{"id":"https://openalex.org/W7160311330","doi":"https://doi.org/10.1016/j.compeleceng.2026.111217","title":"Effective cross-building transfer learning for HVAC control using deep reinforcement learning and joint action dynamics","display_name":"Effective cross-building transfer learning for HVAC control using deep reinforcement learning and joint action dynamics","publication_year":2026,"publication_date":"2026-05-05","ids":{"openalex":"https://openalex.org/W7160311330","doi":"https://doi.org/10.1016/j.compeleceng.2026.111217"},"language":"en","primary_location":{"id":"doi:10.1016/j.compeleceng.2026.111217","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.compeleceng.2026.111217","pdf_url":null,"source":{"id":"https://openalex.org/S121340289","display_name":"Computers & Electrical Engineering","issn_l":"0045-7906","issn":["0045-7906","1879-0755"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers and Electrical Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.compeleceng.2026.111217","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055217873","display_name":"Kevlyn Kadamala","orcid":"https://orcid.org/0000-0002-9478-5675"},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Kevlyn Kadamala","raw_affiliation_strings":["University of Galway, University Road, Galway, H91 TK33, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-9478-5675","affiliations":[{"raw_affiliation_string":"University of Galway, University Road, Galway, H91 TK33, Ireland","institution_ids":["https://openalex.org/I188760350"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009755587","display_name":"Des Chambers","orcid":null},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Des Chambers","raw_affiliation_strings":["University of Galway, University Road, Galway, H91 TK33, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Galway, University Road, Galway, H91 TK33, Ireland","institution_ids":["https://openalex.org/I188760350"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035625780","display_name":"Enda Barrett","orcid":"https://orcid.org/0000-0002-9876-8717"},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Enda Barrett","raw_affiliation_strings":["University of Galway, University Road, Galway, H91 TK33, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-9876-8717","affiliations":[{"raw_affiliation_string":"University of Galway, University Road, Galway, H91 TK33, Ireland","institution_ids":["https://openalex.org/I188760350"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5055217873"],"corresponding_institution_ids":["https://openalex.org/I188760350"],"apc_list":{"value":3100,"currency":"USD","value_usd":3100},"apc_paid":{"value":3100,"currency":"USD","value_usd":3100},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47839097,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"136","issue":null,"first_page":"111217","last_page":"111217"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.16189999878406525,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.16189999878406525,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10121","display_name":"Building Energy and Comfort Optimization","score":0.09650000184774399,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.09610000252723694,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6014000177383423},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5855000019073486},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5331000089645386},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5285000205039978},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.520799994468689},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5031999945640564},{"id":"https://openalex.org/keywords/hvac","display_name":"HVAC","score":0.5001000165939331}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6840000152587891},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6014000177383423},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5855000019073486},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5331000089645386},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5285000205039978},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.5156000256538391},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5031999945640564},{"id":"https://openalex.org/C122346748","wikidata":"https://www.wikidata.org/wiki/Q1798773","display_name":"HVAC","level":3,"score":0.5001000165939331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44519999623298645},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.29159998893737793},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.27239999175071716},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.27079999446868896}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.compeleceng.2026.111217","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.compeleceng.2026.111217","pdf_url":null,"source":{"id":"https://openalex.org/S121340289","display_name":"Computers & Electrical Engineering","issn_l":"0045-7906","issn":["0045-7906","1879-0755"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers and Electrical Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.compeleceng.2026.111217","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.compeleceng.2026.111217","pdf_url":null,"source":{"id":"https://openalex.org/S121340289","display_name":"Computers & Electrical Engineering","issn_l":"0045-7906","issn":["0045-7906","1879-0755"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers and Electrical Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2394637485","display_name":"SFI Centre for Research Training in Artificial Intelligence","funder_award_id":"18/CRT/6223","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"},{"id":"https://openalex.org/F8766430056","display_name":"Research Ireland","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2027036679","https://openalex.org/W2708717249","https://openalex.org/W2948978827","https://openalex.org/W2964657419","https://openalex.org/W2979476646","https://openalex.org/W2985363569","https://openalex.org/W2989354373","https://openalex.org/W3018700377","https://openalex.org/W3034748593","https://openalex.org/W3048265338","https://openalex.org/W3107396186","https://openalex.org/W3116317014","https://openalex.org/W3166166623","https://openalex.org/W4205300464","https://openalex.org/W4225917661","https://openalex.org/W4315480006","https://openalex.org/W4324144157","https://openalex.org/W4381849574","https://openalex.org/W4383112908","https://openalex.org/W4386075839","https://openalex.org/W4391265349","https://openalex.org/W4392582168","https://openalex.org/W4399647325","https://openalex.org/W4401840778","https://openalex.org/W4404625833","https://openalex.org/W4406062430","https://openalex.org/W4407954544","https://openalex.org/W4411196133","https://openalex.org/W7133215300"],"related_works":[],"abstract_inverted_index":{"Advancements":[0],"in":[1,24,58,97,158,185],"Deep":[2],"Reinforcement":[3],"Learning":[4],"(DRL)":[5],"have":[6],"demonstrated":[7],"its":[8,170],"potential":[9],"to":[10,39,109,183],"enhance":[11],"heating,":[12],"ventilation,":[13],"and":[14,21,32,49,113,133,161,173],"air-conditioning":[15],"(HVAC)":[16],"control,":[17],"improving":[18],"energy":[19],"efficiency":[20,172],"occupant":[22],"comfort":[23],"buildings.":[25],"While":[26],"DRL":[27],"typically":[28],"requires":[29],"extensive":[30],"training":[31],"data,":[33],"transfer":[34,52,99,138,163],"learning":[35,53,95,100],"eliminates":[36],"the":[37,41,66,73,125,145,152],"need":[38],"relearn":[40],"underlying":[42],"model":[43],"from":[44,119,181],"scratch,":[45],"thereby":[46],"saving":[47],"time":[48],"resources.":[50],"However,":[51],"may":[54],"not":[55,69],"always":[56],"result":[57],"improved":[59],"performance.":[60],"It":[61],"could":[62],"harm":[63],"performance":[64,174],"if":[65,72],"tasks":[67],"are":[68,78],"similar":[70],"or":[71],"representations":[74,129],"learned":[75],"during":[76],"pre-training":[77,85],"ineffective.":[79],"This":[80],"paper":[81],"presents":[82],"a":[83,105],"novel":[84],"methodology":[86],"for":[87,130,141],"representation":[88],"learning,":[89],"enabling":[90],"effective":[91],"fine-tuning":[92,143],"of":[93],"reinforcement":[94],"(RL)":[96],"cross-building":[98,162],"tasks.":[101],"First,":[102],"we":[103],"pre-train":[104],"variational":[106],"autoencoder":[107],"(VAE)":[108],"jointly":[110,127],"predict":[111],"actions":[112],"next":[114],"states":[115],"using":[116],"data":[117],"derived":[118],"expert":[120],"demonstrations.":[121],"During":[122],"this":[123,139],"process,":[124],"encoder":[126,140],"learns":[128],"action":[131],"prediction":[132],"building":[134],"dynamics.":[135],"We":[136],"then":[137],"RL":[142],"onto":[144],"target":[146],"building.":[147],"Our":[148,165],"simulations":[149],"show":[150],"that":[151],"proposed":[153,166],"method":[154,167],"outperforms":[155],"existing":[156],"algorithms":[157],"both":[159],"same-building":[160],"scenarios.":[164],"consistently":[168],"improves":[169],"sample":[171],"across":[175],"different":[176],"environments,":[177],"showing":[178],"improvements":[179],"ranging":[180],"1%":[182],"12.76%":[184],"overall":[186],"rewards.":[187]},"counts_by_year":[],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2026-05-06T00:00:00"}