arXiv AI August 14, 2026 By William Overman, Mohsen Bayati

Annealed Softmax Greedy in Many-Armed Bayesian Bandits

arXiv:2605. 31034v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) and group-based policy optimization methods such as GRPO update a stochastic policy by sampling multiple completions per prompt and increasing the policy's probability on those with higher reward, regularized by a KL penalty toward a reference policy.

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

reinforcement-learning

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 Machine Learning

Jul 21

Rationalizing Boltzmann Rationality: An Axiomatic Characterization of Entropy-Regularized Policies

arXiv:2607. 17316v1 Announce Type: new Abstract: The softmax policy $\pi(a \mid s) \propto \exp(\beta Q(s,a))$ is the default model of stochastic choice in reinforcement learning (RL).

By Silviu Pitis

agents reinforcement-learning

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 Machine Learning

Jun 19

Stabilizing Bandits using Regularization: Precise Regret and A Quantitative Central Limit Theorem

arXiv:2603. 10184v2 Announce Type: replace-cross Abstract: Statistical inference with bandit data presents fundamental challenges owing to adaptive sampling, which violates the independence assumptions underlying classical asymptotic theory.

By Budhaditya Halder, Ishan Sengupta, Koustav Chowdhury, Samya Praharaj, Koulik Khamaru

reinforcement-learning safety

arXiv AI

Jul 15

Learning When to Trust in Contextual Social Bandits

arXiv:2603. 13356v2 Announce Type: replace Abstract: Robust reinforcement learning typically assumes that feedback sources are either globally trustworthy or corrupted within a fixed global budget.

By Majid Ghasemi, Mark Crowley

reinforcement-learning safety

arXiv Machine Learning

1d ago

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

Related stories

Finite-Time Regret Analysis of Retry-Aware Bandits

Rationalizing Boltzmann Rationality: An Axiomatic Characterization of Entropy-Regularized Policies

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

Stabilizing Bandits using Regularization: Precise Regret and A Quantitative Central Limit Theorem

Learning When to Trust in Contextual Social Bandits

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