Evolution of Artificial Brains in Simulated AnimalBehaviour

Abstract: In this report we simulate artificial intelligence in animals using genetic algorithms. In similar models, advanced artificial neural networks have been used for decision making. We present two simpler decision-making models. Using two models based on linear and radial basis functions we find similar behaviours as those found in other studies, including food seeking, obstacle avoidance and predator-versus-prey dynamics. The results show that both decision-making models are equally efficient at gathering food and avoiding obstacles. The models differed in survival strategies when faced with dangerous obstacles and in a predator-versus-prey situation the predators based on radial basis functions performed better. Some evolutionary phenomena were observed during the evolution of the animals, including an evolutionary armsrace between predator and prey. We hoped to find signs of mimicry as well, but classic mimicry was not found in the results.