Abstract
We propose a chemical genetic algorithm (CGA) in which several types of molecule react with each other in a cell. A cell includes a binary string (DNA) and smaller molecules, and the fundamental mapping from binary substrings on DNA (genotype) to real values for the output parameters (phenotype) is specified by a set of molecules called aminoacyl-tRNAs. Through evolutionary modification of the genetic information on the DNA, the codes on the DNA and the genotype-to-phenotype translation coevolve, which allows optimization of the code translation during evolution. The CGA is applied to several benchmark problems, and its effectiveness is demonstrated in comparison with a simple genetic algorithm (SGA).
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was presented in part at the 8th International Symposium on Artificial Life and Robotics, Oita, Japan, January 24–26, 2003
About this article
Cite this article
Suzuki, H., Sawai, H. Chemical genetic algorithms – a coevolutionary method to optimize code translation in GAs. Artif Life Robotics 8, 46–51 (2004). https://doi.org/10.1007/s10015-004-0287-7
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/s10015-004-0287-7