{"id":"https://openalex.org/W7123338223","doi":"https://doi.org/10.1109/cdc57313.2025.11312866","title":"Stochastic Reinforcement Learning with Stability Guarantees for Control of Unknown Nonlinear Systems","display_name":"Stochastic Reinforcement Learning with Stability Guarantees for Control of Unknown Nonlinear Systems","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123338223","doi":"https://doi.org/10.1109/cdc57313.2025.11312866"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th 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/A5010310669","display_name":"Thanin Quartz","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Thanin Quartz","raw_affiliation_strings":["University of Waterloo,Department of Applied Mathematics,Waterloo,Canada,N2L 3G1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo,Department of Applied Mathematics,Waterloo,Canada,N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018323174","display_name":"Ruikun Zhou","orcid":"https://orcid.org/0000-0001-7265-0617"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ruikun Zhou","raw_affiliation_strings":["University of Waterloo,Department of Applied Mathematics,Waterloo,Canada,N2L 3G1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo,Department of Applied Mathematics,Waterloo,Canada,N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023907914","display_name":"Hans De Sterck","orcid":"https://orcid.org/0000-0002-1641-932X"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hans De Sterck","raw_affiliation_strings":["University of Waterloo,Department of Applied Mathematics,Waterloo,Canada,N2L 3G1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo,Department of Applied Mathematics,Waterloo,Canada,N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100361819","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-2827-0630"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":["University of Waterloo,Department of Applied Mathematics,Waterloo,Canada,N2L 3G1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo,Department of Applied Mathematics,Waterloo,Canada,N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6057","last_page":"6062"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9257000088691711,"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":0.9257000088691711,"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":0.04259999841451645,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.010599999688565731,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.857699990272522},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6610000133514404},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6230999827384949},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5697000026702881},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4756999909877777},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4618000090122223},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4505999982357025},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3808000087738037},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3693000078201294}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.857699990272522},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6610000133514404},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6230999827384949},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6158999800682068},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5697000026702881},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4756999909877777},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4618000090122223},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4505999982357025},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3971000015735626},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C167964875","wikidata":"https://www.wikidata.org/wiki/Q17011487","display_name":"Exponential stability","level":3,"score":0.35830000042915344},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34060001373291016},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.3239000141620636},{"id":"https://openalex.org/C91581856","wikidata":"https://www.wikidata.org/wiki/Q2707001","display_name":"Nonlinear control","level":3,"score":0.28630000352859497},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27639999985694885},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.2705000042915344},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C17061570","wikidata":"https://www.wikidata.org/wiki/Q7960888","display_name":"Wake-sleep algorithm","level":4,"score":0.2678999900817871},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.258899986743927},{"id":"https://openalex.org/C79379906","wikidata":"https://www.wikidata.org/wiki/Q3174497","display_name":"Dynamical systems theory","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4749516248703003,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1991555527","https://openalex.org/W1993851747","https://openalex.org/W2288565641","https://openalex.org/W2298163601","https://openalex.org/W2948652605","https://openalex.org/W2963575966","https://openalex.org/W2973229164","https://openalex.org/W2982316857","https://openalex.org/W3011877239","https://openalex.org/W3045059767","https://openalex.org/W3155511388","https://openalex.org/W3156620736","https://openalex.org/W3204222741","https://openalex.org/W4297792208","https://openalex.org/W4301886962","https://openalex.org/W4396571418","https://openalex.org/W6922480057"],"related_works":[],"abstract_inverted_index":{"Designing":[0],"a":[1,8,60,70,139,159],"stabilizing":[2],"controller":[3],"for":[4,12,149,179],"nonlinear":[5,181],"systems":[6],"is":[7,83],"challenging":[9,103],"task,":[10],"especially":[11],"high-dimensional":[13,104],"problems":[14],"with":[15,158],"unknown":[16],"dynamics.":[17,76],"Traditional":[18],"reinforcement":[19,61,114,154],"learning":[20,62,69,115,155,165],"algorithms":[21],"applied":[22],"to":[23,27,32],"stabilization":[24,45],"tasks":[25],"tend":[26],"drive":[28],"the":[29,33,52,66,75,81,85,91,96,130,134,143,146,163,171,180],"system":[30,67],"close":[31],"equilibrium":[34,53],"point.":[35,54],"However,":[36],"these":[37,108],"approaches":[38],"often":[39],"fall":[40],"short":[41],"of":[42,74,80,98,142,145,162],"achieving":[43],"true":[44],"and":[46,122,127,152],"result":[47],"in":[48],"persistent":[49],"oscillations":[50],"around":[51],"In":[55,107],"this":[56],"work,":[57],"we":[58,137,168],"propose":[59],"algorithm":[63,82,100,111,148],"that":[64,170],"stabilizes":[65,129],"by":[68],"local":[71],"linear":[72],"representation":[73],"The":[77],"main":[78],"component":[79],"integrating":[84],"learned":[86,147,172],"gain":[87],"matrix":[88],"directly":[89],"into":[90],"neural":[92],"policy.":[93],"We":[94],"demonstrate":[95],"effectiveness":[97],"our":[99,110],"on":[101],"several":[102],"dynamical":[105],"systems.":[106,182],"simulations,":[109],"outperforms":[112],"popular":[113],"algorithms,":[116],"such":[117],"as":[118],"soft":[119],"actor-critic":[120],"(SAC)":[121],"proximal":[123],"policy":[124],"optimization":[125],"(PPO),":[126],"successfully":[128],"system.":[131],"To":[132],"support":[133],"numerical":[135],"results,":[136],"provide":[138,176],"theoretical":[140],"analysis":[141,161],"feasibility":[144],"both":[150],"deterministic":[151],"stochastic":[153],"settings,":[156],"along":[157],"convergence":[160],"proposed":[164],"algorithm.":[166],"Furthermore,":[167],"verify":[169],"control":[173],"policies":[174],"indeed":[175],"asymptotic":[177],"stability":[178]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-14T00:00:00"}