UFO FB

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.

Papers & reports (1)

UFO: A General Unsupervised Reinforcement Learning Framework for Humanoid Control

Technical report

Authors & affiliations (1)

Author order: Team authorship

  1. RoboParty Lab Team

    Not provided

First published
Not provided
Latest paper revision
Not provided
Venue
Not provided

Covered model versions

Paper ↗PDF ↗

How to access and use

Public code resources
Public access
Model files
Public access

Training / fine-tuning code

Access
Public access

Verified on · 2026-11-21

Code license
CC BY-NC 4.0

Model files

Model files
Unitree G1 FB · ≈192M stepsAccessWeights licenseCommercial use
ProhibitedTerms

Verified on · 2026-11-21

Release information

SourceVerified on · 2026-11-21

Checks before deployment

Available weights or code do not establish plug-and-play robot compatibility. Check the required configuration, data and interfaces in the source documentation.

Deployment and usage resources

Control and inputs / outputs

Model type
Motion & whole-body control

Scope and training

Output

Actions

Robot form

Humanoid

Training

Reinforcement learning

Submit a source or correction