preprintarXiv (Cornell University)May 1, 2026GREEN OA

Trading off rewards and errors in multi-armed bandits

AEAkram ErraqabiALAlessandro LazaricMVMichal VaľkoEBEmma BrunskillYLYun-En Liu

Université de Montréal · Laboratoire d'Informatique de Paris-Nord · +1 more institution

Indexed inarxivdatacite

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.

Citation impact

11
total citations
FWCI
—
Percentile
—
References
0
Citations per year

Authors

5

Topics & keywords

Topics
Keywords
  • Computer science
  • Maximization
  • Utility maximization
  • Artificial intelligence
  • Machine learning
  • Mathematical optimization
  • Economics
No related works found for this paper.

Funding