google-deepmind/pysc2

Health v2 · maintenance only

Adoption not part of the score

8307 stars · 1163 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

PySC2 is DeepMind's Python component of the StarCraft II Learning Environment, exposing Blizzard's StarCraft II Machine Learning API as a Python reinforcement learning environment. It lets RL agents observe game state and send actions in StarCraft II, including mini-game maps for research.

Use cases

• train reinforcement learning agents in StarCraft II
• build an RL environment around a real-time strategy game
• run StarCraft II mini-games for AI research
• parse StarCraft II replays for machine learning
• benchmark deep RL algorithms on a complex game environment

When to choose

• you need a rich, well-established RL environment with complex multi-agent dynamics
• you want to reproduce DeepMind's StarCraft II RL research
• you need programmatic observation/action interfaces to StarCraft II via Blizzard's API

When to avoid

• you need a lightweight or fast-to-iterate RL environment
• you don't want to install the full StarCraft II game binary
• you need a project with frequent updates and active development

Facets

library · maturity maintenance

reinforcement-learning machine-learning simulation sdk reinforcement-learning machine-learning artificial-intelligence python windows starcraft-ii rl-environment gym-environment blizzard-api deepmind game-ai research game-development linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="google-deepmind/pysc2")