{"id":"https://openalex.org/W4407950635","doi":"https://doi.org/10.1109/cdc56724.2024.10886003","title":"Reinforcement Learning Design for Quickest Change Detection","display_name":"Reinforcement Learning Design for Quickest Change Detection","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4407950635","doi":"https://doi.org/10.1109/cdc56724.2024.10886003"},"language":"en","primary_location":{"id":"doi:10.1109/cdc56724.2024.10886003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","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/A5020695596","display_name":"Austin Cooper","orcid":"https://orcid.org/0000-0001-9032-0750"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Austin Cooper","raw_affiliation_strings":["University of Florida,Department of Electrical and Computer Engineering,Gainesville FL,USA,32611"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida,Department of Electrical and Computer Engineering,Gainesville FL,USA,32611","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047988825","display_name":"Sean Meyn","orcid":"https://orcid.org/0000-0002-8558-365X"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean Meyn","raw_affiliation_strings":["University of Florida,Department of Electrical and Computer Engineering,Gainesville FL,USA,32611"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida,Department of Electrical and Computer Engineering,Gainesville FL,USA,32611","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31335084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3309","last_page":"3316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12659","display_name":"Innovation Diffusion and Forecasting","score":0.6277999877929688,"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/T12659","display_name":"Innovation Diffusion and Forecasting","score":0.6277999877929688,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7807955145835876},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6927438974380493},{"id":"https://openalex.org/keywords/change-detection","display_name":"Change detection","score":0.41738301515579224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37160107493400574}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7807955145835876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6927438974380493},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.41738301515579224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37160107493400574}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc56724.2024.10886003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","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":26,"referenced_works":["https://openalex.org/W1533983758","https://openalex.org/W2015820424","https://openalex.org/W2018319586","https://openalex.org/W2076522620","https://openalex.org/W2086012759","https://openalex.org/W2103641619","https://openalex.org/W2156168464","https://openalex.org/W2890946036","https://openalex.org/W3045688503","https://openalex.org/W3152994159","https://openalex.org/W3194017516","https://openalex.org/W3210638057","https://openalex.org/W4312913802","https://openalex.org/W4375868759","https://openalex.org/W4386057530","https://openalex.org/W4404037788","https://openalex.org/W6637423576","https://openalex.org/W6675932057","https://openalex.org/W6696270109","https://openalex.org/W6768877503","https://openalex.org/W6784311389","https://openalex.org/W6803418194","https://openalex.org/W6808047994","https://openalex.org/W6814111498","https://openalex.org/W6854396549","https://openalex.org/W6873375612"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2568858292","https://openalex.org/W1515964938","https://openalex.org/W2389381914","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433"],"abstract_inverted_index":{"The":[0],"field":[1],"of":[2,11,30,94,139,161,177],"quickest":[3],"change":[4],"detection":[5],"(QCD)":[6],"concerns":[7],"design":[8,103,205],"and":[9,27,74,126,181,199],"analysis":[10],"algorithms":[12,156],"to":[13,59,66,101,129,185],"estimate":[14],"in":[15,37,174,206],"real":[16],"time":[17,19],"the":[18,31,60,69,75,78,122,147,162,170,175,186],"at":[20],"which":[21],"an":[22,112],"important":[23],"event":[24],"takes":[25],"place,":[26],"identify":[28],"properties":[29],"post-change":[32],"behavior.":[33],"It":[34,166],"is":[35,57,81,116,124,135,167,172],"shown":[36,136,168],"this":[38,120],"paper":[39],"that":[40,56,83,137,169,182],"approaches":[41,100],"based":[42,50,89,110,157],"on":[43,51,90,111,158],"reinforcement":[44],"learning":[45],"(RL)":[46],"can":[47,142],"be":[48,143],"adapted":[49,58],"any":[52],"\u201csurrogate":[53],"information":[54,71],"state\u201d":[55],"observations.":[61],"Hence":[62],"we":[63],"are":[64,85,104],"left":[65],"choose":[67],"both":[68],"surrogate":[70],"state":[72],"process":[73],"algorithm.":[76],"For":[77],"former,":[79],"it":[80,134],"argued":[82],"there":[84],"many":[86],"choices":[87],"available,":[88],"a":[91,130,159,183,201],"rich":[92],"theory":[93],"asymptotic":[95],"statistics":[96],"for":[97,119,149,203],"QCD.":[98],"Two":[99],"RL":[102],"considered:":[105],"(i)":[106],"Stochastic":[107],"gradient":[108],"descent":[109],"actor-critic":[113],"formulation.":[114],"Theory":[115],"largely":[117],"complete":[118],"approach:":[121],"algorithm":[123,171,204],"unbiased,":[125],"will":[127],"converge":[128],"local":[131],"minimum.":[132],"However,":[133],"variance":[138],"stochastic":[140],"gradients":[141],"very":[144],"large,":[145],"necessitating":[146],"need":[148],"commensurately":[150],"long":[151],"run":[152],"times.":[153],"(ii)":[154],"Q-learning":[155],"version":[160],"projected":[163,187],"Bellman":[164,188],"equation.":[165],"stable,":[173],"sense":[176],"bounded":[178],"sample":[179],"paths,":[180],"solution":[184],"equation":[189],"exists":[190],"under":[191],"mild":[192],"conditions.":[193],"Numerical":[194],"experiments":[195],"illustrate":[196],"these":[197],"findings,":[198],"provide":[200],"roadmap":[202],"more":[207],"general":[208],"settings.":[209]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}