MOEA-HH

An open-source hyper-heuristic framework for multi-objective optimization.

Introduction

The multi-objective optimization technique is widely used in a variety of applications. Currently, multi-objective evolutionary algorithms (MOEAs) exhibit impressive performance on various multi-objective optimization tasks. However, most of existing MOEAs are designed by human experts and may not be well suited to the specific problem. Moreover, implementing an industrial-grade software package for real-time multi-objective optimization tasks is even harder due to the low efficiency of existing evolutionary algorithms.

Consequently, this package hopes to use machine learning techniques to predict the non-dominated solution directly. Yet, it is impossible to predict the non-dominated solution without making any assumptions due to the free-lunch theorem. In this package, we hope to develop a ranking tool that will give a high rank to non-dominated solutions for a given set of solutions.

Usage

Installation

pip install git+https://github.com/zhenlingcn/MOEA-HH.git

Requirements

Compatibility

Licence

Authors

MOEA-HH was written by Hengzhe Zhang.