Metraipolis › archive › dc_2b006feb8179

Algorithmic Optimality Guarantees for Nonsmooth $H_\infty$ Output-Feedback Policy Search — arXiv:2609.06197

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.06197
License (as archived)
CC0-1.0
Archived
2026-10-16T13:58:53.136Z
SHA-256 of the archived text
02fb4f28e15e66273f1c687839b5daf2be424bad0e7820f7227f1db37e1d3af6
Stable URL of this page
https://metraipolis.com/documento/dc_2b006feb8179

How to cite

Algorithmic Optimality Guarantees for Nonsmooth $H_\infty$ Output-Feedback Policy Search — arXiv:2609.06197 — arXiv (en), https://arxiv.org/abs/2609.06197 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2b006feb8179 (Metraipolis archive dc_2b006feb8179, sha256 02fb4f28e15e66273f1c687839b5daf2be424bad0e7820f7227f1db37e1d3af6)
BibTeX
@misc{dc2b006feb8179,
  title = {Algorithmic Optimality Guarantees for Nonsmooth $H_infty$ Output-Feedback Policy Search — arXiv:2609.06197},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06197},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2b006feb8179; sha256 02fb4f28e15e66273f1c687839b5daf2be424bad0e7820f7227f1db37e1d3af6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06197. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study continuous-time full-order dynamic output-feedback $H_\infty$ policy search, a nonconvex and nonsmooth problem. Direct policy search is a central paradigm in reinforcement learning and continuous control, but rigorous guarantees remain scarce in robust output-feedback settings. The $H_\infty$ problem is a canonical benchmark because it captures disturbance attenuation and robustness while exposing the hard nonsmooth geometry of policy-space optimization. We prove that on the exact identity-gauge slice of the extended convex lift, $\varepsilon$-stationarity yields $O(\varepsilon)$-suboptimality on compact exact slices, which in turn yields convergence-rate guarantees for nonsmooth policy-search methods. This result addresses the finite-time optimality-gap question raised by Guo and Hu [2022] in the more general dynamic output-feedback $H_\infty$ policy-search setting. We further use the established value equivalence supplied by extended convex lifting to formulate a nonstrict-feasibility bisection method with one final strict-feasibility recovery step, yielding an explicit $\varepsilon$-optimal stabilizing controller. These results provide a quantitative and algorithmic strengthening of prior qualitative optimality theory for nonsmooth $H_\infty$ policy search.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Optimization and Control (math.OC) ; Machine Learning (cs.LG); Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.06197 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T13:39:43.154Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).