Neuro-Evolution for competitive co-evolution of biologically canonical predator and prey behaviors

Abstract

This paper presents a simulation of predator (pursuer) and prey (evader) agents operating within a competitive co-evolution process. The aim of the study was to investigate the effects of different resource (food for the prey) distributions and amounts on the adaptation of predator (pursuit) and prey (evasion) behaviors. Predator and prey use Artificial Neural Network (ANN) controllers to simulate behavior, where behaviors are adapted by Neuro-Evolution. The research objectives were two-fold. First, to test the capability of NE for evolving predator and prey behaviors that are effective in environments other than that in which they were evolved. Second, to test the efficacy of NE as a behavioral modeling method for co-evolutionary predator-prey simulations. Results indicated that NE was effective at evolving predator and prey behaviors that also performed well in other environments. Also, NE was successful at deriving behaviors that maintained specific similarities with those reported upon in related predator-prey studies. A key goal of this research was to use a synthetic approach to elucidate behavioral evolution in nature.