{"id":"https://openalex.org/W3010727647","doi":"https://doi.org/10.1109/cdc40024.2019.9030210","title":"Safe Intermittent Reinforcement Learning for Nonlinear Systems","display_name":"Safe Intermittent Reinforcement Learning for Nonlinear Systems","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3010727647","doi":"https://doi.org/10.1109/cdc40024.2019.9030210","mag":"3010727647"},"language":"en","primary_location":{"id":"doi:10.1109/cdc40024.2019.9030210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9030210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th 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/A5053342436","display_name":"Yongliang Yang","orcid":"https://orcid.org/0000-0002-3144-8604"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yongliang Yang","raw_affiliation_strings":["School of Automation and Electrical Engineering, university of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, university of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040301558","display_name":"Kyriakos G. Vamvoudakis","orcid":"https://orcid.org/0000-0003-1978-4848"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyriakos G. Vamvoudakis","raw_affiliation_strings":["Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063118155","display_name":"Hamidreza Modares","orcid":"https://orcid.org/0000-0003-0800-5140"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamidreza Modares","raw_affiliation_strings":["Department of Mechanical Engineering, Michigan State University, East Lansing, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Michigan State University, East Lansing, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022113595","display_name":"Wei He","orcid":"https://orcid.org/0000-0002-8944-9861"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei He","raw_affiliation_strings":["School of Automation and Electrical Engineering, university of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, university of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101512101","display_name":"Yixin Yin","orcid":"https://orcid.org/0000-0001-6056-8878"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixin Yin","raw_affiliation_strings":["School of Automation and Electrical Engineering, university of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, university of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038037619","display_name":"Donald C. Wunsch","orcid":"https://orcid.org/0000-0002-9726-9051"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donald C. Wunsch","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO, USA","institution_ids":["https://openalex.org/I20382870"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5053342436"],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":0.9699,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79249567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"690","last_page":"697"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998000264167786,"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":0.9998000264167786,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9580000042915344,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9426000118255615,"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":0.8146396279335022},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6280668377876282},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.6137837767601013},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5404070615768433},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5378140211105347},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5301238894462585},{"id":"https://openalex.org/keywords/zenos-paradoxes","display_name":"Zeno's paradoxes","score":0.4935232400894165},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.44815006852149963},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4388500154018402},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4374425709247589},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.43598854541778564},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.348554402589798},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.34799420833587646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2595330476760864},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21734124422073364},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1886584758758545},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.1423601508140564},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13627269864082336}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8146396279335022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6280668377876282},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.6137837767601013},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5404070615768433},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5378140211105347},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5301238894462585},{"id":"https://openalex.org/C7707877","wikidata":"https://www.wikidata.org/wiki/Q33378","display_name":"Zeno's paradoxes","level":2,"score":0.4935232400894165},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.44815006852149963},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4388500154018402},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4374425709247589},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.43598854541778564},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.348554402589798},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.34799420833587646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2595330476760864},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21734124422073364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1886584758758545},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.1423601508140564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13627269864082336},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc40024.2019.9030210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9030210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W5108103","https://openalex.org/W1074958431","https://openalex.org/W1519369336","https://openalex.org/W1973378833","https://openalex.org/W1978518835","https://openalex.org/W1983523797","https://openalex.org/W1985235885","https://openalex.org/W2010152647","https://openalex.org/W2062298332","https://openalex.org/W2062373349","https://openalex.org/W2142572589","https://openalex.org/W2193245008","https://openalex.org/W2314983263","https://openalex.org/W2460713275","https://openalex.org/W2484646121","https://openalex.org/W2560370148","https://openalex.org/W2585299106","https://openalex.org/W2600708832","https://openalex.org/W2605628695","https://openalex.org/W2753943679","https://openalex.org/W2772589676","https://openalex.org/W2789789879","https://openalex.org/W2792183503","https://openalex.org/W2793914020","https://openalex.org/W2918660012","https://openalex.org/W2919774326","https://openalex.org/W2970427121","https://openalex.org/W6600197225","https://openalex.org/W6749320919"],"related_works":["https://openalex.org/W4388287607","https://openalex.org/W2383752020","https://openalex.org/W2475803354","https://openalex.org/W2353128426","https://openalex.org/W4232681333","https://openalex.org/W2376477863","https://openalex.org/W2570961029","https://openalex.org/W2155553330","https://openalex.org/W2934679276","https://openalex.org/W2312892224"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"an":[3,62,67],"online":[4,68],"intermittent":[5,69,80],"actor-critic":[6,70],"reinforcement":[7],"learning":[8,71,101],"method":[9],"is":[10,25,40,73,85],"used":[11],"to":[12,27,75,87,95],"stabilize":[13],"nonlinear":[14],"systems":[15],"optimally":[16],"while":[17],"also":[18],"guaranteeing":[19],"safety.":[20],"A":[21],"barrier":[22],"function-based":[23],"transformation":[24],"introduced":[26],"ensure":[28],"that":[29,42],"the":[30,35,43,47,55,58,77,97,100],"system":[31,49],"does":[32],"not":[33],"violate":[34],"user-defined":[36],"safety":[37,44],"constraints.":[38],"It":[39],"shown":[41],"constraints":[45],"of":[46,57,61,99],"original":[48],"can":[50],"be":[51,88],"guaranteed":[52,86],"by":[53],"assuring":[54],"stability":[56],"equilibrium":[59],"point":[60],"appropriately":[63],"transformed":[64],"system.":[65],"Then,":[66],"framework":[72],"developed":[74],"learn":[76],"optimal":[78],"safe":[79],"controller.":[81],"Also,":[82],"Zeno":[83],"behavior":[84],"excluded.":[89],"Finally,":[90],"numerical":[91],"examples":[92],"are":[93],"conducted":[94],"verify":[96],"efficacy":[98],"algorithm.":[102]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}