Skip navigation
User training | Reference and search service

Library catalog

Content aggregators
Please use this identifier to cite or link to this item:

Title: Novelty-driven cooperative coevolution
Authors: Gomes, J.
Mariano, P.
Christensen, A. L.
Keywords: Cooperative coevolution
Multiagent systems
Novelty search
Convergence to stable states
Behaviour exploration
Issue Date: 2017
Publisher: MIT Press
Abstract: Cooperative coevolutionary algorithms (CCEAs) rely on multiple coevolving populations for the evolution of solutions composed of coadapted components. CCEAs enable, for instance, the evolution of cooperative multiagent systems composed of heterogeneous agents, where each agent is modelled as a component of the solution. Previous works have, however, shown that CCEAs are biased toward stability: the evolutionary process tends to converge prematurely to stable states instead of (near-)optimal solutions. In this study, we show how novelty search can be used to avoid the counterproductive attraction to stable states in coevolution. Novelty search is an evolutionary technique that drives evolution toward behavioural novelty and diversity rather than exclusively pursuing a static objective. We evaluate three novelty-based approaches that rely on, respectively (1) the novelty of the team as a whole, (2) the novelty of the agents’ individual behaviour, and (3) the combination of the two. We compare the proposed approaches with traditional fitness-driven cooperative coevolution in three simulated multirobot tasks. Our results show that team-level novelty scoring is the most effective approach, significantly outperforming fitness-driven coevolution at multiple levels. Novelty-driven cooperative coevolution can substantially increase the potential of CCEAs while maintaining a computational complexity that scales well with the number of populations.
Peer reviewed: yes
DOI: 10.1162/EVCO_a_00173
ISSN: 1063-6560
Accession number: WOS:000406004500004
Appears in Collections:IT-RI - Artigo em revista internacional com arbitragem científica

Files in This Item:
File Description SizeFormat 
Novelty-Driven Cooperative Coevolution.pdfVersão Editora1.37 MBAdobe PDFView/Open

FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpace
Formato BibTex MendeleyEndnote Currículo DeGóis 

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.