{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T05:35:49Z","timestamp":1777786549309,"version":"3.51.4"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2154191"],"award-info":[{"award-number":["2154191"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2154190"],"award-info":[{"award-number":["2154190"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/ton.2026.3683808","type":"journal-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T19:47:11Z","timestamp":1777405631000},"page":"4779-4793","source":"Crossref","is-referenced-by-count":0,"title":["Relational Deep Reinforcement Learning for Generalizable Routing in Wireless Networks"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2792-6287","authenticated-orcid":false,"given":"Victoria","family":"Manfredi","sequence":"first","affiliation":[{"name":"Wesleyan University, Middletown, CT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alicia P.","family":"Wolfe","sequence":"additional","affiliation":[{"name":"Wesleyan University, Middletown, CT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheonjin","family":"Park","sequence":"additional","affiliation":[{"name":"University of Connecticut, Mansfield, CT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fordham University, Bronx, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sushirdeep","family":"Narayana","sequence":"additional","affiliation":[{"name":"Wesleyan University, Middletown, CT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7027-7916","authenticated-orcid":false,"given":"Dongjin","family":"Song","sequence":"additional","affiliation":[{"name":"University of Connecticut, Mansfield, CT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7632-6512","authenticated-orcid":false,"given":"Bing","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Connecticut, Mansfield, CT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WoWMoM51794.2021.00029"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1990.204000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2030613.2030649"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref5","first-page":"671","article-title":"Packet routing in dynamically changing networks: A reinforcement learning approach","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Boyan"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9383-6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2913776"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2846401"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3160697"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.14174"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2018.12.037"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.3012832"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3070584"},{"key":"ref15","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe"},{"issue":"178","key":"ref16","first-page":"1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1787"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04105-y"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref20","first-page":"1","article-title":"European international academic networking: A 20 year perspective","volume-title":"Proc. One Step Ahead, 20th Trans. Eur. Res. Educ. Netw. Conf.","author":"Kirstein"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1111322.1111341"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1090\/qam\/102435"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-45778-5_5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1561\/9781601982957"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-585-29603-6_5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MCSA.1999.749281"},{"key":"ref28","volume-title":"Optimized Link State Routing Protocol (OLSR)","author":"Clausen","year":"3626"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-012-0723-2"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2014.2298837"},{"key":"ref31","first-page":"1","article-title":"A deep-reinforcement learning approach for software-defined networking routing optimization","author":"Stampa"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152441"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1049\/iet-net.2018.5082"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2020.3036911"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/1330993"},{"key":"ref36","article-title":"Robust and scalable routing with multi-agent deep reinforcement learning for MANETs","author":"Kaviani","year":"2021","journal-title":"arXiv:2101.03273"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref39","first-page":"70","article-title":"Impact evaluation of control signalling onto distributed learning-based packet routing","volume-title":"Proc. Int. Teletraffic Congr. (ITC)","author":"Alliche"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2024.3485196"},{"key":"ref41","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia","year":"2018","journal-title":"arXiv:1806.01261"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3229607.3229610"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3314148.3314357"},{"key":"ref44","article-title":"Deep reinforcement learning meets graph neural networks: Exploring a routing optimization use case","author":"Almasan","year":"2019","journal-title":"arXiv:1910.07421"},{"key":"ref45","volume-title":"Keras","author":"Chollet et al","year":"2015"},{"key":"ref46","volume-title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems","author":"Abadi et al","year":"2015"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/10723154\/11317935\/11481166-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11317935\/11481166.pdf?arnumber=11481166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:47:24Z","timestamp":1777492044000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11481166\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/ton.2026.3683808","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}