{"id":"https://openalex.org/W2963843073","doi":"https://doi.org/10.1109/adprl.2014.7010616","title":"Nonparametric infinite horizon Kullback-Leibler stochastic control","display_name":"Nonparametric infinite horizon Kullback-Leibler stochastic control","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2963843073","doi":"https://doi.org/10.1109/adprl.2014.7010616","mag":"2963843073"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2014.7010616","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","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/A5091291585","display_name":"Yunpeng Pan","orcid":"https://orcid.org/0000-0002-3373-0769"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yunpeng Pan","raw_affiliation_strings":["Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, Georgia"],"affiliations":[{"raw_affiliation_string":"Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, Georgia","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044505993","display_name":"Evangelos A. Theodorou","orcid":"https://orcid.org/0000-0002-0834-5738"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evangelos A. Theodorou","raw_affiliation_strings":["Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, Georgia"],"affiliations":[{"raw_affiliation_string":"Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, Georgia","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091291585"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":1.227,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.86237334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"6","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9980999827384949,"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/T11236","display_name":"Control Systems and Identification","score":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.7467818856239319},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6654156446456909},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6371121406555176},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5721564888954163},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5604673624038696},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.5415123105049133},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5196136832237244},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5146732926368713},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.5036765933036804},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4990367889404297},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.49785470962524414},{"id":"https://openalex.org/keywords/parametric-programming","display_name":"Parametric programming","score":0.48271891474723816},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4711293876171112},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4472179114818573},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.4398183226585388},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.4362087547779083},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4034695327281952},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.359228253364563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16473063826560974},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.1288871467113495},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1185760498046875}],"concepts":[{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.7467818856239319},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6654156446456909},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6371121406555176},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5721564888954163},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5604673624038696},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.5415123105049133},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5196136832237244},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5146732926368713},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.5036765933036804},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4990367889404297},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.49785470962524414},{"id":"https://openalex.org/C2776045410","wikidata":"https://www.wikidata.org/wiki/Q25111241","display_name":"Parametric programming","level":3,"score":0.48271891474723816},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4711293876171112},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4472179114818573},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.4398183226585388},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.4362087547779083},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4034695327281952},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.359228253364563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16473063826560974},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.1288871467113495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1185760498046875},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/adprl.2014.7010616","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1502922572","https://openalex.org/W1746819321","https://openalex.org/W1966514629","https://openalex.org/W2006373179","https://openalex.org/W2021231414","https://openalex.org/W2025309173","https://openalex.org/W2043962331","https://openalex.org/W2060921867","https://openalex.org/W2073605536","https://openalex.org/W2093524643","https://openalex.org/W2128152413","https://openalex.org/W2129564505","https://openalex.org/W2145060720","https://openalex.org/W2155919457","https://openalex.org/W2160840682","https://openalex.org/W4211049957","https://openalex.org/W6681439324"],"related_works":["https://openalex.org/W3118585974","https://openalex.org/W1970837389","https://openalex.org/W295753746","https://openalex.org/W2246584798","https://openalex.org/W3148378729","https://openalex.org/W2952419548","https://openalex.org/W4367180203","https://openalex.org/W1965471086","https://openalex.org/W2370838117","https://openalex.org/W2291873833"],"abstract_inverted_index":{"We":[0],"present":[1],"two":[2],"nonparametric":[3,80],"approaches":[4],"to":[5,24],"Kullback-Leibler":[6],"(KL)":[7],"control,":[8],"or":[9],"linearly-solvable":[10],"Markov":[11],"decision":[12],"problem":[13],"(LMDP)":[14],"based":[15,50],"on":[16,51,62],"Gaussian":[17],"processes":[18],"(GP)":[19],"and":[20,37,82,96],"Nystr\u00f6m":[21],"approximation.":[22],"Compared":[23],"recently":[25],"developed":[26],"parametric":[27],"methods,":[28],"the":[29,44,67,94,99],"proposed":[30,100],"data-driven":[31],"frameworks":[32],"feature":[33],"accurate":[34],"function":[35],"approximation":[36],"efficient":[38],"on-line":[39,84],"operations.":[40],"Theoretically,":[41],"we":[42,73],"derive":[43],"mathematical":[45],"connection":[46],"of":[47,98],"KL":[48],"control":[49,58,77],"dynamic":[52],"programming":[53],"with":[54,87],"earlier":[55],"work":[56],"in":[57,79],"theory":[59],"which":[60],"relies":[61],"information":[63],"theoretic":[64],"dualities":[65],"for":[66],"infinite":[68],"time":[69],"horizon":[70],"case.":[71],"Algorithmically,":[72],"give":[74],"explicit":[75],"optimal":[76],"policies":[78],"forms,":[81],"propose":[83],"update":[85],"schemes":[86],"budgeted":[88],"computational":[89],"costs.":[90],"Numerical":[91],"results":[92],"demonstrate":[93],"effectiveness":[95],"usefulness":[97],"frameworks.":[101]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}