Competing Crossovers in an Adaptive GA Framework

In this paper we report the results of experiments on multi-parent reproduction in an adaptive genetic algorithm framework. An adaptive mechanism based on competing subpopulations is incorporated into the algorithm in order to detect the best crossovers. Experiments on a number of test functions designed for studying crossover performance show that multi-parent reproduction is superior to traditional two-parent crossover, but the adaptive mechanism is not able to reward better crossovers according to their performance. Nevertheless, the adaptive algorithm exhibits comparable performance to the nonadaptive variant using the best crossover alone. This implies that it is sound and safe to use an adaptive GA with competing subpopulations /crossovers, instead of performing time consuming comparisons in search of the best operators. 1 Introduction The present investigation combines research goals and techniques from two sub-areas in evolutionary computation. One area is the study of reprodu..