Competitive Coevolution through Evolutionary Complexification

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.

[1]  Nolan H. Sigal,et al.  Genetic recombination: the nature of a crossed strand-exchange between two homologous DNA molecules. , 1972, Journal of molecular biology.

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

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

[4]  C. Radding,et al.  Homologous pairing and strand exchange in genetic recombination. , 1982, Annual review of genetics.

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

[6]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[7]  Inman Harvey,et al.  Explorations in Evolutionary Robotics , 1993, Adapt. Behav..

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

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

[10]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

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

[12]  A. Sidow,et al.  Gene duplications and the origins of vertebrate development. , 1994, Development (Cambridge, England). Supplement.

[13]  Bernd Fritzke,et al.  A Growing Neural Gas Network Learns Topologies , 1994, NIPS.

[14]  Conor Ryan,et al.  Pygmies and civil servants , 1994 .

[15]  I. Harvey.  The artificial evolution of adaptive behaviour , 1994 .

[16]  Karl Sims,et al.  Evolving 3d morphology and behavior by competition , 1994 .

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

[18]  John R. Koza,et al.  Gene Duplication to Enable Genetic Programming to Concurrently Evolve Both the Architecture and Work-Performing Steps of a Computer Program , 1995, IJCAI.

[19]  S. Carroll.  Homeotic genes and the evolution of arthropods and chordates , 1995, Nature.

[20]  Risto Miikkulainen,et al.  Visualizing High-Dimensional Structure with the Incremental Grid Growing Neural Network , 1995, ICML.

[21]  B Fritzke,et al.  A growing neural gas network learns topologies. G. Tesauro, DS Touretzky, and TK Leen, editors , 1995, NIPS 1995.

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

[23]  A. Sidow.  Gen(om)e duplications in the evolution of early vertebrates. , 1996, Current opinion in genetics & development.

[24]  Samir W. Mahfoud.  Niching methods for genetic algorithms , 1996 .

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

[26]  Scott Brave,et al.  Evolving deterministic finite automata using cellular encoding , 1996 .

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

[28]  D. Sankoff,et al.  Comparable rates of gene loss and functional divergence after genome duplications early in vertebrate evolution. , 1997, Genetics.

[29]  Richard K. Belew,et al.  Coevolutionary search among adversaries , 1997 .

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

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

[32]  Y L Wang,et al.  Zebrafish hox clusters and vertebrate genome evolution. , 1998, Science.

[33]  Margaret R. Thomson,et al.  Vertebrate genome evolution and the zebrafish gene map , 1998, Nature Genetics.

[34]  Andrew P. Martin.  Increasing Genomic Complexity by Gene Duplication and the Origin of Vertebrates , 1999, The American Naturalist.

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

[36]  Hagai Attias,et al.  A Variational Bayesian Framework for Graphical Models , 1999 .

[37]  A. Force,et al.  Preservation of duplicate genes by complementary, degenerative mutations. , 1999, Genetics.

[38]  David C. Wilkins,et al.  Efficient Bayesian Network Inference: Genetic Algorithms, Stochastic Local Search, and Abstraction , 1999 .

[39]  Carlo C. Maley,et al.  Four steps toward open-ended evolution , 1999 .

[40]  Kristian Lindgrena,et al.  Coevolution of strategies in n-person Prisoner ' s Dilemma , 2000 .

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

[42]  John S. McCaskill,et al.  Emergent Design: Artificial Life for Architecture Design , 2000 .

[43]  Melanie Mitchell,et al.  Evolving Cellular Automata with Genetic Algorithms: A Review of Recent Work , 2000 .

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

[45]  Jordan B. Pollack,et al.  Pareto Optimality in Coevolutionary Learning , 2001, ECAL.

[46]  R. Watson,et al.  Pareto coevolution: using performance against coevolved opponents in a game as dimensions for Pareto selection , 2001 .

[47]  Naonori Ueda,et al.  Bayesian model search for mixture models based on optimizing variational bounds , 2002, Neural Networks.

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

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

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

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

[52]  G. Lewicki,et al.  Approximation by Superpositions of a Sigmoidal Function , 2003 .

[53]  Principles in the Evolutionary Design of Digital Circuits—Part I , 2004, Genetic Programming and Evolvable Machines.

[54]  Julian Francis Miller,et al.  Principles in the Evolutionary Design of Digital Circuits—Part II , 2000, Genetic Programming and Evolvable Machines.

[55]  Nicholas J. Radcliffe,et al.  Genetic set recombination and its application to neural network topology optimisation , 1993, Neural Computing & Applications.

[56]  W. Oechel,et al.  Automatic design and manufacture of robotic lifeforms , 2022 .