arXiv Machine Learning August 4, 2026 By Jonghyun Sim, Wonyoung Kim

Dominant Arm Identification with Mixing and Recycling Observed Samples

Read the original on arXiv Machine Learning →

arXiv:2608. 01545v1 Announce Type: cross Abstract: 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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 16

Best Arm Identification with Minimal Regret

arXiv:2409. 18909v2 Announce Type: replace Abstract: Motivated by real-world applications that necessitate responsible experimentation, we introduce the problem of best arm identification (BAI) with minimal regret.

By Junwen Yang, Vincent Y. F. Tan, Tianyuan Jin

agents reinforcement-learning

arXiv Machine Learning

Jun 9

Multi-Armed Bandits with Arriving Arms: Sequential Screening, Dynamic Regret, and Sublinear Guarantees

arXiv:2606. 09002v1 Announce Type: cross Abstract: We study a stochastic multi-armed bandit problem in which the set of available arms expands over time.

By Deqi Zheng, Xiaoyang Xu, Yuhong Yang

reinforcement-learning benchmarks

arXiv Machine Learning

Jun 2

Tree-Guided Identify-Then-Exploit: A Unified Framework of Best Arm Identification and Regret Minimization for Dueling Bandits

arXiv:2606. 01799v1 Announce Type: new Abstract: We study $N$-armed stochastic dueling bandits under the Condorcet-winner assumption, where three widely adopted objectives are considered: best-arm identification (BAI), weak regret, and strong regret.

By Pu Wang, Yao-Xiang Ding

arXiv Machine Learning

Jun 2

Finite-Time Regret Analysis of Retry-Aware Bandits

arXiv:2605. 20854v2 Announce Type: replace Abstract: We study a stochastic bandit algorithm motivated by retry-aware objectives that value the best outcome among multiple attempts, such as pass@$k$ and max@$k$.

By Bingkui Tong, Junpei Komiyama, Soichiro Nishimori, Paavo Parmas

reinforcement-learning

arXiv AI

Jun 17

Optimism Stabilizes Thompson Sampling for Adaptive Inference

arXiv:2602. 06014v2 Announce Type: replace-cross Abstract: Thompson sampling (TS) is widely used for stochastic multi-armed bandits, yet its inferential properties under adaptive data collection are subtle.

By Shunxing Yan, Han Zhong

arXiv AI

Aug 12

Robust Multi-Agent Bandits with Heavy-Tailed Rewards and Information Asymmetry

arXiv:2608. 10529v1 Announce Type: cross Abstract: The multi-armed bandit problem is a central framework in sequential decision-making, extensively studied under sub-Gaussian reward assumptions.

By Daphne Feng, Ricardo Parada, Lily Jiang, Sophia Yi, William Chang

agents reinforcement-learning

Related stories

Best Arm Identification with Minimal Regret

Multi-Armed Bandits with Arriving Arms: Sequential Screening, Dynamic Regret, and Sublinear Guarantees

Tree-Guided Identify-Then-Exploit: A Unified Framework of Best Arm Identification and Regret Minimization for Dueling Bandits

Finite-Time Regret Analysis of Retry-Aware Bandits

Optimism Stabilizes Thompson Sampling for Adaptive Inference

Robust Multi-Agent Bandits with Heavy-Tailed Rewards and Information Asymmetry