English
Related papers

Related papers: Do We Need to Verify Step by Step? Rethinking Proc…

200 papers

Reinforcement learning is structurally harder than supervised learning because the policy changes the data distribution it learns from. The resulting fragility is especially visible in large-model training, where the training and rollout…

Machine Learning · Computer Science 2026-05-13 Rasool Fakoor , Murdock Aubry , Nicholas Stranges , Alexander J. Smola

While reinforcement learning algorithms provide automated acquisition of optimal policies, practical application of such methods requires a number of design decisions, such as manually designing reward functions that not only define the…

Machine Learning · Computer Science 2022-12-29 Tim G. J. Rudner , Vitchyr H. Pong , Rowan McAllister , Yarin Gal , Sergey Levine

In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy using logged trajectory data generated from a different behavior policy, without execution of the target policy.…

Machine Learning · Computer Science 2022-11-04 Jie Wang , Rui Gao , Hongyuan Zha

Offline reinforcement learning refers to the process of learning policies from fixed datasets, without requiring additional environment interaction. However, it often relies on well-defined reward functions, which are difficult and…

Artificial Intelligence · Computer Science 2025-10-13 Xiancheng Gao , Yufeng Shi , Wengang Zhou , Houqiang Li

The evaluation of supervised machine learning models is a critical stage in the development of reliable predictive systems. Despite the widespread availability of machine learning libraries and automated workflows, model assessment is often…

Machine Learning · Computer Science 2026-04-16 Xuanyan Liu , Ignacio Cabrera Martin , Marcello Trovati , Xiaolong Xu , Nikolaos Polatidis

Improving the multi-step reasoning ability of Large Language Models (LLMs) is a critical yet challenging task. The dominant paradigm, outcome-supervised reinforcement learning (RLVR), rewards only correct final answers, often propagating…

Artificial Intelligence · Computer Science 2025-10-14 Beining Wang , Weihang Su , Hongtao Tian , Tao Yang , Yujia Zhou , Ting Yao , Qingyao Ai , Yiqun Liu

Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, but counteracting off-policy bias without exacerbating variance is challenging. Classically, off-policy bias is corrected in a per-decision…

Machine Learning · Computer Science 2025-12-23 Brett Daley , Martha White , Christopher Amato , Marlos C. Machado

Learning-based approaches for solving large sequential decision making problems have become popular in recent years. The resulting agents perform differently and their characteristics depend on those of the underlying learning approach.…

Machine Learning · Computer Science 2020-08-04 Timo P. Gros , Daniel Höller , Jörg Hoffmann , Verena Wolf

Step-by-step verifiers -- also known as process reward models (PRMs) -- are a key ingredient for test-time scaling. PRMs require step-level supervision, making them expensive to train. This work aims to build data-efficient PRMs as…

Machine Learning · Computer Science 2025-12-09 Muhammad Khalifa , Rishabh Agarwal , Lajanugen Logeswaran , Jaekyeom Kim , Hao Peng , Moontae Lee , Honglak Lee , Lu Wang

Multi-turn interaction remains challenging for online reinforcement learning. A common solution is trajectory-level optimization, which treats each trajectory as a single training sample. However, this approach can be inefficient and yield…

Artificial Intelligence · Computer Science 2025-11-18 Yuhan Chen , Yuxuan Liu , Long Zhang , Pengzhi Gao , Jian Luan , Wei Liu

Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning remains challenging. Reinforcement learning has recently emerged as an effective post-training…

Artificial Intelligence · Computer Science 2026-04-14 Shaoan Xie , Lingjing Kong , Xiangchen Song , Xinshuai Dong , Guangyi Chen , Eric P. Xing , Kun Zhang

Rewards and punishments in different forms are pervasive and present in a wide variety of decision-making scenarios. By observing the outcome of a sufficient number of repeated trials, one would gradually learn the value and usefulness of a…

Machine Learning · Computer Science 2019-06-25 Nikki Lijing Kuang , Clement H. C. Leung

Process Reward Models (PRMs) are a powerful mechanism for steering large language model reasoning by providing fine-grained, step-level supervision. However, this effectiveness comes at a significant cost: PRMs require expert annotations…

Machine Learning · Computer Science 2026-05-12 Artyom Gadetsky , Maxim Kodryan , Siba Smarak Panigrahi , Hang Guo , Maria Brbic

AI methods are used in societally important settings, ranging from credit to employment to housing, and it is crucial to provide fairness in regard to algorithmic decision making. Moreover, many settings are dynamic, with populations…

Machine Learning · Computer Science 2022-11-09 Zhun Deng , He Sun , Zhiwei Steven Wu , Linjun Zhang , David C. Parkes

Process reward models (PRMs) rely on high-quality process supervision data, yet existing construction methods often provide limited control over error location, error type, and trajectory consistency. We propose a controllable and…

Artificial Intelligence · Computer Science 2026-05-05 Yinghui Chi , Lucien Wang

Policy gradient methods are widely adopted reinforcement learning algorithms for tasks with continuous action spaces. These methods succeeded in many application domains, however, because of their notorious sample inefficiency their use…

Machine Learning · Statistics 2024-02-20 Davide Mambelli , Stephan Bongers , Onno Zoeter , Matthijs T. J. Spaan , Frans A. Oliehoek

We consider the problem of reinforcement learning when provided with (1) a baseline control policy and (2) a set of constraints that the learner must satisfy. The baseline policy can arise from demonstration data or a teacher agent and may…

Machine Learning · Computer Science 2021-07-13 Tsung-Yen Yang , Justinian Rosca , Karthik Narasimhan , Peter J. Ramadge

Large reasoning models (LRMs) have recently achieved significant progress in complex reasoning tasks, aided by reinforcement learning with verifiable rewards. However, LRMs often suffer from overthinking, expending excessive computation on…

Artificial Intelligence · Computer Science 2025-08-19 Chuhuai Yue , Chengqi Dong , Yinan Gao , Hang He , Jiajun Chai , Guojun Yin , Wei Lin

Large scale reinforcement learning has become a central tool for improving reasoning in large language models. At this scale, generation is often lagged or asynchronous, so updates are performed on data collected by older policies. This…

Machine Learning · Computer Science 2026-05-28 Otmane Sakhi , Aleksei Arzhantsev , Imad Aouali , Flavian Vasile

Language models must be adapted to understand and follow user instructions. Reinforcement learning is widely used to facilitate this -- typically using fixed criteria such as "helpfulness" and "harmfulness". In our work, we instead propose…

Computation and Language · Computer Science 2025-12-02 Vijay Viswanathan , Yanchao Sun , Shuang Ma , Xiang Kong , Meng Cao , Graham Neubig , Tongshuang Wu