{"id":"https://openalex.org/W2788144765","doi":"https://doi.org/10.1137/17m1138959","title":"Realizable Strategies in Continuous-Time Markov Decision Processes","display_name":"Realizable Strategies in Continuous-Time Markov Decision Processes","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2788144765","doi":"https://doi.org/10.1137/17m1138959","mag":"2788144765"},"language":"en","primary_location":{"id":"doi:10.1137/17m1138959","is_oa":false,"landing_page_url":"https://doi.org/10.1137/17m1138959","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Control and Optimization","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/A5054092600","display_name":"Alexey Piunovskiy","orcid":"https://orcid.org/0000-0002-9683-4856"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alexey Piunovskiy","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5054092600"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4235,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66330806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"56","issue":"1","first_page":"473","last_page":"495"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9801999926567078,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9801999926567078,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9797000288963318,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9761999845504761,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"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":0.794443666934967},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.703931987285614},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6352889537811279},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.6208146810531616},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5638353228569031},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5564640760421753},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5497664213180542},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.49469658732414246},{"id":"https://openalex.org/keywords/markov-renewal-process","display_name":"Markov renewal process","score":0.45778384804725647},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4331699311733246},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.4137667417526245},{"id":"https://openalex.org/keywords/decision-theory","display_name":"Decision theory","score":0.4115445613861084},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2859431505203247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13395172357559204},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08312791585922241}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.794443666934967},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.703931987285614},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6352889537811279},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.6208146810531616},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5638353228569031},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5564640760421753},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5497664213180542},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.49469658732414246},{"id":"https://openalex.org/C163540672","wikidata":"https://www.wikidata.org/wiki/Q1115431","display_name":"Markov renewal process","level":5,"score":0.45778384804725647},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4331699311733246},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.4137667417526245},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.4115445613861084},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2859431505203247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13395172357559204},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08312791585922241}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/17m1138959","is_oa":false,"landing_page_url":"https://doi.org/10.1137/17m1138959","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Control and Optimization","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"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/W13452760","https://openalex.org/W353798833","https://openalex.org/W412831655","https://openalex.org/W434069379","https://openalex.org/W591296147","https://openalex.org/W657312522","https://openalex.org/W1200801359","https://openalex.org/W1518072521","https://openalex.org/W1518931405","https://openalex.org/W1578233523","https://openalex.org/W1964804424","https://openalex.org/W1991625634","https://openalex.org/W2004191028","https://openalex.org/W2028145673","https://openalex.org/W2045668042","https://openalex.org/W2049032169","https://openalex.org/W2056861955","https://openalex.org/W2071966070","https://openalex.org/W2086234877","https://openalex.org/W2092046302","https://openalex.org/W2123649906","https://openalex.org/W2162378322","https://openalex.org/W2183681659","https://openalex.org/W2205548459","https://openalex.org/W2339816922","https://openalex.org/W2341171179","https://openalex.org/W2465828773"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W4323315247","https://openalex.org/W3169161914","https://openalex.org/W3208638985"],"abstract_inverted_index":{"For":[0,69],"the":[1,5,26,33,48,51,55,63,70,81,87,97,106,111],"Borel":[2],"model":[3,52],"of":[4,15,47,84],"continuous-time":[6],"Markov":[7,114],"decision":[8,57,115],"process,":[9],"we":[10,60,79,92],"introduce":[11],"a":[12,19],"wide":[13],"class":[14,83],"control":[16,73,100],"strategies.":[17,90],"In":[18,36],"particular":[20],"case,":[21,39],"such":[22],"strategies":[23,65],"transform":[24],"to":[25,43,54],"standard":[27],"relaxed":[28,64],"strategies,":[29,50,86],"intensively":[30],"studied":[31],"in":[32],"last":[34],"decade.":[35],"another":[37,44],"special":[38,45],"if":[40],"one":[41,102],"restricts":[42],"subclass":[46],"general":[49],"transforms":[53],"semi-Markov":[56],"process.":[58],"Further,":[59],"show":[61,93],"that":[62],"are":[66],"not":[67],"realizable.":[68],"constrained":[71],"optimal":[72,99],"problem":[74],"with":[75],"total":[76],"expected":[77],"costs,":[78],"describe":[80],"sufficient":[82],"realizable":[85],"so-called":[88],"Poisson-related":[89],"Finally,":[91],"that,":[94],"for":[95,110],"solving":[96],"formulated":[98],"problems,":[101],"can":[103],"use":[104],"all":[105],"tools":[107],"developed":[108],"earlier":[109],"classical":[112],"discrete-time":[113],"processes.":[116]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}