Speciation Dynamics: Generating Selective Pressure Towards Diversity

Recent approaches in evolutionary robotics (ER) propose to generate behavioral diversity in order to evolve desired behaviors more easily. These approaches require the definition of a behavioral distance which often includes task-specific features and hence a priori knowledge. Alternative methods, that do not explicitly force selective pressure towards diversity (SPTD) but still generate it, are known from the field of artificial life such as artificial ecologies (AE). In this study, we investigate how SPTD is generated without task-specific behavioral features or other forms of a priori knowledge and detect how methods of generating SPTD can be transferred from the domain of AE to ER. A promising finding is that in both types of systems, in systems from ER that generate behavioral diversity and also in the investigated speciation model, selective pressure is generated towards unpopulated regions of search space. We conclude by hypothesizing how knowledge about self-organizing SPTD in AE could be transferred to the domain of ER.

[1]  Mark Woehrer,et al.  Sexual Selection, Resource Distribution, and Population Size in Synthetic Sympatric Speciation , 2012, ALIFE.

[2]  D. Floreano,et al.  Adaptive Behavior in Competing Co-Evolving Species , 2000 .

[3]  Gregory J. Barlow,et al.  Article in Press Robotics and Autonomous Systems ( ) – Robotics and Autonomous Systems Fitness Functions in Evolutionary Robotics: a Survey and Analysis , 2022 .

[4]  T. Dobzhansky.  Genetics and the Origin of Species , 1937 .

[5]  Kenneth O. Stanley,et al.  Improving evolvability through novelty search and self-adaptation , 2011, 2011 IEEE Congress of Evolutionary Computation (CEC).

[6]  Stefano Nolfi,et al.  How Co-Evolution can Enhance the Adaptive Power of Artificial Evolution: Implications for Evolutionary Robotics , 1998, EvoRobot.

[7]  D. Floreano,et al.  Evolutionary Robotics: The Biology,Intelligence,and Technology , 2000 .

[8]  Stéphane Doncieux,et al.  Using behavioral exploration objectives to solve deceptive problems in neuro-evolution , 2009, GECCO.

[9]  Bruno Sareni,et al.  Fitness sharing and niching methods revisited , 1998, IEEE Trans. Evol. Comput..

[10]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[11]  Wenguo Liu,et al.  Environment-driven distributed evolutionary adaptation in a population of autonomous robotic agents , 2012 .

[12]  Alicia M. Frame,et al.  Magic traits in speciation: 'magic' but not rare? , 2011, Trends in ecology & evolution.

[13]  M. Pagel,et al.  Phylogenies reveal new interpretation of speciation and the Red Queen , 2010, Nature.

[14]  Kenneth O. Stanley,et al.  Exploiting Open-Endedness to Solve Problems Through the Search for Novelty , 2008, ALIFE.

[15]  J. Stradner,et al.  On-line, On-board Evolution of Reaction-Diffusion Control for Self-Adaptation , 2012 .

[16]  Eörs Szathmáry,et al.  The Major Transitions in Evolution , 1997 .

[17]  Stéphane Doncieux,et al.  Encouraging Behavioral Diversity in Evolutionary Robotics: An Empirical Study , 2012, Evolutionary Computation.