{"id":"https://openalex.org/W2914316834","doi":"https://doi.org/10.1109/cdc.2018.8618996","title":"Control-Theoretic Analysis of Smoothness for Stability-Certified Reinforcement Learning","display_name":"Control-Theoretic Analysis of Smoothness for Stability-Certified Reinforcement Learning","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2914316834","doi":"https://doi.org/10.1109/cdc.2018.8618996","mag":"2914316834"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2018.8618996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2018.8618996","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101484129","display_name":"Ming Jin","orcid":"https://orcid.org/0000-0001-7909-4545"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Jin","raw_affiliation_strings":["Department of Industrial Engineering and Operations Research, University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Operations Research, University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042580848","display_name":"Javad Lavaei","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Javad Lavaei","raw_affiliation_strings":["Department of Industrial Engineering and Operations Research, University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Operations Research, University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6840","last_page":"6847"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10305","display_name":"Power System Optimization and Stability","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10305","display_name":"Power System Optimization and Stability","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10876","display_name":"Fault Detection and Control Systems","score":0.995199978351593,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9947999715805054,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7946388721466064},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6336201429367065},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.6028141975402832},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.6003002524375916},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4937334954738617},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.429233580827713},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.42901021242141724},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41809794306755066},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3428935706615448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33989202976226807},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23344671726226807},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.23302438855171204},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20835629105567932},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18315646052360535}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7946388721466064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6336201429367065},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.6028141975402832},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.6003002524375916},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4937334954738617},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.429233580827713},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.42901021242141724},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41809794306755066},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3428935706615448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33989202976226807},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23344671726226807},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.23302438855171204},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20835629105567932},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18315646052360535},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2018.8618996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2018.8618996","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1192553058","https://openalex.org/W1551360398","https://openalex.org/W1673923490","https://openalex.org/W1771410628","https://openalex.org/W1845972764","https://openalex.org/W1868559974","https://openalex.org/W1970789124","https://openalex.org/W1992094515","https://openalex.org/W2003658506","https://openalex.org/W2006859604","https://openalex.org/W2060248504","https://openalex.org/W2063493327","https://openalex.org/W2065313971","https://openalex.org/W2076199517","https://openalex.org/W2076467525","https://openalex.org/W2082847490","https://openalex.org/W2086298643","https://openalex.org/W2097944741","https://openalex.org/W2101075098","https://openalex.org/W2112594540","https://openalex.org/W2121863487","https://openalex.org/W2151237105","https://openalex.org/W2155153696","https://openalex.org/W2160545578","https://openalex.org/W2164479831","https://openalex.org/W2169106666","https://openalex.org/W2291269933","https://openalex.org/W2573774505","https://openalex.org/W2580175322","https://openalex.org/W2962803570","https://openalex.org/W2962879692","https://openalex.org/W2964153729","https://openalex.org/W3103559770","https://openalex.org/W3106238320","https://openalex.org/W3210839039","https://openalex.org/W4211232706","https://openalex.org/W4214717370","https://openalex.org/W4253985045","https://openalex.org/W4293545785","https://openalex.org/W4294555834","https://openalex.org/W4295521014","https://openalex.org/W4297780563","https://openalex.org/W6637162671","https://openalex.org/W6638018090","https://openalex.org/W6639175102","https://openalex.org/W6682367392","https://openalex.org/W6684037837","https://openalex.org/W6735913928","https://openalex.org/W6737893269","https://openalex.org/W6738483526","https://openalex.org/W6835534151"],"related_works":["https://openalex.org/W3185235544","https://openalex.org/W2911623553","https://openalex.org/W4297791327","https://openalex.org/W2897842840","https://openalex.org/W2397777611","https://openalex.org/W1502031429","https://openalex.org/W2417585376","https://openalex.org/W1994157709","https://openalex.org/W4294336468","https://openalex.org/W2797811993"],"abstract_inverted_index":{"It":[0],"is":[1,33],"critical":[2],"to":[3,28,72],"obtain":[4],"stability":[5,100],"certificate":[6],"before":[7],"deploying":[8],"reinforcement":[9,39],"learning":[10,40],"in":[11,25,31,115],"real-world":[12],"mission-critical":[13],"systems.":[14],"This":[15],"study":[16,118],"justifies":[17],"the":[18,74,78,95],"intuition":[19],"that":[20,94],"smoothness":[21,46,96],"(i.e.,":[22],"small":[23,29],"changes":[24,30],"inputs":[26],"lead":[27],"outputs)":[32],"an":[34],"important":[35],"property":[36],"for":[37,60,89,106,123],"stability-certified":[38],"from":[41],"a":[42,53],"control-theoretic":[43],"perspective.":[44],"The":[45,117],"margin":[47,97],"can":[48,98],"be":[49],"obtained":[50],"by":[51],"solving":[52],"feasibility":[54],"problem":[55],"based":[56],"on":[57,83],"semi-definite":[58],"programming":[59],"both":[61,102],"linear":[62],"and":[63,67,85,104],"nonlinear":[64,84],"dynamical":[65],"systems,":[66],"it":[68],"does":[69],"not":[70],"need":[71],"access":[73],"exact":[75],"parameters":[76],"of":[77],"learned":[79],"controllers.":[80],"Numerical":[81],"evaluation":[82],"decentralized":[86],"frequency":[87],"control":[88],"large-scale":[90],"power":[91],"grids":[92],"demonstrates":[93],"certify":[99],"during":[101],"exploration":[103],"deployment":[105],"(deep)":[107],"neural-network":[108],"policies,":[109],"which":[110],"substantially":[111],"surpass":[112],"nominal":[113],"controllers":[114],"performance.":[116],"opens":[119],"up":[120],"new":[121],"opportunities":[122],"robust":[124],"Lipschitz":[125],"continuous":[126],"policy":[127],"learning.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}