Continual Coevolution Through Complexification

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 the full potential of competitive coevolution, genomes must be allowed to complexify as well as optimize over the course of evolution.

[1]  L. V. Valen,et al.  A new evolutionary law , 1973 .

[2]  J. Krebs,et al.  Arms races between and within species , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[3]  J E Darnell,et al.  Speculations on the early course of evolution. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[4]  David E. Goldberg,et al.  Genetic Algorithms with Sharing for Multimodalfunction Optimization , 1987, ICGA.

[5]  Peter J. Angeline,et al.  Competitive Environments Evolve Better Solutions for Complex Tasks , 1993, ICGA.

[6]  Byoung-Tak Zhang,et al.  Evolving Optimal Neural Networks Using Genetic Algorithms with Occam's Razor , 1993, Complex Syst..

[7]  Francesco Mondada,et al.  Mobile Robot Miniaturisation: A Tool for Investigation in Control Algorithms , 1993, ISER.

[8]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[9]  Larry D. Pyeatt,et al.  A comparison between cellular encoding and direct encoding for genetic neural networks , 1996 .

[10]  Paul J. Darwen,et al.  Co-Evolutionary Learning by Automatic Modularisation with Speciation , 1996 .

[11]  Stefano Nolfi,et al.  God Save the Red Queen! Competition in Co-Evolutionary Robotics , 1997 .

[12]  Risto Miikkulainen,et al.  Incremental Evolution of Complex General Behavior , 1997, Adapt. Behav..

[13]  Richard K. Belew,et al.  New Methods for Competitive Coevolution , 1997, Evolutionary Computation.

[14]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[15]  C. Lee Giles,et al.  Talking Helps: Evolving Communicating Agents for the Predator-Prey Pursuit Problem , 2000, Artificial Life.

[16]  James A. Reggia,et al.  Conditions Enabling the Evolution of Inter-Agent Signaling in an Artificial World , 2000, Artificial Life.

[17]  Risto Miikkulainen,et al.  Efficient evolution of neural network topologies , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[18]  Kenneth O. Stanley and Joseph Reisinger and Risto Miikkulainen,et al.  The Dominance Tournament Method of Monitoring Progress in Coevolution , 2002 .

[19]  Risto Miikkulainen,et al.  Efficient Reinforcement Learning Through Evolving Neural Network Topologies , 2002, GECCO.

[20]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.