{"id":"https://openalex.org/W4402262825","doi":"https://doi.org/10.23919/acc60939.2024.10644360","title":"A Practical Reinforcement Learning (RL) Controller Design for Nonlinear Systems","display_name":"A Practical Reinforcement Learning (RL) Controller Design for Nonlinear Systems","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4402262825","doi":"https://doi.org/10.23919/acc60939.2024.10644360"},"language":"en","primary_location":{"id":"doi:10.23919/acc60939.2024.10644360","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/acc60939.2024.10644360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 American Control Conference (ACC)","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/A5078819171","display_name":"Hesam Hassanpour","orcid":null},"institutions":[{"id":"https://openalex.org/I98251732","display_name":"McMaster University","ror":"https://ror.org/02fa3aq29","country_code":"CA","type":"education","lineage":["https://openalex.org/I98251732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hesam Hassanpour","raw_affiliation_strings":["McMaster University,Department of Chemical Engineering,Hamilton,Ontario,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McMaster University,Department of Chemical Engineering,Hamilton,Ontario,Canada","institution_ids":["https://openalex.org/I98251732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016353717","display_name":"Prashant Mhaskar","orcid":"https://orcid.org/0000-0001-5866-211X"},"institutions":[{"id":"https://openalex.org/I98251732","display_name":"McMaster University","ror":"https://ror.org/02fa3aq29","country_code":"CA","type":"education","lineage":["https://openalex.org/I98251732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Prashant Mhaskar","raw_affiliation_strings":["McMaster University,Department of Chemical Engineering,Hamilton,Ontario,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McMaster University,Department of Chemical Engineering,Hamilton,Ontario,Canada","institution_ids":["https://openalex.org/I98251732"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010867791","display_name":"Brandon Corbett","orcid":"https://orcid.org/0000-0001-5360-9811"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brandon Corbett","raw_affiliation_strings":["Sartorius Canada Inc.,Oakville,Ontario,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sartorius Canada Inc.,Oakville,Ontario,Canada","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14943616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1269","last_page":"1274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9998000264167786,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9998000264167786,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.9957000017166138,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8371543884277344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6583415269851685},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.6076706647872925},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.47807908058166504},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43173930048942566},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.41323480010032654},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3971586227416992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2061813473701477},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.184697687625885},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.15211939811706543},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.06407010555267334}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8371543884277344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6583415269851685},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.6076706647872925},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.47807908058166504},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43173930048942566},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.41323480010032654},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3971586227416992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2061813473701477},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.184697687625885},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.15211939811706543},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.06407010555267334},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc60939.2024.10644360","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/acc60939.2024.10644360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2005151817","https://openalex.org/W2009685984","https://openalex.org/W2052284726","https://openalex.org/W2064872182","https://openalex.org/W2121863487","https://openalex.org/W2126624976","https://openalex.org/W2134673975","https://openalex.org/W2145339207","https://openalex.org/W2153954291","https://openalex.org/W2461584603","https://openalex.org/W2738109916","https://openalex.org/W2885282028","https://openalex.org/W2973229164","https://openalex.org/W2989354373","https://openalex.org/W3023586494","https://openalex.org/W3034748593","https://openalex.org/W3210813680","https://openalex.org/W4211147054","https://openalex.org/W6606529088","https://openalex.org/W6748839928"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W2000675896"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,81,139,143],"practically":[4],"implementable":[5],"reinforcement":[6],"learning":[7,25],"(RL)":[8],"approach":[9],"for":[10,118,121,142],"process":[11,26,42],"control":[12,62,120],"applications.":[13],"Standard":[14],"model-free":[15],"RL":[16,29,67,102,106,129],"approaches":[17],"are":[18,92],"not":[19],"applicable":[20],"in":[21],"practice":[22],"because":[23],"the":[24,66,75,96,101,112,127,133],"of":[27,34,84,100,126],"an":[28,51],"agent":[30],"requires":[31],"random":[32],"exploration":[33],"state":[35],"and":[36,44,98],"action":[37],"spaces,":[38],"which":[39],"can":[40],"compromise":[41],"safety":[43],"economic":[45],"objectives.":[46],"To":[47],"tackle":[48],"this":[49],"issue,":[50],"offline":[52,72],"training":[53],"strategy":[54],"is":[55,115,136],"proposed":[56,128],"by":[57,73],"leveraging":[58],"existing":[59],"model":[60],"predictive":[61],"(MPC)":[63],"to":[64,94,111,131],"pre-train":[65],"agent.":[68,103],"MPC":[69,76,113],"actions,":[70],"calculated":[71],"solving":[74],"optimization":[77],"problem":[78],"based":[79],"on":[80],"wide":[82],"range":[83],"initial":[85],"conditions,":[86],"along":[87],"with":[88,108],"its":[89],"objective":[90],"function":[91],"utilized":[93,117],"pretrain":[95],"actor":[97],"critics":[99],"The":[104,124],"pre-trained":[105],"controller,":[107],"similar":[109],"performance":[110,135],"performance,":[114],"then":[116],"online":[119],"further":[122],"training.":[123],"efficacy":[125],"controller":[130],"improve":[132],"tracking":[134],"demonstrated":[137],"using":[138],"simulation":[140],"example":[141],"pH":[144],"neutralization":[145],"process.":[146]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}