Parkour in the Wild: Learning a General and Extensible Agile Locomotion Policy Using Multi-expert Distillation and RL Fine-tuning

作者：Nikita Rudin, Junzhe He, Joshua Aurand, Marco Hutter · 单位：Robotic Systems Lab, ETH Zurich, NVIDIA Switzerland · 会议/期刊：arXiv preprint · 方向：2025 · 发布日期：2025