{"id":"https://openalex.org/W2973117511","doi":"https://doi.org/10.23919/acc.2019.8814892","title":"Distributed Reinforcement Learning with ADMM-RL","display_name":"Distributed Reinforcement Learning with ADMM-RL","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2973117511","doi":"https://doi.org/10.23919/acc.2019.8814892","mag":"2973117511"},"language":"en","primary_location":{"id":"doi:10.23919/acc.2019.8814892","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2019.8814892","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":"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/A5008431584","display_name":"Peter Gr\u00e4f","orcid":"https://orcid.org/0000-0003-3150-3404"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Peter Graf","raw_affiliation_strings":["Budapest University of Technology and Economics"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055162929","display_name":"Jennifer Annoni","orcid":null},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Jennifer Annoni","raw_affiliation_strings":["Budapest University of Technology and Economics"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072710410","display_name":"Christopher J. Bay","orcid":"https://orcid.org/0000-0002-2658-5559"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Christopher Bay","raw_affiliation_strings":["Budapest University of Technology and Economics"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111240190","display_name":"Dave Biagioni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dave Biagioni","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038341934","display_name":"Devon Sigler","orcid":"https://orcid.org/0000-0001-7672-6658"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Devon Sigler","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087968855","display_name":"Monte Lunacek","orcid":"https://orcid.org/0000-0003-3755-224X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Monte Lunacek","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113497996","display_name":"Wesley Jones","orcid":"https://orcid.org/0009-0004-9930-7906"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wesley Jones","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5008431584"],"corresponding_institution_ids":["https://openalex.org/I29770179"],"apc_list":null,"apc_paid":null,"fwci":1.3115,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.81183836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4159","last_page":"4166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10603","display_name":"Smart Grid Energy Management","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.9912999868392944,"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/T12546","display_name":"Smart Parking Systems Research","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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":0.8985346555709839},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7559492588043213},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5661778450012207},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5400140881538391},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4940486252307892},{"id":"https://openalex.org/keywords/distributed-algorithm","display_name":"Distributed algorithm","score":0.4521512985229492},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4451615810394287},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4386337399482727},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.4300861060619354},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3675438165664673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.283169686794281},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13216838240623474},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12341389060020447}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8985346555709839},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559492588043213},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5661778450012207},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5400140881538391},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4940486252307892},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.4521512985229492},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4451615810394287},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4386337399482727},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4300861060619354},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3675438165664673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.283169686794281},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13216838240623474},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12341389060020447},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc.2019.8814892","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2019.8814892","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8999999761581421,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1797178173","https://openalex.org/W1980183459","https://openalex.org/W2011393317","https://openalex.org/W2058532290","https://openalex.org/W2164278908","https://openalex.org/W2164594722","https://openalex.org/W2257208204","https://openalex.org/W2257979135","https://openalex.org/W2289936019","https://openalex.org/W2313629133","https://openalex.org/W2314542973","https://openalex.org/W2341508215","https://openalex.org/W2476720678","https://openalex.org/W2530065124","https://openalex.org/W2545362633","https://openalex.org/W2589898154","https://openalex.org/W2611081443","https://openalex.org/W2735874191","https://openalex.org/W2766713059","https://openalex.org/W2774966954","https://openalex.org/W2785343939","https://openalex.org/W2793472973","https://openalex.org/W2796922012","https://openalex.org/W2887757979","https://openalex.org/W2962893376","https://openalex.org/W2963028406","https://openalex.org/W3100495951","https://openalex.org/W3102961917","https://openalex.org/W3103253084","https://openalex.org/W3104243370","https://openalex.org/W3104678126","https://openalex.org/W4214717370","https://openalex.org/W4292363360","https://openalex.org/W4295113716"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,48,132],"new":[4],"algorithm":[5,80,108],"for":[6,22,63,81,165],"distributed":[7,72,82,94,144,155,161],"Reinforcement":[8],"Learning":[9],"(RL).":[10],"RL":[11],"is":[12],"an":[13],"artificial":[14],"intelligence":[15],"(AI)":[16],"control":[17,73,159],"strategy":[18],"such":[19],"that":[20,61,135],"controls":[21],"highly":[23],"nonlinear":[24],"systems":[25],"over":[26],"multi-step":[27],"time":[28],"horizons":[29],"may":[30],"be":[31],"learned":[32,65],"by":[33,42,146],"experience,":[34],"rather":[35],"than":[36],"directly":[37],"computed":[38],"on":[39],"the":[40,51,78,85,97,100,114,124,139,142],"fly":[41],"optimization.":[43],"Here":[44],"we":[45,128],"introduce":[46],"ADMM-RL,":[47],"combination":[49],"of":[50,55,87,99,102,113,121,141,148],"Alternating":[52],"Direction":[53],"Method":[54],"Multipliers":[56],"(ADMM)":[57],"and":[58,160],"reinforcement":[59],"learning":[60],"allows":[62],"integrating":[64],"controllers":[66],"as":[67],"subsystems":[68],"in":[69,116,153],"generally":[70],"convergent":[71],"applications.":[74],"ADMM":[75,117],"has":[76],"become":[77],"workhorse":[79],"control,":[83],"combining":[84],"advantages":[86,98],"dual":[88],"decomposition":[89],"(namely,":[90,104],"enabling":[91],"decoupled,":[92],"parallel,":[93],"solution)":[95],"with":[96,118,131],"method":[101],"multipliers":[103],"convexification/stability).":[105],"Our":[106],"ADMM-RL":[107,152],"replaces":[109],"one":[110],"or":[111],"more":[112],"subproblems":[115],"several":[119],"steps":[120],"RL.":[122],"When":[123],"nested":[125],"iterations":[126],"converge,":[127],"are":[129],"left":[130],"pretrained":[133],"subsolver":[134],"can":[136],"potentially":[137],"increase":[138],"efficiency":[140],"deployed":[143],"controller":[145],"orders":[147],"magnitude.":[149],"We":[150],"illustrate":[151],"both":[154],"wind":[156],"farm":[157],"yaw":[158],"grid-aware":[162],"demand":[163],"aggregation":[164],"water":[166],"heaters.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}