{"id":"https://openalex.org/W2903410452","doi":"https://doi.org/10.1109/tac.2018.2884649","title":"Primal-Dual Q-Learning Framework for LQR Design","display_name":"Primal-Dual Q-Learning Framework for LQR Design","publication_year":2018,"publication_date":"2018-12-04","ids":{"openalex":"https://openalex.org/W2903410452","doi":"https://doi.org/10.1109/tac.2018.2884649","mag":"2903410452"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2018.2884649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2018.2884649","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-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/A5100654317","display_name":"Donghwan Lee","orcid":"https://orcid.org/0000-0002-4962-8478"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Donghwan Lee","raw_affiliation_strings":["Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035753295","display_name":"Jianghai Hu","orcid":"https://orcid.org/0000-0002-4250-8852"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianghai Hu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100654317"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":3.231,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.93335986,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"64","issue":"9","first_page":"3756","last_page":"3763"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14083","display_name":"Extremum Seeking Control Systems","score":0.9966999888420105,"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"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9901000261306763,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.854772686958313},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5954787731170654},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5903443098068237},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.5732475519180298},{"id":"https://openalex.org/keywords/duality","display_name":"Duality (order theory)","score":0.5407443642616272},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5037075877189636},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49037814140319824},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.46428075432777405},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4523140788078308},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.43379664421081543},{"id":"https://openalex.org/keywords/saddle","display_name":"Saddle","score":0.4161437749862671},{"id":"https://openalex.org/keywords/lagrangian","display_name":"Lagrangian","score":0.4148743152618408},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3952085077762604},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.38962411880493164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23211395740509033},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.18193745613098145},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.07562848925590515}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.854772686958313},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5954787731170654},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5903443098068237},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.5732475519180298},{"id":"https://openalex.org/C2778023678","wikidata":"https://www.wikidata.org/wiki/Q554403","display_name":"Duality (order theory)","level":2,"score":0.5407443642616272},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5037075877189636},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49037814140319824},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.46428075432777405},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4523140788078308},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.43379664421081543},{"id":"https://openalex.org/C2777127463","wikidata":"https://www.wikidata.org/wiki/Q10862618","display_name":"Saddle","level":2,"score":0.4161437749862671},{"id":"https://openalex.org/C53469067","wikidata":"https://www.wikidata.org/wiki/Q505735","display_name":"Lagrangian","level":2,"score":0.4148743152618408},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3952085077762604},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.38962411880493164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23211395740509033},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.18193745613098145},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.07562848925590515},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2018.2884649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2018.2884649","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4785360960","display_name":null,"funder_award_id":"1539527","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W618799468","https://openalex.org/W1534096605","https://openalex.org/W1542938076","https://openalex.org/W1557517019","https://openalex.org/W1576452626","https://openalex.org/W1604591429","https://openalex.org/W1616818660","https://openalex.org/W1965640670","https://openalex.org/W1969729070","https://openalex.org/W2002357820","https://openalex.org/W2011386240","https://openalex.org/W2032173185","https://openalex.org/W2063263407","https://openalex.org/W2097415784","https://openalex.org/W2098432798","https://openalex.org/W2115832833","https://openalex.org/W2121863487","https://openalex.org/W2126394835","https://openalex.org/W2144557480","https://openalex.org/W2165726932","https://openalex.org/W2296319761","https://openalex.org/W2400458653","https://openalex.org/W2501537193","https://openalex.org/W2765399514","https://openalex.org/W2798766386","https://openalex.org/W2912522929","https://openalex.org/W2964314726","https://openalex.org/W3041202696","https://openalex.org/W3139377883","https://openalex.org/W3210839039","https://openalex.org/W4214717370","https://openalex.org/W4233548378","https://openalex.org/W4250589301","https://openalex.org/W4254313632"],"related_works":["https://openalex.org/W1974759779","https://openalex.org/W2808999691","https://openalex.org/W1908830045","https://openalex.org/W4383599100","https://openalex.org/W2474009580","https://openalex.org/W2477123555","https://openalex.org/W4386543804","https://openalex.org/W2136759273","https://openalex.org/W2751243021","https://openalex.org/W2362140329"],"abstract_inverted_index":{"Recently,":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"is":[4,27],"receiving":[5],"more":[6,8],"and":[7,95,121],"attentions":[9],"due":[10],"to":[11,28,48,72,77,116],"its":[12,107,123],"successful":[13],"demonstrations":[14],"outperforming":[15],"human":[16],"performance":[17],"in":[18,46],"certain":[19],"challenging":[20],"tasks.":[21],"The":[22,57],"goal":[23],"of":[24,34,52,80,91,99,106],"this":[25],"paper":[26],"study":[29],"a":[30,111],"new":[31,58],"optimization":[32,59],"formulation":[33],"the":[35,42,62,81,92,96,100,118],"linear":[36],"quadratic":[37],"regulator":[38],"(LQR)":[39],"problem":[40,60,120],"via":[41],"Lagrangian":[43,93],"duality":[44],"theories":[45],"order":[47],"lay":[49],"theoretical":[50],"foundations":[51],"potentially":[53],"effective":[54],"RL":[55,84],"algorithms.":[56,85],"includes":[61],"Q-function":[63],"parameters":[64],"so":[65],"that":[66],"it":[67],"can":[68],"be":[69,78],"directly":[70],"used":[71],"develop":[73],"Q-learning":[74,114],"algorithms,":[75],"known":[76],"one":[79],"most":[82],"popular":[83],"We":[86],"prove":[87],"relations":[88],"between":[89],"saddle-points":[90],"function":[94],"optimal":[97],"solutions":[98],"Bellman":[101],"equation.":[102],"As":[103],"an":[104],"example":[105],"applications,":[108],"we":[109],"propose":[110],"model-free":[112],"primal-dual":[113],"algorithm":[115],"solve":[117],"LQR":[119],"demonstrate":[122],"validity":[124],"through":[125],"examples.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}