YuvrajSingh-mist/NeatRL

Repository of implementations of classic and sota rl algorithms from scratch in PyTorch

38
/ 100
Emerging

This helps AI researchers and students rapidly experiment with different reinforcement learning (RL) algorithms for training autonomous agents. You input an environment (like a game or a simulation) and a chosen RL algorithm, and it outputs a trained agent capable of performing tasks within that environment, along with visualizations of its learning process. This is for machine learning practitioners focused on developing and evaluating intelligent agent behavior.

221 stars.

Use this if you need to quickly train and compare various reinforcement learning agents in simulated environments like games or physics simulations.

Not ideal if you're looking for a low-code solution for deploying agents in complex real-world systems without prior RL expertise.

AI-research agent-training machine-learning-experiments simulated-environments game-AI
No License No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

221

Forks

21

Language

Python

License

Last pushed

Jan 03, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/YuvrajSingh-mist/NeatRL"

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