yandexdataschool/Practical_RL

A course in reinforcement learning in the wild

64
/ 100
Established

This course helps aspiring practitioners understand how to develop intelligent agents that learn optimal behaviors through trial and error in various environments. It takes learners from foundational concepts like decision processes and value-based methods to advanced topics such as deep reinforcement learning, policy gradient methods, and model-based RL. It's designed for anyone interested in building systems that can make sequential decisions to achieve goals, like autonomous robots, game AI, or resource management.

6,460 stars. Actively maintained with 2 commits in the last 30 days.

Use this if you want to learn the practical skills and theoretical background necessary to solve real-world problems using reinforcement learning.

Not ideal if you're looking for a quick API reference or a simple 'black box' solution without understanding the underlying principles.

AI-development autonomous-systems sequential-decision-making machine-learning-engineering control-systems
No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

6,460

Forks

1,796

Language

Jupyter Notebook

License

Unlicense

Last pushed

Mar 05, 2026

Commits (30d)

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yandexdataschool/Practical_RL"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.