{"id":"https://openalex.org/W3192815666","doi":"https://doi.org/10.1109/tpami.2021.3102140","title":"Structured Cooperative Reinforcement Learning With Time-Varying Composite Action Space","display_name":"Structured Cooperative Reinforcement Learning With Time-Varying Composite Action Space","publication_year":2021,"publication_date":"2021-08-04","ids":{"openalex":"https://openalex.org/W3192815666","doi":"https://doi.org/10.1109/tpami.2021.3102140","mag":"3192815666","pmid":"https://pubmed.ncbi.nlm.nih.gov/34347595"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2021.3102140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3102140","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/A5100362638","display_name":"Wenhao Li","orcid":"https://orcid.org/0000-0003-2985-1098"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Li","raw_affiliation_strings":["School of Computer Science and Technology and the MOE Key Laboratory for Advanced Theory and Application in Statistics and Data Science, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2985-1098","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology and the MOE Key Laboratory for Advanced Theory and Application in Statistics and Data Science, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101927070","display_name":"Xiangfeng Wang","orcid":"https://orcid.org/0000-0003-3064-5128"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangfeng Wang","raw_affiliation_strings":["School of Computer Science and Technology and the MOE Key Laboratory for Advanced Theory and Application in Statistics and Data Science, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3064-5128","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology and the MOE Key Laboratory for Advanced Theory and Application in Statistics and Data Science, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101748265","display_name":"Bo Jin","orcid":"https://orcid.org/0000-0003-1028-5989"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Jin","raw_affiliation_strings":["School of Computer Science and Technology and the MOE Key Laboratory for Advanced Theory and Application in Statistics and Data Science, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology and the MOE Key Laboratory for Advanced Theory and Application in Statistics and Data Science, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101186016","display_name":"Dijun Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dijun Luo","raw_affiliation_strings":["Tencent AI Lab, Tencent Inc, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Tencent Inc, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046703129","display_name":"Hongyuan Zha","orcid":"https://orcid.org/0000-0001-7493-0911"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyuan Zha","raw_affiliation_strings":["School of Data Science and AIRS, Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science and AIRS, Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5598,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.85938666,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"44","issue":"11","first_page":"8618","last_page":"8634"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9316999912261963,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7977244853973389},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6777467131614685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6472815275192261},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.601243793964386},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4952625334262848},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.42496538162231445},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3324892520904541},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3316059410572052},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2734016180038452},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1869712471961975}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7977244853973389},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6777467131614685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6472815275192261},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.601243793964386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4952625334262848},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.42496538162231445},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3324892520904541},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3316059410572052},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2734016180038452},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1869712471961975},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2021.3102140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3102140","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:34347595","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34347595","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","score":0.4300000071525574,"display_name":"Zero