A hierarchical cooperative evolutionary algorithm

To successfully search multiple coadaptive subcomponents in a solution, we developed a novel cooperative evolutionary algorithm based on a new computational multilevel selection framework. This algorithm constructs cooperative solutions hierarchically by implementing the idea of group selection. We show that this simple and straightforward algorithm is able to accelerate evolutionary speed and improve solution accuracy on string covering problems as compared to other EAs used in literature. In addition, the structure of the solution and the roles played by each subcomponent in the solution emerge as a result of evolution without human interference. Categories and Subject Descriptors I.2.8 [Problem Solving, Control Methods, and Search]: Heuristic methods General Terms Algorithms, Design, Experimentation Keywords Cooperative evolutionary algorithms, Multilevel selection, Hierarchical model, Emergent decomposition, Coevolution

• Type: Conference
• Year: 2010
• Where: GECCO
• Authors: Shelly Xiaonan Wu, Wolfgang Banzhaf
• Keywords: Cooperative Evolutionary Algorithms, GECCO 2010, Multilevel Selection, Multilevel Selection Framework, Optimization