Evolvability in Evolutionary Robotics: Evolving the Genotype-Phenotype Mapping

Abstract

A completely evolvable genotype-phenotype mapping (ceGPM) is studied with respect to its capability of improving the flexibility of artificial evolution. By letting mutation affect not only controller genotypes, but also the mapping from genotype to phenotype, the future e effects of mutation can change over time. In this way, the need for prior parameter adaptation can be reduced. Experiments indicate that the ceGPM is capable of robustly adapting to a benchmark behavior. A comparison to a related approach shows significant improvements in evolvability.