{"id":"https://openalex.org/W4315471956","doi":"https://doi.org/10.1109/cdc51059.2022.9992584","title":"Structured-policy Q-learning: an LMI-based Design Strategy for Distributed Reinforcement Learning","display_name":"Structured-policy Q-learning: an LMI-based Design Strategy for Distributed Reinforcement Learning","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4315471956","doi":"https://doi.org/10.1109/cdc51059.2022.9992584"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9992584","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9992584","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st 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/A5028413077","display_name":"Lorenzo Sforni","orcid":"https://orcid.org/0000-0002-9910-4525"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Lorenzo Sforni","raw_affiliation_strings":["University of Bologna,Department of Electrical, Electronic and Information Engineering,Bologna,Italy","Department of Electrical, Electronic and Information Engineering, University of Bologna, Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"University of Bologna,Department of Electrical, Electronic and Information Engineering,Bologna,Italy","institution_ids":["https://openalex.org/I9360294"]},{"raw_affiliation_string":"Department of Electrical, Electronic and Information Engineering, University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011466605","display_name":"Andrea Camisa","orcid":"https://orcid.org/0000-0001-8524-2540"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Camisa","raw_affiliation_strings":["University of Bologna,Department of Electrical, Electronic and Information Engineering,Bologna,Italy","Department of Electrical, Electronic and Information Engineering, University of Bologna, Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"University of Bologna,Department of Electrical, Electronic and Information Engineering,Bologna,Italy","institution_ids":["https://openalex.org/I9360294"]},{"raw_affiliation_string":"Department of Electrical, Electronic and Information Engineering, University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017893179","display_name":"Giuseppe Notarstefano","orcid":"https://orcid.org/0000-0002-0906-7848"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giuseppe Notarstefano","raw_affiliation_strings":["University of Bologna,Department of Electrical, Electronic and Information Engineering,Bologna,Italy","Department of Electrical, Electronic and Information Engineering, University of Bologna, Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"University of Bologna,Department of Electrical, Electronic and Information Engineering,Bologna,Italy","institution_ids":["https://openalex.org/I9360294"]},{"raw_affiliation_string":"Department of Electrical, Electronic and Information Engineering, University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028413077"],"corresponding_institution_ids":["https://openalex.org/I9360294"],"apc_list":null,"apc_paid":null,"fwci":0.7078,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67371082,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4059","last_page":"4064"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10046","display_name":"Stability and Control of Uncertain Systems","score":0.9972000122070312,"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/T10046","display_name":"Stability and Control of Uncertain Systems","score":0.9972000122070312,"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":0.9947999715805054,"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/T11347","display_name":"Neural Networks Stability and Synchronization","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7534836530685425},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6190907955169678},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5046612024307251},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4720029830932617},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4506932199001312},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.44993096590042114},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4431035816669464},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4427969753742218},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.43182307481765747},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.42254793643951416},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.31453415751457214},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2248947024345398},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.22003179788589478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1631186604499817}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7534836530685425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6190907955169678},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5046612024307251},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4720029830932617},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4506932199001312},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.44993096590042114},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4431035816669464},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4427969753742218},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43182307481765747},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.42254793643951416},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.31453415751457214},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2248947024345398},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.22003179788589478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1631186604499817},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cdc51059.2022.9992584","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9992584","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:cris.unibo.it:11585/970122","is_oa":false,"landing_page_url":"https://hdl.handle.net/11585/970122","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323988","display_name":"Ministero degli Affari Esteri e della Cooperazione Internazionale","ror":"https://ror.org/02jkm3388"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1616818660","https://openalex.org/W1980183459","https://openalex.org/W2068364617","https://openalex.org/W2098432798","https://openalex.org/W2135519533","https://openalex.org/W2903778291","https://openalex.org/W2914198722","https://openalex.org/W2963272580","https://openalex.org/W2972609400","https://openalex.org/W2979207987","https://openalex.org/W3010758700","https://openalex.org/W3102961917","https://openalex.org/W3137642493","https://openalex.org/W3155335021","https://openalex.org/W3155542523","https://openalex.org/W3155701378","https://openalex.org/W3157457774","https://openalex.org/W3161299873","https://openalex.org/W3213818741"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2937181779"],"abstract_inverted_index":{"In":[0],"this":[1,38],"paper,":[2],"we":[3,65],"consider":[4],"a":[5,30,67,73,77,103,124,159],"Linear":[6],"Quadratic":[7],"optimal":[8,54],"control":[9,25,43,127,161],"problem":[10],"with":[11,29,128,133,163],"the":[12,15,22,48,58,63,85,88,96,110,118,129,145],"assumptions":[13],"that":[14,21,117,140],"system":[16],"dynamics":[17],"is":[18,41,50,92,113,149,155],"unknown":[19],"and":[20,101,132,151,167],"designed":[23],"feedback":[24,91,106,126,147],"has":[26],"to":[27,51],"comply":[28],"desired":[31,78,130],"sparsity":[32,131],"pattern.":[33],"An":[34],"important":[35],"application":[36],"where":[37,47],"set-up":[39],"arises":[40],"distributed":[42,160],"of":[44,87,98,144],"network":[45],"systems,":[46],"aim":[49],"find":[52],"an":[53],"sparse":[55,105,150],"controller":[56],"matching":[57],"communication":[59],"graph.":[60],"To":[61],"tackle":[62],"problem,":[64],"propose":[66],"Reinforcement":[68],"Learning":[69],"framework":[70],"based":[71],"on":[72,109,158],"Q-learning":[74],"scheme":[75,119],"preserving":[76],"policy":[79],"structure.":[80],"At":[81],"each":[82,122],"time":[83],"step":[84],"performance":[86],"current":[89],"candidate":[90],"first":[93],"evaluated":[94],"through":[95],"computation":[97],"its":[99],"Q-function,":[100],"then":[102],"new":[104],"matrix,":[107],"improving":[108],"previous":[111],"one,":[112],"computed.":[114],"We":[115],"prove":[116],"produces":[120],"at":[121],"iteration":[123],"stabilizing":[125],"non-increasing":[134],"cost,":[135],"which":[136],"in":[137],"turns":[138],"indicates":[139],"every":[141],"limit":[142],"point":[143],"computed":[146],"matrices":[148],"stabilizing.":[152],"The":[153],"algorithm":[154],"numerically":[156],"tested":[157],"scenario":[162],"randomly":[164],"generated":[165],"graph":[166],"unstable":[168],"dynamics.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
