Efficiently evolving programs through the search for novelty

摘要: A significant challenge in genetic programming is premature convergence to local optima, which often prevents evolution from solving problems. This paper introduces to genetic programming a method that originated in neuroevolution (ie the evolution of artificial neural networks) that circumvents the problem of deceptive local optima. The main idea is to search only for behavioral novelty instead of for higher fitness values. Although such novelty search abandons following the gradient of the fitness function, if such gradients are deceptive they …