{"id":"https://openalex.org/W3112804989","doi":"https://doi.org/10.1109/access.2020.3045114","title":"Stability-Certified Reinforcement Learning: A Control-Theoretic Perspective","display_name":"Stability-Certified Reinforcement Learning: A Control-Theoretic Perspective","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3112804989","doi":"https://doi.org/10.1109/access.2020.3045114","mag":"3112804989"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3045114","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3045114","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09296215.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09296215.pdf","any_repository_has_fulltext":true},"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/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Jin","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7909-4545","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"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 at Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Operations Research, University of California at Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":4.9453,"has_fulltext":true,"cited_by_count":72,"citation_normalized_percentile":{"value":0.96113454,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"8","issue":null,"first_page":"229086","last_page":"229100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9969000220298767,"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":0.9969000220298767,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9962999820709229,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8725968599319458},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.7035468816757202},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6969834566116333},{"id":"https://openalex.org/keywords/semidefinite-programming","display_name":"Semidefinite programming","score":0.5480473637580872},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5426055192947388},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4872411787509918},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.44973576068878174},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.43054407835006714},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41444632411003113},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.40087488293647766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3578379154205322},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24387767910957336},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16990765929222107}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8725968599319458},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.7035468816757202},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6969834566116333},{"id":"https://openalex.org/C101901036","wikidata":"https://www.wikidata.org/wiki/Q2269096","display_name":"Semidefinite programming","level":2,"score":0.5480473637580872},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5426055192947388},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4872411787509918},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.44973576068878174},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.43054407835006714},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41444632411003113},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.40087488293647766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3578379154205322},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24387767910957336},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16990765929222107},{"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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.3045114","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3045114","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09296215.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:817a4d5cc2024a8db26b4c5fe2b4ef72","is_oa":true,"landing_page_url":"https://doaj.org/article/817a4d5cc2024a8db26b4c5fe2b4ef72","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 229086-229100 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3045114","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3045114","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09296215.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3112804989.pdf","grobid_xml":"https://content.openalex.org/works/W3112804989.grobid-xml"},"referenced_works_count":68,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W206679605","https://openalex.org/W1551360398","https://openalex.org/W1568689741","https://openalex.org/W1575592356","https://openalex.org/W1673923490","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W1845972764","https://openalex.org/W2003658506","https://openalex.org/W2052970196","https://openalex.org/W2053572490","https://openalex.org/W2063493327","https://openalex.org/W2065313971","https://openalex.org/W2076199517","https://openalex.org/W2079121704","https://openalex.org/W2082847490","https://openalex.org/W2086298643","https://openalex.org/W2097460613","https://openalex.org/W2097944741","https://openalex.org/W2112594540","https://openalex.org/W2119717200","https://openalex.org/W2130801532","https://openalex.org/W2137002893","https://openalex.org/W2145339207","https://openalex.org/W2150165932","https://openalex.org/W2160545578","https://openalex.org/W2164479831","https://openalex.org/W2173248099","https://openalex.org/W2462906003","https://openalex.org/W2492791808","https://openalex.org/W2570533838","https://openalex.org/W2572949971","https://openalex.org/W2573774505","https://openalex.org/W2768346313","https://openalex.org/W2777638777","https://openalex.org/W2809808592","https://openalex.org/W2914316834","https://openalex.org/W2962879692","https://openalex.org/W2963249138","https://openalex.org/W2963525569","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964102336","https://openalex.org/W2964153729","https://openalex.org/W2970620827","https://openalex.org/W3210839039","https://openalex.org/W4211232706","https://openalex.org/W4253985045","https://openalex.org/W4294555834","https://openalex.org/W4295521014","https://openalex.org/W4298857966","https://openalex.org/W4317466250","https://openalex.org/W6634413486","https://openalex.org/W6637162671","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6679257226","https://openalex.org/W6681608319","https://openalex.org/W6684037837","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6718836005","https://openalex.org/W6735913928","https://openalex.org/W6738483526","https://openalex.org/W6745893766","https://openalex.org/W6747133071","https://openalex.org/W6763711611"],"related_works":["https://openalex.org/W1983756092","https://openalex.org/W2381295697","https://openalex.org/W2385886188","https://openalex.org/W4306904969","https://openalex.org/W2149537132","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2378309693"],"abstract_inverted_index":{"We":[0,18],"investigate":[1],"the":[2,23,84,93,104],"important":[3],"problem":[4],"of":[5,8,26,30,53],"certifying":[6],"stability":[7,32],"reinforcement":[9,85],"learning":[10,86,101],"policies":[11],"when":[12],"interconnected":[13],"with":[14],"nonlinear":[15],"dynamical":[16],"systems.":[17],"show":[19],"that":[20,83],"by":[21,56],"regulating":[22],"partial":[24],"gradients":[25],"policies,":[27],"strong":[28],"guarantees":[29],"robust":[31],"can":[33,88],"be":[34],"obtained":[35],"based":[36],"on":[37,69],"a":[38,50],"proposed":[39],"semidefinite":[40],"programming":[41],"feasibility":[42],"problem.":[43],"The":[44],"method":[45],"is":[46],"able":[47],"to":[48],"certify":[49],"large":[51],"set":[52],"stabilizing":[54],"controllers":[55],"exploiting":[57],"problem-specific":[58],"structures;":[59],"furthermore,":[60],"we":[61],"analyze":[62],"and":[63,77,97],"establish":[64],"its":[65],"(non)conservatism.":[66],"Empirical":[67],"evaluations":[68],"two":[70],"decentralized":[71],"control":[72],"tasks,":[73],"namely":[74],"multi-flight":[75],"formation":[76],"power":[78],"system":[79],"frequency":[80],"regulation,":[81],"demonstrate":[82],"agents":[87],"have":[89],"high":[90],"performance":[91],"within":[92],"stability-certified":[94],"parameter":[95],"space":[96],"also":[98],"exhibit":[99],"stable":[100],"behaviors":[102],"in":[103],"long":[105],"run.":[106]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":5}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}