Wasserstein Distributionally Robust Control of Partially Observable Linear Systems: Tractable Approximation and Performance Guarantee

TL;DR

This paper introduces a computationally feasible Wasserstein distributionally robust control method for partially observable linear systems, providing performance guarantees and bounds on optimality gap.

Contribution

It develops a tractable approximation for WDRC in partially observable systems and derives explicit control policies with performance guarantees.

Findings

Closed-form optimal control policy derived

Guaranteed cost property established

Performance validated with Gaussian and non-Gaussian disturbances

Abstract

Wasserstein distributionally robust control (WDRC) is an effective method for addressing inaccurate distribution information about disturbances in stochastic systems. It provides various salient features, such as an out-of-sample performance guarantee, while most of the existing methods use full-state observations. In this paper, we develop a computationally tractable WDRC method for discrete-time partially observable linear-quadratic (LQ) control problems. The key idea is to reformulate the WDRC problem as a novel minimax control problem with an approximate Wasserstein penalty. We derive a closed-form expression of the optimal control policy of the approximate problem using a nontrivial Riccati equation. We further show the guaranteed cost property of the resulting controller and identify a provable bound for the optimality gap. Finally, we evaluate the performance of our method through numerical experiments using both Gaussian and non-Gaussian disturbances.