{"id":"https://openalex.org/W2168551972","doi":null,"title":"A Generalization Error for Q-Learning.","display_name":"A Generalization Error for Q-Learning.","publication_year":2005,"publication_date":"2005-07-01","ids":{"openalex":"https://openalex.org/W2168551972","mag":"2168551972","pmid":"https://pubmed.ncbi.nlm.nih.gov/16763665","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/1475741"},"language":"en","primary_location":{"id":"pmid:16763665","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16763665","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of machine learning research : JMLR","raw_type":"Journal Article"},"volume":null,"type":"article","indexed_in":["pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/2027.42/57425","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070589969","display_name":"Susan A. Murphy","orcid":"https://orcid.org/0000-0002-2032-4286","observed_orcids":["https://orcid.org/0000-0002-2032-4286"]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Susan A Murphy","raw_affiliation_strings":["Department of Statistics, University of Michigan, Ann Arbor, MI 48109-1107, USA","Department of Statistics, University of Michigan, Ann Arbor, MI 48109-1107, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Michigan, Ann Arbor, MI 48109-1107, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Department of Statistics, University of Michigan, Ann Arbor, MI 48109-1107, USA#TAB#","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5070589969"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":2.8119,"has_fulltext":true,"cited_by_count":213,"citation_normalized_percentile":{"value":0.90906541,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"6","issue":null,"first_page":"1073","last_page":"1097"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0008999999845400453,"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":0.00019999999494757503,"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/q-learning","display_name":"Q-learning","score":0.9940000176429749},{"id":"https://openalex.org/keywords/generalization-error","display_name":"generalization error","score":0.9860000014305115},{"id":"https://openalex.org/keywords/function-approximation","display_name":"function approximation","score":0.8709999918937683},{"id":"https://openalex.org/keywords/upper-bounds","display_name":"upper bounds","score":0.5989999771118164},{"id":"https://openalex.org/keywords/policy-learning","display_name":"policy learning","score":0.7459999918937683},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.703000009059906}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7965256571769714},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.6770421266555786},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5639652609825134},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.5055785179138184},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.5003504753112793},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4974246323108673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48891130089759827},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45551174879074097},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.44693100452423096},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4370938539505005},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43455949425697327},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4208757281303406},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4103085696697235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3702412247657776},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.329181969165802},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2405300736427307},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.22147592902183533},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.1795569658279419},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.13829681277275085},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.07312232255935669},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"pmid:16763665","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16763665","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of machine learning research : JMLR","raw_type":"Journal Article"},{"id":"pmh:oai:deepblue.lib.umich.edu:2027.42/57425","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/2027.42/57425>","pdf_url":"https://hdl.handle.net/2027.42/57425","source":{"id":"https://openalex.org/S4306400393","display_name":"Deep Blue (University of Michigan)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I27837315","host_organization_name":"University of Michigan","host_organization_lineage":["https://openalex.org/I27837315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:1475741","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1475741","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"J Mach Learn Res","raw_type":"Text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.377.4602","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.377.4602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dept.stat.lsa.umich.edu/~samurphy/papers/QLearningOld.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.377.64","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.377.64","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dept.stat.lsa.umich.edu/~samurphy/papers/QLearningJMLR05.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.75.3904","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.3904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.jmlr.org/papers/volume6/murphy05a/murphy05a.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:deepblue.lib.umich.edu:2027.42/57425","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/2027.42/57425>","pdf_url":"https://hdl.handle.net/2027.42/57425","source":{"id":"https://openalex.org/S4306400393","display_name":"Deep Blue (University of Michigan)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I27837315","host_organization_name":"University of Michigan","host_organization_lineage":["https://openalex.org/I27837315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2127932070","display_name":"Reducing Drug Abuse with Individually Tailored Treatment","funder_award_id":"K02DA015674","funder_id":"https://openalex.org/F4320337347","funder_display_name":"National Institute on Drug Abuse"},{"id":"https://openalex.org/G5498503866","display_name":"Center for Prevention and Treatment Methodology","funder_award_id":"P50DA010075","funder_id":"https://openalex.org/F4320337347","funder_display_name":"National Institute on Drug Abuse"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337347","display_name":"National Institute on Drug Abuse","ror":"https://ror.org/00fq5cm18"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2168551972.pdf","grobid_xml":"https://content.openalex.org/works/W2168551972.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1578605396","https://openalex.org/W1975041940","https://openalex.org/W2036850822","https://openalex.org/W2042542641","https://openalex.org/W2110341150","https://openalex.org/W2169849640"],"related_works":["https://openalex.org/W3006052551","https://openalex.org/W3099754186","https://openalex.org/W2151661095","https://openalex.org/W4416292179","https://openalex.org/W4415796359","https://openalex.org/W51508254","https://openalex.org/W3038013583","https://openalex.org/W2039439610","https://openalex.org/W7097985838","https://openalex.org/W1999254175"],"abstract_inverted_index":{"Planning":[0],"problems":[1],"that":[2,78],"involve":[3],"learning":[4,75],"a":[5,8,52,76],"policy":[6,77],"from":[7],"single":[9],"training":[10],"set":[11],"of":[12,48,57,74],"finite":[13],"horizon":[14],"trajectories":[15],"arise":[16],"in":[17,46],"both":[18],"social":[19],"science":[20],"and":[21,33,61,71],"medical":[22],"fields.":[23],"We":[24],"consider":[25],"Q-learning":[26,53,70],"with":[27],"function":[28],"approximation":[29,59,63],"for":[30],"this":[31],"setting":[32],"derive":[34],"an":[35,62],"upper":[36,43],"bound":[37,44],"on":[38],"the":[39,55,58,67,72,80],"generalization":[40],"error.":[41],"This":[42],"is":[45],"terms":[47],"quantities":[49],"minimized":[50],"by":[51],"algorithm,":[54],"complexity":[56],"space":[60],"term":[64],"due":[65],"to":[66],"mismatch":[68],"between":[69],"goal":[73],"maximizes":[79],"value":[81],"function.":[82]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":18},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":7}],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2025-10-10T00:00:00"}