Competitive Environments Evolve Better Solutions for Complex Tasks

In the typical genetic algorithm experiment, the fitness function is constructed to be independent of the contents of the population to provide a consistent objective measure. Such objectivity entails significant knowledge about the environment which suggests either the problem has previously been solved or other non-evolutionary techniques may be more efficient. Furthermore, for many complex tasks an independent fitness function is either impractical or impossible to provide. In this paper, we demonstrate that competitive fitness functions, i.e. fitness functions that are dependent on the constituents of the population, can provide a more robust training environment than independent fitness functions. We describe three differing methods for competitive fitness, and discuss their respective advantages.

[1]  Arthur L. Samuel,et al.  Some Studies in Machine Learning Using the Game of Checkers , 1967, IBM J. Res. Dev..

[2]  A. L. Samuel,et al.  Some studies in machine learning using the game of checkers. II: recent progress , 1967 .

[3]  A. L. Samuel,et al.  Some Studies in Machine Learning Using the Game of Checkers , 1967, IBM J. Res. Dev..

[4]  K. Dejong,et al.  An analysis of the behavior of a class of genetic adaptive systems , 1975 .

[5]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[6]  Kenneth Alan De Jong,et al.  An analysis of the behavior of a class of genetic adaptive systems. , 1975 .

[7]  Hans J. Berliner,et al.  Experiences in Evaluation with BKG - A Program that Plays Backgammon , 1977, IJCAI.

[8]  W. Hamilton,et al.  The Evolution of Cooperation , 1984 .

[9]  Geoffrey E. Hinton,et al.  Schemata and Sequential Thought Processes in PDP Models , 1986 .

[10]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[11]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[12]  Stephanie Forrest,et al.  Emergent computation: self-organizing, collective, and cooperative phenomena in natural and artificial computing networks , 1990 .

[13]  Gerald Tesauro,et al.  Neurogammon: a neural-network backgammon program , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[14]  W. Daniel Hillis,et al.  Co-evolving parasites improve simulated evolution as an optimization procedure , 1990 .

[15]  Thomas S. Ray,et al.  An Approach to the Synthesis of Life , 1991 .

[16]  John R. Koza,et al.  Genetic evolution and co-evolution of computer programs , 1991 .

[17]  Kristian Lindgren,et al.  Evolutionary phenomena in simple dynamics , 1992 .

[18]  J. Pollack,et al.  Coevolving High-Level Representations , 1993 .