An $\alpha$-No-Regret Algorithm For Graphical Bilinear Bandits
Geovani Rizk, Igor Colin, Albert Thomas, Rida Laraki, Yann Chevaleyre
Abstract
We propose the first regret-based approach to the \emph{Graphical Bilinear Bandits} problem, where $n$ agents in a graph play a stochastic bilinear bandit game with each of their neighbors. This setting reveals a combinatorial NP-hard problem that prevents the use of any existing regret-based algorithm in the (bi-)linear bandit literature. In this paper, we fill this gap and present the first regret-based algorithm for graphical bilinear bandits using the principle of optimism in the face of uncertainty. Theoretical analysis of this new method yields an upper bound of $\tilde{O}(\sqrt{T})$ on the $\alpha$-regret and evidences the impact of the graph structure on the rate of convergence. Finally, we show through various experiments the validity of our approach.
BibTeX
@inproceedings{
rizk2022an,
title={An \${\textbackslash}alpha\$-No-Regret Algorithm For Graphical Bilinear Bandits},
author={Geovani Rizk and Igor Colin and Albert Thomas and Rida Laraki and Yann Chevaleyre},
booktitle={Advances in Neural Information Processing Systems},
editor={Alice H. Oh and Alekh Agarwal and Danielle Belgrave and Kyunghyun Cho},
year={2022},
url={https://openreview.net/forum?id=2zQx2Pxbd7J}
}