Regret Bounds for Batched Bandits
Data Structures and Algorithms
2020-02-19 v2 Machine Learning
Abstract
We present simple and efficient algorithms for the batched stochastic multi-armed bandit and batched stochastic linear bandit problems. We prove bounds for their expected regrets that improve over the best-known regret bounds for any number of batches. In particular, our algorithms in both settings achieve the optimal expected regrets by using only a logarithmic number of batches. We also study the batched adversarial multi-armed bandit problem for the first time and find the optimal regret, up to logarithmic factors, of any algorithm with predetermined batch sizes.
Cite
@article{arxiv.1910.04959,
title = {Regret Bounds for Batched Bandits},
author = {Hossein Esfandiari and Amin Karbasi and Abbas Mehrabian and Vahab Mirrokni},
journal= {arXiv preprint arXiv:1910.04959},
year = {2020}
}