{"id":"https://openalex.org/W7123341039","doi":"https://doi.org/10.1109/cdc57313.2025.11312958","title":"On-policy Safe Reinforcement Learning under Input Saturation and State Constraints for Nonlinear Discrete Time Systems","display_name":"On-policy Safe Reinforcement Learning under Input Saturation and State Constraints for Nonlinear Discrete Time Systems","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123341039","doi":"https://doi.org/10.1109/cdc57313.2025.11312958"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312958","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":"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/A5121663216","display_name":"Satya Marthi","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210110792","display_name":"Centre de Recherche en Automatique de Nancy","ror":"https://ror.org/022r5hc56","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210099203","https://openalex.org/I4210100260","https://openalex.org/I4210110792","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Satya Marthi","raw_affiliation_strings":["Universite de Lorraine, CNRS, CRAN,Nancy,France,F-54000"],"affiliations":[{"raw_affiliation_string":"Universite de Lorraine, CNRS, CRAN,Nancy,France,F-54000","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1294671590","https://openalex.org/I4210110792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079304841","display_name":"Mayank Shekhar Jha","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210110792","display_name":"Centre de Recherche en Automatique de Nancy","ror":"https://ror.org/022r5hc56","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210099203","https://openalex.org/I4210100260","https://openalex.org/I4210110792","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mayank S Jha","raw_affiliation_strings":["Universite de Lorraine, CNRS, CRAN,Nancy,France,F-54000"],"affiliations":[{"raw_affiliation_string":"Universite de Lorraine, CNRS, CRAN,Nancy,France,F-54000","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1294671590","https://openalex.org/I4210110792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016000776","display_name":"Soha Kanso","orcid":"https://orcid.org/0009-0003-0921-1939"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210110792","display_name":"Centre de Recherche en Automatique de Nancy","ror":"https://ror.org/022r5hc56","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210099203","https://openalex.org/I4210100260","https://openalex.org/I4210110792","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Soha Kanso","raw_affiliation_strings":["Universite de Lorraine, CNRS, CRAN,Nancy,France,F-54000"],"affiliations":[{"raw_affiliation_string":"Universite de Lorraine, CNRS, CRAN,Nancy,France,F-54000","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1294671590","https://openalex.org/I4210110792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018171680","display_name":"Jean\u2010Christophe Ponsart","orcid":"https://orcid.org/0000-0003-1610-2418"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210110792","display_name":"Centre de Recherche en Automatique de Nancy","ror":"https://ror.org/022r5hc56","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210099203","https://openalex.org/I4210100260","https://openalex.org/I4210110792","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Christophe Ponsart","raw_affiliation_strings":["Universite de Lorraine, CNRS, CRAN,Nancy,France,F-54000"],"affiliations":[{"raw_affiliation_string":"Universite de Lorraine, CNRS, CRAN,Nancy,France,F-54000","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1294671590","https://openalex.org/I4210110792"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081306534","display_name":"D Theilliol","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210110792","display_name":"Centre de Recherche en Automatique de Nancy","ror":"https://ror.org/022r5hc56","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210099203","https://openalex.org/I4210100260","https://openalex.org/I4210110792","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Didier Theilliol","raw_affiliation_strings":["Universite de Lorraine, CNRS, CRAN,Nancy,France,F-54000"],"affiliations":[{"raw_affiliation_string":"Universite de