{"id":"https://openalex.org/W2740912559","doi":"https://doi.org/10.24963/ijcai.2017/483","title":"Weighted Double Q-learning","display_name":"Weighted Double Q-learning","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2740912559","doi":"https://doi.org/10.24963/ijcai.2017/483","mag":"2740912559"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/483","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/483","pdf_url":"https://www.ijcai.org/proceedings/2017/0483.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0483.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035138959","display_name":"Zongzhang Zhang","orcid":"https://orcid.org/0000-0002-9238-4747"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zongzhang Zhang","raw_affiliation_strings":["Soochow University","Soochow University Suzhou, Jiangsu 215006 China"],"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]},{"raw_affiliation_string":"Soochow University Suzhou, Jiangsu 215006 China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021091060","display_name":"Zhiyuan Pan","orcid":"https://orcid.org/0000-0001-6035-1070"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Pan","raw_affiliation_strings":["Soochow University","Soochow University Suzhou, Jiangsu 215006 China"],"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]},{"raw_affiliation_string":"Soochow University Suzhou, Jiangsu 215006 China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068326377","display_name":"Mykel J. Kochenderfer","orcid":"https://orcid.org/0000-0002-7238-9663"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mykel J. Kochenderfer","raw_affiliation_strings":["Stanford University","Stanford University Stanford, CA 94305 USA"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford, CA 94305 USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5035138959"],"corresponding_institution_ids":["https://openalex.org/I3923682"],"apc_list":null,"apc_paid":null,"fwci":4.5732,"has_fulltext":false,"cited_by_count":84,"citation_normalized_percentile":{"value":0.95670425,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3455","last_page":"3461"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9950000047683716,"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":0.9950000047683716,"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":0.9939000010490417,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9711999893188477,"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/estimator","display_name":"Estimator","score":0.8862261772155762},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6854419708251953},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5500065088272095},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4969659149646759},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4318726658821106},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.42516767978668213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40762075781822205},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.38688674569129944},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37427443265914917},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3723781704902649},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24985259771347046},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.23836246132850647}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.8862261772155762},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6854419708251953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5500065088272095},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4969659149646759},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4318726658821106},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.42516767978668213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40762075781822205},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38688674569129944},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37427443265914917},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3723781704902649},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24985259771347046},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.23836246132850647},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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:10.24963/ijcai.2017/483","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/483","pdf_url":"https://www.ijcai.org/proceedings/2017/0483.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/483","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/483","pdf_url":"https://www.ijcai.org/proceedings/2017/0483.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5794123271","display_name":null,"funder_award_id":"61502323","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740912559.pdf","grobid_xml":"https://content.openalex.org/works/W2740912559.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1589747210","https://openalex.org/W2093253120","https://openalex.org/W2098432798","https://openalex.org/W2115211925","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2122701159","https://openalex.org/W2129670787","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2161966552","https://openalex.org/W2276463593","https://openalex.org/W2341171179","https://openalex.org/W2469051754","https://openalex.org/W2545546008","https://openalex.org/W2746553466","https://openalex.org/W2760506156","https://openalex.org/W2919115771","https://openalex.org/W3011120880","https://openalex.org/W4214717370","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W3087814763","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W4212921133"],"abstract_inverted_index":{"Q-learning":[0,52,89,101],"is":[1,21,104,137],"a":[2,27,98],"popular":[3],"reinforcement":[4],"learning":[5],"algorithm,":[6,102],"but":[7],"it":[8],"can":[9],"perform":[10,140],"poorly":[11],"in":[12,48,122,129],"stochastic":[13],"environments":[14],"due":[15,22],"to":[16,23,139],"overestimating":[17],"action":[18,34,43,78,93],"values.":[19,94],"Overestimation":[20],"the":[24,32,40,50,59,76,80,83,92,107,110,115,120,123,127,130,134],"use":[25],"of":[26,70,85,109,117],"single":[28,124],"estimator":[29,61,74,125],"that":[30],"uses":[31,58,64],"maximum":[33,41],"value":[35],"as":[36],"an":[37],"approximation":[38],"for":[39],"expected":[42],"value.":[44,87],"To":[45],"avoid":[46],"overestimation":[47,121],"Q-learning,":[49],"double":[51,60,100,112,131],"algorithm":[53,136],"was":[54],"recently":[55],"proposed,":[56],"which":[57,103],"method.":[62],"It":[63],"two":[65],"estimators":[66],"from":[67],"independent":[68],"sets":[69],"experiences,":[71],"with":[72,114],"one":[73],"determining":[75],"maximizing":[77],"and":[79,126],"other":[81],"providing":[82],"estimate":[84],"its":[86],"Double":[88],"sometimes":[90],"underestimates":[91],"This":[95],"paper":[96],"introduces":[97],"weighted":[99,111],"based":[105],"on":[106,142],"construction":[108],"estimator,":[113],"goal":[116],"balancing":[118],"between":[119],"underestimation":[128],"estimator.":[132],"Empirically,":[133],"new":[135],"shown":[138],"well":[141],"several":[143],"MDP":[144],"problems.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}