{"id":"https://openalex.org/W4310984191","doi":"https://doi.org/10.1145/3563357.3564064","title":"Accelerate online reinforcement learning for building HVAC control with heterogeneous expert guidances","display_name":"Accelerate online reinforcement learning for building HVAC control with heterogeneous expert guidances","publication_year":2022,"publication_date":"2022-11-09","ids":{"openalex":"https://openalex.org/W4310984191","doi":"https://doi.org/10.1145/3563357.3564064"},"language":"en","primary_location":{"id":"doi:10.1145/3563357.3564064","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3563357.3564064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","raw_type":"proceedings-article"},"type":"article","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/A5101802326","display_name":"Shichao Xu","orcid":"https://orcid.org/0000-0002-9026-6245"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shichao Xu","raw_affiliation_strings":["Northwestern University"],"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102860252","display_name":"Yangyang Fu","orcid":"https://orcid.org/0000-0003-3878-9935"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yangyang Fu","raw_affiliation_strings":["Texas A&M University"],"affiliations":[{"raw_affiliation_string":"Texas A&M University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408475","display_name":"Yixuan Wang","orcid":"https://orcid.org/0000-0003-0847-8570"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixuan Wang","raw_affiliation_strings":["Northwestern University"],"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727948","display_name":"Zhuoran Yang","orcid":"https://orcid.org/0000-0001-5269-9958"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuoran Yang","raw_affiliation_strings":["Yale University"],"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031520161","display_name":"Zheng O\u2019Neill","orcid":"https://orcid.org/0000-0002-8839-7174"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng O'Neill","raw_affiliation_strings":["Texas A&M University"],"affiliations":[{"raw_affiliation_string":"Texas A&M University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101934111","display_name":"Zhaoran Wang","orcid":"https://orcid.org/0000-0002-6617-4842"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaoran Wang","raw_affiliation_strings":["Northwestern University"],"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020896290","display_name":"Qi Zhu","orcid":"https://orcid.org/0000-0002-7700-4099"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Zhu","raw_affiliation_strings":["Northwestern University"],"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101802326"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1642,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.75636848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"89","last_page":"98"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10121","display_name":"Building Energy and Comfort Optimization","score":0.9994999766349792,"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":0.9994999766349792,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11529","display_name":"Refrigeration and Air Conditioning Technologies","score":0.9848999977111816,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hvac","display_name":"HVAC","score":0.8549150228500366},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8402293920516968},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.741746723651886},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5650636553764343},{"id":"https://openalex.org/keywords/subject-matter-expert","display_name":"Subject-matter expert","score":0.5437674522399902},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5129117965698242},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.5007774829864502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4369352459907532},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4298112392425537},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4235551357269287},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4214816093444824},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4160645306110382},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.39046335220336914},{"id":"https://openalex.org/keywords/air-conditioning","display_name":"Air