Regret Bounds for Batched Bandits
Keywords:Online Learning & Bandits, Learning Theory
AbstractWe present simple algorithms for batched stochastic multi-armed bandit and batched stochastic linear bandit problems. We prove bounds for their expected regrets that improve and extend the best known regret bounds of Gao, Han, Ren, and Zhou (NeurIPS 2019), 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 provide the optimal regret, up to logarithmic factors, of any algorithm with predetermined batch sizes.
How to Cite
Esfandiari, H., Karbasi, A., Mehrabian, A., & Mirrokni, V. (2021). Regret Bounds for Batched Bandits. Proceedings of the AAAI Conference on Artificial Intelligence, 35(8), 7340-7348. https://doi.org/10.1609/aaai.v35i8.16901
AAAI Technical Track on Machine Learning I