ethanluoyc/magi

Reinforcement learning library in JAX.

30
/ 100
Emerging

This library helps machine learning researchers and practitioners implement and experiment with reinforcement learning (RL) algorithms. It takes your defined RL environments and agent architectures as input, and outputs trained models capable of learning optimal strategies. Researchers, AI developers, and academics focusing on advanced machine learning would use this to build and test new RL systems.

101 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or developer working with reinforcement learning and need a flexible, JAX-based framework that offers agents not found in DeepMind's Acme library, along with experiment logging integrations.

Not ideal if you are looking for a stable, production-ready library, as it is in alpha development and expects breaking changes.

reinforcement-learning machine-learning-research ai-development algorithm-prototyping
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

101

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Oct 22, 2023

Commits (30d)

0

Get this data via API

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

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