{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T21:42:11Z","timestamp":1757540531251,"version":"3.37.3"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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 NSF","doi-asserted-by":"crossref","award":["1704662","1704092"],"award-info":[{"award-number":["1704662","1704092"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Networking"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tnet.2020.3037231","type":"journal-article","created":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T22:29:37Z","timestamp":1606861777000},"page":"1-12","source":"Crossref","is-referenced-by-count":15,"title":["An Actor-Critic-Based Transfer Learning Framework for Experience-Driven Networking"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2879-3244","authenticated-orcid":false,"given":"Zhiyuan","family":"Xu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1811-4423","authenticated-orcid":false,"given":"Dejun","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4418-0114","authenticated-orcid":false,"given":"Jian","family":"Tang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6029-3744","authenticated-orcid":false,"given":"Yinan","family":"Tang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8224-9891","authenticated-orcid":false,"given":"Tongtong","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Yanzhi","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5833-8894","authenticated-orcid":false,"given":"Guoliang","family":"Xue","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2017.8254101"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2933417"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2883344"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2959245"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/OJVT.2020.2965100"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2924010"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230551"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref28","first-page":"1","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref27","article-title":"Noisy networks for exploration","author":"fortunato","year":"2017","journal-title":"arXiv 1706 10295"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1900271"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485853"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/90.811451"},{"journal-title":"NSFNet","year":"2019","key":"ref20"},{"key":"ref22","first-page":"1","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"2016","journal-title":"Proc 13th AAAI Conf Artif Intell"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOT.2001.948886"},{"key":"ref24","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"arXiv 1801 01290"},{"key":"ref23","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2015","journal-title":"arXiv 1511 06581"},{"key":"ref26","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","first-page":"2829","article-title":"Continuous deep q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015382"},{"key":"ref51","first-page":"153","article-title":"Multi-task Gaussian process prediction","author":"bonilla","year":"2008","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref52","first-page":"1209","article-title":"Learning Gaussian process kernels via hierarchical Bayes","author":"schwaighofer","year":"2005","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","article-title":"Distilling policy distillation","author":"marian czarnecki","year":"2019","journal-title":"arXiv 1902 02186"},{"key":"ref11","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2018.8377343"},{"key":"ref12","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv 1511 05952"},{"key":"ref13","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv 1503 02531"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"journal-title":"The Mathematics of Internet Congestion Control","year":"2012","author":"srikant","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486020"},{"journal-title":"NS3","year":"2019","key":"ref17"},{"key":"ref18","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc of USENIX Symp on Operating Systems Design and Implementation (OSDI)"},{"journal-title":"ARPANET","year":"2019","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904358"},{"key":"ref3","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761737"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2018.1800097"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"journal-title":"Computer Networks A Systems Approach","year":"2007","author":"peterson","key":"ref7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/1610075.1610094"},{"key":"ref9","article-title":"Policy distillation","author":"rusu","year":"2015","journal-title":"arXiv 1511 06295"},{"key":"ref46","first-page":"264","article-title":"Instance weighting for domain adaptation in nlp","author":"jiang","year":"2007","journal-title":"Proc 45th Annu Meeting Assoc Comput Linguistics"},{"journal-title":"Dataset Shift in Machine Learning","year":"2009","author":"quionero-candela","key":"ref45"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219841"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/1281192.1281218"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904329"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2809722"},{"key":"ref44","first-page":"540","article-title":"Transferring naive Bayes classifiers for text classification","volume":"7","author":"dai","year":"2007","journal-title":"Proc AAAI"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"jialin pan","year":"2010","journal-title":"IEEE Trans Knowl Data Eng"}],"container-title":["IEEE\/ACM Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/90\/4359146\/09274515.pdf?arnumber=9274515","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:49:19Z","timestamp":1649443759000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9274515\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/tnet.2020.3037231","relation":{},"ISSN":["1063-6692","1558-2566"],"issn-type":[{"type":"print","value":"1063-6692"},{"type":"electronic","value":"1558-2566"}],"subject":[],"published":{"date-parts":[[2020]]}}}