{"id":"https://openalex.org/W4296437227","doi":"https://doi.org/10.1109/tnnls.2022.3202097","title":"A Distributional Perspective on Multiagent Cooperation With Deep Reinforcement Learning","display_name":"A Distributional Perspective on Multiagent Cooperation With Deep Reinforcement Learning","publication_year":2022,"publication_date":"2022-09-19","ids":{"openalex":"https://openalex.org/W4296437227","doi":"https://doi.org/10.1109/tnnls.2022.3202097","pmid":"https://pubmed.ncbi.nlm.nih.gov/36121959"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3202097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3202097","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/A5038091112","display_name":"Liwei Huang","orcid":"https://orcid.org/0000-0002-7590-144X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["CN","MO"],"is_corresponding":true,"raw_author_name":"Liwei Huang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","State Key Laboratory of IoTSC, University of Macau, Taipa, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"State Key Laboratory of IoTSC, University of Macau, Taipa, China","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002397214","display_name":"Mingsheng Fu","orcid":"https://orcid.org/0000-0002-9257-126X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingsheng Fu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032335578","display_name":"Ananya Rao","orcid":"https://orcid.org/0000-0001-6396-8172"},"institutions":[{"id":"https://openalex.org/I4210150356","display_name":"University of Washington Tacoma","ror":"https://ror.org/05n8t2628","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210150356"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ananya Rao","raw_affiliation_strings":["School of Engineering and Technology, University of Washington, Tacoma, WA, USA"],"affiliations":[{"raw_affiliation_string":"School of Engineering and Technology, University of Washington, Tacoma, WA, USA","institution_ids":["https://openalex.org/I4210150356"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048454018","display_name":"Athirai A. Irissappane","orcid":"https://orcid.org/0000-0001-9682-3500"},"institutions":[{"id":"https://openalex.org/I4210150356","display_name":"University of Washington Tacoma","ror":"https://ror.org/05n8t2628","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210150356"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Athirai A. Irissappane","raw_affiliation_strings":["School of Engineering and Technology, University of Washington, Tacoma, WA, USA"],"affiliations":[{"raw_affiliation_string":"School of Engineering and Technology, University of Washington, Tacoma, WA, USA","institution_ids":["https://openalex.org/I4210150356"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436760","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0002-5348-7671"},"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":"Jie Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012773300","display_name":"Chengzhong Xu","orcid":"https://orcid.org/0000-0001-9480-0356"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Chengzhong Xu","raw_affiliation_strings":["State Key Laboratory of IoTSC, University of Macau, Taipa, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of IoTSC, University of Macau, Taipa, China","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5038091112"],"corresponding_institution_ids":["https://openalex.org/I150229711","https://openalex.org/I204512498"],"apc_list":null,"apc_paid":null,"fwci":0.9716,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79855371,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"35","issue":"3","first_page":"4246","last_page":"4259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9887999892234802,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9860000014305115,"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":0.7820928692817688},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.7690322995185852},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.480966717004776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4492274522781372},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3486648499965668},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.24581077694892883}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7820928692817688},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.7690322995185852},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.480966717004776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4492274522781372},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3486648499965668},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24581077694892883}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2022.3202097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3202097","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:36121959","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36121959","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/17","display_name":"Partnerships for the goals","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G1032881822","display_name":null,"funder_award_id":"0015/2019/AKP","funder_id":"https://openalex.org/F4320321655","funder_display_name":"Science and Technology Development Fund"},{"id":"https://openalex.org/G1131598070","display_name":null,"funder_award_id":"2019YFB2102100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2698479201","display_name":null,"funder_award_id":"2020M673182","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320321655","display_name":"Science and Technology Development Fund","ror":"https://ror.org/044vr6g03"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1641379095","https://openalex.org/W1977261815","https://openalex.org/W2096904991","https://openalex.org/W2099618002","https://openalex.org/W2145339207","https://openalex.org/W2145503167","https://openalex.org/W2150468603","https://openalex.org/W2166533447","https://openalex.org/W2292533394","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2765302304","https://openalex.org/W2789789879","https://openalex.org/W2793914020","https://openalex.org/W2810602713","https://openalex.org/W2898567809","https://openalex.org/W2963658727","https://openalex.org/W2982316857","https://openalex.org/W2999778183","https://openalex.org/W3099518626","https://openalex.org/W3112488842","https://openalex.org/W3115661972","https://openalex.org/W3173211893","https://openalex.org/W4241996101","https://openalex.org/W4385245566","https://openalex.org/W6675423570","https://openalex.org/W6683300800","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6749304979","https://openalex.org/W6750645735","https://openalex.org/W6751629939","https://openalex.org/W6755069753","https://openalex.org/W6758846586","https://openalex.org/W6759679099","https://openalex.org/W6762491519","https://openalex.org/W6767112054","https://openalex.org/W6767151588","https://openalex.org/W6773620346","https://openalex.org/W6779594309","https://openalex.org/W6781750019","https://openalex.org/W6783055029","https://openalex.org/W6784152626","https://openalex.org/W6791043475"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2149537132","https://openalex.org/W2138720691"],"abstract_inverted_index":{"Among":[0],"various":[1],"value":[2,23,44,109,120],"decomposition-based":[3],"multiagent":[4,14,53,93],"reinforcement":[5],"learning":[6],"(MARL)":[7],"algorithms,":[8],"the":[9,13,28,41,48,52,72,106,111,127,137,140,147,155,172,185,194,199,204],"overall":[10,128],"performance":[11],"of":[12,51,67,114,151,158,174,184],"system":[15],"is":[16,57,153],"represented":[17],"by":[18,26],"a":[19,59,83,88,97,115,119],"scalar":[20],"global":[21,37,42],"Q":[22,38,43,65,108],"and":[24,86,143,164],"optimized":[25],"minimizing":[27],"temporal":[29],"difference":[30,138],"(TD)":[31],"error":[32],"with":[33,201],"respect":[34,202],"to":[35,135,203],"that":[36,154,193],"value.":[39],"However,":[40],"cannot":[45],"accurately":[46],"model":[47,90],"distributed":[49,156],"dynamics":[50,157],"system,":[54],"since":[55],"it":[56],"only":[58],"simplified":[60],"representation":[61],"for":[62,110,146],"different":[63,75,182],"individual":[64,107],"values":[66],"agents.":[68],"To":[69,170],"explicitly":[70,162],"consider":[71],"correlations":[73],"between":[74,139],"cooperative":[76],"agents,":[77],"in":[78,102,167],"this":[79,165],"article,":[80],"we":[81,104,131,176],"propose":[82],"distributional":[84,92,99,133],"framework":[85],"construct":[87],"practical":[89],"called":[91],"cooperation":[94],"(DMAC)":[95],"from":[96],"novel":[98],"perspective.":[100],"Specifically,":[101],"DMAC,":[103,175],"view":[105],"executed":[112],"action":[113],"random":[116],"agent":[117],"as":[118],"distribution,":[121],"whose":[122],"expectation":[123],"can":[124,160,196],"further":[125],"represent":[126],"performance.":[129,169],"Then,":[130],"employ":[132],"RL":[134],"minimize":[136],"estimated":[141],"distribution":[142],"its":[144],"target":[145],"optimization.":[148],"The":[149],"advantage":[150],"DMAC":[152,195],"agents":[159],"be":[161],"modeled,":[163],"results":[166,191],"better":[168],"verify":[171],"effectiveness":[173],"conduct":[177],"extensive":[178],"experiments":[179],"under":[180],"nine":[181],"scenarios":[183],"StarCraft":[186],"Multiagent":[187],"Challenge":[188],"(SMAC).":[189],"Experimental":[190],"show":[192],"significantly":[197],"outperform":[198],"baselines":[200],"average":[205],"median":[206],"test":[207],"win":[208],"rate.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}