# AlphaStar: An Evolutionary Computation Perspective

## TL;DR

This paper analyzes AlphaStar, a groundbreaking AI system for StarCraft II, from an evolutionary computation perspective, highlighting its innovative use of EC concepts like Lamarckian evolution and co-evolution.

## Contribution

It offers a novel analysis of AlphaStar through the lens of evolutionary computation, connecting it with EC concepts and practices.

## Key findings

- AlphaStar employs Lamarckian evolution techniques.
- It utilizes competitive co-evolution strategies.
- The system demonstrates effective quality diversity methods.

## Abstract

In January 2019, DeepMind revealed AlphaStar to the world-the first artificial intelligence (AI) system to beat a professional player at the game of StarCraft II-representing a milestone in the progress of AI. AlphaStar draws on many areas of AI research, including deep learning, reinforcement learning, game theory, and evolutionary computation (EC). In this paper we analyze AlphaStar primarily through the lens of EC, presenting a new look at the system and relating it to many concepts in the field. We highlight some of its most interesting aspects-the use of Lamarckian evolution, competitive co-evolution, and quality diversity. In doing so, we hope to provide a bridge between the wider EC community and one of the most significant AI systems developed in recent times.