Papers › On the Global Optimality of Direct Policy Search for Nonsmooth H_∞ Output-Feedback Control

On the Global Optimality of Direct Policy Search for Nonsmooth H_∞ Output-Feedback Control

3 Apr 2023arXiv:2304.00753links table onlyarchive 2025-07-28

Yujie Tang, Yang Zheng

The archive published only this paper's code-link row. Authors, date and abstract are from arXiv's metadata (CC0), read from the Kaggle arXiv metadata snapshot of 2026-09-12 where its title matched the archive's; the title is the archive's.

Direct policy search has achieved great empirical success in reinforcement learning. Recently, there has been increasing interest in studying its theoretical properties for continuous control, and fruitful results have been established for linear quadratic regulator (LQR) and linear quadratic Gaussian (LQG) control that are smooth and nonconvex. In this paper, we consider the standard H_∞ robust control for output feedback systems and investigate the global optimality of direct policy search. Unlike LQR or LQG, the H_∞ cost function is nonsmooth in the policy space. Despite the lack of smoothness and convexity, our main result shows that for a class of non-degenerated stabilizing controllers, all Clarke stationary points of H_∞ robust control are globally optimal and there is no spurious local minimum. Our proof technique is motivated by the idea of differentiable convex liftings (DCL), and we extend DCL to analyze the nonsmooth and nonconvex H_∞ robust control via convex reformulation. Our result sheds some light on the analysis of direct policy search for solving nonsmooth and nonconvex robust control problems.

PaperPDFCode

Code

tyj518/h_inf_global_optimality officialmentioned in paper report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections