thefirebanks/MultiAgent-Systems-StarCraft2-PySC2-Raw

Code to do multi agent systems research on StarCraft II. It contains methods to deal with the Raw Interface from the SC2 API, which has not been officially adapted for Python. This means that, the programmer can now access the objects at the game and the 2D original representation of the map

13
/ 100
Experimental

This project helps AI researchers working with StarCraft II build multi-agent systems. It takes game states and agent actions in StarCraft II's raw interface format, processes them, and returns raw observations or executes raw commands within the game. Researchers can use this to develop and test AI agents that need direct, low-level control and detailed information about the game.

No commits in the last 6 months.

Use this if you are an AI researcher building multi-agent systems for StarCraft II and need to interact with the game using its detailed 'raw' interface to access unit-specific data and control.

Not ideal if you are a StarCraft II AI researcher looking for a fully maintained and widely functional library, as this project is no longer actively developed.

AI-research multi-agent-systems game-AI StarCraft-II reinforcement-learning
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Python

License

Last pushed

Jul 23, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/thefirebanks/MultiAgent-Systems-StarCraft2-PySC2-Raw"

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