Asymptotic Optimality for Decentralised Bandits
Machine Learning
2021-09-21 v1
Abstract
We consider a large number of agents collaborating on a multi-armed bandit problem with a large number of arms. The goal is to minimise the regret of each agent in a communication-constrained setting. We present a decentralised algorithm which builds upon and improves the Gossip-Insert-Eliminate method of Chawla et al. arxiv:2001.05452. We provide a theoretical analysis of the regret incurred which shows that our algorithm is asymptotically optimal. In fact, our regret guarantee matches the asymptotically optimal rate achievable in the full communication setting. Finally, we present empirical results which support our conclusions
Keywords
Cite
@article{arxiv.2109.09427,
title = {Asymptotic Optimality for Decentralised Bandits},
author = {Conor Newton and Ayalvadi Ganesh and Henry W. J. Reeve},
journal= {arXiv preprint arXiv:2109.09427},
year = {2021}
}