{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T16:43:56Z","timestamp":1792169036178,"version":"4.4.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772139"],"award-info":[{"award-number":["61772139"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai\u2013Hong Kong Collaborative Project","award":["18510760900"],"award-info":[{"award-number":["18510760900"]}]},{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2020B010166003"],"award-info":[{"award-number":["2020B010166003"]}]},{"name":"China Mobile Chengdu Institute of Research and Development"},{"DOI":"10.13039\/501100011246","name":"Open Project of State Key Laboratory of Novel Software Technology","doi-asserted-by":"publisher","award":["KFKT2019B03"],"award-info":[{"award-number":["KFKT2019B03"]}],"id":[{"id":"10.13039\/501100011246","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1109\/tsmc.2020.3012832","type":"journal-article","created":{"date-parts":[[2020,8,13]],"date-time":"2020-08-13T20:24:24Z","timestamp":1597350264000},"page":"855-868","source":"Crossref","is-referenced-by-count":96,"title":["Toward Packet Routing With Fully Distributed Multiagent Deep Reinforcement Learning"],"prefix":"10.1109","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0603-5936","authenticated-orcid":false,"given":"Xinyu","family":"You","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanjie","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4168-3998","authenticated-orcid":false,"given":"Yuedong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7095-0621","authenticated-orcid":false,"given":"Hui","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9807-2648","authenticated-orcid":false,"given":"Jin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5496-1809","authenticated-orcid":false,"given":"Huaicheng","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"issue":"14","key":"ref2","first-page":"527","article-title":"Network simulations with the ns-3 simulator","volume":"14","author":"Henderson","year":"2008","journal-title":"SIGCOMM Demonstration"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2010.111910.091238"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref5","first-page":"671","article-title":"Packet routing in dynamically changing networks: A reinforcement learning approach","volume-title":"Advances in Neural Information Processing Systems","author":"Boyan","year":"1994"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2018.12.037"},{"key":"ref7","first-page":"945","article-title":"Predictive Q-routing: A memory-based reinforcement learning approach to adaptive traffic control","volume-title":"Advances in Neural Information Processing Systems","author":"Choi","year":"1996"},{"key":"ref8","first-page":"231","article-title":"Dual reinforcement Q-routing: An on-line adaptive routing algorithm","volume-title":"Proc. Artif. Neural Netw. Eng. Conf.","author":"Kumar"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.17487\/rfc3561"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/190314.190336"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9383-6"},{"key":"ref12","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref13","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Duan"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref15","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mech Learn. (ICML)","author":"Silver"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref18","volume-title":"A survey of learning in multiagent environments: Dealing with non-stationarity","author":"Hernandez-Leal","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2853809"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152441"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7997286"},{"key":"ref24","volume-title":"A deep-reinforcement learning approach for software-defined networking routing optimization","author":"Stampa","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.01.001"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2883907"},{"key":"ref28","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","author":"Foerster","year":"2016"},{"key":"ref29","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn. Vol. 70","author":"Foerster"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.28.1.1"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2773634"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2762343"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CROWNCOM.2009.5189189"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1990.204000"},{"key":"ref35","first-page":"29","article-title":"Deep recurrent Q-learning for partially observable MDPs","volume-title":"Proc. AAAI Fall Symp. Series","author":"Hausknecht"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-80"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2011.111002"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1090\/qam\/102435"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/bf01386390"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2613885"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2505687"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2019.2892696"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2920709"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2019.2929224"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021745"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2015.7477459"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.23919\/WiOPT47501.2019.9144110"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221021\/9682189\/09166753.pdf?arnumber=9166753","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T00:15:05Z","timestamp":1704845705000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9166753\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2]]},"references-count":48,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2020.3012832","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2]]}}}