ABSTRACT
Most genotype-to-phenotype mappings in EAs are redundant, i.e., multiple genotypes can map to the same phenotype. Phenotypes are accessible from one to another through point mutations. However, these mutational connections can be unevenly distributed among phenotypes. Quantitative analysis of such connections helps better characterize the robustness and evolvability of an EA. In this study, we propose two genotype-to-phenotype mapping mechanisms for linear genetic programming (LGP), where the execution and output of a linear genetic program are varied by a regulator. We investigate how such regulatory mappings can alter the genotypic connections among different phenotypes and the robustness and evolvability of phenotypes. We also compare the search ability of LGP using the conventional mapping versus the regulatory mappings, and observe that the regulatory mappings improve the efficiency in all three search scenarios, including random walk, hill climbing, and novelty search.
- Markus Brameier and Wolfgang Banzhaf. 2007. Linear Genetic Programming. Springer.Google Scholar
- Ting Hu and Wolfgang Banzhaf. 2016. Quantitative analysis of evolvability using vertex centralities in phenotype network. In Proceedings of the Genetic and Evolutionary Computation Conference 2016. 733--740.Google Scholar
- Ting Hu and Wolfgang Banzhaf. 2018. Neutrality, robustness, and evolvability in genetic programming. In Genetic Programming Theory and Practice XIV, R Riolo, B Worzel, B Goldman, and B Tozier (Eds.). Springer, Chapter 7, 101--117.Google Scholar
- Ting Hu, Wolfgang Banzhaf, and Jason H Moore. 2014. The effects of recombination on phenotypic exploration and robustness in evolution. Artificial Life 20, 4 (2014), 457--470.Google ScholarDigital Library
- Ting Hu, Marco Tomassini, and Wolfgang Banzhaf. 2019. Complex network analysis of a genetic programming phenotype network. In European Conference on Genetic Programming. Springer, 49--63.Google ScholarDigital Library
- Gregory F Lawler and Vlada Limic. 2010. Random walk: a modern introduction. Vol. 123. Cambridge University Press.Google Scholar
- Joel Lehman and Kenneth O Stanley. 2011. Novelty search and the problem with objectives. In Genetic programming theory and practice IX. Springer, 37--56.Google Scholar
- Naoki Masuda, Mason A Porter, and Renaud Lambiotte. 2017. Random walks and diffusion on networks. Physics reports 716 (2017), 1--58.Google Scholar
- Joshua L. Payne and Andreas Wagner. 2019. The causes of evolvability and their evolution. Nature Reviews Genetics (2019).Google Scholar
- Bart Selman and Carla P Gomes. 2006. Hill-climbing search. Encyclopedia of cognitive science 81 (2006), 82.Google Scholar
- Andreas Wagner. 2008. Robustness and evolvability: a paradox resolved. Proceedings of the Royal Society B: Biological Sciences 275, 1630 (2008), 91--100.Google ScholarCross Ref
Index Terms
- Regulatory genotype-to-phenotype mappings improve evolvability in genetic programming
Recommendations
Evolvability and complexity properties of the digital circuit genotype-phenotype map
GECCO '21: Proceedings of the Genetic and Evolutionary Computation ConferenceRecent research on genotype-phenotype (G-P) maps in natural evolution has contributed significantly to our understanding of neutrality, redundancy, robustness, and evolvability. Here we investigate the properties of the digital logic gate G-P map and ...
A network perspective on genotype–phenotype mapping in genetic programming
AbstractGenotype–phenotype mapping plays an essential role in the design of an evolutionary algorithm. Variation occurs at the genotypic level but fitness is evaluated at the phenotypic level, therefore, this mapping determines if and how variations are ...
Quantitative Analysis of Evolvability using Vertex Centralities in Phenotype Network
GECCO '16: Proceedings of the Genetic and Evolutionary Computation Conference 2016In an evolutionary system, robustness describes the resilience to mutational and environmental changes, whereas evolvability captures the capability of generating novel and adaptive phenotypes. The research literature has not seen an effective ...
Comments