{"id":"https://openalex.org/W4387872879","doi":"https://doi.org/10.1109/icc45041.2023.10279699","title":"Towards Efficient Task Offloading at the Edge Based on Meta-Reinforcement Learning with Hybrid Action Space","display_name":"Towards Efficient Task Offloading at the Edge Based on Meta-Reinforcement Learning with Hybrid Action Space","publication_year":2023,"publication_date":"2023-05-28","ids":{"openalex":"https://openalex.org/W4387872879","doi":"https://doi.org/10.1109/icc45041.2023.10279699"},"language":"en","primary_location":{"id":"doi:10.1109/icc45041.2023.10279699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc45041.2023.10279699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2023 - IEEE International Conference on Communications","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/A5101491458","display_name":"Yang Zhao","orcid":"https://orcid.org/0000-0001-8320-6992"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Yang","raw_affiliation_strings":["East China Normal University,MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China","MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]},{"raw_affiliation_string":"MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101258784","display_name":"Yuxiang Deng","orcid":"https://orcid.org/0009-0003-8954-6850"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Deng","raw_affiliation_strings":["East China Normal University,MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China","MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]},{"raw_affiliation_string":"MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067164243","display_name":"Ting Wang","orcid":"https://orcid.org/0000-0002-7223-8849"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Wang","raw_affiliation_strings":["East China Normal University,MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China","MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]},{"raw_affiliation_string":"MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101931026","display_name":"Haibin Cai","orcid":"https://orcid.org/0000-0003-1398-6676"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibin Cai","raw_affiliation_strings":["East China Normal University,MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China","MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]},{"raw_affiliation_string":"MoE Engineering Research Center of Software/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3276,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82117533,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4039","last_page":"4044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9995999932289124,"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/T10273","display_name":"IoT and Edge/Fog Computing","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/T13553","display_name":"Age of Information Optimization","score":0.9926999807357788,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9187813997268677},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7998765110969543},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.4911329448223114},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4838058352470398},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4586086869239807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4061531126499176},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34633293747901917},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10377860069274902}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9187813997268677},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7998765110969543},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.4911329448223114},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4838058352470398},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4586086869239807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4061531126499176},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34633293747901917},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10377860069274902},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icc45041.2023.10279699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc45041.2023.10279699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2023 - IEEE International Conference on Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9100000262260437,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G3272011694","display_name":null,"funder_award_id":"2020AAA0107400,2021ZD0114600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7568490260","display_name":null,"funder_award_id":"40500-20103-222131","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2195423816","https://openalex.org/W2736601468","https://openalex.org/W2761545465","https://openalex.org/W2787402275","https://openalex.org/W2791432311","https://openalex.org/W2888896501","https://openalex.org/W2910776806","https://openalex.org/W2938321354","https://openalex.org/W2951527505","https://openalex.org/W2963334314","https://openalex.org/W2963616477","https://openalex.org/W2965757358","https://openalex.org/W3037949089","https://openalex.org/W3047538493","https://openalex.org/W3107134109","https://openalex.org/W3130313450","https://openalex.org/W3172247901","https://openalex.org/W3176011594","https://openalex.org/W4226018382","https://openalex.org/W6682137061","https://openalex.org/W6691861496","https://openalex.org/W6741002519"],"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/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W4294873804","https://openalex.org/W4383109125","https://openalex.org/W2891227010"],"abstract_inverted_index":{"As":[0],"a":[1,96,120,128],"critical":[2],"concern":[3],"of":[4,50,52,58],"multi-access":[5],"edge":[6],"computing":[7],"(MEC),":[8],"task":[9,27,100,161],"offloading":[10,28,33,76,88,101],"has":[11,20],"received":[12],"extensive":[13],"attention.":[14],"Although":[15],"deep":[16],"reinforcement":[17],"learning":[18,107,131],"(DRL)":[19],"achieved":[21],"great":[22],"success":[23],"in":[24,47,70,159],"resolving":[25],"the":[26,48,55,59,71,87,141],"problem,":[29],"most":[30],"existing":[31,60,156],"DRL-based":[32],"schemes":[34,61],"only":[35,152],"consider":[36],"either":[37],"continuous":[38],"action":[39,43,110,137],"space":[40,111,138],"or":[41],"discrete":[42],"space,":[44],"which":[45,84],"results":[46,146],"loss":[49],"optimality":[51],"decisions.":[53],"Moreover,":[54],"generalization":[56],"ability":[57],"is":[62],"still":[63],"far":[64],"from":[65],"adaptive":[66],"to":[67,75,79,139],"dynamic":[68],"changes":[69],"environment.":[72],"This":[73],"leads":[74],"strategies":[77],"having":[78],"conduct":[80],"re-sampling":[81],"and":[82,164],"re-training,":[83],"largely":[85],"impairs":[86],"efficiency.":[89],"To":[90],"address":[91],"these":[92],"issues,":[93],"we":[94,126],"propose":[95],"novel":[97],"efficient":[98],"MEC":[99],"scheme":[102],"based":[103],"on":[104],"parameterized":[105,129],"meta-reinforcement":[106,130],"taking":[108],"hybrid":[109,136],"into":[112],"account.":[113],"We":[114],"first":[115],"formulate":[116],"this":[117],"problem":[118],"as":[119],"non-convex":[121],"multi-objective":[122],"optimization":[123,142],"problem.":[124,143],"Then,":[125],"design":[127],"algorithm,":[132],"named":[133],"Meta-Hybrid-PPO,":[134],"with":[135],"solve":[140],"Comprehensive":[144],"experimental":[145],"show":[147],"that":[148],"our":[149],"Meta-Hybrid-PPO":[150],"not":[151],"performs":[153],"better":[154,171],"than":[155],"state-of-the-art":[157],"methods":[158],"reducing":[160],"processing":[162],"latency":[163],"computational":[165],"energy":[166],"consumption":[167],"but":[168],"also":[169],"achieves":[170],"adaptability.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}