{"id":"https://openalex.org/W3008708537","doi":"https://doi.org/10.1109/wsc40007.2019.9004927","title":"Weakly Coupled Markov Decision Processes with Imperfect Information","display_name":"Weakly Coupled Markov Decision Processes with Imperfect Information","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008708537","doi":"https://doi.org/10.1109/wsc40007.2019.9004927","mag":"3008708537"},"language":"en","primary_location":{"id":"doi:10.1109/wsc40007.2019.9004927","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wsc40007.2019.9004927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Winter Simulation Conference (WSC)","raw_type":"proceedings-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/A5028441810","display_name":"Mahshid Salemi Parizi","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahshid Salemi Parizi","raw_affiliation_strings":["University of Washington,Department of Industrial and Systems Engineering,Seattle,WA,USA,98195"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,Department of Industrial and Systems Engineering,Seattle,WA,USA,98195","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068691426","display_name":"Archis Ghate","orcid":"https://orcid.org/0000-0001-6093-5340"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Archis Ghate","raw_affiliation_strings":["University of Washington,Department of Industrial and Systems Engineering,Seattle,WA,USA,98195"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,Department of Industrial and Systems Engineering,Seattle,WA,USA,98195","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2058,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63216783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3609","last_page":"3620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11413","display_name":"Risk and Portfolio Optimization","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.9926999807357788,"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/markov-decision-process","display_name":"Markov decision process","score":0.7049444913864136},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6300642490386963},{"id":"https://openalex.org/keywords/lagrangian-relaxation","display_name":"Lagrangian relaxation","score":0.5988044142723083},{"id":"https://openalex.org/keywords/perfect-information","display_name":"Perfect information","score":0.5924994349479675},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.5855689644813538},{"id":"https://openalex.org/keywords/relaxation","display_name":"Relaxation (psychology)","score":0.5748320817947388},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5716921091079712},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5365078449249268},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.48051509261131287},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4534849524497986},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.43190521001815796},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34776854515075684},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.34475964307785034},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.13768354058265686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11048322916030884}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7049444913864136},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6300642490386963},{"id":"https://openalex.org/C91765299","wikidata":"https://www.wikidata.org/wiki/Q3424292","display_name":"Lagrangian relaxation","level":2,"score":0.5988044142723083},{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.5924994349479675},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.5855689644813538},{"id":"https://openalex.org/C2776029896","wikidata":"https://www.wikidata.org/wiki/Q3935810","display_name":"Relaxation (psychology)","level":2,"score":0.5748320817947388},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5716921091079712},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5365078449249268},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.48051509261131287},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4534849524497986},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.43190521001815796},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34776854515075684},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.34475964307785034},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.13768354058265686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11048322916030884},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"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":[{"id":"doi:10.1109/wsc40007.2019.9004927","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wsc40007.2019.9004927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Winter Simulation Conference (WSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1582436621","https://openalex.org/W1981704813","https://openalex.org/W2039522160","https://openalex.org/W2044069028","https://openalex.org/W2056921512","https://openalex.org/W2061641373","https://openalex.org/W2098432798","https://openalex.org/W2131228644","https://openalex.org/W2135396811","https://openalex.org/W2150328967","https://openalex.org/W2334782222","https://openalex.org/W2579409967","https://openalex.org/W2734696438","https://openalex.org/W2743075836","https://openalex.org/W2963627946","https://openalex.org/W3125634603","https://openalex.org/W3143833270","https://openalex.org/W4239466562","https://openalex.org/W6634907821","https://openalex.org/W6674995601"],"related_works":["https://openalex.org/W131709709","https://openalex.org/W4389475841","https://openalex.org/W4241327272","https://openalex.org/W2120406836","https://openalex.org/W1996214847","https://openalex.org/W2903299703","https://openalex.org/W2117282672","https://openalex.org/W4211224558","https://openalex.org/W4281791088","https://openalex.org/W2119790124"],"abstract_inverted_index":{"Weakly":[0],"coupled":[1,45,73,96],"Markov":[2],"decision":[3],"processes":[4],"(MDPs)":[5],"are":[6,15,60,66,117,121,143],"stochastic":[7,127],"dynamic":[8,103,128],"programs":[9],"where":[10],"decisions":[11],"in":[12],"independent":[13],"sub-MDPs":[14],"linked":[16],"via":[17],"constraints.":[18],"Their":[19],"exact":[20],"solution":[21],"is":[22],"computationally":[23],"intractable.":[24],"Numerical":[25],"experiments":[26],"have":[27],"shown":[28],"that":[29],"Lagrangian":[30,115],"relaxation":[31,116],"can":[32],"be":[33],"an":[34],"effective":[35],"approximation":[36],"technique.":[37],"This":[38,68,92],"paper":[39],"considers":[40],"two":[41],"classes":[42],"of":[43,126],"weakly":[44,72,95],"MDPs":[46],"with":[47,114,138],"imperfect":[48],"information.":[49],"In":[50,75],"the":[51,54,76,79,83],"first":[52],"case,":[53,78],"transition":[55],"probabilities":[56],"for":[57],"each":[58],"sub-MDP":[59],"characterized":[61],"by":[62],"parameters":[63],"whose":[64],"values":[65],"unknown.":[67],"yields":[69,93],"a":[70,89,94,124],"Bayes-adaptive":[71],"MDP.":[74,99],"second":[77],"decision-maker":[80],"cannot":[81],"observe":[82],"actual":[84],"state":[85],"and":[86,132],"instead":[87],"receives":[88],"noisy":[90],"signal.":[91],"partially":[97,139],"observable":[98,140],"Computationally":[100],"tractable":[101],"approximate":[102],"programming":[104],"methods":[105,120],"combining":[106],"semi-stochastic":[107],"certainty":[108],"equivalent":[109],"control":[110],"or":[111],"Thompson":[112],"sampling":[113],"proposed.":[118],"These":[119],"applied":[122],"to":[123,133],"class":[125],"resource":[129],"allocation":[130],"problems":[131,137],"restless":[134],"multi-armed":[135],"bandit":[136],"states.":[141],"Insights":[142],"drawn":[144],"from":[145],"numerical":[146],"experiments.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}