{"id":"https://openalex.org/W3100366369","doi":"https://doi.org/10.1561/2200000071","title":"An Introduction to Deep Reinforcement Learning","display_name":"An Introduction to Deep Reinforcement Learning","publication_year":2018,"publication_date":"2018-12-20","ids":{"openalex":"https://openalex.org/W3100366369","doi":"https://doi.org/10.1561/2200000071","mag":"3100366369"},"language":"en","primary_location":{"id":"doi:10.1561/2200000071","is_oa":false,"landing_page_url":"https://doi.org/10.1561/2200000071","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.12560","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015166903","display_name":"Vincent Fran\u00e7ois-Lavet","orcid":"https://orcid.org/0000-0002-8593-9740"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Vincent Fran\u00e7ois-Lavet","raw_affiliation_strings":["McGill University","McGill University, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"McGill University, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049073875","display_name":"Peter Henderson","orcid":"https://orcid.org/0000-0003-3938-0541"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Peter Henderson","raw_affiliation_strings":["McGill University","McGill University, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"McGill University, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079926596","display_name":"Riashat Islam","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Riashat Islam","raw_affiliation_strings":["McGill University","McGill University, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"McGill University, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001087292","display_name":"Marc G. Bellemare","orcid":"https://orcid.org/0000-0002-6096-0105"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marc G. Bellemare","raw_affiliation_strings":["Google Brain","Google Brain, USA"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Brain, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080591144","display_name":"Jo\u00eblle Pineau","orcid":"https://orcid.org/0000-0003-0747-7250"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA","IL"],"is_corresponding":false,"raw_author_name":"Pineau Joelle","raw_affiliation_strings":["Facebook, McGill University","McGill University, Canada"],"affiliations":[{"raw_affiliation_string":"Facebook, McGill University","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"McGill University, Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5015166903"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":51.2794,"has_fulltext":true,"cited_by_count":1225,"citation_normalized_percentile":{"value":0.99857022,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"11","issue":"3-4","first_page":"219","last_page":"354"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9951000213623047,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9772999882698059,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9108544588088989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7724791765213013},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6746521592140198},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6459547877311707},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6101894378662109},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5065644979476929},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4804379642009735},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.430669903755188},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.12885117530822754},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.058938294649124146}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9108544588088989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7724791765213013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6746521592140198},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6459547877311707},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6101894378662109},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5065644979476929},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4804379642009735},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.430669903755188},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.12885117530822754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.058938294649124146},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1561/2200000071","is_oa":false,"landing_page_url":"https://doi.org/10.1561/2200000071","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:repositorio.unal.edu.co:unal/80758","is_oa":false,"landing_page_url":"https://repositorio.unal.edu.co/handle/unal/80758","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"reponame:Repositorio UN","raw_type":"Trabajo de grado - Maestr\u00eda"},{"id":"pmh:oai:arXiv.org:1811.12560","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.12560","pdf_url":"https://arxiv.org/pdf/1811.12560","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:aleph.bib-bvb.de:BVB01-031590921","is_oa":false,"landing_page_url":"https://www.nowpublishers.com/article/Details/MAL-071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"software, multimedia"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.12560","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.12560","pdf_url":"https://arxiv.org/pdf/1811.12560","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3100366369.pdf","grobid_xml":"https://content.openalex.org/works/W3100366369.grobid-xml"},"referenced_works_count":104,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W87596044","https://openalex.org/W193897080","https://openalex.org/W779494576","https://openalex.org/W1480527676","https://openalex.org/W1520121841","https://openalex.org/W1564393562","https://openalex.org/W1569296262","https://openalex.org/W1608401492","https://openalex.org/W1631187438","https://openalex.org/W1663973292","https://openalex.org/W1762172548","https://openalex.org/W1905399323","https://openalex.org/W1957496711","https://openalex.org/W2074229969","https://openalex.org/W2076337359","https://openalex.org/W2081030963","https://openalex.org/W2098432798","https://openalex.org/W2101234009","https://openalex.org/W2117423905","https://openalex.org/W2145339207","https://openalex.org/W2173564293","https://openalex.org/W2174786457","https://openalex.org/W2176263492","https://openalex.org/W2202514763","https://openalex.org/W2214429195","https://openalex.org/W2335959470","https://openalex.org/W2342840547","https://openalex.org/W2462906003","https://openalex.org/W2472053385","https://openalex.org/W2521274174","https://openalex.org/W2522340145","https://openalex.org/W2547416798","https://openalex.org/W2554120691","https://openalex.org/W2567374473","https://openalex.org/W2579923771","https://openalex.org/W2596367596","https://openalex.org/W2596982695","https://openalex.org/W2604763608","https://openalex.org/W2606433045","https://openalex.org/W2606508169","https://openalex.org/W2609374097","https://openalex.org/W2609650878","https://openalex.org/W2617317556","https://openalex.org/W2617547828","https://openalex.org/W2626778328","https://openalex.org/W2626804490","https://openalex.org/W2735347808","https://openalex.org/W2736601468","https://openalex.org/W2738675347","https://openalex.org/W2739083961","https://openalex.org/W2739473244","https://openalex.org/W2754517384","https://openalex.org/W2759710969","https://openalex.org/W2761873684","https://openalex.org/W2788781499","https://openalex.org/W2797527950","https://openalex.org/W2799164650","https://openalex.org/W2809668646","https://openalex.org/W2897345632","https://openalex.org/W2910401125","https://openalex.org/W2938394653","https://openalex.org/W2941187661","https://openalex.org/W2941389059","https://openalex.org/W2943232250","https://openalex.org/W2947549238","https://openalex.org/W2949117887","https://openalex.org/W2949264490","https://openalex.org/W2949561945","https://openalex.org/W2949980113","https://openalex.org/W2950471160","https://openalex.org/W2950989964","https://openalex.org/W2952332632","https://openalex.org/W2952606116","https://openalex.org/W2952791429","https://openalex.org/W2963125871","https://openalex.org/W2967254933","https://openalex.org/W2968584812","https://openalex.org/W2975727060","https://openalex.org/W2982913475","https://openalex.org/W2994949492","https://openalex.org/W3022746105","https://openalex.org/W3028022888","https://openalex.org/W3089019288","https://openalex.org/W3093186795","https://openalex.org/W3100366369","https://openalex.org/W3100789280","https://openalex.org/W3103346379","https://openalex.org/W3121214275","https://openalex.org/W3122402852","https://openalex.org/W3123133461","https://openalex.org/W3123298421","https://openalex.org/W3131429432","https://openalex.org/W3144406026","https://openalex.org/W3150570724","https://openalex.org/W3157937972","https://openalex.org/W3160861144","https://openalex.org/W4211171425","https://openalex.org/W4237698691","https://openalex.org/W4285719527","https://openalex.org/W4287760041","https://openalex.org/W4288322652","https://openalex.org/W4288333180","https://openalex.org/W4300336601"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W3162204513","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W4380075502"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,7,66],"learning":[2,8,67,100],"is":[3,74,95],"the":[4,76,93],"combination":[5],"of":[6,15,25,34],"(RL)":[9],"and":[10,56,70,81],"deep":[11,40,65,83],"learning.":[12],"This":[13,59],"field":[14],"research":[16],"has":[17],"been":[18],"able":[19],"to":[20,64,79],"solve":[21],"a":[22,37],"wide":[23],"range":[24],"complex":[26],"decision":[27],"making":[28],"tasks":[29],"that":[30],"were":[31],"previously":[32],"out":[33],"reach":[35],"for":[36,88],"machine.":[38],"Thus,":[39],"RL":[41,84],"opens":[42],"up":[43],"many":[44,57],"new":[45],"applications":[46],"in":[47],"domains":[48],"such":[49],"as":[50],"healthcare,":[51],"robotics,":[52],"smart":[53],"grids,":[54],"finance,":[55],"more.":[58],"manuscript":[60],"provides":[61],"an":[62],"introduction":[63],"models,":[68],"algorithms":[69],"techniques.":[71],"Particular":[72],"focus":[73],"on":[75],"aspects":[77],"related":[78],"generalization":[80],"how":[82],"can":[85],"be":[86],"used":[87],"practical":[89],"applications.":[90],"We":[91],"assume":[92],"reader":[94],"familiar":[96],"with":[97],"basic":[98],"machine":[99],"concepts.":[101]},"counts_by_year":[{"year":2026,"cited_by_count":27},{"year":2025,"cited_by_count":226},{"year":2024,"cited_by_count":245},{"year":2023,"cited_by_count":237},{"year":2022,"cited_by_count":186},{"year":2021,"cited_by_count":140},{"year":2020,"cited_by_count":118},{"year":2019,"cited_by_count":43},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}