neural networks research group
areas
•
people
•
projects
•
demos
•
publications
•
software/data
•
Competitive Coevolution through Evolutionary Complexification (2004)
Kenneth O. Stanley
and
Risto Miikkulainen
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.
View:
PDF
,
PS
,
HTML
Citation:
Journal of Artificial Intelligence Research
, 21:63-100, 2004.
Bibtex:
@Article{stanley:jair04, title={Competitive Coevolution through Evolutionary Complexification}, author={Kenneth O. Stanley and Risto Miikkulainen}, volume={21}, journal={Journal of Artificial Intelligence Research}, pages={63-100}, url="http://nn.cs.utexas.edu/?stanley:jair04", year={2004} }
Also show archived content
People
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
Kenneth Stanley
Postdoctoral Alumni
kstanley [at] cs ucf edu
Projects
NEAT: Evolving Increasingly Complex Neural Network Topologies
2000 - 2011
Demos
Neuroevolution of Augmenting Topologies Demos
Kenneth Stanley
2003
Software/Data
NEAT C++
The NEAT package contains source code implementing the NeuroEvolution of Augmenting Topologies method. The source code i...
2010
NEAT C#
The SharpNEAT package contains C# source code for the NeuroEvolution of Augmenting Topologies method (see the original <...
2003
NEAT Delphi
The Delphi NEAT package contains Delphi source code for the NeuroEvolution of Augmenting Topologies method (see the orig...
2003
NEAT Matlab
The Matlab NEAT package contains Matlab source code for the NeuroEvolution of Augmenting Topologies method (see the orig...
2003
NEAT C++ for Microsoft Windows
The Windows NEAT package contains C++ source code for the NeuroEvolution of Augmenting Topologies method (see the origin...
2002
NEAT Java (JNEAT)
The JNEAT package contains Java source code for the NeuroEvolution of Augmenting Topologies method (see the original
2002
Areas of Interest
Evolutionary Computation
Neuroevolution
Reinforcement Learning