title | abstract | layout | series | publisher | issn | id | month | tex_title | firstpage | lastpage | page | order | cycles | bibtex_author | author | date | address | container-title | volume | genre | issued | extras | |||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Cooperative and Stochastic Multi-Player Multi-Armed Bandit: Optimal Regret With Neither Communication Nor Collisions |
We consider the cooperative multi-player version of the stochastic multi-armed bandit problem. We study the regime where the players cannot communicate but have access to shared randomness. In prior work by the first two authors, a strategy for this regime was constructed for two players and three arms, with regret |
inproceedings |
Proceedings of Machine Learning Research |
PMLR |
2640-3498 |
bubeck21b |
0 |
Cooperative and Stochastic Multi-Player Multi-Armed Bandit: Optimal Regret With Neither Communication Nor Collisions |
821 |
822 |
821-822 |
821 |
false |
Bubeck, Sebastien and Budzinski, Thomas and Sellke, Mark |
|
2021-07-21 |
Proceedings of Thirty Fourth Conference on Learning Theory |
134 |
inproceedings |
|