Metadata-Version: 2.4
Name: SMAC
Version: 1.0.0
Summary: SMAC - StarCraft Multi-Agent Challenge.
Home-page: https://github.com/oxwhirl/smac
Author: WhiRL
Author-email: mikayel@samvelyan.com
License: MIT License
Keywords: StarCraft,Multi-Agent Reinforcement Learning
License-File: LICENSE
Requires-Dist: protobuf<3.21
Requires-Dist: pysc2>=3.0.0
Requires-Dist: s2clientprotocol>=4.10.1.75800.0
Requires-Dist: absl-py>=0.1.0
Requires-Dist: numpy>=1.10
Requires-Dist: pygame>=2.0.0
Provides-Extra: dev
Requires-Dist: pre-commit>=2.0.1; extra == "dev"
Requires-Dist: black>=19.10b0; extra == "dev"
Requires-Dist: flake8>=3.7; extra == "dev"
Requires-Dist: flake8-bugbear>=20.1; extra == "dev"
Dynamic: author
Dynamic: author-email
Dynamic: description
Dynamic: home-page
Dynamic: keywords
Dynamic: license
Dynamic: license-file
Dynamic: provides-extra
Dynamic: requires-dist
Dynamic: summary

SMAC - StarCraft Multi-Agent Challenge

SMAC offers a diverse set of decentralised micromanagement challenges based on
StarCraft II game. In these challenges, each of the units is controlled by an
independent, learning agent that has to act based only on local observations,
while the opponent's units are controlled by the built-in StarCraft II AI.

The accompanying paper which outlines the motivation for using SMAC as well as
results using the state-of-the-art deep multi-agent reinforcement learning
algorithms can be found at https://www.arxiv.link

Read the README at https://github.com/oxwhirl/smac for more information.
