{"id":"https://openalex.org/W2170141744","doi":"https://doi.org/10.1561/2200000042","title":"A Tutorial on Linear Function Approximators for Dynamic Programming and Reinforcement Learning","display_name":"A Tutorial on Linear Function Approximators for Dynamic Programming and Reinforcement Learning","publication_year":2013,"publication_date":"2013-12-19","ids":{"openalex":"https://openalex.org/W2170141744","doi":"https://doi.org/10.1561/2200000042","mag":"2170141744"},"language":"en","primary_location":{"id":"doi:10.1561/2200000042","is_oa":false,"landing_page_url":"https://doi.org/10.1561/2200000042","pdf_url":null,"source":{"id":"https://openalex.org/S4210188176","display_name":"Foundations and Trends\u00ae in Machine Learning","issn_l":"1935-8237","issn":["1935-8237","1935-8245"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318575","host_organization_name":"Now Publishers","host_organization_lineage":["https://openalex.org/P4310318575"],"host_organization_lineage_names":["Now Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Foundations and Trends\u00ae in Machine Learning","raw_type":"journal-article"},"type":"article","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/A5059864597","display_name":"Alborz Geramifard","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["RU","US"],"is_corresponding":true,"raw_author_name":"Alborz Geramifard","raw_affiliation_strings":["MIT LIDS","Massachusetts Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"MIT LIDS","institution_ids":["https://openalex.org/I4210109586"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Thomas J. Walsh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Thomas J. Walsh","raw_affiliation_strings":["MIT LIDS"],"affiliations":[{"raw_affiliation_string":"MIT LIDS","institution_ids":["https://openalex.org/I4210109586"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Stefanie Tellex","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefanie Tellex","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Girish Chowdhary","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Girish Chowdhary","raw_affiliation_strings":["MIT LIDS"],"affiliations":[{"raw_affiliation_string":"MIT LIDS","institution_ids":["https://openalex.org/I4210109586"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nicholas Roy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicholas Roy","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Jonathan P. How","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Jonathan P. How","raw_affiliation_strings":["MIT LIDS"],"affiliations":[{"raw_affiliation_string":"MIT LIDS","institution_ids":["https://openalex.org/I4210109586"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5059864597"],"corresponding_institution_ids":["https://openalex.org/I4210109586","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":9.8877,"has_fulltext":false,"cited_by_count":120,"citation_normalized_percentile":{"value":0.97942916,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"6","issue":"4","first_page":"375","last_page":"451"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9790999889373779,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9667999744415283,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6044919490814209},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5109983682632446},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.447807639837265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36929619312286377},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.35025858879089355},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.33478206396102905},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16203802824020386},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.09658655524253845}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6044919490814209},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5109983682632446},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.447807639837265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36929619312286377},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.35025858879089355},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.33478206396102905},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16203802824020386},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.09658655524253845},{"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":2,"locations":[{"id":"doi:10.1561/2200000042","is_oa":false,"landing_page_url":"https://doi.org/10.1561/2200000042","pdf_url":null,"source":{"id":"https://openalex.org/S4210188176","display_name":"Foundations and Trends\u00ae in Machine Learning","issn_l":"1935-8237","issn":["1935-8237","1935-8245"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318575","host_organization_name":"Now Publishers","host_organization_lineage":["https://openalex.org/P4310318575"],"host_organization_lineage_names":["Now Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Foundations and Trends\u00ae in Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:cds.cern.ch:2762208","is_oa":false,"landing_page_url":"http://cds.cern.ch/record/2762208","pdf_url":null,"source":{"id":"https://openalex.org/S4306402195","display_name":"CERN Document Server (European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":97,"referenced_works":["https://openalex.org/W13294968","https://openalex.org/W16046748","https://openalex.org/W87596044","https://openalex.org/W145683767","https://openalex.org/W165060581","https://openalex.org/W1211946649","https://openalex.org/W1515851193","https://openalex.org/W1525482321","https://openalex.org/W1526654727","https://openalex.org/W1547105496","https://openalex.org/W1560724230","https://openalex.org/W1576452626","https://openalex.org/W1585575029","https://openalex.org/W1597303641","https://openalex.org/W1599193893","https://openalex.org/W1626155273","https://openalex.org/W1646707810","https://openalex.org/W1746819321","https://openalex.org/W1819447595","https://openalex.org/W1850488217","https://openalex.org/W1851714595","https://openalex.org/W1920714059","https://openalex.org/W1984901446","https://openalex.org/W2004229888","https://openalex.org/W2009533501","https://openalex.org/W2018500972","https://openalex.org/W2027648864","https://openalex.org/W2028145673","https://openalex.org/W2040766536","https://openalex.org/W2046513829","https://openalex.org/W2048226872","https://openalex.org/W2072931156","https://openalex.org/W2073384958","https://openalex.org/W2075268401","https://openalex.org/W2095487261","https://openalex.org/W2097778153","https://openalex.org/W2098432798","https://openalex.org/W2098614265","https://openalex.org/W2103198983","https://openalex.org/W2104641222","https://openalex.org/W2104753538","https://openalex.org/W2106907982","https://openalex.org/W2107726111","https://openalex.org/W2108596215","https://openalex.org/W2110486110","https://openalex.org/W2112264645","https://openalex.org/W2119567691","https://openalex.org/W2119717200","https://openalex.org/W2121138345","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2123447947","https://openalex.org/W2123979492","https://openalex.org/W2124175081","https://openalex.org/W2124776405","https://openalex.org/W2125074935","https://openalex.org/W2125710232","https://openalex.org/W2126217565","https://openalex.org/W2127107099","https://openalex.org/W2128477394","https://openalex.org/W2132849848","https://openalex.org/W2134540127","https://openalex.org/W2136602922","https://openalex.org/W2137486584","https://openalex.org/W2138326839","https://openalex.org/W2139418546","https://openalex.org/W2140095548","https://openalex.org/W2140778663","https://openalex.org/W2141007261","https://openalex.org/W2146737184","https://openalex.org/W2146957157","https://openalex.org/W2148150594","https://openalex.org/W2150339816","https://openalex.org/W2150923691","https://openalex.org/W2151416233","https://openalex.org/W2151661095","https://openalex.org/W2153039919","https://openalex.org/W2155027007","https://openalex.org/W2156723248","https://openalex.org/W2158738729","https://openalex.org/W2159476216","https://openalex.org/W2164998010","https://openalex.org/W2165131254","https://openalex.org/W2167932108","https://openalex.org/W2171277043","https://openalex.org/W2172968643","https://openalex.org/W2173945562","https://openalex.org/W2200611301","https://openalex.org/W2293177546","https://openalex.org/W2334782222","https://openalex.org/W2341171179","https://openalex.org/W2798909945","https://openalex.org/W3106238320","https://openalex.org/W3139377883","https://openalex.org/W4246906609","https://openalex.org/W4285719527","https://openalex.org/W4299401133"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2024136090","https://openalex.org/W2964765435","https://openalex.org/W2585069576"],"abstract_inverted_index":{"A":[0],"Markov":[1],"Decision":[2],"Process":[3],"(MDP)":[4],"is":[5],"a":[6,82],"natural":[7],"framework":[8],"for":[9,24,41,94],"formulating":[10],"sequential":[11],"decision-making":[12],"problems":[13],"under":[14],"uncertainty.":[15],"In":[16],"recent":[17],"years,":[18],"researchers":[19],"have":[20],"greatly":[21],"advanced":[22],"algorithms":[23,80,112],"learning":[25,68],"and":[26,48,63,74,90,123],"acting":[27],"in":[28,81,118],"MDPs.":[29],"This":[30],"article":[31],"reviews":[32],"such":[33,44,57,70],"algorithms,":[34],"beginning":[35],"with":[36,88,101,114],"well-known":[37],"dynamic":[38,54],"programming":[39,55],"methods":[40,56,69],"solving":[42],"MDPs":[43],"as":[45,58,71],"policy":[46,76],"iteration":[47,91],"value":[49,61],"iteration,":[50,62],"then":[51],"describes":[52],"approximate":[53],"trajectory":[59],"based":[60],"finally":[64],"moves":[65],"to":[66],"reinforcement":[67],"Q-Learning,":[72],"SARSA,":[73],"least-squares":[75],"iteration.":[77],"We":[78],"describe":[79],"unified":[83],"framework,":[84],"giving":[85],"pseudocode":[86],"together":[87],"memory":[89],"complexity":[92],"analysis":[93],"each.":[95],"Empirical":[96],"evaluations":[97],"of":[98,120],"these":[99,111],"techniques":[100],"four":[102,105],"representations":[103],"across":[104],"domains,":[106],"provide":[107],"insight":[108],"into":[109],"how":[110],"perform":[113],"various":[115],"feature":[116],"sets":[117],"terms":[119],"running":[121],"time":[122],"performance.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":15},{"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":2},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}