{"id":"https://openalex.org/W4287846201","doi":"https://doi.org/10.1109/icca54724.2022.9831914","title":"Near-optimal Deep Reinforcement Learning Policies from Data for Zone Temperature Control","display_name":"Near-optimal Deep Reinforcement Learning Policies from Data for Zone Temperature Control","publication_year":2022,"publication_date":"2022-06-27","ids":{"openalex":"https://openalex.org/W4287846201","doi":"https://doi.org/10.1109/icca54724.2022.9831914"},"language":"en","primary_location":{"id":"doi:10.1109/icca54724.2022.9831914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca54724.2022.9831914","pdf_url":null,"source":{"id":"https://openalex.org/S4363608132","display_name":"2022 IEEE 17th International Conference on Control & Automation (ICCA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 17th International Conference on Control & Automation (ICCA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/handle/20.500.14299/196604","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056840318","display_name":"Loris Di Natale","orcid":"https://orcid.org/0000-0002-3295-412X"},"institutions":[{"id":"https://openalex.org/I71824836","display_name":"Swiss Federal Laboratories for Materials Science and Technology","ror":"https://ror.org/02x681a42","country_code":"CH","type":"facility","lineage":["https://openalex.org/I2799323385","https://openalex.org/I71824836"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Loris Di Natale","raw_affiliation_strings":["Swiss Federal Laboratories for Materials Science and Technology (Empa),Urban Energy Systems Laboratory,Dübendorf,Switzerland,8600"],"affiliations":[{"raw_affiliation_string":"Swiss Federal Laboratories for Materials Science and Technology (Empa),Urban Energy Systems Laboratory,Dübendorf,Switzerland,8600","institution_ids":["https://openalex.org/I71824836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005151144","display_name":"Bratislav Svetozarevic","orcid":"https://orcid.org/0000-0001-8921-3915"},"institutions":[{"id":"https://openalex.org/I71824836","display_name":"Swiss Federal Laboratories for Materials Science and Technology","ror":"https://ror.org/02x681a42","country_code":"CH","type":"facility","lineage":["https://openalex.org/I2799323385","https://openalex.org/I71824836"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Bratislav Svetozarevic","raw_affiliation_strings":["Swiss Federal Laboratories for Materials Science and Technology (Empa),Urban Energy Systems Laboratory,Dübendorf,Switzerland,8600"],"affiliations":[{"raw_affiliation_string":"Swiss Federal Laboratories for Materials Science and Technology (Empa),Urban Energy Systems Laboratory,Dübendorf,Switzerland,8600","institution_ids":["https://openalex.org/I71824836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069545422","display_name":"Philipp Heer","orcid":"https://orcid.org/0000-0003-2999-5753"},"institutions":[{"id":"https://openalex.org/I71824836","display_name":"Swiss Federal Laboratories for Materials Science and Technology","ror":"https://ror.org/02x681a42","country_code":"CH","type":"facility","lineage":["https://openalex.org/I2799323385","https://openalex.org/I71824836"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Philipp Heer","raw_affiliation_strings":["Swiss Federal Laboratories for Materials Science and Technology (Empa),Urban Energy Systems Laboratory,Dübendorf,Switzerland,8600"],"affiliations":[{"raw_affiliation_string":"Swiss Federal Laboratories for Materials Science and Technology (Empa),Urban Energy Systems Laboratory,Dübendorf,Switzerland,8600","institution_ids":["https://openalex.org/I71824836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085117832","display_name":"Colin N. Jones","orcid":"https://orcid.org/0000-0001-7239-4799"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Colin N. Jones","raw_affiliation_strings":["Swiss Federal Institute of Technology Lausanne (EPFL),Laboratoire d’Automatique,Lausanne,Switzerland,1015"],"affiliations":[{"raw_affiliation_string":"Swiss Federal Institute of Technology Lausanne (EPFL),Laboratoire d’Automatique,Lausanne,Switzerland,1015","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056840318"],"corresponding_institution_ids":["https://openalex.org/I71824836"],"apc_list":null,"apc_paid":null,"fwci":1.6822,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83495935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"698","last_page":"703"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10121","display_name":"Building Energy and Comfort Optimization","score":0.9991999864578247,"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":0.9991999864578247,"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/T12093","display_name":"Greenhouse Technology and Climate Control","score":0.9750999808311462,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10998","display_name":"Heat Transfer and