Adaptive Multifactorial Evolutionary Optimization for Multitask Reinforcement Learning

Simple item page
dc.contributor.authorMartinez, Aritz D.
dc.contributor.authorDel Ser, Javier
dc.contributor.authorOsaba, Eneko
dc.contributor.authorHerrera, Francisco
dc.contributor.institutionIA
dc.contributor.institutionQuantum
dc.date.issued2022-04-01
dc.descriptionPublisher Copyright: © 1997-2012 IEEE.
dc.description.abstractEvolutionary computation has largely exhibited its potential to complement conventional learning algorithms in a variety of machine learning tasks, especially those related to unsupervised (clustering) and supervised learning. It has not been until lately when the computational efficiency of evolutionary solvers has been put in prospective for training reinforcement learning models. However, most studies framed so far within this context have considered environments and tasks conceived in isolation, without any exchange of knowledge among related tasks. In this manuscript we present A-MFEA-RL, an adaptive version of the well-known MFEA algorithm whose search and inheritance operators are tailored for multitask reinforcement learning environments. Specifically, our approach includes crossover and inheritance mechanisms for refining the exchange of genetic material, which rely on the multilayered structure of modern deep-learning-based reinforcement learning models. In order to assess the performance of the proposed approach, we design an extensive experimental setup comprising multiple reinforcement learning environments of varying levels of complexity, over which the performance of A-MFEA-RL is compared to that furnished by alternative nonevolutionary multitask reinforcement learning approaches. As concluded from the discussion of the obtained results, A-MFEA-RL not only achieves competitive success rates over the simultaneously addressed tasks, but also fosters the exchange of knowledge among tasks that could be intuitively expected to keep a degree of synergistic relationship.en
dc.description.sponsorshipThe work of Aritz D. Martinez and Eneko Osaba was supported by the Basque Government through the ELKARTEK Program (3KIA Project) under Grant KK-2020/00049. The work of Javier Del Ser was supported in part by the Basque Government through the ELKARTEK Program (3KIA Project) under Grant KK-2020/00049, and in part by the Consolidated Research Group MATHMODE (IT1294-19) granted by the Department of Education of the Basque Government. The work of Francisco Herrera was supported in part by the Spanish Government through (SMART-DaSCI) under Grant TIN2017-89517-P, and in part by the BBVA Foundation through Ayudas Fundacion BBVA a Equipos de Investigacion Científica 2018 call (DeepSCOP)
dc.description.statusPeer reviewed
dc.format.extent15
dc.identifier.citationMartinez , A D , Del Ser , J , Osaba , E & Herrera , F 2022 , ' Adaptive Multifactorial Evolutionary Optimization for Multitask Reinforcement Learning ' , IEEE Transactions on Evolutionary Computation , vol. 26 , no. 2 , pp. 233-247 . https://doi.org/10.1109/TEVC.2021.3083362
dc.identifier.doi10.1109/TEVC.2021.3083362
dc.identifier.issn1089-778X
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85107232821&partnerID=8YFLogxK
dc.language.isoeng
dc.relation.ispartofIEEE Transactions on Evolutionary Computation
dc.relation.projectIDDepartment of Education of the Basque Government
dc.relation.projectIDSMART-DaSCI, TIN2017-89517-P
dc.relation.projectIDSpanish Government
dc.relation.projectIDFundación BBVA, FBBVA
dc.relation.projectIDEusko Jaurlaritza, IT1294-19-KK-2020/00049
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subject.keywordsEvolutionary multitasking
dc.subject.keywordsmultifactorial optimization (MFO)
dc.subject.keywordsmultitask reinforcement learning
dc.subject.keywordsneuroevolution (NE)
dc.subject.keywordsSoftware
dc.subject.keywordsTheoretical Computer Science
dc.subject.keywordsComputational Theory and Mathematics
dc.titleAdaptive Multifactorial Evolutionary Optimization for Multitask Reinforcement Learningen
dc.typejournal article
Files