paper-with-me

홈 › Papers

Non-Stochastic Multi-Player Multi-Armed Bandits: Optimal Rate With Collision Information, Sublinear Without

2019-04-28 · Sébastien Bubeck, Yuanzhi Li, Yuval Peres, Mark Sellke

We consider the non-stochastic version of the (cooperative) multi-player multi-armed bandit problem. The model assumes no communication at all between the players, and furthermore when two (or more) players select the same action this results in a maximal loss. We prove the first $\sqrt{T}$-type regret guarantee for this problem, under the feedback model where collisions are announced to the colliding players. Such a bound was not known even for the simpler stochastic version. We also prove the first sublinear guarantee for the feedback model where collision information is not available, namely $T^{1-\frac{1}{2m}}$ where $m$ is the number of players.

📄 PDF Abstract BibTeX arXiv:1904.12233

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Armed Bandits

Similar Papers 제목 키워드 기반

Competing Bandits in Matching Markets

2019-06-12 · Lydia T. Liu, Horia Mania, Michael. I. Jordan

Stable matching, a classical model for two-sided markets, has long been studied with little consideration for how each side's preferences are learned. With the advent of massive online markets powered by data-driven matc…

Multi-Armed Bandits

QuACK: A Multipurpose Queuing Algorithm for Cooperative $k$-Armed Bandits

2024-10-31 · Benjamin Howson, Sarah Filippi, Ciara Pike-Burke

We study the cooperative stochastic $k$-armed bandit problem, where a network of $m$ agents collaborate to find the optimal action. In contrast to most prior work on this problem, which focuses on extending a specific al…

Decentralized Stochastic Multi-Player Multi-Armed Walking Bandits

2022-12-12 · Guojun Xiong, Jian Li

Multi-player multi-armed bandit is an increasingly relevant decision-making problem, motivated by applications to cognitive radio systems. Most research for this problem focuses exclusively on the settings that players h…

Decision MakingDistributed Optimization

A Parallel algorithm for $\mathcal{X}$-Armed bandits

2015-10-26 · Cheng Chen, Shuang Liu, Zhihua Zhang, Wu-Jun Li

The target of $\mathcal{X}$-armed bandit problem is to find the global maximum of an unknown stochastic function $f$, given a finite budget of $n$ evaluations. Recently, $\mathcal{X}$-armed bandits have been widely used …

Coordination without communication: optimal regret in two players multi-armed bandits

2020-02-14 · Sébastien Bubeck, Thomas Budzinski

We consider two agents playing simultaneously the same stochastic three-armed bandit problem. The two agents are cooperating but they cannot communicate. We propose a strategy with no collisions at all between the player…

Multi-Armed BanditsVocal Bursts Valence Prediction