opendilab/DI-star
An artificial intelligence platform for the StarCraft II with large-scale distributed training and grand-master agents.
DI-star is a platform for training advanced AI agents to play StarCraft II. It allows you to feed in gameplay data, either from human replays or self-play, to develop AI agents capable of playing at a grandmaster level. This is primarily for AI researchers and game AI enthusiasts who want to create or test high-skill StarCraft II bots.
1,344 stars. No commits in the last 6 months.
Use this if you are an AI researcher or enthusiast looking to train, test, or interact with high-level StarCraft II AI agents using supervised or reinforcement learning.
Not ideal if you're a casual player looking for a simple plug-and-play AI opponent without any interest in the underlying AI training or development.
Stars
1,344
Forks
124
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 13, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/opendilab/DI-star"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
oxwhirl/smac
SMAC: The StarCraft Multi-Agent Challenge
TorchCraft/TorchCraft
Connecting Torch to StarCraft
google-deepmind/pysc2
StarCraft II Learning Environment
liuruoze/mini-AlphaStar
(JAIR'2022) A mini-scale reproduction code of the AlphaStar program. Note: the original...
alibaba/gym-starcraft
StarCraft environment for OpenAI Gym, based on Facebook's TorchCraft. (In progress)