Dr Leni Le Goff L.LeGoff2@napier.ac.uk
Lecturer
On Pros and Cons of Evolving Topologies with Novelty Search
Le Goff, L�ni K.; Hart, Emma; Coninx, Alexandre; Doncieux, St�phane
Authors
Prof Emma Hart E.Hart@napier.ac.uk
Professor
Alexandre Coninx
St�phane Doncieux
Abstract
Novelty search was proposed as a means of circumventing deception and providing selective pressure towards novel behaviours to provide a path towards open-ended evolution. Initial implementations relied on neuro-evolution approaches which increased network complexity over time. However, although many studies have reported impressive results, it is still not clear whether the benefits of evolving topologies are outweighed by the overall complexity of the approach. Given that novelty search can also be combined with evolutionary methods that utilise fixed topologies, we undertake a systematic comparison of evolving topologies, using two types of fixed topology networks in conjunction with novelty search on two test-beds. We show that evolving topologies do not systematically help, and discuss the practical consequences of these results and the research perspectives opened up.
Citation
Le Goff, L. K., Hart, E., Coninx, A., & Doncieux, S. (2020, July). On Pros and Cons of Evolving Topologies with Novelty Search. Presented at ALIFE 2020: The 2020 Conference on Artificial Life, Online
Presentation Conference Type | Conference Paper (published) |
---|---|
Conference Name | ALIFE 2020: The 2020 Conference on Artificial Life |
Start Date | Jul 13, 2020 |
End Date | Jul 18, 2020 |
Acceptance Date | Jun 1, 2020 |
Online Publication Date | Jul 14, 2020 |
Publication Date | 2020-07 |
Deposit Date | Jul 15, 2020 |
Publicly Available Date | Jul 15, 2020 |
Publisher | MIT Press |
Pages | 423-431 |
Book Title | ALIFE 2020: The 2020 Conference on Artificial Life |
DOI | https://doi.org/10.1162/isal_a_00291 |
Public URL | http://researchrepository.napier.ac.uk/Output/2675916 |
Files
On Pros And Cons Of Evolving Topologies With Novelty Search
(1.3 Mb)
PDF
Publisher Licence URL
http://creativecommons.org/licenses/by/4.0/
Copyright Statement
Published under a Creative Commons Attribution 4.0 International (CC BY 4.0) license.
You might also like
Evolutionary Computation Combinatorial Optimization.
(2004)
Journal Article
A hyper-heuristic ensemble method for static job-shop scheduling.
(2016)
Journal Article
A research agenda for metaheuristic standardization.
(2015)
Presentation / Conference Contribution
A Lifelong Learning Hyper-heuristic Method for Bin Packing
(2015)
Journal Article