Multiple Identifications in Multi-Armed Bandits
Abstract
We study the problem of identifying the top m arms in a multi-armed bandit game. Our proposed solution relies on a new algorithm based on successive rejects of the seemingly bad arms, and successive accepts of the good ones. This algorithmic contribution allows to tackle other multiple identifications settings that were previously out of reach. In particular we show that this idea of successive accepts and rejects applies to the multi-bandit best arm identification problem.
Cite
Text
Bubeck et al. "Multiple Identifications in Multi-Armed Bandits." International Conference on Machine Learning, 2013.Markdown
[Bubeck et al. "Multiple Identifications in Multi-Armed Bandits." International Conference on Machine Learning, 2013.](https://mlanthology.org/icml/2013/bubeck2013icml-multiple/)BibTeX
@inproceedings{bubeck2013icml-multiple,
title = {{Multiple Identifications in Multi-Armed Bandits}},
author = {Bubeck, Séebastian and Wang, Tengyao and Viswanathan, Nitin},
booktitle = {International Conference on Machine Learning},
year = {2013},
pages = {258-265},
volume = {28},
url = {https://mlanthology.org/icml/2013/bubeck2013icml-multiple/}
}