{"id":"https://openalex.org/W4415180790","doi":"https://doi.org/10.23919/ecc65951.2025.11187149","title":"On the Design of Safe Continual RL Methods for Control of Nonlinear Systems","display_name":"On the Design of Safe Continual RL Methods for Control of Nonlinear Systems","publication_year":2025,"publication_date":"2025-06-24","ids":{"openalex":"https://openalex.org/W4415180790","doi":"https://doi.org/10.23919/ecc65951.2025.11187149"},"language":"en","primary_location":{"id":"doi:10.23919/ecc65951.2025.11187149","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ecc65951.2025.11187149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 European Control Conference (ECC)","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/A5037114121","display_name":"Austin Coursey","orcid":"https://orcid.org/0000-0003-1774-6442"},"institutions":[{"id":"https://openalex.org/I4210160740","display_name":"Integrated Software (United States)","ror":"https://ror.org/05dp7m259","country_code":"US","type":"company","lineage":["https://openalex.org/I4210160740"]},{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Austin Coursey","raw_affiliation_strings":["Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA","institution_ids":["https://openalex.org/I4210160740","https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035863735","display_name":"Marcos Qui\u00f1ones-Grueiro","orcid":"https://orcid.org/0000-0001-5391-6774"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]},{"id":"https://openalex.org/I4210160740","display_name":"Integrated Software (United States)","ror":"https://ror.org/05dp7m259","country_code":"US","type":"company","lineage":["https://openalex.org/I4210160740"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marcos Quinones-Grueiro","raw_affiliation_strings":["Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA","institution_ids":["https://openalex.org/I4210160740","https://openalex.org/I200719446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051150754","display_name":"Gautam Biswas","orcid":"https://orcid.org/0000-0002-2752-3878"},"institutions":[{"id":"https://openalex.org/I4210160740","display_name":"Integrated Software (United States)","ror":"https://ror.org/05dp7m259","country_code":"US","type":"company","lineage":["https://openalex.org/I4210160740"]},{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautam Biswas","raw_affiliation_strings":["Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA","institution_ids":["https://openalex.org/I4210160740","https://openalex.org/I200719446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037114121"],"corresponding_institution_ids":["https://openalex.org/I200719446","https://openalex.org/I4210160740"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36467549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"892","last_page":"897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11236","display_name":"Control Systems and Identification","score":0.9537000060081482,"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"}},"topics":[{"id":"https://openalex.org/T11236","display_name":"Control Systems and Identification","score":0.9537000060081482,"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/T10046","display_name":"Stability and Control of Uncertain Systems","score":0.9495999813079834,"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/T11081","display_name":"Advanced Control Systems Design","score":0.9412999749183655,"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":0.7235999703407288},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.5097000002861023},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4569999873638153},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44429999589920044},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4214000105857849},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.35370001196861267},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.3431999981403351},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.33390000462532043}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7235999703407288},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6496000289916992},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.5097000002861023},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4569999873638153},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44429999589920044},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4214000105857849},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.36419999599456787},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.33390000462532043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31709998846054077},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C132835097","wikidata":"https://www.wikidata.org/wiki/Q7663745","display_name":"System safety","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C91581856","wikidata":"https://www.wikidata.org/wiki/Q2707001","display_name":"Nonlinear control","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C2776014549","wikidata":"https://www.wikidata.org/wiki/Q3050847","display_name":"Consolidation (business)","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26969999074935913},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C42259789","wikidata":"https://www.wikidata.org/wiki/Q1392940","display_name":"Fail-safe","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/ecc65951.2025.11187149","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ecc65951.2025.11187149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 European Control Conference (ECC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,167],"(RL)":[2],"algorithms":[3,33,61,70],"have":[4,71],"been":[5,24,72],"successfully":[6],"applied":[7],"to":[8,26,74,126,179],"control":[9],"tasks":[10],"associated":[11],"with":[12,139],"unmanned":[13],"aerial":[14],"vehicles":[15],"and":[16,36,101,136,142,189,195],"robotics.":[17],"In":[18,92],"recent":[19],"years,":[20],"safe":[21,29,59,100,159],"RL":[22,32,60,69,112,160],"has":[23],"proposed":[25,73],"allow":[27],"the":[28,46,79,85,97,133],"execution":[30],"of":[31,81,99],"in":[34,41,122,165,171],"industrial":[35],"mission-critical":[37],"systems":[38,124],"that":[39,108,150,181],"operate":[40],"closed":[42],"loops.":[43],"However,":[44,78],"if":[45],"system":[47],"operating":[48,128],"conditions":[49],"change,":[50],"such":[51],"as":[52],"when":[53],"an":[54,89,151],"unknown":[55],"fault":[56],"occurs,":[57],"typical":[58],"cannot":[62],"adapt":[63],"while":[64],"retaining":[65],"past":[66],"knowledge.":[67],"Continual":[68],"address":[75],"this":[76,93,170],"issue.":[77],"impact":[80],"continual":[82,102,111,166],"adaptation":[83],"on":[84],"system\u2019s":[86],"safety":[87,120,188],"is":[88],"understudied":[90],"problem.":[91],"paper,":[94],"we":[95,105,131,148,173],"study":[96,132],"intersection":[98],"RL.":[103],"First,":[104],"empirically":[106],"demonstrate":[107],"a":[109,158,175],"popular":[110],"algorithm,":[113,161],"elastic":[114,182],"weight":[115,183],"consolidation,":[116],"does":[117],"not":[118],"satisfy":[119],"constraints":[121,141],"nonlinear":[123],"subject":[125],"varying":[127],"conditions.":[129],"Specifically,":[130],"MuJoCo":[134],"HalfCheetah":[135],"Ant":[137],"environments":[138],"velocity":[140],"sudden":[143],"joint":[144],"loss":[145],"non-stationarity.":[146],"Then,":[147],"show":[149],"agent":[152],"trained":[153],"using":[154],"constrained":[155],"policy":[156],"optimization,":[157],"experiences":[162],"catastrophic":[163],"forgetting":[164],"settings.":[168],"With":[169],"mind,":[172],"explore":[174],"simple":[176],"reward-shaping":[177],"method":[178],"ensure":[180],"consolidation":[184],"prioritizes":[185],"remembering":[186],"both":[187],"task":[190],"performance":[191],"for":[192],"safety-constrained,":[193],"nonlinear,":[194],"non-stationary":[196],"systems.":[197]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-15T00:00:00"}
