# Any2Track: Multi-Expert Policy Distillation for General Motion Tracking in Humanoid Robots

- Source: Guyuehome
- Published: 2026-10-12T04:17:00.000Z
- RoboHot: https://robohot.news/en/items/tmaae1k2tt8ocs9c9q6u01kop
- Original: https://www.guyuehome.com/detail?id=2103920409675067394

## Summary

Any2Track addresses the difficulty of a single reinforcement learning policy handling vastly different motions such as dancing, fighting, and getting up from a fall. It uses a two-stage approach: first training specialized teachers by cluster, then using DAgger to aggregate the teachers' behaviors into a single student network, and it presents G1 simulation comparison results.