{"id":"https://openalex.org/W4406857807","doi":"https://doi.org/10.1109/tac.2025.3534639","title":"Multiagent Reinforcement Learning for Constrained Markov Decision Processes by Consensus-Based Primal\u2013Dual Method","display_name":"Multiagent Reinforcement Learning for Constrained Markov Decision Processes by Consensus-Based Primal\u2013Dual Method","publication_year":2025,"publication_date":"2025-01-27","ids":{"openalex":"https://openalex.org/W4406857807","doi":"https://doi.org/10.1109/tac.2025.3534639"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2025.3534639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3534639","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/A5065773338","display_name":"Gaochen Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaochen Cui","raw_affiliation_strings":["CFINS, Department of Automations, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-3423-3792","affiliations":[{"raw_affiliation_string":"CFINS, Department of Automations, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044965133","display_name":"Qing\u2010Shan Jia","orcid":"https://orcid.org/0000-0002-4683-7215"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing-Shan Jia","raw_affiliation_strings":["CFINS, Department of Automations, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4683-7215","affiliations":[{"raw_affiliation_string":"CFINS, Department of Automations, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075845093","display_name":"Xiaohong Guan","orcid":"https://orcid.org/0000-0002-8826-0362"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohong Guan","raw_affiliation_strings":["CFINS, Department of Automations, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8826-0362","affiliations":[{"raw_affiliation_string":"CFINS, Department of Automations, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.4058,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79325137,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"70","issue":"6","first_page":"4217","last_page":"4224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.5824000239372253,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.5824000239372253,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8395911455154419},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7470093965530396},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.7291616797447205},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6430025100708008},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5389841794967651},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5234783887863159},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5049131512641907},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4496944844722748},{"id":"https://openalex.org/keywords/consensus","display_name":"Consensus","score":0.4375162720680237},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4016490876674652},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3681778311729431},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24567431211471558}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8395911455154419},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7470093965530396},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.7291616797447205},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6430025100708008},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5389841794967651},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5234783887863159},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5049131512641907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4496944844722748},{"id":"https://openalex.org/C107107730","wikidata":"https://www.wikidata.org/wiki/Q2994424","display_name":"Consensus","level":3,"score":0.4375162720680237},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4016490876674652},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3681778311729431},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24567431211471558},{"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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2025.3534639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3534639","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":[{"id":"https://metadata.un.org/sdg/16","score":0.6800000071525574,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1761450871","display_name":null,"funder_award_id":"62073182","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G184828240","display_name":null,"funder_award_id":"62192751","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4613428600","display_name":null,"funder_award_id":"L233005","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G5492808859","display_name":null,"funder_award_id":"62125304","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W118602349","https://openalex.org/W1998345701","https://openalex.org/W2033118636","https://openalex.org/W2070570138","https://openalex.org/W2082261506","https://openalex.org/W2161270100","https://openalex.org/W2525042068","https://openalex.org/W2569714389","https://openalex.org/W2575705757","https://openalex.org/W2588802774","https://openalex.org/W2590657229","https://openalex.org/W2790306973","https://openalex.org/W2811160477","https://openalex.org/W2919115771","https://openalex.org/W2963649943","https://openalex.org/W2964208174","https://openalex.org/W2973229164","https://openalex.org/W3173294282","https://openalex.org/W4206497039","https://openalex.org/W4238852866","https://openalex.org/W4302033506","https://openalex.org/W6683001934","https://openalex.org/W6738796088","https://openalex.org/W6749032143","https://openalex.org/W6749304979","https://openalex.org/W6770009701","https://openalex.org/W6771232374","https://openalex.org/W6779279235","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4404955202"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"consider":[4],"multiagent":[5,145],"reinforcement":[6],"learning":[7],"for":[8],"constrained":[9,120],"Markov":[10,121],"decision":[11,122],"processes":[12],"and":[13,26,89,108],"develop":[14],"a":[15,94,111,116],"consensus-based":[16,76],"primal\u2013dual":[17,73],"method":[18,77,125],"to":[19,49,62,80,102,110,126],"solve":[20],"the":[21,39,43,47,59,64,67,72,82,85,90,106,124,128,131,140,144,154,157],"problem,":[22],"which":[23,152],"is":[24,56,78,100,134],"model-free":[25],"with":[27,31,66],"provable":[28],"convergence.":[29],"Compared":[30],"existing":[32],"methods,":[33],"our":[34],"algorithm":[35,99,142,147],"does":[36],"not":[37],"require":[38],"dynamic":[40],"model":[41],"of":[42,84,119,130],"system,":[44],"nor":[45],"ask":[46],"agents":[48,107],"share":[50],"their":[51],"local":[52],"policies.":[53],"The":[54,75,97],"constraint":[55,155],"incorporated":[57],"in":[58,93,156],"objective":[60,158],"function":[61],"form":[63],"Lagrangian":[65],"dual":[68,91],"variables":[69,92],"updated":[70],"through":[71],"method.":[74],"applied":[79],"update":[81],"parameters":[83],"approximate":[86],"action-value":[87],"functions":[88],"distributed":[95],"manner.":[96],"developed":[98,141],"shown":[101],"achieve":[103],"consensus":[104],"among":[105],"converge":[109],"locally":[112],"optimal":[113],"policy.":[114],"For":[115],"certain":[117],"type":[118],"processes,":[123],"ensure":[127],"feasibility":[129],"final":[132],"solution":[133],"developed.":[135],"Numerical":[136],"results":[137],"show":[138],"that":[139],"outperforms":[143],"actor\u2013critic":[146],"(Liu":[148],"et":[149],"al.,":[150],"2018),":[151],"incorporates":[153],"directly.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}