Trading off rewards and errors in multi-armed bandits
Abstract
In multi-armed bandits, the most-explored arms are the most informative, while reward maximization typically pulls only the best arm. We study the tradeoff between identifying arm means accurately and accumulating reward, and present an algorithm with regret guarantees that interpolates between the two objectives. We provide both upper and lower bounds and validate empirically.
Fields of Study & Subjects
Advanced Bandit Algorithms Research
Online Learning and Analytics
Data Stream Mining Techniques
Publication details
- Journal / source
- arXiv (Cornell University)
- Publication date
- 1 May 2026
- Language
- EN
- Document type
- Preprint