{"id":"https://openalex.org/W4404840317","doi":"https://doi.org/10.1109/tcds.2024.3504256","title":"SMART: Sequential Multiagent Reinforcement Learning With Role Assignment Using\u00a0Transformer","display_name":"SMART: Sequential Multiagent Reinforcement Learning With Role Assignment Using\u00a0Transformer","publication_year":2024,"publication_date":"2024-11-29","ids":{"openalex":"https://openalex.org/W4404840317","doi":"https://doi.org/10.1109/tcds.2024.3504256"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2024.3504256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2024.3504256","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","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/A5030762555","display_name":"Yixing Lan","orcid":"https://orcid.org/0000-0003-4503-643X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yixing Lan","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-4503-643X","affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081286464","display_name":"Hao Gao","orcid":"https://orcid.org/0000-0001-6974-4997"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Gao","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-6974-4997","affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-3238-745X","affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055651722","display_name":"Qiang Fang","orcid":"https://orcid.org/0000-0002-5063-6889"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Fang","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-5063-6889","affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003590227","display_name":"Yujun Zeng","orcid":"https://orcid.org/0000-0002-5765-684X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujun Zeng","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-5765-684X","affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030762555"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":1.3245,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84606186,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"17","issue":"3","first_page":"615","last_page":"630"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9254999756813049,"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":0.9254999756813049,"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/computer-science","display_name":"Computer science","score":0.8479982614517212},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8391714096069336},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6723161339759827},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41628652811050415},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.41366010904312134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40667465329170227},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.11701968312263489},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09142887592315674},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0831272304058075}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8479982614517212},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8391714096069336},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6723161339759827},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41628652811050415},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.41366010904312134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40667465329170227},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11701968312263489},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09142887592315674},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0831272304058075},{"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/tcds.2024.3504256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2024.3504256","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1011235699","display_name":null,"funder_award_id":"62403483","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G62426012","display_name":null,"funder_award_id":"U24A20279","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8354495100","display_name":null,"funder_award_id":"U21A20518","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W154189223","https://openalex.org/W1512681781","https://openalex.org/W2149756872","https://openalex.org/W2173717895","https://openalex.org/W2604337321","https://openalex.org/W2747213132","https://openalex.org/W2759848268","https://openalex.org/W2786572318","https://openalex.org/W2896457183","https://openalex.org/W2967474307","https://openalex.org/W2968284168","https://openalex.org/W2982316857","https://openalex.org/W2997502221","https://openalex.org/W3036329728","https://openalex.org/W3036749513","https://openalex.org/W3156295478","https://openalex.org/W3196869853","https://openalex.org/W4214634256","https://openalex.org/W4234761190","https://openalex.org/W4312622223","https://openalex.org/W4362590704","https://openalex.org/W4385834352","https://openalex.org/W4387681925","https://openalex.org/W4387885940","https://openalex.org/W4390120052","https://openalex.org/W6678481081","https://openalex.org/W6682753738","https://openalex.org/W6749304979","https://openalex.org/W6758076299","https://openalex.org/W6758846586","https://openalex.org/W6759315145","https://openalex.org/W6772135379","https://openalex.org/W6775529125","https://openalex.org/W6778883912","https://openalex.org/W6781750019","https://openalex.org/W6783196708","https://openalex.org/W6796289742","https://openalex.org/W6797584944","https://openalex.org/W6800682094","https://openalex.org/W6802002411","https://openalex.org/W6803572779","https://openalex.org/W6838682728","https://openalex.org/W6840753250","https://openalex.org/W6841287799","https://openalex.org/W6844628001"],"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":{"Multiagent":[0],"reinforcement":[1],"learning":[2,17,32,69,107],"(MARL)":[3],"has":[4],"received":[5],"increasing":[6],"attention":[7],"and":[8,16,29,45,78,90,106,120,148,164],"been":[9],"used":[10],"to":[11,115],"solve":[12],"cooperative":[13],"multiagent":[14,104,130,150],"decision-making":[15],"control":[18],"tasks.":[19],"However,":[20],"the":[21,25,30,42,70,82,86,91,100,103,126,144,173,183],"high":[22],"complexity":[23,101],"of":[24,48,72,85,96,102,128,136,185],"joint":[26],"action":[27,83,88,121],"space":[28,89],"nonstationary":[31,129],"process":[33],"are":[34,152],"two":[35],"major":[36],"problems":[37],"that":[38,155],"negatively":[39],"impact":[40],"on":[41,75,143],"sample":[43],"efficiency":[44],"solution":[46],"quality":[47],"MARL.":[49],"To":[50],"this":[51,53],"end,":[52],"article":[54],"proposes":[55],"a":[56,168],"novel":[57],"approach":[58],"named":[59],"sequential":[60],"MARL":[61,159],"with":[62,157],"role":[63,93,117],"assignment":[64,118],"using":[65],"transformer":[66,113],"(SMART).":[67],"By":[68],"effects":[71],"different":[73],"actions":[74],"state":[76],"transitions":[77],"rewards,":[79],"SMART":[80,110,137,166,177],"realizes":[81],"abstraction":[84],"original":[87],"adaptive":[92],"cognitive":[94],"modeling":[95],"multiagent,":[97],"which":[98],"reduces":[99],"exploration":[105],"process.":[108],"Meanwhile,":[109,172],"uses":[111],"causal":[112],"networks":[114],"update":[116],"policy":[119,123,131],"selection":[122],"sequentially,":[124],"alleviating":[125],"influence":[127],"learning.":[132],"The":[133],"convergence":[134],"characteristic":[135],"is":[138],"theoretically":[139],"analyzed.":[140],"Extensive":[141],"experiments":[142],"challenging":[145],"Google":[146],"football":[147],"StarCraft":[149],"challenge":[151],"conducted,":[153],"demonstrating":[154],"compared":[156],"mainstream":[158],"algorithms":[160],"such":[161],"as":[162],"MAT":[163],"HAPPO,":[165],"achieves":[167],"new":[169],"state-of-the-art":[170],"performance.":[171],"learned":[174],"policies":[175],"through":[176],"have":[178],"good":[179],"generalization":[180],"ability":[181],"when":[182],"number":[184],"agents":[186],"changes.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}