{"id":"https://openalex.org/W1996214847","doi":"https://doi.org/10.1109/adprl.2014.7010613","title":"Convergence of value iterations for total-cost MDPs and POMDPs with general state and action sets","display_name":"Convergence of value iterations for total-cost MDPs and POMDPs with general state and action sets","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1996214847","doi":"https://doi.org/10.1109/adprl.2014.7010613","mag":"1996214847"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2014.7010613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","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/A5013021251","display_name":"Eugene A. Feinberg","orcid":"https://orcid.org/0000-0002-8263-0772"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Eugene A. Feinberg","raw_affiliation_strings":["Department of Applied, Stony Brook University, Stony Brook, NY","Department of Applied Mathematics and Statistics Stony Brook University Stony Brook, NY 11794-3600"],"affiliations":[{"raw_affiliation_string":"Department of Applied, Stony Brook University, Stony Brook, NY","institution_ids":["https://openalex.org/I59553526"]},{"raw_affiliation_string":"Department of Applied Mathematics and Statistics Stony Brook University Stony Brook, NY 11794-3600","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069636143","display_name":"Pavlo O. Kasyanov","orcid":"https://orcid.org/0000-0002-6662-0160"},"institutions":[{"id":"https://openalex.org/I202483615","display_name":"National Technical University of Ukraine \u201cIgor Sikorsky Kyiv Polytechnic Institute\u201d","ror":"https://ror.org/00syn5v21","country_code":"UA","type":"education","lineage":["https://openalex.org/I202483615"]},{"id":"https://openalex.org/I70764802","display_name":"National Polytechnic School","ror":"https://ror.org/01gb99w41","country_code":"EC","type":"education","lineage":["https://openalex.org/I70764802"]}],"countries":["EC","UA"],"is_corresponding":false,"raw_author_name":"Pavlo O. Kasyanov","raw_affiliation_strings":["Institute for Applied System Analysis, Kyiv Polytechnic Institute, Kyiv, Ukraine","Institute for Applied System Analysis National Technical University of Ukraine \u201cKyiv Polytechnic Institute\u201d Kyiv 03056, Ukraine"],"affiliations":[{"raw_affiliation_string":"Institute for Applied System Analysis, Kyiv Polytechnic Institute, Kyiv, Ukraine","institution_ids":["https://openalex.org/I202483615"]},{"raw_affiliation_string":"Institute for Applied System Analysis National Technical University of Ukraine \u201cKyiv Polytechnic Institute\u201d Kyiv 03056, Ukraine","institution_ids":["https://openalex.org/I70764802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064586240","display_name":"Michael Z. Zgurovsky","orcid":"https://orcid.org/0000-0001-5896-7466"},"institutions":[{"id":"https://openalex.org/I70764802","display_name":"National Polytechnic School","ror":"https://ror.org/01gb99w41","country_code":"EC","type":"education","lineage":["https://openalex.org/I70764802"]},{"id":"https://openalex.org/I202483615","display_name":"National Technical University of Ukraine \u201cIgor Sikorsky Kyiv Polytechnic Institute\u201d","ror":"https://ror.org/00syn5v21","country_code":"UA","type":"education","lineage":["https://openalex.org/I202483615"]}],"countries":["EC","UA"],"is_corresponding":false,"raw_author_name":"Michael Z. Zgurovsky","raw_affiliation_strings":["National Technical University of Ukraine, Kyiv Polytechnic Institute, Kyiv, Ukraine","National Technical University of Ukraine \u201cKyiv Polytechnic Institute,\u201d Kyiv 03056 Ukraine"],"affiliations":[{"raw_affiliation_string":"National Technical University of Ukraine, Kyiv Polytechnic Institute, Kyiv, Ukraine","institution_ids":["https://openalex.org/I202483615"]},{"raw_affiliation_string":"National Technical University of Ukraine \u201cKyiv Polytechnic Institute,\u201d Kyiv 03056 Ukraine","institution_ids":["https://openalex.org/I70764802"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013021251"],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":4.5067,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.94029513,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"8","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.9896000027656555,"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"}},"topics":[{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.9896000027656555,"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"}},{"id":"https://openalex.org/T11413","display_name":"Risk and Portfolio Optimization","score":0.9721999764442444,"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":0.9674000144004822,"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/markov-decision-process","display_name":"Markov decision