Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits
Abstract
The study of collaborative multi-agent bandits has attracted significant attention recently. In light of this, we initiate the study of a new collaborative setting, consisting of $N$ agents such that each agent is learning one of $M$ stochastic multi-armed bandits to minimize their group cumulative regret. We develop decentralized algorithms which facilitate collaboration between the agents under two scenarios. We characterize the performance of these algorithms by deriving the per agent cumulative regret and group regret upper bounds. We also prove lower bounds for the group regret in this setting, which demonstrates the near-optimal behavior of the proposed algorithms.
Cite
Text
Chawla et al. "Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits." International Conference on Machine Learning, 2023.Markdown
[Chawla et al. "Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits." International Conference on Machine Learning, 2023.](https://mlanthology.org/icml/2023/chawla2023icml-collaborative/)BibTeX
@inproceedings{chawla2023icml-collaborative,
title = {{Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits}},
author = {Chawla, Ronshee and Vial, Daniel and Shakkottai, Sanjay and Srikant, R.},
booktitle = {International Conference on Machine Learning},
year = {2023},
pages = {4189-4217},
volume = {202},
url = {https://mlanthology.org/icml/2023/chawla2023icml-collaborative/}
}