{"id":"https://openalex.org/W2049472152","doi":"https://doi.org/10.1109/ascc.2013.6606023","title":"Policy iteration for parameterized Markov decision processes and its application","display_name":"Policy iteration for parameterized Markov decision processes and its application","publication_year":2013,"publication_date":"2013-06-01","ids":{"openalex":"https://openalex.org/W2049472152","doi":"https://doi.org/10.1109/ascc.2013.6606023","mag":"2049472152"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/ascc.2013.6606023","pdf_url":null,"source":{"id":"https://openalex.org/S4363607827","display_name":"2022 13th Asian Control Conference (ASCC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"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},"type":"article","type_crossref":"proceedings-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/A5100646502","display_name":"Li Xia","orcid":"https://orcid.org/0000-0002-3193-7336"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"funder","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Xia","raw_affiliation_strings":["Center for Intell. & Networked Syst. (CFINS) Dept. of Autom., Tsinghua Univ., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Intell. & Networked Syst. (CFINS) Dept. of Autom., Tsinghua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044965133","display_name":"Qing\u2010Shan Jia","orcid":"https://orcid.org/0000-0002-4683-7215"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"funder","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing-Shan Jia","raw_affiliation_strings":["Center for Intell. & Networked Syst. (CFINS) Dept. of Autom., Tsinghua Univ., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Intell. & Networked Syst. (CFINS) Dept. of Autom., Tsinghua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.329,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":2,"citation_normalized_percentile":{"value":0.408068,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":72,"max":76},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10768","display_name":"Electric Vehicles and Infrastructure","score":0.9953,"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"}},"topics":[{"id":"https://openalex.org/T10768","display_name":"Electric Vehicles and Infrastructure","score":0.9953,"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"}},{"id":"https://openalex.org/T10663","display_name":"Advanced Battery Technologies Research","score":0.9952,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9892,"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/decision-maker","display_name":"Decision maker","score":0.4440298}],"concepts":[{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.94083846},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8654189},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.65948844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.59067726},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.57259697},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5519098},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.44452617},{"id":"https://openalex.org/C2986080485","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision maker","level":2,"score":0.4440298},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39558172},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30481714},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.09623501},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.08024499},{"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":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/ascc.2013.6606023","pdf_url":null,"source":{"id":"https://openalex.org/S4363607827","display_name":"2022 13th Asian Control Conference (ASCC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"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}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions","score":0.78}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":21,"referenced_works":["https://openalex.org/W1531253382","https://openalex.org/W1593494339","https://openalex.org/W2006036383","https://openalex.org/W2051876076","https://openalex.org/W2056215075","https://openalex.org/W2060840612","https://openalex.org/W2066008291","https://openalex.org/W2085990480","https://openalex.org/W2091694970","https://openalex.org/W2098432798","https://openalex.org/W2118000334","https://openalex.org/W2119567691","https://openalex.org/W2120465407","https://openalex.org/W2135232836","https://openalex.org/W2152530926","https://openalex.org/W2334782222","https://openalex.org/W2484957131","https://openalex.org/W2492250943","https://openalex.org/W2611866857","https://openalex.org/W2792298817","https://openalex.org/W320808933"],"related_works":["https://openalex.org/W52153049","https://openalex.org/W4323315247","https://openalex.org/W4321379664","https://openalex.org/W3169161914","https://openalex.org/W2294884454","https://openalex.org/W2096013579","https://openalex.org/W2049472152","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W1515117609"],"abstract_inverted_index":{"In":[0,43],"a":[1,72],"parameterized":[2,85,102],"Markov":[3],"decision":[4,8],"process":[5],"(MDP),":[6],"the":[7,13,18,24,33,40,48,64,78,84,97,107,121],"maker":[9],"has":[10],"to":[11,52,62,83,119],"choose":[12],"optimal":[14],"parameters":[15,34],"which":[16],"induce":[17],"maximal":[19],"average":[20],"system":[21,41],"reward.":[22],"However,":[23],"traditional":[25],"policy":[26,81,88],"iteration":[27,82,89],"algorithm":[28,91,100],"is":[29,36,60,92],"usually":[30],"inapplicable":[31],"because":[32],"choosing":[35],"not":[37],"independent":[38],"of":[39,80,112,124],"state.":[42],"this":[44,54,125],"paper,":[45],"we":[46,105],"use":[47],"direct":[49],"comparison":[50],"approach":[51],"study":[53,106],"problem.":[55],"A":[56],"general":[57],"difference":[58,66],"equation":[59],"derived":[61],"compare":[63],"performance":[65],"under":[67],"different":[68],"parameters.":[69],"We":[70],"derive":[71],"theoretical":[73],"condition":[74],"that":[75],"can":[76],"guarantee":[77],"application":[79],"MDP.":[86,103],"This":[87],"type":[90],"much":[93],"more":[94],"efficient":[95],"than":[96],"gradient":[98],"optimization":[99],"for":[101],"Finally,":[104],"service":[108],"rate":[109],"control":[110],"problem":[111],"closed":[113],"Jackson":[114],"networks":[115],"as":[116],"an":[117],"example":[118],"demonstrate":[120],"main":[122],"idea":[123],"paper.":[126]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2049472152","counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-04-19T01:16:19.844554","created_date":"2016-06-24"}