{"id":"https://openalex.org/W755046805","doi":"https://doi.org/10.1007/978-3-642-27645-3_7","title":"Reinforcement Learning in Continuous State and Action Spaces","display_name":"Reinforcement Learning in Continuous State and Action Spaces","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W755046805","doi":"https://doi.org/10.1007/978-3-642-27645-3_7","mag":"755046805"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-27645-3_7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-27645-3_7","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/A5033135596","display_name":"Hado van Hasselt","orcid":null},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Hado van Hasselt","raw_affiliation_strings":["Center for Mathematics and Computer Science, Centrum Wiskunde en Informatica CWI, Amsterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Center for Mathematics and Computer Science, Centrum Wiskunde en Informatica CWI, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I1341640284"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5033135596"],"corresponding_institution_ids":["https://openalex.org/I1341640284"],"apc_list":null,"apc_paid":null,"fwci":10.1501,"has_fulltext":false,"cited_by_count":188,"citation_normalized_percentile":{"value":0.9855467,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"207","last_page":"251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9876999855041504,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9302207827568054},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.614614725112915},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5834914445877075},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5759080648422241},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5517348051071167},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.509271502494812},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.49826669692993164},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.44658029079437256},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44531092047691345},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4340459108352661},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35604795813560486},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.29772233963012695},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.248752623796463},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15065452456474304},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.07326099276542664}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9302207827568054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.614614725112915},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5834914445877075},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5759080648422241},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5517348051071167},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.509271502494812},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.49826669692993164},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44658029079437256},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44531092047691345},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4340459108352661},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35604795813560486},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.29772233963012695},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.248752623796463},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15065452456474304},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.07326099276542664},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-642-27645-3_7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-27645-3_7","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":[{"id":"https://metadata.un.org/sdg/16","score":0.800000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":196,"referenced_works":["https://openalex.org/W13294968","https://openalex.org/W51508254","https://openalex.org/W60031785","https://openalex.org/W80219033","https://openalex.org/W86816279","https://openalex.org/W100327610","https://openalex.org/W166862392","https://openalex.org/W225768461","https://openalex.org/W355330432","https://openalex.org/W359568995","https://openalex.org/W1487586009","https://openalex.org/W1492186721","https://openalex.org/W1496855202","https://openalex.org/W1497256448","https://openalex.org/W1502364872","https://openalex.org/W1503196123","https://openalex.org/W1506832649","https://openalex.org/W1507222174","https://openalex.org/W1512383952","https://openalex.org/W1514587017","https://openalex.org/W1514875444","https://openalex.org/W1518539242","https://openalex.org/W1533179050","https://openalex.org/W1538558539","https://openalex.org/W1539670134","https://openalex.org/W1543217731","https://openalex.org/W1544598807","https://openalex.org/W1547105496","https://openalex.org/W1550698229","https://openalex.org/W1554663460","https://openalex.org/W1557517019","https://openalex.org/W1559956479","https://openalex.org/W1560688497","https://openalex.org/W1569296262","https://openalex.org/W1574700590","https://openalex.org/W1576660662","https://openalex.org/W1577352482","https://openalex.org/W1579744901","https://openalex.org/W1582436621","https://openalex.org/W1591803298","https://openalex.org/W1594783240","https://openalex.org/W1595483645","https://openalex.org/W1600046456","https://openalex.org/W1601081659","https://openalex.org/W1626155273","https://openalex.org/W1626977535","https://openalex.org/W1646707810","https://openalex.org/W1663973292","https://openalex.org/W1898