{"id":"https://openalex.org/W4407949041","doi":"https://doi.org/10.1109/cdc56724.2024.10886246","title":"Variational Dynamic Programming for Stochastic Optimal Control","display_name":"Variational Dynamic Programming for Stochastic Optimal Control","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4407949041","doi":"https://doi.org/10.1109/cdc56724.2024.10886246"},"language":"en","primary_location":{"id":"doi:10.1109/cdc56724.2024.10886246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886246","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/A5066835422","display_name":"Marc Lambert","orcid":"https://orcid.org/0000-0002-6049-8184"},"institutions":[{"id":"https://openalex.org/I4210153303","display_name":"\u00c9cole Normale Sup\u00e9rieure d'Abidjan","ror":"https://ror.org/04xtpyw05","country_code":"CI","type":"education","lineage":["https://openalex.org/I4210153303"]},{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]}],"countries":["BI","CI"],"is_corresponding":true,"raw_author_name":"Marc Lambert","raw_affiliation_strings":["PSL Research University,Inria,Departement d’Informatique de l’Ecole Normale Superieure"],"affiliations":[{"raw_affiliation_string":"PSL Research University,Inria,Departement d’Informatique de l’Ecole Normale Superieure","institution_ids":["https://openalex.org/I4210103330","https://openalex.org/I4210153303"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001483226","display_name":"Francis Bach","orcid":"https://orcid.org/0000-0001-8644-1058"},"institutions":[{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]},{"id":"https://openalex.org/I4210153303","display_name":"\u00c9cole Normale Sup\u00e9rieure d'Abidjan","ror":"https://ror.org/04xtpyw05","country_code":"CI","type":"education","lineage":["https://openalex.org/I4210153303"]}],"countries":["BI","CI"],"is_corresponding":false,"raw_author_name":"Francis Bach","raw_affiliation_strings":["PSL Research University,Inria,Departement d’Informatique de l’Ecole Normale Superieure"],"affiliations":[{"raw_affiliation_string":"PSL Research University,Inria,Departement d’Informatique de l’Ecole Normale Superieure","institution_ids":["https://openalex.org/I4210103330","https://openalex.org/I4210153303"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037120106","display_name":"Silv\u00e8re Bonnabel","orcid":"https://orcid.org/0000-0002-6001-7766"},"institutions":[{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Silvere Bonnabel","raw_affiliation_strings":["PSL Research University, Centre for Robotics,Mines Paris PSL"],"affiliations":[{"raw_affiliation_string":"PSL Research University, Centre for Robotics,Mines Paris PSL","institution_ids":["https://openalex.org/I2746051580"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066835422"],"corresponding_institution_ids":["https://openalex.org/I4210103330","https://openalex.org/I4210153303"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31753207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1863","last_page":"1870"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.8949000239372253,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.8949000239372253,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8754000067710876,"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/dynamic-programming","display_name":"Dynamic programming","score":0.6207035779953003},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5880045890808105},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5676773190498352},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5488721132278442},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.5041550397872925},{"id":"https://openalex.org/keywords/stochastic-programming","display_name":"Stochastic programming","score":0.4696813225746155},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.42674779891967773},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3222281038761139},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29430943727493286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21266144514083862}],"concepts":[{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6207035779953003},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5880045890808105},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5676773190498352},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5488721132278442},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.5041550397872925},{"id":"https://openalex.org/C137631369","wikidata":"https://www.wikidata.org/wiki/Q7617831","display_name":"Stochastic programming","level":2,"score":0.4696813225746155},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42674779891967773},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3222281038761139},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29430943727493286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21266144514083862}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc56724.2024.10886246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886246","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":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1619551699","https://openalex.org/W1966514629","https://openalex.org/W2048469131","https://openalex.org/W2054091988","https://openalex.org/W2093524643","https://openalex.org/W2107464055","https://openalex.org/W2107662876","https://openalex.org/W2155772159","https://openalex.org/W3027624373","https://openalex.org/W3157027468","https://openalex.org/W3207783658","https://openalex.org/W4206593053","https://openalex.org/W4255064568","https://openalex.org/W4293052541","https://openalex.org/W4298014976","https://openalex.org/W6674884181","https://openalex.org/W6681478256","https://openalex.org/W6747473740","https://openalex.org/W6768720322"],"related_works":["https://openalex.org/W1932159282","https://openalex.org/W175006096","https://openalex.org/W4285537323","https://openalex.org/W2379312070","https://openalex.org/W2136173754","https://openalex.org/W2086136595","https://openalex.org/W2110050003","https://openalex.org/W2953025626","https://openalex.org/W2499081552","https://openalex.org/W2366053282"],"abstract_inverted_index":{"We":[0,76,114],"consider":[1],"the":[2,9,14,25,31,45,66,84,89,110,120],"problem":[3,122],"of":[4,16,123],"stochastic":[5],"optimal":[6,54],"control,":[7],"where":[8,21,65],"state-feedback":[10],"control":[11,55,85,92,108],"policies":[12,86],"take":[13],"form":[15],"a":[17,22,35,61,72],"probability":[18],"distribution":[19],"and":[20,87,109],"penalty":[23],"on":[24,52,119],"entropy":[26],"is":[27,69],"added.":[28],"By":[29],"viewing":[30],"cost":[32],"function":[33,68],"as":[34,71],"KullbackLeibler":[36],"(KL)":[37],"divergence":[38,74],"between":[39],"two":[40],"joint":[41],"distributions,":[42],"we":[43],"bring":[44],"tools":[46],"from":[47],"variational":[48],"inference":[49],"to":[50,79,82,91],"bear":[51],"our":[53],"problem.":[56],"This":[57,99],"allows":[58],"for":[59],"deriving":[60],"dynamic":[62],"programming":[63],"principle,":[64],"value":[67],"defined":[70],"KL":[73],"again.":[75],"then":[77],"resort":[78],"Gaussian":[80],"distributions":[81],"approximate":[83],"apply":[88],"theory":[90],"affine":[93],"nonlinear":[94],"systems":[95],"with":[96],"quadratic":[97],"costs.":[98],"results":[100],"in":[101],"closed-form":[102],"recursive":[103],"updates,":[104],"which":[105],"generalize":[106],"LQR":[107],"backward":[111],"Riccati":[112],"equation.":[113],"illustrate":[115],"this":[116],"novel":[117],"method":[118],"simple":[121],"stabilizing":[124],"an":[125],"inverted":[126],"pendulum.":[127]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}