Paper on Evolving Increasingly Complex NN's

[Kenneth Owen Stanley]

We are pleased to announce the publication of the following article
in the Journal of Artificial Intelligence Research:

Stanley, K.O. and Miikkulainen, R. (2004)
"Competitive Coevolution through Evolutionary Complexification",
Volume 21, pages 63-100.

For quick access via your WWW browser, use this URL:
http://www.jair.org/abstracts/stanley04a.html

Abstract:
Two major goals in machine learning are the discovery and improvement
of solutions to complex problems. In this paper, we argue that
complexification, i.e. the incremental elaboration of solutions
through adding new structure, achieves both these goals. We
demonstrate the power of complexification through the NeuroEvolution
of Augmenting Topologies (NEAT) method, which evolves increasingly
complex neural network architectures. NEAT is applied to an
open-ended coevolutionary robot duel domain where robot controllers
compete head to head. Because the robot duel domain supports a wide
range of strategies, and because coevolution benefits from an
escalating arms race, it serves as a suitable testbed for studying
complexification. When compared to the evolution of networks with
fixed structure, complexifying evolution discovers significantly more
sophisticated strategies. The results suggest that in order to
discover and improve complex solutions, evolution, and search in
general, should be allowed to complexify as well as optimize.

To see animated demos of the Robot Duel domain mentioned
in the paper, please see:
 
 http://nn.cs.utexas.edu/pages/research/neatdemo.html
 
NEAT software is available through the NEAT Page:
 
  http://nn.cs.utexas.edu/keyword?neat