{"id":"https://openalex.org/W2129919091","doi":"https://doi.org/10.1109/cdc.2005.1583460","title":"A Two-Timescale Simulation-Based Gradient Algorithm for Weighted Cost Markov Decision Processes","display_name":"A Two-Timescale Simulation-Based Gradient Algorithm for Weighted Cost Markov Decision Processes","publication_year":2006,"publication_date":"2006-10-04","ids":{"openalex":"https://openalex.org/W2129919091","doi":"https://doi.org/10.1109/cdc.2005.1583460","mag":"2129919091"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2005.1583460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2005.1583460","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/A5100693517","display_name":"Ying He","orcid":"https://orcid.org/0000-0003-1733-9791"},"institutions":[{"id":"https://openalex.org/I2800548410","display_name":"United States National Library of Medicine","ror":"https://ror.org/0060t0j89","country_code":"US","type":"archive","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410"]},{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ying He","raw_affiliation_strings":["Faculty in the Institute for Systems Research, National Library of Medicine, MD, USA","Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, MD 20894, USA. yihe@mail.nih.gov"],"affiliations":[{"raw_affiliation_string":"Faculty in the Institute for Systems Research, National Library of Medicine, MD, USA","institution_ids":["https://openalex.org/I2800548410"]},{"raw_affiliation_string":"Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, MD 20894, USA. yihe@mail.nih.gov","institution_ids":["https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000889975","display_name":"Michael C. Fu","orcid":"https://orcid.org/0000-0003-2105-4932"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M.C. Fu","raw_affiliation_strings":["Faculty in the Institute for Systems Research, University of Maryland, College Park, MD, USA","University of Maryland, College Park"],"affiliations":[{"raw_affiliation_string":"Faculty in the Institute for Systems Research, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013807415","display_name":"Steven I. Marcus","orcid":"https://orcid.org/0000-0002-4926-9567"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S.I. Marcus","raw_affiliation_strings":["Faculty in the Institute for Systems Research, University of Maryland, College Park, MD, USA","University of Maryland, College Park"],"affiliations":[{"raw_affiliation_string":"Faculty in the Institute for Systems Research, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100693517"],"corresponding_institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I2800548410"],"apc_list":null,"apc_paid":null,"fwci":0.437,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70699995,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"8022","last_page":"8027"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10524","display_name":"Traffic control and management","score":0.998199999332428,"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/T10698","display_name":"Transportation Planning and Optimization","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6762351989746094},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6755332350730896},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6679702997207642},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5956985950469971},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5255488157272339},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4753517806529999},{"id":"https://openalex.org/keywords/forward-algorithm","display_name":"Forward algorithm","score":0.4626489579677582},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4475546181201935},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.2543448805809021},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20852875709533691},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18190565705299377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6762351989746094},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6755332350730896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6679702997207642},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5956985950469971},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5255488157272339},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4753517806529999},{"id":"https://openalex.org/C196455857","wikidata":"https://www.wikidata.org/wiki/Q5473264","display_name":"Forward algorithm","level":5,"score":0.4626489579677582},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4475546181201935},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.2543448805809021},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20852875709533691},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18190565705299377},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cdc.2005.1583460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2005.1583460","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.362.3597","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.362.3597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.rhsmith.umd.edu/faculty/mfu/fu_files/HFM05.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W166334722","https://openalex.org/W1516403053","https://openalex.org/W1554366315","https://openalex.org/W1576452626","https://openalex.org/W2004401795","https://openalex.org/W2009303086","https://openalex.org/W2022327893","https://openalex.org/W2063123975","https://openalex.org/W2082261506","https://openalex.org/W2094364653","https://openalex.org/W2100857832","https://openalex.org/W2111303831","https://openalex.org/W2111737463","https://openalex.org/W2120465407","https://openalex.org/W2163743900","https://openalex.org/W3140354042","https://openalex.org/W6630857578"],"related_works":["https://openalex.org/W2161328464","https://openalex.org/W2379651310","https://openalex.org/W2382132287","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2084326697","https://openalex.org/W2027903142","https://openalex.org/W2354322608","https://openalex.org/W2804608325","https://openalex.org/W2077211377"],"abstract_inverted_index":{"We":[0],"develop":[1],"a":[2,28],"novel":[3],"two-timescale":[4],"simulation-based":[5],"gradient":[6],"algorithm":[7,21,34],"for":[8],"weighted":[9],"cost":[10],"Markov":[11],"Decision":[12],"Process":[13],"(MDP)":[14],"problems,":[15],"illustrate":[16],"the":[17,33,40],"effectiveness":[18],"of":[19],"this":[20],"by":[22],"carrying":[23],"out":[24],"numerical":[25],"experiments":[26],"on":[27],"parking":[29],"example,":[30],"and":[31],"compare":[32],"with":[35],"two":[36],"other":[37],"algorithms":[38],"in":[39],"literature.":[41]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
