Chromatic Selection - An Oversimplified Approach to Multi-objective Optimization

摘要

This short paper introduces the chromatic selection, a simple technique implementable with few tens of lines of code, that enable handling multi-value fitness functions with a single-objective evolutionary optimizer. The chromatic selection is problem independent, requires no parameter tuning, and can be used as a drop-in replacement for both parent and survival selections. The resulting tool will not be a full-fledged multi-objective optimizer, lacking the ability to manage Pareto fronts, but it will efficiently seek a single, reasonable, compromise solution. In several practical problems, the time saved, both in computation and development, could represent a substantial advantage.