{"id":"https://openalex.org/W1604128822","doi":"https://doi.org/10.1109/cdc.2005.1583462","title":"Adaptive Optimization of Markov Reward Processes","display_name":"Adaptive Optimization of Markov Reward Processes","publication_year":2006,"publication_date":"2006-10-04","ids":{"openalex":"https://openalex.org/W1604128822","doi":"https://doi.org/10.1109/cdc.2005.1583462","mag":"1604128822"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2005.1583462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2005.1583462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th IEEE Conference on Decision and Control","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/A5004457099","display_name":"Enrique Campos-N\u00e1\u00f1ez","orcid":"https://orcid.org/0000-0002-3036-3772"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"E. Campos-Nanez","raw_affiliation_strings":["Department of Engineering Management and Systems Engineering, George Washington University, Washington D.C., DC, USA","Department of Engineering Management and Systems Engineering, The George Washington University, 1776, G Street Washington, DC, 20052, USA ecamposn@gwu.edu"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Management and Systems Engineering, George Washington University, Washington D.C., DC, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"Department of Engineering Management and Systems Engineering, The George Washington University, 1776, G Street Washington, DC, 20052, USA ecamposn@gwu.edu","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039633806","display_name":"Stephen D. Patek","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S.D. Patek","raw_affiliation_strings":["Department of Systems and Information Engineering, University of Virginia, Charlottesville, VA, USA","University of Virginia'"],"affiliations":[{"raw_affiliation_string":"Department of Systems and Information Engineering, University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"University of Virginia'","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5004457099"],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":null,"apc_paid":null,"fwci":0.8426,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74578172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"8034","last_page":"8041"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.9980999827384949,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9980999827384949,"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/T12288","display_name":"Optimization and Search Problems","score":0.9940000176429749,"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"}},{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9933000206947327,"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/convergence","display_name":"Convergence (economics)","score":0.733441948890686},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6896190643310547},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6482667326927185},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.6344780921936035},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.570270299911499},{"id":"https://openalex.org/keywords/local-optimum","display_name":"Local optimum","score":0.47279518842697144},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.45584267377853394},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.45060962438583374},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28755754232406616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2125076949596405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1663954257965088},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15808281302452087}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.733441948890686},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6896190643310547},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6482667326927185},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6344780921936035},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.570270299911499},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.47279518842697144},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.45584267377853394},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.45060962438583374},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28755754232406616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2125076949596405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1663954257965088},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15808281302452087},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2005.1583462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2005.1583462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th IEEE Conference on Decision and Control","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1523765121","https://openalex.org/W1554366315","https://openalex.org/W1576452626","https://openalex.org/W1608333589","https://openalex.org/W2003308588","https://openalex.org/W2009533501","https://openalex.org/W2009797711","https://openalex.org/W2014916251","https://openalex.org/W2049587418","https://openalex.org/W2068782949","https://openalex.org/W2078273556","https://openalex.org/W2082261506","https://openalex.org/W2091565802","https://openalex.org/W2097415784","https://openalex.org/W2098432798","https://openalex.org/W2104830490","https://openalex.org/W2110688863","https://openalex.org/W2115597380","https://openalex.org/W2120465407","https://openalex.org/W2121863487","https://openalex.org/W2122715318","https://openalex.org/W2123120471","https://openalex.org/W2123225686","https://openalex.org/W2125116811","https://openalex.org/W2142929170","https://openalex.org/W2143116909","https://openalex.org/W2149922771","https://openalex.org/W2150409232","https://openalex.org/W2159871982","https://openalex.org/W2171033527","https://openalex.org/W2173945562","https://openalex.org/W2320680700","https://openalex.org/W2329331109","https://openalex.org/W2503725246","https://openalex.org/W2531891978","https://openalex.org/W3215440445","https://openalex.org/W4214717370","https://openalex.org/W4245744559","https://openalex.org/W4302033506","https://openalex.org/W6673188923"],"related_works":["https://openalex.org/W2992415251","https://openalex.org/W4283765137","https://openalex.org/W2390808588","https://openalex.org/W1660242800","https://openalex.org/W2077211377","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2367222340"],"abstract_inverted_index":{"We":[0,33,49],"consider":[1],"the":[2,6,35,44,55,76,82,95,98],"problem":[3,123],"of":[4,9,16,21,28,38,46,60,75,81,97,100,124,127],"optimizing":[5],"average":[7],"reward":[8],"Markov":[10],"chains":[11],"controlled":[12],"by":[13],"two":[14],"sets":[15],"parameters":[17,23,78],"1)":[18],"a":[19,26,109,122,130],"set":[20,27],"tunable":[22,77],"and":[24,79,105],"2)":[25],"fixed":[29],"but":[30],"unknown":[31,83],"parameters.":[32,84],"study":[34],"convergence":[36,56],"characteristics":[37],"recursive":[39],"estimation":[40],"procedures":[41,64],"based":[42],"on":[43],"observation":[45],"regenerative":[47,103,110],"cycles.":[48],"also":[50],"provide":[51],"sufficient":[52],"conditions":[53],"for":[54],"to":[57,70,108],"local":[58],"optima":[59],"existing":[61],"simulation-based":[62,111],"optimization":[63],"under":[65],"parameter":[66],"certainty,":[67],"in":[68,114,121,129],"order":[69],"achieve":[71],"simultaneous":[72],"optimal":[73,125],"selection":[74],"identification":[80],"To":[85],"illustrate":[86],"our":[87],"approach,":[88],"we":[89],"discuss":[90],"an":[91,101],"algorithm":[92,112],"which":[93],"exploits":[94],"gradient":[96],"likelihood":[99],"observed":[102],"cycle":[104],"its":[106],"application":[107],"introduced":[113],"[1].":[115],"Our":[116],"results":[117],"are":[118],"illustrated":[119],"numerically":[120],"pricing":[126],"services":[128],"multi-class":[131],"loss":[132],"network.":[133]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}