ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2106.04228
44
16
v1v2 (latest)

Decentralized Learning in Online Queuing Systems

8 June 2021
Flore Sentenac
Etienne Boursier
Vianney Perchet
ArXiv (abs)PDFHTML
Abstract

Motivated by packet routing in computer networks, online queuing systems are composed of queues receiving packets at different rates. Repeatedly, they send packets to servers, each of them treating only at most one packet at a time. In the centralized case, the number of accumulated packets remains bounded (i.e., the system is \textit{stable}) as long as the ratio between service rates and arrival rates is larger than 111. In the decentralized case, individual no-regret strategies ensures stability when this ratio is larger than 222. Yet, myopically minimizing regret disregards the long term effects due to the carryover of packets to further rounds. On the other hand, minimizing long term costs leads to stable Nash equilibria as soon as the ratio exceeds ee−1\frac{e}{e-1}e−1e​. Stability with decentralized learning strategies with a ratio below 222 was a major remaining question. We first argue that for ratios up to 222, cooperation is required for stability of learning strategies, as selfish minimization of policy regret, a \textit{patient} notion of regret, might indeed still be unstable in this case. We therefore consider cooperative queues and propose the first learning decentralized algorithm guaranteeing stability of the system as long as the ratio of rates is larger than 111, thus reaching performances comparable to centralized strategies.

View on arXiv
Comments on this paper