hunger"}],"awards":[{"id":"https://openalex.org/G2603165212","display_name":"\u9762\u5411\u5206\u5e03\u5f0f\u6700\u4f18\u5316\u95ee\u9898\u7684\u673a\u5668\u5b66\u4e60\u6c42\u89e3\u7b97\u6cd5\u7814\u7a76","funder_award_id":"12071145","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7814127966","display_name":null,"funder_award_id":"18DZ2270700","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G8036107462","display_name":null,"funder_award_id":"2020AAA0107400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8493621074","display_name":null,"funder_award_id":"20511101100","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"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":76,"referenced_works":["https://openalex.org/W26508367","https://openalex.org/W182887017","https://openalex.org/W2120968583","https://openalex.org/W2133564696","https://openalex.org/W2144366468","https://openalex.org/W2145339207","https://openalex.org/W2150120952","https://openalex.org/W2150468603","https://openalex.org/W2256420211","https://openalex.org/W2539164647","https://openalex.org/W2604645045","https://openalex.org/W2617547828","https://openalex.org/W2626637010","https://openalex.org/W2805516822","https://openalex.org/W2897417898","https://openalex.org/W2900130428","https://openalex.org/W2903006607","https://openalex.org/W2903854080","https://openalex.org/W2937206389","https://openalex.org/W2954771128","https://openalex.org/W2963257680","https://openalex.org/W2964179661","https://openalex.org/W2964261826","https://openalex.org/W2965757358","https://openalex.org/W2970710335","https://openalex.org/W2971631853","https://openalex.org/W2997326755","https://openalex.org/W2997940961","https://openalex.org/W2998367975","https://openalex.org/W2998718698","https://openalex.org/W2999371622","https://openalex.org/W2999862950","https://openalex.org/W3005937767","https://openalex.org/W3019081517","https://openalex.org/W3029584598","https://openalex.org/W3035127651","https://openalex.org/W3035399978","https://openalex.org/W4206413203","https://openalex.org/W4394672593","https://openalex.org/W6603039552","https://openalex.org/W6639949747","https://openalex.org/W6640044251","https://openalex.org/W6678214046","https://openalex.org/W6679434410","https://openalex.org/W6685951826","https://openalex.org/W6690815549","https://openalex.org/W6691861496","https://openalex.org/W6714895740","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6747473740","https://openalex.org/W6749304979","https://openalex.org/W6751511936","https://openalex.org/W6751796012","https://openalex.org/W6754843927","https://openalex.org/W6755069753","https://openalex.org/W6755133785","https://openalex.org/W6755326576","https://openalex.org/W6756851941","https://openalex.org/W6758076299","https://openalex.org/W6758641611","https://openalex.org/W6760560886","https://openalex.org/W6765178646","https://openalex.org/W6767787902","https://openalex.org/W6768539364","https://openalex.org/W6770566355","https://openalex.org/W6771179988","https://openalex.org/W6771932116","https://openalex.org/W6772852760","https://openalex.org/W6774455585","https://openalex.org/W6776449202","https://openalex.org/W6777981532","https://openalex.org/W6779547172","https://openalex.org/W6780178658","https://openalex.org/W6864350279","https://openalex.org/W6864424756"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2145836866","https://openalex.org/W2803255133","https://openalex.org/W2909431601"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"reinforcement":[3,78],"learning":[4,79],"has":[5,189],"achieved":[6],"excellent":[7],"results":[8],"in":[9,68,168,192],"low-dimensional":[10],"static":[11],"action":[12,22,71,99,148,199],"spaces":[13],"such":[14],"as":[15,101],"games":[16],"and":[17,34,65,86,109,182,194],"simple":[18],"robotics.":[19],"However,":[20],"the":[21,48,58,63,83,94,118,128,140,159,163,169,179],"space":[23,100,143],"is":[24],"usually":[25],"composite,":[26],"composed":[27],"of":[28],"multiple":[29],"sub-action":[30,142],"with":[31,97],"different":[32],"functions,":[33],"time-varying":[35,69,197],"for":[36,196],"practical":[37],"tasks.":[38],"The":[39],"existing":[40],"sub-actions":[41,53],"might":[42],"be":[43,55],"temporarily":[44],"invalid":[45],"due":[46],"to":[47,57,116,161],"external":[49],"environment,":[50],"while":[51],"unseen":[52],"can":[54],"added":[56],"current":[59],"system.":[60],"To":[61,123],"solve":[62],"robustness":[64,193],"transferability":[66,195],"problems":[67],"composite":[70,98,198],"spaces,":[72],"we":[73],"propose":[74],"a":[75,102,112,134,145],"structured":[76],"cooperative":[77,104,171],"algorithm":[80],"based":[81],"on":[82,178],"centralized":[84],"critic":[85],"decentralized":[87],"actor":[88],"framework,":[89],"called":[90],"SCORE.":[91],"We":[92,150],"model":[93],"single-agent":[95],"problem":[96,167],"fully":[103,170],"partially":[105,172],"observable":[106,173],"stochastic":[107,174],"game":[108],"further":[110],"employ":[111],"graph":[113],"attention":[114],"network":[115],"capture":[117],"dependencies":[119],"between":[120,127],"heterogeneous":[121,130,141],"sub-actions.":[122],"promote":[124],"tighter":[125],"cooperation":[126],"decomposed":[129],"agents,":[131],"SCORE":[132,160,188],"introduces":[133],"hierarchical":[135],"variational":[136],"autoencoder,":[137],"which":[138],"maps":[139],"into":[144,158],"common":[146],"latent":[147],"space.":[149,200],"also":[151],"incorporate":[152],"an":[153],"implicit":[154],"credit":[155,165],"assignment":[156,166],"structure":[157],"overcome":[162],"multi-agent":[164],"game.":[175],"Performance":[176],"experiments":[177],"proof-of-concept":[180],"task":[181,185],"precision":[183],"agriculture":[184],"show":[186],"that":[187],"significant":[190],"advantages":[191]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}