cs.LG · 2605.00488 Copy arXiv ID · May 1, 2026 Save Trading off rewards and errors in multi-armed bandits Authors: Akram Erraqabi , Alessandro Lazaric , Michal Valko , Emma Brunskill , Yun-En Liu
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.
Explore similar work Aug 2, 2026 · Jonghyun Sim, Wonyoung Kim Multi-Armed Bandits Dominant Paradigm
May 20, 2026 · Bingkui Tong, Junpei Komiyama, Soichiro Nishimori +1 Multi-Armed Bandits Linear Regret
May 8, 2026 · Francesco Bacchiocchi, Matteo Castiglioni, Alberto Marchesi +1 Multi-Armed Bandits O(T^Β)$ Simultaneous Regret
Aug 2, 2026 · stat.ML J/K move · Enter open · S save
Jonghyun Sim, Wonyoung Kim
Chung-Ang University, Seoul, Republic of Korea.
We study the problem of identifying the dominant arm in multi-armed bandits, where the objective is to find the action with the highest probability of exceeding the realized rewards of all other actions. Conventional mean-based and pairwise comparison-based algorithms often fail to identify the arm with the highest realized reward. To address this challenge, we introduce a novel dominant arm criterion and an efficient estimator with theoretical guarantees. Our approach relies on two key technical innovations: (i) a dominance score criterion that an arm beats the locally dominant over the partitioned reward space and (ii) a joint mixing and recycling mechanism coupled with a doubly robust estimator that guarantees simultaneous convergence of the empirical distribution functions for all arms. These key innovations pave a way to efficient computation of global arm dominance. Our proposed elimination algorithm identifies the best dominant arm with nearly optimal rate of sample complexity. Numerical experiments demonstrate that our algorithm consistently achieves exact recovery of the true dominant arm, outperforming existing baselines.