process","score":0.8858023881912231},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.8339253664016724},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7384886145591736},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.6799622178077698},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6639750003814697},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6591148376464844},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6123313903808594},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5993323922157288},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5628793835639954},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.56035977602005},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.45248040556907654},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.37707215547561646},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.284511923789978},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14132007956504822}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8858023881912231},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.8339253664016724},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7384886145591736},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.6799622178077698},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6639750003814697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6591148376464844},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6123313903808594},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5993323922157288},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5628793835639954},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.56035977602005},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.45248040556907654},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.37707215547561646},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.284511923789978},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14132007956504822},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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:10.1109/adprl.2014.7010613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.800000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W391070489","https://openalex.org/W1050019105","https://openalex.org/W1499037879","https://openalex.org/W1529558080","https://openalex.org/W1611140369","https://openalex.org/W1770161726","https://openalex.org/W1966208686","https://openalex.org/W1981452551","https://openalex.org/W1984901446","https://openalex.org/W1985489506","https://openalex.org/W1994945819","https://openalex.org/W2002444764","https://openalex.org/W2010654234","https://openalex.org/W2023517438","https://openalex.org/W2034725503","https://openalex.org/W2040228279","https://openalex.org/W2059608296","https://openalex.org/W2068782949","https://openalex.org/W2089289861","https://openalex.org/W2119481921","https://openalex.org/W2155640779","https://openalex.org/W2265885659","https://openalex.org/W2317531417","https://openalex.org/W2327833721","https://openalex.org/W2951249201","https://openalex.org/W3122532879","https://openalex.org/W3122549769","https://openalex.org/W3123600823","https://openalex.org/W3140571750","https://openalex.org/W4245744559","https://openalex.org/W6627146504","https://openalex.org/W6636475787","https://openalex.org/W6637977763","https://openalex.org/W6655981465","https://openalex.org/W6693116336"],"related_works":["https://openalex.org/W2999848267","https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W1515117609","https://openalex.org/W2903299703","https://openalex.org/W4281791088","https://openalex.org/W4385342861","https://openalex.org/W1574958246"],"abstract_inverted_index":{"This":[0,73],"paper":[1,74,95],"describes":[2,75],"conditions":[3,76,98],"for":[4,83,99],"convergence":[5],"to":[6,15,41,54,116],"optimal":[7,81],"values":[8],"of":[9,38,67,69,114],"the":[10,70],"dynamic":[11,111],"programming":[12],"algorithm":[13],"applied":[14],"total-cost":[16],"Markov":[17],"Decision":[18],"Processes":[19],"(MDPSs)":[20],"with":[21,28,103],"Borel":[22],"state":[23,63],"and":[24,27,107,119],"action":[25,108],"sets":[26,66,109],"possibly":[29],"unbounded":[30],"one-step":[31],"cost":[32],"functions.":[33],"It":[34,46],"also":[35],"studies":[36],"applications":[37,115],"these":[39],"results":[40],"Partially":[42],"Observable":[43,59],"MDPs":[44,60],"(POMDPs).":[45],"is":[47],"well-known":[48],"that":[49],"POMDPs":[50,78,102],"can":[51,85],"be":[52,86],"reduced":[53],"special":[55],"MDPs,":[56],"called":[57],"Completely":[58],"(COMDPs),":[61],"whose":[62],"spaces":[64],"are":[65,122],"probabilities":[68],"original":[71],"states.":[72],"on":[77],"under":[79],"which":[80],"policies":[82],"COMDPs":[84],"found":[87],"by":[88,110],"value":[89],"iteration.":[90],"In":[91],"other":[92],"words,":[93],"this":[94],"provides":[96],"sufficient":[97],"solving":[100],"total-costs":[101],"infinite":[104],"state,":[105],"observation":[106],"programming.":[112],"Examples":[113],"filtration,":[117],"identification,":[118],"inventory":[120],"control":[121],"provided.":[123]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
