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

In this article, we study the simultaneous actuator selection and controller design problem for linear quadratic regulation with Gaussian noise over a finite horizon of length <tex-math notation="LaTeX">T</tex-math> and unknown system model. We consider episodic and nonepisodic 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 <tex-math notation="LaTeX">N</tex-math> episodes, each of which restarts from a given initial condition and has length <tex-math notation="LaTeX">T</tex-math>. In the nonepisodic 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 <tex-math notation="LaTeX">√N</tex-math>-regret for the episodic setting and <tex-math notation="LaTeX">T2/3</tex-math>-regret for the nonepisodic 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.