{"id":"https://openalex.org/W2621122412","doi":"https://doi.org/10.3233/rda-160116","title":"Estimate and approximate policy iteration algorithm for discounted Markov decision models with bounded costs and Borel spaces","display_name":"Estimate and approximate policy iteration algorithm for discounted Markov decision models with bounded costs and Borel spaces","publication_year":2017,"publication_date":"2017-05-31","ids":{"openalex":"https://openalex.org/W2621122412","doi":"https://doi.org/10.3233/rda-160116","mag":"2621122412"},"language":"en","primary_location":{"id":"doi:10.3233/rda-160116","is_oa":false,"landing_page_url":"https://doi.org/10.3233/rda-160116","pdf_url":null,"source":{"id":"https://openalex.org/S2764680446","display_name":"Risk and Decision Analysis","issn_l":"1569-7371","issn":["1569-7371","1875-9173"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Risk and Decision Analysis","raw_type":"journal-article"},"type":"article","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/A5051670491","display_name":"M. Teresa Robles-Alcar\u00e1z","orcid":null},"institutions":[{"id":"https://openalex.org/I4061448","display_name":"Universidad de Sonora","ror":"https://ror.org/00c32gy34","country_code":"MX","type":"education","lineage":["https://openalex.org/I4061448"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"M. Teresa Robles-Alcar\u00e1z","raw_affiliation_strings":["Departamento de Matem\u00e1ticas, Universidad de Sonora, Rosales s/n, Col. Centro, 83000 Hermosillo, Sonora, Mexico"],"affiliations":[{"raw_affiliation_string":"Departamento de Matem\u00e1ticas, Universidad de Sonora, Rosales s/n, Col. Centro, 83000 Hermosillo, Sonora, Mexico","institution_ids":["https://openalex.org/I4061448"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044644205","display_name":"\u00d3scar Vega-Amaya","orcid":"https://orcid.org/0000-0002-8669-5784"},"institutions":[{"id":"https://openalex.org/I4061448","display_name":"Universidad de Sonora","ror":"https://ror.org/00c32gy34","country_code":"MX","type":"education","lineage":["https://openalex.org/I4061448"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"\u00d3scar Vega-Amaya","raw_affiliation_strings":["Departamento de Matem\u00e1ticas, Universidad de Sonora, Rosales s/n, Col. Centro, 83000 Hermosillo, Sonora, Mexico"],"affiliations":[{"raw_affiliation_string":"Departamento de Matem\u00e1ticas, Universidad de Sonora, Rosales s/n, Col. Centro, 83000 Hermosillo, Sonora, Mexico","institution_ids":["https://openalex.org/I4061448"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065340719","display_name":"J. Adolfo Minj\u00e1rez\u2010Sosa","orcid":"https://orcid.org/0000-0002-3453-4508"},"institutions":[{"id":"https://openalex.org/I4061448","display_name":"Universidad de Sonora","ror":"https://ror.org/00c32gy34","country_code":"MX","type":"education","lineage":["https://openalex.org/I4061448"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"J. Adolfo Minj\u00e1rez-Sosa","raw_affiliation_strings":["Departamento de Matem\u00e1ticas, Universidad de Sonora, Rosales s/n, Col. Centro, 83000 Hermosillo, Sonora, Mexico"],"affiliations":[{"raw_affiliation_string":"Departamento de Matem\u00e1ticas, Universidad de Sonora, Rosales s/n, Col. Centro, 83000 Hermosillo, Sonora, Mexico","institution_ids":["https://openalex.org/I4061448"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065340719"],"corresponding_institution_ids":["https://openalex.org/I4061448"],"apc_list":null,"apc_paid":null,"fwci":0.6192,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75183115,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"6","issue":"2","first_page":"79","last_page":"95"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965999722480774,"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":0.9965999722480774,"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":0.9710000157356262,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10603","display_name":"Smart Grid Energy Management","score":0.9661999940872192,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.717023491859436},{"id":"https://openalex.org/keywords/multilinear-map","display_name":"Multilinear map","score":0.6765937805175781},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5739195346832275},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4796350598335266},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.4520461857318878},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.4447063207626343},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4201074540615082},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.41649556159973145},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4103657901287079},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39823639392852783},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3954111635684967},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2179017961025238},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.19596093893051147},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09841617941856384},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.07832911610603333}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.717023491859436},{"id":"https://openalex.org/C84392682","wikidata":"https://www.wikidata.org/wiki/Q1952404","display_name":"Multilinear