arXiv Machine Learning June 5, 2026 By Paavo Parmas, Yongmin Kim, Kohsei Matsutani, Shota Takashiro, Soichiro Nishimori, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

OrderGrad: Optimizing Beyond the Mean with Order-Statistic Policy Gradient Estimation

Read the original on arXiv Machine Learning →

arXiv:2606. 06096v1 Announce Type: new Abstract: Policy-gradient methods usually optimize expected return, but many real world applications care about distributional properties of returns: tail risk, outlier robustness, or best-of-K discovery.

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

arXiv Machine Learning

6d ago

A New First-Order Meta-Learning Algorithm with Convergence Guarantees

arXiv:2409. 03682v2 Announce Type: replace Abstract: Learning new tasks by leveraging prior experience is a fundamental trait of intelligent systems.

By El Mahdi Chayti, Martin Jaggi

llms efficiency safety

arXiv Machine Learning

Jul 14

Rank-Conditioned Sample Reuse for the Plackett--Luce Best-of-$K$ Objective

arXiv:2607. 11146v1 Announce Type: new Abstract: We study the coupled objective J_K^WOR = E_{S ~ PL-WOR_K}[max_{i in S} R_i]: the expected maximum reward of a size-K Plackett-Luce draw without replacement, the law of Gumbel-Top-K / Stochastic Beam Search decoding.

By Melveena Jolly, Midhun Xavier

arXiv AI

Jun 11

Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems

arXiv:2505. 15201v5 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) algorithms sample multiple n>1 solution attempts for each problem and reward them independently.

By Christian Walder, Deep Karkhanis

llms reinforcement-learning

arXiv Machine Learning

Jun 5

On Advantage Estimates for Max@K Policy Gradients

arXiv:2606. 06080v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards is widely used for post-training reasoning models, but sparse outcome rewards make exploration difficult.

By Shota Takashiro, Soichiro Nishimori, Paavo Parmas, Yongmin Kim, Kohsei Matsutani, Gouki Minegishi, Yusuke Iwasawa, Takeshi Kojima, Yutaka Matsuo

llms reinforcement-learning

arXiv Machine Learning

Jun 2

Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback

arXiv:2606. 01081v1 Announce Type: new Abstract: Decision-focused learning (DFL) trains predictive models by optimizing downstream decision quality rather than standalone prediction accuracy.

By Wyame Benslimane, Tinghan Ye, Pascal Van Hentenryck, Paul Grigas

reinforcement-learning benchmarks

arXiv Machine Learning

Jul 2

Generative Refinement for Low-Budget Black-Box Optimization

arXiv:2607. 00691v1 Announce Type: new Abstract: Black-box optimization is a fundamental science and engineering tool that makes it possible to optimize objectives without gradient information.

By Edouard R. Dufour, Pascal Fua

Related stories

A New First-Order Meta-Learning Algorithm with Convergence Guarantees

Rank-Conditioned Sample Reuse for the Plackett--Luce Best-of-$K$ Objective

Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems

On Advantage Estimates for Max@K Policy Gradients

Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback

Generative Refinement for Low-Budget Black-Box Optimization