What it does
Practical_RL is an open course on reinforcement learning, the branch of AI where a program learns by trying actions and getting rewards. It is taught on campus at HSE and the Yandex School of Data Analysis and set up for online students.
Each week has lectures, seminars and homework, starting with the basics and moving to deep learning methods. Every major idea comes with a practical exercise.
Notebooks can be opened in Google Colab in a browser, or run on your own computer.
Who it's for
Students and self-learners with some programming and maths background.
Can I use it without coding?
Developers only. The exercises involve writing Python code. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Web browser, Mac, Windows, Linux
- Computer
- An ordinary computer is fine
- API key
- Not needed
Try it
- Open the course page on GitHub and read the week one materials.
- Open a notebook in Google Colab, or install the course tools on your own computer.
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 (Unlicense): Public domain: no restrictions at all.
- More on staying safe
Where people are talking about it
- Practical RL – A course in reinforcement learning in the wildHacker News · Apr 2017