map","level":2,"score":0.6765937805175781},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5739195346832275},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4796350598335266},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.4520461857318878},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.4447063207626343},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4201074540615082},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.41649556159973145},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4103657901287079},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39823639392852783},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3954111635684967},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2179017961025238},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.19596093893051147},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09841617941856384},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.07832911610603333},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","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/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"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/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/rda-160116","is_oa":false,"landing_page_url":"https://doi.org/10.3233/rda-160116","pdf_url":null,"source":{"id":"https://openalex.org/S2764680446","display_name":"Risk and Decision Analysis","issn_l":"1569-7371","issn":["1569-7371","1875-9173"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Risk and Decision Analysis","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W111165306","https://openalex.org/W1601081659","https://openalex.org/W1972124016","https://openalex.org/W1973515330","https://openalex.org/W1992689405","https://openalex.org/W2010654234","https://openalex.org/W2012547817","https://openalex.org/W2022529355","https://openalex.org/W2044287460","https://openalex.org/W2051772968","https://openalex.org/W2061508005","https://openalex.org/W2068782949","https://openalex.org/W2072227363","https://openalex.org/W2104753538","https://openalex.org/W2106652155","https://openalex.org/W2109634117","https://openalex.org/W2116123258","https://openalex.org/W2118556122","https://openalex.org/W2124477018","https://openalex.org/W2158086975","https://openalex.org/W2158738729","https://openalex.org/W2404471736","https://openalex.org/W2487144912","https://openalex.org/W2797333853","https://openalex.org/W2799119698","https://openalex.org/W2945368799","https://openalex.org/W3125826253","https://openalex.org/W4205818646","https://openalex.org/W4245744559","https://openalex.org/W6653536094","https://openalex.org/W6663456163","https://openalex.org/W7063911039"],"related_works":["https://openalex.org/W1999178348","https://openalex.org/W4296311369","https://openalex.org/W4318719034","https://openalex.org/W37958683","https://openalex.org/W2396820687","https://openalex.org/W3035010459","https://openalex.org/W3151212431","https://openalex.org/W2011892585","https://openalex.org/W2048755684","https://openalex.org/W2364569551"],"abstract_inverted_index":{"This":[0,18],"paper":[1],"provides":[2],"finite-time":[3],"performance":[4,87,144],"bounds":[5,88,145],"for":[6,21,160],"the":[7,54,76,79,86,94,98,102,107,110,120,123,132,135,138,143],"approximate":[8],"policy":[9,103],"iteration":[10,104],"(API)":[11],"algorithm":[12,69],"in":[13,91,129,140],"discounted":[14],"Markov":[15],"decision":[16],"models.":[17],"is":[19,31,70,82,113,126],"done":[20],"a":[22,32,116,149,161],"class":[23,48,162],"of":[24,49,53,93,101,122,137,163],"approximation":[25,95],"operators":[26],"called":[27],"averagers.":[28],"An":[29],"averager":[30],"positive":[33],"linear":[34],"operator":[35],"with":[36,41,157],"norm":[37],"equal":[38],"to":[39,131],"one":[40],"an":[42],"additional":[43],"con":[44],"tinuity":[45],"property.":[46],"The":[47,67,153],"averagers":[50],"includes":[51],"several":[52],"usual":[55],"interpolation":[56],"schemes":[57],"as":[58],"lineal":[59],"and":[60,85,97],"multilinear":[61],"approximations,":[62],"kernel-based":[63],"approximators":[64],"among":[65],"others.":[66],"API":[68],"studied":[71],"under":[72],"two":[73],"settings.":[74],"In":[75,106],"first":[77],"one,":[78],"transition":[80],"probability":[81],"completely":[83],"known":[84],"are":[89,155],"given":[90,114],"terms":[92],"errors":[96,133],"stopping":[99],"error":[100],"algorithm.":[105],"second":[108],"setting,":[109],"system":[111],"evolution":[112],"by":[115,134],"difference":[117],"equation":[118],"where":[119],"distribution":[121],"random":[124],"disturbance":[125],"unknown.":[127],"Thus,":[128],"addition":[130],"application":[136],"API,":[139],"this":[141],"case":[142],"also":[146],"depend":[147],"on":[148],"statistical":[150],"estimation":[151],"error.":[152],"results":[154],"illustrated":[156],"numerical":[158],"approximations":[159],"inventory":[164],"systems.":[165]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}