{"id":"https://openalex.org/W2016588739","doi":"https://doi.org/10.1007/s10288-013-0236-1","title":"Discounted continuous-time Markov decision processes with unbounded rates and randomized history-dependent policies: the dynamic programming approach","display_name":"Discounted continuous-time Markov decision processes with unbounded rates and randomized history-dependent policies: the dynamic programming approach","publication_year":2013,"publication_date":"2013-03-30","ids":{"openalex":"https://openalex.org/W2016588739","doi":"https://doi.org/10.1007/s10288-013-0236-1","mag":"2016588739"},"language":"en","primary_location":{"id":"doi:10.1007/s10288-013-0236-1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10288-013-0236-1","pdf_url":null,"source":{"id":"https://openalex.org/S4210191715","display_name":"4OR","issn_l":"1614-2411","issn":["1614-2411","1619-4500"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4OR","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":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Alexey Piunovskiy","raw_affiliation_strings":["Department of Mathematical Sciences, University of Liverpool, Liverpool, L69 7ZL, UK","#N##TAB##TAB##TAB##TAB# University of Liverpool#N##TAB##TAB##TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Mathematical Sciences, University of Liverpool, Liverpool, L69 7ZL, UK","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"#N##TAB##TAB##TAB##TAB# University of Liverpool#N##TAB##TAB##TAB#","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036373241","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0002-3200-6306"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["Department of Mathematical Sciences, University of Liverpool, Liverpool, L69 7ZL, UK","#N##TAB##TAB##TAB##TAB# University of Liverpool#N##TAB##TAB##TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Mathematical Sciences, University of Liverpool, Liverpool, L69 7ZL, UK","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"#N##TAB##TAB##TAB##TAB# University of Liverpool#N##TAB##TAB##TAB#","institution_ids":["https://openalex.org/I146655781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054092600"],"corresponding_institution_ids":["https://openalex.org/I146655781"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":3.4838,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92713503,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"12","issue":"1","first_page":"49","last_page":"75"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9909999966621399,"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":0.9909999966621399,"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/T12137","display_name":"Economic theories and models","score":0.9589999914169312,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10974","display_name":"Advanced Queuing Theory Analysis","score":0.9528999924659729,"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/markov-decision-process","display_name":"Markov decision process","score":0.897148847579956},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6391058564186096},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.6308832168579102},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6105568408966064},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.6056309342384338},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.6055498719215393},{"id":"https://openalex.org/keywords/markov-kernel","display_name":"Markov kernel","score":0.5731348395347595},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5620142817497253},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.5584972500801086},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5128536224365234},{"id":"https://openalex.org/keywords/markov-renewal-process","display_name":"Markov renewal process","score":0.4585326910018921},{"id":"https://openalex.org/keywords/markov-property","display_name":"Markov property","score":0.4452534317970276},{"id":"https://openalex.org/keywords/time-reversibility","display_name":"Time reversibility","score":0.44331562519073486},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4247584640979767},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.39439457654953003},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.37568435072898865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.37322062253952026},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.33151569962501526},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11507508158683777}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.897148847579956},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6391058564186096},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.6308832168579102},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6105568408966064},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.6056309342384338},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6055498719215393},{"id":"https://openalex.org/C106666656","wikidata":"https://www.wikidata.org/wiki/Q6771323","display_name":"Markov kernel","level":5,"score":0.5731348395347595},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5620142817497253},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.5584972500801086},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5128536224365234},{"id":"https://openalex.org/C163540672","wikidata":"https://www.wikidata.org/wiki/Q1115431","display_name":"Markov renewal process","level":5,"score":0.4585326910018921},{"id":"https://openalex.org/C189973286","wikidata":"https://www.wikidata.org/wiki/Q176695","display_name":"Markov property","level":4,"score":0.4452534317970276},{"id":"https://openalex.org/C98735484","wikidata":"https://www.wikidata.org/wiki/Q186971","display_name":"Time reversibility","level":5,"score":0.44331562519073486},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4247584640979767},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.39439457654953003},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.37568435072898865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.37322062253952026},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.33151569962501526},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11507508158683777},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10288-013-0236-1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10288-013-0236-1","pdf_url":null,"source":{"id":"https://openalex.org/S4210191715","display_name":"4OR","issn_l":"1614-2411","issn":["1614-2411","1619-4500"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4OR","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/45f8f7a8-7e21-4e27-9cf5-013434ce8e8e","is_oa":false,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/45f8f7a8-7e21-4e27-9cf5-013434ce8e8e","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Piunovskiy, A & Zhang, Y 2014, 'Discounted continuous-time Markov decision processes with unbounded rates and randomized history-dependent policies : The dynamic programming approach', 4OR, vol. 12, no. 1, pp. 49-75. https://doi.org/10.1007/s10288-013-0236-1","raw_type":"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W13452760","https://openalex.org/W434069379","https://openalex.org/W657312522","https://openalex.org/W1578233523","https://openalex.org/W1672382258","https://openalex.org/W1980480099","https://openalex.org/W1983558443","https://openalex.org/W1984329922","https://openalex.org/W1989510286","https://openalex.org/W1995379941","https://openalex.org/W2004191028","https://openalex.org/W2010654234","https://openalex.org/W2025030740","https://openalex.org/W2031019231","https://openalex.org/W2039184239","https://openalex.org/W2045668042","https://openalex.org/W2049032169","https://openalex.org/W2079291782","https://openalex.org/W2086234877","https://openalex.org/W2088065116","https://openalex.org/W2092046302","https://openalex.org/W2119567691","https://openalex.org/W2150606382","https://openalex.org/W2162378322","https://openalex.org/W2334782222","https://openalex.org/W2465828773","https://openalex.org/W3101717792","https://openalex.org/W4210545817","https://openalex.org/W4237655005"],"related_works":["https://openalex.org/W3022014775","https://openalex.org/W2019735591","https://openalex.org/W1974839821","https://openalex.org/W4285429136","https://openalex.org/W2096496337","https://openalex.org/W2026691440","https://openalex.org/W2356987663","https://openalex.org/W2005003293","https://openalex.org/W34472511","https://openalex.org/W2016588739"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}