{"id":"https://openalex.org/W3009660502","doi":"https://doi.org/10.1109/access.2020.2977400","title":"Risk Aversion Operator for Addressing Maximization Bias in Q-Learning","display_name":"Risk Aversion Operator for Addressing Maximization Bias in Q-Learning","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3009660502","doi":"https://doi.org/10.1109/access.2020.2977400","mag":"3009660502"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.2977400","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2977400","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09019603.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09019603.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101886919","display_name":"Wang Bi","orcid":"https://orcid.org/0000-0002-4365-0148"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bi Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-4365-0148","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100659161","display_name":"Xuelian Li","orcid":"https://orcid.org/0000-0002-0553-8569"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelian Li","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-0553-8569","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056485034","display_name":"Zhiqiang Gao","orcid":"https://orcid.org/0000-0001-7381-9349"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Gao","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7381-9349","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056989262","display_name":"Yangjun Zhong","orcid":"https://orcid.org/0000-0002-2417-6567"},"institutions":[{"id":"https://openalex.org/I4510145","display_name":"Jiangxi University of Science and Technology","ror":"https://ror.org/03q0t9252","country_code":"CN","type":"education","lineage":["https://openalex.org/I4510145"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangjun Zhong","raw_affiliation_strings":["School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2417-6567","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, China","institution_ids":["https://openalex.org/I4510145"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.2608,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.61409391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"8","issue":null,"first_page":"43098","last_page":"43110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9904999732971191,"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":0.9904999732971191,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9649999737739563,"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/T10320","display_name":"Neural Networks and Applications","score":0.945900022983551,"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/operator","display_name":"Operator (biology)","score":0.7304280996322632},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7032846212387085},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.6918129920959473},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5526639819145203},{"id":"https://openalex.org/keywords/risk-aversion","display_name":"Risk aversion (psychology)","score":0.5061957240104675},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.48787498474121094},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4787580072879791},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.36027342081069946},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35640665888786316},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2572062611579895},{"id":"https://openalex.org/keywords/expected-utility-hypothesis","display_name":"Expected utility hypothesis","score":0.1942933201789856}],"concepts":[{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.7304280996322632},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7032846212387085},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.6918129920959473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5526639819145203},{"id":"https://openalex.org/C129915516","wikidata":"https://www.wikidata.org/wiki/Q17083550","display_name":"Risk aversion (psychology)","level":3,"score":0.5061957240104675},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.48787498474121094},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4787580072879791},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.36027342081069946},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35640665888786316},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2572062611579895},{"id":"https://openalex.org/C205706631","wikidata":"https://www.wikidata.org/wiki/Q2319304","display_name":"Expected utility hypothesis","level":2,"score":0.1942933201789856},{"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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.2977400","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2977400","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09019603.