{"id":"https://openalex.org/W2606378794","doi":"https://doi.org/10.1109/tnnls.2016.2609500","title":"Off-Policy Reinforcement Learning for Synchronization in Multiagent Graphical Games","display_name":"Off-Policy Reinforcement Learning for Synchronization in Multiagent Graphical Games","publication_year":2017,"publication_date":"2017-04-17","ids":{"openalex":"https://openalex.org/W2606378794","doi":"https://doi.org/10.1109/tnnls.2016.2609500","mag":"2606378794","pmid":"https://pubmed.ncbi.nlm.nih.gov/28436891"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2016.2609500","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2016.2609500","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5070599005","display_name":"Jinna Li","orcid":"https://orcid.org/0000-0001-9985-6308"},"institutions":[{"id":"https://openalex.org/I48780066","display_name":"Shenyang University of Chemical Technology","ror":"https://ror.org/03dbpdh75","country_code":"CN","type":"education","lineage":["https://openalex.org/I48780066"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinna Li","raw_affiliation_strings":["College of Information Engineering, Shenyang University of Chemical Technology, Shenyang, China","State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"College of Information Engineering, Shenyang University of Chemical Technology, Shenyang, China","institution_ids":["https://openalex.org/I48780066"]},{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063118155","display_name":"Hamidreza Modares","orcid":"https://orcid.org/0000-0003-0800-5140"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamidreza Modares","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO, USA","institution_ids":["https://openalex.org/I20382870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042520521","display_name":"Tianyou Chai","orcid":"https://orcid.org/0000-0002-4623-1483"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyou Chai","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["Northeastern University, Shenyang, China","UTA Research Institute, The University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"UTA Research Institute, The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100365448","display_name":"Lihua Xie","orcid":"https://orcid.org/0000-0002-7137-4136"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lihua Xie","raw_affiliation_strings":["School of Electrical and Electronic Engineering, College of Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, College of Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070599005"],"corresponding_institution_ids":["https://openalex.org/I48780066","https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":18.7842,"has_fulltext":false,"cited_by_count":188,"citation_normalized_percentile":{"value":0.99526882,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"28","issue":"10","first_page":"2434","last_page":"2445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9944000244140625,"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":0.9830999970436096,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8889672160148621},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7477249503135681},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6646300554275513},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.6359087228775024},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5267291069030762},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5179861783981323},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.49676233530044556},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4833471477031708},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4789474606513977},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4622383713722229},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4394875168800354},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.41429033875465393},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29686543345451355},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16933223605155945},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1631631851196289}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8889672160148621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7477249503135681},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6646300554275513},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.6359087228775024},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5267291069030762},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5179861783981323},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.49676233530044556},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4833471477031708},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4789474606513977},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4622383713722229},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4394875168800354},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.41429033875465393},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29686543345451355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16933223605155945},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1631631851196289},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2016.2609500","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2016.2609500","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:28436891","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28436891","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G5156944241","display_name":null,"funder_award_id":"61525302","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7272473876","display_name":null,"funder_award_id":"61590922","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G74425646","display_name":null,"funder_award_id":"61673280","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7583496911","display_name":null,"funder_award_id":"61333012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G772161998","display_name":null,"funder_award_id":"61304028","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8743717570","display_name":null,"funder_award_id":"61503257","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8875637860","display_name":null,"funder_award_id":"61104093","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W575429305","https://openalex.org/W1513689897","https://openalex.org/W1578630563","https://openalex.org/W1614417283","https://openalex.org/W1684533383","https://openalex.org/W1912694276","https://openalex.org/W1918371733","https://openalex.org/W1972243698","https://openalex.org/W1983523909","https://openalex.org/W1991284037","https://openalex.org/W1995286048","https://openalex.org/W1998361253","https://openalex.org/W1999678919","https://openalex.org/W1999728505","https://openalex.org/W2005127705","https://openalex.org/W2040871222","https://openalex.org/W2052649120","https://openalex.org/W2055300044","https://openalex.org/W2081514674","https://openalex.org/W2083283377","https://openalex.org/W2092215165","https://openalex.org/W2093300195","https://openalex.org/W2093831009","https://openalex.org/W2105850748","https://openalex.org/W2108286682","https://openalex.org/W2108383324","https://openalex.org/W2116540016","https://openalex.org/W2130751725","https://openalex.org/W2478654971","https://openalex.org/W2767784613","https://openalex.org/W3142915818","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1859185863","https://openalex.org/W4307691181","https://openalex.org/W4285537323","https://openalex.org/W1932159282","https://openalex.org/W2964126589","https://openalex.org/W3016225735","https://openalex.org/W2808418668","https://openalex.org/W1518875602","https://openalex.org/W3105579180","https://openalex.org/W2017412075"],"abstract_inverted_index":{"This":[0,16],"paper":[1],"develops":[2],"an":[3,107,140],"off-policy":[4,41,84,141],"reinforcement":[5],"learning":[6],"(RL)":[7],"algorithm":[8,43,143,178],"to":[9,28,73,76,92,122,188],"solve":[10],"optimal":[11,53,156,171],"synchronization":[12,54],"of":[13,23,36,60,196],"multiagent":[14],"systems.":[15],"is":[17,44,71,87,144,147,167],"accomplished":[18],"by":[19,134,175],"using":[20,130,162],"the":[21,39,52,61,94,98,131,154,170,176,180,189,194,197],"framework":[22],"graphical":[24],"games.":[25],"In":[26],"contrast":[27],"traditional":[29],"control":[30,66,125,157],"protocols,":[31],"which":[32],"require":[33],"complete":[34],"knowledge":[35,59],"agent":[37,62,75,91,161],"dynamics,":[38],"proposed":[40,177,198],"RL":[42,142],"a":[45],"model-free":[46],"approach,":[47],"in":[48,149],"that":[49,146,169],"it":[50],"solves":[51],"problem":[55],"without":[56],"knowing":[57],"any":[58],"dynamics.":[63],"A":[64],"prescribed":[65,136],"policy,":[67,70,104,109],"called":[68,102],"behavior":[69,137],"applied":[72],"each":[74,90,160],"generate":[77],"and":[78,105,112,127,152,184],"collect":[79],"data":[80,132],"for":[81,89,97,159],"learning.":[82],"An":[83],"Bellman":[85],"equation":[86],"derived":[88],"learn":[93],"value":[95,128],"function":[96],"policy":[99,158],"under":[100],"evaluation,":[101],"target":[103,124],"find":[106],"improved":[108],"simultaneously.":[110],"Actor":[111],"critic":[113],"neural":[114],"networks":[115],"along":[116],"with":[117],"least-square":[118],"approach":[119],"are":[120],"employed":[121],"approximate":[123,155],"policies":[126,173],"functions":[129],"generated":[133],"applying":[135],"policies.":[138],"Finally,":[139],"presented":[145],"implemented":[148],"real":[150],"time":[151],"gives":[153],"only":[163],"measured":[164],"data.":[165],"It":[166],"shown":[168],"distributed":[172],"found":[174],"satisfy":[179],"global":[181],"Nash":[182],"equilibrium":[183],"synchronize":[185],"all":[186],"agents":[187],"leader.":[190],"Simulation":[191],"results":[192],"illustrate":[193],"effectiveness":[195],"method.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":30},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":29},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}