{"id":"https://openalex.org/W3171599858","doi":"https://doi.org/10.1145/3447548.3467181","title":"Hierarchical Reinforcement Learning for Scarce Medical Resource Allocation with Imperfect Information","display_name":"Hierarchical Reinforcement Learning for Scarce Medical Resource Allocation with Imperfect Information","publication_year":2021,"publication_date":"2021-08-13","ids":{"openalex":"https://openalex.org/W3171599858","doi":"https://doi.org/10.1145/3447548.3467181","mag":"3171599858"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3467181","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","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/A5051274227","display_name":"Qianyue Hao","orcid":"https://orcid.org/0000-0002-7109-3588"},"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":"Qianyue Hao","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062365263","display_name":"Fengli Xu","orcid":"https://orcid.org/0000-0002-5720-4026"},"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":false,"raw_author_name":"Fengli Xu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007536250","display_name":"Lin Chen","orcid":"https://orcid.org/0000-0002-2605-749X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lin Chen","raw_affiliation_strings":["The Hong Kong University of Science and Technology, HongKong, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, HongKong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029925982","display_name":"Pan Hui","orcid":"https://orcid.org/0000-0002-0848-2599"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Pan Hui","raw_affiliation_strings":["The Hong Kong University of Science and Technology, HongKong, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, HongKong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100355277","display_name":"Yong Li","orcid":"https://orcid.org/0000-0001-5617-1659"},"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":false,"raw_author_name":"Yong Li","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051274227"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.1797,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.77688571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2955","last_page":"2963"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10410","display_name":"COVID-19 epidemiological studies","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2611","display_name":"Modeling and Simulation"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10410","display_name":"COVID-19 epidemiological studies","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2611","display_name":"Modeling and Simulation"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9861000180244446,"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/T11773","display_name":"Healthcare Operations and Scheduling Optimization","score":0.9648000001907349,"subfield":{"id":"https://openalex.org/subfields/3604","display_name":"Emergency Medical Services"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8206309080123901},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7763211727142334},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5538104772567749},{"id":"https://openalex.org/keywords/economic-shortage","display_name":"Economic shortage","score":0.537388026714325},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.5159521698951721},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4900585412979126},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45492663979530334},{"id":"https://openalex.org/keywords/perfect-information","display_name":"Perfect information","score":0.43552497029304504},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.42621034383773804},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40308672189712524},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.36296436190605164},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.2203499972820282},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11073362827301025},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10351759195327759}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8206309080123901},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7763211727142334},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5538104772567749},{"id":"https://openalex.org/C194051981","wikidata":"https://www.wikidata.org/wiki/Q1337691","display_name":"Economic shortage","level":3,"score":0.537388026714325},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.5159521698951721},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4900585412979126},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45492663979530334},{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.43552497029304504},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.42621034383773804},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40308672189712524},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.36296436190605164},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2203499972820282},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11073362827301025},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10351759195327759},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3447548.3467181","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-113214","is_oa":false,"landing_page_url":"http://www.scopus.com/record/display.url?eid=2-s2.0-85114928343&origin=inward","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-113214","is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-113214","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/3"}],"awards":[{"id":"https://openalex.org/G1757078732","display_name":null,"funder_award_id":"20031887521","funder_id":"https://openalex.org/F4320329777","funder_display_name":"Beijing National Research Center For Information Science And Technology"},{"id":"https://openalex.org/G7024251178","display_name":null,"funder_award_id":"2020AAA0106000","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8724681935","display_name":null,"funder_award_id":"U1936217, 61971267, 61972223, 61941117, 61861136003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329777","display_name":"Beijing National Research Center For Information Science And Technology","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2001387206","https://openalex.org/W2008072444","https://openalex.org/W2089141625","https://openalex.org/W2112202856","https://openalex.org/W2133393736","https://openalex.org/W2145339207","https://openalex.org/W2150355110","https://openalex.org/W2183128369","https://openalex.org/W3001118548","https://openalex.org/W3003573988","https://openalex.org/W3003668884","https://openalex.org/W3012690896","https://openalex.org/W3012804303","https://openalex.org/W3016327299","https://openalex.org/W3020358767","https://openalex.org/W3084053817","https://openalex.org/W3101490008","https://openalex.org/W3161096839"],"related_works":["https://openalex.org/W2360321812","https://openalex.org/W2395295193","https://openalex.org/W3122057932","https://openalex.org/W2113798763","https://openalex.org/W3088364074","https://openalex.org/W2004230228","https://openalex.org/W2610227658","https://openalex.org/W2145796981","https://openalex.org/W2900431508","https://openalex.org/W2050340470"],"abstract_inverted_index":{"Facing":[0],"the":[1,52,63,107,128,133,148,156,164],"outbreak":[2],"of":[3,65],"COVID-19,":[4],"shortage":[5],"in":[6,36,51,73],"medical":[7,16],"resources":[8],"becomes":[9],"increasingly":[10],"outstanding.":[11],"Therefore,":[12],"efficient":[13,112],"strategies":[14],"for":[15,28,48],"resource":[17],"allocation":[18],"are":[19,59],"urgently":[20],"called":[21],"for.":[22],"Reinforcement":[23],"learning":[24,91],"(RL)":[25],"is":[26],"powerful":[27],"decision":[29,49],"making,":[30],"but":[31],"three":[32],"key":[33],"challenges":[34],"exist":[35],"solving":[37],"this":[38,84],"problem":[39],"via":[40],"RL:":[41],"(1)":[42],"complex":[43],"situation":[44],"and":[45,113,155,169],"countless":[46,108],"choices":[47,109],"making":[50],"real":[53,74,114,143],"world;":[54],"(2)":[55],"only":[56],"imperfect":[57,129],"information":[58,130],"available":[60],"due":[61],"to":[62,104,110,126],"latency":[64],"pandemic":[66,80,138],"spreading;":[67],"(3)":[68],"limitations":[69],"on":[70,142,173],"conducting":[71],"experiments":[72,154],"world":[75,144],"since":[76],"we":[77,86],"cannot":[78],"set":[79],"outbreaks":[81],"arbitrarily.":[82],"In":[83],"paper,":[85],"propose":[87],"a":[88,94,100,120,137],"hierarchical":[89],"reinforcement":[90],"method":[92,161],"with":[93,106],"corresponding":[95],"training":[96],"algorithm.":[97],"We":[98,117,135,151],"design":[99,119],"decomposed":[101],"action":[102],"space":[103],"deal":[105],"ensure":[111],"time":[115],"strategies.":[116],"also":[118],"recurrent":[121],"neural":[122],"network":[123],"based":[124,141],"framework":[125],"utilize":[127],"obtained":[131],"from":[132],"environment.":[134],"build":[136],"spreading":[139],"simulator":[140],"data,":[145],"serving":[146],"as":[147],"experimental":[149],"platform.":[150],"conduct":[152],"extensive":[153],"results":[157],"show":[158],"that":[159],"our":[160],"outperforms":[162],"all":[163],"baselines,":[165],"which":[166],"reduces":[167],"infections":[168],"deaths":[170],"by":[171],"14.25%":[172],"average.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}