{"id":"https://openalex.org/W7137832840","doi":"https://doi.org/10.1609/aaai.v40i24.39081","title":"Benchmarking Reinforcement Learning Algorithms for ICU Ventilator Settings: An Interpretable and Probabilistic Patient Environment for Doctor Agents","display_name":"Benchmarking Reinforcement Learning Algorithms for ICU Ventilator Settings: An Interpretable and Probabilistic Patient Environment for Doctor Agents","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137832840","doi":"https://doi.org/10.1609/aaai.v40i24.39081"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i24.39081","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i24.39081","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39081/43043","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39081/43043","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125714278","display_name":"Ya-Hsi Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ya-Hsi Chang","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103017921","display_name":"Po\u2010Chih Kuo","orcid":"https://orcid.org/0000-0003-4020-3147"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Po-Chih Kuo","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11111111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"24","first_page":"19970","last_page":"19977"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10322","display_name":"Respiratory Support and Mechanisms","score":0.4115000069141388,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10322","display_name":"Respiratory Support and Mechanisms","score":0.4115000069141388,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.12240000069141388,"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/T13248","display_name":"Healthcare Technology and Patient Monitoring","score":0.05429999902844429,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7889999747276306},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.781499981880188},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7770000100135803},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6832000017166138},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.3991999924182892},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.3741999864578247},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.3734000027179718},{"id":"https://openalex.org/keywords/intensive-care","display_name":"Intensive care","score":0.358599990606308}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7889999747276306},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.781499981880188},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7770000100135803},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6832000017166138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6777999997138977},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5922999978065491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5681999921798706},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.3741999864578247},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C2987404301","wikidata":"https://www.wikidata.org/wiki/Q679690","display_name":"Intensive care","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25780001282691956},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i24.39081","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i24.39081","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39081/43043","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/39081","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/39081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i24.39081","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i24.39081","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39081/43043","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.46690958738327026,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137832840.pdf","grobid_xml":"https://content.openalex.org/works/W7137832840.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Mechanical":[0],"ventilation":[1],"is":[2,28],"essential":[3],"in":[4,62,130],"intensive":[5],"care":[6],"units":[7],"(ICUs),":[8],"but":[9],"prolonged":[10],"use":[11],"increases":[12],"patient":[13,45],"risk.":[14],"Reinforcement":[15],"learning":[16],"(RL)":[17],"offers":[18],"potential":[19],"for":[20,135,149],"optimizing":[21],"ventilator":[22],"management,":[23],"yet":[24],"its":[25],"clinical":[26],"adoption":[27],"limited":[29],"by":[30],"the":[31,106],"lack":[32],"of":[33,108,144],"interpretable":[34,42,142],"and":[35,43,53,67,74,82,124],"realistic":[36],"simulation":[37],"environments.":[38],"We":[39],"propose":[40],"an":[41],"probabilistic":[44,76],"environment":[46],"simulator":[47,70],"based":[48],"on":[49,111],"action-based":[50],"k-nearest":[51],"neighbors":[52],"empirical":[54,127],"transition":[55],"probabilities,":[56],"modeling":[57],"stochastic":[58],"state":[59],"transitions":[60],"grounded":[61],"real":[63],"ICU":[64],"data":[65],"(MIMIC-IV":[66],"eICU).":[68],"The":[69],"supports":[71],"anomaly":[72],"detection":[73],"provides":[75],"next-state":[77],"distributions":[78],"to":[79,104],"enhance":[80],"transparency":[81],"safety.":[83],"Within":[84],"this":[85],"environment,":[86],"we":[87],"benchmark":[88,139],"seven":[89],"offline":[90],"RL":[91,118],"algorithms":[92],"under":[93],"clinically":[94],"guided":[95],"reward":[96,101,109],"designs,":[97],"including":[98],"five":[99],"distinct":[100],"function":[102],"configurations":[103],"explore":[105],"impact":[107],"shaping":[110],"agent":[112],"behavior.":[113],"Our":[114],"results":[115],"show":[116],"that":[117],"agents":[119],"such":[120],"as":[121],"Double":[122],"DQN":[123],"NFQ":[125],"outperform":[126],"physician":[128],"policies":[129],"meeting":[131],"extubation":[132],"guidelines,":[133],"especially":[134],"high-severity":[136],"patients.":[137],"This":[138],"enables":[140],"standardized,":[141],"evaluation":[143],"RL-based":[145],"decision":[146],"support":[147],"tools":[148],"critical":[150],"care.":[151]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}