Archive-based cooperative coevolutionary algorithms

Abstract

Archive-based cooperative coevolutionary algorithms attempt to retain a set of individuals which act as good collaborators for other coevolved individuals in the evolutionary system. We introduce a new archive-based algorithm, called iCCEA, which compares favorably with other cooperative coevolutionary algorithms. We explain the current problems with cooperative coevolution which have given rise to archive methods, detail the iCCEA algorithm, compare it against other traditional and archive-based methods on basic problem domains, and discuss the reasons behind the performance of various algorithms.

Reference sharing: a new collaboration model for cooperative coevolution

“…An archive-based collaboration model (Panait et al 2006), a variant of 1 + N collaboration model, maintains collaborators in archives, one per population. The archives preserve useful information in past generations.…”

“…Those individuals who mostly help individuals from other populations to improve themselves are intended to be good collaborators and encouraged to collaborate with new individuals in the next generation. Panait et al (2006) designed their archives with a dynamic size. Initially, the archive of each population was a copy of the population itself.…”

Cooperative coevolution and univariate estimation of distribution algorithms

“…But even this upper bound is problematic: large values of N are more accurate and more likely to converge to the optimum; but may require more total number of evaluations than is realistic given the evaluation budget. Thus recent empirical work [2,9] has focused on reducing the total number of evaluations by identifying an archive of individuals from the collaborating population(s) which provide as good an assessment as testing with the entire collaborating population would provide. As it turns out, this archive size can be very small, resulting in a significant reduction in evaluations.…”

Cooperative Coevolution for Agrifood Process Modeling

“…Individuals of a subpopulation are evaluated by aggregation with individuals of other subpopulations. Multi-species cooperative co-evolution has been applied to various problems [43,55,54,22,36,66], including learning problems [8], and some theoretical analyses have been recently proposed, see [48,10,52], or [65] for an analysis considering a relationship between cooperative co-evolution and evolutionary game theory.…”