Open-ended behavioral complexity for evolved virtual creatures

In the 19 years since Karl Sims' landmark publication on evolving virtual creatures (Sims, 1994), much of the future work he proposed has been implemented, having a significant impact on multiple fields including graphics, evolutionary computation, and artificial life. There has, however been one notable exception to this progress. Despite the potential benefits, there has been no clear increase in the behavioral complexity of evolved virtual creatures (EVCs) beyond the light following demonstrated in Sims' original work. This paper presents an open-ended method to move beyond this limit, making use of high-level human input in the form of a syllabus of intermediate learning tasks--along with mechanisms for preservation, reuse, and combination of previously learned tasks. This method (named ESP for its three components: encapsulation, syllabus, and pandemonium) is employed to evolve a virtual creature with behavioral complexity that clearly exceeds previously achieved levels. ESP thus demonstrates that EVCs may indeed have the potential to one day rival the behavioral complexity--and therefore the entertainment value--of their non-virtual counterparts.

[1]  Marvin Minsky,et al.  Society of Mind: A Response to Four Reviews , 1991, Artif. Intell..

[2]  Thomas Miconi,et al.  In Silicon No One Can Hear You Scream: Evolving Fighting Creatures , 2008, EuroGP.

[3]  Hod Lipson,et al.  Automatic Design and Manufacture of Soft Robots , 2012, IEEE Transactions on Robotics.

[4]  Chang-Hun Kim,et al.  Evolving Flying Creatures with Path Following Behaviors , 2004 .

[5]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[6]  F. Heider,et al.  An experimental study of apparent behavior , 1944 .

[7]  Kenneth O. Stanley,et al.  Evolving a diversity of virtual creatures through novelty search and local competition , 2011, GECCO '11.

[8]  Risto Miikkulainen,et al.  Evolving Keepaway Soccer Players through Task Decomposition , 2003, GECCO.

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

[10]  Karl Sims,et al.  Evolving virtual creatures , 1994, SIGGRAPH.

[11]  Dorothea Heiss-Czedik,et al.  An Introduction to Genetic Algorithms. , 1997, Artificial Life.

[12]  Risto Miikkulainen,et al.  Evolving Soccer Keepaway Players Through Task Decomposition , 2005, Machine Learning.

[13]  Patrice D. Tremoulet,et al.  Perceptual causality and animacy , 2000, Trends in Cognitive Sciences.

[14]  Malcolm I. Heywood,et al.  Hierarchical task decomposition through symbiosis in reinforcement learning , 2012, GECCO '12.

[15]  Christoph Adami,et al.  Evolving Virtual Creatures and Catapults , 2007, Artificial Life.

[16]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[17]  Borys Wróbel,et al.  Co-evolution of morphology and control of soft-bodied multicellular animats , 2012, GECCO '12.

[18]  Chang-Hun Kim,et al.  Generating flying creatures using body-brain co-evolution , 2003, SCA '03.

[19]  Jordan B. Pollack,et al.  Automatic design and manufacture of robotic lifeforms , 2000, Nature.

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

[21]  Manuela M. Veloso,et al.  Layered Learning , 2000, ECML.

[22]  Kyrre Glette,et al.  Evolution of artificial muscle-based robotic locomotion in PhysX , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[23]  Hervé Luga,et al.  A New Step for Artificial Creatures , 2007, 2007 IEEE Symposium on Artificial Life.

[24]  G. Reeke.  The society of mind , 1991 .

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

[26]  Christian Jacob,et al.  Evolution of vision capabilities in embodied virtual creatures , 2010, GECCO '10.