstract

We study the simultaneous actuator selection and controller design problem for linear quadratic regulation with Gaussian noise over a finite horizon of length $T$ and unknown system model. We consider both episodic and non-episodic settings of the problem and propose online algorithms that specify both the sets of actuators to be utilized under a cardinality constraint and the controls corresponding to the sets of selected actuators. In the episodic setting, the interaction with the system breaks into $N$ episodes, each of which restarts from a given initial condition and has length $T$. In the non-episodic setting, the interaction goes on continuously. Our online algorithms leverage a multiarmed bandit algorithm to select the sets of actuators and a certainty equivalence approach to design the corresponding controls. We show that our online algorithms yield $\sqrt{N}$-regret for the episodic setting and $T^{2/3}$-regret for the non-episodic setting. We extend our algorithm design and analysis to show scalability with respect to both the total number of candidate actuators and the cardinality constraint. We numerically validate our theoretical results.