{"id":"https://openalex.org/W4400230177","doi":"https://doi.org/10.1109/iscas58744.2024.10558623","title":"Model Predictive Control-Based Reinforcement Learning","display_name":"Model Predictive Control-Based Reinforcement Learning","publication_year":2024,"publication_date":"2024-05-19","ids":{"openalex":"https://openalex.org/W4400230177","doi":"https://doi.org/10.1109/iscas58744.2024.10558623"},"language":"en","primary_location":{"id":"doi:10.1109/iscas58744.2024.10558623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas58744.2024.10558623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5010615576","display_name":"Qiang Han","orcid":"https://orcid.org/0000-0001-5646-3950"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qiang Han","raw_affiliation_strings":["The University of Western Australia,Department of Electrical, Electronic & Computer Engineering,Perth,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Western Australia,Department of Electrical, Electronic & Computer Engineering,Perth,Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014216530","display_name":"Farid Boussa\u00efd","orcid":"https://orcid.org/0000-0001-7250-7407"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Farid Boussaid","raw_affiliation_strings":["The University of Western Australia,Department of Electrical, Electronic & Computer Engineering,Perth,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Western Australia,Department of Electrical, Electronic & Computer Engineering,Perth,Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009750573","display_name":"Mohammed Bennamoun","orcid":"https://orcid.org/0000-0002-6603-3257"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mohammed Bennamoun","raw_affiliation_strings":["The University of Western Australia,Department of Computer Science and Software Engineering,Perth,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Western Australia,Department of Computer Science and Software Engineering,Perth,Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177877127"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9800000190734863,"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":0.9800000190734863,"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":0.9106000065803528,"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":0.7736994028091431},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.6515748500823975},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6482995748519897},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4680834412574768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41747626662254333},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3561369776725769}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7736994028091431},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.6515748500823975},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6482995748519897},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4680834412574768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41747626662254333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3561369776725769}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iscas58744.2024.10558623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas58744.2024.10558623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/50a87a14-f863-4baa-a0be-c3de21b6e492","is_oa":false,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/50a87a14-f863-4baa-a0be-c3de21b6e492","pdf_url":null,"source":{"id":"https://openalex.org/S4306402492","display_name":"UWA Profiles and Research Repository (UWA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Han, Q, Boussaid, F & Bennamoun, M 2024, Model Predictive Control-Based Reinforcement Learning. in ISCAS 2024 - IEEE International Symposium on Circuits and Systems. Proceedings - IEEE International Symposium on Circuits and Systems, IEEE, Institute of Electrical and Electronics Engineers, Piscataway, 2024 IEEE International Symposium on Circuits and Systems, ISCAS 2024, Singapore, Singapore, 19/05/24. https://doi.org/10.1109/ISCAS58744.2024.10558623","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2034996255","https://openalex.org/W2035003264","https://openalex.org/W2130711276","https://openalex.org/W2969472090","https://openalex.org/W3038822267","https://openalex.org/W3089418186","https://openalex.org/W4211081235","https://openalex.org/W4283311409","https://openalex.org/W4283590445","https://openalex.org/W4285184150","https://openalex.org/W4296413606","https://openalex.org/W4318475970","https://openalex.org/W4320481930","https://openalex.org/W4321764793","https://openalex.org/W4361011606","https://openalex.org/W4377142595","https://openalex.org/W4381733438","https://openalex.org/W6675999342"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"has":[3],"garnered":[4],"much":[5],"attention":[6],"in":[7,68,76,99],"the":[8,64,73,79,91,100,119,133],"field":[9],"of":[10,132],"control":[11],"due":[12],"to":[13,16,22,34],"its":[14],"capacity":[15],"learn":[17],"from":[18],"interactions":[19],"and":[20,24,40,78,96,126],"adapt":[21],"complex":[23],"dynamic":[25,81],"environments.":[26],"However,":[27],"RL":[28,61,69,105,109,124],"is":[29,70,83],"challenging":[30],"because":[31],"it":[32],"needs":[33],"balance":[35],"exploration,":[36],"seeking":[37],"new":[38],"strategies,":[39],"exploitation,":[41],"leveraging":[42],"known":[43],"strategies":[44],"for":[45,93],"maximum":[46],"gain.":[47],"To":[48],"address":[49],"these":[50],"challenges,":[51],"this":[52],"paper":[53],"proposes":[54],"a":[55],"Model":[56],"Predictive":[57],"Control":[58],"(MPC)":[59],"based":[60],"approach,":[62],"where":[63],"state":[65],"value":[66],"function":[67,75],"utilized":[71],"as":[72],"cost":[74],"MPC,":[77],"system":[80,101],"model":[82],"represented":[84],"by":[85],"neural":[86],"networks":[87],"(NNs).":[88],"This":[89],"eliminates":[90],"need":[92],"human":[94],"intervention":[95],"addresses":[97],"inaccuracies":[98],"model.":[102],"Additionally,":[103],"MPC-guided":[104],"accelerates":[106],"convergence":[107],"during":[108],"training,":[110],"thereby":[111],"enhancing":[112],"sample":[113],"efficiency.":[114],"Reported":[115],"results":[116],"demonstrate":[117],"that":[118],"proposed":[120],"method":[121],"outperforms":[122],"traditional":[123],"algorithms":[125],"does":[127],"not":[128],"require":[129],"prior":[130],"knowledge":[131],"system.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}