Plain-AyI
← All projects
AI models & research

Dopamine

A small research toolkit for trying out ideas in reinforcement learning, where AI learns by trial and error.

Research-backedNew this week

What it does

Dopamine is a research framework for reinforcement learning, a type of AI that learns by trying actions and getting rewards, for example by playing video games.

It aims to be small and easy to understand so researchers can test new ideas quickly. It includes ready-made versions of several well-known learning methods and supports classic Atari games and physics simulations as test worlds.

The README notes it is not an official Google product.

Who it's for

AI researchers and students studying reinforcement learning.

Can I use it without coding?

Developers only. It is Python code meant to be read and changed by researchers. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Linux, Mac
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