{"id":"https://openalex.org/W4401576535","doi":"https://doi.org/10.1145/3688849","title":"A Meta-Learning Approach to Mitigating the Estimation Bias of Q-Learning","display_name":"A Meta-Learning Approach to Mitigating the Estimation Bias of Q-Learning","publication_year":2024,"publication_date":"2024-08-14","ids":{"openalex":"https://openalex.org/W4401576535","doi":"https://doi.org/10.1145/3688849"},"language":"en","primary_location":{"id":"doi:10.1145/3688849","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3688849","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3688849","source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3688849","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102584793","display_name":"Tao Tan","orcid":"https://orcid.org/0009-0001-1083-8769"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Tan","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China and State Key Laboratory of Cognitive Intelligence, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0001-1083-8769","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China and State Key Laboratory of Cognitive Intelligence, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064190343","display_name":"Hong Xie","orcid":"https://orcid.org/0000-0001-7935-7210"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Xie","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China and State Key Laboratory of Cognitive Intelligence, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7935-7210","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China and State Key Laboratory of Cognitive Intelligence, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662669","display_name":"Xiaoyu Shi","orcid":"https://orcid.org/0000-0002-4267-7795"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Shi","raw_affiliation_strings":["Chinese Academy of Sciences, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-4267-7795","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Chongqing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091667639","display_name":"Mingsheng Shang","orcid":"https://orcid.org/0000-0002-7024-2270"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingsheng Shang","raw_affiliation_strings":["Chinese Academy of Sciences, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-7024-2270","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Chongqing, China","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2778,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6103208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"18","issue":"9","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9977999925613403,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9977999925613403,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9962000250816345,"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":0.9944000244140625,"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/meta-learning","display_name":"Meta learning (computer science)","score":0.7769242525100708},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.6380777955055237},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6361377239227295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6246755123138428},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5538856387138367},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5453247427940369},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.520901620388031},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5196757912635803},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4988272190093994},{"id":"https://openalex.org/keywords/meta-analysis","display_name":"Meta-analysis","score":0.49489420652389526},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47670644521713257},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.43064790964126587},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3472329378128052},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.26918619871139526},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2572754919528961},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07809346914291382}],"concepts":[{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.7769242525100708},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.6380777955055237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6361377239227295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6246755123138428},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5538856387138367},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5453247427940369},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.520901620388031},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5196757912635803},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4988272190093994},{"id":"https://openalex.org/C95190672","wikidata":"https://www.wikidata.org/wiki/Q815382","display_name":"Meta-analysis","level":2,"score":0.49489420652389526},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47670644521713257},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.43064790964126587},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3472329378128052},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.26918619871139526},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2572754919528961},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07809346914291382},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3688849","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3688849","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3688849","source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3688849","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3688849","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3688849","source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4401576535.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1941445455","https://openalex.org/W2037195155","https://openalex.org/W2108692343","https://openalex.org/W2122701159","https://openalex.org/W2145339207","https://openalex.org/W2162699601","https://openalex.org/W2165698076","https://openalex.org/W2608239929","https://openalex.org/W2941439130","https://openalex.org/W3007054387","https://openalex.org/W3011120880","https://openalex.org/W3131687345","https://openalex.org/W3206719683","https://openalex.org/W3211287969","https://openalex.org/W3212057508","https://openalex.org/W4200241545","https://openalex.org/W4211225923","https://openalex.org/W4214717370","https://openalex.org/W4283210454","https://openalex.org/W4360913297","https://openalex.org/W4391427676","https://openalex.org/W6677067356","https://openalex.org/W6790917506"],"related_works":["https://openalex.org/W3201126466","https://openalex.org/W2320718078","https://openalex.org/W2653530212","https://openalex.org/W2576994247","https://openalex.org/W4282827391","https://openalex.org/W2608353378","https://openalex.org/W4249206767","https://openalex.org/W2786928087","https://openalex.org/W3163412989","https://openalex.org/W4294873804"],"abstract_inverted_index":{"It":[0],"is":[1,101],"a":[2,68,86],"longstanding":[3],"problem":[4,45],"that":[5,18,62,209],"Q-learning":[6,19,212,231],"suffers":[7],"from":[8,15,77,85,151],"the":[9,16,21,28,48,73,104,115,123,126,149,156,164,171,174,178,193,196,202,236,241,250,254,263,282],"overestimation":[10,74],"bias.":[11,60,75,204],"This":[12,181],"issue":[13,84],"originates":[14],"fact":[17],"uses":[20],"expectation":[22],"of":[23,34,50,118,159],"maximum":[24,29,51,105,119,160,197,222,237,283],"Q-value":[25,107,120,199,239],"to":[26,42,57,94,102,113,138,146,154,185,200],"approximate":[27],"expected":[30,106,198,238],"Q-value.":[31],"A":[32],"number":[33],"algorithms,":[35,79],"such":[36],"as":[37],"Double":[38],"Q-learning,":[39],"were":[40],"proposed":[41,278],"address":[43,163],"this":[44,54,63,80,83],"by":[46],"reducing":[47],"estimation":[49,116,157,203],"Q-value,":[52,223,284],"but":[53],"may":[55,66],"lead":[56],"an":[58],"underestimation":[59,64],"Note":[61],"bias":[65,117,158],"have":[67],"larger":[69],"performance":[70],"penalty":[71],"than":[72,235,249],"Different":[76],"previous":[78],"article":[81],"studies":[82],"fresh":[87],"perspective,":[88],"i.e.,":[89,221],"meta-learning":[90,109],"view,":[91],"which":[92],"leads":[93],"our":[95,210,229,267,277],"Meta-Debias":[96,211,230],"Q-learning.":[97],"The":[98],"main":[99],"idea":[100],"extract":[103,195],"with":[108],"over":[110],"multiple":[111],"tasks":[112,153,176,190],"remove":[114,155,201],"and":[121,177,191,225,245,266,286],"help":[122],"agent":[124,194],"choose":[125],"optimal":[127,251],"action":[128],"more":[129],"accurately.":[130],"However,":[131],"there":[132],"are":[133],"two":[134,165,255],"challenges:":[135],"(1)":[136],"How":[137,145],"automatically":[139],"select":[140,186],"suitable":[141],"training":[142,175,189],"tasks?":[143],"(2)":[144],"positively":[147],"transfer":[148],"meta-knowledge":[150],"selected":[152],"Q-value?":[161],"To":[162],"challenges":[166],"mentioned":[167],"above,":[168],"we":[169,261],"quantify":[170],"similarity":[172,182,268],"between":[173],"test":[179],"task.":[180],"enables":[183],"us":[184],"appropriate":[187],"\u201cpartial\u201d":[188],"helps":[192],"Extensive":[205],"experiment":[206],"results":[207,271],"show":[208],"outperforms":[213,280],"SOTA":[214],"baselines":[215],"drastically":[216],"in":[217,240,253,281],"three":[218],"evaluation":[219],"indicators,":[220],"policy,":[224,285],"reward.":[226,287],"More":[227],"specifically,":[228],"only":[232,246],"underestimates":[233],"\\(1.2*10^{-3}\\)":[234],"multi-armed":[242],"bandit":[243],"environment":[244],"differs":[247],"\\(5.04\\%-5\\%=0.04\\%\\)":[248],"policy":[252],"states":[256],"MDP":[257],"environment.":[258],"In":[259],"addition,":[260],"compare":[262],"uniform":[264],"weight":[265],"weight.":[269],"Experiment":[270],"reveal":[272],"fundamental":[273],"insights":[274],"into":[275],"why":[276],"algorithm":[279]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}