{"id":"https://openalex.org/W114364418","doi":null,"title":"Error bounds for approximate value iteration","display_name":"Error bounds for approximate value iteration","publication_year":2005,"publication_date":"2005-07-09","ids":{"openalex":"https://openalex.org/W114364418","mag":"114364418"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.513.7791","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.513.7791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.aaai.org/Papers/AAAI/2005/AAAI05-159.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5006533777","display_name":"R\u00e9mi Munos","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210107641","display_name":"Centre de Math\u00e9matiques Appliqu\u00e9es de l'\u00c9cole polytechnique","ror":"https://ror.org/012e1xn46","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I142476485","https://openalex.org/I4210107641","https://openalex.org/I4210141950","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"R\u00e9mi Munos","raw_affiliation_strings":["CENTRE DE MATH\u00c9MATIQUES APPLIQU\u00c9ES ECOLE POLYTECHNIQUE, PALAISEAU CEDEX, FRANCE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CENTRE DE MATH\u00c9MATIQUES APPLIQU\u00c9ES ECOLE POLYTECHNIQUE, PALAISEAU CEDEX, FRANCE","institution_ids":["https://openalex.org/I142476485","https://openalex.org/I4210107641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006533777"],"corresponding_institution_ids":["https://openalex.org/I142476485","https://openalex.org/I4210107641"],"apc_list":null,"apc_paid":null,"fwci":2.3389,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.88270345,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1006","last_page":"1011"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9189000129699707,"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":0.9189000129699707,"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":0.07800000160932541,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.00039999998989515007,"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/approximate-value-iteration","display_name":"approximate value iteration","score":0.9990000128746033},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8809999823570251},{"id":"https://openalex.org/keywords/error-bounds","display_name":"error bounds","score":0.7649999856948853},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"supervised learning","score":0.6439999938011169},{"id":"https://openalex.org/keywords/bellman-operator","display_name":"Bellman operator","score":0.8399999737739563},{"id":"https://openalex.org/keywords/value-function-approximation","display_name":"value function approximation","score":0.7509999871253967},{"id":"https://openalex.org/keywords/approximation-power","display_name":"approximation power","score":0.6010000109672546}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7748352289199829},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.5845039486885071},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5773175954818726},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.5727481842041016},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5644002556800842},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5547595024108887},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5395424365997314},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5359400510787964},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.5285913944244385},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.48761311173439026},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.42971867322921753},{"id":"https://openalex.org/C145242015","wikidata":"https://www.wikidata.org/wiki/Q774123","display_name":"Approximation theory","level":2,"score":0.42678767442703247},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4224715828895569},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4142829179763794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35966697335243225},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3496381640434265},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34100407361984253},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09033748507499695},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.513.7791","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.513.7791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.aaai.org/Papers/AAAI/2005/AAAI05-159.pdf","raw_type":"text"},{"id":"mag:114364418","doi":null,"is_oa":false,"landing_page_url":"http://chercheurs.lille.inria.fr/~munos/papers/files/AAAI05-159.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306420577","display_name":"National Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"National Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1502893368","https://openalex.org/W1515851193","https://openalex.org/W1547105496","https://openalex.org/W1575592356","https://openalex.org/W1576452626","https://openalex.org/W1689445748","https://openalex.org/W1730555343","https://openalex.org/W1745373831","https://openalex.org/W2021302824","https://openalex.org/W2115755118","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2123737232","https://openalex.org/W2130005627","https://openalex.org/W2132096648","https://openalex.org/W2334782222","https://openalex.org/W3125826253"],"related_works":["https://openalex.org/W2012547817","https://openalex.org/W7099431763","https://openalex.org/W2128812357","https://openalex.org/W2507723477","https://openalex.org/W2127487139","https://openalex.org/W2134932665","https://openalex.org/W2097656225","https://openalex.org/W2921102909","https://openalex.org/W7096179269","https://openalex.org/W2110002798"],"abstract_inverted_index":{"Approximate":[0],"Value":[1],"Iteration":[2],"(AVI)":[3],"is":[4,38],"an":[5,44,120],"method":[6],"for":[7,102],"solving":[8],"a":[9,18,68],"Markov":[10],"Decision":[11],"Problem":[12],"by":[13,31,58],"making":[14],"successive":[15],"calls":[16],"to":[17,88,94],"supervised":[19],"learning":[20],"(SL)":[21],"algorithm.":[22,111],"Sequence":[23],"of":[24,54,70,75,92,108,116],"value":[25],"rep-resentations":[26],"Vn":[27,35],"are":[28,65],"processed":[29],"iteratively":[30],"Vn+1":[32],"=":[33,104],"AT":[34],"where":[36],"T":[37],"the":[39,49,52,55,59,62,76,90,95,109,114],"Bellman":[40],"operator":[41],"and":[42,61,86],"A":[43],"approximation":[45,77,96],"operator.":[46],"Bounds":[47],"on":[48,119],"error":[50],"between":[51],"performance":[53,91],"policies":[56],"induced":[57],"algorithm":[60],"optimal":[63,121],"policy":[64],"given":[66],"as":[67],"function":[69],"weighted":[71],"Lp-norms":[72],"(p":[73],"1)":[74],"errors.":[78],"The":[79],"results":[80],"extend":[81],"usual":[82],"analysis":[83],"in":[84,100],"L1-norm,":[85],"allow":[87],"relate":[89],"AVI":[93],"power":[97],"(usually":[98],"expressed":[99],"Lp-norm,":[101],"p":[103],"1":[105],"or":[106],"2)":[107],"SL":[110],"We":[112],"illustrate":[113],"tightness":[115],"these":[117],"bounds":[118],"replacement":[122],"problem.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":7},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}