What it does
AReaL is infrastructure for training large AI models using reinforcement learning, a way of teaching models by rewarding good results.
It is built to be fully asynchronous, which its makers say makes training fast and able to scale, and it is aimed at reasoning and agent-style models.
It was originally developed by researchers at Tsinghua University and Ant Group.
Who it's for
Researchers and engineers training reasoning or agent AI models with reinforcement learning.
Can I use it without coding?
Developers only. It is training infrastructure used by writing code and needs powerful hardware. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Linux, Server
- Computer
- Works best on a powerful computer or one with a graphics card (GPU)
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe
Where people are talking about it
- AReaL: A Large-Scale Asynchronous Reinforcement Learning SystemResearch paper · May 2025