Designing a generalised reward for Building Energy Management Reinforcement Learning agents

Simple item page
dc.contributor.authorMartinez, Ruben Mulero
dc.contributor.authorGoikolea, Benat Arregi
dc.contributor.authorBeitia, Inigo Mendialdua
dc.contributor.authorMartinez, Roberto Garay
dc.contributor.authorMulero, Rubén
dc.contributor.authorArregi, Beñat
dc.contributor.authorMendialdua, Iñigo
dc.contributor.authorGaray, Roberto
dc.contributor.editorSolic, Petar
dc.contributor.editorNizetic, Sandro
dc.contributor.editorRodrigues, Joel J. P. C.
dc.contributor.editorRodrigues, Joel J.P.C.
dc.contributor.editorGonzalez-de-Artaza, Diego Lopez-de-Ipina
dc.contributor.editorPerkovic, Toni
dc.contributor.editorCatarinucci, Luca
dc.contributor.editorPatrono, Luigi
dc.contributor.institutionDIGITALIZACIÓN Y AUTOMATIZACIÓN DE LA CONSTRUCCIÓN
dc.contributor.institutionEDIFICACIÓN DE ENERGÍA POSITIVA
dc.contributor.institutionTecnalia Research & Innovation
dc.date.issued2021-09-08
dc.descriptionPublisher Copyright: © 2021 University of Split, FESB.
dc.description.abstractThe reduction of the carbon footprint of buildings is a challenging task, partly due to the conflicting goals of maximising occupant comfort and minimising energy consumption. An intelligent management of Heating, Ventilation and Air Conditioning (HVAC) systems is creating a promising research line in which the creation of suitable algorithms could reduce energy consumption maintaining occupants' comfort. In this regard, Reinforcement Learning (RL) approaches are giving a good balance between data requirements and intelligent operations to control building systems. However, there is a gap concerning how to create a generalised reward signal that can train RL agents without delimiting the problem to a specific or controlled scenario. To tackle it, an analysis and discussion is presented about the necessary requirements for the creation of generalist rewards, with the objective of laying the foundations that allow the creation of generalist intelligent agents for building energy management.en
dc.description.statusPeer reviewed
dc.format.extent6
dc.format.extent203716
dc.identifier.citationMartinez , R M , Goikolea , B A , Beitia , I M , Martinez , R G , Mulero , R , Arregi , B , Mendialdua , I & Garay , R 2021 , Designing a generalised reward for Building Energy Management Reinforcement Learning agents . in P Solic , S Nizetic , J J P C Rodrigues , J J P C Rodrigues , D L-I Gonzalez-de-Artaza , T Perkovic , L Catarinucci & L Patrono (eds) , unknown . 2021 6th International Conference on Smart and Sustainable Technologies, SpliTech 2021 , IEEE , pp. 1-6 , 6th International Conference on Smart and Sustainable Technologies, SpliTech 2021 , Bol and Split , Croatia , 8/09/21 . https://doi.org/10.23919/SpliTech52315.2021.9566345
dc.identifier.citationconference
dc.identifier.doi10.23919/SpliTech52315.2021.9566345
dc.identifier.isbn978-1-6654-4202-2
dc.identifier.isbn978-953-290-112-2
dc.identifier.isbn978-9-5329-0112-2
dc.identifier.isbn9789532901122
dc.identifier.otherresearchoutputwizard: 11556/1256
dc.identifier.otherresearchoutputwizard: 11556/1255
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85118449323&partnerID=8YFLogxK
dc.language.isoeng
dc.publisherIEEE
dc.relation.ispartofunknown
dc.relation.ispartofseries2021 6th International Conference on Smart and Sustainable Technologies, SpliTech 2021
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subject.keywordsReinforcement learning
dc.subject.keywordsReward
dc.subject.keywordsGeneralised
dc.subject.keywordsBuilding
dc.subject.keywordsEnergy efficiency
dc.subject.keywordsHVAC
dc.subject.keywordsReinforcement learning
dc.subject.keywordsReward
dc.subject.keywordsGeneralised
dc.subject.keywordsBuilding
dc.subject.keywordsEnergy efficiency
dc.subject.keywordsHVAC
dc.subject.keywordsArtificial Intelligence
dc.subject.keywordsComputer Science Applications
dc.subject.keywordsDecision Sciences (miscellaneous)
dc.subject.keywordsRenewable Energy, Sustainability and the Environment
dc.subject.keywordsSafety, Risk, Reliability and Quality
dc.subject.keywordsHealth Informatics
dc.subject.keywordsSDG 7 - Affordable and Clean Energy
dc.subject.keywordsSDG 12 - Responsible Consumption and Production
dc.subject.keywordsSDG 13 - Climate Action
dc.subject.keywordsFunding Info
dc.subject.keywordsThe work described in this paper was partially supported by the Basque Government under ELKARTEK project (LANTEGI4.0 KK-2020/00072).
dc.subject.keywordsThe work described in this paper was partially supported by the Basque Government under ELKARTEK project (LANTEGI4.0 KK-2020/00072).
dc.subject.keywordsProject ID
dc.subject.keywordsLANTEGI4.0 KK-2020/00072
dc.subject.keywordsLANTEGI4.0 KK-2020/00072
dc.titleDesigning a generalised reward for Building Energy Management Reinforcement Learning agentsen
dc.typeconference output
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
2021136865.pdf
Size:
198.94 KB
Format:
Adobe Portable Document Format
Download