{"id":"https://openalex.org/W4285114354","doi":"https://doi.org/10.1109/jiot.2022.3187067","title":"Adaptive Stochastic ADMM for Decentralized Reinforcement Learning in Edge IoT","display_name":"Adaptive Stochastic ADMM for Decentralized Reinforcement Learning in Edge IoT","publication_year":2022,"publication_date":"2022-06-29","ids":{"openalex":"https://openalex.org/W4285114354","doi":"https://doi.org/10.1109/jiot.2022.3187067"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2022.3187067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2022.3187067","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","raw_type":"journal-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/A5052823220","display_name":"Wanlu Lei","orcid":"https://orcid.org/0000-0002-9878-3722"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]},{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Wanlu Lei","raw_affiliation_strings":["Interconnection Design in Baseband and Interconnect Department, Ericsson AB, Stockholm, Sweden","Division of Information Science and Engineering, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Interconnection Design in Baseband and Interconnect Department, Ericsson AB, Stockholm, Sweden","institution_ids":["https://openalex.org/I1306339040"]},{"raw_affiliation_string":"Division of Information Science and Engineering, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100421130","display_name":"Yu Ye","orcid":"https://orcid.org/0000-0003-4686-0973"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Yu Ye","raw_affiliation_strings":["Division of Information Science and Engineering, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Division of Information Science and Engineering, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037292846","display_name":"Ming Xiao","orcid":"https://orcid.org/0000-0002-5407-0835"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ming Xiao","raw_affiliation_strings":["Division of Information Science and Engineering, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Division of Information Science and Engineering, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041348422","display_name":"Mikael Skoglund","orcid":"https://orcid.org/0000-0002-7926-5081"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Mikael Skoglund","raw_affiliation_strings":["Division of Information Science and Engineering, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Division of Information Science and Engineering, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063667378","display_name":"Zhu Han","orcid":"https://orcid.org/0000-0002-6606-5822"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhu Han","raw_affiliation_strings":["Computer Science Department, University of Houston, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5052823220"],"corresponding_institution_ids":["https://openalex.org/I1306339040","https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":1.3806,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.8165856,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"9","issue":"22","first_page":"22958","last_page":"22971"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9995999932289124,"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/T11392","display_name":"Energy Harvesting in Wireless Networks","score":0.9994000196456909,"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/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7015501260757446},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5668354630470276},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4934143126010895},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4885810315608978},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.47583436965942383},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.46017375588417053},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4250005781650543},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3643549382686615},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2142947018146515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2125566601753235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7015501260757446},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5668354630470276},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4934143126010895},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4885810315608978},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.47583436965942383},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.46017375588417053},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4250005781650543},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3643549382686615},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2142947018146515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2125566601753235},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2022.3187067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2022.3187067","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G31471538","display_name":null,"funder_award_id":"CNS-2128368","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G400433832","display_name":null,"funder_award_id":"CNS-2107216","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1522301498","https://openalex.org/W1571416372","https://openalex.org/W1616857247","https://openalex.org/W1658008008","https://openalex.org/W1663274500","https://openalex.org/W1771410628","https://openalex.org/W1985256709","https://openalex.org/W2012587148","https://openalex.org/W2044212