Benign Nonconvex Landscapes in Optimal and Robust Control, Part I: Global Optimality
IEEE Transactions on Automatic Control · 2026-08 · 71 (8) · 5334-5349
DOI: 10.1109/tac.2026.3675544 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Automatic Control, 2026-08. Verfasst von Yang Zheng und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Science Foundation.
Abstract (Originalsprache)
Direct policy search has achieved great empirical success in reinforcement learning. Many recent studies have revisited its theoretical foundation for continuous control, which reveals elegant nonconvex geometry in various benchmark problems. This article considers two fundamental optimal and robust control problems with partial observability: linear quadratic Gaussian (LQG) control and $\mathcal {H}_\infty$ robust control. In the policy space, the former problem is smooth but nonconvex, while the latter one is nonsmooth and nonconvex. We highlight some interesting and surprising “discontinuity” of LQG and $\mathcal {H}_\infty$ cost functions around the boundary of their domains. Despite the lack of convexity (and possibly smoothness), we show that for a class of nondegenerate policies, all Clarke stationary points are globally optimal and there is no spurious local minimum for both LQG and $\mathcal {H}_\infty$ control. The main results are established by a new and unified framework of Extended Convex Lifting (ECL), which reconciles the gap between nonconvex policy optimization and convex reformulations. This ECL framework is of independent interest, and we discuss its details in Part II of this article.
Förderung
- National Natural Science Foundation of China
- National Science Foundation
Zitieren
APA
Zheng, Y., Pai, C. R., & Tang, Y. (2026). Benign Nonconvex Landscapes in Optimal and Robust Control, Part I: Global Optimality. IEEE Transactions on Automatic Control, 71(8), 5334-5349. https://doi.org/10.1109/tac.2026.3675544
Vancouver
Zheng Y, Pai CR, Tang Y. Benign Nonconvex Landscapes in Optimal and Robust Control, Part I: Global Optimality. IEEE Transactions on Automatic Control. 2026;71(8):5334-5349. doi:10.1109/tac.2026.3675544
BibTeX
@article{Zheng2026,
author = {Zheng, Yang and Pai, Chih-Fan Rich and Tang, Yujie},
title = {Benign Nonconvex Landscapes in Optimal and Robust Control, Part I: Global Optimality},
journal = {IEEE Transactions on Automatic Control},
year = {2026},
volume = {71},
number = {8},
pages = {5334--5349},
doi = {10.1109/tac.2026.3675544}
}
EUVIMED