{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T02:42:02Z","timestamp":1773369722213,"version":"3.50.1"},"reference-count":36,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers and Electrical Engineering"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1016\/j.compeleceng.2025.110836","type":"journal-article","created":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T17:59:31Z","timestamp":1763575171000},"page":"110836","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Prioritized Experience Replay and Four-Trajectory Exploration - Multi-agents Proximal Policy Optimization: Multi-agents Reinforcement Learning-Based service migration strategy under vehicular edge computing"],"prefix":"10.1016","volume":"129","author":[{"given":"Lei","family":"Ye","sequence":"first","affiliation":[]},{"given":"Yulan","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1517-7701","authenticated-orcid":false,"given":"Qingwen","family":"Han","sequence":"additional","affiliation":[]},{"given":"Lingqiu","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Kaiwen","family":"Ling","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.compeleceng.2025.110836_b1","series-title":"2016 international conference on information society (i-society)","first-page":"17","article-title":"Experimenting with docker: Linux container and base OS attack surfaces","author":"Mohallel","year":"2016"},{"issue":"2","key":"10.1016\/j.compeleceng.2025.110836_b2","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1016\/j.dcan.2021.12.002","article-title":"Adaptnf: Adaptive service chain scheduling with stateless migration and NF consolidation","volume":"9","author":"Li","year":"2023","journal-title":"Digit Commun Netw"},{"issue":"5","key":"10.1016\/j.compeleceng.2025.110836_b3","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1145\/323627.323629","article-title":"Preemptable remote execution facilities for the V-system","volume":"19","author":"Theimer","year":"1985","journal-title":"SIGOPS Oper Syst Rev"},{"key":"10.1016\/j.compeleceng.2025.110836_b4","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1145\/1618525.1618528","article-title":"Post-copy live migration of virtual machines","volume":"43","author":"Hines","year":"2009","journal-title":"Oper Syst Rev"},{"issue":"3","key":"10.1016\/j.compeleceng.2025.110836_b5","doi-asserted-by":"crossref","first-page":"3","DOI":"10.3390\/fi9030037","article-title":"A novel hybrid-copy algorithm for live migration of virtual machine","volume":"9","author":"Lei","year":"2017","journal-title":"Futur Internet"},{"key":"10.1016\/j.compeleceng.2025.110836_b6","series-title":"2013 IEEE global communications conference","first-page":"1291","article-title":"An analytical model for follow me cloud","author":"Taleb","year":"2013"},{"key":"10.1016\/j.compeleceng.2025.110836_b7","series-title":"2014 IEEE international conference on communications","first-page":"1350","article-title":"A Markov decision process-based service migration procedure for follow me cloud","author":"Ksentini","year":"2014"},{"issue":"1","key":"10.1016\/j.compeleceng.2025.110836_b8","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/TMC.2022.3225239","article-title":"Computing and communication cost-aware service migration enabled by transfer reinforcement learning for dynamic vehicular edge computing networks","volume":"23","author":"Peng","year":"2024","journal-title":"IEEE Trans Mob Comput"},{"issue":"4","key":"10.1016\/j.compeleceng.2025.110836_b9","doi-asserted-by":"crossref","first-page":"2786","DOI":"10.1109\/TNSE.2022.3169786","article-title":"Reinforced-LSTM trajectory prediction-driven dynamic service migration: A case study","volume":"9","author":"Zhao","year":"2022","journal-title":"IEEE Trans Netw Sci Eng"},{"issue":"2","key":"10.1016\/j.compeleceng.2025.110836_b10","doi-asserted-by":"crossref","DOI":"10.1002\/cpe.7487","article-title":"A hierarchical decentralized architecture to enable adaptive scalable virtual machine migration","volume":"35","author":"Hummaida","year":"2023","journal-title":"Concurr Comput Pract. Exp"},{"issue":"2","key":"10.1016\/j.compeleceng.2025.110836_b11","doi-asserted-by":"crossref","first-page":"2175","DOI":"10.1109\/TCC.2022.3192560","article-title":"Transfer