On the Combination of Coevolution and Novelty Search

F. Franz*, J. Paredis, R. Mockel

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

269 Downloads (Pure)

Abstract

This paper develops a new method for coevolution, named Fitness-Diversity Driven Coevolution (FDDC). This approach builds on existing methods by a combination of a (predator-prey) Coevolutionary Genetic Algorithm (CGA) and novelty search. The innovation lies in replacing the absolute novelty measure with a relative one, called Fitness-Diversity. FDDC overcomes problems common in both CGAs (premature convergence and unbalanced coevolution) and in novelty search (construction of an archive). As a proof of principle, Spring Loaded Inverted Pendulums (SLIPs) are coevolved with 2Dterrains the SLIPs must learn to traverse.
Original languageEnglish
Title of host publicationIEEE Congress on Evolutionary Computation
PublisherIEEE
Pages201-208
Number of pages8
ISBN (Print)9781509046010
DOIs
Publication statusPublished - 2017
EventIEEE Congress on Evolutionary Computation (CEC) - San Sebastián, Spain
Duration: 5 Jun 20178 Jun 2017
https://www.esteco.com/corporate/ieee-congress-evolutionary-computation-cec-2017#:~:text=CEC%202017%20is%20a%20congress,for%20the%20benefit%20of%20humanity.

Publication series

SeriesIEEE Congress on Evolutionary Computation

Conference

ConferenceIEEE Congress on Evolutionary Computation (CEC)
Abbreviated titleCEC 2017
Country/TerritorySpain
CitySan Sebastián
Period5/06/178/06/17
Internet address

Keywords

  • LOADED INVERTED PENDULUM
  • OPTIMIZATION

Cite this