Fixed-Budget Best-Arm Identification in Structured Bandits

Fixed-Budget Best-Arm Identification in Structured Bandits

MohammadJavad Azizi, Branislav Kveton, Mohammad Ghavamzadeh

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
Main Track. Pages 2798-2804. https://doi.org/10.24963/ijcai.2022/388

Best-arm identification (BAI) in a fixed-budget setting is a bandit problem where the learning agent maximizes the probability of identifying the optimal (best) arm after a fixed number of observations. Most works on this topic study unstructured problems with a small number of arms, which limits their applicability. We propose a general tractable algorithm that incorporates the structure, by successively eliminating suboptimal arms based on their mean reward estimates from a joint generalization model. We analyze our algorithm in linear and generalized linear models (GLMs), and propose a practical implementation based on a G-optimal design. In linear models, our algorithm has competitive error guarantees to prior works and performs at least as well empirically. In GLMs, this is the first practical algorithm with analysis for fixed-budget BAI.
Keywords:
Machine Learning: Online Learning
Machine Learning: Active Learning
Machine Learning: Reinforcement Learning