生态系统中协同进化的含义是几个生存能力相关联的种群的同时进化,在遗传算法中应用协同进化的实质是改变了个体适应度的计算方法:经典遗传算法中个体的适应度由它的染色体所决定,协同进化中个体的适应度却是由个体在协同关系中的表现决定。根据个体之间的适应度关联方式的不同,协同进化在遗传算法中应用可以分为两种:竞争协同进化算法、合作协同进化算法。竞争协同进化算法中的个体适应度由个体在竞争中的表现决定;合作协同进化算法中的个体适应度决定于个体在合作中的表现。对这两种方法的实质以及主要思想进行了述评。
Ecological coevolution refers to the simultaneous evolution of two or more species with inter-species assessment. The essence to apply coevolution in genetic algorithms is to change the way to evaluate individuals. Standard genetic algorithms evaluate individuals by their chromosomes, independent of other individuals in the evolutionary system. Coevolutionary algorithms evaluate individuals by their performance relative to others. According the way to evaluate individuals, the applications of coevolution in genetic algorithms are generally divided into two categories: Competitive Coevolution Algorithm (Comp-CEA) and Cooperative Coevolutionary Algorithm (Coop-CEA). Comp-CEA assesses individuals by their competitive performance in relation to evaluators. Coop-CEA assesses individuals by their cooperative performance relative to cooperators. This paper commented on the main ideas of Comp-CEA and Coop-CEA and the relevant key skills.