{"id":"https://openalex.org/W4399389685","doi":"https://doi.org/10.1287/ijoc.2022.0236","title":"Transfer Reinforcement Learning for Mixed Observability Markov Decision Processes with Time-Varying Interval-Valued Parameters and Its Application in Pandemic Control","display_name":"Transfer Reinforcement Learning for Mixed Observability Markov Decision Processes with Time-Varying Interval-Valued Parameters and Its Application in Pandemic Control","publication_year":2024,"publication_date":"2024-06-06","ids":{"openalex":"https://openalex.org/W4399389685","doi":"https://doi.org/10.1287/ijoc.2022.0236"},"language":"en","primary_location":{"id":"doi:10.1287/ijoc.2022.0236","is_oa":false,"landing_page_url":"https://doi.org/10.1287/ijoc.2022.0236","pdf_url":null,"source":{"id":"https://openalex.org/S165318533","display_name":"INFORMS journal on computing","issn_l":"1091-9856","issn":["1091-9856","1526-5528"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315699","host_organization_name":"Institute for Operations Research and the Management Sciences","host_organization_lineage":["https://openalex.org/P4310315699"],"host_organization_lineage_names":["Institute for Operations Research and the Management Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INFORMS Journal on Computing","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/A5072446616","display_name":"Mu Du","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mu Du","raw_affiliation_strings":["School of Economics and Management, Dalian University of Technology, Dalian 116024, China","School of Economics and Management, Dalian University of Technology, Dalian 116024, China;"],"affiliations":[{"raw_affiliation_string":"School of Economics and Management, Dalian University of Technology, Dalian 116024, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Economics and Management, Dalian University of Technology, Dalian 116024, China;","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052620797","display_name":"Hongtao Yu","orcid":"https://orcid.org/0000-0003-1785-972X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongtao Yu","raw_affiliation_strings":["School of Economics and Management, Dalian University of Technology, Dalian 116024, China","School of Economics and Management, Dalian University of Technology, Dalian 116024, China;"],"affiliations":[{"raw_affiliation_string":"School of Economics and Management, Dalian University of Technology, Dalian 116024, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Economics and Management, Dalian University of Technology, Dalian 116024, China;","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049992511","display_name":"Nan Kong","orcid":"https://orcid.org/0000-0002-4047-3414"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nan Kong","raw_affiliation_strings":["Weldon School of Biomedical Engineering, Purdue University, West Lafayette, Indiana 47907"],"affiliations":[{"raw_affiliation_string":"Weldon School of Biomedical Engineering, Purdue University, West Lafayette, Indiana 47907","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072446616"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.7274,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74200875,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"37","issue":"2","first_page":"315","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":0.9915000200271606,"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":0.9915000200271606,"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":0.9790999889373779,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9715999960899353,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.8765368461608887},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7236425876617432},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6414997577667236},{"id":"https://openalex.org/keywords/interval","display_name":"Interval (graph theory)","score":0.5928795337677002},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5476096272468567},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5236339569091797},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4860439896583557},{"id":"https://openalex.org/keywords/pandemic","display_name":"Pandemic","score":0.4781447649002075},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4573518633842468},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4539007544517517},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.443452388048172},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.42390117049217224},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33967188000679016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2728040814399719},{"id":"https://openalex.org/keywords/coronavirus-disease-2019","display_name":"Coronavirus