Learning with a Budget: Identifying the Best Arm with Resource Constraints
Abstract
In many applications, evaluating the effectiveness of different alternatives comes with varying costs or resource usage. Motivated by such heterogeneity, we study the Best Arm Identification with Resource Constraints (BAIwRC) problem, where an agent seeks to identify the best alternative (aka arm) in the presence of resource constraints. Each arm pull consumes one or more types of limited resources. We make two key contributions. First, we propose the Successive Halving with Resource Rationing (SH-RR) algorithm, which integrates resource-aware allocation into the classical successive halving framework on best arm identification. The SH-RR algorithm unifies the theoretical analysis for both the stochastic and deterministic consumption settings, with a new \textit{effective consumption measure
Cite
@article{arxiv.2602.24146,
title = {Learning with a Budget: Identifying the Best Arm with Resource Constraints},
author = {Zitian Li and Wang Chi Cheung},
journal= {arXiv preprint arXiv:2602.24146},
year = {2026}
}
Comments
A preliminary version of this work, titled 'Best Arm Identification with Resource Constraints,' was presented at the 27th International Conference on Artificial Intelligence and Statistics (AISTATS 2024). This manuscript extends the original conference paper by providing improved theoretical results and more generalized conclusions, aiming for future journal submission. arXiv admin note: substantial text overlap with arXiv:2402.19090