A coevolutionary algorithm with spieces as varying contexts

Abstract

A coevolutionary algorithm is an extension of the conventional genetic algorithm that incorporates the strategy of divide and conquer in developing a complex solution in the form of interacting co-adapted subcomponents. It takes advantage of the reduced search space by evolving species associated with subsets of variables independently but cooperatively. In this paper we propose an efficient coevolutionary algorithm combining species splitting and merging together. Our algorithm conducts efficient local search in the reduced search space by splitting species for independent variables while it conducts global search by merging species for interdependent variables. We have experimented the proposed algorithm with several benchmarking function optimization and have shown that the algorithm outperforms existing coevolutionary algorithms