yandexdataschool/Practical_RL
A course in reinforcement learning in the wild
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.
Stars
6,460
Forks
1,796
Language
Jupyter Notebook
License
Unlicense
Category
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.
Compare
Related frameworks
DLR-RM/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
google-deepmind/dm_control
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning...
Denys88/rl_games
RL implementations
pytorch/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
Stable-Baselines-Team/stable-baselines3-contrib
Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code