{"id":"https://openalex.org/W3114551027","doi":"https://doi.org/10.1109/ictai50040.2020.00068","title":"WD3: Taming the Estimation Bias in Deep Reinforcement Learning","display_name":"WD3: Taming the Estimation Bias in Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-11-01","ids":{"openalex":"https://openalex.org/W3114551027","doi":"https://doi.org/10.1109/ictai50040.2020.00068","mag":"3114551027"},"language":"en","primary_location":{"id":"doi:10.1109/ictai50040.2020.00068","doi":"https://doi.org/10.1109/ictai50040.2020.00068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictai50040.2020.00068","pdf_url":null,"source":{"id":"https://openalex.org/S4210176007","display_name":"IEEE International Conference on Tools with Artificial Intelligence (ICTAI)","issn_l":"1082-3409","issn":["1082-3409","2375-0197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.12622","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100734678","display_name":"Qiang He","orcid":"https://orcid.org/0000-0003-0014-1586","observed_orcids":["https://orcid.org/0000-0003-0014-1586"]},"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":false,"raw_author_name":"Qiang He","raw_affiliation_strings":["School of Artificial Intelligence, University of 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/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010013507","display_name":"Xinwen Hou","orcid":"https://orcid.org/0000-0002-8468-001X","observed_orcids":["https://orcid.org/0000-0002-8468-001X"]},"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/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinwen Hou","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6796,"has_fulltext":true,"cited_by_count":36,"citation_normalized_percentile":{"value":0.87905145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"391","last_page":"398"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/overestimation-bias","display_name":"overestimation bias","score":0.7649999856948853},{"id":"https://openalex.org/keywords/underestimation-bias","display_name":"underestimation bias","score":0.9110000133514404},{"id":"https://openalex.org/keywords/twin-delayed-deep-deterministic-policy-gradient","display_name":"TD3","score":0.8059999942779541},{"id":"https://openalex.org/keywords/deep-q-network","display_name":"deep Q-network","score":0.6980000138282776},{"id":"https://openalex.org/keywords/ddpg","display_name":"deep deterministic policy gradient","score":0.8450000286102295},{"id":"https://openalex.org/keywords/critic-weighting","display_name":"CRITIC weighting","score":0.7080000042915344},{"id":"https://openalex.org/keywords/continuous-control","display_name":"continuous control","score":0.7960000038146973},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.6380000114440918}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9003276824951172},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7436182498931885},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6931765079498291},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6749187707901001},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5785244703292847},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5762648582458496},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4931151568889618},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4799118936061859},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4496708810329437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4402509331703186},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2724608778953552},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20860669016838074},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","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},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ictai50040.2020.00068","doi":"https://doi.org/10.1109/ictai50040.2020.00068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictai50040.2020.00068","pdf_url":null,"source":{"id":"https://openalex.org/S4210176007","display_name":"IEEE International Conference on Tools with Artificial Intelligence (ICTAI)","issn_l":"1082-3409","issn":["1082-3409","2375-0197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2006.12622","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.12622","pdf_url":"https://arxiv.org/pdf/2006.12622","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2006.12622","doi":"https://doi.org/10.48550/arxiv.2006.12622","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.12622","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2006.12622","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.12622","pdf_url":"https://arxiv.org/pdf/2006.12622","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2926682098","display_name":null,"funder_award_id":"2017YFC1200601","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4418836096","display_name":null,"funder_award_id":"31672325","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8540295966","display_name":null,"funder_award_id":"2017YFC1200601","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3114551027.pdf","grobid_xml":"https://content.openalex.org/works/W3114551027.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1663973292","https://openalex.org/W1994616650","https://openalex.org/W2017957151","https://openalex.org/W2100677568","https://openalex.org/W2121092017","https://openalex.org/W2145339207","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2623491082","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2899806036","https://openalex.org/W2902907165","https://openalex.org/W2904246096","https://openalex.org/W2953334758","https://openalex.org/W2963267001","https://openalex.org/W2963276097","https://openalex.org/W2964121744","https://openalex.org/W2981030070","https://openalex.org/W2982316857","https://openalex.org/W2995617888","https://openalex.org/W3091471537","https://openalex.org/W4302570325"],"related_works":["https://openalex.org/W3212083176","https://openalex.org/W3000642679","https://openalex.org/W3120214316","https://openalex.org/W4388514485","https://openalex.org/W4410086950","https://openalex.org/W3199711351","https://openalex.org/W2978943496","https://openalex.org/W3109855760","https://openalex.org/W4308211465","https://openalex.org/W3122820739"],"abstract_inverted_index":{"The":[0],"overestimation":[1],"phenomenon":[2],"caused":[3],"by":[4,73],"function":[5,86],"approximation":[6],"is":[7],"a":[8,38,53,75],"well-known":[9],"issue":[10],"in":[11,112],"value-based":[12],"reinforcement":[13],"learning":[14,82],"algorithms":[15,122],"such":[16],"as":[17],"deep":[18],"Q-networks":[19],"and":[20,68,90],"DDPG,":[21,88],"which":[22,42,62,94],"could":[23,99],"lead":[24],"to":[25],"suboptimal":[26],"policies.":[27],"To":[28],"address":[29],"this":[30],"issue,":[31],"TD3":[32],"takes":[33],"the":[34,65,71,81,102,113,120],"minimum":[35],"value":[36,85,106],"between":[37,87],"pair":[39,76],"of":[40,77,84,105],"critics,":[41],"introduces":[43],"underestimation":[44],"bias.":[45],"By":[46],"unifying":[47],"these":[48],"two":[49],"opposites,":[50],"we":[51],"propose":[52],"novel":[54],"Weighted":[55],"Delayed":[56],"Deep":[57],"Deterministic":[58],"Policy":[59],"Gradient":[60],"algorithm,":[61,93],"can":[63],"reduce":[64],"estimation":[66,103],"error":[67,104],"further":[69],"improve":[70],"performance":[72],"weighting":[74],"critics.":[78],"We":[79,108],"compare":[80],"process":[83],"TD3,":[89],"our":[91,97,110],"proposed":[92],"verifies":[95],"that":[96],"algorithm":[98,111],"indeed":[100],"eliminate":[101],"function.":[107],"evaluate":[109],"OpenAI":[114],"Gym":[115],"continuous":[116],"control":[117],"tasks,":[118],"outperforming":[119],"state-of-the-art":[121],"on":[123],"every":[124],"environment":[125],"tested.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-01-05T00:00:00"}