作者: W. B. Langdon , W. Banzhaf
关键词: Genetic programming 、 Algorithm complexity 、 Tree (data structure) 、 Genetic algorithm 、 Theoretical computer science 、 Entropy (information theory) 、 Computer science 、 Algorithm 、 Random binary tree 、 Crossover 、 Random walk
摘要: To investigate the fundamental causes of bloat, six artificial random binary tree search spaces are presented. Fitness is given by program syntax (the genetic programming genotype). GP populations evolved on both problems and with "building blocks". These compared to explicit ineffective code (introns, junk code, inviable code). Our results suggest entropy walk explanation bloat remains viable. The hard building block problem might be used in further studies, e.g. standard subtree crossover.