EUVIMEDEUVIMED entdecken
Crossref

Asynchronous Stochastic Approximation with Applications to Average-Reward Reinforcement Learning

Huizhen Yu, Yi Wan, Richard S. Sutton

SIAM Journal on Control and Optimization · 30.06.2026 · 64 (3) · 1456-1481

DOI: 10.1137/25m1769806 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SIAM Journal on Control and Optimization, online erschienen am 20.05.2026. Verfasst von Huizhen Yu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: Alberta Machine Intelligence Institute, Natural Sciences and Engineering Research Council of Canada.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper investigates the stability and convergence properties of asynchronous stochastic approximation (SA) algorithms, with a focus on extensions relevant to average-reward reinforcement learning. We first extend a stability proof method of Borkar and Meyn to accommodate more general noise conditions than previously considered, thereby yielding broader convergence guarantees for asynchronous SA. To sharpen the convergence analysis, we further examine the shadowing properties of asynchronous SA, building on a dynamical systems approach of Hirsch and Benaïm. These results provide a theoretical foundation for a class of relative value iteration-based reinforcement learning algorithms—developed and analyzed in a companion paper—for solving average-reward Markov and semi-Markov decision processes.

Förderung

  • Alberta Machine Intelligence Institute
  • Natural Sciences and Engineering Research Council of Canada

Zitieren

APA

Yu, H., Wan, Y., & Sutton, R. S. (2026). Asynchronous Stochastic Approximation with Applications to Average-Reward Reinforcement Learning. SIAM Journal on Control and Optimization, 64(3), 1456-1481. https://doi.org/10.1137/25m1769806

Vancouver

Yu H, Wan Y, Sutton RS. Asynchronous Stochastic Approximation with Applications to Average-Reward Reinforcement Learning. SIAM Journal on Control and Optimization. 2026;64(3):1456-1481. doi:10.1137/25m1769806

BibTeX
@article{Yu2026,
  author = {Yu, Huizhen and Wan, Yi and Sutton, Richard S.},
  title = {Asynchronous Stochastic Approximation with Applications to Average-Reward Reinforcement Learning},
  journal = {SIAM Journal on Control and Optimization},
  year = {2026},
  volume = {64},
  number = {3},
  pages = {1456--1481},
  doi = {10.1137/25m1769806}
}
Kostenlos starten →