Challenges of ELA-based Function Evolution using Genetic Programming - Reproducability files

Zenodo (CERN European Organization for Nuclear Research)

Abstract

This repository contains the data and code for the paper "Challenges of ELA-based Function Evolution using Genetic Programming" This repository consists of separated folders, which contain the following data: ## Code: This is the main code used to run the GP functions. The main executable is 'main_gp.py', which executes a single run of the GP system (based on the passed-in argument, which is an index from 0-71 in our experiments). The data for the BBOB functions are generated using the 'preliminary' folder and the 'get_ela_preliminary.py' file. ## Data_GP: This contains the full logs from each GP run, separated by target function and dimension. ## data_random_func: This contains the same kind of data but for the Random Function Generator. ## Reproducibility: This contains all code used to analyse and visualize the resulting data. The notebook is structured in the same way as the paper, separated by figure.

Authors 7

1. Fu Xing Long

   BMW (Germany) · BMW Group (Germany)

   Affiliation as printed

   BMW Group

2. Diederick Vermetten Aachen

   Leiden University

   Affiliation as printed

   Leiden University

3. Anna V. Kononova Aachen

   Leiden University

   Affiliation as printed

   Leiden University

4. Roman Kalkreuth

   Sorbonne Université

   Affiliation as printed

   Sorbonne University

5. Kaifeng Yang

   University of Applied Sciences Upper Austria

   Affiliation as printed

   University of Applied Sciences Upper Austria

6. Thomas Bäck Aachen

   Leiden University

   Affiliation as printed

   Leiden University

7. Bas van Stein Aachen

   Leiden University

   Affiliation as printed

   Leiden University