{"id":"https://openalex.org/W2040503115","doi":"https://doi.org/10.1137/110844957","title":"Reversible Markov Decision Processes with an Average-Reward Criterion","display_name":"Reversible Markov Decision Processes with an Average-Reward Criterion","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2040503115","doi":"https://doi.org/10.1137/110844957","mag":"2040503115"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1137/110844957","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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-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/A5062316763","display_name":"Randy Cogill","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Randy Cogill","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036585419","display_name":"Peng Cheng","orcid":"https://orcid.org/0000-0002-9797-6944"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng Peng","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":3,"citation_normalized_percentile":{"value":0.573554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":76,"max":78},"biblio":{"volume":"51","issue":"1","first_page":"402","last_page":"418"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12056","display_name":"Bayesian Monte Carlo Methods in Scientific Inference","score":0.9965,"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"}},"topics":[{"id":"https://openalex.org/T12056","display_name":"Bayesian Monte Carlo Methods in Scientific Inference","score":0.9965,"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"}},{"id":"https://openalex.org/T11031","display_name":"Network Formation and Game Dynamics","score":0.9923,"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/T10772","display_name":"Distributed Fault Tolerance and Consistency in Systems","score":0.9804,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-chains","display_name":"Markov Chains","score":0.506065},{"id":"https://openalex.org/keywords/inverse-problems","display_name":"Inverse Problems","score":0.503676}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.82644916},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5928788},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5346346},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49465248},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.45134187},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.42598295},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.35890102},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.27024752}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1137/110844957","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":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.78,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":9,"referenced_works":["https://openalex.org/W1964535365","https://openalex.org/W1986269714","https://openalex.org/W2010557618","https://openalex.org/W2108710283","https://openalex.org/W2130954568","https://openalex.org/W2136647665","https://openalex.org/W2152620356","https://openalex.org/W2168739325","https://openalex.org/W4256577680"],"related_works":["https://openalex.org/W577409191","https://openalex.org/W3198596521","https://openalex.org/W3123622825","https://openalex.org/W3121350303","https://openalex.org/W2913022628","https://openalex.org/W2162655762","https://openalex.org/W2161367706","https://openalex.org/W2055345933","https://openalex.org/W2031153922","https://openalex.org/W1990452411"],"abstract_inverted_index":{"A":[0],"wide":[1],"variety":[2],"of":[3,15,25,50,64,78,85,89,138],"stochastic":[4],"models":[5],"have":[6],"an":[7,83],"important":[8],"property":[9],"known":[10],"as":[11,75,121],"reversibility.":[12,79],"The":[13],"analysis":[14,24,84],"reversible":[16,59,90,122,128],"Markov":[17,27,55,65,91],"chains":[18],"is":[19],"often":[20,33],"significantly":[21],"simpler":[22],"than":[23,149],"general":[26,118],"chains,":[28],"particularly":[29],"since":[30],"there":[31],"are":[32,132],"simple":[34],"closed-form":[35],"expressions":[36],"for":[37,54,116],"their":[38,101],"invariant":[39],"probability":[40],"mass":[41],"functions.":[42],"In":[43],"this":[44],"paper":[45],"we":[46,81],"study":[47],"the":[48,139],"structure":[49],"optimal":[51,62],"control":[52,63],"policies":[53],"decision":[56,66,92],"processes":[57,123],"with":[58],"dynamics.":[60],"For":[61],"processes,":[67,93],"significant":[68],"analytical":[69],"and":[70,126,145],"computational":[71],"simplifications":[72,114],"can":[73],"arise":[74],"a":[76,86,98,135,150,156],"result":[77],"Here":[80],"present":[82],"special":[87],"class":[88],"namely":[94],"those":[95],"that":[96,112],"contain":[97],"cycle":[99],"through":[100],"communication":[102],"graph":[103],"under":[104],"any":[105],"policy.":[106],"These":[107,130],"results":[108,131],"provide":[109],"encouraging":[110],"evidence":[111],"similar":[113],"hold":[115],"more":[117],"models,":[119],"such":[120],"without":[124],"cycles":[125],"partition":[127],"processes.":[129],"demonstrated":[133],"on":[134],"control-based":[136],"variant":[137],"Metropolis--Hastings":[140],"algorithm,":[141],"yielding":[142],"faster":[143],"convergence":[144],"better":[146],"asymptotic":[147],"performance":[148],"conventional":[151],"algorithm":[152],"when":[153],"applied":[154],"to":[155],"combinatorial":[157],"optimization":[158],"problem.":[159]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2040503115","counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2024-10-03T20:55:26.261202","created_date":"2016-06-24"}