reinforcement learning for adaptive task offloading over distributed edge clouds","volume":"11","author":"Shuai","year":"2023","journal-title":"IEEE Trans Cloud Comput"},{"key":"10.1016\/j.compeleceng.2025.110836_b12","doi-asserted-by":"crossref","first-page":"3722","DOI":"10.1109\/ACCESS.2018.2888478","article-title":"Pre-migration of vehicle to network services based on priority in mobile edge computing","volume":"7","author":"Yu","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.compeleceng.2025.110836_b13","doi-asserted-by":"crossref","first-page":"84272","DOI":"10.1109\/ACCESS.2020.2992275","article-title":"Interference aware service migration in vehicular fog computing","volume":"8","author":"Ge","year":"2020","journal-title":"IEEE Access"},{"issue":"2","key":"10.1016\/j.compeleceng.2025.110836_b14","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1109\/TCC.2016.2525987","article-title":"Follow-me cloud: When cloud services follow mobile users","volume":"7","author":"Taleb","year":"2019","journal-title":"IEEE Trans Cloud Comput"},{"key":"10.1016\/j.compeleceng.2025.110836_b15","series-title":"2014 IEEE military communications conference","first-page":"835","article-title":"Mobility-induced service migration in mobile micro-clouds","author":"Wang","year":"2014"},{"key":"10.1016\/j.compeleceng.2025.110836_b16","series-title":"2015 IFIP networking conference","first-page":"1","article-title":"Dynamic service migration in mobile edge-clouds","author":"Wang","year":"2015"},{"issue":"3","key":"10.1016\/j.compeleceng.2025.110836_b17","doi-asserted-by":"crossref","first-page":"1272","DOI":"10.1109\/TNET.2019.2916577","article-title":"Dynamic service migration in mobile edge computing based on Markov decision process","volume":"27","author":"Wang","year":"2019","journal-title":"IEEE\/ACM Trans Netw"},{"issue":"2","key":"10.1016\/j.compeleceng.2025.110836_b18","doi-asserted-by":"crossref","first-page":"30:1","DOI":"10.1145\/3239565","article-title":"A dynamic service migration mechanism in edge cognitive computing","volume":"19","author":"Chen","year":"2019","journal-title":"ACM Trans Internet Technol"},{"issue":"11","key":"10.1016\/j.compeleceng.2025.110836_b19","doi-asserted-by":"crossref","first-page":"10190","DOI":"10.1109\/TVT.2018.2867191","article-title":"Mobility-aware edge caching and computing in vehicle networks: A deep reinforcement learning","volume":"67","author":"Tan","year":"2018","journal-title":"IEEE Trans Veh Technol"},{"issue":"1","key":"10.1016\/j.compeleceng.2025.110836_b20","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1109\/TVT.2017.2760281","article-title":"And computing for connected vehicles: A deep reinforcement learning approach","volume":"67","author":"He","year":"2018","journal-title":"IEEE Trans Veh Technol"},{"issue":"1","key":"10.1016\/j.compeleceng.2025.110836_b21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13638-020-01801-6","article-title":"Decentralized computation offloading for multi-user mobile edge computing: A deep reinforcement learning approach","volume":"2020","author":"Chen","year":"2020","journal-title":"EURASIP J Wirel Commun Netw"},{"key":"10.1016\/j.compeleceng.2025.110836_b22","series-title":"Int. FLAIRS conf. proc","article-title":"A closer look at invalid action masking in policy gradient algorithms","volume":"Vol. 35","author":"Huang","year":"2022"},{"key":"10.1016\/j.compeleceng.2025.110836_b23","series-title":"Deep recurrent Q-learning for partially observable MDPs","author":"Hausknecht","year":"2017"},{"key":"10.1016\/j.compeleceng.2025.110836_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.compeleceng.2022.108552","article-title":"Service migration for mobile edge computing based on partially observable Markov decision processes","volume":"106","author":"Chen","year":"2023","journal-title":"Comput Electr Eng"},{"key":"10.1016\/j.compeleceng.2025.110836_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.future.2024.107612","article-title":"Service migration with edge collaboration: Multi-agent deep reinforcement learning approach combined with user preference adaptation","volume":"165","author":"Chen","year":"2025","journal-title":"Future Gener Comput