{"id":"https://openalex.org/W3183922633","doi":"https://doi.org/10.23919/acc50511.2021.9483244","title":"Convex Q-Learning","display_name":"Convex Q-Learning","publication_year":2021,"publication_date":"2021-05-25","ids":{"openalex":"https://openalex.org/W3183922633","doi":"https://doi.org/10.23919/acc50511.2021.9483244","mag":"3183922633"},"language":"en","primary_location":{"id":"doi:10.23919/acc50511.2021.9483244","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc50511.2021.9483244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/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":["Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL","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":["Department of Mechanical Science and Engineering, Coordinated Science Laboratory, University of Illinois at Urbana-Champaign (UIUC)"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical Science and Engineering, Coordinated Science Laboratory, 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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sean P. Meyn","raw_affiliation_strings":["Inria International Chair, Paris, France"],"affiliations":[{"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":["Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain"],"affiliations":[{"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":1.2237,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.8323776,"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":"4749","last_page":"4756"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9975000023841858,"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"}},"topics":[{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9975000023841858,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9894000291824341,"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/computer-science","display_name":"Computer science","score":0.5074660181999207},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.45845121145248413},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3270440101623535},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.1366630494594574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5074660181999207},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.45845121145248413},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3270440101623535},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.1366630494594574}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc50511.2021.9483244","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc50511.2021.9483244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4531343814","display_name":null,"funder_award_id":"W911NF1810334","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8205755443","display_name":null,"funder_award_id":"EPCN 1935389","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/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W13294968","https://openalex.org/W118602349","https://openalex.org/W166862392","https://openalex.org/W192920577","https://openalex.org/W1542595278","https://openalex.org/W1576452626","https://openalex.org/W1745373831","https://openalex.org/W1771410628","https://openalex.org/W1964535365","https://openalex.org/W1967037758","https://openalex.org/W1990337648","https://openalex.org/W1996395235","https://openalex.org/W2040766536","https://openalex.org/W2071983464","https://openalex.org/W2097886690","https://openalex.org/W2111753883","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2151661095","https://openalex.org/W2155968351","https://openalex.org/W2160698719","https://openalex.org/W2173564293","https://openalex.org/W2604204246","https://openalex.org/W2604960773","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2765302304","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2950888428","https://openalex.org/W2951799221","https://openalex.org/W2962741973","https://openalex.org/W2962767126","https://openalex.org/W2963423916","https://openalex.org/W2963757175","https://openalex.org/W2963923407","https://openalex.org/W2964043796","https://openalex.org/W2964291307","https://openalex.org/W2973067663","https://openalex.org/W2991953019","https://openalex.org/W3010805990","https://openalex.org/W3048357344","https://openalex.org/W3102148032","https://openalex.org/W3157563228","https://openalex.org/W3175771377","https://openalex.org/W3186276499","https://openalex.org/W3210638057","https://openalex.org/W4214717370","https://openalex.org/W4287728256","https://openalex.org/W4298857966","https://openalex.org/W4298876402","https://openalex.org/W4307347247","https://openalex.org/W4391410851","https://openalex.org/W6600556750","https://openalex.org/W6632504492","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6683300800","https://openalex.org/W6685444567","https://openalex.org/W6692846177","https://openalex.org/W6735939104","https://openalex.org/W6744838376","https://openalex.org/W6744927671","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6770929369","https://openalex.org/W6780641033","https://openalex.org/W6782194943","https://openalex.org/W6784215524"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027"],"abstract_inverted_index":{"It":[0],"is":[1,15,27,49,100,112,134,151],"well":[2],"known":[3],"that":[4,65,143],"the":[5,18,28,32,41,47,50,59,69,76,108,132,145],"extension":[6],"of":[7,34,62,79,96,107],"Watkins'":[8],"algorithm":[9,51,157],"to":[10,83,126],"general":[11,115],"function":[12,119,159],"approximation":[13],"settings":[14],"challenging:":[16],"does":[17],"\u201cprojected":[19],"Bellman":[20,109,146],"equation\u201d":[21],"have":[22],"a":[23,36,104,140],"solution?":[24],"If":[25],"so,":[26],"solution":[29],"useful":[30],"in":[31,46,58,68],"sense":[33],"generating":[35],"good":[37],"policy?":[38],"And,":[39],"if":[40],"preceding":[42],"questions":[43,54],"are":[44,55,66,89,163,174],"answered":[45],"affirmative,":[48],"consistent?":[52],"These":[53,161],"unanswered":[56],"even":[57],"special":[60],"case":[61],"Q-function":[63],"approximations":[64],"linear":[67,118],"parameter.":[70],"The":[71],"challenge":[72],"seems":[73],"paradoxical,":[74],"given":[75],"long":[77],"history":[78],"convex":[80,97,105,137,141],"analytic":[81],"approaches":[82],"dynamic":[84],"programming.":[85],"Our":[86],"main":[87],"contributions":[88],"summarized":[90],"as":[91],"follows:":[92],"(i)A":[93],"new":[94],"class":[95],"Q-learning":[98,138],"algorithms":[99],"introduced":[101],"based":[102],"on":[103],"relaxation":[106],"equation.":[110],"Convergence":[111],"established":[113],"under":[114],"conditions":[116],"for":[117,149,155,165],"approximation.":[120,160],"(ii)A":[121],"batch":[122],"implementation":[123],"appears":[124],"similar":[125],"LSPI":[127],"and":[128],"DQN":[129,150],"algorithms,":[130],"but":[131],"difference":[133],"substantial:":[135],"while":[136],"solves":[139],"program":[142],"approximates":[144],"equation,":[147],"theory":[148],"no":[152],"stronger":[153],"than":[154],"Watkins":[156],"with":[158,169],"results":[162],"obtained":[164],"deterministic":[166],"nonlinear":[167],"systems":[168],"total":[170],"cost":[171],"criterion.":[172],"Extensions":[173],"proposed.":[175]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-08-02T00:00:00"}