Hwhitetooth/jax_muzero

An implementation of MuZero in JAX.

39
/ 100
Emerging

This project provides an advanced artificial intelligence agent, MuZero, capable of learning to master complex games and decision-making tasks without being told the rules. It takes raw observations from an environment, such as a game screen, and outputs optimal actions to achieve high scores or desired outcomes. Developers and researchers working on cutting-edge reinforcement learning applications would use this for training AI agents.

No commits in the last 6 months.

Use this if you are a machine learning researcher or developer working with reinforcement learning and want to experiment with or apply a JAX-based implementation of the MuZero algorithm, especially for tasks like game AI or sequential decision-making.

Not ideal if you are looking for a pre-trained, plug-and-play AI solution for a specific problem or if you are not familiar with deep reinforcement learning concepts and JAX.

reinforcement-learning game-ai jax-development ai-research deep-learning-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

57

Forks

9

Language

Python

License

MIT

Last pushed

Nov 08, 2022

Commits (30d)

0

Get this data via API

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

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