Multiplayer Bandits Without Observing Collision Information

DOI10.1287/moor.2021.1168zbMath1489.91058arXiv1808.08416OpenAlexW3212502353MaRDI QIDQ5085139

Abbas Mehrabian, Gábor Lugosi

Publication date: 27 June 2022

Published in: Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1808.08416

zbMATH Keywords

decentralized algorithmssequential decision makingdistributed learningopportunistic spectrum accessanticoordination gamesmultiplayer bandits

Mathematics Subject Classification ID

Stochastic games, stochastic differential games (91A15) Sequential estimation (62L12) Probabilistic games; gambling (91A60) Distributed algorithms (68W15)

Related Items (1)

Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Asymptotically efficient allocation rules for the multiarmed bandit problem with multiple plays-Part I: I.I.D. rewards
• Distributed Learning in Multi-Armed Bandit With Multiple Players
• High-Dimensional Probability
• Bandit Algorithms
• Introduction to Multi-Armed Bandits

This page was built for publication: Multiplayer Bandits Without Observing Collision Information