Batched Multi-Armed Bandits Problem
Abstract
In this paper, we study the multi-armed bandit problem in the batched setting where the employed policy must split data into a small number of batches. While the minimax regret for the two-armed stochastic bandits has been completely characterized in \cite{perchet2016batched}, the effect of the number of arms on the regret for the multi-armed case is still open. Moreover, the question whether adaptively chosen batch sizes will help to reduce the regret also remains underexplored. In this paper, we propose the BaSE (batched successive elimination) policy to achieve the rate-optimal regrets (within logarithmic factors) for batched multi-armed bandits, with matching lower bounds even if the batch sizes are determined in an adaptive manner.
Cite
Text
Gao et al. "Batched Multi-Armed Bandits Problem." Neural Information Processing Systems, 2019.Markdown
[Gao et al. "Batched Multi-Armed Bandits Problem." Neural Information Processing Systems, 2019.](https://mlanthology.org/neurips/2019/gao2019neurips-batched/)BibTeX
@inproceedings{gao2019neurips-batched,
title = {{Batched Multi-Armed Bandits Problem}},
author = {Gao, Zijun and Han, Yanjun and Ren, Zhimei and Zhou, Zhengqing},
booktitle = {Neural Information Processing Systems},
year = {2019},
pages = {503-513},
url = {https://mlanthology.org/neurips/2019/gao2019neurips-batched/}
}