{"id":"https://openalex.org/W3166693688","doi":"https://doi.org/10.1109/icme51207.2021.9428174","title":"Attentive Update of Multi-Critic for Deep Reinforcement Learning","display_name":"Attentive Update of Multi-Critic for Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3166693688","doi":"https://doi.org/10.1109/icme51207.2021.9428174","mag":"3166693688"},"language":"en","primary_location":{"id":"doi:10.1109/icme51207.2021.9428174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100404176","display_name":"Qing Li","orcid":"https://orcid.org/0000-0003-3370-471X"},"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":"Qing Li","raw_affiliation_strings":["University of Science and Technology of China (USTC),CAS Key Laboratory of GIPAS, EEIS Department","CAS Key Laboratory of GIPAS, EEIS Department, University of Science and Technology of China (USTC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),CAS Key Laboratory of GIPAS, EEIS Department","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"CAS Key Laboratory of GIPAS, EEIS Department, University of Science and Technology of China (USTC)","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"]},{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I4210137491","display_name":"National Science Centre","ror":"https://ror.org/03ha2q922","country_code":"PL","type":"government","lineage":["https://openalex.org/I4210137491"]}],"countries":["CN","PL"],"is_corresponding":false,"raw_author_name":"Wengang Zhou","raw_affiliation_strings":["University of Science and Technology of China (USTC),CAS Key Laboratory of GIPAS, EEIS Department","CAS Key Laboratory of GIPAS, EEIS Department, University of Science and Technology of China (USTC)","Institute of Artificial Intelligence, Hefei Comprehensive National Science Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),CAS Key Laboratory of GIPAS, EEIS Department","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"CAS Key Laboratory of GIPAS, EEIS Department, University of Science and Technology of China (USTC)","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center","institution_ids":["https://openalex.org/I4210105595","https://openalex.org/I4210137491"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101907040","display_name":"Yun Zhou","orcid":"https://orcid.org/0000-0002-2306-8986"},"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":"Yun Zhou","raw_affiliation_strings":["University of Science and Technology of China (USTC),CAS Key Laboratory of GIPAS, EEIS Department","CAS Key Laboratory of GIPAS, EEIS Department, University of Science and Technology of China (USTC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),CAS Key Laboratory of GIPAS, EEIS Department","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"CAS Key Laboratory of GIPAS, EEIS Department, University of Science and Technology of China (USTC)","institution_ids":["https://openalex.org/I126520041"]}]},{"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"]},{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I4210137491","display_name":"National Science Centre","ror":"https://ror.org/03ha2q922","country_code":"PL","type":"government","lineage":["https://openalex.org/I4210137491"]}],"countries":["CN","PL"],"is_corresponding":false,"raw_author_name":"Houqiang Li","raw_affiliation_strings":["University of Science and Technology of China (USTC),CAS Key Laboratory of GIPAS, EEIS Department","CAS Key Laboratory of GIPAS, EEIS Department, University of Science and Technology of China (USTC)","Institute of Artificial Intelligence, Hefei Comprehensive National Science Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),CAS Key Laboratory of GIPAS, EEIS Department","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"CAS Key Laboratory of GIPAS, EEIS Department, University of Science and Technology of China (USTC)","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center","institution_ids":["https://openalex.org/I4210105595","https://openalex.org/I4210137491"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9782000184059143,"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":0.9735000133514404,"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":0.8556094169616699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6574645042419434},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6376367807388306},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46873101592063904},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.46679478883743286},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4646560549736023}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8556094169616699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6574645042419434},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6376367807388306},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46873101592063904},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.46679478883743286},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4646560549736023},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme51207.2021.9428174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2119717200","https://openalex.org/W2131600418","https://openalex.org/W2201581102","https://openalex.org/W2280163991","https://openalex.org/W2620038827","https://openalex.org/W2754517384","https://openalex.org/W2766447205","https://openalex.org/W2781726626","https://openalex.org/W2786928559","https://openalex.org/W2787938642","https://openalex.org/W2798705390","https://openalex.org/W2953364219","https://openalex.org/W2963095800","https://openalex.org/W2963430540","https://openalex.org/W2963744840","https://openalex.org/W2963864421","https://openalex.org/W2982238716","https://openalex.org/W2982316857","https://openalex.org/W3009584650","https://openalex.org/W3049002444","https://openalex.org/W3172115140","https://openalex.org/W4302570325","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6695011786","https://openalex.org/W6730111887","https://openalex.org/W6735506055","https://openalex.org/W6747473740","https://openalex.org/W6748554570","https://openalex.org/W6748839928","https://openalex.org/W6767334564","https://openalex.org/W6774583691","https://openalex.org/W6780559895","https://openalex.org/W6780571964"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Unstable":[0],"training":[1,40,60],"and":[2,16,94,126,148],"inefficient":[3,48],"exploration":[4,49],"remain":[5],"challenging":[6],"problems":[7],"in":[8],"Reinforcement":[9],"Learning":[10],"(RL),":[11],"especially":[12],"when":[13],"handling":[14],"continuous":[15],"high-dimensional":[17],"state":[18],"space.":[19],"In":[20,67],"prior":[21],"works,":[22],"deep":[23],"RL":[24],"methods":[25],"based":[26],"on":[27,152],"the":[28,35,39,52,61,64,79,90,121,129,149,153,160],"ensemble":[29,75,102],"framework":[30,76],"combine":[31],"multiple":[32],"models":[33],"of":[34,54,56,84,92,107,155,162],"critics":[36,62,80,122],"to":[37,51,77,88,136],"stabilize":[38],"process.":[41],"However,":[42],"these":[43],"approaches":[44],"still":[45],"suffer":[46],"from":[47],"due":[50],"loss":[53],"diversity":[55,91],"critic":[57,74,101,135],"caused":[58],"by":[59],"with":[63,81,112,123,131,143],"same":[65],"samples.":[66],"this":[68],"paper,":[69],"we":[70],"develop":[71],"a":[72,132],"new":[73,100],"train":[78],"different":[82,144],"sets":[83],"samples,":[85,125],"so":[86],"as":[87],"maintain":[89],"critic,":[93],"therefore":[95],"explore":[96],"more":[97],"efficiently.":[98],"The":[99],"framework,":[103],"named":[104],"Attentive":[105],"Update":[106],"Multi-Critic":[108],"(AUMC),":[109],"is":[110],"compatible":[111],"various":[113],"off-policy":[114,145],"actor-critic":[115,146],"algorithms.":[116],"Specifically,":[117],"AUMC":[118,142],"attentively":[119],"trains":[120],"masked":[124],"then":[127],"updates":[128],"actor":[130],"randomly":[133],"chosen":[134],"encourage":[137],"efficient":[138],"exploration.":[139],"We":[140],"couple":[141],"algorithms,":[147],"consistent":[150],"improvements":[151],"suite":[154],"OpenAI":[156],"Gym":[157],"tasks":[158],"demonstrate":[159],"effectiveness":[161],"our":[163],"method.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}