Polymorphy and Hybridization in Genetically Programmed Networks

In this paper we discuss the polymorphic abilities of a new distributed representation for genetic programming, called Genetically Programmed Networks. These are inspired in a common structure in natural complex adaptive systems, where system functionality frequently emerges from the combined functionality of simple computational entities, densely interconnected for information exchange. A Genetically Programmed Network can be evolved into a distributed program, a rule based system or a neural network with simple adjustments to the evolutionary algorithm. The space of possible network topologies can also be easily controlled. This allows the fast exploration of various search spaces thus increasing the possibility of finding a (or a better) solution. Experimental results are presented to support our claims.

[1]  Jean-Arcady Meyer,et al.  A hierarchical classifier system implementing a motivationally autonomous animat , 1994 .

[2]  P Bourgine,et al.  Towards a Practice of Autonomous Systems , 1992 .

[3]  John J. Grefenstette,et al.  An Evolutionary Approach to Learning in Robots. , 1994 .

[4]  J. K. Kinnear,et al.  Advances in Genetic Programming , 1994 .

[5]  Ernesto Costa,et al.  Genetically programming networks to evolve memory mechanisms , 1999 .

[6]  P. Husbands,et al.  Analysis of Evolved Sensory-motor Controllers Analysis of Evolved Sensory-motor Controllers , 1992 .

[7]  Martin C. Martin,et al.  Genetic programming in C++: implementation issues , 1994 .

[8]  Marco Dorigo,et al.  Genetics-based machine learning and behavior-based robotics: a new synthesis , 1993, IEEE Trans. Syst. Man Cybern..

[9]  Stefano Nolfi,et al.  How to Evolve Autonomous Robots: Different Approaches in Evolutionary Robotics , 1994 .

[10]  John R. Koza,et al.  Hidden Order: How Adaptation Builds Complexity. , 1995, Artificial Life.

[11]  Ernesto Costa,et al.  Building agents with memory: an approach using genetically programmed networks , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[12]  Ernesto Costa,et al.  Evolving Controllers for Autonomous Agents Using Genetically Programmed Networks , 1999, EuroGP.

[13]  Inman Harvey,et al.  Issues in evolutionary robotics , 1993 .

[14]  Kevin Barraclough,et al.  I and i , 2001, BMJ : British Medical Journal.

[15]  Francesco Mondada,et al.  Automatic creation of an autonomous agent: genetic evolution of a neural-network driven robot , 1994 .

[16]  Rodney A. Brooks,et al.  Artificial Life and Real Robots , 1992 .

[17]  John H. Holland,et al.  Hidden Order: How Adaptation Builds Complexity , 1995 .

[18]  Riccardo Poli,et al.  Why Ants are Hard , 1998 .

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