{"id":"https://openalex.org/W169931978","doi":"https://doi.org/10.1007/978-3-642-27645-3_1","title":"Reinforcement Learning and Markov Decision Processes","display_name":"Reinforcement Learning and Markov Decision Processes","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W169931978","doi":"https://doi.org/10.1007/978-3-642-27645-3_1","mag":"169931978"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-27645-3_1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-27645-3_1","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-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/A5090948866","display_name":"Martijn van Otterlo","orcid":null},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Martijn van Otterlo","raw_affiliation_strings":[", Artificial Intelligence, Radboud University Nijmegen, B.02.30 Spinozagebouw, Montessorilaan 3, Nijmegen, 6500, Netherlands","Radboud University, Nijmegen, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":", Artificial Intelligence, Radboud University Nijmegen, B.02.30 Spinozagebouw, Montessorilaan 3, Nijmegen, 6500, Netherlands","institution_ids":["https://openalex.org/I145872427"]},{"raw_affiliation_string":"Radboud University, Nijmegen, The Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060596453","display_name":"Marco Wiering","orcid":"https://orcid.org/0000-0003-4331-7537"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marco Wiering","raw_affiliation_strings":["Department of Artificial Intelligence, University of Groningen, Groningen, The Netherlands","Fac. Mathematics &, Natural Sciences, University of Groningen, Nijenborgh 9, Groningen, 9747 AG, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, University of Groningen, Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]},{"raw_affiliation_string":"Fac. Mathematics &, Natural Sciences, University of Groningen, Nijenborgh 9, Groningen, 9747 AG, Netherlands","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5090948866"],"corresponding_institution_ids":["https://openalex.org/I145872427"],"apc_list":null,"apc_paid":null,"fwci":3.8073,"has_fulltext":false,"cited_by_count":616,"citation_normalized_percentile":{"value":0.9408498,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9732999801635742,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.9703999757766724,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8418116569519043},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8376388549804688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6883640885353088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5877238512039185},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5130133032798767},{"id":"https://openalex.org/keywords/situated","display_name":"Situated","score":0.4539957642555237},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4157696068286896},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4153575599193573},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1573127806186676}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8418116569519043},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8376388549804688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6883640885353088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5877238512039185},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5130133032798767},{"id":"https://openalex.org/C132829578","wikidata":"https://www.wikidata.org/wiki/Q581151","display_name":"Situated","level":2,"score":0.4539957642555237},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4157696068286896},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4153575599193573},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1573127806186676},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-642-27645-3_1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-27645-3_1","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-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W108082272","https://openalex.org/W139877375","https://openalex.org/W162907590","https://openalex.org/W600489529","https://openalex.org/W802219403","https://openalex.org/W1258105458","https://openalex.org/W1487219635","https://openalex.org/W1491843047","https://openalex.org/W1498254356","https://openalex.org/W1499697567","https://openalex.org/W1510283917","https://openalex.org/W1546167776","https://openalex.org/W1549353711","https://openalex.org/W1557517019","https://openalex.org/W1569054662","https://openalex.org/W1576452626","https://openalex.org/W1592402337","https://openalex.org/W1777239053","https://openalex.org/W1796544916","https://openalex.org/W1858844946","https://openalex.org/W1931792391","https://openalex.org/W1980035368","https://openalex.org/W1993430596","https://openalex.org/W1993711637","https://openalex.org/W2009303086","https://openalex.org/W2009533501","https://openalex.org/W2020609518","https://openalex.org/W2023797067","https://openalex.org/W2028145673","https://openalex.org/W2048226872","https://openalex.org/W2054726834","https://openalex.org/W2054940200","https://openalex.org/W2061504687","https://openalex.org/W2071311198","https://openalex.org/W2079247031","https://openalex.org/W2091565802","https://openalex.org/W2098432798","https://openalex.org/W2100677568","https://openalex.org/W2101915445","https://openalex.org/W2105757562","https://openalex.org/W2107726111","https://openalex.org/W2113043717","https://openalex.org/W2116708838","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2122410182","https://openalex.org/W2124175081","https://openalex.org/W2136719210","https://openalex.org/W2147670284","https://openalex.org/W2150339816","https://openalex.org/W2156737235","https://openalex.org/W2168024904","https://openalex.org/W2174803659","https://openalex.org/W2182044576","https://openalex.org/W2198041288","https://openalex.org/W2334782222","https://openalex.org/W2341171179","https://openalex.org/W2419990545","https://openalex.org/W2489939061","https://openalex.org/W2505362238","https://openalex.org/W2610686804","https://openalex.org/W2623293810","https://openalex.org/W2785592078","https://openalex.org/W2984109677","https://openalex.org/W3011120880","https://openalex.org/W3023407077","https://openalex.org/W3139377883","https://openalex.org/W3142468893","https://openalex.org/W4214717370","https://openalex.org/W4214807090","https://openalex.org/W4231832368","https://openalex.org/W4246515624","https://openalex.org/W4285719527","https://openalex.org/W4302574020","https://openalex.org/W4307347247","https://openalex.org/W6631189298"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W3168977894"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":70},{"year":2024,"cited_by_count":134},{"year":2023,"cited_by_count":102},{"year":2022,"cited_by_count":87},{"year":2021,"cited_by_count":78},{"year":2020,"cited_by_count":48},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":32},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}