{"id":"https://openalex.org/W2093253120","doi":"https://doi.org/10.1109/adprl.2013.6614994","title":"Bias-corrected Q-learning to control max-operator bias in Q-learning","display_name":"Bias-corrected Q-learning to control max-operator bias in Q-learning","publication_year":2013,"publication_date":"2013-04-01","ids":{"openalex":"https://openalex.org/W2093253120","doi":"https://doi.org/10.1109/adprl.2013.6614994","mag":"2093253120"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2013.6614994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2013.6614994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","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/A5100348868","display_name":"Donghun Lee","orcid":"https://orcid.org/0000-0002-7941-2395"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Donghun Lee","raw_affiliation_strings":["Department of Computer Science, Princeton University, Princeton, NJ, USA","Department of Computer Science, Princeton University, Princeton , NJ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Department of Computer Science, Princeton University, Princeton , NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064859854","display_name":"Boris Defourny","orcid":"https://orcid.org/0000-0003-0405-5538"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Defourny","raw_affiliation_strings":["Operations Research and Financial Engineering, Princeton University, Princeton, NJ, USA","Oper. Res. & Financial Eng., Princeton Univ., Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Operations Research and Financial Engineering, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Oper. Res. & Financial Eng., Princeton Univ., Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054833334","display_name":"Warren B. Powell","orcid":"https://orcid.org/0000-0002-4364-7555"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Warren B. Powell","raw_affiliation_strings":["Operations Research and Financial Engineering, Princeton University, Princeton, NJ, USA","Oper. Res. & Financial Eng., Princeton Univ., Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Operations Research and Financial Engineering, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Oper. Res. & Financial Eng., Princeton Univ., Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100348868"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":0.9618,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.82634171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"93","last_page":"99"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9958999752998352,"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/operator","display_name":"Operator (biology)","score":0.6732140779495239},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5442032217979431},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5421314239501953},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4037640690803528},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3980492353439331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32429391145706177},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.2839452028274536}],"concepts":[{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.6732140779495239},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5442032217979431},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5421314239501953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4037640690803528},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3980492353439331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32429391145706177},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2839452028274536},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/adprl.2013.6614994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2013.6614994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W170196830","https://openalex.org/W1550698229","https://openalex.org/W1579312135","https://openalex.org/W1581367540","https://openalex.org/W1625390266","https://openalex.org/W1826343992","https://openalex.org/W1977357978","https://openalex.org/W2056740053","https://openalex.org/W2071983464","https://openalex.org/W2083205357","https://openalex.org/W2115192345","https://openalex.org/W2115211925","https://openalex.org/W2118686230","https://openalex.org/W2122701159","https://openalex.org/W2124839177","https://openalex.org/W2150147323","https://openalex.org/W2156828234","https://openalex.org/W2165131254","https://openalex.org/W2168405694","https://openalex.org/W2276463593","https://openalex.org/W2791590751","https://openalex.org/W3009585715","https://openalex.org/W3011120880","https://openalex.org/W4233696721","https://openalex.org/W4245296547","https://openalex.org/W4321428174","https://openalex.org/W6607005992","https://openalex.org/W6636578284","https://openalex.org/W6678494045","https://openalex.org/W6682198394","https://openalex.org/W6694514460"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2051487156","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027","https://openalex.org/W2962838298"],"abstract_inverted_index":{"We":[0,48,76],"identify":[1],"a":[2,50,85],"class":[3],"of":[4,20,32,46],"stochastic":[5],"control":[6],"problems":[7],"with":[8,54,87],"highly":[9,88],"random":[10,89],"rewards":[11,90],"and":[12,62,93],"high":[13,18],"discount":[14],"factor":[15],"which":[16,37],"induce":[17,39],"levels":[19,31],"statistical":[21],"error":[22],"in":[23,35,84],"the":[24,40,59,65,70,99],"estimated":[25],"action-value":[26],"function.":[27],"This":[28],"produces":[29],"significant":[30],"max-operator":[33,60,100],"bias":[34],"Q-learning,":[36],"can":[38],"algorithm":[41,53,66],"to":[42,69],"diverge":[43],"for":[44],"millions":[45],"iterations.":[47],"present":[49],"bias-corrected":[51,80],"Q-learning":[52,74,81,92],"asymptotically":[55,67],"unbiased":[56],"resistance":[57],"against":[58],"bias,":[61],"show":[63,77],"that":[64,79],"converges":[68],"optimal":[71],"policy,":[72],"as":[73],"does.":[75],"experimentally":[78],"performs":[82],"well":[83],"domain":[86],"where":[91],"other":[94],"related":[95],"algorithms":[96],"suffer":[97],"from":[98],"bias.":[101]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}