{"id":"https://openalex.org/W4287167427","doi":"https://doi.org/10.1016/j.artint.2026.104519","title":"An offline risk-aware policy selection method for Bayesian Markov decision processes","display_name":"An offline risk-aware policy selection method for Bayesian Markov decision processes","publication_year":2026,"publication_date":"2026-03-16","ids":{"openalex":"https://openalex.org/W4287167427","doi":"https://doi.org/10.1016/j.artint.2026.104519"},"language":"en","primary_location":{"id":"doi:10.1016/j.artint.2026.104519","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.artint.2026.104519","pdf_url":null,"source":{"id":"https://openalex.org/S196139623","display_name":"Artificial Intelligence","issn_l":"0004-3702","issn":["0004-3702","1872-7921"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.artint.2026.104519","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043519978","display_name":"Giorgio Angelotti","orcid":"https://orcid.org/0000-0002-1878-5833"},"institutions":[{"id":"https://openalex.org/I4210098964","display_name":"Toulouse Mathematics Institute","ror":null,"country_code":"FR","type":null,"lineage":["https://openalex.org/I4210098964"]},{"id":"https://openalex.org/I4210139096","display_name":"National Higher French Institute of Aeronautics and Space","ror":null,"country_code":"FR","type":null,"lineage":["https://openalex.org/I4210139096"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Giorgio Angelotti","raw_affiliation_strings":["ANITI - Artificial and Natural Intelligence Toulouse Institute, University of Toulouse, France","F\u00e9d\u00e9ration ENAC ISAE-SUPAERO ONERA, University of Toulouse, France"],"raw_orcid":"https://orcid.org/0000-0002-1878-5833","affiliations":[{"raw_affiliation_string":"ANITI - Artificial and Natural Intelligence Toulouse Institute, University of Toulouse, France","institution_ids":["https://openalex.org/I4210098964"]},{"raw_affiliation_string":"F\u00e9d\u00e9ration ENAC ISAE-SUPAERO ONERA, University of Toulouse, France","institution_ids":["https://openalex.org/I4210139096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001788642","display_name":"Nicolas Drougard","orcid":"https://orcid.org/0000-0003-0002-9973"},"institutions":[{"id":"https://openalex.org/I4210098964","display_name":"Toulouse Mathematics Institute","ror":null,"country_code":"FR","type":null,"lineage":["https://openalex.org/I4210098964"]},{"id":"https://openalex.org/I4210139096","display_name":"National Higher French Institute of Aeronautics and Space","ror":null,"country_code":"FR","type":null,"lineage":["https://openalex.org/I4210139096"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Drougard","raw_affiliation_strings":["ANITI - Artificial and Natural Intelligence Toulouse Institute, University of Toulouse, France","F\u00e9d\u00e9ration ENAC ISAE-SUPAERO ONERA, University of Toulouse, France"],"raw_orcid":"https://orcid.org/0000-0003-0002-9973","affiliations":[{"raw_affiliation_string":"ANITI - Artificial and Natural Intelligence Toulouse Institute, University of Toulouse, France","institution_ids":["https://openalex.org/I4210098964"]},{"raw_affiliation_string":"F\u00e9d\u00e9ration ENAC ISAE-SUPAERO ONERA, University of Toulouse, France","institution_ids":["https://openalex.org/I4210139096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019098556","display_name":"Caroline Ponzoni Carvalho Chanel","orcid":"https://orcid.org/0000-0003-3578-4186"},"institutions":[{"id":"https://openalex.org/I4210098964","display_name":"Toulouse Mathematics Institute","ror":null,"country_code":"FR","type":null,"lineage":["https://openalex.org/I4210098964"]},{"id":"https://openalex.org/I4210139096","display_name":"National Higher French Institute of Aeronautics and Space","ror":null,"country_code":"FR","type":null,"lineage":["https://openalex.org/I4210139096"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Caroline P\u2024\u2009C. Chanel","raw_affiliation_strings":["ANITI - Artificial and Natural Intelligence Toulouse Institute, University of Toulouse, France","F\u00e9d\u00e9ration ENAC ISAE-SUPAERO ONERA, University of Toulouse, France"],"raw_orcid":"https://orcid.org/0000-0003-3578-4186","affiliations":[{"raw_affiliation_string":"ANITI - Artificial and Natural Intelligence Toulouse Institute, University of Toulouse, France","institution_ids":["https://openalex.org/I4210098964"]},{"raw_affiliation_string":"F\u00e9d\u00e9ration ENAC ISAE-SUPAERO ONERA, University of Toulouse, France","institution_ids":["https://openalex.org/I4210139096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5019098556"],"corresponding_institution_ids":["https://openalex.org/I4210098964","https://openalex.org/I4210139096"],"apc_list":{"value":4260,"currency":"USD","value_usd":4260},"apc_paid":{"value":4260,"currency":"USD","value_usd":4260},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00060678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"354","issue":null,"first_page":"104519","last_page":"104519"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9836999773979187,"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":0.9836999773979187,"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":0.9699000120162964,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.965399980545044,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8007075190544128},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.726783812046051},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6877719163894653},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6490535140037537},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5772726535797119},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5030187964439392},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4909101128578186},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4641370177268982},