Evolving the Behavior of Machines: From Micro to Macroevolution

TL;DR

This paper explores the shift from microevolution to macroevolution in artificial evolution, emphasizing diversity and creativity in evolving complex systems like neural networks and designs.

Contribution

It highlights the transition from optimization-focused evolution to macroevolution, fostering diversity and creativity in evolving complex artifacts.

Findings

Macroevolution promotes diverse species and solutions.

Applications include evolving gaits, game levels, and aerodynamic designs.

The approach enhances creativity beyond traditional optimization.

Abstract

Evolution gave rise to creatures that are arguably more sophisticated than the greatest human-designed systems. This feat has inspired computer scientists since the advent of computing and led to optimization tools that can evolve complex neural networks for machines -- an approach known as "neuroevolution". After a few successes in designing evolvable representations for high-dimensional artifacts, the field has been recently revitalized by going beyond optimization: to many, the wonder of evolution is less in the perfect optimization of each species than in the creativity of such a simple iterative process, that is, in the diversity of species. This modern view of artificial evolution is moving the field away from microevolution, following a fitness gradient in a niche, to macroevolution, filling many niches with highly different species. It already opened promising applications, like evolving gait repertoires, video game levels for different tastes, and diverse designs for aerodynamic bikes.