{"id":"https://openalex.org/W4386825178","doi":"https://doi.org/10.1109/tnsm.2023.3316626","title":"Offline Reinforcement Learning for Asynchronous Task Offloading in Mobile Edge Computing","display_name":"Offline Reinforcement Learning for Asynchronous Task Offloading in Mobile Edge Computing","publication_year":2023,"publication_date":"2023-09-18","ids":{"openalex":"https://openalex.org/W4386825178","doi":"https://doi.org/10.1109/tnsm.2023.3316626"},"language":"en","primary_location":{"id":"doi:10.1109/tnsm.2023.3316626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnsm.2023.3316626","pdf_url":null,"source":{"id":"https://openalex.org/S173527311","display_name":"IEEE Transactions on Network and Service Management","issn_l":"1932-4537","issn":["1932-4537","2373-7379"],"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 Transactions on Network and Service Management","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/A5076424029","display_name":"Bolei Zhang","orcid":"https://orcid.org/0000-0002-9406-4499"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bolei Zhang","raw_affiliation_strings":["School of Computer, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-9406-4499","affiliations":[{"raw_affiliation_string":"School of Computer, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100602821","display_name":"Fu Xiao","orcid":"https://orcid.org/0000-0003-1815-2793"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu Xiao","raw_affiliation_strings":["School of Computer, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0003-1815-2793","affiliations":[{"raw_affiliation_string":"School of Computer, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023896344","display_name":"Lifa Wu","orcid":"https://orcid.org/0000-0001-5457-1923"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lifa Wu","raw_affiliation_strings":["School of Computer, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":1.0528,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78215718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"21","issue":"1","first_page":"939","last_page":"952"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9991000294685364,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9991000294685364,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T13553","display_name":"Age of Information Optimization","score":0.9947999715805054,"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/computer-science","display_name":"Computer science","score":0.9040334224700928},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7646708488464355},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.7514041662216187},{"id":"https://openalex.org/keywords/computation-offloading","display_name":"Computation offloading","score":0.6552196741104126},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.616178035736084},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6062216758728027},{"id":"https://openalex.org/keywords/mobile-edge-computing","display_name":"Mobile edge computing","score":0.6003533601760864},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.48271510004997253},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4310623109340668},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.32251060009002686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2681189179420471}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9040334224700928},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7646708488464355},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.7514041662216187},{"id":"https://openalex.org/C2781041963","wikidata":"https://www.wikidata.org/wiki/Q18348618","display_name":"Computation offloading","level":4,"score":0.6552196741104126},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.616178035736084},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6062216758728027},{"id":"https://openalex.org/C2776061582","wikidata":"https://www.wikidata.org/wiki/Q25325231","display_name":"Mobile edge computing","level":3,"score":0.6003533601760864},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.48271510004997253},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4310623109340668},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.32251060009002686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2681189179420471}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tnsm.2023.3316626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnsm.2023.3316626","pdf_url":null,"source":{"id":"https://openalex.org/S173527311","display_name":"IEEE Transactions on Network and Service Management","issn_l":"1932-4537","issn":["1932-4537","2373-7379"],"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 Transactions on Network and Service