{"id":"https://openalex.org/W4392719362","doi":"https://doi.org/10.1109/tac.2024.3375248","title":"Distributed Multiagent Reinforcement Learning Based on Graph-Induced Local Value Functions","display_name":"Distributed Multiagent Reinforcement Learning Based on Graph-Induced Local Value Functions","publication_year":2024,"publication_date":"2024-03-12","ids":{"openalex":"https://openalex.org/W4392719362","doi":"https://doi.org/10.1109/tac.2024.3375248"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2024.3375248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3375248","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/A5073846906","display_name":"Gangshan Jing","orcid":"https://orcid.org/0000-0003-0066-204X"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gangshan Jing","raw_affiliation_strings":["School of Automation, Chongqing University, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040513070","display_name":"He Bai","orcid":"https://orcid.org/0000-0002-4247-0698"},"institutions":[{"id":"https://openalex.org/I115475287","display_name":"Oklahoma State University","ror":"https://ror.org/01g9vbr38","country_code":"US","type":"education","lineage":["https://openalex.org/I115475287"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"He Bai","raw_affiliation_strings":["Oklahoma State University, Stillwater, OK, USA"],"affiliations":[{"raw_affiliation_string":"Oklahoma State University, Stillwater, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054187846","display_name":"Jemin George","orcid":"https://orcid.org/0000-0001-8417-5411"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jemin George","raw_affiliation_strings":["U.S. Army Research Laboratory, Adelphi, MD, USA"],"affiliations":[{"raw_affiliation_string":"U.S. Army Research Laboratory, Adelphi, MD, USA","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055360778","display_name":"Aranya Chakrabortty","orcid":"https://orcid.org/0000-0002-3474-8215"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aranya Chakrabortty","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078394771","display_name":"P. Sharma","orcid":null},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piyush K. Sharma","raw_affiliation_strings":["U.S. Army Research Laboratory, Adelphi, MD, USA"],"affiliations":[{"raw_affiliation_string":"U.S. Army Research Laboratory, Adelphi, MD, USA","institution_ids":["https://openalex.org/I166416128"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5073846906"],"corresponding_institution_ids":["https://openalex.org/I158842170"],"apc_list":null,"apc_paid":null,"fwci":1.0245,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.78683626,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"69","issue":"10","first_page":"6636","last_page":"6651"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9932000041007996,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9930999875068665,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8256797790527344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5728929042816162},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5142921805381775},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4992377758026123},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.41880089044570923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3713133931159973},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.36871930956840515},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3415301740169525},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2942847013473511},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2771545648574829},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14348292350769043}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8256797790527344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5728929042816162},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5142921805381775},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4992377758026123},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.41880089044570923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3713133931159973},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36871930956840515},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3415301740169525},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2942847013473511},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2771545648574829},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14348292350769043},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2024.3375248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3375248","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G5361399887","display_name":null,"funder_award_id":"2212582","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5921719111","display_name":null,"funder_award_id":"62203073","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7416579264","display_name":null,"funder_award_id":"ECCS 1931932","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/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1542941925","https://openalex.org/W1701050018","https://openalex.org/W1918371733","https://openalex.org/W2046859786","https://openalex.org/W2074796812","https://openalex.org/W2110906765","https://openalex.org/W2149479912","https://openalex.org/W2580909119","https://openalex.org/W2766447205","https://openalex.org/W2904304778","https://openalex.org/W2948432982","https://openalex.org/W2964305565","https://openalex.org/W2968526727","https://openalex.org/W2972523776","https://openalex.org/W2982493444","https://openalex.org/W2991046523","https://openalex.org/W3035141911","https://openalex.org/W3082658705","https://openalex.org/W3118685725","https://openalex.org/W3134022240","https://openalex.org/W3156295478","https://openalex.org/W3157457774","https://openalex.org/W3163894240","https://openalex.org/W3171210634","https://openalex.org/W3213818741","https://openalex.org/W3217389438","https://openalex.org/W4221146329","https://openalex.org/W4244375620","https://openalex.org/W4287758272","https://openalex.org/W4381327650","https://openalex.org/W4394586218","https://openalex.org/W6637228341","https://openalex.org/W6676769901","https://openalex.org/W6677834374","https://openalex.org/W6679365036","https://openalex.org/W6736572398","https://openalex.org/W6745209853","https://openalex.org/W6749032143","https://openalex.org/W6752380930","https://openalex.org/W6754297394","https://openalex.org/W6756870468","https://openalex.org/W6758646351","https://openalex.org/W6771232374","https://openalex.org/W6779279235","https://openalex.org/W6779874797","https://openalex.org/W6780486084","https://openalex.org/W6782649914","https://openalex.org/W6790723713","https://openalex.org/W6796258226","https://openalex.org/W6802973543","https://openalex.org/W6849609359"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Achieving":[0],"distributed":[1,44,95,178],"reinforcement":[2,51],"learning":[3,52],"(RL)":[4],"for":[5,46,138],"large-scale":[6,171],"cooperative":[7,49],"multi-agent":[8,50],"systems":[9],"(MASs)":[10],"is":[11,111,146],"challenging":[12],"because:":[13],"(i)":[14],"each":[15],"agent":[16],"has":[17],"access":[18],"to":[19,32,113,170],"only":[20],"limited":[21],"information;":[22],"(ii)":[23],"issues":[24],"on":[25,99,121],"scalability":[26,169],"and":[27,83,133,154,176],"sample":[28,47,115],"efficiency":[29],"emerge":[30],"due":[31],"the":[33,56,78,105,122,151,156],"curse":[34],"of":[35,58,72],"dimensionality.":[36],"In":[37],"this":[38,62],"paper,":[39],"we":[40,92],"propose":[41,93],"a":[42,89,147,166],"general":[43],"framework":[45],"efficient":[48,136],"(MARL)":[53],"by":[54],"utilizing":[55],"structures":[57],"graphs":[59,68],"involved":[60],"in":[61,75],"problem.":[63],"We":[64],"introduce":[65],"three":[66,70],"coupling":[67,106,142],"describing":[69],"types":[71],"inter-agent":[73],"couplings":[74],"MARL,":[76],"namely,":[77],"state":[79],"graph,":[80,91],"observation":[81],"graph":[82],"reward":[84],"graph.":[85],"By":[86],"further":[87],"considering":[88],"communication":[90],"two":[94],"RL":[96,163,179],"approaches":[97],"based":[98],"local":[100],"value":[101],"functions":[102],"derived":[103],"from":[104],"graphs.":[107,125,143],"The":[108,126],"first":[109],"approach":[110,128],"able":[112],"reduce":[114],"complexity":[116],"significantly":[117,167],"under":[118],"specific":[119],"conditions":[120],"aforementioned":[123],"four":[124],"second":[127],"provides":[129],"an":[130],"approximate":[131],"solution":[132],"can":[134],"be":[135],"even":[137],"problems":[139],"with":[140,174],"dense":[141],"Here":[144],"there":[145],"trade-off":[148],"between":[149],"minimizing":[150],"approximation":[152],"error":[153],"reducing":[155],"computational":[157],"complexity.":[158],"Simulations":[159],"show":[160],"that":[161],"our":[162],"algorithms":[164],"have":[165],"improved":[168],"MASs":[172],"compared":[173],"centralized":[175],"consensus-based":[177],"algorithms.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}