{"id":"https://openalex.org/W4385484663","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191504","title":"TLMIX: Twin Leader Mixing Network for Cooperative Multi-Agent Reinforcement Learning","display_name":"TLMIX: Twin Leader Mixing Network for Cooperative Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385484663","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191504"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191504","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5108136474","display_name":"Yu Zhang","orcid":"https://orcid.org/0009-0001-4340-8028"},"institutions":[{"id":"https://openalex.org/I116265982","display_name":"Qinghai University","ror":"https://ror.org/05h33bt13","country_code":"CN","type":"education","lineage":["https://openalex.org/I116265982"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Qinghai University,Department of Computer Technology and Applications,Xining,China","Department of Computer Technology and Applications, Qinghai University, Xining, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qinghai University,Department of Computer Technology and Applications,Xining,China","institution_ids":["https://openalex.org/I116265982"]},{"raw_affiliation_string":"Department of Computer Technology and Applications, Qinghai University, Xining, China","institution_ids":["https://openalex.org/I116265982"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077301558","display_name":"Pengyu Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengyu Gao","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101526456","display_name":"Zhe Wu","orcid":"https://orcid.org/0000-0002-2095-0180"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhe Wu","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038088235","display_name":"Yusheng Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I116265982","display_name":"Qinghai University","ror":"https://ror.org/05h33bt13","country_code":"CN","type":"education","lineage":["https://openalex.org/I116265982"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yusheng Jiang","raw_affiliation_strings":["Qinghai University,Department of Computer Technology and Applications,Xining,China","Department of Computer Technology and Applications, Qinghai University, Xining, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qinghai University,Department of Computer Technology and Applications,Xining,China","institution_ids":["https://openalex.org/I116265982"]},{"raw_affiliation_string":"Department of Computer Technology and Applications, Qinghai University, Xining, China","institution_ids":["https://openalex.org/I116265982"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076090670","display_name":"Junliang Xing","orcid":"https://orcid.org/0000-0001-6801-0510"},"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":"Junliang Xing","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China","Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090751520","display_name":"Pin Tao","orcid":"https://orcid.org/0000-0003-2687-7997"},"institutions":[{"id":"https://openalex.org/I116265982","display_name":"Qinghai University","ror":"https://ror.org/05h33bt13","country_code":"CN","type":"education","lineage":["https://openalex.org/I116265982"]},{"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":"Pin Tao","raw_affiliation_strings":["Qinghai University,Department of Computer Technology and Applications,Xining,China","Department of Computer Science and Technology, Tsinghua University, Beijing, China","Department of Computer Technology and Applications, Qinghai University, Xining, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qinghai University,Department of Computer Technology and Applications,Xining,China","institution_ids":["https://openalex.org/I116265982"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Technology and Applications, Qinghai University, Xining, China","institution_ids":["https://openalex.org/I116265982"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9884999990463257,"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":0.9872999787330627,"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":0.8803014755249023},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7479231953620911},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7267336845397949},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5778869390487671},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4898490607738495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48527762293815613},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.47578585147857666},{"id":"https://openalex.org/keywords/mixing","display_name":"Mixing (physics)","score":0.4634229242801666},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4498696029186249},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3530833125114441}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8803014755249023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7479231953620911},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7267336845397949},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5778869390487671},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4898490607738495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48527762293815613},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.47578585147857666},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.4634229242801666},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4498696029186249},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3530833125114441},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191504","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G8078203462","display_name":null,"funder_award_id":"62076238,62222606","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2012812921","https://openalex.org/W2101934420","https://openalex.org/W2121092017","https://openalex.org/W2292533394","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2787938642","https://openalex.org/W2807741983","https://openalex.org/W2949963774","https://openalex.org/W2963658727","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2966157599","https://openalex.org/W2979284752","https://openalex.org/W2996896271","https://openalex.org/W3034363643","https://openalex.org/W3089778445","https://openalex.org/W3091970450","https://openalex.org/W3099689767","https://openalex.org/W3163926178","https://openalex.org/W3175698408","https://openalex.org/W4225725685","https://openalex.org/W4286748781","https://openalex.org/W4287755265","https://openalex.org/W4288594419","https://openalex.org/W4295598622","https://openalex.org/W4296594713","https://openalex.org/W4298857966","https://openalex.org/W4299802797","https://openalex.org/W6637967152","https://openalex.org/W6677939520","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6737849119","https://openalex.org/W6738796088","https://openalex.org/W6748839928","https://openalex.org/W6749304979","https://openalex.org/W6752380930","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6779713346","https://openalex.org/W6783196708","https://openalex.org/W6783906689","https://openalex.org/W6784152626","https://openalex.org/W6795908048","https://openalex.org/W6797064975","https://openalex.org/W6803290710","https://openalex.org/W6840380725","https://openalex.org/W6843543632"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W4384574988","https://openalex.org/W2768629321","https://openalex.org/W1914583973","https://openalex.org/W2130711276","https://openalex.org/W4308828368"],"abstract_inverted_index":{"Recent":[0],"methods":[1],"of":[2,21,152],"cooperative":[3],"multiagent":[4,39,79],"rein-forcement":[5],"learning":[6,82],"built":[7],"upon":[8],"the":[9,85,99,129,134,150,168],"individual":[10,143],"global":[11,64,105],"max":[12],"value":[13],"decomposition":[14],"principle":[15],"show":[16],"promising":[17],"results":[18,162],"using":[19],"variants":[20],"deep":[22],"mixing":[23,119],"networks,":[24],"and":[25,88,147,167,182],"credit":[26,44,48,100],"assignment":[27,45],"plays":[28],"a":[29,38,72,94,117,123],"crucial":[30],"role":[31],"in":[32,37,137],"it.":[33],"However,":[34],"each":[35,52],"agent":[36,53,112],"system":[40],"requires":[41],"not":[42],"only":[43],"but":[46],"also":[47,115],"feedback":[49,101],"which":[50,132],"tells":[51],"how":[54],"many":[55],"rewards":[56],"it":[57],"should":[58],"obtain":[59],"to":[60,97,107,121],"maximize":[61],"expected":[62],"cumulative":[63],"rewards.":[65],"In":[66],"this":[67],"work,":[68],"we":[69],"propose":[70],"TLMIX,":[71],"novel":[73],"Twin":[74],"Leader":[75],"Mixing":[76],"Network":[77],"for":[78,111],"cooperation":[80],"reinforcement":[81],"while":[83],"maintaining":[84],"centralized":[86],"training":[87],"decentralized":[89],"execution":[90],"paradigm.":[91],"TLMIX":[92,114,173],"introduces":[93,116],"leader":[95],"network":[96,120],"address":[98],"issue":[102],"by":[103,141,157],"utilizing":[104],"information":[106],"provide":[108],"reasonable":[109],"objectives":[110],"networks.":[113],"twin":[118,145],"find":[122],"more":[124],"accurate":[125],"target":[126],"function":[127],"from":[128],"Q-value":[130],"functions,":[131],"avoids":[133],"rapid":[135],"increase":[136],"parameter":[138],"scale":[139],"caused":[140,156],"introducing":[142],"agents'":[144],"networks":[146],"effectively":[148],"mitigates":[149],"accumulation":[151],"high":[153],"overestimation":[154],"errors":[155],"temporal":[158],"difference":[159],"updates.":[160],"Extensive":[161],"on":[163,179],"SMAC":[164],"experimental":[165],"scenarios":[166],"Predator-Prey":[169],"environment":[170],"demonstrate":[171],"that":[172],"significantly":[174],"outperforms":[175],"comparable":[176],"benchmark":[177],"algorithms":[178],"convergence":[180],"speed":[181],"performance.":[183]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}