{"id":"https://openalex.org/W50090763","doi":"https://doi.org/10.1007/978-3-319-11662-4_11","title":"Selecting Near-Optimal Approximate State Representations in Reinforcement Learning","display_name":"Selecting Near-Optimal Approximate State Representations in Reinforcement Learning","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W50090763","doi":"https://doi.org/10.1007/978-3-319-11662-4_11","mag":"50090763"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-11662-4_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-11662-4_11","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/A5031149136","display_name":"Ronald Ortner","orcid":"https://orcid.org/0000-0001-6033-2208"},"institutions":[{"id":"https://openalex.org/I182712176","display_name":"Montanuniversit\u00e4t Leoben","ror":"https://ror.org/02fhfw393","country_code":"AT","type":"education","lineage":["https://openalex.org/I182712176"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Ronald Ortner","raw_affiliation_strings":["Montanuniversitaet Leoben, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Montanuniversitaet Leoben, Austria","institution_ids":["https://openalex.org/I182712176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055126334","display_name":"Odalric-Ambrym Maillard","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Odalric-Ambrym Maillard","raw_affiliation_strings":["The Technion, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Technion, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064627349","display_name":"Daniil Ryabko","orcid":"https://orcid.org/0000-0001-5080-9930"},"institutions":[{"id":"https://openalex.org/I4210128776","display_name":"Inria Chile","ror":"https://ror.org/03c3zes23","country_code":"CL","type":"facility","lineage":["https://openalex.org/I4210128776"]},{"id":"https://openalex.org/I4210138412","display_name":"Centre Inria de l'Universit\u00e9 de Lille","ror":"https://ror.org/04eej9726","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210138412"]}],"countries":["CL","FR"],"is_corresponding":false,"raw_author_name":"Daniil Ryabko","raw_affiliation_strings":["Inria Lille-Nord Europe, \u00e9quipe SequeL, France","Inria, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria Lille-Nord Europe, \u00e9quipe SequeL, France","institution_ids":["https://openalex.org/I4210138412"]},{"raw_affiliation_string":"Inria, Chile","institution_ids":["https://openalex.org/I4210128776"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.4484,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.81165667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"140","last_page":"154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9973999857902527,"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"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9912999868392944,"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":0.8710372447967529},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.8355578184127808},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7983794808387756},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7962223887443542},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6018812656402588},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5054707527160645},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4954115152359009},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.47450679540634155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4432083070278168},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4384850859642029},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3877623379230499},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3751494586467743},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2718004584312439},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22047469019889832},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14866122603416443}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8710372447967529},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8355578184127808},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7983794808387756},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7962223887443542},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6018812656402588},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5054707527160645},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4954115152359009},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.47450679540634155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4432083070278168},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4384850859642029},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3877623379230499},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3751494586467743},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2718004584312439},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22047469019889832},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14866122603416443},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-319-11662-4_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-11662-4_11","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":[{"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":10,"referenced_works":["https://openalex.org/W1509780496","https://openalex.org/W1662803991","https://openalex.org/W1850488217","https://openalex.org/W1968653071","https://openalex.org/W2118693324","https://openalex.org/W2137125320","https://openalex.org/W2146911536","https://openalex.org/W2156738026","https://openalex.org/W2158282517","https://openalex.org/W2951333509"],"related_works":["https://openalex.org/W4292701710","https://openalex.org/W4287863949","https://openalex.org/W4287102143","https://openalex.org/W1850488217","https://openalex.org/W2970347269","https://openalex.org/W3096874164","https://openalex.org/W2357975469","https://openalex.org/W2937181779","https://openalex.org/W2145363145","https://openalex.org/W3168977894"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}