{"id":"https://openalex.org/W1589747210","doi":"https://doi.org/10.1038/nature14540","title":"Reinforcement learning improves behaviour from evaluative feedback","display_name":"Reinforcement learning improves behaviour from evaluative feedback","publication_year":2015,"publication_date":"2015-05-26","ids":{"openalex":"https://openalex.org/W1589747210","doi":"https://doi.org/10.1038/nature14540","mag":"1589747210"},"language":"en","primary_location":{"id":"doi:10.1038/nature14540","is_oa":false,"landing_page_url":"https://doi.org/10.1038/nature14540","pdf_url":null,"source":{"id":"https://openalex.org/S137773608","display_name":"Nature","issn_l":"0028-0836","issn":["0028-0836","1476-4687"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature","raw_type":"journal-article"},"type":"review","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/A5009722403","display_name":"Michael L. Littman","orcid":"https://orcid.org/0000-0002-5596-1840"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael L. Littman","raw_affiliation_strings":["Department of Computer Science, Brown University, Providence, 02912, Rhode Island, USA","Department of Computer Science, Brown University, Providence, Rhode Island 02912, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Brown University, Providence, 02912, Rhode Island, USA","institution_ids":["https://openalex.org/I27804330"]},{"raw_affiliation_string":"Department of Computer Science, Brown University, Providence, Rhode Island 02912, USA","institution_ids":["https://openalex.org/I27804330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5009722403"],"corresponding_institution_ids":["https://openalex.org/I27804330"],"apc_list":{"value":9750,"currency":"EUR","value_usd":11690},"apc_paid":null,"fwci":33.2202,"has_fulltext":false,"cited_by_count":363,"citation_normalized_percentile":{"value":0.9971932,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"521","issue":"7553","first_page":"445","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":0.9984999895095825,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9796000123023987,"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":0.9775000214576721,"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":0.8754371404647827},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7608231902122498},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6006388664245605},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5889357328414917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5402601957321167},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36502861976623535},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.24669140577316284},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.11720100045204163},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07405564188957214}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8754371404647827},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7608231902122498},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6006388664245605},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5889357328414917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5402601957321167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36502861976623535},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24669140577316284},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.11720100045204163},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07405564188957214},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1038/nature14540","is_oa":false,"landing_page_url":"https://doi.org/10.1038/nature14540","pdf_url":null,"source":{"id":"https://openalex.org/S137773608","display_name":"Nature","issn_l":"0028-0836","issn":["0028-0836","1476-4687"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W13294968","https://openalex.org/W745775011","https://openalex.org/W1491843047","https://openalex.org/W1557517019","https://openalex.org/W1618543586","https://openalex.org/W1625390266","https://openalex.org/W1646707810","https://openalex.org/W1777239053","https://openalex.org/W1931792391","https://openalex.org/W1968774621","https://openalex.org/W1971623008","https://openalex.org/W1977655452","https://openalex.org/W1983362322","https://openalex.org/W2009708807","https://openalex.org/W2014518776","https://openalex.org/W2027795129","https://openalex.org/W2039522160","https://openalex.org/W2040598998","https://openalex.org/W2041367235","https://openalex.org/W2056740053","https://openalex.org/W2058879737","https://openalex.org/W2061562262","https://openalex.org/W2075268401","https://openalex.org/W2100677568","https://openalex.org/W2100787464","https://openalex.org/W2107726111","https://openalex.org/W2108734173","https://openalex.org/W2112420033","https://openalex.org/W2112899086","https://openalex.org/W2115870554","https://openalex.org/W2117726420","https://openalex.org/W2118490768","https://openalex.org/W2119998956","https://openalex.org/W2121110499","https://openalex.org/W2121863487","https://openalex.org/W2125074935","https://openalex.org/W2133993682","https://openalex.org/W2134042548","https://openalex.org/W2138909795","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2156869222","https://openalex.org/W2164424353","https://openalex.org/W2165131254","https://openalex.org/W2165905123","https://openalex.org/W2166948894","https://openalex.org/W2168405694","https://openalex.org/W2181849516","https://openalex.org/W2341171179","https://openalex.org/W2346626577","https://openalex.org/W2401533533","https://openalex.org/W2488247662","https://openalex.org/W2489939061","https://openalex.org/W2575731723","https://openalex.org/W2911296969","https://openalex.org/W2951802169","https://openalex.org/W3021909058","https://openalex.org/W3103780890","https://openalex.org/W3198350258","https://openalex.org/W4214717370","https://openalex.org/W4246270964","https://openalex.org/W4285719527","https://openalex.org/W4321428174","https://openalex.org/W7065010408"],"related_works":["https://openalex.org/W2501594388","https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4313488044","https://openalex.org/W3209574120","https://openalex.org/W4312192474"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":42},{"year":2023,"cited_by_count":48},{"year":2022,"cited_by_count":34},{"year":2021,"cited_by_count":60},{"year":2020,"cited_by_count":35},{"year":2019,"cited_by_count":35},{"year":2018,"cited_by_count":31},{"year":2017,"cited_by_count":30},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}