{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:20:59Z","timestamp":1740169259693,"version":"3.37.3"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3129132","type":"journal-article","created":{"date-parts":[[2021,11,17]],"date-time":"2021-11-17T22:54:45Z","timestamp":1637189685000},"page":"154471-154483","source":"Crossref","is-referenced-by-count":4,"title":["Policy Distillation for Real-Time Inference in Fronthaul Congestion Control"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2112-3723","authenticated-orcid":false,"given":"Jean P.","family":"Martins","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9850-4407","authenticated-orcid":false,"given":"Igor","family":"Almeida","sequence":"additional","affiliation":[]},{"given":"Ricardo","family":"Souza","sequence":"additional","affiliation":[]},{"given":"Silvia","family":"Lins","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1400097.1400105"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.17487\/rfc0793"},{"key":"ref33","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume":"80","author":"fujimoto","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn Res"},{"key":"ref32","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"hasselt","year":"2016","journal-title":"Proc 13th AAAI Conf Artif Intell (AAAI)"},{"key":"ref31","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume":"32","author":"silver","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn (ICML)"},{"key":"ref30","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent (ICLR)"},{"key":"ref37","first-page":"343","article-title":"PCC vivace: Online-learning congestion control","author":"dong","year":"2018","journal-title":"Proc 15th USENIX Conf Netw Syst Design Implement (NSDI)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.17487\/RFC8257"},{"journal-title":"The Addition of Explicit Congestion Notification (ECN) to IP","year":"2001","author":"floyd","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.17487\/rfc2914"},{"key":"ref28","first-page":"1","article-title":"Deep reinforcement learning and the deadly triad","volume":"abs 1812 2648","author":"van hasselt","year":"2018","journal-title":"CoRR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref29","first-page":"1","article-title":"Rainbow: Combining improvements in deep reinforcement learning","volume":"abs 1710 2298","author":"hessel","year":"2017","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/9781118399439"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2556011"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904358"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155250"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405892"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref23","article-title":"Challenges of real-world reinforcement learning","author":"dulac-arnold","year":"2019","journal-title":"Proc ICML Workshop RL RealLife"},{"key":"ref26","volume":"135","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN49398.2020.9209750"},{"key":"ref50","first-page":"1","article-title":"ns3-gym: Extending OpenAI gym for networking research","volume":"abs 1810 3943","author":"gawlowicz","year":"2018","journal-title":"CoRR"},{"key":"ref51","first-page":"561","article-title":"Ray: A distributed framework for emerging AI applications","author":"moritz","year":"2018","journal-title":"Proc 12th USENIX Conf Oper Syst Design Implement (OSDI)"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref58","first-page":"6639","article-title":"CatBoost: Unbiased boosting with categorical features","author":"prokhorenkova","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref57","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3055564"},{"key":"ref55","article-title":"Policy distillation","author":"rusu","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent (ICLR)"},{"key":"ref54","first-page":"1","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"Proc NIPS Deep Learn Represent Learn Workshop"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"ref52","first-page":"3053","article-title":"RLlib: Abstractions for distributed reinforcement learning","volume":"80","author":"liang","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2626324"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2006.188"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2018.2835758"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3229543.3229550"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2892046"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761187"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3342280.3342302"},{"key":"ref17","article-title":"MVFST-RL: An asynchronous RL framework for congestion control with delayed actions","author":"sivakumar","year":"2019","journal-title":"Proc NeurIPS Workshop Mach Learn Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LATINCOM48065.2019.8937857"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933761"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2020.107692"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.9.000172"},{"key":"ref6","first-page":"3050","article-title":"A deep reinforcement learning perspective on internet congestion control","author":"jay","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2019.2948520"},{"key":"ref8","article-title":"When machine learning meets congestion control: A survey and comparison","author":"jiang","year":"2020","journal-title":"arXiv 2010 11397"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900509"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CloudNet.2018.8549505"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.2000603"},{"journal-title":"Telco Distributed DC with Transport Protocol Enhancement for 5G Mobile Networks A Survey","year":"2017","author":"cheng","key":"ref46"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1851182.1851192"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2999572.2999593"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787484"},{"article-title":"BBR congestion control: IETF 99 update","year":"0","author":"cardwell","key":"ref42"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3012426.3022184"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787510"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.10.000573"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09618962.pdf?arnumber=9618962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T20:53:24Z","timestamp":1646686404000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9618962\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3129132","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}