paper-with-me

Papers

An Optimal Algorithm for Multiplayer Multi-Armed Bandits

2019-09-28 · Alexandre Proutiere, Po-An Wang

The paper addresses the Multiplayer Multi-Armed Bandit (MMAB) problem, where $M$ decision makers or players collaborate to maximize their cumulative reward. When several players select the same arm, a collision occurs and no reward is collected on this arm. Players involved in a collision are informed about this collision. We present DPE (Decentralized Parsimonious Exploration), a decentralized algorithm that achieves the same regret as that obtained by an optimal centralized algorithm. Our algorithm has better regret guarantees than the state-of-the-art algorithm SIC-MMAB \cite{boursier2019}. As in SIC-MMAB, players communicate through collisions only. An additional important advantage of DPE is that it requires very little communication. Specifically, the expected number of rounds where players use collisions to communicate is finite.

📄 PDF Abstract BibTeX arXiv:1909.13079

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Armed Bandits

Similar Papers 제목 키워드 기반

A Practical Algorithm for Multiplayer Bandits when Arm Means Vary Among Players

2019-02-04 · Etienne Boursier, Emilie Kaufmann, Abbas Mehrabian, Vianney Perchet

We study a multiplayer stochastic multi-armed bandit problem in which players cannot communicate, and if two or more players pull the same arm, a collision occurs and the involved players receive zero reward. We consider…

Open-Ended Question Answering

On Regret-Optimal Learning in Decentralized Multi-player Multi-armed Bandits

2015-05-04 · Naumaan Nayyar, Dileep Kalathil, Rahul Jain

We consider the problem of learning in single-player and multiplayer multiarmed bandit models. Bandit problems are classes of online learning problems that capture exploration versus exploitation tradeoffs. In a multiarm…

Multi-Armed Bandits

Multi-Player Approaches for Dueling Bandits

2024-05-25 · Or Raveh, Junya Honda, Masashi Sugiyama

Various approaches have emerged for multi-armed bandits in distributed systems. The multiplayer dueling bandit problem, common in scenarios with only preference-based information like human feedback, introduces challenge…

Multi-Armed Bandits

SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed Bandits

2018-09-21 · NeurIPS 2019 12 · Etienne Boursier, Vianney Perchet

Motivated by cognitive radio networks, we consider the stochastic multiplayer multi-armed bandit problem, where several players pull arms simultaneously and collisions occur if one of them is pulled by several players at…

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…