AlfredStar: a fresh take on AI for StarCraft II

Deepmind's AlphaGo revolutionized the game of Go, achieving superhuman mastery and pulling off unprecedented, groundbreaking plays. However, Deepmind moved on from their AlphaStar too soon in 2019, leaving its potential in StarCraft II only partially realized.

There have been significant advancements in the field of machine learning since 2019. Leveraging the latest technologies, AlfredStar aims to play delightful StarCraft II games at a superhuman level, while being trained and operated at a fraction of the cost required by AlphaStar.

Approach

Rather than training a monolithic neural network end-to-end, AlfredStar separates strategy from execution. Strategies are written in SC2L, a domain-specific language, then compiled to playbook and executed by a lightweight runtime. This separation enables deterministic replay, human-readable strategies, and efficient iteration.