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5e20fbe54d404a4a83cf45e6ef47892a","is_oa":true,"landing_page_url":"https://doaj.org/article/5e20fbe54d404a4a83cf45e6ef47892a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 43098-43110 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.2977400","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2977400","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09019603.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3009660502.pdf","grobid_xml":"https://content.openalex.org/works/W3009660502.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W51508254","https://openalex.org/W1845972764","https://openalex.org/W1980516134","https://openalex.org/W2013406658","https://openalex.org/W2014296507","https://openalex.org/W2093253120","https://openalex.org/W2115211925","https://openalex.org/W2121863487","https://openalex.org/W2150339816","https://openalex.org/W2155968351","https://openalex.org/W2158091072","https://openalex.org/W2610686804","https://openalex.org/W2740912559","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2787938642","https://openalex.org/W2788862220","https://openalex.org/W2808421695","https://openalex.org/W2890192685","https://openalex.org/W2895095767","https://openalex.org/W2901269509","https://openalex.org/W2911933223","https://openalex.org/W2938321354","https://openalex.org/W2951368390","https://openalex.org/W2953299257","https://openalex.org/W2962847657","https://openalex.org/W2963049774","https://openalex.org/W2963169817","https://openalex.org/W2963267001","https://openalex.org/W2963376229","https://openalex.org/W2969304542","https://openalex.org/W2978562821","https://openalex.org/W3009870883","https://openalex.org/W3011120880","https://openalex.org/W4214717370","https://openalex.org/W4241521318","https://openalex.org/W4248967692","https://openalex.org/W4293871015","https://openalex.org/W4298188144","https://openalex.org/W4299857007","https://openalex.org/W6602057636","https://openalex.org/W6677067356","https://openalex.org/W6681795105","https://openalex.org/W6685366099","https://openalex.org/W6687688904","https://openalex.org/W6713603661","https://openalex.org/W6739455066","https://openalex.org/W6744838376","https://openalex.org/W6748645729","https://openalex.org/W6748839928","https://openalex.org/W6752725515","https://openalex.org/W6754479021","https://openalex.org/W6758235034","https://openalex.org/W6762410422"],"related_works":["https://openalex.org/W4287880334","https://openalex.org/W4366700029","https://openalex.org/W4285230481","https://openalex.org/W4385769873","https://openalex.org/W2015759683","https://openalex.org/W4281634296","https://openalex.org/W4319161863","https://openalex.org/W2371687270","https://openalex.org/W4307819175","https://openalex.org/W4311888330"],"abstract_inverted_index":{"In":[0,145,205],"Q-learning,":[1],"the":[2,8,15,31,38,45,55,60,62,67,70,77,80,83,90,96,103,110,113,121,133,137,142,149,161,168,179,183,189,195,201,214,218,223],"reduced":[3,65],"chance":[4,219],"of":[5,18,23,82,99,124,139,160,167,197,220],"converging":[6,140,221],"to":[7,28,76,136,141,147,182,222],"optimal":[9,117,210,224],"policy":[10,115,211],"is":[11,51,130,176,193,212],"partly":[12],"caused":[13],"by":[14,44,69,132,178],"estimated":[16,104],"bias":[17,105],"action":[19,24,164,198],"values.":[20],"The":[21,41,126],"estimation":[22],"values":[25,42,63,199],"usually":[26],"leads":[27,135],"biases":[29],"like":[30],"overestimation":[32],"and":[33,89,116,200],"underestimation":[34,68],"thus":[35],"it":[36],"hurts":[37],"current":[39,114],"policy.":[40,144,225],"produced":[43],"maximization":[46,56,87],"operator":[47,88,156,174],"are":[48,64,203],"overestimated,":[49],"which":[50,102,129,157,175],"well":[52],"known":[53],"as":[54],"bias.":[57],"For":[58],"correcting":[59],"bias,":[61],"towards":[66],"double":[71,91],"estimators":[72,92],"operator.":[73],"However,":[74],"according":[75],"proposed":[78,215],"analysis,":[79],"performances":[81],"two":[84],"operators":[85,134],"(the":[86],"operator)":[93],"rely":[94],"on":[95,186],"undetermined":[97],"dynamic":[98],"environment":[100],"in":[101],"results":[106],"from":[107],"not":[108],"only":[109],"difference":[111],"between":[112],"policy,":[118],"but":[119],"also":[120],"sampling":[122,127],"error":[123,128],"reward.":[125],"increased":[131],"risk":[138],"non-optimal":[143],"order":[146],"reduce":[148],"risk,":[150],"this":[151,187],"paper":[152],"proposes":[153],"a":[154],"flexible":[155],"takes":[158],"account":[159],"most":[162],"visited":[163],"value":[165],"instead":[166],"greedy":[169],"value,":[170],"named":[171],"Risk":[172,190],"Aversion":[173,191],"inspired":[177],"humans\u2019":[180],"response":[181],"uncertainty.":[184],"Based":[185],"operator,":[188],"Q-learning":[192],"proposed;":[194],"boundary":[196],"convergence":[202],"proven.":[204],"three":[206],"demonstration":[207],"tasks":[208],"whose":[209],"known,":[213],"algorithm":[216],"increases":[217]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}