Human-in-the-loop Online Rejection Sampling for Robotic Manipulation

作者：Guanxing Lu, Rui Zhao, Haitao Lin, He Zhang, Yansong Tang, Equal contribution Project lead Corresponding author · 单位：Tsinghua Shenzhen International Graduate School, Tencent Robotics X · 会议/期刊：arXiv · 日期：2025-10-30 · 来源：Low-Level Learning-Based Action Modelling / Learning Strategy / RL and IL / IL Pre-training + RL Fine-tuning