{"id":"https://openalex.org/W4413393619","doi":"https://doi.org/10.23919/acc63710.2025.11108095","title":"Local-Global Learning of Interpretable Control Policies: The Interface between MPC and Reinforcement Learning","display_name":"Local-Global Learning of Interpretable Control Policies: The Interface between MPC and Reinforcement Learning","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W4413393619","doi":"https://doi.org/10.23919/acc63710.2025.11108095"},"language":"en","primary_location":{"id":"doi:10.23919/acc63710.2025.11108095","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11108095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5093657039","display_name":"Thomas Banker","orcid":"https://orcid.org/0000-0002-3519-0823"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Thomas Banker","raw_affiliation_strings":["University of California,Department of Chemical and Biomolecular Engineering,Berkeley,CA,USA,94720"],"affiliations":[{"raw_affiliation_string":"University of California,Department of Chemical and Biomolecular Engineering,Berkeley,CA,USA,94720","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022622508","display_name":"Nathan P. Lawrence","orcid":"https://orcid.org/0000-0002-7147-0048"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan P. Lawrence","raw_affiliation_strings":["University of California,Department of Chemical and Biomolecular Engineering,Berkeley,CA,USA,94720"],"affiliations":[{"raw_affiliation_string":"University of California,Department of Chemical and Biomolecular Engineering,Berkeley,CA,USA,94720","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101555401","display_name":"Ali Mesbah","orcid":"https://orcid.org/0000-0002-1700-0600"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Mesbah","raw_affiliation_strings":["University of California,Department of Chemical and Biomolecular Engineering,Berkeley,CA,USA,94720"],"affiliations":[{"raw_affiliation_string":"University of California,Department of Chemical and Biomolecular Engineering,Berkeley,CA,USA,94720","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5093657039"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":1.2656,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83365232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1367","last_page":"1376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.6855999827384949,"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":0.6855999827384949,"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":0.858595609664917},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6353870630264282},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.5668506622314453},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5044225454330444},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.49730709195137024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4785761833190918},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3704671561717987},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.051463574171066284}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.858595609664917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6353870630264282},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.5668506622314453},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5044225454330444},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.49730709195137024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4785761833190918},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3704671561717987},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.051463574171066284},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc63710.2025.11108095","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11108095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","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"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337510","display_name":"Fusion Energy Sciences","ror":"https://ror.org/02n3j8t12"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1458771408","https://openalex.org/W1608758704","https://openalex.org/W1679855469","https://openalex.org/W1967821692","https://openalex.org/W1978956894","https://openalex.org/W1980035368","https://openalex.org/W2018691083","https://openalex.org/W2027701333","https://openalex.org/W2046376809","https://openalex.org/W2075303074","https://openalex.org/W2091735588","https://openalex.org/W2091755682","https://openalex.org/W2123871098","https://openalex.org/W2152161277","https://openalex.org/W2223181934","https://openalex.org/W2496276084","https://openalex.org/W2557055507","https://openalex.org/W2616006440","https://openalex.org/W2769617651","https://openalex.org/W2822752092","https://openalex.org/W2842089854","https://openalex.org/W2930426397","https://openalex.org/W2948652605","https://openalex.org/W2963184939","https://openalex.org/W2969408081","https://openalex.org/W2973229164","https://openalex.org/W2985363569","https://openalex.org/W4213251304","https://openalex.org/W4294690657","https://openalex.org/W4296124382","https://openalex.org/W4298300677","https://openalex.org/W4385451973","https://openalex.org/W4386515812","https://openalex.org/W4401414310","https://openalex.org/W4406763956"],"related_works":["https://openalex.org/W1990079087","https://openalex.org/W3202234113","https://openalex.org/W4306904969","https://openalex.org/W2101188133","https://openalex.org/W4248731570","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2556120871"],"abstract_inverted_index":{"Making":[0],"optimal":[1,13,95,162],"decisions":[2],"under":[3,164],"uncertainty":[4],"is":[5,15,25,41,65],"a":[6,45,77,91],"shared":[7],"problem":[8],"among":[9],"distinct":[10,134],"fields.":[11],"While":[12],"control":[14,54,73,96],"commonly":[16],"studied":[17],"in":[18,116,150],"the":[19,31,38,62,86,107,146],"framework":[20],"of":[21,30,53,80,132],"dynamic":[22],"programming,":[23],"it":[24],"approached":[26],"with":[27,58],"differing":[28],"perspectives":[29],"Bellman":[32,39,63,109],"optimality":[33,47],"condition.":[34],"In":[35],"one":[36],"perspective,":[37],"equation":[40,64],"used":[42],"to":[43,69],"derive":[44,70],"global":[46,108],"condition":[48],"useful":[49],"for":[50,94,98,136,159],"iterative":[51],"learning":[52,99,118,139],"policies":[55,74],"through":[56,125],"interactions":[57],"an":[59,130],"environment.":[60],"Alternatively,":[61],"also":[66],"widely":[67],"adopted":[68],"tractable":[71],"optimization-based":[72],"that":[75,104],"satisfy":[76,106],"local":[78,101],"notion":[79],"optimality.":[81],"By":[82],"leveraging":[83],"ideas":[84],"from":[85],"two":[87,133],"perspectives,":[88],"we":[89],"present":[90],"local-global":[92,117,152],"paradigm":[93],"suited":[97],"interpretable":[100],"decision":[102],"makers":[103],"approximately":[105],"equation.":[110],"The":[111],"benefits":[112],"and":[113,140,148,161],"practical":[114],"complications":[115],"are":[119,123],"discussed.":[120],"These":[121],"aspects":[122],"exemplified":[124],"case":[126],"studies,":[127],"which":[128],"give":[129],"overview":[131],"strategies":[135],"unifying":[137],"reinforcement":[138],"model":[141],"predictive":[142],"control.":[143],"We":[144],"discuss":[145],"challenges":[147],"trade-offs":[149],"these":[151],"strategies,":[153],"towards":[154],"highlighting":[155],"future":[156],"research":[157],"opportunities":[158],"safe":[160],"decision-making":[163],"uncertainty.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}