A multiset genetic algorithm for the optimization of deceptive problems
Proceedings of the 15th annual conference on Genetic and evolutionary computation
| Hi-index | 0.00 |
The Multiset Genetic Algorithm (MuGA) was adapted to real coded problems, tested in benchmark functions, and compared to competitive algorithms. Genetic operators were adapted to take into account the multiset representation of the population, which is the main distinctive feature and advantage of MuGA. The new operators extend existing ones, incorporating the influence of the number of copies each multi-individual has. Preliminary results obtained, without particular tuning efforts, position MuGA close to the best results obtained by other approaches. Future work will improve limitations found in maintaining a high genetic diversity.