{"id":"https://openalex.org/W7105594144","doi":"https://doi.org/10.1109/tg.2025.3629681","title":"Adaptive Graph Coordination Strategy in Multiagent Reinforcement Learning","display_name":"Adaptive Graph Coordination Strategy in Multiagent Reinforcement Learning","publication_year":2025,"publication_date":"2025-11-13","ids":{"openalex":"https://openalex.org/W7105594144","doi":"https://doi.org/10.1109/tg.2025.3629681"},"language":null,"primary_location":{"id":"doi:10.1109/tg.2025.3629681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2025.3629681","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"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 Games","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":null,"display_name":"Zhongwei Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongwei Yu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingqing Ruan","orcid":"https://orcid.org/0000-0002-4857-9053"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingqing Ruan","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4857-9053","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":null,"display_name":"Dengpeng Xing","orcid":"https://orcid.org/0000-0002-8251-9118"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dengpeng Xing","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8251-9118","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7374485,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"1","first_page":"151","last_page":"162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7041000127792358,"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":0.7041000127792358,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.09610000252723694,"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"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.03610000014305115,"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/graph","display_name":"Graph","score":0.5925999879837036},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5817999839782715},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.545799970626831},{"id":"https://openalex.org/keywords/directed-graph","display_name":"Directed graph","score":0.42969998717308044},{"id":"https://openalex.org/keywords/graph-rewriting","display_name":"Graph rewriting","score":0.39890000224113464},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.3926999866962433}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7207000255584717},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5925999879837036},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5817999839782715},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.545799970626831},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41760000586509705},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4020000100135803},{"id":"https://openalex.org/C558772884","wikidata":"https://www.wikidata.org/wiki/Q1508564","display_name":"Graph rewriting","level":3,"score":0.39890000224113464},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C107257861","wikidata":"https://www.wikidata.org/wiki/Q656316","display_name":"Coordination game","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3255999982357025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31450000405311584},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3125},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.28110000491142273},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.26570001244544983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tg.2025.3629681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2025.3629681","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"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 Games","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7166604399681091,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2807741983","https://openalex.org/W2983178256","https://openalex.org/W2997072274","https://openalex.org/W2997502221","https://openalex.org/W2998367975","https://openalex.org/W3119186746","https://openalex.org/W3173215816","https://openalex.org/W3173782550","https://openalex.org/W3194351817","https://openalex.org/W3202423398","https://openalex.org/W4205536455","https://openalex.org/W4306680355","https://openalex.org/W4403904960","https://openalex.org/W7124259585"],"related_works":[],"abstract_inverted_index":{"Many":[0],"real-world":[1],"applications":[2],"involve":[3],"a":[4,18,53,70,76,113,122],"team":[5],"of":[6,35,151],"agents":[7],"who":[8],"must":[9],"coordinate":[10],"each":[11],"other's":[12],"policies":[13],"in":[14,43,137],"real-time":[15],"to":[16,28,80,83,90,106,126],"achieve":[17],"shared":[19],"goal.":[20],"Previous":[21],"studies":[22],"mainly":[23],"focus":[24],"on":[25,131,143],"decentralized":[26],"control":[27,38,81],"maximize":[29],"common":[30],"rewards,":[31],"with":[32,155],"little":[33],"consideration":[34],"coordination":[36,57,134],"between":[37,115],"policies,":[39],"which":[40],"is":[41],"critical":[42],"dynamic":[44],"and":[45,69,86,101,111,117,158],"complicated":[46],"environments.":[47],"Viewing":[48],"this":[49],"issue,":[50],"we":[51,98],"propose":[52],"novel":[54],"adaptive":[55,66],"graph":[56,67,95,109],"strategy":[58],"that":[59],"factorizes":[60],"the":[61,92,108,132,138,149,152],"joint":[62],"policy":[63,125],"into":[64],"an":[65,87],"generator":[68],"graph-based":[71,123],"coordinated":[72,124,161],"policy.":[73],"We":[74,119],"employ":[75],"difference":[77],"aware":[78],"module":[79,89],"when":[82],"generate":[84],"graphs":[85],"encoder-decoder":[88],"acquire":[91],"underlying":[93],"decision":[94],"structure.":[96],"Moreover,":[97],"introduce":[99],"DAGness-":[100],"DAG":[102],"depth":[103],"constrained":[104],"optimization":[105],"adjust":[107],"structure":[110],"strike":[112],"balance":[114],"efficiency":[116],"performance.":[118],"also":[120],"present":[121],"make":[127],"asynchronous":[128],"decisions":[129],"based":[130],"inter-agent":[133],"dependencies":[135],"implied":[136],"generated":[139],"graph.":[140],"Empirical":[141],"evaluations":[142],"some":[144],"cooperative":[145],"multi-agent":[146],"environments":[147],"demonstrate":[148],"superiority":[150],"proposed":[153],"method,":[154],"faster":[156],"convergence":[157],"more":[159],"efficient":[160],"policies.":[162]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-13T00:00:00"}