Novelty-driven cooperative coevolution
Autor(a) principal: | |
---|---|
Data de Publicação: | 2017 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10071/13859 |
Resumo: | 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. |
id |
RCAP_7dc1c53c75f04e0929c6e41aaa5bac78 |
---|---|
oai_identifier_str |
oai:repositorio.iscte-iul.pt:10071/13859 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Novelty-driven cooperative coevolutionCooperative coevolutionMultiagent systemsNeuroevolutionNovelty searchConvergence to stable statesBehaviour explorationCooperative 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.MIT Press2017-07-05T10:06:44Z2017-01-01T00:00:00Z20172019-04-01T17:25:17Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10071/13859eng1063-656010.1162/EVCO_a_00173Gomes, J.Mariano, P.Christensen, A. L.info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-11-09T17:23:45Zoai:repositorio.iscte-iul.pt:10071/13859Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T22:10:52.527154Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Novelty-driven cooperative coevolution |
title |
Novelty-driven cooperative coevolution |
spellingShingle |
Novelty-driven cooperative coevolution Gomes, J. Cooperative coevolution Multiagent systems Neuroevolution Novelty search Convergence to stable states Behaviour exploration |
title_short |
Novelty-driven cooperative coevolution |
title_full |
Novelty-driven cooperative coevolution |
title_fullStr |
Novelty-driven cooperative coevolution |
title_full_unstemmed |
Novelty-driven cooperative coevolution |
title_sort |
Novelty-driven cooperative coevolution |
author |
Gomes, J. |
author_facet |
Gomes, J. Mariano, P. Christensen, A. L. |
author_role |
author |
author2 |
Mariano, P. Christensen, A. L. |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Gomes, J. Mariano, P. Christensen, A. L. |
dc.subject.por.fl_str_mv |
Cooperative coevolution Multiagent systems Neuroevolution Novelty search Convergence to stable states Behaviour exploration |
topic |
Cooperative coevolution Multiagent systems Neuroevolution Novelty search Convergence to stable states Behaviour exploration |
description |
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. |
publishDate |
2017 |
dc.date.none.fl_str_mv |
2017-07-05T10:06:44Z 2017-01-01T00:00:00Z 2017 2019-04-01T17:25:17Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10071/13859 |
url |
http://hdl.handle.net/10071/13859 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
1063-6560 10.1162/EVCO_a_00173 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
MIT Press |
publisher.none.fl_str_mv |
MIT Press |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799134662773178368 |