liuruoze/mini-AlphaStar

(JAIR'2022) A mini-scale reproduction code of the AlphaStar program. Note: the original AlphaStar is the AI proposed by DeepMind to play StarCraft II. JAIR = Journal of Artificial Intelligence Research.

46
/ 100
Emerging

This project helps researchers and AI practitioners create and train artificial intelligence to play StarCraft II. It takes game replay data as input and produces a trained AI model capable of strategic gameplay. The AI can then be used to simulate game scenarios or compete against other players, offering a practical tool for studying real-time strategy AI.

360 stars. No commits in the last 6 months.

Use this if you are an AI researcher or enthusiast interested in developing and evaluating AI agents for complex real-time strategy games like StarCraft II, especially if you need a scalable research platform.

Not ideal if you're looking for an out-of-the-box StarCraft II AI for casual play, or if you lack significant computational resources like a dedicated server with a GPU.

AI-research Reinforcement-Learning StarCraft-II Game-AI Strategy-simulation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

360

Forks

59

Language

Python

License

Apache-2.0

Last pushed

Nov 09, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/liuruoze/mini-AlphaStar"

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