259180","https://openalex.org/W1907796993","https://openalex.org/W1914583973","https://openalex.org/W1965227651","https://openalex.org/W1965555277","https://openalex.org/W1966517492","https://openalex.org/W1970511700","https://openalex.org/W1970789124","https://openalex.org/W1987187457","https://openalex.org/W1993740947","https://openalex.org/W1994923984","https://openalex.org/W1997543377","https://openalex.org/W2002592134","https://openalex.org/W2009086942","https://openalex.org/W2009303086","https://openalex.org/W2016589492","https://openalex.org/W2020009149","https://openalex.org/W2020609518","https://openalex.org/W2022306346","https://openalex.org/W2024303516","https://openalex.org/W2027648864","https://openalex.org/W2028145673","https://openalex.org/W2032856141","https://openalex.org/W2035808435","https://openalex.org/W2041367235","https://openalex.org/W2049287437","https://openalex.org/W2050838777","https://openalex.org/W2064018461","https://openalex.org/W2067259779","https://openalex.org/W2072931156","https://openalex.org/W2073258676","https://openalex.org/W2073384958","https://openalex.org/W2075268401","https://openalex.org/W2080233464","https://openalex.org/W2082261506","https://openalex.org/W2084840427","https://openalex.org/W2087480365","https://openalex.org/W2091565802","https://openalex.org/W2092070658","https://openalex.org/W2094387729","https://openalex.org/W2097451572","https://openalex.org/W2098432798","https://openalex.org/W2100677568","https://openalex.org/W2100752967","https://openalex.org/W2101539915","https://openalex.org/W2102295697","https://openalex.org/W2103019454","https://openalex.org/W2103626435","https://openalex.org/W2104753538","https://openalex.org/W2105563853","https://openalex.org/W2107726111","https://openalex.org/W2107977784","https://openalex.org/W2108596215","https://openalex.org/W2108682071","https://openalex.org/W2112036188","https://openalex.org/W2112449769","https://openalex.org/W2113913482","https://openalex.org/W2115211925","https://openalex.org/W2116339921","https://openalex.org/W2116459397","https://openalex.org/W2116850952","https://openalex.org/W2117341272","https://openalex.org/W2117812871","https://openalex.org/W2119053738","https://openalex.org/W2119567691","https://openalex.org/W2119717200","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2123859855","https://openalex.org/W2124175081","https://openalex.org/W2124776405","https://openalex.org/W2125523964","https://openalex.org/W2125612430","https://openalex.org/W2126410641","https://openalex.org/W2129670787","https://openalex.org/W2130801532","https://openalex.org/W2130990842","https://openalex.org/W2131600418","https://openalex.org/W2132351269","https://openalex.org/W2134042548","https://openalex.org/W2134140787","https://openalex.org/W2136064843","https://openalex.org/W2136495462","https://openalex.org/W2137104525","https://openalex.org/W2138537392","https://openalex.org/W2139418546","https://openalex.org/W2139465937","https://openalex.org/W2141559645","https://openalex.org/W2142916680","https://openalex.org/W2144446635","https://openalex.org/W2148067905","https://openalex.org/W2148948822","https://openalex.org/W2150355110","https://openalex.org/W2151012394","https://openalex.org/W2151416233","https://openalex.org/W2152195021","https://openalex.org/W2154549708","https://openalex.org/W2154987621","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2156909104","https://openalex.org/W2158091072","https://openalex.org/W2158316397","https://openalex.org/W2158907787","https://openalex.org/W2160279936","https://openalex.org/W2160561608","https://openalex.org/W2162401674","https://openalex.org/W2162813238","https://openalex.org/W2163712217","https://openalex.org/W2163913714","https://openalex.org/W2164145253","https://openalex.org/W2164858444","https://openalex.org/W2165905123","https://openalex.org/W2166160300","https://openalex.org/W2166843422","https://openalex.org/W2172968643","https://openalex.org/W2208154600","https://openalex.org/W2305205647","https://openalex.org/W2309755354","https://openalex.org/W2334782222","https://openalex.org/W2341171179","https://openalex.org/W2487144912","https://openalex.org/W2522381472","https://openalex.org/W2560674852","https://openalex.org/W2561675875","https://openalex.org/W2595840341","https://openalex.org/W2598912124","https://openalex.org/W2766736793","https://openalex.org/W2779378862","https://openalex.org/W2787259794","https://openalex.org/W2798500587","https://openalex.org/W2912565176","https://openalex.org/W3004042307","https://openalex.org/W3011120880","https://openalex.org/W3101822862","https://openalex.org/W3103182070","https://openalex.org/W3121926921","https://openalex.org/W4211007335","https://openalex.org/W4212774754","https://openalex.org/W4214717370","https://openalex.org/W4232335189","https://openalex.org/W4245296547","https://openalex.org/W4256451422","https://openalex.org/W4285719527","https://openalex.org/W4299401133","https://openalex.org/W4300944962","https://openalex.org/W4307347247","https://openalex.org/W4388297464"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2386410636","https://openalex.org/W2742483371","https://openalex.org/W4400868993","https://openalex.org/W2025663273","https://openalex.org/W3038962357","https://openalex.org/W2808418668","https://openalex.org/W2152445738","https://openalex.org/W3148138296","https://openalex.org/W4388937744"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":24},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":24},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}