Coevolving the "Ideal" Trainer: Application to the Discovery of Cellular Automata Rules

Coevolution provides a framework to implement search heuristics that are more elaborate than those driving the exploration of the state space in canonical evolutionary systems. However, some drawbacks have also to be overcome in order to ensure continuous progress on the long term. This paper presents the concept of coevolutionary learning and introduces a search procedure which successfully addresses the underlying impediments in coevolutionary search. The application of this algorithm to the discovery of cellular automata rules for a classi cation task is described. This work resulted in a signi cant improvement over previously known best rules for this task.

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

[2]  James P. Crutchfield,et al.  Revisiting the Edge of Chaos: Evolving Cellular Automata to Perform Computations , 1993, Complex Syst..

[3]  James P. Crutchfield,et al.  A Genetic Algorithm Discovers Particle-Based Computation in Cellular Automata , 1994, PPSN.

[4]  Kenneth A. De Jong,et al.  A Cooperative Coevolutionary Approach to Function Optimization , 1994, PPSN.

[5]  Melanie Mitchell,et al.  Evolving cellular automata to perform computations: mechanisms and impediments , 1994 .

[6]  Phil Husbands,et al.  Distributed Coevolutionary Genetic Algorithms for Multi-Criteria and Multi-Constraint Optimisation , 1994, Evolutionary Computing, AISB Workshop.

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

[8]  Jan Paredis,et al.  Co-evolutionary Constraint Satisfaction , 1994, PPSN.

[9]  Craig W. Reynolds.  Competition, Coevolution and the Game of Tag , 1994 .

[10]  John J. Grefenstette,et al.  A Coevolutionary Approach to Learning Sequential Decision Rules , 1995, ICGA.

[11]  Land,et al.  No perfect two-state cellular automata for density classification exists. , 1995, Physical review letters.

[12]  Corso Elvezia.  Discovering Solutions with Low Kolmogorov Complexity and High Generalization Capability , 1995 .

[13]  Jürgen Schmidhuber.  Discovering Solutions with Low Kolmogorov Complexity and High Generalization Capability , 1995, ICML.

[14]  Jan Paredis,et al.  The Symbiotic Evolution of Solutions and Their Representations , 1995, International Conference on Genetic Algorithms.

[15]  Dave Cliff,et al.  Tracking the Red Queen: Measurements of Adaptive Progress in Co-Evolutionary Simulations , 1995, ECAL.

[16]  Jan Paredis,et al.  Coevolutionary Computation , 1995, Artificial Life.

[17]  Jordan B. Pollack,et al.  Co-Evolving Intertwined Spirals , 1996, Evolutionary Programming.

[18]  Capcarrere,et al.  Two-state, r=1 Cellular Automaton that Classifies Density. , 1996, Physical review letters.

[19]  M. Sipper.  Co-evolving non-uniform cellular automata to perform computations , 1996 .

[20]  Richard K. Belew,et al.  A competitive approach to game learning , 1996, COLT '96.

[21]  Dave Cliff,et al.  Co-evolution of pursuit and evasion II: Simulation Methods and results , 1996 .

[22]  David E. Moriarty,et al.  Symbiotic Evolution of Neural Networks in Sequential Decision Tasks , 1997 .

[23]  Mitchell A. Potter,et al.  The design and analysis of a computational model of cooperative coevolution , 1997 .

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

[25]  Jan Paredis,et al.  Coevolving Cellular Automata: Be Aware of the Red Queen! , 1997, ICGA.