MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models

作者：Han Zhao, Wenxuan Song, Donglin Wang, Xinyang Tong, Pengxiang Ding, Xuelian Cheng, Zongyuan Ge · 单位：Zhejiang University, China, MiLAB, Westlake University, China, AIM Lab, Faculty of IT, Monash University, Australia, HKUST(GZ), China · 会议/期刊：ICRA 2025 · 方向：2025 · 发布日期：2025