Policy Optimization in Robust Control: Weak Convexity and Subgradient Methods

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Watanabe, Yuto, Liao, Feng-Yi, Zheng, Yang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915524161568768
author Watanabe, Yuto
Liao, Feng-Yi
Zheng, Yang
author_facet Watanabe, Yuto
Liao, Feng-Yi
Zheng, Yang
contents Robust control seeks stabilizing policies that perform reliably under adversarial disturbances, with $\mathcal{H}_\infty$ control as a classical formulation. It is known that policy optimization of robust $\mathcal{H}_\infty$ control naturally lead to nonsmooth and nonconvex problems. This paper builds on recent advances in nonsmooth optimization to analyze discrete-time static output-feedback $\mathcal{H}_\infty$ control. We show that the $\mathcal{H}_\infty$ cost is weakly convex over any convex subset of a sublevel set. This structural property allows us to establish the first non-asymptotic deterministic convergence rate for the subgradient method under suitable assumptions. In addition, we prove a weak Polyak-Łojasiewicz (PL) inequality in the state-feedback case, implying that all stationary points are globally optimal. We finally present a few numerical examples to validate the theoretical results.
format Preprint
id arxiv_https___arxiv_org_abs_2509_25633
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Policy Optimization in Robust Control: Weak Convexity and Subgradient Methods
Watanabe, Yuto
Liao, Feng-Yi
Zheng, Yang
Optimization and Control
Systems and Control
Robust control seeks stabilizing policies that perform reliably under adversarial disturbances, with $\mathcal{H}_\infty$ control as a classical formulation. It is known that policy optimization of robust $\mathcal{H}_\infty$ control naturally lead to nonsmooth and nonconvex problems. This paper builds on recent advances in nonsmooth optimization to analyze discrete-time static output-feedback $\mathcal{H}_\infty$ control. We show that the $\mathcal{H}_\infty$ cost is weakly convex over any convex subset of a sublevel set. This structural property allows us to establish the first non-asymptotic deterministic convergence rate for the subgradient method under suitable assumptions. In addition, we prove a weak Polyak-Łojasiewicz (PL) inequality in the state-feedback case, implying that all stationary points are globally optimal. We finally present a few numerical examples to validate the theoretical results.
title Policy Optimization in Robust Control: Weak Convexity and Subgradient Methods
topic Optimization and Control
Systems and Control
url https://arxiv.org/abs/2509.25633