Timezone: »

Batched Multi-armed Bandits Problem
Zijun Gao · Yanjun Han · Zhimei Ren · Zhengqing Zhou

Wed Dec 11 03:50 PM -- 04:05 PM (PST) @ West Exhibition Hall A

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.

Author Information

Zijun Gao (Stanford University)
Yanjun Han (Stanford University)
Zhimei Ren (Stanford University)
Zhengqing Zhou (Stanford University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors