Batched Bandit Problems
Name
Rigollet_Batched bandit.pdf
Size
326.43 KB
Format
Adobe PDF
Checksum (MD5)
85518b7f29de595bd97c6b635c4a20d4
Author(s)
Perchet, Vianney
Rigollet, Philippe
Chassang, Sylvain
Snowberg, Erik
Date Issued
September 24, 2015
Journal
forthcoming in Annals of Statistics
Publisher
Institute of Mathematical Statistics
Citation
Perchet, Vianney, Philippe Rigollet, Sylvain Chassang, and Erik Snowberg. "Batched Bandit Problems." Annals of Statistics (2015).
Version
Author's final manuscript
Abstract
Motivated by practical applications, chiefly clinical trials, we study the regret achievable for stochastic bandits under the constraint that the employed policy must split trials into a small number of batches. Our results show that a very small number of batches gives close to minimax optimal regret bounds. As a byproduct, we derive optimal policies with low switching cost for stochastic bandits.
MIT Department
Massachusetts Institute of Technology. Department of Mathematics
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