Lorraine, CNRS, CRAN,Nancy,France,F-54000","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1294671590","https://openalex.org/I4210110792"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5121663216"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210110792","https://openalex.org/I90183372"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.76433367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4817","last_page":"4824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9884999990463257,"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":0.9884999990463257,"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":0.006300000008195639,"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":0.0007999999797903001,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7228999733924866},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6668000221252441},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5142999887466431},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.5083000063896179},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.45329999923706055},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4212999939918518},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.3691999912261963},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.3668000102043152}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7228999733924866},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6668000221252441},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5902000069618225},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5142999887466431},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.5083000063896179},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4223000109195709},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4212999939918518},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C9930424","wikidata":"https://www.wikidata.org/wiki/Q7426587","display_name":"Saturation (graph theory)","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2955999970436096},{"id":"https://openalex.org/C81845259","wikidata":"https://www.wikidata.org/wiki/Q290117","display_name":"Quadratic programming","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.2824000120162964},{"id":"https://openalex.org/C201030206","wikidata":"https://www.wikidata.org/wiki/Q5165805","display_name":"Control-Lyapunov function","level":5,"score":0.28209999203681946},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.27399998903274536},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312958","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":[{"id":"https://metadata.un.org/sdg/16","score":0.4127107262611389,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2010152647","https://openalex.org/W2048687352","https://openalex.org/W2107674817","https://openalex.org/W2108286682","https://openalex.org/W2137092694","https://openalex.org/W2152161277","https://openalex.org/W2165726932","https://openalex.org/W2484646121","https://openalex.org/W2560504659","https://openalex.org/W2966735560","https://openalex.org/W2968945909","https://openalex.org/W3048735518","https://openalex.org/W4292249799","https://openalex.org/W4301886962","https://openalex.org/W4308463062","https://openalex.org/W4320488099","https://openalex.org/W4382404404","https://openalex.org/W4388052828","https://openalex.org/W4388852236","https://openalex.org/W4391021937","https://openalex.org/W4402264196","https://openalex.org/W4403097602","https://openalex.org/W4412422405","https://openalex.org/W4413392944"],"related_works":[],"abstract_inverted_index":{"This":[0,31,108],"paper":[1,109],"proposes":[2,67],"an":[3],"on-policy":[4,68],"Policy":[5],"Iteration":[6],"(PI)":[7],"safe":[8,63],"reinforcement":[9],"learning":[10,29],"(RL)":[11],"framework":[12],"for":[13,62],"control":[14,49,79],"of":[15,36,92],"nonlinear":[16],"discrete-time":[17],"control-affine":[18],"systems":[19],"with":[20],"input":[21,50,72],"saturation":[22,51,73],"constraints,":[23],"ensuring":[24],"safety":[25,83,121],"throughout":[26],"exploration":[27,37,86,93],"and":[28,52,106,123,141],"phases.":[30],"work":[32],"emphasizes":[33],"the":[34,42,46,55,77,85,89,116,125,134],"importance":[35],"noise":[38,94],"while":[39],"also":[40,110],"addressing":[41],"challenges":[43],"resulting":[44],"from":[45],"conflict":[47],"between":[48],"exploration.":[53],"Against":[54],"typically":[56],"adopted":[57],"off-policy":[58],"PI":[59,69],"based":[60,138],"approaches":[61],"RL,":[64],"our":[65],"approach":[66],"algorithm":[70],"under":[71,120],"to":[74,118],"iteratively":[75],"learn":[76],"optimal":[78],"policy.":[80],"To":[81],"ensure":[82],"during":[84],"phase,":[87],"where":[88],"high":[90],"magnitude":[91],"could":[95],"compromise":[96],"system":[97],"safety,":[98],"a":[99],"so":[100],"called":[101],"fall-back":[102],"policy":[103],"is":[104],"proposed":[105],"incorporated.":[107],"develops":[111],"novel":[112],"theoretical":[113],"guarantees":[114],"on":[115],"convergence":[117],"optimality":[119],"restrictions":[122],"evaluates":[124],"effectiveness":[126],"through":[127],"simulation":[128],"studies,":[129],"comparing":[130],"its":[131],"performance":[132],"against":[133],"traditional":[135],"Quadratic":[136],"Programming":[137],"Control":[139,142],"Lyapunov":[140],"Barrier":[143],"function":[144],"(QP-CLF-CBF)":[145],"approach.":[146]},"counts_by_year":[],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2026-01-14T00:00:00"}
