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.

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 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 AI

Sep 24

Softmax gradient policy for variance minimization and risk-averse multi armed bandits

The paper introduces a new algorithm for the Multi‑Armed Bandit problem that prioritizes selecting the arm with the lowest variance rather than the highest expected reward, using a softmax policy parameterization. It constructs an unbiased estimate of the minimal‑variance objective by drawing two independent samples from the chosen arm and proves convergence under natural conditions. Numerical experiments demonstrate the algorithm’s practical behavior and provide implementation guidance, while also addressing general risk‑aware trade‑offs between average reward and variance.

By Gabriel Turinici

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

1d ago

Regret Analysis of Retry-Based Bandits

arXiv:2605.20854v3 Announce Type: replace Abstract: We provide the first regret analysis of ReMax in stochastic multi-armed bandits. Originally introduced for reinforcement learning, ReMax is motivat...

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

reinforcement-learning

arXiv Machine Learning

23h ago

Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation: The Case of Multi-Armed Bandits

arXiv:2505. 03155v2 Announce Type: replace Abstract: Policy gradient (PG) methods have played an essential role in the empirical successes of reinforcement learning.

By Max Qiushi Lin, Jincheng Mei, Matin Aghaei, Michael Lu, Bo Dai, Alekh Agarwal, Dale Schuurmans, Csaba Szepesvari, Sharan Vaswani

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

One email a morning, machine-written

Related stories

Finite-Time Regret Analysis of Retry-Aware Bandits

Softmax gradient policy for variance minimization and risk-averse multi armed bandits

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

Regret Analysis of Retry-Based Bandits

Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation: The Case of Multi-Armed Bandits

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