disease 2019 (COVID-19)","score":0.21410387754440308},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20611613988876343},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.16457337141036987},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13667815923690796},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.08420434594154358}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.8765368461608887},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7236425876617432},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6414997577667236},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.5928795337677002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5476096272468567},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5236339569091797},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4860439896583557},{"id":"https://openalex.org/C89623803","wikidata":"https://www.wikidata.org/wiki/Q12184","display_name":"Pandemic","level":5,"score":0.4781447649002075},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4573518633842468},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4539007544517517},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.443452388048172},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.42390117049217224},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33967188000679016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2728040814399719},{"id":"https://openalex.org/C3008058167","wikidata":"https://www.wikidata.org/wiki/Q84263196","display_name":"Coronavirus disease 2019 (COVID-19)","level":4,"score":0.21410387754440308},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20611613988876343},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.16457337141036987},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13667815923690796},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08420434594154358},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.0},{"id":"https://openalex.org/C524204448","wikidata":"https://www.wikidata.org/wiki/Q788926","display_name":"Infectious disease (medical specialty)","level":3,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1287/ijoc.2022.0236","is_oa":false,"landing_page_url":"https://doi.org/10.1287/ijoc.2022.0236","pdf_url":null,"source":{"id":"https://openalex.org/S165318533","display_name":"INFORMS journal on computing","issn_l":"1091-9856","issn":["1091-9856","1526-5528"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315699","host_organization_name":"Institute for Operations Research and the Management Sciences","host_organization_lineage":["https://openalex.org/P4310315699"],"host_organization_lineage_names":["Institute for Operations Research and the Management Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INFORMS Journal on Computing","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:inm:orijoc:v:37:y:2025:i:2:p:315-337","is_oa":false,"landing_page_url":"http://doi.org/10.1287/ijoc.2022.0236","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W158722652","https://openalex.org/W1989031074","https://openalex.org/W1994511922","https://openalex.org/W2034556874","https://openalex.org/W2049265876","https://openalex.org/W2056584142","https://openalex.org/W2100495367","https://openalex.org/W2124717663","https://openalex.org/W2145339207","https://openalex.org/W2151786492","https://openalex.org/W2165698076","https://openalex.org/W2396228150","https://openalex.org/W2535746817","https://openalex.org/W2790390961","https://openalex.org/W2801121008","https://openalex.org/W2966007356","https://openalex.org/W3003573988","https://openalex.org/W3009876049","https://openalex.org/W3015017477","https://openalex.org/W3034133814","https://openalex.org/W3092157573","https://openalex.org/W3139422081","https://openalex.org/W3152304309","https://openalex.org/W3198564127","https://openalex.org/W3209953248","https://openalex.org/W3213597450","https://openalex.org/W3216311662","https://openalex.org/W4206657242","https://openalex.org/W4252527162","https://openalex.org/W4297964528","https://openalex.org/W4378802168","https://openalex.org/W4383112908","https://openalex.org/W4388116499"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W1515117609","https://openalex.org/W4323315247","https://openalex.org/W2294884454","https://openalex.org/W3169161914","https://openalex.org/W4321379664","https://openalex.org/W2211790881"],"abstract_inverted_index":{"We":[0,195],"investigate":[1],"a":[2,49,94,123,238,249],"novel":[3,95],"type":[4],"of":[5,125,136,141,151,158,200,226,242,274,318,352],"online":[6,28,53,86,119,286],"sequential":[7],"decision":[8,16,259,283],"problem":[9,179,235],"under":[10,40,174],"uncertainty,":[11],"namely":[12],"mixed":[13],"observability":[14],"Markov":[15,282],"process":[17],"with":[18,27,131,154,205,219,237],"time-varying":[19,70],"interval-valued":[20],"parameters":[21],"(MOMDP-TVIVP).":[22],"Such":[23],"data-driven":[24],"optimization":[25],"problems":[26],"learning":[29,98,105,110],"widely":[30],"have":[31],"real-world":[32],"applications":[33],"(e.g.,":[34],"coordinating":[35],"surveillance":[36],"and":[37,56,69,79,128,178,193,289,322,327,330,360,383],"intervention":[38],"activities":[39],"limited":[41],"resources":[42],"for":[43,73,85,221,234,298],"pandemic":[44,250],"control).":[45],"Solving":[46],"MOMDP-TVIVP":[47],"is":[48,270,355,386],"great":[50],"challenge":[51],"as":[52,367,369],"system":[54,170,287],"identification":[55,288],"reoptimization":[57],"based":[58],"on":[59,229,248],"newly":[60,132],"observational":[61,134],"data":[62,135],"are":[63,82],"required":[64],"considering":[65],"the":[66,77,118,137,147,155,163,198,271,313,325,334,341,350,358,371],"unobserved":[67],"states":[68],"parameters.":[71],"Moreover,":[72],"many":[74],"practical":[75],"problems,":[76],"action":[78],"state":[80],"spaces":[81],"intractably":[83],"large":[84],"optimization.":[87],"To":[88,116],"address":[89],"this":[90,353],"challenge,":[91],"we":[92,121],"propose":[93],"transfer":[96,104],"reinforcement":[97,109],"(TRL)-based":[99],"algorithmic":[100],"approach":[101,143,184,269],"that":[102,182,348],"ingrates":[103],"(TL)":[106],"into":[107],"deep":[108],"(DRL)":[111],"in":[112,169,188,207,231,254,263,280,300,310,331],"an":[113],"offline-online":[114],"scheme.":[115],"accelerate":[117],"reoptimization,":[120],"pretrain":[122],"collection":[124],"promising":[126],"networks":[127,153],"fine-tune":[129],"them":[130],"acquired":[133],"system.":[138],"The":[139,346,379],"hallmark":[140],"our":[142,183],"comes":[144],"from":[145,370],"combining":[146],"strong":[148],"approximation":[149],"ability":[150],"neural":[152,277],"high":[156],"flexibility":[157],"TL":[159],"through":[160],"efficiently":[161],"adapting":[162],"previously":[164],"learned":[165],"policy":[166],"to":[167,324,340],"changes":[168],"dynamics.":[171],"Computational":[172],"study":[173,247,354],"different":[175],"uncertainty":[176],"configurations":[177],"scales":[180],"shows":[181,257],"outperforms":[185],"existing":[186],"methods":[187],"solution":[189,212],"optimality,":[190],"robustness,":[191],"efficiency,":[192],"scalability.":[194],"also":[196],"demonstrate":[197],"value":[199],"fine-tuning":[201,220],"by":[202,217,293,312,333],"comparing":[203],"TRL":[204,218,262],"DRL,":[206],"which":[208],"at":[209,388],"least":[210],"21%":[211],"improvement":[213],"can":[214],"be":[215],"yielded":[216],"no":[222],"more":[223],"than":[224],"0.62%":[225],"time":[227],"spent":[228],"pretraining":[230],"each":[232],"period":[233],"instances":[236],"continuous":[239],"state-action":[240],"space":[241],"modest":[243],"dimensionality.":[244],"A":[245],"retrospective":[246],"control":[251],"use":[252],"case":[253],"Shanghai,":[255],"China":[256,319],"improved":[258],"making":[260],"via":[261],"several":[264],"public":[265],"health":[266],"metrics.":[267],"Our":[268],"first-ever":[272],"endeavor":[273],"employing":[275],"intensive":[276],"network":[278],"training":[279],"solving":[281],"processes":[284],"requiring":[285],"reoptimization.":[290],"History:":[291],"Accepted":[292],"Paul":[294],"Brooks,":[295],"Area":[296],"Editor":[297],"Applications":[299],"Biology,":[301],"Medicine,":[302],"&":[303],"Healthcare.":[304],"Funding:":[305],"This":[306],"work":[307],"was":[308],"supported":[309],"part":[311,332],"National":[314,335],"Natural":[315],"Science":[316,336],"Foundation":[317,337],"[Grants":[320],"72371051":[321],"72201047]":[323],"first":[326],"second":[328],"authors":[329],"[Grant":[338],"1825725]":[339],"third":[342],"author.":[343],"Supplemental":[344,362],"Material:":[345],"software":[347,374],"supports":[349],"findings":[351],"available":[356,387],"within":[357],"paper":[359],"its":[361],"Information":[363],"(":[364,376],"https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.0236":[365],")":[366],"well":[368],"IJOC":[372,381],"GitHub":[373],"repository":[375],"https://github.com/INFORMSJoC/2022.0236":[377],").":[378],"complete":[380],"Software":[382],"Data":[384],"Repository":[385],"https://informsjoc.github.io/":[389],".":[390]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}