arXiv preprint 2025 / 强化学习方法 / 自探索数据采集

World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training

作者：Junjin Xiao, Yandan Yang, Xinyuan Chang, Ronghan Chen, Feng Xiong, Mu Xu, Wei-Shi Zheng, Qing Zhang · 单位：School of Computer Science and Engineering, Sun Yat-sen University, China, AMap, Alibaba Group Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China · 会议/期刊：arXiv preprint 2025 · 方向：强化学习方法 / 自探索数据采集 · 发布日期：2025-09-29

视觉语言动作强化学习方法高效训练强化学习世界模型自探索数据采集数据采集
新标签打开 AlphaXiv新标签打开 Code
World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training figure
AlphaXiv 中文概览（可滚动查看）