Learning with a Budget: Identifying the Best Arm with Resource Constraints
This addresses resource-efficient decision-making in applications with heterogeneous costs, but it is incremental as it builds on the classical successive halving framework.
The paper tackles the Best Arm Identification with Resource Constraints problem, where an agent must identify the best alternative under limited resources, and proposes the SH-RR algorithm, achieving a unified theoretical analysis for stochastic and deterministic settings with a new effective consumption measure.
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