Name
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. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1109/SASO.2010.27 | Self-Adaptive and Self-Organizing Systems |
Keywords | Field | DocType |
genotype-phenotype mapping,benchmark behavior,artificial evolution,evolvable genotype-phenotype mapping,prior parameter adaptation,future e effect,related approach,controller genotype,evolutionary robotics,significant improvement,evolutionary computation,artificial life,automata,mobile robots | Artificial life,Genotype,Evolutionary robotics,Phenotype,Evolutionary algorithm,Evolvability,Computer science,Evolutionary computation,Aerospace electronics,Artificial intelligence,Computational biology,Distributed computing | Conference |
ISBN | Citations | PageRank |
978-0-7695-4232-4 | 0 | 0.34 |
References | Authors | |
3 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Lukas Koenig | 1 | 0 | 0.34 |
| Hartmut Schmeck | 2 | 1034 | 120.58 |