Asymptotic Performance of Thompson Sampling in the Batched Multi-Armed Bandits
This addresses the challenge of delayed feedback in bandit algorithms for applications like online advertising or clinical trials, though it is incremental as it extends existing Thompson sampling analysis to a batched setting.
The paper tackles the problem of Thompson sampling's performance in batched multi-armed bandits with delayed feedback, showing it achieves the same asymptotic performance as with instantaneous feedback when batch sizes increase subexponentially, and proposes an adaptive scheme reducing batches to Θ(log T) while maintaining performance.
We study the asymptotic performance of the Thompson sampling algorithm in the batched multi-armed bandit setting where the time horizon $T$ is divided into batches, and the agent is not able to observe the rewards of her actions until the end of each batch. We show that in this batched setting, Thompson sampling achieves the same asymptotic performance as in the case where instantaneous feedback is available after each action, provided that the batch sizes increase subexponentially. This result implies that Thompson sampling can maintain its performance even if it receives delayed feedback in $ω(\log T)$ batches. We further propose an adaptive batching scheme that reduces the number of batches to $Θ(\log T)$ while maintaining the same performance. Although the batched multi-armed bandit setting has been considered in several recent works, previous results rely on tailored algorithms for the batched setting, which optimize the batch structure and prioritize exploration in the beginning of the experiment to eliminate suboptimal actions. We show that Thompson sampling, on the other hand, is able to achieve a similar asymptotic performance in the batched setting without any modifications.