{"id":"https://openalex.org/W4385477979","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191692","title":"Demystifying Complex Treatment Recommendations: A Hierarchical Cooperative Multi-Agent RL Approach","display_name":"Demystifying Complex Treatment Recommendations: A Hierarchical Cooperative Multi-Agent RL Approach","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385477979","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191692"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191692","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","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/A5108815886","display_name":"Dilruk Perera","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4210150261","display_name":"National University Health System","ror":"https://ror.org/05tjjsh18","country_code":"SG","type":"education","lineage":["https://openalex.org/I4210150261"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dilruk Perera","raw_affiliation_strings":["Institute of Data Science, Saw Swee Hock School of Public Health, National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Data Science, Saw Swee Hock School of Public Health, National University of Singapore","institution_ids":["https://openalex.org/I165932596","https://openalex.org/I4210150261"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390236","display_name":"Siqi Liu","orcid":"https://orcid.org/0000-0002-4675-5498"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Siqi Liu","raw_affiliation_strings":["NUS Graduate School - ISEP, Institute of Data Science, National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NUS Graduate School - ISEP, Institute of Data Science, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022222926","display_name":"Mengling Feng","orcid":"https://orcid.org/0000-0002-5338-6248"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4210150261","display_name":"National University Health System","ror":"https://ror.org/05tjjsh18","country_code":"SG","type":"education","lineage":["https://openalex.org/I4210150261"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mengling Feng","raw_affiliation_strings":["Institute of Data Science, Saw Swee Hock School of Public Health, National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Data Science, Saw Swee Hock School of Public Health, National University of Singapore","institution_ids":["https://openalex.org/I165932596","https://openalex.org/I4210150261"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9994999766349792,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9994999766349792,"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/T11773","display_name":"Healthcare Operations and Scheduling Optimization","score":0.9925000071525574,"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"}},{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.9664999842643738,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7675018310546875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.727382242679596},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5700246691703796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5630912780761719},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5406988859176636},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5124419331550598},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.476481169462204},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4525038003921509},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.4443935751914978}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7675018310546875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.727382242679596},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5700246691703796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5630912780761719},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5406988859176636},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5124419331550598},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.476481169462204},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4525038003921509},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.4443935751914978},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191692","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","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":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G281004060","display_name":null,"funder_award_id":"AISG-GC-2019-001-2A,AISG2-TC-2022-004","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"}],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1526654727","https://openalex.org/W1607813664","https://openalex.org/W1977655452","https://openalex.org/W2003552981","https://openalex.org/W2025535766","https://openalex.org/W2121506959","https://openalex.org/W2134672787","https