{"id":"https://openalex.org/W7138970547","doi":"https://doi.org/10.1109/globecom59602.2025.11432319","title":"Diffusion-Based Reinforcement Learning for Efficient Task Scheduling in CAV Network","display_name":"Diffusion-Based Reinforcement Learning for Efficient Task Scheduling in CAV Network","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W7138970547","doi":"https://doi.org/10.1109/globecom59602.2025.11432319"},"language":null,"primary_location":{"id":"doi:10.1109/globecom59602.2025.11432319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom59602.2025.11432319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2025 - 2025 IEEE Global Communications Conference","raw_type":"proceedings-article"},"type":"conference-paper","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/A5068110218","display_name":"Xiang Cheng","orcid":"https://orcid.org/0000-0002-5943-0326"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Cheng","raw_affiliation_strings":["Pengcheng Laboratory,Frontier Research Center,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory,Frontier Research Center,Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129830335","display_name":"Zhi Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Mao","raw_affiliation_strings":["Pengcheng Laboratory,Frontier Research Center,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory,Frontier Research Center,Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129942028","display_name":"Ying Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Information and Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Information and Communication Engineering","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130148824","display_name":"Wen Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Wu","raw_affiliation_strings":["Pengcheng Laboratory,Frontier Research Center,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory,Frontier Research Center,Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2529","last_page":"2534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","score":0.2939999997615814,"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":0.2939999997615814,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.1307000070810318,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10761","display_name":"Vehicular Ad Hoc Networks (VANETs)","score":0.12780000269412994,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8015999794006348},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7372000217437744},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6628000140190125},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5784000158309937},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5252000093460083},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.4900999963283539},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4334999918937683},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.43070000410079956}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8015999794006348},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7639999985694885},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7372000217437744},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6628000140190125},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5784000158309937},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5252000093460083},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.4900999963283539},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4334999918937683},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4332999885082245},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.43070000410079956},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.37450000643730164},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.3555000126361847},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3319000005722046},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3082999885082245},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.30799999833106995},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.3025999963283539},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.25920000672340393}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globecom59602.2025.11432319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom59602.2025.11432319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2025 - 2025 IEEE Global Communications Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.40907660126686096,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2124021837","https://openalex.org/W2256420211","https://openalex.org/W2965757358","https://openalex.org/W2975241278","https://openalex.org/W3004718830","https://openalex.org/W3110381504","https://openalex.org/W3163231210","https://openalex.org/W4205946715","https://openalex.org/W4319778953","https://openalex.org/W4362714396","https://openalex.org/W4386025821","https://openalex.org/W4386038516","https://openalex.org/W4386275616","https://openalex.org/W4386275752","https://openalex.org/W4386275760","https://openalex.org/W4391164477","https://openalex.org/W4396680618"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,58,80,103],"investigate":[4],"a":[5,33,60,85,105],"dependency-aware":[6],"task":[7,19,54,69,77,162],"scheduling":[8,45],"problem":[9,63,83],"in":[10,51,117],"connected":[11],"autonomous":[12],"vehicle":[13],"(CAV)":[14],"networks,":[15],"where":[16],"each":[17],"computation":[18],"consists":[20],"of":[21,95],"multiple":[22],"dependent":[23],"subtasks":[24],"and":[25,76,144],"can":[26,159],"be":[27],"distributed":[28],"to":[29,125,168],"nearby":[30],"vehicles":[31],"or":[32],"roadside":[34],"unit":[35],"(RSU)":[36],"for":[37,131],"processing.":[38],"However,":[39],"the":[40,52,67,82,92,127,156],"time-varying":[41],"environment":[42,74],"makes":[43,114],"real-time":[44],"decisions":[46,116],"challenging,":[47],"which":[48,138],"will":[49],"result":[50],"increased":[53],"completion":[55,70,163],"delay.":[56,71],"Therefore,":[57],"formulate":[59],"long-term":[61],"optimization":[62],"aimed":[64],"at":[65],"minimizing":[66],"average":[68],"To":[72,90],"capture":[73],"dynamics":[75],"arrivals":[78],"randomness,":[79],"transform":[81],"into":[84],"parameterized-action":[86],"Markov":[87],"decision":[88,147],"process.":[89],"improve":[91],"exploration":[93],"efficiency":[94],"conventional":[96],"single-step":[97],"deterministic":[98],"policies":[99],"with":[100],"sparse":[101],"reward,":[102],"propose":[104],"novel":[106],"diffusion":[107,121],"policy-based":[108],"reinforcement":[109],"learning":[110],"(RL)":[111],"algorithm":[112,158],"that":[113,155],"continuous":[115,133,146],"real":[118],"time.":[119],"The":[120],"model":[122],"is":[123],"employed":[124],"replace":[126],"original":[128],"policy":[129],"network":[130],"generating":[132],"actions":[134],"through":[135,148],"iterative":[136],"denoising,":[137],"inherently":[139],"captures":[140],"multi-modal":[141],"action":[142],"distributions":[143],"enables":[145],"multi-step":[149],"refinement.":[150],"Extensive":[151],"simulation":[152],"results":[153],"demonstrate":[154],"proposed":[157],"significantly":[160],"reduce":[161],"delay":[164],"by":[165],"11.1%":[166],"compared":[167],"state-of-the-art":[169],"benchmarks.":[170]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-20T00:00:00"}