{"id":"https://openalex.org/W3200610000","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534005","title":"Adaptive Advantage Estimation for Actor-Critic Algorithms","display_name":"Adaptive Advantage Estimation for Actor-Critic Algorithms","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3200610000","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534005","mag":"3200610000"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9534005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/A5041934391","display_name":"Yurou Chen","orcid":"https://orcid.org/0000-0002-0022-7219"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yurou Chen","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","The State Key Lab of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"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 Lab of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100772534","display_name":"Fengyi Zhang","orcid":"https://orcid.org/0000-0002-7485-109X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengyi Zhang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","The State Key Lab of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"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 Lab of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100434504","display_name":"Zhiyong Liu","orcid":"https://orcid.org/0000-0003-2148-1846"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Liu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","The Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, China","The State Key Lab of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"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 Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"raw_affiliation_string":"The State Key Lab of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.11982819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9871000051498413,"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/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9104999899864197,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.8882938623428345},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.772222638130188},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.7359534502029419},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6273906826972961},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5990328192710876},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5086311101913452},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4819052517414093},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.44313958287239075},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4243509769439697},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3602125346660614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.278027206659317},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22906014323234558},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.22675853967666626}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.8882938623428345},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.772222638130188},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.7359534502029419},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6273906826972961},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5990328192710876},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5086311101913452},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4819052517414093},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.44313958287239075},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4243509769439697},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3602125346660614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.278027206659317},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22906014323234558},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22675853967666626},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9534005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7209134053","display_name":null,"funder_award_id":"2017YFB1300202","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"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":49,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1520048352","https://openalex.org/W1521427077","https://openalex.org/W1646152356","https://openalex.org/W1771410628","https://openalex.org/W2089434629","https://openalex.org/W2094387729","https://openalex.org/W2100785108","https://openalex.org/W2106261932","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2127107099","https://openalex.org/W2143958939","https://openalex.org/W2144446635","https://openalex.org/W2145339207","https://openalex.org/W2152238966","https://openalex.org/W2156718681","https://openalex.org/W2156737235","https://openalex.org/W2158782408","https://openalex.org/W2257979135","https://openalex.org/W2736601468","https://openalex.org/W2783637925","https://openalex.org/W2786036274","https://openalex.org/W2787938642","https://openalex.org/W2963923407","https://openalex.org/W2964006217","https://openalex.org/W3011120880","https://openalex.org/W3046626913","https://openalex.org/W3081243957","https://openalex.org/W3093287223","https://openalex.org/W3103182070","https://openalex.org/W4214717370","https://openalex.org/W4295598622","https://openalex.org/W4297797010","https://openalex.org/W6627932998","https://openalex.org/W6630994837","https://openalex.org/W6636774829","https://openalex.org/W6638018090","https://openalex.org/W6639949747","https://openalex.org/W6675278435","https://openalex.org/W6676072908","https://openalex.org/W6683195989","https://openalex.org/W6741002519","https://openalex.org/W6748267705","https://openalex.org/W6748638692","https://openalex.org/W6748839928","https://openalex.org/W6749304979","https://openalex.org/W6766497270","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W1494268238","https://openalex.org/W154868527","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W3122602933","https://openalex.org/W2950038056","https://openalex.org/W1544940847","https://openalex.org/W4231271795","https://openalex.org/W2289285490"],"abstract_inverted_index":{"Critics":[0],"are":[1,84,96],"applied":[2],"to":[3,23,66,86,121],"estimating":[4],"policy":[5],"gradients":[6],"in":[7,70],"the":[8,44,111],"actor-critic":[9],"framework,":[10],"an":[11],"essential":[12],"part":[13],"of":[14,39,80],"Reinforcement":[15],"Learning":[16],"methods.":[17],"An":[18],"appropriate":[19],"critic":[20,38],"is":[21,64],"supposed":[22],"balance":[24],"variance":[25,41,81],"from":[26],"sample":[27,50],"returns":[28,51],"and":[29,42,52,82,103],"bias":[30,83],"introduced":[31],"by":[32],"parameterized":[33],"value":[34,53],"functions.":[35],"A":[36],"typical":[37],"balancing":[40],"bias,":[43],"generalized":[45],"advantage":[46,94,113],"estimator":[47],"(GAE),":[48],"combines":[49],"functions":[54],"with":[55,91],"a":[56,62],"fixed":[57],"weight":[58,89],"parameter.":[59],"However,":[60],"such":[61],"parameter":[63],"hard":[65],"fit,":[67],"which":[68,92],"results":[69,99],"no":[71],"promised":[72],"stability":[73],"for":[74],"GAE.":[75,122],"In":[76],"this":[77],"paper,":[78],"indicators":[79],"proposed":[85],"get":[87],"adaptive":[88,93,112],"parameters,":[90],"estimators":[95,114],"obtained.":[97],"Empirical":[98],"on":[100],"both":[101],"2D":[102],"3D":[104],"simulated":[105],"robotic":[106],"locomotion":[107],"tasks":[108],"show":[109],"that":[110],"achieve":[115],"similar":[116],"or":[117],"superior":[118],"performance":[119],"compared":[120]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}