What it does
Reinforcement learning is a way of training AI by trial and error, for example learning to play a video game by earning points. CleanRL offers clear versions of well-known methods for doing this.
Each method lives in a single file, so readers can see every detail in one place. Its makers say this makes it a good reference for learning how the methods really work.
It includes tools for logging experiments and recording gameplay videos, and can be scaled up to run many experiments in the cloud.
Who it's for
Students and researchers studying reinforcement learning.
Can I use it without coding?
Developers only. You run and read Python scripts; it is not meant to be used as a ready-made app. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Mac, Linux, Cloud
- 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.
- No standard license listed. Check the GitHub page before using it for business.
- More on staying safe