arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

期刊&会议

Robotics: Science and Systems · 会议 · Robotics

2026-08-13 至 2026-08-13 收录 1
2510.06710 2026-08-13 cs.RO 版本更新

RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models

RLinf-VLA: 一种用于视觉-语言-动作模型强化学习的统一高效框架

Hongzhi Zang, Mingjie Wei, Si Xu, Yongji Wu, Zhen Guo, Yuanqing Wang, Hao Lin, Peihong Wang, Liangzhi Shi, Yuqing Xie, Zhexuan Xu, Zhihao Liu, Kang Chen, Wenhao Tang, Quanlu Zhang, Weinan Zhang, Chao Yu, Yu Wang

机构 * Tsinghua University(清华大学) Zhongguancun Academy(中关村学院) Infinigence AI Peking University(北京大学) UC Berkeley(加州大学伯克利分校) Harbin Institute of Technology(哈尔滨工程学院) Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)

AI总结 RLinf-VLA是一种统一高效的框架,用于提升视觉-语言-动作模型在具身环境中的强化学习性能,通过统一接口和高效资源分配实现统一和可扩展的训练。

Comments Accepted to RSS 2026. This is the technical report of the RLinf Team, focusing on the algorithm side. For the system-level design, please refer to arXiv:2509.15965. The open-sourced code link: https://github.com/RLinf/RLinf

URL PDF HTML 收藏