{"id":"https://openalex.org/W2113617958","doi":"https://doi.org/10.1109/acc.2008.4586462","title":"Optimal trade-off between exploration and exploitation","display_name":"Optimal trade-off between exploration and exploitation","publication_year":2008,"publication_date":"2008-06-01","ids":{"openalex":"https://openalex.org/W2113617958","doi":"https://doi.org/10.1109/acc.2008.4586462","mag":"2113617958"},"language":"en","primary_location":{"id":"doi:10.1109/acc.2008.4586462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2008.4586462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 American Control Conference","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/A5062033277","display_name":"Alex Simpkins","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alex Simpkins","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, University of California, La Jolla, CA, USA","Dept. of Mech. and Aerosp. Eng., Univ. of California San Diego, La Jolla, CA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of California, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Dept. of Mech. and Aerosp. Eng., Univ. of California San Diego, La Jolla, CA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028003129","display_name":"Raymond de Callafon","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raymond de Callafon","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, University of California, La Jolla, CA, USA","Dept. of Mech. and Aerosp. Eng., Univ. of California San Diego, La Jolla, CA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of California, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Dept. of Mech. and Aerosp. Eng., Univ. of California San Diego, La Jolla, CA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108520754","display_name":"Emanuel Todorov","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emanuel Todorov","raw_affiliation_strings":["Department of Cognitive Science, University of California, San Diego, CA, USA","University of California,  San Diego"],"affiliations":[{"raw_affiliation_string":"Department of Cognitive Science, University of California, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"University of California,  San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062033277"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":1.1572,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.77178132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10982","display_name":"Motor Control and Adaptation","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10982","display_name":"Motor Control and Adaptation","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10114","display_name":"Balance, Gait, and Falls Prevention","score":0.9638000130653381,"subfield":{"id":"https://openalex.org/subfields/3612","display_name":"Physical Therapy, Sports Therapy and Rehabilitation"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9484999775886536,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7725095748901367},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6823443174362183},{"id":"https://openalex.org/keywords/formalism","display_name":"Formalism (music)","score":0.5370840430259705},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5166359543800354},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.4995737075805664},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.49934935569763184},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4535568058490753},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.43019038438796997},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.41118869185447693},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21660196781158447},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14945486187934875},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.13702690601348877}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7725095748901367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6823443174362183},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.5370840430259705},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5166359543800354},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.4995737075805664},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.49934935569763184},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4535568058490753},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.43019038438796997},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.41118869185447693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21660196781158447},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14945486187934875},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.13702690601348877},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acc.2008.4586462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2008.4586462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 American Control Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W178056938","https://openalex.org/W1529558080","https://openalex.org/W1600022730","https://openalex.org/W1679855469","https://openalex.org/W1854776945","https://openalex.org/W1964377184","https://openalex.org/W1965324089","https://openalex.org/W1981159762","https://openalex.org/W1988472059","https://openalex.org/W2019374575","https://openalex.org/W2029776687","https://openalex.org/W2067603665","https://openalex.org/W2090167557","https://openalex.org/W2093817972","https://openalex.org/W2101905421","https://openalex.org/W2103116139","https://openalex.org/W2108794116","https://openalex.org/W2268119109","https://openalex.org/W2293807537","https://openalex.org/W2725760423","https://openalex.org/W3022192383","https://openalex.org/W4214612718","https://openalex.org/W4250248097","https://openalex.org/W4302367620","https://openalex.org/W6637244337"],"related_works":["https://openalex.org/W2943897807","https://openalex.org/W3120484221","https://openalex.org/W4366198066","https://openalex.org/W3047748938","https://openalex.org/W2358522863","https://openalex.org/W4386034604","https://openalex.org/W278441094","https://openalex.org/W3099285423","https://openalex.org/W4381248241","https://openalex.org/W2336173978"],"abstract_inverted_index":{"Control":[0],"in":[1,84,150],"an":[2],"uncertain":[3],"environment":[4],"often":[5],"involves":[6],"a":[7,45,85,125],"trade-off":[8,94],"between":[9],"exploratory":[10],"actions,":[11],"whose":[12],"goal":[13],"is":[14,60,97,110,143],"to":[15,69,99,107,136],"gather":[16],"sensory":[17],"information,":[18],"and":[19,29,95],"\"regular\"":[20],"actions":[21],"which":[22,72,87,152],"exploit":[23],"the":[24,31,50,63,74,82,89,92,112,115,119],"information":[25],"gathered":[26],"so":[27],"far":[28],"pursue":[30],"task":[32],"objectives.":[33],"In":[34,56,77],"principle":[35],"both":[36],"types":[37],"of":[38,52,91,114],"action":[39],"can":[40],"be":[41,67],"modeled":[42],"by":[43],"minimizing":[44],"single":[46],"cost":[47],"function":[48],"within":[49],"framework":[51],"stochastic":[53],"optimal":[54,103],"control.":[55,104],"practice":[57],"however":[58],"this":[59,78],"difficult,":[61],"because":[62],"control":[64,132],"law":[65],"must":[66],"sensitive":[68],"estimation":[70],"uncertainty":[71],"violates":[73],"certainty-equivalence":[75],"principle.":[76],"paper":[79],"we":[80],"formalize":[81],"problem":[83],"way":[86],"captures":[88],"essence":[90],"exploration-exploitation":[93],"yet":[96],"amenable":[98],"numerical":[100],"methods":[101],"for":[102,146],"The":[105,130],"key":[106],"our":[108],"approach":[109],"augmenting":[111],"dynamics":[113],"partially-observable":[116],"plant":[117],"with":[118],"Kalman":[120],"filter":[121],"dynamics,":[122],"thus":[123],"obtaining":[124],"higher-dimensional":[126],"but":[127],"fully-observable":[128],"plant.":[129],"resulting":[131],"laws":[133],"compare":[134],"favorably":[135],"other":[137],"more":[138],"ad-hoc":[139],"approaches.":[140],"Our":[141],"formalism":[142],"also":[144],"suitable":[145],"modeling":[147],"human":[148],"behavior":[149],"tasks":[151],"benefit":[153],"from":[154],"active":[155],"exploration.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
