In competitive coevolution, the goal is to establish an arms race'' that will lead to increasingly sophisticated strategies. However, in practice, the process often leads to idiosyncrasies rather than continual improvement. Applying the NEAT method for evolving neural networks to a competitive simulated robot duel domain, we will demonstrate that (1) as evolution progresses the networks become more complex, (2) complexification elaborates on existing strategies, and (3) if NEAT is allowed to complexify, it finds dramatically more sophisticated strategies than when it is limited to fixed-topology networks. The results suggest that in order to realize thefull potential of competitive coevolution, genomes must be allowed to complexify as well as optimize over the course of evolution.

PDF, PS

In William B. Langdon and Erick Cantu-Paz and Keith E. Mathias and Rajkumar Roy and David Davis and Riccardo Poli and Karthik Balakrishnan and Vasant Honavar and G{"u}nter Rudolph and Joachim Wegener and Larry Bull and Mitchell A. Potter and Alan C. Schultz, editors, Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2002), 8, San Francisco, 2002. Morgan Kaufmann.

@InProceedings{stanley:gecco02b, title={Continual Coevolution Through Complexification}, author={Kenneth O. Stanley and Risto Miikkulainen}, booktitle={Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2002)}, editor={William B. Langdon and Erick Cantu-Paz and Keith E. Mathias and Rajkumar Roy and David Davis and Riccardo Poli and Karthik Balakrishnan and Vasant Honavar and G{"u}nter Rudolph and Joachim Wegener and Larry Bull and Mitchell A. Potter and Alan C. Schultz}, address={San Francisco}, publisher={Morgan Kaufmann}, pages={8}, url="http://nn.cs.utexas.edu/?stanley:gecco02a", year={2002} }