Improving the Quality of the Pareto Frontier Approximation Obtained by Semi-elitist Evolutionary Multi-agent System Using Distributed and Decentralized Frontier Crowding Mechanism

摘要

The paper presents one of additional mechanisms called distributed frontier crowding which can be introduced to the Semi-Elitist Evolutionary Multi Agent System—selEMAS and which can significantly improve the quality of obtained Pareto frontier approximation. The preliminary experimental comparative studies are based on a typical multi-objective problem presenting the most important features of the proposed approach.