{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T23:59:25Z","timestamp":1780444765629,"version":"3.54.1"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["#ICE-T:RC 1836921"],"award-info":[{"award-number":["#ICE-T:RC 1836921"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Select. Areas Commun."],"published-print":{"date-parts":[[2021,9]]},"DOI":"10.1109\/jsac.2021.3064657","type":"journal-article","created":{"date-parts":[[2021,3,9]],"date-time":"2021-03-09T21:03:22Z","timestamp":1615323802000},"page":"2878-2889","source":"Crossref","is-referenced-by-count":21,"title":["A Multi-Task-Learning-Based Transfer Deep Reinforcement Learning Design for Autonomic Optical Networks"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7805-6237","authenticated-orcid":false,"given":"Xiaoliang","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6378-7005","authenticated-orcid":false,"given":"Roberto","family":"Proietti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8997-9988","authenticated-orcid":false,"given":"Che-Yu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S. J. Ben","family":"Yoo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2019.2897313"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.10.00D126"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ECOC.2018.8535437"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1364\/OFC.2020.M1B.3"},{"key":"ref31","article-title":"Actor-mimic: Deep multitask and transfer reinforcement learning","author":"parisotto","year":"2015","journal-title":"arXiv 1511 06342"},{"key":"ref30","first-page":"4055","article-title":"Successor features for transfer in reinforcement learning","author":"barreto","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1364\/OFC.2020.Th3D.1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2019.2902454"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1364\/OE.27.019398"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.11.000C48"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.12.000A18"},{"key":"ref29","article-title":"Learning invariant feature spaces to transfer skills with reinforcement learning","author":"gupta","year":"2017","journal-title":"arXiv 1703 02949"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2012.2227683"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2012.6146481"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2019.2923615"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1364\/OE.27.007896"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2019.2894179"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.11.000547"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2019.2924345"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900151"},{"key":"ref25","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":"ref50","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.5.00A100"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1364\/OE.27.035700"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2017.2747223"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2880039"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ECOC.2018.8535155"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2019.2902487"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.9.001202"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737413"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2019.2925312"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2019.2927867"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref19","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2015.7293303"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2013.2294389"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.10.000A43"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1364\/OFC.2018.M3A.5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1701191"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.osn.2014.05.018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.10.000D84"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390225"},{"key":"ref45","article-title":"Multi-task deep reinforcement learning with PopArt","author":"hessel","year":"2018","journal-title":"arXiv 1809 04474"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1364\/OFC.2010.OMU3"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.5.000836"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3229543.3229554"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2018.2795345"},{"key":"ref44","article-title":"Distral: Robust multitask reinforcement learning","author":"teh","year":"2017","journal-title":"arXiv 1707 04175"},{"key":"ref43","article-title":"FreezeOut: Accelerate training by progressively freezing layers","author":"brock","year":"2017","journal-title":"arXiv 1706 04983"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/49\/9516449\/09373585.pdf?arnumber=9373585","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,8]],"date-time":"2021-11-08T22:33:55Z","timestamp":1636410835000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9373585\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9]]},"references-count":51,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/jsac.2021.3064657","relation":{},"ISSN":["0733-8716","1558-0008"],"issn-type":[{"value":"0733-8716","type":"print"},{"value":"1558-0008","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9]]}}}