{"id":"https://openalex.org/W32403112","doi":"https://doi.org/10.1007/bf00992698","title":"Q-learning","display_name":"Q-learning","publication_year":1992,"publication_date":"1992-05-01","ids":{"openalex":"https://openalex.org/W32403112","doi":"https://doi.org/10.1007/bf00992698","mag":"32403112"},"language":"en","primary_location":{"id":"doi:10.1007/bf00992698","is_oa":true,"landing_page_url":"https://doi.org/10.1007/bf00992698","pdf_url":"https://link.springer.com/content/pdf/10.1007/BF00992698.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/BF00992698.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109045866","display_name":"Christopher J. Watkins","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163231","display_name":"The FRAM Centre","ror":"https://ror.org/05x7v6y85","country_code":"NO","type":"facility","lineage":["https://openalex.org/I4210163231"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Christopher J. C. H. Watkins","raw_affiliation_strings":["25b Framfield Road, N5 IUU, Highbury, London, England","25b Framfield Road, Highbury, London N5 1UU, England#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"25b Framfield Road, N5 IUU, Highbury, London, England","institution_ids":["https://openalex.org/I4210163231"]},{"raw_affiliation_string":"25b Framfield Road, Highbury, London N5 1UU, England#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075063030","display_name":"Peter Dayan","orcid":"https://orcid.org/0000-0003-3476-1839"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Dayan","raw_affiliation_strings":["Centre for Cognitive Science, University of Edinburgh, 2 Buccleuch Place, EH8 9EH, Edinburgh, Scotland","Centre for Cognitive Science, University of Edinburgh, 2 Buccleuch Place, Edinburgh EH8 9EH, Scotland#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Cognitive Science, University of Edinburgh, 2 Buccleuch Place, EH8 9EH, Edinburgh, Scotland","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Cognitive Science, University of Edinburgh, 2 Buccleuch Place, Edinburgh EH8 9EH, Scotland#TAB#","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109045866"],"corresponding_institution_ids":["https://openalex.org/I4210163231"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":19.5287,"has_fulltext":true,"cited_by_count":8953,"citation_normalized_percentile":{"value":0.99330318,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"8","issue":"3-4","first_page":"279","last_page":"292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9043999910354614,"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":0.9043999910354614,"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/sketch","display_name":"Sketch","score":0.6807084679603577},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5771201848983765},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5733039975166321},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5706813931465149},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5679721832275391},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5647444128990173},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5517730116844177},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5334587097167969},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4668614864349365},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.44813379645347595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41840797662734985},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3925969898700714},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.33937591314315796},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.3089245557785034},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.30259573459625244},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08328121900558472}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.6807084679603577},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5771201848983765},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5733039975166321},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5706813931465149},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5679721832275391},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5647444128990173},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5517730116844177},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5334587097167969},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4668614864349365},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.44813379645347595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41840797662734985},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3925969898700714},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.33937591314315796},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3089245557785034},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30259573459625244},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08328121900558472},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/bf00992698","is_oa":true,"landing_page_url":"https://doi.org/10.1007/bf00992698","pdf_url":"https://link.springer.com/content/pdf/10.1007/BF00992698.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:pure.mpg.de:item_3022498","is_oa":true,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0002-D738-D","pdf_url":"http://hdl.handle.net/21.11116/0000-0002-D738-D","source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.mpg.de:item_3022498","is_oa":true,"landing_page_url":"https://hdl.handle.net/21.11116/0000-0002-D738-D","pdf_url":"http://hdl.handle.net/21.11116/0000-0002-D738-D","source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/bf00992698","is_oa":true,"landing_page_url":"https://doi.org/10.1007/bf00992698","pdf_url":"https://link.springer.com/content/pdf/10.1007/BF00992698.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W32403112.pdf","grobid_xml":"https://content.openalex.org/works/W32403112.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W569156507","https://openalex.org/W1491843047","https://openalex.org/W1500245617","https://openalex.org/W1569296262","https://openalex.org/W1586172133","https://openalex.org/W1640646391","https://openalex.org/W2015667537","https://openalex.org/W2035446426","https://openalex.org/W2141559645","https://openalex.org/W2235056388","https://openalex.org/W2914112863","https://openalex.org/W3011120880","https://openalex.org/W4298300677","https://openalex.org/W7038606143"],"related_works":["https://openalex.org/W2101748387","https://openalex.org/W2145363145","https://openalex.org/W2937181779","https://openalex.org/W2146763310","https://openalex.org/W1626977535","https://openalex.org/W4382935469","https://openalex.org/W3167472281","https://openalex.org/W3198564127","https://openalex.org/W2156992384","https://openalex.org/W1511927616"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":76},{"year":2025,"cited_by_count":653},{"year":2024,"cited_by_count":1007},{"year":2023,"cited_by_count":1105},{"year":2022,"cited_by_count":916},{"year":2021,"cited_by_count":882},{"year":2020,"cited_by_count":773},{"year":2019,"cited_by_count":570},{"year":2018,"cited_by_count":400},{"year":2017,"cited_by_count":279},{"year":2016,"cited_by_count":199},{"year":2015,"cited_by_count":165},{"year":2014,"cited_by_count":173},{"year":2013,"cited_by_count":164},{"year":2012,"cited_by_count":164}],"updated_date":"2026-05-19T08:33:51.333923","created_date":"2016-06-24T00:00:00"}
