Fractal proteins are a new evolvable method of mapping genotype to phenotype through a developmental process, where genes are expressed into proteins comprised of subsets of the Mandelbrot Set. The resulting network of gene and protein interactions can be designed by evolution to produce specific patterns, that in turn can be used to solve problems. Here the use of fractal gene regulatory networks for learning a robot path through a series of obstacles is described. The results indicate the ability of this system to learn regularities in solutions and automatically create and use modules.
展开▼
