tuotuoLyu/FPO
Agent
Can I trust it?
Worth a closer look before you use it.
Warnings Check
Very new: it was created 2 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change 2 days ago.
Licence OK
MIT: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
Official code for Flow Policy Optimization (FPO), a reinforcement fine-tuning method for the flow-matching VLA policy pi0. It trains a latent actor with PPO-style clipped updates, using a likelihood-free ratio based on per-sample changes in the conditional flow-matching loss and…
Who it's for
Robotics researchers and ML engineers fine-tuning vision-language-action policies such as pi0 with reinforcement learning in JAX
How to use it
Install
pip install -e .From its README. Check it there before running it.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up tuotuoLyu/FPO in my project. Follow its README: https://github.com/tuotuoLyu/FPO. Explain each step and check it is safe before running anything.
Star curve
Alternatives
Similar projects named in its profile. Each link searches the directory.
Get alerts for repos like this
We'll email you when something in AI agents starts rising. Free, once a week, only what matches.
23,098 GitHub repos watched and ranked every hour. Figures as of 31 October 2026.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/tuotuoLyu/FPO?ref=badge)Similar repos
- tuotuoLyu/ForesightSafety-VLA
A safety-focused diagnostic benchmark for vision-language-action robot policies on the RoboTwin simulator. It provides 66 safety-augmented scenarios across 13 hazard categories, controlled variation o
- ZhuoyangLiu2005/agentic-wam
A research codebase for AW-0, a world action model for robot manipulation that jointly denoises a code plan, future video and robot actions in one mixture-of-transformers. It includes pretraining, pos
- zfkarl/RSIPO
A research framework for agentic reinforcement learning in which agent skills and the policy co-evolve during training. The policy summarizes its own trajectories into skills, and a skill-enhanced cop
- zgcagi/Harness-RSI
A survey and companion reading list on how execution experience becomes persistent harness state for a fixed base model. It covers update targets, evolutionary search, theory, evaluation, applications
- liuyisen-bin/transformer-sru-lys
Hierarchical reinforcement learning navigation for the Unitree G1 29DOF robot. A LiDAR CNN, spatial Transformer and SRU policy outputs velocity commands at 5 Hz for a frozen low-level controller at 50
- NVlabs/ASPIRE
A research framework for robotics in which an LLM-driven coding agent refines sensorimotor skills through iterative debugging and evolutionary search instead of gradient-based training. Evaluated on L