{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:47:06Z","timestamp":1784213226212,"version":"3.55.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20519"],"award-info":[{"award-number":["U21A20519"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772072"],"award-info":[{"award-number":["61772072"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Networking"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tnet.2023.3289172","type":"journal-article","created":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T17:27:26Z","timestamp":1689182846000},"page":"566-581","source":"Crossref","is-referenced-by-count":66,"title":["Ensuring Threshold AoI for UAV-Assisted Mobile Crowdsensing by Multi-Agent Deep Reinforcement Learning With Transformer"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0199-0488","authenticated-orcid":false,"given":"Hao","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0252-329X","authenticated-orcid":false,"given":"Chi Harold","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoming","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0181-8379","authenticated-orcid":false,"given":"Guoren","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3860-6257","authenticated-orcid":false,"given":"Kin K.","family":"Leung","sequence":"additional","affiliation":[{"name":"Electrical and Electronic Engineering (EEE) Department, and the Computing Department, Imperial College, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2008.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467070"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.2976927"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2017.2680245"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2014.2378511"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.adhoc.2019.04.001"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2019.2930642"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SAHCN.2011.5984917"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3123606"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2009.05.009"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2021.105643"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref13","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv:1912.06680"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2908171"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2864373"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2938509"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3089120"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3181036"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3125982"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2020.107644"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/s22010223"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904353"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.3027555"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3140796"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.2970744"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS50562.2020.9162913"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796732"},{"key":"ref29","first-page":"4292","article-title":"QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. ICML","author":"Rashid"},{"key":"ref30","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. NIPS","author":"Lowe"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.01955"},{"key":"ref32","article-title":"Is independent learning all you need in the starcraft multi-agent challenge?","author":"de Witt","year":"2020","journal-title":"arXiv:2011.09533"},{"key":"ref33","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref34","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"80","author":"Zhang"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i9.21169"},{"key":"ref36","first-page":"1406","article-title":"IMPALA: scalable distributed deep-RL with importance weighted actor-learner architectures","volume-title":"Proc. ICML","author":"Espeholt"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-218X(01)00351-1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2005.09.012"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2014.10.029"},{"key":"ref40","article-title":"An efficient graph convolutional network technique for the travelling salesman problem","author":"Joshi","year":"2019","journal-title":"arXiv:1906.01227"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-08011-1_14"},{"key":"ref42","first-page":"1","article-title":"Learning to perform local rewriting for combinatorial optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Chen"},{"key":"ref43","article-title":"Learning 2-opt heuristics for the traveling salesman problem via deep reinforcement learning","author":"Costa","year":"2020","journal-title":"arXiv:2004.01608"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2982508"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3041401"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3014788"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3153316"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2955732"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2016.7422404"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2790401"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2902862"},{"key":"ref52","first-page":"7487","article-title":"Stabilizing transformers for reinforcement learning","volume-title":"Proc. ICML","author":"Parisotto"},{"key":"ref53","first-page":"1","article-title":"Exploration by random network distillation","volume-title":"Proc. ICLR","author":"Burda"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref55","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv:1412.3555"},{"key":"ref56","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020462"},{"key":"ref58","volume-title":"CRAWDAD Dataset EPFL\/Mobility","author":"Piorkowski","year":"2009"},{"key":"ref59","volume-title":"DJI Matrice 300 RTK\u2014Built Tough, Works Smart","year":"2020"},{"key":"ref60","first-page":"1","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","volume-title":"Proc. ICLR","author":"Kuba"},{"key":"ref61","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv:1706.05296"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488791"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3023861"},{"key":"ref64","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"Salimans","year":"2017","journal-title":"arXiv:1703.03864"},{"key":"ref65","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. ICLR","author":"Lillicrap"}],"container-title":["IEEE\/ACM Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/90\/10439254\/10181012.pdf?arnumber=10181012","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T14:01:32Z","timestamp":1709301692000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10181012\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":65,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnet.2023.3289172","relation":{},"ISSN":["1063-6692","1558-2566"],"issn-type":[{"value":"1063-6692","type":"print"},{"value":"1558-2566","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}