{"id":"https://openalex.org/W3085733781","doi":"https://doi.org/10.1109/jiot.2020.3023111","title":"Deep Multiagent Reinforcement-Learning-Based Resource Allocation for Internet of Controllable Things","display_name":"Deep Multiagent Reinforcement-Learning-Based Resource Allocation for Internet of Controllable Things","publication_year":2020,"publication_date":"2020-09-10","ids":{"openalex":"https://openalex.org/W3085733781","doi":"https://doi.org/10.1109/jiot.2020.3023111","mag":"3085733781"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2020.3023111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2020.3023111","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/A5013964496","display_name":"Bo Gu","orcid":"https://orcid.org/0000-0003-0556-2769"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Gu","raw_affiliation_strings":["School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0556-2769","affiliations":[{"raw_affiliation_string":"School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106615651","display_name":"Xu Zhang","orcid":"https://orcid.org/0000-0001-6951-6353"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Zhang","raw_affiliation_strings":["School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082169968","display_name":"Ziqi Lin","orcid":"https://orcid.org/0000-0003-4765-2236"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqi Lin","raw_affiliation_strings":["School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018409592","display_name":"Mamoun Alazab","orcid":"https://orcid.org/0000-0002-1928-3704"},"institutions":[{"id":"https://openalex.org/I29894533","display_name":"Charles Darwin University","ror":"https://ror.org/048zcaj52","country_code":"AU","type":"education","lineage":["https://openalex.org/I29894533"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mamoun Alazab","raw_affiliation_strings":["College of Engineering, IT and Environment, Charles Darwin University, Darwin, NT, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1928-3704","affiliations":[{"raw_affiliation_string":"College of Engineering, IT and Environment, Charles Darwin University, Darwin, NT, Australia","institution_ids":["https://openalex.org/I29894533"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.1095,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.97290173,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"8","issue":"5","first_page":"3066","last_page":"3074"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","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/T13553","display_name":"Age of Information Optimization","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/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.9991999864578247,"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/T11392","display_name":"Energy Harvesting in Wireless Networks","score":0.9988999962806702,"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":0.87477707862854},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8663454055786133},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7123194932937622},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.5989514589309692},{"id":"https://openalex.org/keywords/subcarrier","display_name":"Subcarrier","score":0.5775923728942871},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5720038414001465},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.49247488379478455},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4306989014148712},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.4301730692386627},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4275500774383545},{"id":"https://openalex.org/keywords/channel-state-information","display_name":"Channel state information","score":0.42286932468414307},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3989656865596771},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3433591425418854},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.2917119562625885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2898094356060028},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.2613191604614258},{"id":"https://openalex.org/keywords/orthogonal-frequency-division-multiplexing","display_name":"Orthogonal frequency-division multiplexing","score":0.21101725101470947},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1504209339618683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.87477707862854},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8663454055786133},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7123194932937622},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.5989514589309692},{"id":"https://openalex.org/C198329298","wikidata":"https://www.wikidata.org/wiki/Q586358","display_name":"Subcarrier","level":4,"score":0.5775923728942871},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5720038414001465},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.49247488379478455},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4306989014148712},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.4301730692386627},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4275500774383545},{"id":"https://openalex.org/C148063708","wikidata":"https://www.wikidata.org/wiki/Q5072511","display_name":"Channel