conditioning","score":0.3600198030471802},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3418562412261963},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18507066369056702},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.17034971714019775}],"concepts":[{"id":"https://openalex.org/C122346748","wikidata":"https://www.wikidata.org/wiki/Q1798773","display_name":"HVAC","level":3,"score":0.8549150228500366},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8402293920516968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.741746723651886},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5650636553764343},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.5437674522399902},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5129117965698242},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5007774829864502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4369352459907532},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4298112392425537},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4235551357269287},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4214816093444824},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4160645306110382},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.39046335220336914},{"id":"https://openalex.org/C103742991","wikidata":"https://www.wikidata.org/wiki/Q173725","display_name":"Air conditioning","level":2,"score":0.3600198030471802},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3418562412261963},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18507066369056702},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.17034971714019775},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3563357.3564064","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3563357.3564064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1235554658","display_name":null,"funder_award_id":"DE-EE0009150","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6305127867","display_name":null,"funder_award_id":"1834701, 2038853","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W101507059","https://openalex.org/W1593349661","https://openalex.org/W1979910178","https://openalex.org/W1996058353","https://openalex.org/W2019348145","https://openalex.org/W2079784202","https://openalex.org/W2114519460","https://openalex.org/W2159200188","https://openalex.org/W2164861471","https://openalex.org/W2176075926","https://openalex.org/W2292753902","https://openalex.org/W2527328725","https://openalex.org/W2590361174","https://openalex.org/W2625874945","https://openalex.org/W2957897705","https://openalex.org/W2972239117","https://openalex.org/W2974232099","https://openalex.org/W2982041329","https://openalex.org/W3023669592","https://openalex.org/W3033324992","https://openalex.org/W3037440645","https://openalex.org/W3037631072","https://openalex.org/W3048265338","https://openalex.org/W3107396186","https://openalex.org/W3130457093","https://openalex.org/W3193645253","https://openalex.org/W3215436808","https://openalex.org/W3217060725","https://openalex.org/W6780159193"],"related_works":["https://openalex.org/W2124618300","https://openalex.org/W4251129740","https://openalex.org/W4289529465","https://openalex.org/W1983574532","https://openalex.org/W1752292405","https://openalex.org/W2038540893","https://openalex.org/W2036908429","https://openalex.org/W2277666011","https://openalex.org/W2279978373","https://openalex.org/W4235667779"],"abstract_inverted_index":{"Building":[0],"heating,":[1],"ventilation,":[2],"and":[3,16,34,68,139,162],"air":[4],"conditioning":[5],"(HVAC)":[6],"systems":[7],"account":[8],"for":[9,30,93,110],"nearly":[10],"half":[11],"of":[12,18,37,66,117],"building":[13,38],"energy":[14,20],"consumption":[15,21],"20%":[17],"total":[19],"in":[22,123],"the":[23,32,47,64,118,127,148,158],"US.":[24],"Their":[25],"operation":[26],"is":[27,89],"also":[28],"crucial":[29],"ensuring":[31],"physical":[33,70,137],"mental":[35],"health":[36],"occupants.":[39],"Compared":[40],"with":[41,151],"traditional":[42],"model-based":[43],"HVAC":[44,111],"control":[45,112],"methods,":[46],"recent":[48],"model-free":[49,74],"deep":[50],"reinforcement":[51,108,145],"learning":[52,109,131],"(DRL)":[53],"based":[54],"methods":[55],"have":[56],"shown":[57],"good":[58,86],"performance":[59],"while":[60],"do":[61],"not":[62],"require":[63],"development":[65],"detailed":[67],"costly":[69],"models.":[71],"However,":[72],"these":[73],"DRL":[75],"approaches":[76],"often":[77],"suffer":[78],"from":[79,120,134,140,166],"long":[80],"training":[81,155],"time":[82],"to":[83,105,174],"reach":[84],"a":[85,90,102],"performance,":[87],"which":[88],"major":[91],"obstacle":[92],"their":[94],"practical":[95],"deployment.":[96],"In":[97],"this":[98],"work,":[99],"we":[100],"present":[101],"systematic":[103],"approach":[104],"accelerate":[106],"online":[107],"by":[113,157],"taking":[114],"full":[115],"advantage":[116],"knowledge":[119],"domain":[121],"experts":[122],"various":[124],"forms.":[125],"Specifically,":[126],"algorithm":[128],"stages":[129],"include":[130],"expert":[132,149,160,168],"functions":[133,150],"existing":[135],"abstract":[136],"models":[138],"historical":[141],"data":[142],"via":[143],"offline":[144],"learning,":[146],"integrating":[147],"rule-based":[152],"guidelines,":[153],"conducting":[154],"guided":[156],"integrated":[159],"function":[161],"performing":[163],"policy":[164],"initialization":[165],"distilled":[167],"function.":[169],"Experimental":[170],"results":[171],"demonstrate":[172],"up":[173],"8.8X":[175],"speedup":[176],"over":[177],"previous":[178],"DRL-based":[179],"methods.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}