{"id":"https://openalex.org/W4296512951","doi":"https://doi.org/10.1109/cog51982.2022.9893619","title":"LILAC: Learning a Leader for Cooperative Reinforcement Learning","display_name":"LILAC: Learning a Leader for Cooperative Reinforcement Learning","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4296512951","doi":"https://doi.org/10.1109/cog51982.2022.9893619"},"language":"en","primary_location":{"id":"doi:10.1109/cog51982.2022.9893619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Games (CoG)","raw_type":"proceedings-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/A5103161416","display_name":"Yuqian Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuqian Fu","raw_affiliation_strings":["The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences,Beijing,China","Electronic Information School, Wuhan University, Wuhan, China","The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210094879"]},{"raw_affiliation_string":"Electronic Information School, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073383645","display_name":"Jiajun Chai","orcid":"https://orcid.org/0000-0002-7611-064X"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Chai","raw_affiliation_strings":["The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences,Beijing,China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210094879"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080193690","display_name":"Yuanheng Zhu","orcid":"https://orcid.org/0000-0001-5384-423X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanheng Zhu","raw_affiliation_strings":["The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences,Beijing,China","The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210094879"]},{"raw_affiliation_string":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences,Beijing,China","The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210094879"]},{"raw_affiliation_string":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103161416"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I37461747","https://openalex.org/I4210094879"],"apc_list":null,"apc_paid":null,"fwci":0.3977,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66939548,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"325","issue":null,"first_page":"49","last_page":"55"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.941100001335144,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.8531143665313721},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7062107920646667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5595081448554993},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49991798400878906},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.479907363653183},{"id":"https://openalex.org/keywords/lilac","display_name":"lilac","score":0.4767269194126129},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36208829283714294},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10569792985916138}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8531143665313721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7062107920646667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5595081448554993},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49991798400878906},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.479907363653183},{"id":"https://openalex.org/C2780113379","wikidata":"https://www.wikidata.org/wiki/Q6565319","display_name":"lilac","level":2,"score":0.4767269194126129},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36208829283714294},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10569792985916138},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cog51982.2022.9893619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.5,"id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2100836571","https://openalex.org/W2145339207","https://openalex.org/W2157331557","https://openalex.org/W2604279009","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2807741983","https://openalex.org/W2911917164","https://openalex.org/W2949963774","https://openalex.org/W2991046523","https://openalex.org/W3033770108","https://openalex.org/W3034971464","https://openalex.org/W3042185737","https://openalex.org/W3046288222","https://openalex.org/W3084241738","https://openalex.org/W3089778445","https://openalex.org/W3091147964","https://openalex.org/W3196869853","https://openalex.org/W3210169707","https://openalex.org/W4205272462","https://openalex.org/W4226170924","https://openalex.org/W4287755265","https://openalex.org/W4288091739","https://openalex.org/W4295598622","https://openalex.org/W4299802797","https://openalex.org/W6738796088","https://openalex.org/W6749304979","https://openalex.org/W6752380930","https://openalex.org/W6762491519","https://openalex.org/W6767327128","https://openalex.org/W6771274123","https://openalex.org/W6775529125","https://openalex.org/W6781750019","https://openalex.org/W6783196708","https://openalex.org/W6784152626"],"related_works":["https://openalex.org/W2952861336","https://openalex.org/W2614173027","https://openalex.org/W2375379617","https://openalex.org/W4392553150","https://openalex.org/W4247618586","https://openalex.org/W2361499598","https://openalex.org/W4230960514","https://openalex.org/W4312940119","https://openalex.org/W2806266150","https://openalex.org/W4312632707"],"abstract_inverted_index":{"In":[0,108],"cooperative":[1,106],"multi-agent":[2],"reinforcement":[3,57],"learning,role-based":[4],"learning":[5,11,58],"promises":[6],"to":[7,64,67,89,97,101,110,128,148,153],"reach":[8],"satisfactory":[9],"policy":[10],"through":[12],"the":[13,28,76,81,112,130,164,169],"decomposition":[14],"of":[15,27,34,75,114,156,163],"complicated":[16],"tasks":[17],"using":[18],"roles.":[19,69,160],"Different":[20],"roles":[21,35,100],"are":[22,144],"responsible":[23],"for":[24,55,158],"different":[25,102,159],"aspects":[26],"task.":[29],"However,":[30],"how":[31],"this":[32,45],"group":[33],"can":[36],"be":[37],"quickly":[38],"identified":[39],"is":[40,126],"not":[41],"clear.":[42],"To":[43],"address":[44],"problem,":[46],"we":[47],"propose":[48],"a":[49,53,62,72,85,117],"novel":[50],"framework,":[51],"LearnIng":[52],"LeAder":[54],"Cooperative":[56],"(LILAC),":[59],"which":[60],"introduces":[61],"leader":[63,165],"integrate":[65],"information":[66,83],"assign":[68,98],"Leaders":[70],"take":[71],"broad":[73],"view":[74],"whole":[77],"task":[78],"and":[79,104,140,152],"feed":[80],"integrated":[82],"into":[84],"Gaussian":[86],"mixture":[87],"model":[88],"sample":[90],"role":[91],"embedding":[92],"distribution.":[93],"It":[94],"enables":[95],"LILAC":[96,147,167],"appropriate":[99],"agents":[103],"improves":[105],"performance.":[107],"order":[109],"evaluate":[111],"cooperation":[113],"multiple":[115],"agents,":[116],"mixing":[118],"network,":[119],"inputted":[120],"by":[121,146],"individual":[122],"local":[123],"utility":[124],"networks,":[125],"constructed":[127],"estimate":[129],"global":[131],"action":[132],"value.":[133],"Two":[134],"loss":[135,139],"functions,":[136],"temporal":[137],"difference":[138],"mean":[141],"divergence":[142],"loss,":[143],"adopted":[145],"learn":[149],"network":[150],"parameters":[151],"encourage":[154],"diversity":[155],"policies":[157],"By":[161],"virtue":[162],"module,":[166],"outperforms":[168],"StarCraft":[170],"II":[171],"micromanagement":[172],"benchmark":[173],"in":[174],"our":[175],"experiments,":[176],"especially":[177],"on":[178],"challenging":[179],"tasks.":[180]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}