Finding a diverse set of decision variables in evolutionary many-objective optimization
Kaname Narukawa · 2013
In this paper, we modify an evolutionary many-objective optimization algorithm so that it can find a diverse set of solutions in the decision variable space. The modification is based on considering the Euclidean distance in the decision variable space. The effect of our modification is examined by using benchmark test problems. From computational experiments, we can say that a diverse set of solutions in the decision variable space is searched by the modification.