{"id":"https://openalex.org/W4409723389","doi":"https://doi.org/10.1109/tase.2025.3563725","title":"Attention With System Entropy for Optimizing Credit Assignment in Cooperative Multi-Agent Reinforcement Learning","display_name":"Attention With System Entropy for Optimizing Credit Assignment in Cooperative Multi-Agent Reinforcement Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409723389","doi":"https://doi.org/10.1109/tase.2025.3563725"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2025.3563725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3563725","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","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/A5100323831","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0003-3747-9484"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wei","raw_affiliation_strings":["School of Mathematical Sciences, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3747-9484","affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haibin Li","orcid":"https://orcid.org/0009-0007-5555-2477"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibin Li","raw_affiliation_strings":["Institute of Artificial Intelligence, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-5555-2477","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102872631","display_name":"Shiyuan Zhou","orcid":"https://orcid.org/0000-0002-6408-8350"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyuan Zhou","raw_affiliation_strings":["School of Mathematical Sciences, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103190187","display_name":"Baifeng Li","orcid":"https://orcid.org/0000-0003-1271-701X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baifeng Li","raw_affiliation_strings":["School of Mathematical Sciences, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101501086","display_name":"Xue Liu","orcid":"https://orcid.org/0000-0002-7854-7845"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Liu","raw_affiliation_strings":["Institute of Artificial Intelligence, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7854-7845","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.8842,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.97888061,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"22","issue":null,"first_page":"14775","last_page":"14787"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11270","display_name":"Complex Systems and Time Series Analysis","score":0.4244000017642975,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11270","display_name":"Complex Systems and Time Series Analysis","score":0.4244000017642975,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12659","display_name":"Innovation Diffusion and Forecasting","score":0.42309999465942383,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.41999998688697815,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7933560609817505},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5428043603897095},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5135600566864014},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4531944990158081},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44673678278923035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39580199122428894},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.320964515209198},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.26783493161201477},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14650660753250122}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7933560609817505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5428043603897095},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5135600566864014},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4531944990158081},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44673678278923035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39580199122428894},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.320964515209198},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26783493161201477},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14650660753250122},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2025.3563725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3563725","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G199691692","display_name":null,"funder_award_id":"62276013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G437053041","display_name":null,"funder_award_id":"62050132","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8351431548","display_name":null,"funder_award_id":"62141605","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8641424965","display_name":null,"funder_award_id":"1192012","funder_id":"https://openalex.org/F4320334977","funder_display_name":"Beijing Municipal Natural Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334977","display_name":"Beijing Municipal Natural Science Foundation","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1995875735","https://openalex.org/W2145339207","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2768629321","https://openalex.org/W2968526727","https://openalex.org/W2981038142","https://openalex.org/W2982316857","https://openalex.org/W2991046523","https://openalex.org/W3008337835","https://openalex.org/W3042342701","https://openalex.org/W3111258566","https://openalex.org/W3117215073","https://openalex.org/W3156295478","https://openalex.org/W3194730353","https://openalex.org/W3196002652","https://openalex.org/W3201464020","https://openalex.org/W3204518412","https://openalex.org/W4205373550","https://openalex.org/W4226033453","https://openalex.org/W4226292595","https://openalex.org/W4289333622","https://openalex.org/W4361802167","https://openalex.org/W4385245566","https://openalex.org/W4386285856","https://openalex.org/W4391640441","https://openalex.org/W6752380930","https://openalex.org/W6754689381","https://openalex.org/W6755069753","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6762737111","https://openalex.org/W6766805167","https://openalex.org/W6767151588","https://openalex.org/W6773620346","https://openalex.org/W6775683342","https://openalex.org/W6781750019","https://openalex.org/W6849773618"],"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":{"In":[0,94],"cooperative":[1,161],"multi-agent":[2,162],"reinforcement":[3],"learning":[4,92],"(MARL),":[5],"value":[6,29,120,146],"function":[7,30,147],"factorization":[8,31,60],"methods":[9,32],"have":[10],"been":[11],"proposed":[12],"to":[13,45,50,71,85,118,140],"address":[14],"the":[15,37,51,65,79,91,104,142,151,165,171],"dimensionality":[16],"explosion":[17],"problem":[18],"encountered":[19],"in":[20,90,145],"centralized":[21],"training":[22],"and":[23,88,107,132,135,169,182,198],"decentralized":[24],"execution":[25],"(CTDE).":[26],"The":[27,184],"existing":[28],"lack":[33],"a":[34,158],"perspective":[35],"from":[36],"global":[38,133],"system":[39,105,115],"when":[40],"addressing":[41],"credit":[42,82,143],"assignment,":[43],"failing":[44],"measure":[46,117],"each":[47,126],"agent\u2019s":[48,127],"contribution":[49],"current":[52],"system.":[53],"A":[54],"typical":[55],"limitation":[56],"is":[57],"that":[58,188],"these":[59],"approaches":[61],"primarily":[62],"rely":[63],"on":[64,99,164],"proximity":[66],"of":[67,81,153,160],"local":[68,86,131],"individual":[69],"groups":[70],"assign":[72],"credit.":[73],"There":[74],"are":[75],"challenges":[76],"such":[77],"as":[78],"sensitivity":[80],"assignment":[83,144],"weights":[84],"information":[87],"instability":[89],"process.":[93],"this":[95,123],"study,":[96],"we":[97,156],"focus":[98],"redistributing":[100],"agents\u2019":[101],"features":[102],"during":[103],"evolution":[106],"suggest":[108],"employing":[109],"an":[110],"enhanced":[111],"attention":[112,139],"mechanism":[113],"with":[114,173],"entropy":[116],"factorize":[119],"function.":[121],"Specifically,":[122],"method":[124,190],"emphasizes":[125],"representation":[128],"between":[129],"their":[130],"contributions":[134],"then":[136],"redesigns":[137],"multi-head":[138],"optimize":[141],"factorization.":[148],"To":[149],"evaluate":[150],"effectiveness":[152],"our":[154,189],"method,":[155],"conduct":[157],"series":[159],"tasks":[163],"StarCraft":[166],"II":[167],"platform":[168],"compare":[170],"results":[172,186],"several":[174],"state-of-the-art":[175],"techniques,":[176],"including":[177],"Qatten,":[178],"QMIX,":[179],"QTRAN,":[180],"COMA,":[181],"VDN.":[183],"experimental":[185],"demonstrate":[187],"achieves":[191],"faster":[192],"overall":[193],"convergence":[194],"speed,":[195],"higher":[196],"stability,":[197],"robust":[199],"performance":[200],"across":[201],"various":[202],"scenarios.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
