{"id":"https://openalex.org/W1979308911","doi":"https://doi.org/10.1007/s10489-012-0412-6","title":"Learning via human feedback in continuous state and action spaces","display_name":"Learning via human feedback in continuous state and action spaces","publication_year":2013,"publication_date":"2013-02-01","ids":{"openalex":"https://openalex.org/W1979308911","doi":"https://doi.org/10.1007/s10489-012-0412-6","mag":"1979308911"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-012-0412-6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-012-0412-6","pdf_url":null,"source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"},"type":"article","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/A5043775193","display_name":"Ngo Anh Vien","orcid":"https://orcid.org/0000-0001-9646-267X"},"institutions":[{"id":"https://openalex.org/I24227732","display_name":"University of Applied Sciences Ravensburg-Weingarten","ror":"https://ror.org/00s4rmz74","country_code":"DE","type":"education","lineage":["https://openalex.org/I24227732"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Ngo Anh Vien","raw_affiliation_strings":["Institute of Artificial Intelligence, Ravensburg-Weingarten University of Applied Sciences, Weingarten, 88250, Germany","Institute of Artificial Intelligence, Ravensburg-Weingarten University of Applied Sciences, Weingarten, Germany 88250#TAB#"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Ravensburg-Weingarten University of Applied Sciences, Weingarten, 88250, Germany","institution_ids":["https://openalex.org/I24227732"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Ravensburg-Weingarten University of Applied Sciences, Weingarten, Germany 88250#TAB#","institution_ids":["https://openalex.org/I24227732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016544515","display_name":"Wolfgang Ertel","orcid":"https://orcid.org/0009-0005-8967-3766"},"institutions":[{"id":"https://openalex.org/I24227732","display_name":"University of Applied Sciences Ravensburg-Weingarten","ror":"https://ror.org/00s4rmz74","country_code":"DE","type":"education","lineage":["https://openalex.org/I24227732"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang Ertel","raw_affiliation_strings":["Institute of Artificial Intelligence, Ravensburg-Weingarten University of Applied Sciences, Weingarten, 88250, Germany","Institute of Artificial Intelligence, Ravensburg-Weingarten University of Applied Sciences, Weingarten, Germany 88250#TAB#"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Ravensburg-Weingarten University of Applied Sciences, Weingarten, 88250, Germany","institution_ids":["https://openalex.org/I24227732"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Ravensburg-Weingarten University of Applied Sciences, Weingarten, Germany 88250#TAB#","institution_ids":["https://openalex.org/I24227732"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111474615","display_name":"Tae Choong Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tae Choong Chung","raw_affiliation_strings":["Department of Computer Engineering, Kyung Hee University, Seoul, South Korea","Dept. of Comput. Engg., Kyung Hee Univ., Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Kyung Hee University, Seoul, South Korea","institution_ids":["https://openalex.org/I35928602"]},{"raw_affiliation_string":"Dept. of Comput. Engg., Kyung Hee Univ., Seoul, South Korea","institution_ids":["https://openalex.org/I35928602"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043775193"],"corresponding_institution_ids":["https://openalex.org/I24227732"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":5.9723,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.95840732,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":"39","issue":"2","first_page":"267","last_page":"278"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"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":0.9976000189781189,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8584405779838562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8304081559181213},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6655839681625366},{"id":"https://openalex.org/keywords/trainer","display_name":"Trainer","score":0.5392976403236389},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5107753276824951},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.487396776676178},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.48496556282043457},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.45975399017333984},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.37935638427734375},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2815907597541809},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11450168490409851}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8584405779838562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8304081559181213},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6655839681625366},{"id":"https://openalex.org/C2780463512","wikidata":"https://www.wikidata.org/wiki/Q15122700","display_name":"Trainer","level":2,"score":0.5392976403236389},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5107753276824951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.487396776676178},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.48496556282043457},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45975399017333984},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.37935638427734375},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2815907597541809},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11450168490409851},{"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10489-012-0412-6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-012-0412-6","pdf_url":null,"source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/54d98fd1-f271-4668-879f-446bc5267bdc","is_oa":false,"landing_page_url":"https://pure.qub.ac.uk/en/publications/54d98fd1-f271-4668-879f-446bc5267bdc","pdf_url":null,"source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ngo, V, Ertel, W & Chung, T 2013, 'Learning via human feedback in continuous state and action spaces', Applied Intelligence, vol. 39, no. 2, pp. 267-278. https://doi.org/10.1007/s10489-012-0412-6","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W8222043","https://openalex.org/W107548292","https://openalex.org/W121023703","https://openalex.org/W309123013","https://openalex.org/W354832773","https://openalex.org/W564530069","https://openalex.org/W1483373940","https://openalex.org/W1515851193","https://openalex.org/W1539975474","https://openalex.org/W1541084404","https://openalex.org/W1557517019","https://openalex.org/W1585546214","https://openalex.org/W1883625788","https://openalex.org/W1951419471","https://openalex.org/W1966980013","https://openalex.org/W1971681797","https://openalex.org/W1985921566","https://openalex.org/W1999874108","https://openalex.org/W2009303086","https://openalex.org/W2012392077","https://openalex.org/W2013649454","https://openalex.org/W2022111686","https://openalex.org/W2041367235","https://openalex.org/W2046727971","https://openalex.org/W2054940200","https://openalex.org/W2056588157","https://openalex.org/W2070678636","https://openalex.org/W2091565802","https://openalex.org/W2094387729","https://openalex.org/W2098584016","https://openalex.org/W2099001564","https://openalex.org/W2103626435","https://openalex.org/W2105656578","https://openalex.org/W2110064869","https://openalex.org/W2116157560","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2131600418","https://openalex.org/W2144366468","https://openalex.org/W2154549708","https://openalex.org/W2155027007","https://openalex.org/W2156869222","https://openalex.org/W2158462832","https://openalex.org/W2169022337","https://openalex.org/W2219171079","https://openalex.org/W2294422333","https://openalex.org/W2492794003","https://openalex.org/W2602256192","https://openalex.org/W2787259794","https://openalex.org/W3198350258","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W1866966336","https://openalex.org/W1985489398","https://openalex.org/W638029546","https://openalex.org/W4285792946","https://openalex.org/W4388176369","https://openalex.org/W2920061524","https://openalex.org/W2000494260","https://openalex.org/W154293939","https://openalex.org/W2035734194","https://openalex.org/W2046935328"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}