# The Impact of Batch Learning in Stochastic Bandits

arXiv: https://arxiv.org/abs/2111.02071 · HTML: https://mlsanity.com/paper/2111.02071/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 24 references that are in the map.
- First posted on arXiv 3 Nov 2021.

## Builds on (most cited first, 10 of 10)

- [Online Learning under Delayed Feedback](https://mlsanity.com/paper/1306.0686/) (2013)
- [Batched Multi-armed Bandits Problem](https://mlsanity.com/paper/1904.01763/) (2019)
- [Offline Multi-Action Policy Learning: Generalization and Optimization](https://mlsanity.com/paper/1810.04778/) (2018)
- [Scalable Generalized Linear Bandits: Online Computation and Hashing](https://mlsanity.com/paper/1706.00136/) (2017)
- [Sequential Batch Learning in Finite-Action Linear Contextual Bandits](https://mlsanity.com/paper/2004.06321/) (2020)
- [Online Learning with Switching Costs and Other Adaptive Adversaries](https://mlsanity.com/paper/1302.4387/) (2013)
- [Stochastic Bandit Models for Delayed Conversions](https://mlsanity.com/paper/1706.09186/) (2017)
- [Regret Bounds for Batched Bandits](https://mlsanity.com/paper/1910.04959/) (2019)
- [An Efficient Bandit Algorithm for Realtime Multivariate Optimization](https://mlsanity.com/paper/1810.09558/) (2018)
- [Estimation Considerations in Contextual Bandits](https://mlsanity.com/paper/1711.07077/) (2017)

## Built on by (most cited first, 1 of 1)

- [The Impact of Batch Learning in Stochastic Linear Bandits](https://mlsanity.com/paper/2202.06657/) (2022)

## Abstract (arXiv)

We consider a special case of bandit problems, namely batched bandits. Motivated by natural restrictions of recommender systems and e-commerce platforms, we assume that a learning agent observes responses batched in groups over a certain time period. Unlike previous work, we consider a more practically relevant batch-centric scenario of batch learning. We provide a policy-agnostic regret analysis and demonstrate upper and lower bounds for the regret of a candidate policy. Our main theoretical results show that the impact of batch learning can be measured in terms of online behavior. Finally, we demonstrate the consistency of theoretical results by conducting empirical experiments and reflect on the optimal batch size choice.