FreeAIRepo
Training & fine-tuning

tuotuoLyu/FPO

Official code for "Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models" (ICRA 2026): Flow Policy Optimization for pi0

Commercial OK · MITPython

Rising: created 6d ago

  • 129stars
  • 4forks
  • 0open issues
  • updated 6d ago

About FPO

FPO is a free, open-source machine learning tool by tuotuoLyu, written mainly in Python. Official code for "Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models" (ICRA 2026): Flow Policy Optimization for pi0. It has 129 GitHub stars and 4 forks, and was last updated 6d ago. It's released under the MIT license, a standard open-source license.

Similar free tools

All Training & fine-tuning tools →

FPO FAQ

Can I use FPO commercially?

Yes. MIT is a permissive license: commercial use is allowed as long as you keep the license notice. This is a plain-English summary, not legal advice.

Is FPO free?

Yes. FPO is open source and free to use. It's released under the MIT license, a standard open-source license.

Does FPO run on a Mac?

The project doesn't say. Check its installation guide before you start.

Does FPO need a GPU?

The project doesn't state hardware needs. AI models generally run much faster with a GPU.

Is FPO still maintained?

Yes. It was last updated 6d ago and has 0 open issues on GitHub.

What are alternatives to FPO?

Similar free, open-source tools include transformers, scikit-learn, keras, stable-baselines3.

Related topics

Maintain FPO? Add a FreeAIRepo badge to your README
Featured on FreeAIRepo
[![Featured on FreeAIRepo](https://www.freeairepo.com/badge/tuotuoLyu/FPO.svg)](https://www.freeairepo.com/repo/tuotuoLyu/FPO)