{"id":"https://openalex.org/W4387539636","doi":"https://doi.org/10.1007/s00521-023-09029-3","title":"Offline reinforcement learning in high-dimensional stochastic environments","display_name":"Offline reinforcement learning in high-dimensional stochastic environments","publication_year":2023,"publication_date":"2023-10-11","ids":{"openalex":"https://openalex.org/W4387539636","doi":"https://doi.org/10.1007/s00521-023-09029-3"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-023-09029-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-023-09029-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-023-09029-3.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-023-09029-3.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093044554","display_name":"F\u00e9licien H\u00eache","orcid":"https://orcid.org/0009-0004-3425-8189"},"institutions":[{"id":"https://openalex.org/I173439891","display_name":"HES-SO University of Applied Sciences and Arts Western Switzerland","ror":"https://ror.org/01xkakk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I173439891"]},{"id":"https://openalex.org/I90843659","display_name":"Universit\u00e9 de Franche-Comt\u00e9","ror":"https://ror.org/03pcc9z86","country_code":"FR","type":"education","lineage":["https://openalex.org/I90843659"]}],"countries":["CH","FR"],"is_corresponding":true,"raw_author_name":"F\u00e9licien H\u00eache","raw_affiliation_strings":["Nanomedecine Lab, Imagery and Therapeutics, University of Franche-Comt\u00e9, Besan\u00e7on, France","School of Engineering and Management, University of Applied Sciences and Arts Western Switzerland (HES-SO), Yverdon-les-Bains, Switzerland"],"raw_orcid":"https://orcid.org/0009-0004-3425-8189","affiliations":[{"raw_affiliation_string":"Nanomedecine Lab, Imagery and Therapeutics, University of Franche-Comt\u00e9, Besan\u00e7on, France","institution_ids":["https://openalex.org/I90843659"]},{"raw_affiliation_string":"School of Engineering and Management, University of Applied Sciences and Arts Western Switzerland (HES-SO), Yverdon-les-Bains, Switzerland","institution_ids":["https://openalex.org/I173439891"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021078383","display_name":"Oussama Barakat","orcid":"https://orcid.org/0009-0009-2855-2660"},"institutions":[{"id":"https://openalex.org/I90843659","display_name":"Universit\u00e9 de Franche-Comt\u00e9","ror":"https://ror.org/03pcc9z86","country_code":"FR","type":"education","lineage":["https://openalex.org/I90843659"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Oussama Barakat","raw_affiliation_strings":["Nanomedecine Lab, Imagery and Therapeutics, University of Franche-Comt\u00e9, Besan\u00e7on, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanomedecine Lab, Imagery and Therapeutics, University of Franche-Comt\u00e9, Besan\u00e7on, France","institution_ids":["https://openalex.org/I90843659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051364162","display_name":"T. Desmettre","orcid":"https://orcid.org/0000-0003-4585-5494"},"institutions":[{"id":"https://openalex.org/I4210094149","display_name":"H\u00f4pital Beau-S\u00e9jour","ror":"https://ror.org/00ntwgk39","country_code":"CH","type":"healthcare","lineage":["https://openalex.org/I4210094149"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Thibaut Desmettre","raw_affiliation_strings":["Emergency Department, H\u00f4pitaux Universitaires de Gen\u00e8ve (HUG), Gen\u00e8ve, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-4585-5494","affiliations":[{"raw_affiliation_string":"Emergency Department, H\u00f4pitaux Universitaires de Gen\u00e8ve (HUG), Gen\u00e8ve, Switzerland","institution_ids":["https://openalex.org/I4210094149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030994028","display_name":"Tania Marx","orcid":"https://orcid.org/0000-0002-1443-9423"},"institutions":[{"id":"https://openalex.org/I4210087978","display_name":"Centre Hospitalier Universitaire de Besan\u00e7on","ror":"https://ror.org/0084te143","country_code":"FR","type":"healthcare","lineage":["https://openalex.org/I4210087978"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Tania Marx","raw_affiliation_strings":["Emergency Department, Centre Hospitalier Universitaire (CHU), Besan\u00e7on, France"],"raw_orcid":"https://orcid.org/0000-0002-1443-9423","affiliations":[{"raw_affiliation_string":"Emergency Department, Centre Hospitalier Universitaire (CHU), Besan\u00e7on, France","institution_ids":["https://openalex.org/I4210087978"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043087021","display_name":"Stephan Robert","orcid":"https://orcid.org/0000-0002-7326-2357"},"institutions":[{"id":"https://openalex.org/I173439891","display_name":"HES-SO