{"id":"https://openalex.org/W4315488689","doi":"https://doi.org/10.1109/cdc51059.2022.9992867","title":"Convex Analytic Theory for Convex Q-Learning","display_name":"Convex Analytic Theory for Convex Q-Learning","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4315488689","doi":"https://doi.org/10.1109/cdc51059.2022.9992867"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9992867","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc51059.2022.9992867","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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 61st Conference on Decision and Control (CDC)","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/A5038013125","display_name":"Fan L\u00fc","orcid":"https://orcid.org/0000-0002-8496-3941"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fan Lu","raw_affiliation_strings":["University of Florida,Department of Electrical and Computer Engineering,Gainesville,FL,32611"],"affiliations":[{"raw_affiliation_string":"University of Florida,Department of Electrical and Computer Engineering,Gainesville,FL,32611","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081314418","display_name":"Prashant G. Mehta","orcid":"https://orcid.org/0000-0003-1265-7942"},"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":false,"raw_author_name":"Prashant G. Mehta","raw_affiliation_strings":["University of Illinois at Urbana-Champaign (UIUC),Mechanical Science and Engineering,Coordinated Science Laboratory and the Department","Coordinated Science Laboratory and the Department, Mechanical Science and Engineering, University of Illinois at Urbana-Champaign (UIUC)"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign (UIUC),Mechanical Science and Engineering,Coordinated Science Laboratory and the Department","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Coordinated Science Laboratory and the Department, Mechanical Science and Engineering, University of Illinois at Urbana-Champaign (UIUC)","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047988825","display_name":"Sean Meyn","orcid":"https://orcid.org/0000-0002-8558-365X"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Sean P. Meyn","raw_affiliation_strings":["University of Florida,Department of Electrical and Computer Engineering,Gainesville,FL,32611","Inria International Chair, Paris, France"],"affiliations":[{"raw_affiliation_string":"University of Florida,Department of Electrical and Computer Engineering,Gainesville,FL,32611","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"Inria International Chair, Paris, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077167635","display_name":"Gergely Neu","orcid":"https://orcid.org/0000-0001-6287-3796"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Gergely Neu","raw_affiliation_strings":["Universitat Pompeu Fabra (Barcelona, Spain),Department of Information and Communication Technologies","Department of Information and Communication Technologies, Universitat Pompeu Fabra (Barcelona, Spain)"],"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra (Barcelona, Spain),Department of Information and Communication Technologies","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Department of Information and Communication Technologies, Universitat Pompeu Fabra (Barcelona, Spain)","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038013125"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":0.8249,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82241681,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"130","issue":null,"first_page":"4065","last_page":"4071"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9868000149726868,"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"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9868000149726868,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.983299970626831,"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"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9675999879837036,"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/convex-analysis","display_name":"Convex analysis","score":0.5722832679748535},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.5481087565422058},{"id":"https://openalex.org/keywords/proper-convex-function","display_name":"Proper convex function","score":0.5283292531967163},{"id":"https://openalex.org/keywords/convex-combination","display_name":"Convex