{"id":"https://openalex.org/W1975162409","doi":"https://doi.org/10.1137/s0363012903420875","title":"Optimal Control of Ergodic Continuous-Time Markov Chains with Average Sample-Path Rewards","display_name":"Optimal Control of Ergodic Continuous-Time Markov Chains with Average Sample-Path Rewards","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W1975162409","doi":"https://doi.org/10.1137/s0363012903420875","mag":"1975162409"},"language":"en","primary_location":{"id":"doi:10.1137/s0363012903420875","is_oa":false,"landing_page_url":"https://doi.org/10.1137/s0363012903420875","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/A5101505539","display_name":"Xianping Guo","orcid":"https://orcid.org/0000-0001-6954-5947"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xianping Guo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100635237","display_name":"Xi\u2010Ren Cao","orcid":"https://orcid.org/0000-0001-5165-8804"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xi-Ren Cao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101505539"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0713,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.9156717,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"44","issue":"1","first_page":"29","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973999857902527,"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":0.9973999857902527,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9945999979972839,"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"}},{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.991599977016449,"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/mathematics","display_name":"Mathematics","score":0.8532365560531616},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6490378975868225},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5743628144264221},{"id":"https://openalex.org/keywords/ergodic-theory","display_name":"Ergodic theory","score":0.5566257834434509},{"id":"https://openalex.org/keywords/martingale","display_name":"Martingale (probability theory)","score":0.5483412146568298},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.48719972372055054},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4464893043041229},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.4408930838108063},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.43060675263404846},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41192519664764404},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3862476348876953},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13705125451087952},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.10447466373443604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.10358178615570068},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.09972292184829712}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.8532365560531616},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6490378975868225},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5743628144264221},{"id":"https://openalex.org/C122044880","wikidata":"https://www.wikidata.org/wiki/Q5498822","display_name":"Ergodic theory","level":2,"score":0.5566257834434509},{"id":"https://openalex.org/C48406656","wikidata":"https://www.wikidata.org/wiki/Q534112","display_name":"Martingale (probability theory)","level":2,"score":0.5483412146568298},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.48719972372055054},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4464893043041229},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.4408930838108063},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.43060675263404846},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41192519664764404},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3862476348876953},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13705125451087952},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.10447466373443604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.10358178615570068},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.09972292184829712},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/s0363012903420875","is_oa":false,"landing_page_url":"https://doi.org/10.1137/s0363012903420875","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W5657644","https://openalex.org/W48288425","https://openalex.org/W109663536","https://openalex.org/W184225095","https://openalex.org/W1518931405","https://openalex.org/W1524028581","https://openalex.org/W1578233523","https://openalex.org/W1964680067","https://openalex.org/W1967037758","https://openalex.org/W1970303738","https://openalex.org/W1984006577","https://openalex.org/W1988044028","https://openalex.org/W1991513691","https://openalex.org/W1998119014","https://openalex.org/W2006115861","https://openalex.org/W2028145673","https://openalex.org/W2029631728","https://openalex.org/W2035446426","https://openalex.org/W2051442802","https://openalex.org/W2057261803","https://openalex.org/W2061879839","https://openalex.org/W2068466946","https://openalex.org/W2068782949","https://openalex.org/W2075313566","https://openalex.org/W2081405254","https://openalex.org/W2083661550","https://openalex.org/W2095550302","https://openalex.org/W2098000180","https://openalex.org/W2109174772","https://openalex.org/W2119567691","https://openalex.org/W2121291657","https://openalex.org/W2131783016","https://openalex.org/W2142032013","https://openalex.org/W2150301222","https://openalex.org/W2161297030","https://openalex.org/W2168617462","https://openalex.org/W2171033527","https://openalex.org/W2313728779","https://openalex.org/W2317531417","https://openalex.org/W2334782222","https://openalex.org/W4210545817","https://openalex.org/W4232251398","https://openalex.org/W4237594416","https://openalex.org/W4298856952"],"related_works":["https://openalex.org/W3083204406","https://openalex.org/W2385944013","https://openalex.org/W2332749656","https://openalex.org/W2805455506","https://openalex.org/W2151299863","https://openalex.org/W2232389929","https://openalex.org/W4292816064","https://openalex.org/W2950790738","https://openalex.org/W2345009014","https://openalex.org/W3151248404"],"abstract_inverted_index":{"In":[0],"this":[1,54],"paper":[2],"we":[3],"study":[4],"continuous-time":[5],"Markov":[6,44],"decision":[7],"processes":[8],"with":[9,93],"the":[10,27,32,59,63,68,87,101,104,107],"average":[11,108],"sample-path":[12],"reward":[13,21,110],"(ASPR)":[14],"criterion":[15],"and":[16,20,67,77,106],"possibly":[17],"unbounded":[18],"transition":[19],"rates.":[22],"We":[23,72,91],"propose":[24],"conditions":[25],"on":[26,58],"system's":[28],"primitive":[29],"data":[30],"for":[31,81],"existence":[33],"of":[34,42,53,70],"$\\epsilon$-ASPR-optimal":[35,88],"(deterministic)":[36],"stationary":[37,89],"policies":[38,45],"in":[39],"a":[40],"class":[41],"randomized":[43],"satisfying":[46],"some":[47],"additional":[48],"continuity":[49],"assumptions.":[50],"The":[51],"proof":[52],"fact":[55],"is":[56],"based":[57],"time":[60],"discretization":[61],"technique,":[62],"martingale":[64],"stability":[65],"theory,":[66],"concept":[69],"potential.":[71],"also":[73],"provide":[74],"both":[75],"policy":[76],"value":[78],"iteration":[79],"algorithms":[80],"computing,":[82],"or":[83],"at":[84],"least":[85],"approximating,":[86],"policies.":[90],"illustrate":[92],"examples":[94],"our":[95],"main":[96],"results":[97],"as":[98,100],"well":[99],"difference":[102],"between":[103],"ASPR":[105],"expected":[109],"criteria.":[111]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}