Adaptive Adjustment of Weight Parameters for Diploid Genetic Algorithm with a Network Structure

A new diploid genetic algorithm (DipGA) with network structure which enables autonomous adaptation to dynamic environment is proposed in this paper. The proposed algorithm has the network weights changed adaptively according to the pattern of dynamics in the environment during the evolving loop. The state of the art of the algorithm is that the genotypes of population and network parameters controlling phenotypes are co-evolved by the dynamics of environment. Thus, the algorithm can memorize the dynamics of environment in mutual effects between genes and manifestation networks. In order to evaluate the adaptation, simulation experiments based on typical benchmark functions with dynamics are conducted. The experiment results show that the algorithm improves the performance of following to the change of environment, and adapts to the dynamics.