Comparison of Different Genotype Encodings for Simulated Three-Dimensional Agents

We analyze the effect of different genetic encodings used for evolving three-dimensional agents with physical morphologies. The complex phenotypes used in such systems often require nontrivial encodings. Different encodings used in Framsticksa system for evolving three-dimensional agentsare presented. These include a low-level direct mapping and two higher-level encodings: one recurrent and one developmental. Quantitative results are presented from three simple optimization tasks (passive height, active height, and locomotion speed). The low-level encoding produced solutions of lower fitness than the two higher-level encodings under similar conditions. Results from recurrent and developmental encodings had similar fitness values but displayed qualitative differences. Desirable advantages and some drawbacks of more complex encodings are established.

[1]  Hiroaki Kitano,et al.  Designing Neural Networks Using Genetic Algorithms with Graph Generation System , 1990, Complex Syst..

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

[3]  L. Darrell Whitley,et al.  Transforming the search space with Gray coding , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[4]  L. Darrell Whitley,et al.  Cellular Encoding Applied to Neurocontrol , 1995, ICGA.

[5]  Frédéric Gruau,et al.  Modular Genetic Neural Networks for Six-Legged Locomotion , 1995, Artificial Evolution.

[6]  Maja J. Matarić,et al.  A Developmental Model for the Evolution of Complete Autonomous Agents , 1996 .

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

[8]  Peter Eggenberger,et al.  Evolving Morphologies of Simulated 3d Organisms Based on Differential Gene Expression , 1997 .

[9]  Vesselin K. Vassilev.  An Information Measure of Landscapes , 1997, ICGA.

[10]  G. Wagner,et al.  A case study of the evolution of modularity: towards a bridge between evolutionary biology, artificial life, neuro- and cognitive science , 1998 .

[11]  Ádám Rotaru-Varga.  Modularity in Evolved Artificial Neural Networks , 1999, ECAL.

[12]  Maciej Komosinski,et al.  Framsticks: Towards a Simulation of a Nature-Like World, Creatures and Evolution , 1999, ECAL.

[13]  John S. McCaskill,et al.  From Directed to Open-Ended Evolution in a Complex Simulation Model , 2000 .

[14]  Jordan B. Pollack,et al.  Evolutionary Techniques in Physical Robotics , 2000, ICES.

[15]  Maciej Komosinski,et al.  The World of Framsticks: Simulation, Evolution, Interaction , 2000, Virtual Worlds.

[16]  Maciej Komosinski,et al.  From Directed to Open-Ended Evolution in a Complex Simulation Model , 2000 .

[17]  Chandana Paul,et al.  Investigating Morphological Symmetry and Locomotive Efficiency using Virtual Embodied Evolution , 2000 .

[18]  Colm Massey,et al.  Recent Developments in the Evolution of Morphologies and Controllers for Physically Simulated Creatures , 2000, Artificial Life.

[19]  Maciej Komosinski,et al.  On estimating similarity of artificial and real organisms , 2001 .

[20]  Gregory S. Hornby,et al.  Body-brain co-evolution using L-systems as a generative encoding , 2001 .

[21]  R. Pfeifer,et al.  Repeated structure and dissociation of genotypic and phenotypic complexity in artificial ontogeny , 2001 .

[22]  Jordan B. Pollack,et al.  Creating High-Level Components with a Generative Representation for Body-Brain Evolution , 2002, Artificial Life.

[23]  Maciej Komosin´ski,et al.  The Framsticks system: versatile simulator of 3D agents and their evolution , 2003 .

[24]  R. Beer,et al.  20 – A developmental model for the evolution of complete autonomous agents , 2003 .

[25]  Risto Miikkulainen,et al.  A Taxonomy for Artificial Embryogeny , 2003, Artificial Life.