Syst"},{"issue":"1","key":"10.1016\/j.compeleceng.2025.110836_b26","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/JIOT.2023.3296075","article-title":"Multiagent deep reinforcement learning for dynamic avatar migration in aIoT-enabled vehicular metaverses with trajectory prediction","volume":"11","author":"Chen","year":"2024","journal-title":"IEEE Internet Things J"},{"issue":"10","key":"10.1016\/j.compeleceng.2025.110836_b27","doi-asserted-by":"crossref","first-page":"9073","DOI":"10.1109\/TVT.2018.2865211","article-title":"Delay-tolerant data traffic to software-defined vehicular networks with mobile edge computing in smart city","volume":"67","author":"Li","year":"2018","journal-title":"IEEE Trans Veh Technol"},{"issue":"8","key":"10.1016\/j.compeleceng.2025.110836_b28","doi-asserted-by":"crossref","first-page":"9041","DOI":"10.1109\/TVT.2020.2999617","article-title":"A joint service migration and mobility optimization approach for vehicular edge computing","volume":"69","author":"Yuan","year":"2020","journal-title":"IEEE Trans Veh Technol"},{"issue":"6","key":"10.1016\/j.compeleceng.2025.110836_b29","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevE.69.066138","article-title":"Estimating mutual information","volume":"69","author":"Kraskov","year":"2004","journal-title":"Phys Rev E"},{"issue":"1","key":"10.1016\/j.compeleceng.2025.110836_b30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1017\/S0269888912000057","article-title":"Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems","volume":"27","author":"Matignon","year":"2012","journal-title":"Knowl Eng Rev"},{"key":"10.1016\/j.compeleceng.2025.110836_b31","unstructured":"Lowe R, Wu Y, Tamar A, Harb J, Abbeel P, Mordatch I. Multi-agent actor-critic for mixed cooperative-competitive environments. In: Proceedings of the 31st international conference on neural information processing systems. NIPS, Long Beach, CA, USA; 2017, p. 6382\u201393. http:\/\/dx.doi.org\/10.48550\/arXiv.1706.02275."},{"key":"10.1016\/j.compeleceng.2025.110836_b32","series-title":"Counterfactual multi-agent policy gradients","author":"Foerster","year":"2024"},{"issue":"11","key":"10.1016\/j.compeleceng.2025.110836_b33","doi-asserted-by":"crossref","first-page":"17496","DOI":"10.1109\/TVT.2024.3419554","article-title":"Multiple reconfigurable intelligent surfaces aided vehicular edge computing networks: A MAPPO-based approach","volume":"73","author":"Ning","year":"2024","journal-title":"IEEE Trans Veh Technol"},{"key":"10.1016\/j.compeleceng.2025.110836_b34","doi-asserted-by":"crossref","first-page":"1712","DOI":"10.1109\/OJVT.2024.3486197","article-title":"Multi-agent deep reinforcement learning based optimizing joint 3D trajectories and phase shifts in RIS-assisted UAV-enabled wireless communications","volume":"5","author":"Tesfaw","year":"2024","journal-title":"IEEE Open J Veh Technol"},{"key":"10.1016\/j.compeleceng.2025.110836_b35","series-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"10.1016\/j.compeleceng.2025.110836_b36","series-title":"Proc. AAAI Conf. Artif. Intell.","first-page":"1","article-title":"Deep reinforcement learning with double Q-learning","volume":"Vol. 30","author":"van Hasselt","year":"2016"}],"container-title":["Computers and Electrical Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0045790625007797?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0045790625007797?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T15:21:47Z","timestamp":1773328907000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0045790625007797"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":36,"alternative-id":["S0045790625007797"],"URL":"https:\/\/doi.org\/10.1016\/j.compeleceng.2025.110836","relation":{},"ISSN":["0045-7906"],"issn-type":[{"value":"0045-7906","type":"print"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Prioritized Experience Replay and Four-Trajectory Exploration - Multi-agents Proximal Policy Optimization: Multi-agents Reinforcement Learning-Based service migration strategy under vehicular edge computing","name":"articletitle","label":"Article Title"},{"value":"Computers and Electrical Engineering","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compeleceng.2025.110836","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"110836"}}