{"id":"https://openalex.org/W4408861211","doi":"https://doi.org/10.1109/icm62621.2025.10934768","title":"Real-World Implementation of Offline Model-Free Reinforcement Learning for Thermostat Control","display_name":"Real-World Implementation of Offline Model-Free Reinforcement Learning for Thermostat Control","publication_year":2025,"publication_date":"2025-02-28","ids":{"openalex":"https://openalex.org/W4408861211","doi":"https://doi.org/10.1109/icm62621.2025.10934768"},"language":"en","primary_location":{"id":"doi:10.1109/icm62621.2025.10934768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icm62621.2025.10934768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Mechatronics (ICM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003649415","display_name":"Sara Ghane","orcid":"https://orcid.org/0000-0002-0159-175X"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Sara Ghane","raw_affiliation_strings":["University of Antwerp - imec,IDLab - Faculty of Applied Engineering,Antwerp,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Antwerp - imec,IDLab - Faculty of Applied Engineering,Antwerp,Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044983597","display_name":"Furkan Elmaz","orcid":"https://orcid.org/0000-0002-7030-0784"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Furkan Elmaz","raw_affiliation_strings":["University of Antwerp - imec,IDLab - Faculty of Applied Engineering,Antwerp,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Antwerp - imec,IDLab - Faculty of Applied Engineering,Antwerp,Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011515106","display_name":"Stef Jacobs","orcid":"https://orcid.org/0000-0001-8179-3468"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Stef Jacobs","raw_affiliation_strings":["University of Antwerp,EMIB, Faculty of Applied Engineering,Antwerp,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Antwerp,EMIB, Faculty of Applied Engineering,Antwerp,Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029430198","display_name":"Thomas Huybrechts","orcid":"https://orcid.org/0000-0002-5611-6331"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Thomas Huybrechts","raw_affiliation_strings":["University of Antwerp - imec,IDLab - Faculty of Applied Engineering,Antwerp,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Antwerp - imec,IDLab - Faculty of Applied Engineering,Antwerp,Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074201753","display_name":"Ivan Verhaert","orcid":"https://orcid.org/0000-0002-5238-6123"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Ivan Verhaert","raw_affiliation_strings":["University of Antwerp,EMIB, Faculty of Applied Engineering,Antwerp,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Antwerp,EMIB, Faculty of Applied Engineering,Antwerp,Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015248763","display_name":"Siegfried Mercelis","orcid":"https://orcid.org/0000-0001-9355-6566"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Siegfried Mercelis","raw_affiliation_strings":["University of Antwerp - imec,IDLab - Faculty of Applied Engineering,Antwerp,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Antwerp - imec,IDLab - Faculty of Applied Engineering,Antwerp,Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059346676","display_name":"Erik Mannens","orcid":"https://orcid.org/0000-0001-7946-4884"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Erik Mannens","raw_affiliation_strings":["University of Antwerp - imec,IDLab,Department of Computer Science,Antwerp,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Antwerp - imec,IDLab,Department of Computer Science,Antwerp,Belgium","institution_ids":["https://openalex.org/I149213910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149213910"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10121","display_name":"Building Energy and Comfort Optimization","score":0.9674000144004822,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10121","display_name":"Building Energy and Comfort Optimization","score":0.9674000144004822,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11529","display_name":"Refrigeration and Air Conditioning Technologies","score":0.9469000101089478,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9452999830245972,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/thermostat","display_name":"Thermostat","score":0.9484107494354248},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8417167663574219},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6674347519874573},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.558185875415802},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5128200650215149},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3065270483493805},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15716639161109924},{"id":"https://openalex.org/keywords/mechanical-engineering","display_name":"Mechanical engineering","score":0.08132246136665344},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.06111058592796326}],"concepts":[{"id":"https://openalex.org/C187819001","wikidata":"https://www.wikidata.org/wiki/Q187665","display_name":"Thermostat","level":2,"score":0.9484107494354248},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8417167663574219},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6674347519874573},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.558185875415802},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5128200650215149},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3065270483493805},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15716639161109924},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.08132246136665344},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.06111058592796326}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icm62621.2025.10934768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icm62621.2025.10934768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Mechatronics (ICM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W3024350433","https://openalex.org/W3130417286","https://openalex.org/W3167675320","https://openalex.org/W3206570716","https://openalex.org/W4214717370","https://openalex.org/W4226494903","https://openalex.org/W4293498985","https://openalex.org/W4380887568","https://openalex.org/W6685444567","https://openalex.org/W6876276602"],"related_works":["https://openalex.org/W2038237118","https://openalex.org/W3121872160","https://openalex.org/W2349862066","https://openalex.org/W2099131511","https://openalex.org/W4237978858","https://openalex.org/W2042349461","https://openalex.org/W2211199051","https://openalex.org/W1965959983","https://openalex.org/W2061338932","https://openalex.org/W2156382201"],"abstract_inverted_index":{"This":[0],"study":[1],"introduces":[2],"a":[3,22,113],"model-free,":[4],"offline":[5,85],"Reinforcement":[6],"Learning":[7],"(RL)":[8],"approach":[9],"for":[10,89],"optimizing":[11],"the":[12,29,36,82,87,101],"thermostat":[13,63],"control":[14,64],"in":[15,78,108],"heating":[16],"systems.":[17],"Specifically,":[18],"historical":[19],"data":[20],"from":[21],"real-world":[23],"building":[24],"was":[25],"used":[26],"to":[27,48,74,96,112],"train":[28],"RL":[30,44,83,102],"agent":[31],"that":[32],"is":[33,47],"based":[34],"on":[35,68],"Dueling":[37],"Double":[38],"Deep":[39],"Q-Network":[40],"(DQN)":[41],"algorithm.":[42],"The":[43],"agent's":[45],"objective":[46],"balance":[49],"thermal":[50],"comfort":[51],"with":[52],"energy":[53,79,109],"savings,":[54],"by":[55],"controlling":[56],"indoor":[57,119],"temperature":[58,120],"set":[59],"points.":[60],"Traditional":[61],"rule-based":[62,114],"methods":[65],"often":[66],"depend":[67],"fixed":[69],"schedules":[70],"and":[71],"lack":[72],"adaptability":[73],"varying":[75],"conditions,":[76],"resulting":[77],"inefficiencies.":[80],"Training":[81],"model":[84,103],"eliminates":[86],"requirement":[88],"live":[90],"interaction,":[91],"thereby":[92],"preventing":[93],"potential":[94],"disruptions":[95],"occupant":[97],"comfort.":[98],"During":[99],"evaluation,":[100],"achieved":[104],"an":[105],"18.66%":[106],"reduction":[107],"use":[110],"compared":[111],"controller,":[115],"while":[116],"maintaining":[117],"recommended":[118],"levels.":[121]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}