Please use this identifier to cite or link to this item:
http://hdl.handle.net/10071/25483
Author(s): | Mariano, P. Christensen, A. L. Gomes, J. |
Editor: | Thomas Bartz-Beielstein, Jürgen Branke, Bogdan Filipič, Jim Smith |
Date: | 2014 |
Title: | Novelty search in competitive coevolution |
Volume: | 8672 |
Event title: | 13th International Conference |
ISBN: | 978-3-319-10762-2 |
DOI (Digital Object Identifier): | 10.1007/978-3-319-10762-2_23 |
Keywords: | Competitive coevolution Behavioural diversity Novelty search Convergence Evolutionary robotics |
Abstract: | One of the main motivations for the use of competitive coevolution systems is their ability to capitalise on arms races between competing species to evolve increasingly sophisticated solutions. Such arms races can, however, be hard to sustain, and it has been shown that the competing species often converge prematurely to certain classes of behaviours. In this paper, we investigate if and how novelty search, an evolutionary technique driven by behavioural novelty, can overcome convergence in coevolution. We propose three methods for applying novelty search to coevolutionary systems with two species: (i) score both populations according to behavioural novelty; (ii) score one population according to novelty, and the other according to fitness; and (iii) score both populations with a combination of novelty and fitness. We evaluate the methods in a predator-prey pursuit task. Our results show that novelty-based approaches can evolve a significantly more diverse set of solutions, when compared to traditional fitness-based coevolution. |
Peerreviewed: | yes |
Access type: | Open Access |
Appears in Collections: | IT-CRI - Comunicações a conferências internacionais |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
conferenceobject_81101.pdf | Versão Aceite | 344,14 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.