Abstract
Novelty search in evolutionary robotics measures a distance of potential novelty solutions to their k-nearest neighbors in the search space. This distance presents an additional objective to the fitness function, with which each individual in population is evaluated. In this study, the novelty search was applied within the differential evolution. The preliminary results on CEC-14 Benchmark function suite show its potential for using also in the future.
Author supplied keywords
Cite
CITATION STYLE
Fister, I., Iglesias, A., Galvez, A., Del Ser, J., & Osaba, E. (2018). Using novelty search in differential evolution. In Communications in Computer and Information Science (Vol. 887, pp. 534–542). Springer Verlag. https://doi.org/10.1007/978-3-319-94779-2_46
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
