English
Related papers

Related papers: LLMs Can Learn to Reason Via Off-Policy RL

200 papers

Supervised fine-tuning (SFT) is the predominant method for adapting large language models (LLMs), yet it often struggles with generalization compared to reinforcement learning (RL). In this work, we posit that this performance disparity…

Computation and Language · Computer Science 2026-02-03 Rui Ming , Haoyuan Wu , Shoubo Hu , Zhuolun He , Bei Yu

Offline reinforcement learning requires reconciling two conflicting aims: learning a policy that improves over the behavior policy that collected the dataset, while at the same time minimizing the deviation from the behavior policy so as to…

Machine Learning · Computer Science 2021-10-13 Ilya Kostrikov , Ashvin Nair , Sergey Levine

Recent advances in large reasoning models (LRMs) demonstrate that sophisticated behaviors such as multi-step reasoning and self-reflection can emerge via reinforcement learning with verifiable rewards~(\textit{RLVR}). However, existing…

Machine Learning · Computer Science 2025-06-24 Jianhao Yan , Yafu Li , Zican Hu , Zhi Wang , Ganqu Cui , Xiaoye Qu , Yu Cheng , Yue Zhang

A key problem in off-policy Reinforcement Learning (RL) is the mismatch, or distribution shift, between the dataset and the distribution over states and actions visited by the learned policy. This problem is exacerbated in the fully offline…

Machine Learning · Computer Science 2023-11-28 Melrose Roderick , Gaurav Manek , Felix Berkenkamp , J. Zico Kolter

We introduce a novel reinforcement learning algorithm (AGRO, for Any-Generation Reward Optimization) for fine-tuning large-language models. AGRO leverages the concept of generation consistency, which states that the optimal policy satisfies…

Machine Learning · Computer Science 2025-04-01 Yunhao Tang , Taco Cohen , David W. Zhang , Michal Valko , Rémi Munos

Standard human preference-based alignment methods, such as Reinforcement Learning from Human Feedback (RLHF), are a cornerstone for aligning large language models (LLMs) with human values. However, these methods typically assume that…

Artificial Intelligence · Computer Science 2026-03-02 Xiaoyang Cao , Zelai Xu , Mo Guang , Kaiwen Long , Michiel A. Bakker , Yu Wang , Chao Yu

Large Language Models (LLMs) have shown impressive reasoning capabilities in well-defined problems with clear solutions, such as mathematics and coding. However, they still struggle with complex real-world scenarios like business…

Computation and Language · Computer Science 2025-05-29 Xiaoqian Liu , Ke Wang , Yongbin Li , Yuchuan Wu , Wentao Ma , Aobo Kong , Fei Huang , Jianbin Jiao , Junge Zhang

On-policy distillation (OPD) has become a promising paradigm for reasoning-oriented post-training of large language models (LLMs), especially when combined with reinforcement learning from verifiable rewards (RLVR). Existing OPD methods…

Most prior approaches to offline reinforcement learning (RL) have taken an iterative actor-critic approach involving off-policy evaluation. In this paper we show that simply doing one step of constrained/regularized policy improvement using…

Machine Learning · Computer Science 2021-12-06 David Brandfonbrener , William F. Whitney , Rajesh Ranganath , Joan Bruna

Supervised imitation-based approaches are often favored over off-policy reinforcement learning approaches for learning policies offline, since their straightforward optimization objective makes them computationally efficient and stable to…

Machine Learning · Computer Science 2025-12-30 Adam Jelley , Trevor McInroe , Sam Devlin , Amos Storkey

Knowledge distillation improves large language model (LLM) reasoning by compressing the knowledge of a teacher LLM to train smaller LLMs. On-policy distillation advances this approach by having the student sample its own trajectories while…

Machine Learning · Computer Science 2026-03-23 Siyan Zhao , Zhihui Xie , Mengchen Liu , Jing Huang , Guan Pang , Feiyu Chen , Aditya Grover

Offline learning is a key part of making reinforcement learning (RL) useable in real systems. Offline RL looks at scenarios where there is data from a system's operation, but no direct access to the system when learning a policy. Recent…

Machine Learning · Computer Science 2021-03-18 Arthur Argenson , Gabriel Dulac-Arnold

Off-policy Learning to Rank (LTR) aims to optimize a ranker from data collected by a deployed logging policy. However, existing off-policy learning to rank methods often make strong assumptions about how users generate the click data, i.e.,…

Machine Learning · Computer Science 2023-10-31 Zeyu Zhang , Yi Su , Hui Yuan , Yiran Wu , Rishab Balasubramanian , Qingyun Wu , Huazheng Wang , Mengdi Wang

We evaluate benchmark deep reinforcement learning algorithms on the task of portfolio optimisation using simulated data. The simulator to generate the data is based on correlated geometric Brownian motion with the Bertsimas-Lo market impact…

Computational Engineering, Finance, and Science · Computer Science 2025-08-07 Chung I Lu

Large language models are increasingly trained via reinforcement learning for personalized recommendation tasks, but standard methods like GRPO rely on sparse, sequence-level rewards. These obscure which tokens actually contribute to…

Artificial Intelligence · Computer Science 2026-05-08 Abhijnan Nath , Alireza Bagheri Garakani , Tianchen Zhou , Fan Yang , Yan Gao , Nikhil Krishnaswamy

This paper introduces two simple techniques to improve off-policy Reinforcement Learning (RL) algorithms. First, we formulate off-policy RL as a stochastic proximal point iteration. The target network plays the role of the variable of…

Machine Learning · Computer Science 2020-08-04 Marco Maggipinto , Gian Antonio Susto , Pratik Chaudhari

Offline reinforcement learning (RL purely from logged data) is an important avenue for deploying RL techniques in real-world scenarios. However, existing hyperparameter selection methods for offline RL break the offline assumption by…

Recently, Offline Reinforcement Learning (RL) has achieved remarkable progress with the emergence of various algorithms and datasets. However, these methods usually focus on algorithmic advancements, ignoring that many low-level…

Machine Learning · Computer Science 2023-06-02 Bingyi Kang , Xiao Ma , Yirui Wang , Yang Yue , Shuicheng Yan

Post training via GRPO has demonstrated remarkable effectiveness in improving the generation quality of flow-matching models. However, GRPO suffers from inherently low sample efficiency due to its on-policy training paradigm. To address…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Liyu Zhang , Kehan Li , Tingrui Han , Tao Zhao , Yuxuan Sheng , Shibo He , Chao Li

Large Language Models (LLMs) have shown promise in solving complex mathematical problems, yet they still fall short of producing accurate and consistent solutions. Reinforcement Learning (RL) is a framework for aligning these models with…

Artificial Intelligence · Computer Science 2026-02-10 Ali Hatamizadeh , Shrimai Prabhumoye , Igor Gitman , Ximing Lu , Seungju Han , Wei Ping , Yejin Choi , Jan Kautz
‹ Prev 1 4 5 6 7 8 10 Next ›