{"id":"https://openalex.org/W4225665995","doi":"https://doi.org/10.1109/tg.2022.3232390","title":"CTDS: Centralized Teacher With Decentralized Student for Multiagent Reinforcement Learning","display_name":"CTDS: Centralized Teacher With Decentralized Student for Multiagent Reinforcement Learning","publication_year":2022,"publication_date":"2022-12-27","ids":{"openalex":"https://openalex.org/W4225665995","doi":"https://doi.org/10.1109/tg.2022.3232390"},"language":"en","primary_location":{"id":"doi:10.1109/tg.2022.3232390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2022.3232390","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"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 Games","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/A5046073205","display_name":"Jian Zhao","orcid":"https://orcid.org/0000-0003-4895-990X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jian Zhao","raw_affiliation_strings":["CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044832538","display_name":"Xunhan Hu","orcid":"https://orcid.org/0000-0003-0239-3541"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunhan Hu","raw_affiliation_strings":["CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101849390","display_name":"Mingyu Yang","orcid":"https://orcid.org/0000-0002-6077-6711"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyu Yang","raw_affiliation_strings":["CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046805800","display_name":"Wengang Zhou","orcid":"https://orcid.org/0000-0003-1690-9836"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wengang Zhou","raw_affiliation_strings":["CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102713772","display_name":"Jiangcheng Zhu","orcid":"https://orcid.org/0000-0002-6610-721X"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangcheng Zhu","raw_affiliation_strings":["Huawei Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078141810","display_name":"Houqiang Li","orcid":"https://orcid.org/0000-0003-2188-3028"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houqiang Li","raw_affiliation_strings":["CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5046073205"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":3.5853,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.93588427,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"16","issue":"1","first_page":"140","last_page":"150"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6414765119552612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.633547306060791},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5993765592575073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.535230815410614},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.5079126954078674},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44504639506340027},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34029316902160645},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15449118614196777},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14403054118156433}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6414765119552612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.633547306060791},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5993765592575073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.535230815410614},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.5079126954078674},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44504639506340027},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34029316902160645},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15449118614196777},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14403054118156433},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tg.2022.3232390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2022.3232390","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"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 Games","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2262853887","display_name":null,"funder_award_id":"61836011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6308808780","display_name":null,"funder_award_id":"62021001","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":52,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2012812921","https://openalex.org/W2099618002","https://openalex.org/W2166533447","https://openalex.org/W2292533394","https://openalex.org/W2404646363","https://openalex.org/W2588790649","https://openalex.org/W2617547828","https://openalex.org/W2626637010","https://openalex.org/W2739879705","https://openalex.org/W2747213132","https://openalex.org/W2756196406","https://openalex.org/W2897611955","https://openalex.org/W2963736842","https://openalex.org/W2973721503","https://openalex.org/W2981038142","https://openalex.org/W2996037775","https://openalex.org/W2996896271","https://openalex.org/W2997006708","https://openalex.org/W2997502221","https://openalex.org/W3004640943","https://openalex.org/W3099689767","https://openalex.org/W3138971305","https://openalex.org/W3178094535","https://openalex.org/W3192815666","https://openalex.org/W3200878391","https://openalex.org/W4281622133","https://openalex.org/W4286748781","https://openalex.org/W4288594419","https://openalex.org/W4299802797","https://openalex.org/W4389473504","https://openalex.org/W6638523607","https://openalex.org/W6712181171","https://openalex.org/W6713411898","https://openalex.org/W6732837357","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6743188669","https://openalex.org/W6744537943","https://openalex.org/W6749304979","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6762811270","https://openalex.org/W6767327128","https://openalex.org/W6773620346","https://openalex.org/W6781750019","https://openalex.org/W6784152626","https://openalex.org/W6787618087","https://openalex.org/W6799518687","https://openalex.org/W6838682728","https://openalex.org/W6840380725","https://openalex.org/W6846392434"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2967463586","https://openalex.org/W2074679142","https://openalex.org/W2765830098","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W3157641275","https://openalex.org/W4312300846","https://openalex.org/W2104042711","https://openalex.org/W4206221578"],"abstract_inverted_index":{"Due":[0],"to":[1,37,129,171,178,196],"the":[2,25,39,42,50,103,107,122,126,131,138,146,155,198,204,210],"partial":[3,127],"observability":[4],"and":[5,98,154,203],"communication":[6],"constraints":[7],"in":[8,73],"many":[9],"multiagent":[10],"reinforcement":[11],"learning":[12,38,51,111],"(MARL)":[13],"tasks,":[14],"centralized":[15,33],"training":[16,153],"with":[17,45,86],"decentralized":[18,158],"execution":[19,159],"(CTDE)":[20],"has":[21],"become":[22],"one":[23],"of":[24,41,52,67,94,149,157,189,200],"most":[26],"widely":[27],"used":[28],"MARL":[29,213],"paradigms.":[30],"In":[31,141],"CTDE,":[32],"information":[34],"is":[35,58,166,169],"dedicated":[36],"allocation":[40],"team":[43,108],"reward":[44,109],"a":[46,82,87,95,99,186],"mixing":[47],"network":[48],"while":[49,121],"individual":[53,112],"<italic":[54,113,132,190],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[55,114,133,191],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Q</i>":[56,115,134],"-values":[57,116,135],"usually":[59],"based":[60],"on":[61,118,185],"local":[62],"observations.":[63],"The":[64],"insufficient":[65],"utility":[66],"global":[68,119,150],"observation":[69,120,151],"will":[70],"degrade":[71],"performance":[72],"challenging":[74,187],"environments.":[75],"To":[76],"this":[77,79,142],"end,":[78],"work":[80],"proposes":[81],"novel":[83],"Centralized":[84],"Teacher":[85],"Decentralized":[88],"Student":[89],"(CTDS)":[90],"framework,":[91],"which":[92,168],"consists":[93],"teacher":[96,104,139],"model":[97,105,124],"student":[100,123],"model.":[101,140],"Specifically,":[102],"allocates":[106],"by":[110,137],"conditioned":[117],"utilizes":[125],"observations":[128],"approximate":[130],"estimated":[136],"way,":[143],"CTDS":[144,164,208],"balances":[145],"full":[147],"utilization":[148],"during":[152],"feasibility":[156],"for":[160],"online":[161],"inference.":[162],"Our":[163],"framework":[165],"generic,":[167],"ready":[170],"be":[172],"applied":[173],"upon":[174],"existing":[175,211],"CTDE":[176],"methods":[177],"boost":[179],"their":[180],"performance.":[181],"We":[182],"conduct":[183],"experiments":[184],"set":[188],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">StarCraft":[192],"II</i>":[193],"micromanagement":[194],"tasks":[195],"test":[197],"effectiveness":[199],"our":[201],"method":[202],"results":[205],"show":[206],"that":[207],"outperforms":[209],"value-based":[212],"methods.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
