EUVIMEDEUVIMED entdecken
Crossref

GINO-Q: Learning an Asymptotically Optimal Index Policy for Restless Multi-armed Bandits

Gongpu Chen, Soung Chang Liew, Deniz Gündüz

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (24) · 20032-20040

DOI: 10.1609/aaai.v40i24.39088 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Gongpu Chen und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The restless multi-armed bandit (RMAB) framework is a popular model with applications across a wide variety of fields. However, its solution is hindered by the exponentially growing state space (with respect to the number of arms) and the combinatorial action space, making traditional reinforcement learning methods infeasible for large-scale instances. In this paper, we propose GINO-Q, a three-timescale stochastic approximation algorithm designed to learn an asymptotically optimal index policy for RMABs. GINO-Q mitigates the curse of dimensionality by decomposing the RMAB into a series of subproblems, each with the same dimension as a single arm, ensuring that complexity increases linearly with the number of arms. Unlike recently developed Whittle-index-based algorithms, GINO-Q does not require RMABs to be indexable, enhancing its flexibility and applicability. Our experimental results demonstrate that GINO-Q consistently learns near-optimal policies, even for non-indexable RMABs where Whittle-index-based algorithms perform poorly, and it converges significantly faster than existing baselines.

Zitieren

APA

Chen, G., Liew, S. C., & Gündüz, D. (2026). GINO-Q: Learning an Asymptotically Optimal Index Policy for Restless Multi-armed Bandits. Proceedings of the AAAI Conference on Artificial Intelligence, 40(24), 20032-20040. https://doi.org/10.1609/aaai.v40i24.39088

Vancouver

Chen G, Liew SC, Gündüz D. GINO-Q: Learning an Asymptotically Optimal Index Policy for Restless Multi-armed Bandits. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(24):20032-20040. doi:10.1609/aaai.v40i24.39088

BibTeX
@article{Chen2026,
  author = {Chen, Gongpu and Liew, Soung Chang and Gündüz, Deniz},
  title = {GINO-Q: Learning an Asymptotically Optimal Index Policy for Restless Multi-armed Bandits},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {24},
  pages = {20032--20040},
  doi = {10.1609/aaai.v40i24.39088}
}
Kostenlos starten →