Management","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2227299984","display_name":null,"funder_award_id":"62202238","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5630865570","display_name":null,"funder_award_id":"BK20200752","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G8776636448","display_name":null,"funder_award_id":"2019YFB2101704","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W2025652426","https://openalex.org/W2025725209","https://openalex.org/W2043794511","https://openalex.org/W2158782408","https://openalex.org/W2195423816","https://openalex.org/W2483192650","https://openalex.org/W2516316490","https://openalex.org/W2617547828","https://openalex.org/W2736601468","https://openalex.org/W2889540440","https://openalex.org/W2897798676","https://openalex.org/W2905026759","https://openalex.org/W2914154006","https://openalex.org/W2918714081","https://openalex.org/W2920054549","https://openalex.org/W2968424451","https://openalex.org/W2997072274","https://openalex.org/W3022566517","https://openalex.org/W3047266715","https://openalex.org/W3096084597","https://openalex.org/W3113406384","https://openalex.org/W3134823279","https://openalex.org/W3152617927","https://openalex.org/W3172247901","https://openalex.org/W3174997142","https://openalex.org/W3179018212","https://openalex.org/W4206817004","https://openalex.org/W4226313405","https://openalex.org/W4285229621","https://openalex.org/W4285820523","https://openalex.org/W4293566037","https://openalex.org/W4298857966","https://openalex.org/W4387171915","https://openalex.org/W4387185245","https://openalex.org/W4408574154","https://openalex.org/W6637967152","https://openalex.org/W6683204974","https://openalex.org/W6684921986","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6747106673","https://openalex.org/W6747473740","https://openalex.org/W6747941106","https://openalex.org/W6749304979","https://openalex.org/W6757469721","https://openalex.org/W6767327128","https://openalex.org/W6776438516","https://openalex.org/W6777656069","https://openalex.org/W6779265984","https://openalex.org/W6791413555","https://openalex.org/W6796880758"],"related_works":["https://openalex.org/W4200420173","https://openalex.org/W4225987626","https://openalex.org/W3120617837","https://openalex.org/W3127808443","https://openalex.org/W2916011811","https://openalex.org/W3034137700","https://openalex.org/W4362496467","https://openalex.org/W2902693277","https://openalex.org/W4378977105","https://openalex.org/W4406207611"],"abstract_inverted_index":{"Edge":[0],"servers,":[1],"which":[2,63,112],"are":[3,27,64,157,204,221],"located":[4],"in":[5,80,88,103,146,254,279],"close":[6],"proximity":[7],"to":[8,39,46,94,133,182,199,215,223],"mobile":[9,37],"users,":[10],"have":[11,68],"become":[12],"key":[13],"components":[14],"for":[15,34],"providing":[16],"augmented":[17],"computation":[18],"and":[19,29,66,140,180,227,248],"bandwidth.":[20],"As":[21,153],"the":[22,35,41,52,56,100,135,143,147,154,192,195,201,208,225,233,238,251,271,273,280],"resources":[23,54],"of":[24,43,51,194,229],"edge":[25,57,81,136],"servers":[26],"limited":[28],"shared,":[30],"it":[31],"is":[32],"critical":[33],"decentralized":[36],"users":[38,169],"determine":[40],"amount":[42],"offloaded":[44],"workload,":[45],"avoid":[47,99],"competition":[48],"or":[49],"waste":[50],"public":[53],"at":[55],"servers.":[58],"Reinforcement":[59],"learning":[60],"(RL)":[61],"methods,":[62],"sequential":[65],"model-free,":[67],"been":[69],"widely":[70],"considered":[71],"as":[72,170],"a":[73,118,129,162,171,183,243],"promising":[74],"approach.":[75],"However,":[76],"directly":[77],"deploying":[78],"RL":[79,110],"computing":[82,137],"remains":[83],"elusive,":[84],"since":[85],"arbitrary":[86],"exploration":[87],"real":[89,244],"online":[90,217,281],"environments":[91],"often":[92],"leads":[93],"poor":[95],"user":[96],"experience.":[97],"To":[98],"costly":[101],"interactions,":[102],"this":[104,255],"paper,":[105],"we":[106,160,190,235],"propose":[107],"an":[108],"offline":[109,120,131,148,196,239],"framework":[111],"can":[113,176,212,264],"be":[114,178,213],"optimized":[115],"by":[116],"using":[117],"static":[119],"dataset":[121],"only.":[122],"In":[123,232,270],"essence,":[124],"our":[125,230,262],"method":[126],"first":[127,236],"trains":[128],"supervised":[130],"model":[132,197],"simulate":[134],"environment":[138,149,241,256],"dynamics,":[139],"then":[141,177,249],"optimize":[142,250],"offloading":[144,155,210,252],"policy":[145,253],"with":[150,242],"cost-free":[151],"interactions.":[152],"requests":[156],"mostly":[158],"asynchronous,":[159],"adopt":[161],"mean-field":[163],"approach":[164],"that":[165,207,261],"treats":[166],"all":[167],"neighboring":[168],"single":[172],"agent.":[173],"The":[174,258],"problem":[175],"simplified":[179],"reduced":[181],"game":[184],"between":[185],"only":[186],"two":[187],"players.":[188],"Moreover,":[189],"limit":[191],"length":[193],"rollout":[198],"ensure":[200],"simulated":[202],"trajectories":[203],"accurate,":[205],"so":[206],"trained":[209],"policies":[211],"generalized":[214],"unseen":[216],"environments.":[218],"Theoretical":[219],"analyses":[220],"conducted":[222],"validate":[224],"accuracy":[226],"convergence":[228],"algorithm.":[231],"experiments,":[234],"train":[237],"simulation":[240],"historical":[245],"data":[246],"set,":[247],"model.":[257],"results":[259],"show":[260],"algorithm":[263,274],"converge":[265],"very":[266],"fast":[267],"during":[268],"training.":[269],"execution,":[272],"still":[275],"achieves":[276],"high":[277],"performance":[278],"environment.":[282]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}