{"id":"https://openalex.org/W4407949723","doi":"https://doi.org/10.1109/cdc56724.2024.10886726","title":"Fast Reinforcement Learning For Optimal Control of Nonlinear Systems Using Transfer Learning","display_name":"Fast Reinforcement Learning For Optimal Control of Nonlinear Systems Using Transfer Learning","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4407949723","doi":"https://doi.org/10.1109/cdc56724.2024.10886726"},"language":"en","primary_location":{"id":"doi:10.1109/cdc56724.2024.10886726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd 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/A5100767800","display_name":"Yujia Wang","orcid":"https://orcid.org/0000-0002-6402-3514"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yujia Wang","raw_affiliation_strings":["National University of Singapore,Department of Chemical and Biomolecular Engineering,Singapore,117585"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Chemical and Biomolecular Engineering,Singapore,117585","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112281896","display_name":"Ming Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ming Xiao","raw_affiliation_strings":["National University of Singapore,Department of Chemical and Biomolecular Engineering,Singapore,117585"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Chemical and Biomolecular Engineering,Singapore,117585","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103121977","display_name":"Zhe Wu","orcid":"https://orcid.org/0009-0006-2598-3789"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhe Wu","raw_affiliation_strings":["National University of Singapore,Department of Chemical and Biomolecular Engineering,Singapore,117585"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Chemical and Biomolecular Engineering,Singapore,117585","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100767800"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3178186,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5654","last_page":"5661"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9707000255584717,"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":0.9707000255584717,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.9684000015258789,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9052000045776367,"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":0.8236759901046753},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7220642566680908},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5840237736701965},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5404755473136902},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4389103651046753}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8236759901046753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7220642566680908},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5840237736701965},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5404755473136902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4389103651046753},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc56724.2024.10886726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2962708723","https://openalex.org/W2964849820","https://openalex.org/W3045059767","https://openalex.org/W4281738288","https://openalex.org/W4322773459","https://openalex.org/W4368232611","https://openalex.org/W4382937767","https://openalex.org/W4383112908","https://openalex.org/W4387385622","https://openalex.org/W4389082827","https://openalex.org/W6636267554","https://openalex.org/W6751818914","https://openalex.org/W6838701874"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Traditional":[0],"reinforcement":[1,47],"learning":[2,48,62,74,111],"(RL)":[3],"methods":[4],"for":[5,79,119,138],"optimal":[6,135,156,168],"control":[7,82,94,98,131,157,169],"of":[8,27,31,106,155,158],"nonlinear":[9],"processes":[10],"often":[11],"face":[12],"challenges":[13],"such":[14],"as":[15],"substantial":[16],"demands":[17],"on":[18],"computational":[19,77,173],"resources":[20],"and":[21,24,76,91,133,144,175],"training":[22],"time,":[23],"the":[25,29,32,85,93,104,107,110,120,129,134,139,142,167],"difficulty":[26],"ensuring":[28],"safety":[30,105,176],"closed-loop":[33],"system":[34,108],"during":[35],"training.":[36],"To":[37],"overcome":[38],"these":[39],"challenges,":[40],"this":[41],"work":[42],"proposes":[43],"a":[44,64,81,97,116,159],"safe":[45],"transfer":[46],"(TRL)":[49],"framework.":[50],"The":[51],"algorithm":[52,122],"leverages":[53],"knowledge":[54],"obtained":[55],"from":[56],"pre-trained":[57],"source":[58,145],"tasks":[59],"to":[60,102],"expedite":[61],"in":[63,165],"new":[65],"yet":[66],"related":[67],"target":[68,143],"task,":[69],"thereby":[70],"significantly":[71],"reducing":[72],"both":[73],"time":[75],"overhead":[78],"optimizing":[80],"policy.":[83],"Additionally,":[84],"proposed":[86],"TRL":[87,121],"method":[88],"collects":[89],"data":[90],"optimizes":[92],"policy":[95,132],"within":[96],"invariant":[99],"set":[100],"(CIS)":[101],"ensure":[103],"throughout":[109],"process.":[112],"Furthermore,":[113],"we":[114,148],"develop":[115],"theoretical":[117],"analysis":[118],"that":[123],"establishes":[124],"an":[125,153],"error":[126],"bound":[127],"between":[128,141],"approximate":[130],"ones,":[136],"accounting":[137],"discrepancy":[140],"tasks.":[146],"Finally,":[147],"validate":[149],"our":[150],"approach":[151],"using":[152],"example":[154],"chemical":[160],"reactor,":[161],"showcasing":[162],"its":[163],"effectiveness":[164],"solving":[166],"problem":[170],"with":[171],"improved":[172],"efficiency":[174],"guarantees.":[177]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}