{"id":"https://openalex.org/W4382365084","doi":"https://doi.org/10.1109/itw55543.2023.10161640","title":"Minimizing the Outage Probability in a Markov Decision Process","display_name":"Minimizing the Outage Probability in a Markov Decision Process","publication_year":2023,"publication_date":"2023-04-23","ids":{"openalex":"https://openalex.org/W4382365084","doi":"https://doi.org/10.1109/itw55543.2023.10161640"},"language":"en","primary_location":{"id":"doi:10.1109/itw55543.2023.10161640","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/itw55543.2023.10161640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Information Theory Workshop (ITW)","raw_type":"proceedings-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/A5073070039","display_name":"Vincent Corlay","orcid":"https://orcid.org/0000-0002-9406-8377"},"institutions":[{"id":"https://openalex.org/I4210089619","display_name":"Mitsubishi Electric (France)","ror":"https://ror.org/0075b7k59","country_code":"FR","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210089619","https://openalex.org/I4210133125"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Vincent Corlay","raw_affiliation_strings":["Mitsubishi Electric R&D Centre Europe,Rennes,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric R&D Centre Europe,Rennes,France","institution_ids":["https://openalex.org/I4210089619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089201363","display_name":"Jean-Christophe Sibel","orcid":"https://orcid.org/0009-0007-5826-0904"},"institutions":[{"id":"https://openalex.org/I4210089619","display_name":"Mitsubishi Electric (France)","ror":"https://ror.org/0075b7k59","country_code":"FR","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210089619","https://openalex.org/I4210133125"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Christophe Sibel","raw_affiliation_strings":["Mitsubishi Electric R&D Centre Europe,Rennes,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric R&D Centre Europe,Rennes,France","institution_ids":["https://openalex.org/I4210089619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.065403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"107","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T13553","display_name":"Age of Information Optimization","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8715766668319702},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7439599633216858},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.7103255987167358},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7072325348854065},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.702433168888092},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.6087728142738342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.505251944065094},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4904501140117645},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.48888009786605835},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4754345417022705},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.466572642326355},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42500293254852295},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4015042185783386},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21047788858413696},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07880675792694092}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8715766668319702},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7439599633216858},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.7103255987167358},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7072325348854065},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.702433168888092},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.6087728142738342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.505251944065094},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4904501140117645},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.48888009786605835},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4754345417022705},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.466572642326355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42500293254852295},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4015042185783386},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21047788858413696},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07880675792694092},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itw55543.2023.10161640","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/itw55543.2023.10161640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Information Theory Workshop (ITW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2145339207","https://openalex.org/W4213251304","https://openalex.org/W4298876402","https://openalex.org/W4322729780","https://openalex.org/W4376478334","https://openalex.org/W4385804948","https://openalex.org/W6683300800","https://openalex.org/W6850814497"],"related_works":["https://openalex.org/W2357975469","https://openalex.org/W3089496523","https://openalex.org/W2808418668","https://openalex.org/W2937181779","https://openalex.org/W3096874164","https://openalex.org/W2146763310","https://openalex.org/W3167472281","https://openalex.org/W2182304831","https://openalex.org/W1556532828","https://openalex.org/W2124144580"],"abstract_inverted_index":{"Standard":[0],"Markov":[1],"decision":[2],"process":[3],"(MDP)":[4],"and":[5],"reinforcement":[6],"learning":[7,72],"algorithms":[8],"optimize":[9,25],"the":[10,15,29,32,49,57,69],"policy":[11],"with":[12],"respect":[13],"to":[14,24,63,68],"expected":[16],"gain.":[17],"We":[18,53],"propose":[19],"an":[20,26,46],"algorithm":[21,41,59],"which":[22],"enables":[23],"alternative":[27],"objective:":[28],"probability":[30],"that":[31],"gain":[33],"is":[34],"greater":[35],"than":[36],"a":[37],"given":[38],"value.":[39],"The":[40],"can":[42],"be":[43,61],"seen":[44],"as":[45],"extension":[47,73],"of":[48,74],"value":[50],"iteration":[51],"algorithm.":[52],"also":[54],"show":[55],"how":[56],"proposed":[58],"could":[60],"generalized":[62],"use":[64],"neural":[65],"networks,":[66],"similarly":[67],"deep":[70],"Q":[71,75],"learning.":[76]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}