Adapting a Genotype-phenotype Mapping to Phenotypic Complexity

The marvel of biological development has motivated researchers to apply artificial development in bio-inspired systems. Among the possible features of artificial development that are being investigated is the potential for improving scalability of evolutionary optimization techniques,by applying artificial development as an indirect mapping.Currently, few guidelines exist as to when development is likely to achieve such improvements. We investigate one guideline based on the complexity of the phenotypic objective and propose a grammatical mapping which can adapt to this complexity. Earlier findings on the correlation between the performance of indirect mappings and phenotypic complexity are confirmed in a new context. Adaptation of an indirect mapping to phenotypic complexity is shown to work well given certain conditions.