google-deepmind/pysc2
StarCraft II Learning Environment
Provides Python bindings to Blizzard's StarCraft II ML API with both raw and feature-layer observation spaces, enabling agents to interact through structured action/observation interfaces. Includes curated mini-game environments designed for curriculum learning and benchmarking, alongside tools for replay analysis and human-agent interaction for debugging. Compatible with standard RL frameworks through its environment abstraction layer, supporting both single-agent scripted baselines and multi-agent competitive scenarios.
8,262 stars. No commits in the last 6 months.
Stars
8,262
Forks
1,166
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 23, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/google-deepmind/pysc2"
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
liuruoze/mini-AlphaStar
(JAIR'2022) A mini-scale reproduction code of the AlphaStar program. Note: the original...
opendilab/DI-star
An artificial intelligence platform for the StarCraft II with large-scale distributed training...
alibaba/gym-starcraft
StarCraft environment for OpenAI Gym, based on Facebook's TorchCraft. (In progress)