{"id":"https://openalex.org/W2012547817","doi":"https://doi.org/10.1137/040614384","title":"Performance Bounds in $L_p$\u2010norm for Approximate Value Iteration","display_name":"Performance Bounds in $L_p$\u2010norm for Approximate Value Iteration","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2012547817","doi":"https://doi.org/10.1137/040614384","mag":"2012547817"},"language":"en","primary_location":{"id":"doi:10.1137/040614384","is_oa":false,"landing_page_url":"https://doi.org/10.1137/040614384","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Control and Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/inria-00124685","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006533777","display_name":"R\u00e9mi Munos","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"R\u00e9mi Munos","raw_affiliation_strings":["Sequential Learning"],"affiliations":[{"raw_affiliation_string":"Sequential Learning","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5006533777"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.3126,"has_fulltext":false,"cited_by_count":107,"citation_normalized_percentile":{"value":0.95320169,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"46","issue":"2","first_page":"541","last_page":"561"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9998000264167786,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9998000264167786,"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/T11236","display_name":"Control Systems and Identification","score":0.9979000091552734,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.8254347443580627},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.6240926384925842},{"id":"https://openalex.org/keywords/approximation-error","display_name":"Approximation error","score":0.5158235430717468},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4833966791629791},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.47711971402168274},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.45784705877304077},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4434024691581726},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3932093679904938},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.390977144241333},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.37690305709838867},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.3753703534603119},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3000912070274353},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12947461009025574},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.10026618838310242}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.8254347443580627},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.6240926384925842},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.5158235430717468},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4833966791629791},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.47711971402168274},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45784705877304077},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4434024691581726},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3932093679904938},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.390977144241333},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.37690305709838867},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3753703534603119},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3000912070274353},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12947461009025574},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.10026618838310242},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1137/040614384","is_oa":false,"landing_page_url":"https://doi.org/10.1137/040614384","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Control and Optimization","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.466.4205","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.466.4205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.archives-ouvertes.fr/docs/00/12/46/85/PDF/avi_siam_final.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.643.3396","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.643.3396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/~pabbeel/cs287-fa09/readings/Munos-avi-siam.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00124685v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00124685","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"SIAM Journal on Control and Optimization, 2007, 46 (2), pp.541-561. ⟨10.1137/040614384⟩","raw_type":"Journal articles"}],"best_oa_location":{"id":"pmh:oai:HAL:inria-00124685v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00124685","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"SIAM Journal on Control and Optimization, 2007, 46 (2), pp.541-561. ⟨10.1137/040614384⟩","raw_type":"Journal articles"},"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W107583932","https://openalex.org/W183991413","https://openalex.org/W1502893368","https://openalex.org/W1506832649","https://openalex.org/W1545148916","https://openalex.org/W1547105496","https://openalex.org/W1575592356","https://openalex.org/W1689445748","https://openalex.org/W1730555343","https://openalex.org/W1745373831","https://openalex.org/W1966294600","https://openalex.org/W2010029425","https://openalex.org/W2021302824","https://openalex.org/W2078935796","https://openalex.org/W2115755118","https://openalex.org/W2121863487","https://openalex.org/W2123737232","https://openalex.org/W2132096648","https://openalex.org/W2139418546","https://openalex.org/W2148603752","https://openalex.org/W2329923236","https://openalex.org/W2341171179","https://openalex.org/W3125826253","https://openalex.org/W3198350258","https://openalex.org/W4231428347","https://openalex.org/W4247446124","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2161367706","https://openalex.org/W3013781205","https://openalex.org/W2156992384","https://openalex.org/W3174740571","https://openalex.org/W91039700","https://openalex.org/W2570542232","https://openalex.org/W2169324952","https://openalex.org/W2528400528","https://openalex.org/W2962728842","https://openalex.org/W1608462400"],"abstract_inverted_index":{"Approximate":[0],"value":[1,17,23],"iteration":[2],"(AVI)":[3],"is":[4,36,149],"a":[5,20,51,90,150,175,188],"method":[6],"for":[7],"solving":[8],"large":[9],"Markov":[10],"decision":[11],"problems":[12],"by":[13,50,74,165],"approximating":[14],"the":[15,30,37,59,69,75,110,124,129,133,138,154,161,166,182,194,202,206,211,214],"optimal":[16,218],"function":[18,24,91],"with":[19],"sequence":[21],"of":[22,62,68,113,126,132,143,153,160,196,213],"representations":[25],"$V_n$":[26],"processed":[27],"according":[28],"to":[29,115,121,128,192],"iterations":[31],"$V_{n+1}=\\mathcal{AT}":[32],"V_n$,":[33],"where":[34],"$\\mathcal{T}$":[35],"so\u2010called":[38],"Bellman":[39],"operator":[40],"and":[41,140],"$\\mathcal{A}$":[42],"an":[43,97,217],"approximation":[44,71,99,130],"operator,":[45],"which":[46,118],"may":[47],"be":[48],"implemented":[49],"supervised":[52],"learning":[53],"(SL)":[54],"algorithm.":[55,77],"Usual":[56],"bounds":[57,112,215],"on":[58,216],"asymptotic":[60],"performance":[61,111,125,151,195],"AVI":[63,114,127,197],"are":[64],"established":[65],"in":[66,101,158,205],"terms":[67,159],"$L_\\infty$\u2010norm":[70],"errors":[72,163],"induced":[73],"SL":[76,82,134],"However,":[78],"most":[79],"widely":[80],"used":[81,191,204],"algorithms":[83],"(such":[84],"as":[85],"least":[86],"squares":[87],"regression)":[88],"return":[89],"(the":[92],"best":[93],"fit)":[94],"that":[95,178],"minimizes":[96],"empirical":[98],"error":[100],"$L_p$\u2010norm":[102,162],"($p\\geq":[103],"1$).":[104],"In":[105],"this":[106],"paper,":[107],"we":[108],"extend":[109],"weighted":[116],"$L_p$\u2010norms,":[117],"enables":[119],"us":[120],"directly":[122],"relate":[123],"power":[131],"algorithm,":[135],"hence":[136],"assuring":[137],"tightness":[139,212],"practical":[141],"relevance":[142],"these":[144],"bounds.":[145],"The":[146,169],"main":[147],"result":[148],"bound":[152,171],"resulting":[155],"policies":[156],"expressed":[157],"introduced":[164],"successive":[167],"approximations.":[168],"new":[170],"takes":[172],"into":[173],"account":[174],"concentration":[176],"coefficient":[177],"estimates":[179],"how":[180],"much":[181],"discounted":[183],"future\u2010state":[184],"distributions":[185],"starting":[186],"from":[187,201],"probability":[189],"measure":[190],"assess":[193],"can":[198],"possibly":[199],"differ":[200],"distribution":[203],"regression":[207],"operation.":[208],"We":[209],"illustrate":[210],"replacement":[219],"problem.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}