Multi-Player Bandits: The Adversarial Case
Machine Learning
2019-02-22 v1 Machine Learning
Abstract
We consider a setting where multiple players sequentially choose among a common set of actions (arms). Motivated by a cognitive radio networks application, we assume that players incur a loss upon colliding, and that communication between players is not possible. Existing approaches assume that the system is stationary. Yet this assumption is often violated in practice, e.g., due to signal strength fluctuations. In this work, we design the first Multi-player Bandit algorithm that provably works in arbitrarily changing environments, where the losses of the arms may even be chosen by an adversary. This resolves an open problem posed by Rosenski, Shamir, and Szlak (2016).
Cite
@article{arxiv.1902.08036,
title = {Multi-Player Bandits: The Adversarial Case},
author = {Pragnya Alatur and Kfir Y. Levy and Andreas Krause},
journal= {arXiv preprint arXiv:1902.08036},
year = {2019}
}