Codelab for Starcraft II pysc2 machine learning research You can see the current development here The goal is to offer a general overview of how the StarCraft II Learning environment works, bring out some machine learning concepts to get started. It includes a overview in a how to train an agent using GCP

What pySC2 and StarCraft II API are Basics theoretical concepts of Deep Reinforcement Learning to get started Basic interaction with StarCraft II API Training and modify Machine Learning agent Evaluating how training and evaluating works Train a Machine Learning agent in GCP

A computer connected to the internet with Python3 installed

-The library pySC2 installed

-Starcraft II game -no license required-

-keras

-keras-rl

Basic driving of bash console Basic knowledge of Python - data structures, lists, functions, loops - Basic knowledge of object-oriented programming -classes, methods, decorators - Conceptual knowledge about Neural Networks

Thanks to :

-AbdonRD

-Flipper83

pysc2 repository

pysc2 paper

StarCraftII data analysis from replays

StarCraftII mini-games and other agents

Design a container image for the codelab