English

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

Systems and Control 2022-09-08 v2 Systems and Control

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.

Keywords

Cite

@article{arxiv.2203.17045,
  title  = {Wasserstein Distributionally Robust Control of Partially Observable Linear Systems: Tractable Approximation and Performance Guarantee},
  author = {Astghik Hakobyan and Insoon Yang},
  journal= {arXiv preprint arXiv:2203.17045},
  year   = {2022}
}

Comments

Accepted to be presented at CDC 22

R2 v1 2026-06-24T10:33:22.313Z