{"id":"https://openalex.org/W4387917799","doi":"https://doi.org/10.1109/jiot.2023.3327121","title":"Parameterized Deep Reinforcement Learning With Hybrid Action Space for Edge Task Offloading","display_name":"Parameterized Deep Reinforcement Learning With Hybrid Action Space for Edge Task Offloading","publication_year":2023,"publication_date":"2023-10-24","ids":{"openalex":"https://openalex.org/W4387917799","doi":"https://doi.org/10.1109/jiot.2023.3327121"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2023.3327121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2023.3327121","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/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":["Engineering Research Center of Software/Hardware Co-Design Technology and Application, Ministry of Education, and the Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7223-8849","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Software/Hardware Co-Design Technology and Application, Ministry of Education, and the 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":["Engineering Research Center of Software/Hardware Co-Design Technology and Application, Ministry of Education, and the Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Research Center of Software/Hardware Co-Design Technology and Application, Ministry of Education, and the 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/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":["Engineering Research Center of Software/Hardware Co-Design Technology and Application, Ministry of Education, and the Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Research Center of Software/Hardware Co-Design Technology and Application, Ministry of Education, and the 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/A5000322016","display_name":"Yang Wang","orcid":"https://orcid.org/0000-0001-6125-183X"},"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":"Yang Wang","raw_affiliation_strings":["Engineering Research Center of Software/Hardware Co-Design Technology and Application, Ministry of Education, and the Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6125-183X","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Software/Hardware Co-Design Technology and Application, Ministry of Education, and the 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":["Engineering Research Center of Software/Hardware Co-Design Technology and Application, Ministry of Education, and the Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1398-6676","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Software/Hardware Co-Design Technology and Application, Ministry of Education, and the 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":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.5001,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.96271315,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"11","issue":"6","first_page":"10754","last_page":"10767"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9923999905586243,"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":0.9891999959945679,"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/computer-science","display_name":"Computer science","score":0.8713353872299194},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8507015705108643},{"id":"https://openalex.org/keywords/mobile-edge-computing","display_name":"Mobile edge computing","score":0.5901253819465637},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5690174102783203},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5290946960449219},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5181097388267517},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.49615272879600525},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.43414896726608276},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.4145500063896179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29138654470443726},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.22501042485237122},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12641963362693787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8713353872299194},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8507015705108643},{"id":"https://openalex.org/C2776061582","wikidata":"https://www.wikidata.org/wiki/Q25325231","display_name":"Mobile edge