University of Applied Sciences and Arts Western Switzerland","ror":"https://ror.org/01xkakk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I173439891"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Stephan Robert-Nicoud","raw_affiliation_strings":["School of Engineering and Management, University of Applied Sciences and Arts Western Switzerland (HES-SO), Yverdon-les-Bains, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-7326-2357","affiliations":[{"raw_affiliation_string":"School of Engineering and Management, University of Applied Sciences and Arts Western Switzerland (HES-SO), Yverdon-les-Bains, Switzerland","institution_ids":["https://openalex.org/I173439891"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5093044554"],"corresponding_institution_ids":["https://openalex.org/I173439891","https://openalex.org/I90843659"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.7875,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7800012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"36","issue":"2","first_page":"585","last_page":"598"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9979000091552734,"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":0.9979000091552734,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9934999942779541,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9370999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cvar","display_name":"CVAR","score":0.7848997116088867},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7157560586929321},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6959282159805298},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.6081055402755737},{"id":"https://openalex.org/keywords/risk-measure","display_name":"Risk measure","score":0.5843061208724976},{"id":"https://openalex.org/keywords/expected-shortfall","display_name":"Expected shortfall","score":0.48294371366500854},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4603421986103058},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.44652700424194336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43284469842910767},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4226987063884735},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41318416595458984},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20178866386413574},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.13330653309822083},{"id":"https://openalex.org/keywords/risk-management","display_name":"Risk management","score":0.1050664484500885}],"concepts":[{"id":"https://openalex.org/C2779922397","wikidata":"https://www.wikidata.org/wiki/Q5014755","display_name":"CVAR","level":4,"score":0.7848997116088867},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7157560586929321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6959282159805298},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.6081055402755737},{"id":"https://openalex.org/C2781472820","wikidata":"https://www.wikidata.org/wiki/Q2154759","display_name":"Risk measure","level":3,"score":0.5843061208724976},{"id":"https://openalex.org/C5496284","wikidata":"https://www.wikidata.org/wiki/Q5420856","display_name":"Expected shortfall","level":3,"score":0.48294371366500854},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4603421986103058},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.44652700424194336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43284469842910767},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4226987063884735},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41318416595458984},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20178866386413574},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.13330653309822083},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.1050664484500885},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s00521-023-09029-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-023-09029-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-023-09029-3.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},{"id":"pmh:oai:hesso.tind.io:13059","is_oa":false,"landing_page_url":"http://arodes.hes-so.ch/record/13059","pdf_url":null,"source":{"id":"https://openalex.org/S4306402432","display_name":"ArODES (HES-SO (https://www.hes-so.ch/))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210088449","host_organization_name":"HES-SO Gen\u00e8ve","host_organization_lineage":["https://openalex.org/I4210088449"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arodes.hes-so.ch/record/13059","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/s00521-023-09029-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-023-09029-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-023-09029-3.