DLR-RM/stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

76
/ 100
Verified

This is a tool for machine learning researchers and practitioners working with Reinforcement Learning (RL). It provides reliable, tested implementations of various RL algorithms. You input a defined environment and an RL algorithm, and it outputs a trained agent that can learn to make decisions within that environment.

12,878 stars. Used by 12 other packages. Actively maintained with 2 commits in the last 30 days. Available on PyPI.

Use this if you are a researcher or advanced practitioner who needs robust, benchmarked reinforcement learning algorithms to develop and test new ideas or compare against existing approaches.

Not ideal if you are new to Reinforcement Learning and lack fundamental knowledge, as this library assumes prior understanding.

Reinforcement Learning AI Research Algorithm Prototyping Decision Making Systems Agent Training
Maintenance 13 / 25
Adoption 15 / 25
Maturity 25 / 25
Community 23 / 25

How are scores calculated?

Stars

12,878

Forks

2,081

Language

Python

License

MIT

Last pushed

Feb 21, 2026

Commits (30d)

2

Dependencies

6

Reverse dependents

12

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/DLR-RM/stable-baselines3"

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