{"id":"https://openalex.org/W2978943496","doi":"https://doi.org/10.1109/ijcnn.2019.8852397","title":"Mixing Update Q-value for Deep Reinforcement Learning","display_name":"Mixing Update Q-value for Deep Reinforcement Learning","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2978943496","doi":"https://doi.org/10.1109/ijcnn.2019.8852397","mag":"2978943496"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8852397","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852397","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","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/A5027959882","display_name":"Zhunan Li","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhunan Li","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010013507","display_name":"Xinwen Hou","orcid":"https://orcid.org/0000-0002-8468-001X"},"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/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":"Xinwen Hou","raw_affiliation_strings":["Center for Research on Intelligent System and Engineering, Institute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Center for Research on Intelligent System and Engineering, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027959882"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.5601,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.75411161,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9883000254631042,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9462000131607056,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8743405342102051},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6576614379882812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6412135362625122},{"id":"https://openalex.org/keywords/mixing","display_name":"Mixing (physics)","score":0.6001865267753601},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.5971032381057739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5188276171684265},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.48250365257263184},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.47625160217285156},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41115912795066833},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2615259289741516},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24074479937553406},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10336676239967346}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8743405342102051},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6576614379882812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6412135362625122},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.6001865267753601},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.5971032381057739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5188276171684265},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.48250365257263184},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.47625160217285156},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41115912795066833},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2615259289741516},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24074479937553406},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10336676239967346},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2019.8852397","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852397","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W51508254","https://openalex.org/W1522301498","https://openalex.org/W1757796397","https://openalex.org/W2017957151","https://openalex.org/W2100677568","https://openalex.org/W2115211925","https://openalex.org/W2121863487","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2746553466","https://openalex.org/W2787938642","https://openalex.org/W2963864421","https://openalex.org/W2963923407","https://openalex.org/W2964121744","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W4298857966","https://openalex.org/W4302570325","https://openalex.org/W6602057636","https://openalex.org/W6631190155","https://openalex.org/W6637967152","https://openalex.org/W6677067356","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6748839928","https://openalex.org/W6775686901","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W1998888747","https://openalex.org/W3087814763","https://openalex.org/W2892507673","https://openalex.org/W2361647908","https://openalex.org/W2937181779"],"abstract_inverted_index":{"The":[0],"value-based":[1],"reinforcement":[2],"learning":[3],"methods":[4],"are":[5],"known":[6],"to":[7,18,37,70,80,109],"overestimate":[8],"action":[9,57],"values":[10],"such":[11],"as":[12,102],"deep":[13],"Q-learning,":[14,53],"which":[15],"could":[16],"lead":[17],"suboptimal":[19],"policies.":[20],"This":[21],"problem":[22],"also":[23,107],"persists":[24],"in":[25],"an":[26],"actor-critic":[27],"algorithm.":[28],"In":[29],"this":[30,106],"paper,":[31],"we":[32],"propose":[33,76],"a":[34,66,77],"novel":[35],"mechanism":[36,49],"minimize":[38],"its":[39],"effects":[40],"on":[41,51,60,113],"both":[42],"the":[43,46,61,72,81,93,99],"critic":[44],"and":[45,63,90],"actor.":[47],"Our":[48],"builds":[50],"Double":[52],"by":[54],"mixing":[55],"update":[56],"value":[58],"based":[59],"minimum":[62],"maximum":[64],"between":[65],"pair":[67],"of":[68],"critics":[69],"limit":[71],"overestimation.":[73],"We":[74],"then":[75],"specific":[78],"adaptation":[79],"Twin":[82],"Delayed":[83],"Deep":[84],"Deterministic":[85],"policy":[86],"gradient":[87],"algorithm":[88,95],"(TD3)":[89],"show":[91],"that":[92,105],"resulting":[94],"not":[96],"only":[97],"reduces":[98],"observed":[100],"overestimations,":[101],"hypothesized,":[103],"but":[104],"leads":[108],"much":[110],"better":[111],"performance":[112],"several":[114],"tasks.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}