{"id":"https://openalex.org/W2397607997","doi":null,"title":"Analysis of Classification-based Policy Iteration Algorithms","display_name":"Analysis of Classification-based Policy Iteration Algorithms","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2397607997","mag":"2397607997"},"language":"en","primary_location":{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/24626","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/24626","pdf_url":"http://hdl.handle.net/20.500.12210/24626","source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'\u00c9tudes en Civilisations, Langues et Lettres \u00c9trang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.12210/24626","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014791481","display_name":"Alessandro Lazaric","orcid":"https://orcid.org/0000-0002-8970-413X","observed_orcids":["https://orcid.org/0000-0002-8970-413X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lazaric, Alessandro","raw_affiliation_strings":["SEQUEL - Sequential Learning (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SEQUEL - Sequential Learning (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013843778","display_name":"Mohammad Ghavamzadeh","orcid":"https://orcid.org/0000-0003-0930-8688","observed_orcids":["https://orcid.org/0000-0003-0930-8688"]},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ghavamzadeh, Mohammad","raw_affiliation_strings":["Adobe Advanced Technology Labs - Adobe Systems Inc. (United States)","SEQUEL - Sequential Learning (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Advanced Technology Labs - Adobe Systems Inc. (United States)","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"SEQUEL - Sequential Learning (France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006533777","display_name":"R\u00e9mi Munos","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Munos, R\u00e9mi","raw_affiliation_strings":["DeepMind [London] (United Kingdom)","SEQUEL - Sequential Learning (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind [London] (United Kingdom)","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"SEQUEL - Sequential Learning (France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9028,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.88029738,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"17","issue":null,"first_page":"1","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9951000213623047,"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":0.9951000213623047,"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":0.0027000000700354576,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0012000000569969416,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/finite-sample-analysis","display_name":"finite-sample analysis","score":0.9419999718666077},{"id":"https://openalex.org/keywords/consistency","display_name":"consistency","score":0.5799999833106995},{"id":"https://openalex.org/keywords/reinforcement-learning-algorithms","display_name":"reinforcement learning algorithms","score":0.531000018119812}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.6849093437194824},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5942233800888062},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.565407931804657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5126199126243591},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4992530345916748},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4243414103984833},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4163145422935486},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41460278630256653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21080899238586426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1754438281059265},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1338193714618683},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.11770546436309814},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/24626","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/24626","pdf_url":"http://hdl.handle.net/20.500.12210/24626","source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'\u00c9tudes en Civilisations, Langues et Lettres \u00c9trang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:HAL:hal-01401513v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01401513","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Machine Learning Research, 2016, 17, pp.1 - 30","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/24626","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/24626","pdf_url":"http://hdl.handle.net/20.500.12210/24626","source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'\u00c9tudes en Civilisations, Langues et Lettres \u00c9trang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1729111207","display_name":"Extraction and Transfer of Knowledge in Reinforcement Learning","funder_award_id":"ANR-14-CE24-0010","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320322727","display_name":"Minist\u00e8re de l'Education Nationale, de l'Enseignement Superieur et de la Recherche","ror":"https://ror.org/03sjk9a61"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2397607997.pdf","grobid_xml":"https://content.openalex.org/works/W2397607997.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W55145144","https://openalex.org/W55778226","https://openalex.org/W56894658","https://openalex.org/W107583932","https://openalex.org/W1484867920","https://openalex.org/W1526641569","https://openalex.org/W1564947197","https://openalex.org/W1573195610","https://openalex.org/W1575592356","https://openalex.org/W1600830292","https://openalex.org/W1878054055","https://openalex.org/W2003603259","https://openalex.org/W2010029425","https://openalex.org/W2012547817","https://openalex.org/W2025263811","https://openalex.org/W2028145673","https://openalex.org/W2037199950","https://openalex.org/W2058239479","https://openalex.org/W2072931156","https://openalex.org/W2104753538","https://openalex.org/W2106191340","https://openalex.org/W2109301240","https://openalex.org/W2117355432","https://openalex.org/W2123917165","https://openalex.org/W2128547596","https://openalex.org/W2128812357","https://openalex.org/W2130005627","https://openalex.org/W2130599357","https://openalex.org/W2131490088","https://openalex.org/W2133435356","https://openalex.org/W2134289401","https://openalex.org/W2138663952","https://openalex.org/W2142261479","https://openalex.org/W2148603752","https://openalex.org/W2150821861","https://openalex.org/W2165060096","https://openalex.org/W2165421048","https://openalex.org/W2181692883"],"related_works":["https://openalex.org/W7099069081","https://openalex.org/W7097710430","https://openalex.org/W2509789900","https://openalex.org/W2165060096","https://openalex.org/W55778226","https://openalex.org/W7098870203","https://openalex.org/W7100055089","https://openalex.org/W7017144453","https://openalex.org/W2103568863","https://openalex.org/W2181692883"],"abstract_inverted_index":{"We":[0,155],"introduce":[1],"a":[2,13,49,56,85,111,166],"variant":[3],"of":[4,32,37,61,64,70,78,105,160,168],"the":[5,27,30,33,38,42,62,68,76,79,92,114,128,143,158,161],"classification-based":[6,121,131],"approach":[7],"to":[8,103,139],"policy":[9,65,81,93,122,132,169],"iteration":[10,123,133],"which":[11,88],"uses":[12],"cost-sensitive":[14],"loss":[15],"function":[16],"weighting":[17],"each":[18,74],"classification":[19],"mistake":[20],"by":[21,41],"its":[22,106],"actual":[23],"regret,":[24],"that":[25,98,130],"is,":[26],"difference":[28],"between":[29,113],"action-value":[31],"greedy":[34,100],"action":[35,39],"and":[36,84,116],"chosen":[40],"classifier.":[43],"For":[44],"this":[45,120],"algorithm,":[46],"we":[47],"provide":[48],"full":[50],"finite-sample":[51],"analysis.":[52],"Our":[53],"results":[54],"state":[55],"performance":[57],"bound":[58],"in":[59,73,119],"terms":[60],"number":[63,69],"improvement":[66],"steps,":[67],"rollouts":[71],"used":[72],"iteration,":[75],"capacity":[77,86],"considered":[80],"space":[82,94],"(classifier),":[83],"measure":[87],"indicates":[89],"how":[90],"well":[91],"can":[95,145],"approximate":[96],"policies":[97,144],"are":[99],"with":[101,171],"respect":[102],"any":[104],"members.":[107],"The":[108],"analysis":[109],"reveals":[110],"tradeoff":[112],"estimation":[115],"approximation":[117],"errors":[118],"setting.":[124],"Furthermore":[125],"it":[126],"confirms":[127],"intuition":[129],"algorithms":[134],"could":[135],"be":[136,146],"favorably":[137],"compared":[138],"value-based":[140],"approaches":[141],"when":[142,163],"approximated":[147],"more":[148],"easily":[149],"than":[150],"their":[151],"corresponding":[152],"value":[153],"functions.":[154],"also":[156],"study":[157],"consistency":[159],"algorithm":[162],"there":[164],"exists":[165],"sequence":[167],"spaces":[170],"increasing":[172],"capacity.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}