Hugging Face Trending Papers August 18, 2026

Toward the Optimal Regret-Instability Trade-off in Multi-Armed Bandits

Read the original on Hugging Face Trending Papers →

Multi-armed bandit algorithms are evaluated by regret, yet comparable regret can coexist with different allocations across independent runs. We study the trade-off between worst-case regret $\mathcal{R}_{K,T}$ and instability $\mathcal S_{K,T}$, defined as the largest standard deviation of a terminal pull count, for $K$ arms and $T$ rounds.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

reinforcement-learning

arXiv Machine Learning

Aug 19

Toward the Optimal Regret-Instability Trade-off in Multi-Armed Bandits

arXiv:2608. 17841v1 Announce Type: cross Abstract: Multi-armed bandit algorithms are evaluated by regret, yet comparable regret can coexist with different allocations across independent runs.

By Kaifei Wang, Yinyu Ye, Han Zhong

reinforcement-learning

arXiv Machine Learning

Aug 18

Does 1/2-Tsallis-INF Also Work Well for Best-Arm Identification?

arXiv:2608. 15365v1 Announce Type: new Abstract: Regret minimization (RM) and best-arm identification (BAI) are two fundamental objectives in multi-armed bandits.

By Jingxin Zhan, Yuze Han, Zhihua Zhang

diffusion safety

arXiv Machine Learning

Jun 29

Learning in Markovian bandits with non-observable states and constrained decision epochs

arXiv:2606. 27448v1 Announce Type: new Abstract: This paper studies the problem of regret minimization in Markovian bandits with \emph{non-observable states} and possibly \emph{constrained} decision epochs.

By Thomas Hira, Victor Boone, Urtzi Ayesta, Ina Maria Verloop

reinforcement-learning benchmarks safety

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 Machine Learning

Aug 18

Last-Iterate Analyses of FTRL with the 1/2-Tsallis Entropy in Stochastic Bandits

arXiv:2510. 22819v3 Announce Type: replace Abstract: The convergence analysis of online learning algorithms is central to machine learning theory, where the last-iterate convergence is particularly important, as it captures the learner's actual decisions and describes the evolution of the learning process over time.

By Jingxin Zhan, Yuze Han, Zhihua Zhang

safety

arXiv Machine Learning

Jul 23

Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence

arXiv:2607. 19854v1 Announce Type: new Abstract: We study horizon-free regret minimization for finite-horizon time-homogeneous tabular Markov decision processes with $S$ states, $A$ actions, horizon $H$, and per-trajectory total reward bounded by $1$.

By Runlong Zhou, Zihan Zhang, Maryam Fazel, Simon S. Du

reinforcement-learning

One email a morning, machine-written

Related stories

Toward the Optimal Regret-Instability Trade-off in Multi-Armed Bandits

Does 1/2-Tsallis-INF Also Work Well for Best-Arm Identification?

Learning in Markovian bandits with non-observable states and constrained decision epochs

Optimism Stabilizes Thompson Sampling for Adaptive Inference

Last-Iterate Analyses of FTRL with the 1/2-Tsallis Entropy in Stochastic Bandits

Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence