{"id":"https://openalex.org/W4388470074","doi":"https://doi.org/10.1109/tnnls.2023.3326744","title":"Celebrating Diversity With Subtask Specialization in Shared Multiagent Reinforcement Learning","display_name":"Celebrating Diversity With Subtask Specialization in Shared Multiagent Reinforcement Learning","publication_year":2023,"publication_date":"2023-11-07","ids":{"openalex":"https://openalex.org/W4388470074","doi":"https://doi.org/10.1109/tnnls.2023.3326744","pmid":"https://pubmed.ncbi.nlm.nih.gov/37934639"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3326744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3326744","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/A5031844582","display_name":"Chenghao Li","orcid":"https://orcid.org/0000-0002-6650-9673"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenghao Li","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071784141","display_name":"Tonghan Wang","orcid":"https://orcid.org/0000-0002-7703-6074"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tonghan Wang","raw_affiliation_strings":["Harvard University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101980621","display_name":"Chengjie Wu","orcid":"https://orcid.org/0000-0002-2145-8868"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengjie Wu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014109600","display_name":"Qianchuan Zhao","orcid":"https://orcid.org/0000-0002-7952-5621"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianchuan Zhao","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101912623","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0002-9386-5825"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010176958","display_name":"Chongjie Zhang","orcid":"https://orcid.org/0000-0001-8068-0162"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chongjie Zhang","raw_affiliation_strings":["Washington University in St. Louis, St. Louis, MO, USA"],"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis, St. Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5031844582"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.5289,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7274975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"36","issue":"2","first_page":"2051","last_page":"2065"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9868000149726868,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9824000000953674,"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/interpretability","display_name":"Interpretability","score":0.856022834777832},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7636466026306152},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7219109535217285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5949783325195312},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5904361009597778},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.5270959138870239},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.509477436542511},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4311942458152771},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3233780264854431},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3204473853111267}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.856022834777832},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7636466026306152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7219109535217285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5949783325195312},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5904361009597778},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.5270959138870239},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.509477436542511},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4311942458152771},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3233780264854431},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3204473853111267},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3326744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3326744","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:37934639","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37934639","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","score":0.46000000834465027,"display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G184828240","display_name":null,"funder_award_id":"62192751","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2265996673","display_name":null,"funder_award_id":"U1813216","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4254987650","display_name":null,"funder_award_id":"2017YFC0704100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5983507987","display_name":null,"funder_award_id":"2016YFB0901900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1592847719","https://openalex.org/W1641379095","https://openalex.org/W2109910161","https://openalex.org/W2120340025","https://openalex.org/W2404646363","https://openalex.org/W2588790649","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2954360742","https://openalex.org/W2963134677","https://openalex.org/W2963523627","https://openalex.org/W2964067469","https://openalex.org/W2997070234","https://openalex.org/W2997502221","https://openalex.org/W3034646721","https://openalex.org/W3037148280","https://openalex.org/W3037620198","https://openalex.org/W3091970450","https://openalex.org/W3099689767","https://openalex.org/W3114980465","https://openalex.org/W3122177264","https://openalex.org/W3170118067","https://openalex.org/W3210169707","https://openalex.org/W4214913711","https://openalex.org/W4286748781","https://openalex.org/W4287867830","https://openalex.org/W4288594419","https://openalex.org/W6677834374","https://openalex.org/W6680096503","https://openalex.org/W6703271639","https://openalex.org/W6738796088","https://openalex.org/W6740801417","https://openalex.org/W6748603076","https://openalex.org/W6749304979","https://openalex.org/W6752380930","https://openalex.org/W6756303580","https://openalex.org/W6757784512","https://openalex.org/W6758507868","https://openalex.org/W6758846586","https://openalex.org/W6761754428","https://openalex.org/W6762491519","https://openalex.org/W6762492177","https://openalex.org/W6764724164","https://openalex.org/W6765044274","https://openalex.org/W6767089667","https://openalex.org/W6767327128","https://openalex.org/W6767649332","https://openalex.org/W6769462197","https://openalex.org/W6771235960","https://openalex.org/W6771807793","https://openalex.org/W6773447848","https://openalex.org/W6775522024","https://openalex.org/W6775529125","https://openalex.org/W6779101081","https://openalex.org/W6779728822","https://openalex.org/W6779911164","https://openalex.org/W6780191816","https://openalex.org/W6781750019","https://openalex.org/W6783196708","https://openalex.org/W6783906689","https://openalex.org/W6784152626","https://openalex.org/W6787376135","https://openalex.org/W6787618087","https://openalex.org/W6788646031","https://openalex.org/W6790486821","https://openalex.org/W6790747386","https://openalex.org/W6791079441","https://openalex.org/W6797584944","https://openalex.org/W6797805403"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W4388685194","https://openalex.org/W4312407344","https://openalex.org/W2894289927"],"abstract_inverted_index":{"Subtask":[0],"decomposition":[1],"offers":[2],"a":[3,38],"promising":[4],"approach":[5,40],"for":[6,44],"achieving":[7],"and":[8,29,73,86],"comprehending":[9],"complex":[10],"cooperative":[11],"behaviors":[12],"in":[13,70,94],"multiagent":[14],"systems.":[15],"Nonetheless,":[16],"existing":[17],"methods":[18],"often":[19],"depend":[20],"on":[21],"intricate":[22],"high-level":[23],"strategies,":[24],"which":[25],"can":[26],"hinder":[27],"interpretability":[28],"learning":[30],"efficiency.":[31],"To":[32],"tackle":[33],"these":[34],"challenges,":[35],"we":[36,67],"propose":[37],"novel":[39],"that":[41],"specializes":[42],"subtasks":[43],"subgroups":[45],"by":[46],"employing":[47],"diverse":[48],"observation":[49],"representation":[50],"encoders":[51],"within":[52],"information":[53],"bottlenecks.":[54],"Moreover,":[55],"to":[56,82],"enhance":[57],"the":[58],"efficiency":[59],"of":[60],"subtask":[61,89],"specialization":[62],"while":[63],"promoting":[64],"sophisticated":[65],"cooperation,":[66],"introduce":[68],"diversity":[69],"both":[71],"optimization":[72],"neural":[74],"network":[75],"architectures.":[76],"These":[77],"advancements":[78],"enable":[79],"our":[80],"method":[81],"achieve":[83],"state-of-the-art":[84],"performance":[85],"offer":[87],"interpretable":[88],"factorization":[90],"across":[91],"various":[92],"scenarios":[93],"Google":[95],"Research":[96],"Football":[97],"(GRF).":[98]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}