{"id":"https://openalex.org/W2419696377","doi":"https://doi.org/10.1109/wodes.2016.7497868","title":"Optimization of parametric policies of Markov decision processes under a variance criterion","display_name":"Optimization of parametric policies of Markov decision processes under a variance criterion","publication_year":2016,"publication_date":"2016-05-01","ids":{"openalex":"https://openalex.org/W2419696377","doi":"https://doi.org/10.1109/wodes.2016.7497868","mag":"2419696377"},"language":"en","primary_location":{"id":"doi:10.1109/wodes.2016.7497868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wodes.2016.7497868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 13th International Workshop on Discrete Event Systems (WODES)","raw_type":"proceedings-article"},"type":"conference-paper","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":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Li Xia","raw_affiliation_strings":["Center for Intelligent and Networked Systems (CFINS), Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Intelligent and Networked Systems (CFINS), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100646502"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.3883,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58007267,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"42","issue":null,"first_page":"332","last_page":"337"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T12288","display_name":"Optimization and Search Problems","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.743278980255127},{"id":"https://openalex.org/keywords/variance-based-sensitivity-analysis","display_name":"Variance-based sensitivity analysis","score":0.7373262643814087},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6628486514091492},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6306378245353699},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5965217351913452},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.5743854641914368},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5554300546646118},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.5066710114479065},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.45009028911590576},{"id":"https://openalex.org/keywords/variance-function","display_name":"Variance function","score":0.43436428904533386},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.4311114251613617},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.39812397956848145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.35981285572052},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.326647013425827},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15002065896987915},{"id":"https://openalex.org/keywords/one-way-analysis-of-variance","display_name":"One-way analysis of variance","score":0.14869478344917297},{"id":"https://openalex.org/keywords/analysis-of-variance","display_name":"Analysis of variance","score":0.09592369198799133}],"concepts":[{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.743278980255127},{"id":"https://openalex.org/C108311543","wikidata":"https://www.wikidata.org/wiki/Q7915756","display_name":"Variance-based sensitivity analysis","level":4,"score":0.7373262643814087},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6628486514091492},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6306378245353699},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5965217351913452},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.5743854641914368},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5554300546646118},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.5066710114479065},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.45009028911590576},{"id":"https://openalex.org/C120488996","wikidata":"https://www.wikidata.org/wiki/Q17016064","display_name":"Variance function","level":3,"score":0.43436428904533386},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4311114251613617},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.39812397956848145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35981285572052},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.326647013425827},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15002065896987915},{"id":"https://openalex.org/C152587130","wikidata":"https://www.wikidata.org/wiki/Q7092351","display_name":"One-way analysis of variance","level":3,"score":0.14869478344917297},{"id":"https://openalex.org/C99476002","wikidata":"https://www.wikidata.org/wiki/Q42297","display_name":"Analysis of variance","level":2,"score":0.09592369198799133},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wodes.2016.7497868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wodes.2016.7497868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 13th International Workshop on Discrete Event Systems (WODES)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W163688550","https://openalex.org/W1516418405","https://openalex.org/W1602773783","https://openalex.org/W1678814353","https://openalex.org/W1993239624","https://openalex.org/W2004245628","https://openalex.org/W2005426889","https://openalex.org/W2013614847","https://openalex.org/W2014323878","https://openalex.org/W2056215075","https://openalex.org/W2067110063","https://openalex.org/W2083635875","https://openalex.org/W2093862975","https://openalex.org/W2098432798","https://openalex.org/W2119567691","https://openalex.org/W2162849300","https://openalex.org/W2163940180","https://openalex.org/W2171033527","https://openalex.org/W2334782222","https://openalex.org/W2484957131","https://openalex.org/W2611866857","https://openalex.org/W2952647718","https://openalex.org/W4231893760","https://openalex.org/W4236670843","https://openalex.org/W6637429886"],"related_works":["https://openalex.org/W2315999538","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532","https://openalex.org/W341703941","https://openalex.org/W228711507","https://openalex.org/W2091116596","https://openalex.org/W2006580754","https://openalex.org/W1991452706","https://openalex.org/W2041983147"],"abstract_inverted_index":{"The":[0,13,89],"variance":[1,23,48,82,90,108,127,165],"criterion":[2,8],"is":[3,93,143],"an":[4],"uncommon":[5],"while":[6],"important":[7],"in":[9,131,153],"Markov":[10],"decision":[11],"processes.":[12],"non-Markovian":[14],"property":[15,106],"caused":[16],"by":[17],"the":[18,26,39,47,51,55,64,80,86,102,121,125,132,140,148,154],"nonlinear":[19,105],"(quadratic)":[20],"structure":[21],"of":[22,41,44,57,67,79,104,107,139,150],"function":[24,109],"makes":[25],"traditional":[27],"MDP":[28],"approaches":[29,152],"invalid":[30],"for":[31,95,163],"this":[32,35,96,164],"problem.":[33,167],"In":[34],"paper,":[36],"we":[37,70,118],"study":[38],"optimization":[40,52,166],"parametric":[42],"policies":[43],"MDPs":[45],"under":[46],"criterion,":[49],"where":[50],"parameters":[53],"are":[54],"probabilities":[56],"selecting":[58],"actions":[59],"at":[60],"each":[61],"state.":[62],"With":[63,114],"basic":[65],"idea":[66],"sensitivity-based":[68],"optimization,":[69],"derive":[71],"a":[72,76,111,160],"difference":[73,91],"formula":[74,78,92],"and":[75,98],"derivative":[77],"reward":[81],"with":[83,124,147],"respect":[84],"to":[85],"system":[87],"parameter.":[88],"fundamental":[94],"problem":[97],"it":[99],"partly":[100],"handles":[101],"difficulty":[103],"through":[110],"nonnegative":[112],"term.":[113],"these":[115],"sensitivity":[116],"formulas,":[117],"prove":[119],"that":[120],"optimal":[122,141],"policy":[123,134,142],"minimal":[126],"can":[128,158],"be":[129],"found":[130],"deterministic":[133],"space.":[135],"A":[136],"necessary":[137],"condition":[138],"also":[144],"derived.":[145],"Compared":[146],"counterpart":[149],"gradient-based":[151],"literature,":[155],"our":[156],"approach":[157],"provide":[159],"clear":[161],"viewpoint":[162]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}