state information","level":3,"score":0.42286932468414307},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3989656865596771},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3433591425418854},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.2917119562625885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2898094356060028},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.2613191604614258},{"id":"https://openalex.org/C40409654","wikidata":"https://www.wikidata.org/wiki/Q375889","display_name":"Orthogonal frequency-division multiplexing","level":3,"score":0.21101725101470947},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1504209339618683},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2020.3023111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2020.3023111","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2007178635","https://openalex.org/W2023472100","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2166706236","https://openalex.org/W2317911375","https://openalex.org/W2341380473","https://openalex.org/W2483325812","https://openalex.org/W2507533130","https://openalex.org/W2513356504","https://openalex.org/W2518231294","https://openalex.org/W2591988884","https://openalex.org/W2601125325","https://openalex.org/W2616867685","https://openalex.org/W2737159091","https://openalex.org/W2746553466","https://openalex.org/W2783165406","https://openalex.org/W2801412442","https://openalex.org/W2808560727","https://openalex.org/W2892023691","https://openalex.org/W2895341959","https://openalex.org/W2921537971","https://openalex.org/W2922273628","https://openalex.org/W2936616973","https://openalex.org/W2963000651","https://openalex.org/W2968018638","https://openalex.org/W2969195240","https://openalex.org/W3000142059","https://openalex.org/W3005260862","https://openalex.org/W3035100146","https://openalex.org/W3102812201","https://openalex.org/W3104396742","https://openalex.org/W4214717370","https://openalex.org/W6652106736","https://openalex.org/W6684249991"],"related_works":["https://openalex.org/W2155294209","https://openalex.org/W2808418668","https://openalex.org/W2169491089","https://openalex.org/W2359859694","https://openalex.org/W2101748387","https://openalex.org/W2357975469","https://openalex.org/W4380550992","https://openalex.org/W4322760752","https://openalex.org/W3096874164","https://openalex.org/W2146763310"],"abstract_inverted_index":{"Ultrareliable":[0],"and":[1,38,59,80,167],"low-latency":[2],"communication":[3],"(URLLC)":[4],"is":[5,63,148,155],"a":[6,42,76,83,113,131],"prerequisite":[7],"for":[8,30,158],"the":[9,13,23,72,94,98,127,138,152,161,168],"successful":[10],"implementation":[11],"of":[12,15,25,45,100],"Internet":[14],"Controllable":[16],"Things.":[17],"In":[18],"this":[19],"article,":[20],"we":[21],"investigate":[22],"potential":[24],"deep":[26,85],"reinforcement":[27],"learning":[28,114],"(DRL)":[29],"joint":[31],"subcarrier-power":[32,120],"allocation":[33,90,121],"to":[34,55,65,92],"achieve":[35],"low":[36],"latency":[37],"high":[39],"reliability":[40],"in":[41,97,130,144],"general":[43],"form":[44],"device-to-device":[46],"(D2D)":[47],"networks,":[48],"where":[49,160],"each":[50,60,108],"subcarrier":[51],"can":[52],"be":[53,172],"allocated":[54],"multiple":[56,67],"D2D":[57,61,109],"pairs":[58],"pair":[62,110],"permitted":[64],"utilize":[66],"subcarriers.":[68],"We":[69],"first":[70],"formulate":[71],"above":[73],"problem":[74],"as":[75,112],"Markov":[77],"decision":[78],"process":[79],"then":[81],"propose":[82],"double":[84],"$Q$":[86],"-network":[87],"(DQN)-based":[88],"resource":[89],"algorithm":[91,140,154],"learn":[93],"optimal":[95],"policy":[96],"absence":[99],"full":[101],"instantaneous":[102],"channel":[103],"state":[104],"information":[105],"(CSI).":[106],"Specifically,":[107],"acts":[111],"agent":[115],"that":[116,137,151],"adjusts":[117],"its":[118],"own":[119],"strategy":[122],"iteratively":[123],"through":[124],"interactions":[125],"with":[126],"operating":[128],"environment":[129],"trial-and-error":[132],"fashion.":[133],"Simulation":[134],"results":[135],"demonstrate":[136],"proposed":[139,153],"achieves":[141],"near-optimal":[142],"performance":[143],"real":[145],"time.":[146],"It":[147],"worth":[149],"mentioning":[150],"especially":[156],"suitable":[157],"cases":[159],"environmental":[162],"dynamics":[163],"are":[164],"not":[165],"accurate":[166],"CSI":[169],"delay":[170],"cannot":[171],"ignored.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":16},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T08:27:34.040176","created_date":"2025-10-10T00:00:00"}