{"id":"https://openalex.org/W2891102807","doi":"https://doi.org/10.23919/acc.2019.8814663","title":"Distributed Q-Learning for Dynamically Decoupled Systems","display_name":"Distributed Q-Learning for Dynamically Decoupled Systems","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2891102807","doi":"https://doi.org/10.23919/acc.2019.8814663","mag":"2891102807"},"language":"en","primary_location":{"id":"doi:10.23919/acc.2019.8814663","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2019.8814663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1809.08745","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052498925","display_name":"Siavash Alemzadeh","orcid":"https://orcid.org/0000-0002-2259-3172"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I46020346","display_name":"American Institute of Aeronautics and Astronautics","ror":"https://ror.org/00a1rzv11","country_code":"US","type":"other","lineage":["https://openalex.org/I46020346"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siavash Alemzadeh","raw_affiliation_strings":["William E. Boeing Department of Aeronautics and Astronautics, University of Washington, Seattle, WA, USA","Univ. of Washington, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"William E. Boeing Department of Aeronautics and Astronautics, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I46020346","https://openalex.org/I201448701"]},{"raw_affiliation_string":"Univ. of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040511603","display_name":"Mehran Mesbahi","orcid":"https://orcid.org/0000-0001-6972-6588"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I46020346","display_name":"American Institute of Aeronautics and Astronautics","ror":"https://ror.org/00a1rzv11","country_code":"US","type":"other","lineage":["https://openalex.org/I46020346"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehran Mesbahi","raw_affiliation_strings":["William E. Boeing Department of Aeronautics and Astronautics, University of Washington, Seattle, WA, USA","Univ. of Washington, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"William E. Boeing Department of Aeronautics and Astronautics, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I46020346","https://openalex.org/I201448701"]},{"raw_affiliation_string":"Univ. of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3856,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60602343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9939000010490417,"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"}},{"id":"https://openalex.org/T10046","display_name":"Stability and Control of Uncertain Systems","score":0.9843999743461609,"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/computer-science","display_name":"Computer science","score":0.7398216724395752},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.6793991327285767},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6280717253684998},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.5557427406311035},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.555122971534729},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.460690975189209},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.45693439245224},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44488412141799927},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.41081929206848145},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3634112477302551},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3507325053215027},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.19437989592552185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18275731801986694},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12601327896118164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7398216724395752},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.6793991327285767},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6280717253684998},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.5557427406311035},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.555122971534729},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.460690975189209},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45693439245224},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44488412141799927},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.41081929206848145},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3634112477302551},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3507325053215027},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.19437989592552185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18275731801986694},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12601327896118164},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.23919/acc.2019.8814663","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2019.8814663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 American Control Conference (ACC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1809.08745","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.08745","pdf_url":"https://arxiv.org/pdf/1809.08745","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2891102807","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1809.08745.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1809.08745","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1809.08745","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1809.08745","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.08745","pdf_url":"https://arxiv.org/pdf/1809.08745","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2891102807.pdf","grobid_xml":"https://content.openalex.org/works/W2891102807.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W6614468","https://openalex.org/W32403112","https://openalex.org/W33114918","https://openalex.org/W1513798530","https://openalex.org/W1597990070","https://openalex.org/W1788292158","https://openalex.org/W1918371733","https://openalex.org/W2093038430","https://openalex.org/W2104359570","https://openalex.org/W2135519533","https://openalex.org/W2136598296","https://openalex.org/W2146890818","https://openalex.org/W2152161277","https://openalex.org/W2164894752","https://openalex.org/W2508598219","https://openalex.org/W2730945235","https://openalex.org/W2761923184","https://openalex.org/W2773122208","https://openalex.org/W2883399842","https://openalex.org/W2888103878","https://openalex.org/W2909227050","https://openalex.org/W2962951410","https://openalex.org/W2963539937","https://openalex.org/W2964071008"],"related_works":["https://openalex.org/W3136246956","https://openalex.org/W2466955207","https://openalex.org/W2126310365","https://openalex.org/W3095424680","https://openalex.org/W2784721046","https://openalex.org/W23560277","https://openalex.org/W2802030052","https://openalex.org/W2044463529","https://openalex.org/W1576260368","https://openalex.org/W3103567921","https://openalex.org/W2897355207","https://openalex.org/W2587975700","https://openalex.org/W2606642825","https://openalex.org/W2791393106","https://openalex.org/W3184003142","https://openalex.org/W2023391151","https://openalex.org/W1582977901","https://openalex.org/W2924384716","https://openalex.org/W2807485049","https://openalex.org/W3007472775"],"abstract_inverted_index":{"Control":[0],"of":[1,9,25,35,89,104],"large-scale":[2],"networked":[3],"systems":[4],"often":[5],"necessitates":[6],"the":[7,13,16,33,42,54,57,80,86,90,101,109,114,130],"availability":[8],"complex":[10],"models":[11,24],"for":[12,100,120],"interactions":[14,27],"amongst":[15],"agents.":[17],"However,":[18],"in":[19],"many":[20],"applications":[21],"building":[22],"accurate":[23],"these":[26],"might":[28],"be":[29],"prohibitive":[30],"due":[31],"to":[32,69,113],"curse":[34],"dimensionality":[36],"or":[37],"their":[38],"inherent":[39],"complexity.":[40],"In":[41,60],"meantime,":[43],"data-guided":[44],"control":[45],"methods":[46],"can":[47],"circumvent":[48],"model":[49],"complexity":[50],"by":[51],"directly":[52],"synthesizing":[53],"controller":[55,111,119],"from":[56,93],"observed":[58],"data.":[59],"this":[61],"paper,":[62],"we":[63],"propose":[64],"a":[65,71,94,125],"distributed":[66,87],"Q-learning":[67],"algorithm":[68],"design":[70],"feedback":[72],"mechanism":[73],"given":[74],"an":[75,133],"underlying":[76],"graph":[77],"structure":[78],"parameterizing":[79],"agents'":[81],"communication.":[82],"We":[83,123],"assume":[84],"that":[85,99],"nature":[88],"system":[91],"arises":[92],"common":[95],"cost":[96],"and":[97,128],"show":[98],"particular":[102],"case":[103],"identical":[105],"dynamically":[106],"decoupled":[107],"systems,":[108],"learned":[110],"converges":[112],"optimal":[115],"Linear":[116],"Quadratic":[117],"Regulator":[118],"each":[121],"subsystem.":[122],"provide":[124],"convergence":[126],"analysis":[127],"verify":[129],"result":[131],"with":[132],"example.":[134]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
