{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:41:20Z","timestamp":1781797280561,"version":"3.54.5"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62071067, 62001054, 61771068"],"award-info":[{"award-number":["62071067, 62001054, 61771068"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the National Postdoctoral Program for Innovative Talents","award":["BX20200067"],"award-info":[{"award-number":["BX20200067"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2021M690469"],"award-info":[{"award-number":["2021M690469"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the National Key RD Program of China","award":["2020YFB1807805"],"award-info":[{"award-number":["2020YFB1807805"]}]},{"name":"the Ministry of Education and China Mobile Joint Fund","award":["MCM20200202"],"award-info":[{"award-number":["MCM20200202"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmc.2021.3105963","type":"journal-article","created":{"date-parts":[[2021,8,19]],"date-time":"2021-08-19T20:00:10Z","timestamp":1629403210000},"page":"1-1","source":"Crossref","is-referenced-by-count":18,"title":["RTHop: Real-Time Hop-by-hop Mobile Network Routing by Decentralized Learning with Semantic Attention"],"prefix":"10.1109","author":[{"given":"Bo","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haifeng","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianxi","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1900271"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2018.05.001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1800644"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2019.01.036"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2767608"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2759728"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737525"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2889880"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2812868"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933968"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2017.1600117"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1800603"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2017.08.058"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2014.2349905"},{"key":"ref17","first-page":"3067","article-title":"Real-time reinforcement learning","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Ramstedt"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2018.00079"},{"key":"ref19","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2019.02.050"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2865661"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2661201"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2013.02.003"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2017.1700244"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2827050"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2904188"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS46320.2019.00034"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2016.7841756"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2011.2126593"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2012.2227790"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2012.2230404"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2018.2866093"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/9.182479"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485853"},{"key":"ref35","first-page":"9861","article-title":"Reinforcement learning for solving the vehicle routing problem","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Nazari"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CASE48305.2020.9216877"},{"key":"ref38","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref39","first-page":"5567","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref40","volume-title":"Phase Transitions and Critical Phenomena","author":"Stanley","year":"1971"},{"issue":"4","key":"ref41","first-page":"1039","article-title":"Nash Q-learning for general-sum stochastic games","volume":"4","author":"Hu","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2307\/1969529"},{"key":"ref43","article-title":"Multi-agent reinforcement learning for networked system control","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chu"},{"key":"ref44","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref45","article-title":"At human speed: Deep reinforcement learning with action delay","author":"Firoiu","year":"1810","journal-title":"CoRR"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3343180.3343191"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2020.2985651"},{"key":"ref48","first-page":"5279","article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref49","first-page":"1531","article-title":"A natural policy gradient","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Kakade"},{"key":"ref50","first-page":"573","article-title":"A kronecker-factored approximate fisher matrix for convolution layers","volume-title":"Proc. 33nd Int. Conf. Mach. Learn.","author":"Grosse"},{"key":"ref51","first-page":"2408","article-title":"Optimizing neural networks with kronecker-factored approximate curvature","volume-title":"Proc. 33nd Int. Conf. Mach. Learn.","author":"Martens"},{"key":"ref52","article-title":"Policy optimization with penalized point probability distance: An alternative to proximal policy optimization","author":"Chu","year":"2018"},{"key":"ref53","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref54","article-title":"Openai gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-008-9056-7"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3465055"},{"key":"ref57","article-title":"A structured self-attentive sentence embedding","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Lin"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2011.111002"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2880754"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.5220\/0006105602530262"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2942306"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7755\/4358975\/09519165.pdf?arnumber=9519165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:38:53Z","timestamp":1705016333000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9519165\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/tmc.2021.3105963","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}