mjx-project/mjx

Mjx: A framework for Mahjong AI research

42
/ 100
Emerging

Mjx helps researchers in artificial intelligence (AI) develop and evaluate AI players for Japanese Mahjong (Riichi Mahjong). It takes in game logic and AI decision-making rules, and simulates thousands of Mahjong games very quickly, providing game outcomes and performance metrics. This is for AI researchers and game developers who are creating or refining Mahjong-playing AI.

205 stars. No commits in the last 6 months.

Use this if you are developing or testing Mahjong AI and need a fast, accurate, and scalable game simulator to run many evaluation games.

Not ideal if you are looking for a casual Mahjong game to play yourself, or if you need a simulator for a different variant of Mahjong.

AI-research game-AI Mahjong reinforcement-learning game-simulation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

205

Forks

25

Language

C++

License

MIT

Category

card-game-ai

Last pushed

Apr 19, 2024

Commits (30d)

0

Get this data via API

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

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