Sébastien Bubeck, Thomas Budzinski, Mark Sellke. Cooperative and Stochastic Multi-Player Multi-Armed Bandit: Optimal Regret With Neither Communication Nor Collisions. In Mikhail Belkin, Samory Kpotufe, editors, Conference on Learning Theory, COLT 2021, 15-19 August 2021, Boulder, Colorado, USA. Volume 134 of Proceedings of Machine Learning Research, pages 821-822, PMLR, 2021. [doi]
@inproceedings{BubeckBS21,
title = {Cooperative and Stochastic Multi-Player Multi-Armed Bandit: Optimal Regret With Neither Communication Nor Collisions},
author = {Sébastien Bubeck and Thomas Budzinski and Mark Sellke},
year = {2021},
url = {http://proceedings.mlr.press/v134/bubeck21b.html},
researchr = {https://researchr.org/publication/BubeckBS21},
cites = {0},
citedby = {0},
pages = {821-822},
booktitle = {Conference on Learning Theory, COLT 2021, 15-19 August 2021, Boulder, Colorado, USA},
editor = {Mikhail Belkin and Samory Kpotufe},
volume = {134},
series = {Proceedings of Machine Learning Research},
publisher = {PMLR},
}