{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:33:52Z","timestamp":1775745232162,"version":"3.50.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022YFB2901303"],"award-info":[{"award-number":["2022YFB2901303"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62132004"],"award-info":[{"award-number":["62132004"]}],"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":["62221003"],"award-info":[{"award-number":["62221003"]}],"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":["61832013"],"award-info":[{"award-number":["61832013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tpds.2023.3284651","type":"journal-article","created":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T13:22:01Z","timestamp":1686662521000},"page":"2337-2351","source":"Crossref","is-referenced-by-count":30,"title":["Scalable Deep Reinforcement Learning-Based Online Routing for Multi-Type Service Requirements"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2630-4558","authenticated-orcid":false,"given":"Chenyi","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4482-448X","authenticated-orcid":false,"given":"Pingfei","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4847-4585","authenticated-orcid":false,"given":"Mingwei","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3481-8447","authenticated-orcid":false,"given":"Yuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"given":"Nan","family":"Geng","sequence":"additional","affiliation":[{"name":"Huawei Technology, Beijing, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1109\/TMC.2010.28","article-title":"QELAR: A machine-learning-based adaptive routing protocol for energy-efficient and lifetime-extended underwater sensor networks","volume":"9","author":"hu","year":"2010","journal-title":"IEEE Trans Mobile Comput"},{"key":"ref12","first-page":"945","article-title":"Predictive Q-routing: A memory-based reinforcement learning approach to adaptive traffic control","author":"choi","year":"1996","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485853"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.adhoc.2018.08.003"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472902"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-14413-5_2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2656877.2656890"},{"key":"ref55","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"2017","journal-title":"Proc ACM Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486011"},{"key":"ref54","first-page":"14 070","article-title":"Reinforcement learning with convex constraints","author":"miryoosefi","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152441"},{"key":"ref16","first-page":"265","article-title":"Evaluating and boosting reinforcement learningfor intra-domain routing","author":"xu","year":"2019","journal-title":"Proc IEEE Int Conf Mobile Ad-hoc Sensor Syst"},{"key":"ref19","article-title":"How attentive are graph attention networks?","author":"brody","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488736"},{"key":"ref51","article-title":"A deep-reinforcement learning approach for software-defined networking routing optimization","author":"stampa","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2877686"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3025432"},{"key":"ref45","first-page":"671","article-title":"Packet routing in dynamically changing networks: A reinforcement learning approach","author":"boyan","year":"1994","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2960033"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3132491"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2017.2709742"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LCN.2018.8638099"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2016.1600317WC"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3229607.3229610"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2019.04.014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2012.2187305"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3341216.3342213"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2014.2371999"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LCN.1998.727649"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2749760"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2001.916274"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.1999.751451"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1111322.1111341"},{"key":"ref34","year":"2004"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1096536.1096551"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2011.111002"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2017.2731419"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2017.2657643"},{"key":"ref33","article-title":"Pytorch implementations of reinforcement learning algorithms","author":"kostrikov","year":"2018"},{"key":"ref32","year":"2020"},{"key":"ref2","first-page":"11","article-title":"Supporting differentiated service classes: Queue scheduling disciplines","author":"semeria","year":"2001","journal-title":"Juniper Networks"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.17487\/RFC2475"},{"key":"ref39","first-page":"3050","article-title":"A deep reinforcement learning perspective on internet congestion control","author":"jay","year":"2019","journal-title":"Proc ACM Int Conf Mach Learn"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP52444.2021.9651930"},{"key":"ref24","first-page":"5867","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","author":"zhang","year":"2018","journal-title":"Proc ACM Int Conf Mach Learn"},{"key":"ref23","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref26","article-title":"QoS routing for supporting resource reservation","author":"wang","year":"1996","journal-title":"IEEE J Sel Areas Commun"},{"key":"ref25","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015"},{"key":"ref20","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1868447.1868466"},{"key":"ref28","article-title":"Towards safe online reinforcement learning in computer systems","author":"mao","year":"0","journal-title":"Proc NeurIPS Mach Learn Syst Workshop"},{"key":"ref27","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.bjp.2013.11.004"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/10153956\/10149369.pdf?arnumber=10149369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T13:53:38Z","timestamp":1689602018000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10149369\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":55,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2023.3284651","relation":{"is-supplemented-by":[{"id-type":"doi","id":"10.36227\/techrxiv.21587436.v1","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.21587436","asserted-by":"object"}],"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.21587436.v1","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.21587436","asserted-by":"object"}]},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}