{"id":"https://openalex.org/W2130304665","doi":"https://doi.org/10.1007/978-3-540-72927-3_23","title":"Q-Learning with Linear Function Approximation","display_name":"Q-Learning with Linear Function Approximation","publication_year":2007,"publication_date":"2007-06-12","ids":{"openalex":"https://openalex.org/W2130304665","doi":"https://doi.org/10.1007/978-3-540-72927-3_23","mag":"2130304665"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-540-72927-3_23","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-72927-3_23","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5101616573","display_name":"Francisco S. Melo","orcid":"https://orcid.org/0000-0001-5705-7372"},"institutions":[{"id":"https://openalex.org/I4387152517","display_name":"Instituto Superior T\u00e9cnico","ror":"https://ror.org/03db2by73","country_code":null,"type":"education","lineage":["https://openalex.org/I141596103","https://openalex.org/I4387152517"]},{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Francisco S. Melo","raw_affiliation_strings":["Institute for Systems and Robotics, Instituto Superior T\u00e9cnico, Lisboa, Portugal","Institute for Systems and Robotics, Instituto Superior T\u00e9cnico, Lisboa, Portugal,"],"affiliations":[{"raw_affiliation_string":"Institute for Systems and Robotics, Instituto Superior T\u00e9cnico, Lisboa, Portugal","institution_ids":["https://openalex.org/I4210166615","https://openalex.org/I4387152517"]},{"raw_affiliation_string":"Institute for Systems and Robotics, Instituto Superior T\u00e9cnico, Lisboa, Portugal,","institution_ids":["https://openalex.org/I4210166615","https://openalex.org/I4387152517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082125744","display_name":"Isabel Ribeiro","orcid":"https://orcid.org/0000-0001-6083-0290"},"institutions":[{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]},{"id":"https://openalex.org/I4387152517","display_name":"Instituto Superior T\u00e9cnico","ror":"https://ror.org/03db2by73","country_code":null,"type":"education","lineage":["https://openalex.org/I141596103","https://openalex.org/I4387152517"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"M. Isabel Ribeiro","raw_affiliation_strings":["Institute for Systems and Robotics, Instituto Superior T\u00e9cnico, Lisboa, Portugal","Institute for Systems and Robotics, Instituto Superior T\u00e9cnico, Lisboa, Portugal,"],"affiliations":[{"raw_affiliation_string":"Institute for Systems and Robotics, Instituto Superior T\u00e9cnico, Lisboa, Portugal","institution_ids":["https://openalex.org/I4210166615","https://openalex.org/I4387152517"]},{"raw_affiliation_string":"Institute for Systems and Robotics, Instituto Superior T\u00e9cnico, Lisboa, Portugal,","institution_ids":["https://openalex.org/I4210166615","https://openalex.org/I4387152517"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101616573"],"corresponding_institution_ids":["https://openalex.org/I4210166615","https://openalex.org/I4387152517"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.5988,"has_fulltext":false,"cited_by_count":89,"citation_normalized_percentile":{"value":0.86174825,"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":"308","last_page":"322"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9983999729156494,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/convergence","display_name":"Convergence (economics)","score":0.7703268527984619},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6297801733016968},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.6081023216247559},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.59676593542099},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5195163488388062},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4917290508747101},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.48076102137565613},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3908756375312805},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06808707118034363},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.060360223054885864}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7703268527984619},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6297801733016968},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.6081023216247559},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.59676593542099},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5195163488388062},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4917290508747101},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.48076102137565613},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3908756375312805},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06808707118034363},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.060360223054885864},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/978-3-540-72927-3_23","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-72927-3_23","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.107.5434","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.107.5434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://welcome.isr.ist.utl.pt/img/pdfs/1702_COLT07QLPO-Proceedings.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.108.6854","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.108.6854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://welcome.isr.ist.utl.pt/img/pdfs/1707_RT-602-07.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.109.6914","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.109.6914","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://welcome.isr.ist.utl.pt/img/pdfs/1706_COLT07QLPO.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W131709709","https://openalex.org/W180325379","https://openalex.org/W1512407760","https://openalex.org/W1518539242","https://openalex.org/W1538075516","https://openalex.org/W1539216098","https://openalex.org/W1547105496","https://openalex.org/W1550698229","https://openalex.org/W1553308207","https://openalex.org/W1554898028","https://openalex.org/W1557517019","https://openalex.org/W1576452626","https://openalex.org/W1597173708","https://openalex.org/W1597303641","https://openalex.org/W1600046456","https://openalex.org/W1646707810","https://openalex.org/W1679945064","https://openalex.org/W1965413238","https://openalex.org/W1980035368","https://openalex.org/W1981276685","https://openalex.org/W1995713768","https://openalex.org/W1998172110","https://openalex.org/W2009533501","https://openalex.org/W2011233848","https://openalex.org/W2032100464","https://openalex.org/W2041367235","https://openalex.org/W2065134213","https://openalex.org/W2071983464","https://openalex.org/W2094364653","https://openalex.org/W2100677568","https://openalex.org/W2106983679","https://openalex.org/W2107977784","https://openalex.org/W2124175081","https://openalex.org/W2125074935","https://openalex.org/W2125510930","https://openalex.org/W2132351269","https://openalex.org/W2139418546","https://openalex.org/W2165131254","https://openalex.org/W2169982856","https://openalex.org/W2346626577","https://openalex.org/W2489939061","https://openalex.org/W2557332589","https://openalex.org/W2787259794","https://openalex.org/W3011120880","https://openalex.org/W3023407077","https://openalex.org/W3139377883","https://openalex.org/W4212774754"],"related_works":["https://openalex.org/W1994680671","https://openalex.org/W2000283393","https://openalex.org/W2002320543","https://openalex.org/W2061947244","https://openalex.org/W2150232912","https://openalex.org/W2054940838","https://openalex.org/W3106170641","https://openalex.org/W4321855183","https://openalex.org/W2952513607","https://openalex.org/W2383918176"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