084","https://openalex.org/W2119717200","https://openalex.org/W2123705108","https://openalex.org/W2134130436","https://openalex.org/W2141788746","https://openalex.org/W2144446635","https://openalex.org/W2530849036","https://openalex.org/W2594560857","https://openalex.org/W2604718646","https://openalex.org/W2617089797","https://openalex.org/W2623902153","https://openalex.org/W2736601468","https://openalex.org/W2766401293","https://openalex.org/W2766447205","https://openalex.org/W2788115019","https://openalex.org/W2803652442","https://openalex.org/W2898652425","https://openalex.org/W2904012927","https://openalex.org/W2937905591","https://openalex.org/W2945566309","https://openalex.org/W2964043796","https://openalex.org/W2964098968","https://openalex.org/W2982530739","https://openalex.org/W2994803162","https://openalex.org/W3009440920","https://openalex.org/W3013377893","https://openalex.org/W3014507393","https://openalex.org/W3023434827","https://openalex.org/W3028318515","https://openalex.org/W3035221273","https://openalex.org/W3040922689","https://openalex.org/W3041911152","https://openalex.org/W3089192431","https://openalex.org/W3102661755","https://openalex.org/W3108171015","https://openalex.org/W3111812716","https://openalex.org/W3119938028","https://openalex.org/W3126909561","https://openalex.org/W3156926772","https://openalex.org/W3157279585","https://openalex.org/W3193505445","https://openalex.org/W4205984388","https://openalex.org/W4214717370","https://openalex.org/W4289760659","https://openalex.org/W4297796878","https://openalex.org/W4301501993","https://openalex.org/W6631190155","https://openalex.org/W6636881020","https://openalex.org/W6637136231","https://openalex.org/W6638018090","https://openalex.org/W6680008295","https://openalex.org/W6692846177","https://openalex.org/W6741002519","https://openalex.org/W6748741829","https://openalex.org/W6749032143","https://openalex.org/W6751972096","https://openalex.org/W6762954024","https://openalex.org/W6774781930","https://openalex.org/W6787650878","https://openalex.org/W6791840442","https://openalex.org/W6794146056"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2389214306","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548"],"abstract_inverted_index":{"Edge":[0],"computing":[1],"provides":[2],"a":[3,40,57,69,77,86,126,173],"promising":[4,58],"paradigm":[5],"to":[6,18,35,55,81,84,88,156,268],"support":[7],"the":[8,23,90,94,114,154,168,179,209,252,255],"implementation":[9,132],"of":[10,12,96,116,122,211,254,259],"Internet":[11],"Things":[13],"(IoT)":[14],"by":[15,171],"offloading":[16],"tasks":[17],"nearby":[19],"edge":[20,72],"nodes.":[21],"Meanwhile,":[22],"increasing":[24],"network":[25,79],"size":[26],"makes":[27],"it":[28],"impractical":[29],"for":[30,60,130,167],"centralized":[31],"data":[32],"processing":[33],"due":[34],"limited":[36],"bandwidth,":[37],"and":[38,53,62,103,133,152,176,201,213,240,262,264],"consequently":[39],"decentralized":[41,70,117,131,157,235],"learning":[42,47,225],"scheme":[43],"is":[44],"preferable.":[45],"Reinforcement":[46],"(RL)":[48],"has":[49,125,134,181],"been":[50],"widely":[51],"investigated":[52],"shown":[54,135],"be":[56],"solution":[59],"decision-making":[61],"optimal":[63],"control":[64],"processes.":[65],"For":[66,227],"RL":[67,158,236],"in":[68,105,234,257],"setup,":[71],"nodes":[73],"(agents)":[74],"connected":[75],"through":[76],"communication":[78,100,260],"aim":[80],"work":[82],"collaboratively":[83],"find":[85],"policy":[87],"optimize":[89],"global":[91],"reward":[92],"as":[93],"sum":[95],"local":[97],"rewards.":[98],"However,":[99],"costs,":[101],"scalability,":[102],"adaptation":[104],"complex":[106,269],"environments":[107],"with":[108,159,222,238],"heterogeneous":[109,241],"agents":[110],"may":[111],"significantly":[112],"limit":[113],"performance":[115,228],"RL.":[118],"Alternating":[119],"direction":[120],"method":[121],"multipliers":[123],"(ADMM)":[124],"structure":[127],"that":[128,178,247],"allows":[129],"faster":[136],"convergence":[137,165,192],"than":[138],"gradient":[139],"descent-based":[140],"methods.":[141],"Therefore,":[142],"we":[143,218,230],"propose":[144],"an":[145],"adaptive":[146],"stochastic":[147],"incremental":[148],"ADMM":[149],"(asI-ADMM)":[150],"algorithm":[151,221],"apply":[153],"asI-ADMM":[155,180],"edge-computing-empowered":[160],"IoT":[161,270],"networks.":[162],"We":[163],"provide":[164],"properties":[166],"proposed":[169,249],"algorithms":[170,250],"designing":[172],"Lyapunov":[174],"function":[175],"prove":[177],"<inline-formula":[182,195,202],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[183,196,203],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[184,197,204],"<tex-math":[185,198,205],"notation=\"LaTeX\">$\\mathcal":[186],"{O}(1/k)":[187],"+":[188],"\\mathcal":[189],"{O}(1/M)$":[190],"</tex-math></inline-formula>":[191,200,207],"rate,":[193],"where":[194],"notation=\"LaTeX\">$k$":[199],"notation=\"LaTeX\">$M$":[206],"are":[208],"number":[210],"iterations":[212],"batch":[214],"samples,":[215],"respectively.":[216],"Then,":[217],"test":[219],"our":[220,248],"two":[223,232],"supervised":[224],"problems.":[226],"evaluation,":[229],"simulate":[231],"applications":[233],"settings":[237],"homogeneous":[239],"agents.":[242],"The":[243],"experimental":[244],"results":[245],"show":[246],"outperform":[251],"state":[253],"art":[256],"terms":[258],"costs":[261],"scalability":[263],"can":[265],"well":[266],"adapt":[267],"environments.":[271]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}