combination","score":0.5272471308708191},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.43470078706741333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.39807963371276855},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.3319419026374817},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.2931637465953827},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.1097949743270874}],"concepts":[{"id":"https://openalex.org/C12108790","wikidata":"https://www.wikidata.org/wiki/Q2234833","display_name":"Convex analysis","level":4,"score":0.5722832679748535},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.5481087565422058},{"id":"https://openalex.org/C50862404","wikidata":"https://www.wikidata.org/wiki/Q3075259","display_name":"Proper convex function","level":5,"score":0.5283292531967163},{"id":"https://openalex.org/C111110010","wikidata":"https://www.wikidata.org/wiki/Q2627315","display_name":"Convex combination","level":4,"score":0.5272471308708191},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.43470078706741333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39807963371276855},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3319419026374817},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.2931637465953827},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.1097949743270874}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc51059.2022.9992867","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc51059.2022.9992867","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W118602349","https://openalex.org/W1646707810","https://openalex.org/W1964535365","https://openalex.org/W2040766536","https://openalex.org/W2097886690","https://openalex.org/W2111753883","https://openalex.org/W2112032710","https://openalex.org/W2123395972","https://openalex.org/W2144902422","https://openalex.org/W2151661095","https://openalex.org/W2160698719","https://openalex.org/W2169982856","https://openalex.org/W2973067663","https://openalex.org/W2991953019","https://openalex.org/W3183922633","https://openalex.org/W3210638057","https://openalex.org/W4214717370","https://openalex.org/W4253284464","https://openalex.org/W4387124176","https://openalex.org/W6600556750","https://openalex.org/W6612245137","https://openalex.org/W6678945949","https://openalex.org/W6680602176","https://openalex.org/W6681302627","https://openalex.org/W6770929369","https://openalex.org/W6856864769"],"related_works":["https://openalex.org/W2026600343","https://openalex.org/W2013655535","https://openalex.org/W4382519084","https://openalex.org/W2376997122","https://openalex.org/W2999421545","https://openalex.org/W2478309485","https://openalex.org/W3175838852","https://openalex.org/W2040676043","https://openalex.org/W165488893","https://openalex.org/W2391247224"],"abstract_inverted_index":{"In":[0],"recent":[1],"years":[2],"there":[3],"has":[4,93],"been":[5],"a":[6,53,87,112,131],"collective":[7],"research":[8],"effort":[9],"to":[10,25,102,115,148],"find":[11],"new":[12],"formulations":[13],"of":[14,40,43,78,89],"reinforcement":[15],"learning":[16],"that":[17,32,96,156],"are":[18],"simultaneously":[19],"more":[20,23],"efficient":[21],"and":[22,52],"amenable":[24],"analysis.":[26],"This":[27,59],"paper":[28,60],"concerns":[29],"one":[30],"approach":[31],"builds":[33],"on":[34,62,130],"the":[35,63,69,98,116,169],"linear":[36],"programming":[37],"(LP)":[38],"formulation":[39],"optimal":[41],"control":[42],"Manne.":[44],"A":[45,106],"primal":[46],"version":[47,88],"is":[48,56,81,109,137,144,154,159],"called":[49],"logistic":[50,90],"Q-learning,":[51,91],"dual":[54,77],"variant":[55],"convex":[57,79,157],"Q-learning.":[58],"focuses":[61],"latter,":[64],"while":[65],"building":[66],"bridges":[67],"with":[68,146],"former.":[70],"The":[71,76,135,142],"main":[72],"contributions":[73],"follow:":[74],"(i)":[75],"Q-learning":[80,117,158,165],"not":[82],"precisely":[83],"Manne\u2019s":[84],"LP":[85],"or":[86],"but":[92],"similar":[94],"structure":[95],"reveals":[97],"need":[99],"for":[100,111],"regularization":[101],"avoid":[103],"over-fitting.":[104],"(ii)":[105],"sufficient":[107],"condition":[108],"obtained":[110],"bounded":[113],"solution":[114],"LP.":[118],"(iii)":[119],"Simulation":[120],"studies":[121],"reveal":[122],"numerical":[123],"challenges":[124],"when":[125],"addressing":[126],"sampled-data":[127],"systems":[128],"based":[129],"continuous":[132],"time":[133],"model.":[134],"challenge":[136],"addressed":[138],"using":[139],"state-dependent":[140],"sampling.":[141],"theory":[143],"illustrated":[145],"applications":[147],"examples":[149],"from":[150],"OpenAI":[151],"gym.":[152],"It":[153],"shown":[155],"successful":[160],"in":[161],"cases":[162],"where":[163],"standard":[164],"diverges,":[166],"such":[167],"as":[168],"LQR":[170],"problem.":[171]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}