Toni-SM/skrl

Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments

74
/ 100
Verified

This library helps machine learning engineers and researchers design and train reinforcement learning agents for complex tasks like robotics control or game AI. You provide simulated environments and task definitions, and it outputs trained agent policies that can make decisions to achieve goals within those environments. It's built for practitioners who develop and experiment with advanced AI behaviors.

1,011 stars. Actively maintained with 8 commits in the last 30 days. Available on PyPI.

Use this if you are a machine learning engineer working on reinforcement learning projects and need a flexible, modular toolkit to implement and test various algorithms and environments.

Not ideal if you are looking for a pre-trained, ready-to-deploy AI solution for a specific problem without needing to customize or train agents.

reinforcement-learning robotics-simulation game-ai autonomous-systems agent-training
Maintenance 17 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 22 / 25

How are scores calculated?

Stars

1,011

Forks

133

Language

Python

License

MIT

Last pushed

Feb 24, 2026

Commits (30d)

8

Dependencies

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/Toni-SM/skrl"

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