Novel Multi-Objective Genetic Algorithm Based on Static Bayesian Game Strategy

Abstract

Multi-objective evolutionary algorithms (MOEAs) have been the mainstream to solve multi-objectives optimization problems. In this paper we add the static Bayesian game strategy into MOGA and propose a novel multi-objective genetic algorithm(SBG-MOGA). Conventional MOGAs use non-dominated sorting methods to push the population to move toward the real Pareto front. This approach has a good performance at earlier stages of the evolution, however it becomes hypodynamic at the later stages. In SBG-MOGA the objectives to be optimized are similar to players in a static Bayesian game. A player is a rational person who has his own strategy space. A player selects a strategy and takes an action to realize his strategy in order to achieve the maximal income for the objective he works on. The game strategy will generate a tensile force over the population and this will obtain a better multi-objective optimization performance. Moreover, the algorithm is verified by several simulation experiments and its performance is tested by different benchmark functions.