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4493371844291687},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4159141778945923},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09982907772064209}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8007075190544128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.726783812046051},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6877719163894653},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6490535140037537},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5772726535797119},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5030187964439392},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4909101128578186},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4641370177268982},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4493371844291687},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4159141778945923},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09982907772064209},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1016/j.artint.2026.104519","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.artint.2026.104519","pdf_url":null,"source":{"id":"https://openalex.org/S196139623","display_name":"Artificial Intelligence","issn_l":"0004-3702","issn":["0004-3702","1872-7921"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2105.13431","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2105.13431","pdf_url":"https://arxiv.org/pdf/2105.13431","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-05645523v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05645523","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Artificial Intelligence (AIJ), 2026, 354, pp.104519. ⟨10.1016/j.artint.2026.104519⟩","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2105.13431","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2105.13431","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1016/j.artint.2026.104519","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.artint.2026.104519","pdf_url":null,"source":{"id":"https://openalex.org/S196139623","display_name":"Artificial Intelligence","issn_l":"0004-3702","issn":["0004-3702","1872-7921"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G3010527862","display_name":null,"funder_award_id":"ANR\u201019","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G3778207229","display_name":null,"funder_award_id":"PI3A-0004","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G3879958799","display_name":null,"funder_award_id":"19-PI3A-0004","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G602161992","display_name":null,"funder_award_id":"ANR-19-PI3A-0004","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F7608296345","display_name":"Artificial and Natural Intelligence Toulouse Institute","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1965878388","https://openalex.org/W2168565265","https://openalex.org/W2165622730","https://openalex.org/W2966375141","https://openalex.org/W1495775210","https://openalex.org/W4298293062","https://openalex.org/W2019291268","https://openalex.org/W3124407081"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W187740018"],"abstract_inverted_index":{"In":[0,111,193],"Offline":[1,8],"Model":[2],"Learning":[3],"for":[4,168,211],"Planning":[5],"and":[6,42,82,122,146,203,219],"in":[7,36,180,223],"Reinforcement":[9],"Learning,":[10],"the":[11,16,19,23,30,33,37,47,67,71,75,79,83,102,125,143,149,157,171,194,224],"limited":[12],"data":[13],"set":[14,163],"hinders":[15],"estimate":[17],"of":[18,22,32,49,69,164,190],"Value":[20],"function":[21],"relative":[24],"Markov":[25],"Decision":[26],"Process":[27],"(MDP).":[28],"Consequently,":[29],"performance":[31],"obtained":[34],"policy":[35,52,150],"real":[38,225],"world":[39],"is":[40,118,124],"bounded":[41],"possibly":[43],"risky,":[44],"especially":[45],"when":[46,98],"deployment":[48],"a":[50,108,133,153,161,187,208],"wrong":[51],"can":[53],"lead":[54],"to":[55,94,101,199,215],"catastrophic":[56],"consequences.":[57],"For":[58],"this":[59],"reason,":[60],"several":[61],"pathways":[62],"are":[63],"being":[64],"followed":[65],"with":[66,92,177],"scope":[68],"reducing":[70],"model":[72,81,95,139],"error":[73],"(or":[74],"distributional":[76],"shift":[77],"between":[78,160],"learned":[80],"true":[84],"one)":[85],"and,":[86],"more":[87],"broadly,":[88],"obtaining":[89],"risk-aware":[90,154],"solutions":[91],"respect":[93],"uncertainty.":[96],"But":[97],"it":[99],"comes":[100],"final":[103],"application":[104],"which":[105],"baseline":[106],"should":[107],"practitioner":[109],"choose?":[110],"an":[112,120],"offline":[113,217],"context":[114],"where":[115],"computational":[116],"time":[117],"not":[119],"issue":[121],"robustness":[123],"priority":[126],"we":[127],"propose":[128],"Exploitation":[129],"vs":[130],"Caution":[131],"(EvC),":[132],"paradigm":[134],"that":[135,151,213],"(1)":[136],"elegantly":[137],"incorporates":[138],"uncertainty":[140],"abiding":[141],"by":[142,170],"Bayesian":[144,158],"formalism,":[145],"(2)":[147],"selects":[148],"maximizes":[152],"objective":[155],"over":[156],"posterior":[159],"fixed":[162],"candidate":[165],"policies":[166,202],"provided,":[167],"instance,":[169],"current":[172],"baselines.":[173],"We":[174],"validate":[175],"EvC":[176,197],"state-of-the-art":[178],"approaches":[179],"different":[181],"discrete,":[182],"yet":[183],"simple,":[184],"environments":[185],"offering":[186],"fair":[188],"variety":[189],"MDP":[191],"classes.":[192],"tested":[195],"scenarios":[196],"manages":[198],"select":[200],"robust":[201],"hence":[204],"stands":[205],"out":[206],"as":[207],"useful":[209],"tool":[210],"practitioners":[212],"aim":[214],"apply":[216],"planning":[218],"reinforcement":[220],"learning":[221],"solvers":[222],"world.":[226]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2022-07-25T00:00:00"}