English
Related papers

Related papers: Stable Asynchrony: Variance-Controlled Off-Policy …

200 papers

Model-based offline reinforcement Learning (RL) is a promising approach that leverages existing data effectively in many real-world applications, especially those involving high-dimensional inputs like images and videos. To alleviate the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Shenghua Wan , Ziyuan Chen , Le Gan , Shuai Feng , De-Chuan Zhan

While flow matching is elegant, its reliance on single-sample conditional velocities leads to high-variance training targets that destabilize optimization and slow convergence. By explicitly characterizing this variance, we identify 1) a…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Donglin Yang , Yongxing Zhang , Xin Yu , Liang Hou , Xin Tao , Pengfei Wan , Xiaojuan Qi , Renjie Liao

Continual supervised fine-tuning (SFT) is the de facto recipe for adapting large language models (LLMs) to a stream of downstream tasks, but it suffers from catastrophic forgetting of earlier capabilities. Recent work shows that on-policy…

Machine Learning · Computer Science 2026-05-29 Yan Chen , Taojie Zhu , Meng Zhang , Xin Chen , Jiaqi Huang , Dongyang Xu , Yizhi Wang

Reinforcement learning has become a cornerstone for aligning and unlocking the reasoning capabilities of large-scale models. At its core, the training loop of GRPO and its variants alternates between rollout sampling and policy update.…

Machine Learning · Computer Science 2026-05-21 Xikai Zhang , Yongzhi Li , Likang Xiao , Yingze Zhang , Yanhua Cheng , Quan Chen , Peng Jiang , Wenjun Wu , Liu Liu

Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications. Previous primal-dual style approaches suffer from instability issues and lack optimality…

Machine Learning · Computer Science 2022-06-20 Zuxin Liu , Zhepeng Cen , Vladislav Isenbaev , Wei Liu , Zhiwei Steven Wu , Bo Li , Ding Zhao

Large Language Models (LLMs) are increasingly deployed in business-critical domains such as finance, education, healthcare, and customer support, where users expect consistent and reliable recommendations. Yet LLMs often exhibit variability…

Machine Learning · Computer Science 2026-04-20 Sonal Prabhune , Balaji Padmanabhan , Kaushik Dutta

We revisit policy-gradient optimization for Large Language Models (LLMs) from a single-stream perspective. Prevailing group-based methods like GRPO reduce variance with on-the-fly baselines but suffer from critical flaws: frequent…

Machine Learning · Computer Science 2025-09-24 Zhongwen Xu , Zihan Ding

Vision-Language-Action (VLA) models based on flow matching have shown excellent performance in general-purpose robotic manipulation tasks. However, the action accuracy of these models on complex downstream tasks is unsatisfactory. One…

Robotics · Computer Science 2025-09-05 Hongyin Zhang , Shiyuan Zhang , Junxi Jin , Qixin Zeng , Yifan Qiao , Hongchao Lu , Donglin Wang

Reinforcement Learning with Verifiable Rewards (RLVR) has become a promising paradigm for scaling reasoning capabilities of Large Language Models (LLMs). However, the sparsity of binary verifier rewards often leads to low efficiency and…

Machine Learning · Computer Science 2026-05-22 Shuo Yang , Jinda Lu , Kexin Huang , Chiyu Ma , Shaohang Wei , Yuyang Liu , Guoyin Wang , Jingren Zhou , Li Yuan

We seek to understand what facilitates sample-efficient learning from historical datasets for sequential decision-making, a problem that is popularly known as offline reinforcement learning (RL). Further, we are interested in algorithms…

Machine Learning · Computer Science 2024-02-07 Thanh Nguyen-Tang , Raman Arora

Reinforcement learning (RL) is a key paradigm for post-training large language models (LLMs), but the widely used Group Relative Policy Optimization (GRPO) often suffers from entropy collapse: exploration quickly disappears, policies…

Machine Learning · Computer Science 2026-05-19 Chen Wang , Zhaochun Li , Jionghao Bai , Hexuan Deng , Ge Lan , Yue Wang

Deep reinforcement learning has been able to solve various tasks successfully, however, due to the construction of policy gradient and training dynamics, tuning deep reinforcement learning models remains challenging. As one of the most…

Machine Learning · Computer Science 2026-02-11 Hanyong Wang , Menglong Yang

Recently, GRPO-based reinforcement learning has shown remarkable progress in optimizing flow-matching models, effectively improving their alignment with task-specific rewards. Within these frameworks, the policy update relies on…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Jing Wang , Jiajun Liang , Jie Liu , Henglin Liu , Gongye Liu , Jun Zheng , Wanyuan Pang , Ao Ma , Zhenyu Xie , Xintao Wang , Meng Wang , Pengfei Wan , Xiaodan Liang

We study the problem of training and fine-tuning expressive policies with online reinforcement learning (RL) given an offline dataset. Training expressive policy classes with online RL present a unique challenge of stable value…

Machine Learning · Computer Science 2026-05-01 Perry Dong , Qiyang Li , Dorsa Sadigh , Chelsea Finn

Existing studies on constrained reinforcement learning (RL) may obtain a well-performing policy in the training environment. However, when deployed in a real environment, it may easily violate constraints that were originally satisfied…

Machine Learning · Computer Science 2024-05-06 Zhongchang Sun , Sihong He , Fei Miao , Shaofeng Zou

Reinforcement Learning (RL) has demonstrated its potential to improve the reasoning ability of Large Language Models (LLMs). One major limitation of most existing Reinforcement Finetuning (RFT) methods is that they are on-policy RL in…

Machine Learning · Computer Science 2025-07-14 Jing Liang , Hongyao Tang , Yi Ma , Jinyi Liu , Yan Zheng , Shuyue Hu , Lei Bai , Jianye Hao

Recently, foundation models such as OpenAI's O1 and O3, along with DeepSeek's R1, have demonstrated strong reasoning capacities and problem-solving skills acquired through large-scale reinforcement learning (RL), with wide applications in…

Machine Learning · Computer Science 2025-04-29 Tianbing Xu

Reinforcement learning (RL) post-training has proven effective at unlocking reasoning, self-reflection, and tool-use capabilities in large language models. As models extend to omni-modal inputs and agentic multi-turn workflows, RL training…

Computation and Language · Computer Science 2026-04-15 Liujie Zhang , Benzhe Ning , Rui Yang , Xiaoyan Yu , Jiaxing Li , Lumeng Wu , Jia Liu , Minghao Li , Weihang Chen , Weiqi Hu , Lei Zhang

Reinforcement learning (RL) is vital for optimizing large language models (LLMs). Recent Group Relative Policy Optimization (GRPO) estimates advantages using multiple on-policy outputs per prompt, leading to high computational costs and low…

Computation and Language · Computer Science 2025-06-12 Siheng Li , Zhanhui Zhou , Wai Lam , Chao Yang , Chaochao Lu

Incorporating prior data into online reinforcement learning accelerates training but typically forces a difficult trade-off between high computational costs and long, multi-stage training pipelines. While fixed-length stabilization phases…

Machine Learning · Computer Science 2026-05-21 Carlo Romeo , Girolamo Macaluso , Alessandro Sestini , Andrew D. Bagdanov