Optimization","score":0.9714000225067139,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8574795722961426},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7843239307403564},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.656451404094696},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6541824340820312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6523313522338867},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4215969443321228},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4142049551010132},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38391804695129395},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3674130141735077},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.36549052596092224},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.32201361656188965},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1132260262966156}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8574795722961426},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7843239307403564},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.656451404094696},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6541824340820312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6523313522338867},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4215969443321228},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4142049551010132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38391804695129395},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3674130141735077},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.36549052596092224},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.32201361656188965},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1132260262966156},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icca54724.2022.9831914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca54724.2022.9831914","pdf_url":null,"source":{"id":"https://openalex.org/S4363608132","display_name":"2022 IEEE 17th International Conference on Control & Automation (ICCA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 17th International Conference on Control & Automation (ICCA)","raw_type":"proceedings-article"},{"id":"pmh:oai:dora:empa_31183","is_oa":false,"landing_page_url":"https://www.dora.lib4ri.ch/empa/islandora/object/empa%3A31183","pdf_url":null,"source":{"id":"https://openalex.org/S4306401298","display_name":"DORA Empa (Swiss Federal Laboratories for Materials Science and Technology (Empa))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71824836","host_organization_name":"Swiss Federal Laboratories for Materials Science and Technology","host_organization_lineage":["https://openalex.org/I71824836"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"},{"id":"pmh:oai:infoscience.epfl.ch:301591","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/196604","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:301591","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/196604","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"},"sustainable_development_goals":[{"score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1991784919","https://openalex.org/W2108152153","https://openalex.org/W2746553466","https://openalex.org/W2754517384","https://openalex.org/W2787938642","https://openalex.org/W2801379499","https://openalex.org/W2924196570","https://openalex.org/W2957897705","https://openalex.org/W2963864421","https://openalex.org/W2968917279","https://openalex.org/W2989354373","https://openalex.org/W3161175155","https://openalex.org/W3199775902","https://openalex.org/W3212810272","https://openalex.org/W4200635769","https://openalex.org/W4205653889","https://openalex.org/W4285106921","https://openalex.org/W4292551110","https://openalex.org/W6677067356","https://openalex.org/W6684921986","https://openalex.org/W6748839928","https://openalex.org/W6751027425","https://openalex.org/W6767164110"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W1501776718","https://openalex.org/W2615136228","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2768698792"],"abstract_inverted_index":{"Replacing":[0],"poorly":[1],"performing":[2],"existing":[3],"controllers":[4,18],"with":[5],"smarter":[6],"solutions":[7],"will":[8],"decrease":[9],"the":[10,14,37,70,77,113],"energy":[11],"intensity":[12],"of":[13,72],"building":[15],"sector.":[16],"Recently,":[17],"based":[19],"on":[20,107],"Deep":[21],"Reinforcement":[22],"Learning":[23],"(DRL)":[24],"have":[25],"been":[26],"shown":[27],"to":[28,64,76,101,109],"be":[29,110],"more":[30],"effective":[31],"than":[32],"conventional":[33,132],"baselines.":[34],"However,":[35],"since":[36],"optimal":[38,79,96],"solution":[39],"is":[40,44,59],"usually":[41],"unknown,":[42],"it":[43],"still":[45,60],"unclear":[46],"if":[47,57],"DRL":[48,73,126],"agents":[49,74,127],"are":[50,99],"attaining":[51],"near-optimal":[52,138],"performance":[53,71],"in":[54],"general":[55],"or":[56],"there":[58],"a":[61],"large":[62],"gap":[63],"bridge.In":[65],"this":[66],"paper,":[67],"we":[68,84],"investigate":[69],"compared":[75],"theoretically":[78],"solution.":[80],"To":[81],"that":[82,125],"end,":[83],"leverage":[85],"Physically":[86],"Consistent":[87],"Neural":[88],"Networks":[89],"(PCNNs)":[90],"as":[91],"simulation":[92],"environments,":[93],"for":[94],"which":[95],"control":[97],"inputs":[98],"easy":[100],"compute.":[102],"Furthermore,":[103],"PCNNs":[104],"solely":[105],"rely":[106],"data":[108],"trained,":[111],"avoiding":[112],"difficult":[114],"physics-based":[115],"modeling":[116],"phase,":[117],"while":[118],"retaining":[119],"physical":[120],"consistency.":[121],"Our":[122],"results":[123],"hint":[124],"not":[128],"only":[129],"clearly":[130],"outperform":[131],"rule-based":[133],"controllers,":[134],"they":[135],"furthermore":[136],"attain":[137],"performance.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2022-07-26T00:00:00"}