Evolutionary reinforcement learning of artificial neural networks

Issue title: Hybridization of Intelligent Systems

Guest editors: M. Köppenx and R. Webery

Article type: Research Article

Authors: Siebel, Nils T.^{; *} | Sommer, Gerald

Affiliations: Cognitive Systems Group, Institute of Computer Science, Christian-Albrechts-University of Kiel, Germany | [x] Kyushu Institute of Technology | [y] University of Chile

Correspondence: [*] Corresponding author. E-mail: nils@siebel-research.de

Abstract: In this article we describe EANT, Evolutionary Acquisition of Neural Topologies, a method that creates neural networks by evolutionary reinforcement learning. The structure of the networks is developed using mutation operators, starting from a minimal structure. Their parameters are optimised using CMA-ES, Covariance Matrix Adaptation Evolution Strategy, a derandomised variant of evolution strategies. EANT can create neural networks that are very specialised; they achieve a very good performance while being relatively small. This can be seen in experiments where our method competes with a different one, called NEAT, NeuroEvolution of Augmenting Topologies, to create networks that control a robot in a visual servoing scenario.

DOI: 10.3233/HIS-2007-4304

Journal: International Journal of Hybrid Intelligent Systems, vol. 4, no. 3, pp. 171-183, 2007