Using Machine Learning to Improve Evolutionary Multi-Objective Optimization

Abstract

Multiobjective optimization problems (MOPs) arise in many real-world applications. MOPs involve two or more objectives with the aim to be optimized. With these problems im- provement of one objective may led to deterioration of another. The primary goal of most multiobjective evolutionary algorithms (MOEA) is to generate a set of solutions for approx- imating the whole or part of the Pareto optimal front, which could provide decision makers a good insight to the problem.Over the last decades or so, several different and remarkable multiobjective evolutionary algorithms, have been developed with successful applications.

However, MOEAs are still in their infancy. The objective of this research is to study how to use and apply machine learning (ML) to improve evolutionary multiobjective opti- misation (EMO). The EMO method is the multiobjective evolutionary algorithm based on decomposition (MOEA/D). The MOEA/D has become one of the most widely used algo- rithmic frameworks in the area of multiobjective evolutionary computation and won has won an international algorithm contest.