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323833","display_name":"Centre Hospitalier Universitaire Vaudois","ror":"https://ror.org/05a353079"},{"id":"https://openalex.org/F4320326610","display_name":"Haute \u00e9cole Sp\u00e9cialis\u00e9e de Suisse Occidentale","ror":"https://ror.org/03r5zec51"},{"id":"https://openalex.org/F4320337753","display_name":"Interreg","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387539636.pdf","grobid_xml":"https://content.openalex.org/works/W4387539636.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W174509281","https://openalex.org/W569478347","https://openalex.org/W1553648478","https://openalex.org/W1647779468","https://openalex.org/W2019291268","https://openalex.org/W2041946752","https://openalex.org/W2046033161","https://openalex.org/W2053984877","https://openalex.org/W2109122936","https://openalex.org/W2129175615","https://openalex.org/W2150983233","https://openalex.org/W2257979135","https://openalex.org/W2488157181","https://openalex.org/W2604382266","https://openalex.org/W2765302304","https://openalex.org/W2781585732","https://openalex.org/W2795843265","https://openalex.org/W2799151646","https://openalex.org/W2902907165","https://openalex.org/W2963015795","https://openalex.org/W2963561234","https://openalex.org/W2967727187","https://openalex.org/W2979216345","https://openalex.org/W2994849131","https://openalex.org/W3015082424","https://openalex.org/W3016525976","https://openalex.org/W3017262417","https://openalex.org/W3022853033","https://openalex.org/W3037494843","https://openalex.org/W3094387578","https://openalex.org/W3100226171","https://openalex.org/W3122167364","https://openalex.org/W3124407081","https://openalex.org/W3150177537","https://openalex.org/W3216656735","https://openalex.org/W4205703615","https://openalex.org/W4206697161","https://openalex.org/W4287689949","https://openalex.org/W4287810981","https://openalex.org/W4293801385","https://openalex.org/W4360584316","https://openalex.org/W4380738448","https://openalex.org/W4382981485","https://openalex.org/W6605950425","https://openalex.org/W6828894009"],"related_works":["https://openalex.org/W2232143283","https://openalex.org/W2250138104","https://openalex.org/W2002736235","https://openalex.org/W2499931925","https://openalex.org/W48101171","https://openalex.org/W2384833971","https://openalex.org/W1997933673","https://openalex.org/W1592419251","https://openalex.org/W2031780815","https://openalex.org/W3190823906"],"abstract_inverted_index":{"Abstract":[0],"Offline":[1,130],"reinforcement":[2],"learning":[3],"(RL)":[4],"has":[5],"emerged":[6],"as":[7],"a":[8,58,90,111,150],"promising":[9],"paradigm":[10],"for":[11],"real-world":[12],"applications":[13],"since":[14],"it":[15,106],"aims":[16],"to":[17,37,53,78,109,139,148,160],"train":[18,62,140],"policies":[19,63,141],"directly":[20],"from":[21,39],"datasets":[22],"of":[23,49,66,94,170],"past":[24,30],"interactions":[25],"with":[26],"the":[27,55,83,95,115,120],"environment.":[28],"The":[29,46],"few":[31],"years,":[32],"algorithms":[33],"have":[34],"been":[35],"introduced":[36],"learn":[38],"high-dimensional":[40,143],"observational":[41],"states":[42],"in":[43,114,119,142,168],"offline":[44,146],"settings.":[45],"general":[47,76],"idea":[48],"these":[50],"methods":[51,167],"is":[52,86,107,137],"encode":[54],"environment":[56],"into":[57],"latent":[59,116],"space":[60,117],"and":[61,88,118,145,172],"on":[64,124,174],"top":[65],"this":[67,71,75,125],"smaller":[68],"representation.":[69],"In":[70],"paper,":[72],"we":[73,100,127,155],"extend":[74],"method":[77],"stochastic":[79,144,175],"environments":[80],"(i.e.,":[81],"where":[82],"reward":[84],"function":[85],"stochastic)":[87],"consider":[89],"risk":[91,112,152],"measure":[92,113],"instead":[93],"classical":[96],"expected":[97],"return.":[98],"First,":[99],"show":[101,156],"that,":[102],"under":[103],"some":[104],"assumptions,":[105],"equivalent":[108],"minimizing":[110],"natural":[121],"space.":[122],"Based":[123],"result,":[126],"present":[128],"Latent":[129],"Distributional":[131],"Actor-Critic":[132],"(LODAC),":[133],"an":[134],"algorithm":[135],"which":[136],"able":[138],"settings":[147],"minimize":[149,161],"given":[151],"measure.":[153],"Empirically,":[154],"that":[157],"using":[158],"LODAC":[159],"Conditional":[162],"Value-at-Risk":[163],"(CVaR)":[164],"outperforms":[165],"previous":[166],"terms":[169],"CVaR":[171],"return":[173],"environments.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2023-10-12T00:00:00"}