{"id":"https://openalex.org/W1848006316","doi":"https://doi.org/10.1007/978-3-642-04921-7_37","title":"Improving Optimistic Exploration in Model-Free Reinforcement Learning","display_name":"Improving Optimistic Exploration in Model-Free Reinforcement Learning","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W1848006316","doi":"https://doi.org/10.1007/978-3-642-04921-7_37","mag":"1848006316"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-04921-7_37","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-04921-7_37","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","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/A5052315074","display_name":"Marek Grze\u015b","orcid":null},"institutions":[{"id":"https://openalex.org/I52099693","display_name":"University of York","ror":"https://ror.org/04m01e293","country_code":"GB","type":"education","lineage":["https://openalex.org/I52099693"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Marek Grze\u015b","raw_affiliation_strings":["Department of Computer Science, University of York, Heslington, York, YO10 5DD, United Kingdom","Department of Computer Science, University of York, Heslington York, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of York, Heslington, York, YO10 5DD, United Kingdom","institution_ids":["https://openalex.org/I52099693"]},{"raw_affiliation_string":"Department of Computer Science, University of York, Heslington York, United Kingdom","institution_ids":["https://openalex.org/I52099693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009587907","display_name":"Daniel Kudenko\u22c6","orcid":"https://orcid.org/0000-0003-3359-3255"},"institutions":[{"id":"https://openalex.org/I52099693","display_name":"University of York","ror":"https://ror.org/04m01e293","country_code":"GB","type":"education","lineage":["https://openalex.org/I52099693"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniel Kudenko","raw_affiliation_strings":["Department of Computer Science, University of York, Heslington, York, YO10 5DD, United Kingdom","Department of Computer Science, University of York, Heslington York, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of York, Heslington, York, YO10 5DD, United Kingdom","institution_ids":["https://openalex.org/I52099693"]},{"raw_affiliation_string":"Department of Computer Science, University of York, Heslington York, United Kingdom","institution_ids":["https://openalex.org/I52099693"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052315074"],"corresponding_institution_ids":["https://openalex.org/I52099693"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.2894,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.595295,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"360","last_page":"369"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9822999835014343,"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/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9650999903678894,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8968944549560547},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8646652102470398},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5757501125335693},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5543333292007446},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5534157156944275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5415587425231934},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5193601846694946},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.48114097118377686},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.45506948232650757},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35531795024871826},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.24215015769004822},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21861660480499268},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06269186735153198}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8968944549560547},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8646652102470398},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5757501125335693},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5543333292007446},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5534157156944275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5415587425231934},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5193601846694946},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.48114097118377686},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.45506948232650757},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35531795024871826},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.24215015769004822},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21861660480499268},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06269186735153198},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-642-04921-7_37","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-04921-7_37","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W584392662","https://openalex.org/W1487219635","https://openalex.org/W1491843047","https://openalex.org/W1504212531","https://openalex.org/W1515851193","https://openalex.org/W1515933446","https://openalex.org/W1540659332","https://openalex.org/W1576452626","https://openalex.org/W1716849269","https://openalex.org/W1987187457","https://openalex.org/W2085575316","https://openalex.org/W2100677568","https://openalex.org/W2107726111","https://openalex.org/W2121863487","https://openalex.org/W2122410182","https://openalex.org/W2144744117","https://openalex.org/W2168319199","https://openalex.org/W4210551050","https://openalex.org/W4214717370","https://openalex.org/W4214807090","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W3099153698","https://openalex.org/W4297873223","https://openalex.org/W3009457412","https://openalex.org/W2350784623"],"abstract_inverted_index":null,"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
