{"id":"https://openalex.org/W4294691315","doi":"https://doi.org/10.23919/acc53348.2022.9867805","title":"Convergence and optimality of policy gradient primal-dual method for constrained Markov decision processes","display_name":"Convergence and optimality of policy gradient primal-dual method for constrained Markov decision processes","publication_year":2022,"publication_date":"2022-06-08","ids":{"openalex":"https://openalex.org/W4294691315","doi":"https://doi.org/10.23919/acc53348.2022.9867805"},"language":"en","primary_location":{"id":"doi:10.23919/acc53348.2022.9867805","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867805","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","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 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/A5008672638","display_name":"Dong-Sheng Ding","orcid":"https://orcid.org/0000-0002-5051-4777"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dongsheng Ding","raw_affiliation_strings":["University of Southern California,Department of Electrical and Computer Engineering,Los Angeles,CA,90089"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Department of Electrical and Computer Engineering,Los Angeles,CA,90089","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047410441","display_name":"Kaiqing Zhang","orcid":"https://orcid.org/0000-0002-7446-7581"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaiqing Zhang","raw_affiliation_strings":["Massachusetts Institute of Technology,LIDS and CSAIL,Cambridge,MA,02139"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,LIDS and CSAIL,Cambridge,MA,02139","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019604570","display_name":"Tamer Ba\u015far","orcid":"https://orcid.org/0000-0003-4406-7875"},"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":"Tamer Basar","raw_affiliation_strings":["University of Illinois at Urbana-Champaign,Department of Electrical and Computer Engineering and Coordinated Science Laboratory,Urbana,IL,61801"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign,Department of Electrical and Computer Engineering and Coordinated Science Laboratory,Urbana,IL,61801","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087790067","display_name":"Mihailo R. Jovanovi\u0107","orcid":"https://orcid.org/0000-0002-4181-2924"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mihailo R. Jovanovic","raw_affiliation_strings":["University of Southern California,Department of Electrical and Computer Engineering,Los Angeles,CA,90089"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Department of Electrical and Computer Engineering,Los Angeles,CA,90089","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008672638"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.7271,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.71202327,"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":"2851","last_page":"2856"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9961000084877014,"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/T12288","display_name":"Optimization and Search Problems","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/mathematical-optimization","display_name":"Mathematical optimization","score":0.6744894981384277},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6242396235466003},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6213066577911377},{"id":"https://openalex.org/keywords/sublinear-function","display_name":"Sublinear function","score":0.5993518829345703},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.5849714875221252},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5117108821868896},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.49381884932518005},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.48514828085899353},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.46370798349380493},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4546833038330078},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.44354888796806335},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4291410446166992},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3758735656738281},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.35701173543930054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.07147425413131714}],"concepts":[{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6744894981384277},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6242396235466003},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6213066577911377},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.5993518829345703},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.5849714875221252},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5117108821868896},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.49381884932518005},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.48514828085899353},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.46370798349380493},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4546833038330078},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.44354888796806335},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4291410446166992},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3758735656738281},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.35701173543930054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.07147425413131714},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc53348.2022.9867805","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867805","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","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 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1484478478","https://openalex.org/W1504265534","https://openalex.org/W1518931405","https://openalex.org/W1845972764","https://openalex.org/W2070570138","https://openalex.org/W2111492941","https://openalex.org/W2155511972","https://openalex.org/W2788014517","https://openalex.org/W2804791273","https://openalex.org/W2901573274","https://openalex.org/W2942608247","https://openalex.org/W2947996939","https://openalex.org/W2963525569","https://openalex.org/W2981915592","https://openalex.org/W3008953696","https://openalex.org/W3046366290","https://openalex.org/W3098983831","https://openalex.org/W3101517963","https://openalex.org/W3125031134","https://openalex.org/W3162902207","https://openalex.org/W4287725923","https://openalex.org/W4287829052","https://openalex.org/W4288020947","https://openalex.org/W4288269457","https://openalex.org/W4288363736","https://openalex.org/W4293545785","https://openalex.org/W4297824337","https://openalex.org/W4320473289","https://openalex.org/W6687063787","https://openalex.org/W6737893269","https://openalex.org/W6748512255","https://openalex.org/W6751725685","https://openalex.org/W6756427573","https://openalex.org/W6763002318","https://openalex.org/W6763496775","https://openalex.org/W6767486501","https://openalex.org/W6770009701","https://openalex.org/W6770744290","https://openalex.org/W6774091466","https://openalex.org/W6774406872","https://openalex.org/W6774521036","https://openalex.org/W6780486084","https://openalex.org/W6780587392","https://openalex.org/W6785471904","https://openalex.org/W6785819423","https://openalex.org/W6789855942","https://openalex.org/W6902717962"],"related_works":["https://openalex.org/W2367222340","https://openalex.org/W2349149331","https://openalex.org/W2161367706","https://openalex.org/W2380172021","https://openalex.org/W2022701811","https://openalex.org/W2117282672","https://openalex.org/W2962728842","https://openalex.org/W4287185865","https://openalex.org/W4226246290","https://openalex.org/W3159422316"],"abstract_inverted_index":{"We":[0],"study":[1],"constrained":[2,61],"Markov":[3],"decision":[4],"processes":[5],"with":[6,78],"finite":[7],"state":[8],"and":[9,46,88,102],"action":[10],"spaces.":[11],"The":[12],"optimal":[13,19],"solution":[14],"of":[15,57,59,83,110],"a":[16,25,94],"discounted":[17],"infinite-horizon":[18],"control":[20],"problem":[21,63],"is":[22],"obtained":[23],"using":[24],"Policy":[26],"Gradient":[27],"Primal-Dual":[28],"(PG-PD)":[29],"method":[30,36],"without":[31],"any":[32],"policy":[33,43,65],"parametrization.":[34],"This":[35],"updates":[37],"the":[38,47,55,60,69,85,89,108],"primal":[39],"variable":[40,49],"via":[41,50],"projected":[42,51],"gradient":[44],"ascent":[45],"dual":[48],"sub-gradient":[52],"descent.":[53],"Despite":[54],"lack":[56],"concavity":[58],"maximization":[62],"in":[64,81],"space,":[66],"we":[67,98],"exploit":[68],"underlying":[70],"structure":[71],"to":[72,106],"provide":[73],"non-asymptotic":[74],"global":[75],"convergence":[76],"guarantees":[77],"sublinear":[79],"rates":[80],"terms":[82],"both":[84],"optimality":[86],"gap":[87],"constraint":[90],"violation.":[91],"Furthermore,":[92],"for":[93],"sample-based":[95],"PG-PD":[96],"algorithm,":[97],"quantify":[99],"sample":[100],"complexity":[101],"offer":[103],"computational":[104],"experiments":[105],"demonstrate":[107],"effectiveness":[109],"our":[111],"results.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}