{"id":"https://openalex.org/W4415137818","doi":"https://doi.org/10.1109/cdc57313.2025.11312840","title":"Revisiting Dynamic Programming for Exploration: Insights from a Simple Dual Control Problem","display_name":"Revisiting Dynamic Programming for Exploration: Insights from a Simple Dual Control Problem","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W4415137818","doi":"https://doi.org/10.1109/cdc57313.2025.11312840"},"language":"en","primary_location":{"id":"doi:10.1109/cdc57313.2025.11312840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.univ-lorraine.fr/hal-05102303/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104136589","display_name":"Ying Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ying Wang","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Decision and Control Systems,Stockholm,Sweden,10044","KTH - KTH Royal Institute of Technology [Stockholm] (SE-100 44, Stockholm, Sweden - Sweden)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Decision and Control Systems,Stockholm,Sweden,10044","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"KTH - KTH Royal Institute of Technology [Stockholm] (SE-100 44, Stockholm, Sweden - Sweden)","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088692636","display_name":"K\u00e9vin Colin","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210110792","display_name":"Centre de Recherche en Automatique de Nancy","ror":"https://ror.org/022r5hc56","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210099203","https://openalex.org/I4210100260","https://openalex.org/I4210110792","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"K\u00e9vin Colin","raw_affiliation_strings":["Université de Lorraine,CNRS, CRAN,Nancy,France,F-54000","CRAN - Centre de Recherche en Automatique de Nancy (Universit\u00e9 de Lorraine, Campus Sciences, BP 70239, 54506 Vandoeuvre-les-Nancy Cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Lorraine,CNRS, CRAN,Nancy,France,F-54000","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1294671590","https://openalex.org/I4210110792"]},{"raw_affiliation_string":"CRAN - Centre de Recherche en Automatique de Nancy (Universit\u00e9 de Lorraine, Campus Sciences, BP 70239, 54506 Vandoeuvre-les-Nancy Cedex - France)","institution_ids":["https://openalex.org/I4210110792","https://openalex.org/I90183372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075622665","display_name":"Yue Ju","orcid":"https://orcid.org/0009-0006-4437-1833"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Yue Ju","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Decision and Control Systems,Stockholm,Sweden,10044","KTH - KTH Royal Institute of Technology [Stockholm] (SE-100 44, Stockholm, Sweden - Sweden)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Decision and Control Systems,Stockholm,Sweden,10044","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"KTH - KTH Royal Institute of Technology [Stockholm] (SE-100 44, Stockholm, Sweden - Sweden)","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005023019","display_name":"Mirko Pasquini","orcid":"https://orcid.org/0000-0002-7856-4899"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Mirko Pasquini","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Decision and Control Systems,Stockholm,Sweden,10044","KTH - KTH Royal Institute of Technology [Stockholm] (SE-100 44, Stockholm, Sweden - Sweden)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Decision and Control Systems,Stockholm,Sweden,10044","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"KTH - KTH Royal Institute of Technology [Stockholm] (SE-100 44, Stockholm, Sweden - Sweden)","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047606099","display_name":"H\u00e5kan Hjalmarsson","orcid":"https://orcid.org/0000-0002-9368-3079"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"H\u00e5kan Hjalmarsson","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Decision and Control Systems,Stockholm,Sweden,10044","KTH - KTH Royal Institute of Technology [Stockholm] (SE-100 44, Stockholm, Sweden - Sweden)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Decision and Control Systems,Stockholm,Sweden,10044","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"KTH - KTH Royal Institute of Technology [Stockholm] (SE-100 44, Stockholm, Sweden - Sweden)","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31270022,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1018","last_page":"1023"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.9769999980926514,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.9769999980926514,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/dynamic-programming","display_name":"Dynamic