Beyond Human Demonstrations: Diffusion-Based Reinforcement Learning to Generate Data for VLA Training

作者：Rushuai Yang, Hangxing Wei, Ran Zhang, Zhiyuan Feng, Xiaoyu Chen, Tong Li, Chuheng Zhang, Li Zhao, Jiang Bian, Xiu Su, Yi Chen · 单位：Hong Kong University of Science and Technology, Hong Kong, China, Microsoft Research Asia, Beijing, China, Wuhan University, Wuhan, China, University of Chinese Academy of Sciences, Beijing, China, Tsinghua University, Beijing, China, Big Data Institute, Central South University, Changsha, China · 会议/期刊：arXiv preprint 2025 · 方向：自探索数据采集 · 发布日期：2025-09-24