Metraipolis › archive › dc_b98bbc8101cb
(Cheap) Stochastic Policy Gradient Converges with High Probability for Linear Quadratic Regulator — arXiv:2609.19712
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19712
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T04:20:50.083Z
- SHA-256 of the archived text
06f138cf6042ed9c030b6cb9ef62892028bf7f2dbc23963634bd6656e294c45d- Stable URL of this page
https://metraipolis.com/documento/dc_b98bbc8101cb
How to cite
(Cheap) Stochastic Policy Gradient Converges with High Probability for Linear Quadratic Regulator — arXiv:2609.19712 — arXiv (en), https://arxiv.org/abs/2609.19712 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b98bbc8101cb (Metraipolis archive dc_b98bbc8101cb, sha256 06f138cf6042ed9c030b6cb9ef62892028bf7f2dbc23963634bd6656e294c45d)
BibTeX
@misc{dcb98bbc8101cb,
title = {(Cheap) Stochastic Policy Gradient Converges with High Probability for Linear Quadratic Regulator — arXiv:2609.19712},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19712},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b98bbc8101cb; sha256 06f138cf6042ed9c030b6cb9ef62892028bf7f2dbc23963634bd6656e294c45d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19712. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study the convergence of the vanilla stochastic policy gradient method applied to the linear quadratic regulator (LQR) problem. The method is cheap in the following sense: (1) at each iteration only $\tilde{O}(1)$ interactions with the environment are needed, therefore allowing frequent policy improvement steps, and (2) to ensure stability throughout and convergence to an $\epsilon$-optimal policy with probability $1-\delta$, only $O(\mathtt{Polylog}(1/\delta)/\epsilon)$ interactions are needed. To the best of our knowledge, this appears to be the first time that a stochastic model-free policy optimization method for LQR converges with high probability with $\tilde{O}(1)$ per-iteration computation and polylogarithmic dependence on the confidence level. The convergence analysis presented here is agnostic to LQR specifics and hence could be potentially generalized to a broader class of problems.
Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-18 in math.OC).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2609.19712 — 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 2026-10-10T04:09:28.167Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).