Awesome Robotics Manipulation · full_paper

Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models

作者：Shuaihang Chen, Feng Gao, Yinuo Chen, Kang Chen, Tonghe Zhang, Hongzhi Zang, Weinan Zhang, Chao Yu, Yu Wang · 单位：Tsinghua University, Harbin Institute of Technology, Peking Unviersity, Carnegie Mellon University, Shanghai AI Laboratory, Zhongguancun Academy · 会议/期刊：arXiv · 日期：2026-02-13 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with RL

模仿学习强化学习视觉语言动作触觉机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models figure
AlphaXiv 中文论文页面（可滚动查看）