A survey on multi-player bandits

2022/11/29 by Étienne Boursier, Boursier, Etienne, Vianney Perchet +1 · 4 citations
Computer Science · Decision Sciences · Engineering · #Advanced Bandit Algorithms Research #Advanced Wireless Network Optimization #Cognitive Radio Networks and Spectrum Sensing #Computer Science and Game Theory (cs.GT) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.2211.16275

openalex publication_date 2022/11/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01

Abstract

Due mostly to its application to cognitive radio networks, multiplayer bandits gained a lot of interest in the last decade. A considerable progress has been made on its theoretical aspect. However, the current algorithms are far from applicable and many obstacles remain between these theoretical results and a possible implementation of multiplayer bandits algorithms in real cognitive radio networks. This survey contextualizes and organizes the rich multiplayer bandits literature. In light of the existing works, some clear directions for future research appear. We believe that a further study of these different directions might lead to theoretical algorithms adapted to real-world situations.

Citations

• Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed\n Bandit Problem with Multiple Plays
• Online Bandit Learning against an Adaptive Adversary: from Regret to\n Policy Regret
• Thompson Sampling for Combinatorial Semi-Bandits
• Cooperative Online Learning: Keeping your Neighbors Updated
• Multi-Player Bandits: The Adversarial Case
• Efficient Change-Point Detection for Tackling Piecewise-Stationary Bandits
• Decentralized Multi-player Multi-armed Bandits with No Collision Information
• Statistical Efficiency of Thompson Sampling for Combinatorial Semi-Bandits
• Asymptotically Optimal Strategies For Combinatorial Semi-Bandits in Polynomial Time
• Towards Optimal Algorithms for Multi-Player Bandits without Collision Sensing Information
• Dominate or Delete: Decentralized Competing Bandits in Serial Dictatorship
• Decentralized Learning in Online Queuing Systems
• Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization
• Competing for Shareable Arms in Multi-Player Multi-Armed Bandits

Cited by

• KernelBand: Boosting LLM-based Kernel Optimization with a Hierarchical and Hardware-aware Multi-armed Bandit
• Bandit Learning in Housing Markets
• Decentralized Asynchronous Multi-player Bandits
• Choosing the Better Bandit Algorithm under Data Sharing: When Do A/B Experiments Work?

Related

• Multi-Player Bandits: The Adversarial Case
• A High Performance, Low Complexity Algorithm for Multi-Player Bandits\n Without Collision Sensing Information
• Multi-player Bandits for Distributed Cognitive Radar
• Decentralized Asynchronous Multi-player Bandits
• Adversarial Multi-Player Bandits for Cognitive Radar Networks