# Batched Thompson Sampling for Multi-Armed Bandits

arXiv: https://arxiv.org/abs/2108.06812 · HTML: https://mlsanity.com/paper/2108.06812/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 27 references that are in the map.
- First posted on arXiv 15 Aug 2021.

## Builds on (most cited first, 6 of 6)

- [Batched Multi-armed Bandits Problem](https://mlsanity.com/paper/1904.01763/) (2019)
- [Provably Efficient Q-Learning with Low Switching Cost](https://mlsanity.com/paper/1905.12849/) (2019)
- [Online Learning with Switching Costs and Other Adaptive Adversaries](https://mlsanity.com/paper/1302.4387/) (2013)
- [MOTS: Minimax Optimal Thompson Sampling](https://mlsanity.com/paper/2003.01803/) (2020)
- [Parallelizing Thompson Sampling](https://mlsanity.com/paper/2106.01420/) (2021)
- [Multinomial Logit Bandit with Low Switching Cost](https://mlsanity.com/paper/2007.04876/) (2020)

## Built on by (most cited first, 2 of 2)

- [Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits](https://mlsanity.com/paper/2301.11442/) (2023)
- [Breaking the log(1/Delta2) Barrier: Better Batched Best Arm Identification with Adaptive Grids](https://mlsanity.com/paper/2501.17370/) (2025)

## Abstract (arXiv)

We study Thompson Sampling algorithms for stochastic multi-armed bandits in the batched setting, in which we want to minimize the regret over a sequence of arm pulls using a small number of policy changes (or, batches). We propose two algorithms and demonstrate their effectiveness by experiments on both synthetic and real datasets. We also analyze the proposed algorithms from the theoretical aspect and obtain almost tight regret-batches tradeoffs for the two-arm case.