{"id":"https://openalex.org/W4391709651","doi":"https://doi.org/10.1109/tsp.2024.3372699","title":"Multi-Timescale Ensemble $Q$-Learning for Markov Decision Process Policy Optimization","display_name":"Multi-Timescale Ensemble $Q$-Learning for Markov Decision Process Policy Optimization","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391709651","doi":"https://doi.org/10.1109/tsp.2024.3372699"},"language":"en","primary_location":{"id":"doi:10.1109/tsp.2024.3372699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2024.3372699","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Signal Processing","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2402.05476","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038241805","display_name":"Talha Bozkus","orcid":"https://orcid.org/0000-0001-5178-8676"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Talha Bozkus","raw_affiliation_strings":["Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072739163","display_name":"Urbashi Mitra","orcid":"https://orcid.org/0000-0002-8896-1177"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Urbashi Mitra","raw_affiliation_strings":["Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5038241805"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":2.5919,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.90471256,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"72","issue":null,"first_page":"1427","last_page":"1442"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.7694000005722046,"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/T10703","display_name":"Business Process Modeling and Analysis","score":0.7694000005722046,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.7537000179290771,"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/T10763","display_name":"Digital Transformation in Industry","score":0.7014999985694885,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.7585041522979736},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.6039037704467773},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5859715938568115},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5751201510429382},{"id":"https://openalex.org/keywords/decision-process","display_name":"Decision process","score":0.5078676342964172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5068989396095276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44582968950271606},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.42326247692108154},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38863253593444824},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.26863062381744385},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.22552955150604248},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.18679854273796082},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16543346643447876},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08022338151931763}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7585041522979736},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.6039037704467773},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5859715938568115},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5751201510429382},{"id":"https://openalex.org/C2984634286","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision process","level":2,"score":0.5078676342964172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5068989396095276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44582968950271606},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.42326247692108154},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38863253593444824},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.26863062381744385},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.22552955150604248},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.18679854273796082},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16543346643447876},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08022338151931763},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tsp.2024.3372699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2024.3372699","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2402.05476","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.05476","pdf_url":"https://arxiv.org/pdf/2402.05476","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.05476","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.05476","pdf_url":"https://arxiv.org/pdf/2402.05476","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G1032653388","display_name":null,"funder_award_id":"CCF-2200221","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2291874825","display_name":null,"funder_award_id":"N00014-15-1-2550","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G271388722","display_name":null,"funder_award_id":"RINGS-2148313","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3642481650","display_name":null,"funder_award_id":"2018-04359","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G4657123650","display_name":null,"funder_award_id":"W911NF1910269","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G622752539","display_name":null,"funder_award_id":"CCF-2008927","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G655554843","display_name":null,"funder_award_id":"CIF-2311653","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7660872698","display_name":null,"funder_award_id":"DESC0021417","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8741606322","display_name":null,"funder_award_id":"503400-78050","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320332603","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4391709651.pdf"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W166862392","https://openalex.org/W1918371733","https://openalex.org/W2020129240","https://openalex.org/W2044768394","https://openalex.org/W2089834667","https://openalex.org/W2106622742","https://openalex.org/W2121712307","https://openalex.org/W2124715093","https://openalex.org/W2124839177","https://openalex.org/W2130304665","https://openalex.org/W2145979309","https://openalex.org/W2146950091","https://openalex.org/W2746553466","https://openalex.org/W2912285628","https://openalex.org/W2964278142","https://openalex.org/W3005226193","https://openalex.org/W3008988392","https://openalex.org/W3044889796","https://openalex.org/W3197013133","https://openalex.org/W3207342878","https://openalex.org/W4312814819","https://openalex.org/W4360584597","https://openalex.org/W4372266961","https://openalex.org/W6602057636","https://openalex.org/W6637967152","https://openalex.org/W6681795105","https://openalex.org/W6712173889","https://openalex.org/W6735506055","https://openalex.org/W6748519856","https://openalex.org/W6751494529","https://openalex.org/W6762863188","https://openalex.org/W6763704811","https://openalex.org/W6769467942","https://openalex.org/W6771936881","https://openalex.org/W6774583691","https://openalex.org/W6789305357","https://openalex.org/W6791334070","https://openalex.org/W6792120457","https://openalex.org/W6796971187","https://openalex.org/W6797702751","https://openalex.org/W6800089562","https://openalex.org/W6846298114","https://openalex.org/W7000276917","https://openalex.org/W7047359524"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2101748387","https://openalex.org/W2357975469","https://openalex.org/W4380550992","https://openalex.org/W4322760752","https://openalex.org/W3096874164","https://openalex.org/W2970347269","https://openalex.org/W2146763310","https://openalex.org/W3167472281","https://openalex.org/W2937181779"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,40],"(RL)":[2],"is":[3,50],"a":[4,35],"classical":[5,45],"tool":[6],"to":[7,52,100,142,150],"solve":[8],"network":[9,132],"control":[10],"or":[11],"policy":[12,105,146],"optimization":[13],"problems":[14],"in":[15,83,168],"unknown":[16],"environments.":[17],"The":[18,109],"original":[19],"<italic":[20,46,66,122,158],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[21,47,67,123,159],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Q</i>":[22,48,68,124,160],"-learning":[23,49,69,161],"suffers":[24],"from":[25],"performance":[26],"and":[27,78,121],"complexity":[28,154],"challenges":[29,55],"across":[30,130],"very":[31],"large":[32],"networks.":[33],"Herein,":[34],"novel":[36],"model-free":[37],"ensemble":[38],"reinforcement":[39],"algorithm":[41,138],"which":[42,58],"adapts":[43],"the":[44,85,96,113,116,136,156,169],"proposed":[51,137],"handle":[53],"these":[54],"for":[56],"networks":[57],"admit":[59],"Markov":[60],"decision":[61],"process":[62],"(MDP)":[63],"models.":[64],"Multiple":[65],"algorithms":[70],"are":[71,87,126],"run":[72],"on":[73,95],"multiple,":[74],"distinct,":[75],"synthetically":[76],"created":[77],"structurally":[79],"related":[80],"Markovian":[81],"environments":[82],"parallel;":[84],"outputs":[86],"fused":[88],"using":[89],"an":[90,102],"adaptive":[91],"weighting":[92],"mechanism":[93],"based":[94],"Jensen-Shannon":[97],"divergence":[98],"(JSD)":[99],"obtain":[101],"approximately":[103],"optimal":[104],"with":[106,148],"low":[107],"complexity.":[108],"theoretical":[110,170],"justification":[111],"of":[112,118],"algorithm,":[114],"including":[115],"convergence":[117],"key":[119],"statistics":[120],"-functions":[125],"provided.":[127],"Numerical":[128,163],"results":[129,164],"several":[131],"models":[133],"show":[134],"that":[135],"can":[139],"achieve":[140],"up":[141,149],"55%":[143],"less":[144,152],"average":[145],"error":[147],"50%":[151],"runtime":[153],"than":[155],"state-of-the-art":[157],"algorithms.":[162],"validate":[165],"assumptions":[166],"made":[167],"analysis.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}