paper-with-me

홈 › Papers

Multi-Player Bandits -- a Musical Chairs Approach

2015-12-09 · Jonathan Rosenski, Ohad Shamir, Liran Szlak

We consider a variant of the stochastic multi-armed bandit problem, where multiple players simultaneously choose from the same set of arms and may collide, receiving no reward. This setting has been motivated by problems arising in cognitive radio networks, and is especially challenging under the realistic assumption that communication between players is limited. We provide a communication-free algorithm (Musical Chairs) which attains constant regret with high probability, as well as a sublinear-regret, communication-free algorithm (Dynamic Musical Chairs) for the more difficult setting of players dynamically entering and leaving throughout the game. Moreover, both algorithms do not require prior knowledge of the number of players. To the best of our knowledge, these are the first communication-free algorithms with these types of formal guarantees. We also rigorously compare our algorithms to previous works, and complement our theoretical findings with experiments.

📄 PDF Abstract BibTeX arXiv:1512.02866

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A survey on multi-player bandits

2022-11-29 · Etienne Boursier, Vianney Perchet

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…

Survey

Multiplayer Information Asymmetric Contextual Bandits

2025-03-11 · William Chang, Yuanhao Lu

Single-player contextual bandits are a well-studied problem in reinforcement learning that has seen applications in various fields such as advertising, healthcare, and finance. In light of the recent work on \emph{inform…

Multi-Armed Bandits

Constant or logarithmic regret in asynchronous multiplayer bandits

2023-05-31 · Hugo Richard, Etienne Boursier, Vianney Perchet

Multiplayer bandits have recently been extensively studied because of their application to cognitive radio networks. While the literature mostly considers synchronous players, radio networks (e.g. for IoT) tend to have a…

Regret Analysis of Sleeping Competing Bandits

2026-03-20 · Shinnosuke Uba, Yutaro Yamaguchi arxiv

The Competing Bandits framework is a recently emerging area that integrates multi-armed bandits in online learning with stable matching in game theory. While conventional models assume that all players and arms are const…

Multi-Armed Bandits

Multi-Player Bandits: A Trekking Approach

2018-09-17 · Manjesh K. Hanawal, Sumit J. Darak

We study stochastic multi-armed bandits with many players. The players do not know the number of players, cannot communicate with each other and if multiple players select a common arm they collide and none of them recei…

Multi-Armed Bandits