UFO: A General Unsupervised Reinforcement Learning Framework for Humanoid Control
Technical report
Authors & affiliations (1)
Author order: Team authorship
- First published
- Not provided
- Latest paper revision
- Not provided
- Venue
- Not provided
Model family: UFO is an unsupervised reinforcement-learning framework for humanoid whole-body control. It implements Forward–Backward and TeCH training and supports motion tracking, goal reaching and reward-conditioned behavior. The published G1 FB policy was tested on hardware.
Technical report
Author order: Team authorship
Verified on · 2026-11-21
| File | Access | Weights license | Commercial use |
|---|---|---|---|
| Unitree G1 FB · ≈192M steps | Access | Weights license | Commercial use ProhibitedTerms Verified on · 2026-11-21 |
SourceVerified on · 2026-11-21
Available weights or code do not establish plug-and-play robot compatibility. Check the required configuration, data and interfaces in the source documentation.
Actions
Humanoid
Reinforcement learning