{"id":"https://openalex.org/W2101786389","doi":"https://doi.org/10.1007/978-3-642-27645-3","title":"Reinforcement Learning","display_name":"Reinforcement Learning","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2101786389","doi":"https://doi.org/10.1007/978-3-642-27645-3","mag":"2101786389"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-27645-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-27645-3","pdf_url":null,"source":{"id":"https://openalex.org/S4210169857","display_name":"Adaptation, learning, and optimization","issn_l":"1867-4534","issn":["1867-4534","1867-4542"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptation, Learning, and Optimization","raw_type":"book"},"type":"book","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/A5060596453","display_name":"Marco Wiering","orcid":"https://orcid.org/0000-0003-4331-7537"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wiering, Marco","raw_affiliation_strings":["Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090948866","display_name":"Martijn van Otterlo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"van Otterlo, Martijn","raw_affiliation_strings":["Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.5679,"has_fulltext":false,"cited_by_count":675,"citation_normalized_percentile":{"value":0.97752809,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11810","display_name":"Complex Systems and Decision Making","score":0.3343000113964081,"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"}},"topics":[{"id":"https://openalex.org/T11810","display_name":"Complex Systems and Decision Making","score":0.3343000113964081,"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":0.8143860101699829},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.7706713676452637},{"id":"https://openalex.org/keywords/adaptive-behavior","display_name":"Adaptive behavior","score":0.42213425040245056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36928266286849976},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3466168940067291},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.31249725818634033},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.11144140362739563}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8143860101699829},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.7706713676452637},{"id":"https://openalex.org/C68784500","wikidata":"https://www.wikidata.org/wiki/Q1570691","display_name":"Adaptive behavior","level":2,"score":0.42213425040245056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36928266286849976},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3466168940067291},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.31249725818634033},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.11144140362739563}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/978-3-642-27645-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-27645-3","pdf_url":null,"source":{"id":"https://openalex.org/S4210169857","display_name":"Adaptation, learning, and optimization","issn_l":"1867-4534","issn":["1867-4534","1867-4542"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptation, Learning, and Optimization","raw_type":"book"},{"id":"pmh:oai:cds.cern.ch:1488063","is_oa":false,"landing_page_url":"http://cds.cern.ch/record/1488063","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":""},{"id":"pmh:oai:dial.uclouvain.be:ebook:34552","is_oa":false,"landing_page_url":"http://hdl.handle.net/2078/ebook:34552","pdf_url":null,"source":{"id":"https://openalex.org/S4306401902","display_name":"Digital Access to Libraries (Universit\u00e9 catholique de Louvain (UCL), l'Universit\u00e9 de Namur (UNamur) and the Universit\u00e9 Saint-Louis (USL-B))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I95674353","host_organization_name":"UCLouvain","host_organization_lineage":["https://openalex.org/I95674353"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:rug:oai:pure.rug.nl:publications/d1afac99-aad5-4818-8c9d-47063c7109df","is_oa":false,"landing_page_url":"https://research.rug.nl/en/publications/d1afac99-aad5-4818-8c9d-47063c7109df","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/book"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W103885025","https://openalex.org/W158722652","https://openalex.org/W1231217497","https://openalex.org/W1549543673","https://openalex.org/W1990593743","https://openalex.org/W2134197408","https://openalex.org/W2174817438","https://openalex.org/W2270477652","https://openalex.org/W2511088267","https://openalex.org/W2586680856"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2076061571","https://openalex.org/W2106552856","https://openalex.org/W1987513656","https://openalex.org/W2072376847"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":75},{"year":2024,"cited_by_count":55},{"year":2023,"cited_by_count":86},{"year":2022,"cited_by_count":77},{"year":2021,"cited_by_count":60},{"year":2020,"cited_by_count":40},{"year":2019,"cited_by_count":46},{"year":2018,"cited_by_count":47},{"year":2017,"cited_by_count":41},{"year":2016,"cited_by_count":42},{"year":2015,"cited_by_count":36},{"year":2014,"cited_by_count":27},{"year":2013,"cited_by_count":21},{"year":2012,"cited_by_count":8}],"updated_date":"2026-06-14T07:44:22.658603","created_date":"2016-06-24T00:00:00"}