{"id":"https://openalex.org/W4409326448","doi":"https://doi.org/10.1109/lra.2025.3559828","title":"Self-Organised Sequential Multi-Agent Reinforcement Learning for Closely Cooperation Tasks","display_name":"Self-Organised Sequential Multi-Agent Reinforcement Learning for Closely Cooperation Tasks","publication_year":2025,"publication_date":"2025-04-10","ids":{"openalex":"https://openalex.org/W4409326448","doi":"https://doi.org/10.1109/lra.2025.3559828"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3559828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3559828","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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/A5057736812","display_name":"\u6d69\u5e73 \u5ddd\u526f","orcid":"https://orcid.org/0000-0002-8112-5950"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Fu","raw_affiliation_strings":["College of Electronic and Information Engineering, Tongji University, Shanghai, China","College of Electronic and Information Engineering, Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, China"],"affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"College of Electronic and Information Engineering, Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010299064","display_name":"Mingyu You","orcid":"https://orcid.org/0000-0003-2758-167X"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyu You","raw_affiliation_strings":["College of Electronic and Information Engineering, Tongji University, Shanghai, China","College of Electronic and Information Engineering, Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, China"],"affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"College of Electronic and Information Engineering, Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101789136","display_name":"Hongjun Zhou","orcid":"https://orcid.org/0000-0002-6256-2485"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongjun Zhou","raw_affiliation_strings":["College of Electronic and Information Engineering, Tongji University, Shanghai, China","College of Electronic and Information Engineering, Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, China"],"affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"College of Electronic and Information Engineering, Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049557511","display_name":"Bin He","orcid":"https://orcid.org/0000-0003-3193-6269"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin He","raw_affiliation_strings":["College of Electronic and Information Engineering, Tongji University, Shanghai, China","College of Electronic and Information Engineering, Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, China"],"affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"College of Electronic and Information Engineering, Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057736812"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0916466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"6","first_page":"5967","last_page":"5974"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.6499000191688538,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.6499000191688538,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7085285782814026},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5824156403541565},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5236660838127136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3441697955131531},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.25038957595825195},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.14993801712989807}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7085285782814026},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5824156403541565},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5236660838127136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3441697955131531},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25038957595825195},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.14993801712989807}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3559828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3559828","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2575069074","display_name":null,"funder_award_id":"62088101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2851762336","display_name":null,"funder_award_id":"62473290","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":21,"referenced_works":["https://openalex.org/W2053241734","https://openalex.org/W2091635795","https://openalex.org/W2101786389","https://openalex.org/W2135674171","https://openalex.org/W2968526727","https://openalex.org/W2991046523","https://openalex.org/W4205898562","https://openalex.org/W4360584316","https://openalex.org/W4384519332","https://openalex.org/W4385245566","https://openalex.org/W6712181171","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6741002519","https://openalex.org/W6762491519","https://openalex.org/W6762779116","https://openalex.org/W6766805167","https://openalex.org/W6775529125","https://openalex.org/W6783196708","https://openalex.org/W6804171592","https://openalex.org/W6840380725"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Cooperative":[0],"tasks":[1,10],"are":[2,64],"common":[3],"in":[4,20,59,94,166,197,204],"multi-agent":[5,123],"systems,":[6],"with":[7,66,80,213],"closely":[8,61],"cooperative":[9],"being":[11],"a":[12,18,31,39,60,120,181,198],"special":[13],"case":[14],"of":[15,23,69,137,183,224],"this,":[16],"where":[17],"change":[19,133],"the":[21,24,35,45,67,74,81,95,102,134,138,143,159,172,178,190,222],"state":[22],"environment":[25],"requires":[26,50],"multiple":[27,51],"agents":[28,52,191],"to":[29,53,87,108,132,147,157,192],"perform":[30],"specific":[32],"operation":[33],"at":[34],"same":[36],"time.":[37],"Take":[38],"box-pushing":[40,219],"task":[41,63],"as":[42],"an":[43,153],"example,":[44],"box":[46],"is":[47],"heavy":[48],"and":[49,164,207,210],"push":[54],"it":[55,99],"simultaneously.":[56],"Optimal":[57],"actions":[58,68],"cooperation":[62],"correlated":[65],"other":[70],"agents,":[71],"which":[72,85],"makes":[73,98],"individual":[75],"optimal":[76,83,90,113,149],"action":[77,174,186],"potentially":[78],"inconsistent":[79],"group":[82,148,179,185,195],"action,":[84],"leads":[86],"more":[88],"non-globally":[89],"Nash":[91],"equilibrium":[92],"policies":[93,196],"problem.":[96],"This":[97],"easier":[100],"for":[101,162],"policy":[103,140,145,160],"learned":[104,144],"by":[105],"reinforcement":[106,124],"learning":[107,125],"fall":[109],"into":[110,180],"these":[111],"locally":[112],"policies.":[114,150],"In":[115],"this":[116],"paper,":[117],"we":[118],"propose":[119,129,152],"self-organised":[121],"sequential":[122,130],"algorithm":[126],"(SOS-MARL).":[127],"We":[128,170,201],"decision-making":[131],"optimization":[135],"objective":[136],"agent's":[139],"so":[141],"that":[142],"tends":[146],"And":[151],"automatic":[154],"grouping":[155],"mechanism":[156],"make":[158],"smoother":[161],"training":[163],"reasoning":[165],"large-scale":[167],"agent":[168],"environments.":[169],"decompose":[171],"joint":[173],"value":[175],"factorization":[176],"outside":[177],"combination":[182],"each":[184],"value,":[187],"thus":[188],"guiding":[189],"improve":[193],"their":[194],"fine-grained":[199],"manner.":[200],"deployed":[202],"scenarios":[203],"both":[205],"simulated":[206],"real":[208],"environments":[209],"compared":[211],"SOS-MARL":[212],"various":[214],"classical":[215],"MARL":[216],"algorithms":[217],"on":[218],"tasks,":[220],"demonstrating":[221],"state-of-the-art":[223],"our":[225],"method.":[226]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