://openalex.org/W2396212074","https://openalex.org/W2525984666","https://openalex.org/W2535327675","https://openalex.org/W2579898249","https://openalex.org/W2619989803","https://openalex.org/W2781726626","https://openalex.org/W2788477667","https://openalex.org/W2899259578","https://openalex.org/W2901839060","https://openalex.org/W2962676505","https://openalex.org/W2970315086","https://openalex.org/W3008110675","https://openalex.org/W3087645508","https://openalex.org/W3107955501","https://openalex.org/W3109305078","https://openalex.org/W3120101765","https://openalex.org/W3123348991","https://openalex.org/W3171599858","https://openalex.org/W3199814407","https://openalex.org/W3216656735","https://openalex.org/W4214732234","https://openalex.org/W4289171906","https://openalex.org/W4295598622","https://openalex.org/W4301178047","https://openalex.org/W6631500254","https://openalex.org/W6677916933","https://openalex.org/W6737133519","https://openalex.org/W6738969012","https://openalex.org/W6746030470","https://openalex.org/W6747473740","https://openalex.org/W6749304979","https://openalex.org/W6756634552","https://openalex.org/W6766883460","https://openalex.org/W6783106408","https://openalex.org/W6786789126"],"related_works":["https://openalex.org/W2109940557","https://openalex.org/W2466832359","https://openalex.org/W4391210591","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W2579634771","https://openalex.org/W2034019356"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"techniques":[3,126],"are":[4,118],"widely":[5],"adopted":[6],"in":[7,61,122,127],"healthcare":[8],"research":[9],"to":[10,23,43,88,111,152,182,242,255],"learn":[11],"effective":[12,113],"policies":[13],"for":[14],"complex":[15,45,219],"sequential":[16],"decision-making":[17,58],"tasks,":[18],"such":[19],"as":[20,69,77],"treatment":[21,46,67,75,92,189,194,246,280],"recommendation":[22,68,190],"achieve":[24],"better":[25],"clinical":[26,114,129],"outcomes.":[27],"However,":[28,116],"existing":[29,48],"RL":[30,49,86,200],"based":[31],"solutions":[32],"suffer":[33],"from":[34],"two":[35],"major":[36],"limitations.":[37],"(1)":[38],"Burdens":[39],"a":[40,70,78,84,145,161,198,204,224,231,244],"single":[41,85],"agent":[42,87,233],"make":[44,112],"recommendations:":[47],"algorithms":[50],"do":[51],"not":[52],"explicitly":[53],"support":[54],"the":[55,74,90,128,166,186,218,258,268,278,284],"common":[56],"hierarchical":[57,205],"processes":[59],"used":[60],"practise.":[62],"That":[63],"is,":[64],"they":[65],"consider":[66],"singular":[71],"decision":[72],"and":[73,82,106,136,157,165,176,191,208,291],"space":[76],"flat":[79],"search":[80],"space,":[81],"expect":[83],"select":[89],"best":[91],"outright.":[93],"(2)":[94],"Sub":[95],"optimal":[96],"patient":[97,104,155,210,249,293],"state":[98,124,211,250],"representation":[99,102,125,212,251],"techniques:":[100],"accurate":[101],"of":[103,133,139,144,168,188,226,261,272],"states":[105,260],"their":[107,158,264],"dynamics":[108,159],"is":[109,221,253],"essential":[110],"decisions.":[115],"there":[117],"three":[119,269],"main":[120],"limitations":[121,271],"current":[123,273],"environment:":[130],"(i)":[131],"lack":[132,143],"clear":[134],"structure":[135],"high":[137],"variability":[138],"input":[140],"features;":[141],"(ii)":[142],"temporal":[146],"context,":[147],"which":[148,171],"makes":[149],"it":[150],"difficult":[151],"fully":[153],"capture":[154],"conditions":[156],"at":[160],"given":[162],"time;":[163],"(iii)":[164],"use":[167],"imputation":[169],"techniques,":[170],"undermines":[172],"personalization,":[173],"introduce":[174],"biases":[175],"errors":[177],"that":[178,202,234,283],"can":[179],"cause":[180],"harm":[181],"patients.":[183],"To":[184],"address":[185],"complexities":[187],"generate":[192],"superior":[193],"policies,":[195],"we":[196],"propose":[197],"consolidated":[199],"solution":[201,286],"incorporates":[203],"multi-agent":[206],"architecture":[207],"advanced":[209],"technique.":[213],"In":[214],"our":[215],"proposed":[216,285],"architecture,":[217],"task":[220,281],"decomposed":[222],"into":[223],"hierarchy":[225],"subtasks,":[227],"each":[228],"handled":[229],"by":[230,238],"specialized":[232],"coordinates":[235],"skills":[236],"learned":[237],"lower":[239],"level":[240],"agents":[241],"determine":[243],"high-level":[245],"policy.":[247],"The":[248],"technique":[252],"designed":[254],"effectively":[256],"encode":[257],"changing":[259],"patients":[262],"throughout":[263],"hospital":[265],"stay,":[266],"addressing":[267],"primary":[270],"approaches.":[274],"Our":[275],"experiments":[276],"using":[277],"sepsis":[279],"shows":[282],"consistently":[287],"outperforms":[288],"state-of-the-art":[289],"baselines":[290],"improves":[292],"survival.":[294]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}