{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T06:40:17Z","timestamp":1774680017044,"version":"3.50.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100006690","name":"SWAN Networks, a spin-off company of Politecnico di Milano","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006690","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Select. Areas Commun."],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1109\/jsac.2020.3041385","type":"journal-article","created":{"date-parts":[[2020,12,3]],"date-time":"2020-12-03T20:37:40Z","timestamp":1607027860000},"page":"2198-2212","source":"Crossref","is-referenced-by-count":86,"title":["On Deep Reinforcement Learning for Traffic Engineering in SD-WAN"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4712-3767","authenticated-orcid":false,"given":"Sebastian","family":"Troia","sequence":"first","affiliation":[]},{"given":"Federico","family":"Sapienza","sequence":"additional","affiliation":[]},{"given":"Leonardo","family":"Vare","sequence":"additional","affiliation":[]},{"given":"Guido","family":"Maier","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3129676.3129731"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1088\/1749-4699\/8\/1\/014008"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref31","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref30","article-title":"An overview of gradient descent optimization algorithms","author":"ruder","year":"2016","journal-title":"arXiv 1609 04747"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1080\/00051144.2020.1774731"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/NAS.2016.7549408"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ANTS.2015.7413664"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CNSM.2013.6727820"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486019"},{"key":"ref40","year":"2020","journal-title":"Gnu scientific library"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2486001.2486012"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2866942"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2017.1700200"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/863955.863957"},{"key":"ref15","article-title":"A deep-reinforcement learning approach for software-defined networking routing optimization","author":"stampa","year":"2017","journal-title":"arXiv 1709 07080"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CompComm.2018.8780950"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1005686.1005697"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1364\/OFC.2019.M2A.6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2020.3022278"},{"key":"ref28","article-title":"Theory and application of reward shaping in reinforcement learning","author":"laud","year":"2004"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CCNC.2015.7158022"},{"key":"ref27","article-title":"Reward shaping in episodic reinforcement learning","author":"grzes","year":"2017","journal-title":"Proc 16th Int Conf Auton Agents Multiagent Syst (AAMAS)"},{"key":"ref3","author":"uppal","year":"2015","journal-title":"Software defined wan for dummies"},{"key":"ref6","year":"2013","journal-title":"Floodlight"},{"key":"ref29","article-title":"Mastering chess and Shogi by self-play with a general reinforcement learning algorithm","author":"silver","year":"2017","journal-title":"arXiv 1712 01815"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CloudNet.2012.6483685"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ColComCon.2019.8809153"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.2986957"},{"key":"ref2","author":"graziani","year":"2014","journal-title":"Connecting Networks Companion Guide"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISITIA49792.2020.9163762"},{"key":"ref1","year":"2019","journal-title":"Five ways sd-wan is transforming cloud connectivity"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICGCIoT.2018.8752969"},{"key":"ref22","author":"sutton","year":"2011","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref21","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","article-title":"Benchmarking batch deep reinforcement learning algorithms","author":"fujimoto","year":"2019","journal-title":"arXiv 1910 01708"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WoWMoM.2014.6918985"},{"key":"ref41","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICTON51198.2020.9203058"},{"key":"ref26","year":"2000","journal-title":"Generic Routing Encapsulation (GRE)-IETF Tools"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref25","year":"2020","journal-title":"Open Vswitch"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/49\/9457209\/09279336.pdf?arnumber=9279336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T20:41:11Z","timestamp":1635280871000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9279336\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7]]},"references-count":43,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/jsac.2020.3041385","relation":{},"ISSN":["0733-8716","1558-0008"],"issn-type":[{"value":"0733-8716","type":"print"},{"value":"1558-0008","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7]]}}}