Charles Explorer logo
🇬🇧

Towards Efficient Evolution of Morphology and Control

Publication at Charles University |
2008

Abstract

We propose a novel algorithm for the evolution of body and control of three-dimensional, physically simulated virtual creatures controlled by artificial neural networks. The proposed algorithm is inspired by NeuroEvolution of Augmenting Topologies (NEAT) which efficiently evolves artificial neural networks.

Large-scale experiments have shown that the proposed algorithm evolves creatures using significantly less fitness evaluations than a standard genetic algorithm on all four tested fitness functions