{"id":"https://openalex.org/W2735095024","doi":"https://doi.org/10.23919/acc.2017.7963427","title":"Deep reinforcement learning for partial differential equation control","display_name":"Deep reinforcement learning for partial differential equation control","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2735095024","doi":"https://doi.org/10.23919/acc.2017.7963427","mag":"2735095024"},"language":"en","primary_location":{"id":"doi:10.23919/acc.2017.7963427","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2017.7963427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 American Control Conference (ACC)","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/A5109495187","display_name":"Amir\u2010massoud Farahmand","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amir-massoud Farahmand","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028481793","display_name":"Saleh Nabi","orcid":"https://orcid.org/0000-0002-7408-3764"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saleh Nabi","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054931604","display_name":"Daniel Nikovski","orcid":"https://orcid.org/0000-0003-2919-645X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel N. Nikovski","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5109495187"],"corresponding_institution_ids":["https://openalex.org/I4210159266"],"apc_list":null,"apc_paid":null,"fwci":2.2364,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.88187912,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3120","last_page":"3127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9976000189781189,"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":0.9976000189781189,"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":0.9592999815940857,"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/T10360","display_name":"Fluid Dynamics and Turbulent Flows","score":0.9591000080108643,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/partial-differential-equation","display_name":"Partial differential equation","score":0.7445776462554932},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7378687858581543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5766500234603882},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4694734811782837},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.454552561044693},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4533592164516449},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44560328125953674},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4253784120082855},{"id":"https://openalex.org/keywords/hvac","display_name":"HVAC","score":0.42074114084243774},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41923367977142334},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.41623392701148987},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.353593647480011},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.34632429480552673},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34020793437957764},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2888997197151184},{"id":"https://openalex.org/keywords/air-conditioning","display_name":"Air conditioning","score":0.2536852955818176},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1517103910446167},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.1031883955001831}],"concepts":[{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.7445776462554932},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7378687858581543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5766500234603882},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4694734811782837},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.454552561044693},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4533592164516449},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44560328125953674},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4253784120082855},{"id":"https://openalex.org/C122346748","wikidata":"https://www.wikidata.org/wiki/Q1798773","display_name":"HVAC","level":3,"score":0.42074114084243774},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41923367977142334},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.41623392701148987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.353593647480011},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.34632429480552673},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34020793437957764},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2888997197151184},{"id":"https://openalex.org/C103742991","wikidata":"https://www.wikidata.org/wiki/Q173725","display_name":"Air conditioning","level":2,"score":0.2536852955818176},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1517103910446167},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.1031883955001831},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/acc.2017.7963427","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2017.7963427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 American Control Conference (ACC)","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.polymtl.ca:63133","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401013","display_name":"PolyPublie (\u00c9cole Polytechnique de Montr\u00e9al)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45683168","host_organization_name":"Polytechnique Montr\u00e9al","host_organization_lineage":["https://openalex.org/I45683168"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W166862392","https://openalex.org/W1484867920","https://openalex.org/W1522301498","https://openalex.org/W1554944419","https://openalex.org/W1954793758","https://openalex.org/W2012547817","https://openalex.org/W2013927160","https://openalex.org/W2031267231","https://openalex.org/W2080971404","https://openalex.org/W2101234009","https://openalex.org/W2111625536","https://openalex.org/W2113651538","https://openalex.org/W2117355432","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2122125541","https://openalex.org/W2128812357","https://openalex.org/W2135957782","https://openalex.org/W2145339207","https://openalex.org/W2154997814","https://openalex.org/W2155007355","https://openalex.org/W2160284799","https://openalex.org/W2162501865","https://openalex.org/W2163605009","https://openalex.org/W2171033594","https://openalex.org/W2252611364","https://openalex.org/W2257979135","https://openalex.org/W2292609460","https://openalex.org/W2342840547","https://openalex.org/W2384495648","https://openalex.org/W2460675832","https://openalex.org/W2569147070","https://openalex.org/W2898957651","https://openalex.org/W2964121744","https://openalex.org/W2964161785","https://openalex.org/W4211221179","https://openalex.org/W4214717370","https://openalex.org/W4299401133","https://openalex.org/W6631190155","https://openalex.org/W6675354045","https://openalex.org/W6676872911","https://openalex.org/W6677106874","https://openalex.org/W6677549092","https://openalex.org/W6677737365","https://openalex.org/W6679100793","https://openalex.org/W6682849425","https://openalex.org/W6684191040","https://openalex.org/W6704559304"],"related_works":["https://openalex.org/W2112866972","https://openalex.org/W4240233711","https://openalex.org/W2900606913","https://openalex.org/W4320003279","https://openalex.org/W2326910963","https://openalex.org/W3111008797","https://openalex.org/W4287552621","https://openalex.org/W4376649626","https://openalex.org/W593427938","https://openalex.org/W2166790877"],"abstract_inverted_index":{"This":[0],"paper":[1],"develops":[2],"a":[3,22,32,75,87,96,100],"data-driven":[4],"method":[5],"for":[6,69,78,99],"control":[7,55,68,84],"of":[8,35,38,66,95],"partial":[9],"differential":[10],"equations":[11],"(PDE)":[12],"based":[13],"on":[14],"deep":[15],"reinforcement":[16],"learning":[17,94],"(RL)":[18],"techniques.":[19],"We":[20,58,89],"design":[21,56,85],"Deep":[23],"Fitted":[24],"Q-Iteration":[25],"(DFQI)":[26],"algorithm":[27,62],"that":[28],"works":[29],"directly":[30],"with":[31],"high-dimensional":[33],"representation":[34],"the":[36,45,52,60,64,92],"state":[37],"PDE,":[39,73],"thus":[40],"allowing":[41],"us":[42],"to":[43,63,102],"avoid":[44],"model":[46,77],"order":[47],"reduction":[48],"step":[49],"common":[50],"in":[51,86],"conventional":[53],"PDE":[54,101],"approaches.":[57],"apply":[59],"DFQI":[61],"problem":[65],"flow":[67],"time-varying":[70],"2D":[71],"convection-diffusion":[72],"as":[74],"simplified":[76],"heating,":[79],"ventilating,":[80],"air":[81],"conditioning":[82],"(HVAC)":[83],"room.":[88],"also":[90],"study":[91],"transfer":[93],"policy":[97],"learned":[98],"another":[103],"one.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}