programming","score":0.6254000067710876},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.6129000186920166},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.566100001335144},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5393999814987183},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5268999934196472},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4871000051498413},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.48590001463890076},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.4733000099658966}],"concepts":[{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6389999985694885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6355000138282776},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6254000067710876},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.6129000186920166},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.566100001335144},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5393999814987183},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5268999934196472},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4871000051498413},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.48590001463890076},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.4733000099658966},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3905999958515167},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.29600000381469727},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05102303v1","is_oa":true,"landing_page_url":"https://hal.univ-lorraine.fr/hal-05102303","pdf_url":"https://hal.univ-lorraine.fr/hal-05102303/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC), Dec 2025, Rio de Janeiro, Brazil. pp.1018-1023, ⟨10.1109/CDC57313.2025.11312840⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-05102303v1","is_oa":true,"landing_page_url":"https://hal.univ-lorraine.fr/hal-05102303","pdf_url":"https://hal.univ-lorraine.fr/hal-05102303/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC), Dec 2025, Rio de Janeiro, Brazil. pp.1018-1023, ⟨10.1109/CDC57313.2025.11312840⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415137818.pdf","grobid_xml":"https://content.openalex.org/works/W4415137818.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,185],"dual":[1],"control":[2,139,159],"problem,":[3,78],"first":[4],"introduced":[5],"by":[6,43,111],"Feldbaum":[7],"in":[8,99],"the":[9,15,38,55,64,68,95,106,142,146,165,175,179,200],"1960s,":[10],"is":[11,109,169,188],"recognized":[12],"as":[13],"encapsulating":[14],"\"exploration":[16],"versus":[17],"exploitation\"":[18],"dilemma,":[19],"central":[20],"to":[21,33,54,80,172],"online":[22],"learning":[23],"and":[24,84,124,136,182],"control.":[25],"Numerous":[26],"heuristic-based":[27],"exploration":[28,91,123,167,176,197],"methods":[29,198],"have":[30],"been":[31],"developed":[32],"facilitate":[34],"active":[35],"learning.":[36],"However,":[37],"theoretically":[39],"optimal":[40,107],"solution":[41,98],"provided":[42],"dynamic":[44],"programming":[45],"(DP)":[46],"remains":[47],"computationally":[48],"intractable":[49],"for":[50,73,88],"most":[51],"problems":[52],"due":[53],"curse":[56],"of":[57,70,118,145,164],"dimensionality.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62,103],"revisit":[63],"DP":[65,97,148],"framework":[66],"within":[67],"context":[69],"regret":[71],"minimization":[72],"a":[74,113],"simple":[75,101],"real-time":[76],"optimization":[77,115],"aiming":[79],"identify":[81],"valuable":[82],"insights":[83],"uncover":[85],"new":[86],"avenues":[87],"simplified":[89],"DP-based":[90,166],"strategies.":[92],"By":[93],"deriving":[94],"two-horizon":[96,147],"our":[100],"setting,":[102],"observe":[104],"that":[105],"input":[108],"obtained":[110],"solving":[112],"closed-form":[114],"problem":[116],"composed":[117],"two":[119],"distinct":[120],"components":[121],"representing":[122],"exploitation":[125,181],"separately,":[126],"clearly":[127],"highlighting":[128],"their":[129],"inherent":[130],"trade-off.":[131],"For":[132],"longer":[133],"horizons,":[134],"receding":[135],"cyclic":[137],"horizon":[138],"based":[140,177],"on":[141,178],"iterative":[143],"application":[144],"provide":[149],"possible":[150],"approximations,":[151],"reducing":[152],"computational":[153],"complexity":[154],"while":[155],"yielding":[156],"useful":[157],"suboptimal":[158],"policies.":[160],"A":[161],"key":[162],"advantage":[163],"method":[168,187],"its":[170],"ability":[171],"automatically":[173],"adjust":[174],"current":[180],"system":[183],"uncertainty.":[184],"proposed":[186],"studied":[189],"numerically":[190],"through":[191],"comparative":[192],"evaluations":[193],"against":[194],"classical":[195],"heuristic":[196],"from":[199],"literature.":[201]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-14T00:00:00"}