{"id":"https://openalex.org/W3201191077","doi":"https://doi.org/10.3233/aic-190632","title":"Deterministic policies based on maximum regrets in MDPs with imprecise rewards","display_name":"Deterministic policies based on maximum regrets in MDPs with imprecise rewards","publication_year":2021,"publication_date":"2021-09-21","ids":{"openalex":"https://openalex.org/W3201191077","doi":"https://doi.org/10.3233/aic-190632","mag":"3201191077"},"language":"en","primary_location":{"id":"doi:10.3233/aic-190632","is_oa":false,"landing_page_url":"https://doi.org/10.3233/aic-190632","pdf_url":null,"source":{"id":"https://openalex.org/S176303223","display_name":"AI Communications","issn_l":"0921-7126","issn":["0921-7126","1875-8452"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AI Communications","raw_type":"journal-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/A5027553821","display_name":"Pegah Alizadeh","orcid":"https://orcid.org/0000-0002-7231-5840"},"institutions":[{"id":"https://openalex.org/I4210121459","display_name":"P\u00f4le L\u00e9onard de Vinci","ror":"https://ror.org/02setav13","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210121459"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Pegah Alizadeh","raw_affiliation_strings":["L\u00e9onard de Vinci P\u00f4le Universitaire, Research Center, 92 916 Paris, La D\u00e9fense, France. E-mail:\u00a0pegah.alizadeh@devinci.fr"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L\u00e9onard de Vinci P\u00f4le Universitaire, Research Center, 92 916 Paris, La D\u00e9fense, France. E-mail:\u00a0pegah.alizadeh@devinci.fr","institution_ids":["https://openalex.org/I4210121459"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107961345","display_name":"Emiliano Traversi","orcid":"https://orcid.org/0000-0003-4673-3982"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210091279","display_name":"Universit\u00e9 Sorbonne Paris Nord","ror":"https://ror.org/0199hds37","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210091279"]},{"id":"https://openalex.org/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emiliano Traversi","raw_affiliation_strings":["LIPN-UMR CNRS 7030, Universit\u00e9 Sorbonne Paris Nord, Villetaneuse, France. E-mails:\u00a0emiliano.traversi@lipn.univ-paris13.fr,\u00a0aomar.osmani@lipn.univ-paris13.fr"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIPN-UMR CNRS 7030, Universit\u00e9 Sorbonne Paris Nord, Villetaneuse, France. E-mails:\u00a0emiliano.traversi@lipn.univ-paris13.fr,\u00a0aomar.osmani@lipn.univ-paris13.fr","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4210156583","https://openalex.org/I1294671590","https://openalex.org/I4210091279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002599627","display_name":"Aomar Osmani","orcid":"https://orcid.org/0000-0002-1778-6527"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210091279","display_name":"Universit\u00e9 Sorbonne Paris Nord","ror":"https://ror.org/0199hds37","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210091279"]},{"id":"https://openalex.org/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Aomar Osmani","raw_affiliation_strings":["LIPN-UMR CNRS 7030, Universit\u00e9 Sorbonne Paris Nord, Villetaneuse, France. E-mails:\u00a0emiliano.traversi@lipn.univ-paris13.fr,\u00a0aomar.osmani@lipn.univ-paris13.fr"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIPN-UMR CNRS 7030, Universit\u00e9 Sorbonne Paris Nord, Villetaneuse, France. E-mails:\u00a0emiliano.traversi@lipn.univ-paris13.fr,\u00a0aomar.osmani@lipn.univ-paris13.fr","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4210156583","https://openalex.org/I1294671590","https://openalex.org/I4210091279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027553821"],"corresponding_institution_ids":["https://openalex.org/I4210121459"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13564382,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":"4","first_page":"229","last_page":"244"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9807000160217285,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9807000160217285,"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/T10315","display_name":"Decision-Making and Behavioral Economics","score":0.9731000065803528,"subfield":{"id":"https://openalex.org/subfields/1800","display_name":"General Decision