Metraipolis › archive › dc_050a8d973aff

Zeroth-Order Policy Optimization for Scheduling in Queueing Networks — arXiv:2611.01186

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01186
License (as archived)
CC0-1.0
Archived
2026-11-03T18:36:44.201Z
SHA-256 of the archived text
bd438ab1d0a917bb62bd9a8946a89480f9c881428bb37aee9ebf90214cb0fc05
Stable URL of this page
https://metraipolis.com/documento/dc_050a8d973aff

How to cite

Zeroth-Order Policy Optimization for Scheduling in Queueing Networks — arXiv:2611.01186 — arXiv (en), https://arxiv.org/abs/2611.01186 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_050a8d973aff (Metraipolis archive dc_050a8d973aff, sha256 bd438ab1d0a917bb62bd9a8946a89480f9c881428bb37aee9ebf90214cb0fc05)
BibTeX
@misc{dc050a8d973aff,
  title = {Zeroth-Order Policy Optimization for Scheduling in Queueing Networks — arXiv:2611.01186},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01186},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_050a8d973aff; sha256 bd438ab1d0a917bb62bd9a8946a89480f9c881428bb37aee9ebf90214cb0fc05},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01186. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reinforcement learning in queueing network scheduling presents significant challenges because of the countably infinite state space and the high stochasticity in transitions. In this paper, we propose zeroth-order policy optimization algorithms that are easy to implement and rely solely on estimates of the average cost, a single scalar quantity, without requiring the estimation of value or advantage functions. Our analysis focuses on back-pressure guarded policies and establishes uniform smoothness of the average cost objective with respect to the policy parameters. Building on this property, we establish finite-time convergence guarantees to an $\epsilon$-stationary policy for the proposed algorithms. Numerical experiments on multiple queueing networks, including systems beyond classical exponential service distribution, demonstrate competitive performance, outperforming gradient-based RL methods like PPO and traditional queueing baselines.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.01186 — 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 2026-11-03T18:12:54.481Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).