computing","level":3,"score":0.5901253819465637},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5690174102783203},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5290946960449219},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5181097388267517},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.49615272879600525},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.43414896726608276},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.4145500063896179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29138654470443726},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.22501042485237122},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12641963362693787},{"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/jiot.2023.3327121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2023.3327121","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":47,"referenced_works":["https://openalex.org/W1696146724","https://openalex.org/W2195423816","https://openalex.org/W2256420211","https://openalex.org/W2472333518","https://openalex.org/W2594560857","https://openalex.org/W2624989916","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2761545465","https://openalex.org/W2761862361","https://openalex.org/W2787402275","https://openalex.org/W2791432311","https://openalex.org/W2801812796","https://openalex.org/W2888896501","https://openalex.org/W2896079731","https://openalex.org/W2897417898","https://openalex.org/W2898155611","https://openalex.org/W2902006351","https://openalex.org/W2902174104","https://openalex.org/W2905026759","https://openalex.org/W2963317446","https://openalex.org/W2963334314","https://openalex.org/W2963616477","https://openalex.org/W2963618158","https://openalex.org/W2965757358","https://openalex.org/W3035007032","https://openalex.org/W3037949089","https://openalex.org/W3041971333","https://openalex.org/W3047516387","https://openalex.org/W3047538493","https://openalex.org/W3107134109","https://openalex.org/W3123257271","https://openalex.org/W3130313450","https://openalex.org/W3133913697","https://openalex.org/W3163488673","https://openalex.org/W3212941463","https://openalex.org/W4213387087","https://openalex.org/W4226018382","https://openalex.org/W4226200846","https://openalex.org/W4255504389","https://openalex.org/W6638018090","https://openalex.org/W6691861496","https://openalex.org/W6692846177","https://openalex.org/W6740222838","https://openalex.org/W6741002519","https://openalex.org/W6755326576","https://openalex.org/W6808915831"],"related_works":["https://openalex.org/W3154796165","https://openalex.org/W4361251304","https://openalex.org/W2902693277","https://openalex.org/W4378977105","https://openalex.org/W3139051647","https://openalex.org/W3024547383","https://openalex.org/W4210813012","https://openalex.org/W3174690704","https://openalex.org/W2968424451","https://openalex.org/W4221092438"],"abstract_inverted_index":{"Multiaccess":[0],"edge":[1,26,61,108],"computing":[2],"(MEC)":[3],"has":[4],"emerged":[5],"as":[6],"a":[7,83,86,126,149,161],"promising":[8],"solution":[9],"that":[10,171],"can":[11],"enable":[12],"low-end":[13],"terminal":[14],"devices":[15],"to":[16,25,34,56,71,160],"run":[17],"large":[18],"complex":[19],"applications":[20],"by":[21,136],"offloading":[22,30,45,104,110,157,176,183],"their":[23],"tasks":[24],"servers.":[27],"The":[28],"task":[29,109,156],"strategy,":[31],"determining":[32],"how":[33],"offload":[35],"tasks,":[36],"remains":[37],"the":[38,60,91,101,107,137,180],"most":[39,76],"critical":[40],"issue":[41],"of":[42,103,163,187],"MEC.":[43],"Traditional":[44],"approaches":[46],"either":[47,82],"suffer":[48],"from":[49],"high":[50,175],"computational":[51],"complexity":[52],"or":[53,85],"poor":[54],"self-adjustability":[55],"dynamic":[57],"changes":[58],"in":[59,96,112,185],"environment.":[62],"Deep":[63],"reinforcement":[64],"learning":[65],"(DRL)":[66],"provides":[67],"an":[68],"effective":[69],"way":[70],"tackle":[72],"these":[73],"issues.":[74],"However,":[75],"existing":[77,181],"DRL-based":[78,151],"methods":[79],"solely":[80],"consider":[81],"continuous":[84,119],"discrete":[87,117],"action":[88,93,141],"space,":[89],"where":[90],"limited":[92],"space":[94],"results":[95,169],"accuracy":[97],"loss":[98],"and":[99,118,178,194],"restricts":[100],"optimality":[102],"decisions.":[105],"Nevertheless,":[106],"problem":[111],"practice":[113],"often":[114],"confronts":[115],"both":[116],"actions.":[120],"In":[121],"this":[122],"article,":[123],"we":[124,146],"propose":[125],"tailored":[127],"proximal":[128],"policy":[129],"optimization":[130],"(PPO)-based":[131],"method,":[132],"named":[133],"Hybrid-PPO,":[134,145],"enhanced":[135],"parameterized":[138],"discrete-continuous":[139],"hybrid":[140],"space.":[142],"Assisted":[143],"with":[144],"further":[147],"design":[148],"novel":[150],"multiserver":[152],"multitask":[153],"collaborative":[154],"partial":[155],"scheme":[158],"adhering":[159],"series":[162],"specifically":[164],"built":[165],"formal":[166],"models.":[167],"Experimental":[168],"prove":[170],"our":[172],"approach":[173],"achieves":[174],"efficiency":[177],"outperforms":[179],"state-of-the-art":[182],"schemes":[184],"terms":[186],"convergence":[188],"rate,":[189],"energy":[190],"cost,":[191,193],"time":[192],"generalizability":[195],"under":[196],"various":[197],"network":[198],"conditions.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}