Sciences"},"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.9659000039100647,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.9271582961082458},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8216116428375244},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.811646580696106},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6031290292739868},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5827609896659851},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43954622745513916},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4136393070220947},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19185397028923035},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12187689542770386}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9271582961082458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8216116428375244},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.811646580696106},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6031290292739868},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5827609896659851},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43954622745513916},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4136393070220947},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19185397028923035},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12187689542770386},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/aic-190632","is_oa":false,"landing_page_url":"https://doi.org/10.3233/aic-190632","pdf_url":null,"source":{"id":"https://openalex.org/S176303223","display_name":"AI Communications","issn_l":"0921-7126","issn":["0921-7126","1875-8452"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AI Communications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W9932698","https://openalex.org/W206243501","https://openalex.org/W1515851193","https://openalex.org/W1531340371","https://openalex.org/W1541317966","https://openalex.org/W1597160459","https://openalex.org/W1965878388","https://openalex.org/W1988217924","https://openalex.org/W2044121814","https://openalex.org/W2058066080","https://openalex.org/W2074902040","https://openalex.org/W2107086007","https://openalex.org/W2108692343","https://openalex.org/W2119567691","https://openalex.org/W2120518702","https://openalex.org/W2145964516","https://openalex.org/W2154023516","https://openalex.org/W2155153696","https://openalex.org/W2168565265","https://openalex.org/W2264110120","https://openalex.org/W2334782222","https://openalex.org/W2405100124","https://openalex.org/W2556090351","https://openalex.org/W2725263144","https://openalex.org/W2774277131","https://openalex.org/W6632351690","https://openalex.org/W6713597259"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W2970347269","https://openalex.org/W4287863949","https://openalex.org/W4287102143","https://openalex.org/W1850488217","https://openalex.org/W2945119207","https://openalex.org/W3182614517","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"Markov":[0],"Decision":[1],"Process":[2],"Models":[3],"(MDPs)":[4],"are":[5,92],"a":[6,79,99,104,118,134,146],"powerful":[7],"tool":[8],"for":[9,43,75,95,98,116],"planning":[10],"tasks":[11],"and":[12,125],"sequential":[13],"decision-making":[14],"issues.":[15],"In":[16,37],"this":[17,38],"work":[18],"we":[19,40,121],"deal":[20],"with":[21,23,30],"MDPs":[22],"imprecise":[24],"rewards,":[25],"often":[26],"used":[27],"when":[28],"dealing":[29],"situations":[31],"where":[32,128],"the":[33,45,49,53,59,64,76,110,129,140,150],"data":[34],"is":[35],"uncertain.":[36],"context,":[39],"provide":[41,103],"algorithms":[42],"finding":[44,117],"policy":[46,86,136,143,147],"that":[47],"minimizes":[48],"maximum":[50],"regret.":[51],"To":[52,107],"best":[54],"of":[55,112,132],"our":[56],"knowledge,":[57],"all":[58],"regret-based":[60],"methods":[61],"proposed":[62],"in":[63],"literature":[65],"focus":[66],"on":[67],"providing":[68],"an":[69,83,113],"optimal":[70,84,141],"stochastic":[71,142],"policy.":[72,153],"We":[73],"introduce":[74],"first":[77],"time":[78],"method":[80],"to":[81,145],"calculate":[82],"deterministic":[85,119,135,152],"using":[87,133],"optimization":[88],"approaches.":[89],"Deterministic":[90],"policies":[91],"easily":[93],"interpretable":[94],"users":[96],"because":[97],"given":[100],"state":[101],"they":[102],"unique":[105],"choice.":[106],"better":[108],"motivate":[109],"use":[111],"exact":[114,151],"procedure":[115],"policy,":[120],"show":[122],"some":[123],"(theoretical":[124],"experimental)":[126],"cases":[127],"intuitive":[130],"idea":[131],"obtained":[137],"after":[138],"\u201cdeterminizing\u201d":[139],"leads":[144],"far":[148],"from":[149]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}